Merge nfs containerization work from Trond's tree

The nfs containerization work is a prerequisite for Jeff Layton's reboot
recovery rework.

Documentation/DocBook/device-drivers.tmpl

@@ -102,9 +102,12 @@ X!Iinclude/linux/kobject.h
 !Iinclude/linux/device.h
      </sect1>
      <sect1><title>Device Drivers Base</title>
+!Idrivers/base/init.c
 !Edrivers/base/driver.c
 !Edrivers/base/core.c
+!Edrivers/base/syscore.c
 !Edrivers/base/class.c
+!Idrivers/base/node.c
 !Edrivers/base/firmware_class.c
 !Edrivers/base/transport_class.c
 <!-- Cannot be included, because
@@ -113,13 +116,18 @@ X!Iinclude/linux/kobject.h
      exceed allowed 44 characters maximum
 X!Edrivers/base/attribute_container.c
 -->
-!Edrivers/base/sys.c
+!Edrivers/base/dd.c
 <!--
 X!Edrivers/base/interface.c
 -->
 !Iinclude/linux/platform_device.h
 !Edrivers/base/platform.c
 !Edrivers/base/bus.c
+     </sect1>
+     <sect1><title>Device Drivers DMA Management</title>
+!Edrivers/base/dma-buf.c
+!Edrivers/base/dma-coherent.c
+!Edrivers/base/dma-mapping.c
      </sect1>
      <sect1><title>Device Drivers Power Management</title>
 !Edrivers/base/power/main.c
@@ -219,7 +227,7 @@ X!Isound/sound_firmware.c
   <chapter id="uart16x50">
      <title>16x50 UART Driver</title>
 !Edrivers/tty/serial/serial_core.c
-!Edrivers/tty/serial/8250.c
+!Edrivers/tty/serial/8250/8250.c
   </chapter>
 
   <chapter id="fbdev">

Documentation/filesystems/nfs/idmapper.txt

@@ -4,13 +4,21 @@ ID Mapper
 =========
 Id mapper is used by NFS to translate user and group ids into names, and to
 translate user and group names into ids.  Part of this translation involves
-performing an upcall to userspace to request the information.  Id mapper will
-user request-key to perform this upcall and cache the result.  The program
-/usr/sbin/nfs.idmap should be called by request-key, and will perform the
-translation and initialize a key with the resulting information.
+performing an upcall to userspace to request the information.  There are two
+ways NFS could obtain this information: placing a call to /sbin/request-key
+or by placing a call to the rpc.idmap daemon.
+
+NFS will attempt to call /sbin/request-key first.  If this succeeds, the
+result will be cached using the generic request-key cache.  This call should
+only fail if /etc/request-key.conf is not configured for the id_resolver key
+type, see the "Configuring" section below if you wish to use the request-key
+method.
+
+If the call to /sbin/request-key fails (if /etc/request-key.conf is not
+configured with the id_resolver key type), then the idmapper will ask the
+legacy rpc.idmap daemon for the id mapping.  This result will be stored
+in a custom NFS idmap cache.
 
- NFS_USE_NEW_IDMAPPER must be selected when configuring the kernel to use this
- feature.
 
 ===========
 Configuring

Documentation/filesystems/nfs/pnfs.txt

@@ -53,3 +53,57 @@ lseg maintains an extra reference corresponding to the NFS_LSEG_VALID
 bit which holds it in the pnfs_layout_hdr's list.  When the final lseg
 is removed from the pnfs_layout_hdr's list, the NFS_LAYOUT_DESTROYED
 bit is set, preventing any new lsegs from being added.
+
+layout drivers
+--------------
+
+PNFS utilizes what is called layout drivers. The STD defines 3 basic
+layout types: "files" "objects" and "blocks". For each of these types
+there is a layout-driver with a common function-vectors table which
+are called by the nfs-client pnfs-core to implement the different layout
+types.
+
+Files-layout-driver code is in: fs/nfs/nfs4filelayout.c && nfs4filelayoutdev.c
+Objects-layout-deriver code is in: fs/nfs/objlayout/.. directory
+Blocks-layout-deriver code is in: fs/nfs/blocklayout/.. directory
+
+objects-layout setup
+--------------------
+
+As part of the full STD implementation the objlayoutdriver.ko needs, at times,
+to automatically login to yet undiscovered iscsi/osd devices. For this the
+driver makes up-calles to a user-mode script called *osd_login*
+
+The path_name of the script to use is by default:
+	/sbin/osd_login.
+This name can be overridden by the Kernel module parameter:
+	objlayoutdriver.osd_login_prog
+
+If Kernel does not find the osd_login_prog path it will zero it out
+and will not attempt farther logins. An admin can then write new value
+to the objlayoutdriver.osd_login_prog Kernel parameter to re-enable it.
+
+The /sbin/osd_login is part of the nfs-utils package, and should usually
+be installed on distributions that support this Kernel version.
+
+The API to the login script is as follows:
+	Usage: $0 -u <URI> -o <OSDNAME> -s <SYSTEMID>
+	Options:
+		-u		target uri e.g. iscsi://<ip>:<port>
+				(allways exists)
+				(More protocols can be defined in the future.
+				 The client does not interpret this string it is
+				 passed unchanged as recieved from the Server)
+		-o		osdname of the requested target OSD
+				(Might be empty)
+				(A string which denotes the OSD name, there is a
+				 limit of 64 chars on this string)
+		-s 		systemid of the requested target OSD
+				(Might be empty)
+				(This string, if not empty is always an hex
+				 representation of the 20 bytes osd_system_id)
+
+blocks-layout setup
+-------------------
+
+TODO: Document the setup needs of the blocks layout driver

Documentation/kernel-parameters.txt

@@ -1657,6 +1657,14 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			of returning the full 64-bit number.
 			The default is to return 64-bit inode numbers.
 
+	nfs.max_session_slots=
+			[NFSv4.1] Sets the maximum number of session slots
+			the client will attempt to negotiate with the server.
+			This limits the number of simultaneous RPC requests
+			that the client can send to the NFSv4.1 server.
+			Note that there is little point in setting this
+			value higher than the max_tcp_slot_table_limit.
+
 	nfs.nfs4_disable_idmapping=
 			[NFSv4] When set to the default of '1', this option
 			ensures that both the RPC level authentication
@@ -1670,6 +1678,21 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			back to using the idmapper.
 			To turn off this behaviour, set the value to '0'.
 
+	nfs.send_implementation_id =
+			[NFSv4.1] Send client implementation identification
+			information in exchange_id requests.
+			If zero, no implementation identification information
+			will be sent.
+			The default is to send the implementation identification
+			information.
+
+
+	objlayoutdriver.osd_login_prog=
+			[NFS] [OBJLAYOUT] sets the pathname to the program which
+			is used to automatically discover and login into new
+			osd-targets. Please see:
+			Documentation/filesystems/pnfs.txt for more explanations
+
 	nmi_debug=	[KNL,AVR32,SH] Specify one or more actions to take
 			when a NMI is triggered.
 			Format: [state][,regs][,debounce][,die]

MAINTAINERS

@@ -159,7 +159,7 @@ S:	Maintained
 F:	drivers/net/ethernet/realtek/r8169.c
 
 8250/16?50 (AND CLONE UARTS) SERIAL DRIVER
-M:	Greg Kroah-Hartman <gregkh@suse.de>
+M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 L:	linux-serial@vger.kernel.org
 W:	http://serial.sourceforge.net
 S:	Maintained
@@ -1783,9 +1783,9 @@ X:	net/wireless/wext*
 
 CHAR and MISC DRIVERS
 M:	Arnd Bergmann <arnd@arndb.de>
-M:	Greg Kroah-Hartman <greg@kroah.com>
+M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git
-S:	Maintained
+S:	Supported
 F:	drivers/char/*
 F:	drivers/misc/*
 
@@ -2320,7 +2320,7 @@ F:	lib/lru_cache.c
 F:	Documentation/blockdev/drbd/
 
 DRIVER CORE, KOBJECTS, DEBUGFS AND SYSFS
-M:	Greg Kroah-Hartman <gregkh@suse.de>
+M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core-2.6.git
 S:	Supported
 F:	Documentation/kobject.txt
@@ -6276,15 +6276,15 @@ S:	Maintained
 F:	arch/alpha/kernel/srm_env.c
 
 STABLE BRANCH
-M:	Greg Kroah-Hartman <greg@kroah.com>
+M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 L:	stable@vger.kernel.org
-S:	Maintained
+S:	Supported
 
 STAGING SUBSYSTEM
-M:	Greg Kroah-Hartman <gregkh@suse.de>
+M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging.git
 L:	devel@driverdev.osuosl.org
-S:	Maintained
+S:	Supported
 F:	drivers/staging/
 
 STAGING - AGERE HERMES II and II.5 WIRELESS DRIVERS
@@ -6669,8 +6669,8 @@ S:	Maintained
 K:	^Subject:.*(?i)trivial
 
 TTY LAYER
-M:	Greg Kroah-Hartman <gregkh@suse.de>
-S:	Maintained
+M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty-2.6.git
 F:	drivers/tty/
 F:	drivers/tty/serial/serial_core.c
@@ -6958,7 +6958,7 @@ S:	Maintained
 F:	drivers/usb/serial/digi_acceleport.c
 
 USB SERIAL DRIVER
-M:	Greg Kroah-Hartman <gregkh@suse.de>
+M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 L:	linux-usb@vger.kernel.org
 S:	Supported
 F:	Documentation/usb/usb-serial.txt
@@ -6973,9 +6973,8 @@ S:	Maintained
 F:	drivers/usb/serial/empeg.c
 
 USB SERIAL KEYSPAN DRIVER
-M:	Greg Kroah-Hartman <greg@kroah.com>
+M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 L:	linux-usb@vger.kernel.org
-W:	http://www.kroah.com/linux/
 S:	Maintained
 F:	drivers/usb/serial/*keyspan*
 
@@ -7003,7 +7002,7 @@ F:	Documentation/video4linux/sn9c102.txt
 F:	drivers/media/video/sn9c102/
 
 USB SUBSYSTEM
-M:	Greg Kroah-Hartman <gregkh@suse.de>
+M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 L:	linux-usb@vger.kernel.org
 W:	http://www.linux-usb.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb-2.6.git
@@ -7090,7 +7089,7 @@ F:	fs/hppfs/
 
 USERSPACE I/O (UIO)
 M:	"Hans J. Koch" <hjk@hansjkoch.de>
-M:	Greg Kroah-Hartman <gregkh@suse.de>
+M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 S:	Maintained
 F:	Documentation/DocBook/uio-howto.tmpl
 F:	drivers/uio/

arch/microblaze/kernel/setup.c

@@ -26,7 +26,6 @@
 #include <linux/cache.h>
 #include <linux/of_platform.h>
 #include <linux/dma-mapping.h>
-#include <linux/cpu.h>
 #include <asm/cacheflush.h>
 #include <asm/entry.h>
 #include <asm/cpuinfo.h>
@@ -227,23 +226,5 @@ static int __init setup_bus_notifier(void)
 
 	return 0;
 }
-arch_initcall(setup_bus_notifier);
-
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
-
-static int __init topology_init(void)
-{
-	int i, ret;
-
-	for_each_present_cpu(i) {
-		struct cpu *c = &per_cpu(cpu_devices, i);
 
-		ret = register_cpu(c, i);
-		if (ret)
-			printk(KERN_WARNING "topology_init: register_cpu %d "
-						"failed (%d)\n", i, ret);
-	}
-
-	return 0;
-}
-subsys_initcall(topology_init);
+arch_initcall(setup_bus_notifier);

arch/sparc/Kconfig

@@ -33,6 +33,7 @@ config SPARC
 config SPARC32
 	def_bool !64BIT
 	select GENERIC_ATOMIC64
+	select CLZ_TAB
 
 config SPARC64
 	def_bool 64BIT

arch/sparc/lib/divdi3.S

@@ -17,23 +17,9 @@ along with GNU CC; see the file COPYING.  If not, write to
 the Free Software Foundation, 59 Temple Place - Suite 330,
 Boston, MA 02111-1307, USA.  */
 
-	.data
-	.align 8
-	.globl	__clz_tab
-__clz_tab:
-	.byte	0,1,2,2,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5
-	.byte	6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6
-	.byte	7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7
-	.byte	7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7
-	.byte	8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8
-	.byte	8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8
-	.byte	8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8
-	.byte	8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8
-	.size	 __clz_tab,256
-	.global .udiv
-
 	.text
 	.align 4
+	.global .udiv
 	.globl __divdi3
 __divdi3:
 	save %sp,-104,%sp

arch/x86/include/asm/cmpxchg.h

@@ -145,13 +145,13 @@ extern void __add_wrong_size(void)
 
 #ifdef __HAVE_ARCH_CMPXCHG
 #define cmpxchg(ptr, old, new)						\
-	__cmpxchg((ptr), (old), (new), sizeof(*ptr))
+	__cmpxchg(ptr, old, new, sizeof(*(ptr)))
 
 #define sync_cmpxchg(ptr, old, new)					\
-	__sync_cmpxchg((ptr), (old), (new), sizeof(*ptr))
+	__sync_cmpxchg(ptr, old, new, sizeof(*(ptr)))
 
 #define cmpxchg_local(ptr, old, new)					\
-	__cmpxchg_local((ptr), (old), (new), sizeof(*ptr))
+	__cmpxchg_local(ptr, old, new, sizeof(*(ptr)))
 #endif
 
 /*

arch/x86/kernel/dumpstack.c

@@ -252,7 +252,8 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err)
 	unsigned short ss;
 	unsigned long sp;
 #endif
-	printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
+	printk(KERN_DEFAULT
+	       "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
 #ifdef CONFIG_PREEMPT
 	printk("PREEMPT ");
 #endif

arch/x86/kernel/dumpstack_64.c

@@ -129,7 +129,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	if (!stack) {
 		if (regs)
 			stack = (unsigned long *)regs->sp;
-		else if (task && task != current)
+		else if (task != current)
 			stack = (unsigned long *)task->thread.sp;
 		else
 			stack = &dummy;
@@ -269,11 +269,11 @@ void show_registers(struct pt_regs *regs)
 		unsigned char c;
 		u8 *ip;
 
-		printk(KERN_EMERG "Stack:\n");
+		printk(KERN_DEFAULT "Stack:\n");
 		show_stack_log_lvl(NULL, regs, (unsigned long *)sp,
-				   0, KERN_EMERG);
+				   0, KERN_DEFAULT);
 
-		printk(KERN_EMERG "Code: ");
+		printk(KERN_DEFAULT "Code: ");
 
 		ip = (u8 *)regs->ip - code_prologue;
 		if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) {

arch/x86/kernel/reboot.c

@@ -39,6 +39,14 @@ static int reboot_mode;
 enum reboot_type reboot_type = BOOT_ACPI;
 int reboot_force;
 
+/* This variable is used privately to keep track of whether or not
+ * reboot_type is still set to its default value (i.e., reboot= hasn't
+ * been set on the command line).  This is needed so that we can
+ * suppress DMI scanning for reboot quirks.  Without it, it's
+ * impossible to override a faulty reboot quirk without recompiling.
+ */
+static int reboot_default = 1;
+
 #if defined(CONFIG_X86_32) && defined(CONFIG_SMP)
 static int reboot_cpu = -1;
 #endif
@@ -67,6 +75,12 @@ bool port_cf9_safe = false;
 static int __init reboot_setup(char *str)
 {
 	for (;;) {
+		/* Having anything passed on the command line via
+		 * reboot= will cause us to disable DMI checking
+		 * below.
+		 */
+		reboot_default = 0;
+
 		switch (*str) {
 		case 'w':
 			reboot_mode = 0x1234;
@@ -295,14 +309,6 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "P4S800"),
 		},
 	},
-	{	/* Handle problems with rebooting on VersaLogic Menlow boards */
-		.callback = set_bios_reboot,
-		.ident = "VersaLogic Menlow based board",
-		.matches = {
-			DMI_MATCH(DMI_BOARD_VENDOR, "VersaLogic Corporation"),
-			DMI_MATCH(DMI_BOARD_NAME, "VersaLogic Menlow board"),
-		},
-	},
 	{ /* Handle reboot issue on Acer Aspire one */
 		.callback = set_kbd_reboot,
 		.ident = "Acer Aspire One A110",
@@ -316,7 +322,12 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 
 static int __init reboot_init(void)
 {
-	dmi_check_system(reboot_dmi_table);
+	/* Only do the DMI check if reboot_type hasn't been overridden
+	 * on the command line
+	 */
+	if (reboot_default) {
+		dmi_check_system(reboot_dmi_table);
+	}
 	return 0;
 }
 core_initcall(reboot_init);
@@ -465,7 +476,12 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = {
 
 static int __init pci_reboot_init(void)
 {
-	dmi_check_system(pci_reboot_dmi_table);
+	/* Only do the DMI check if reboot_type hasn't been overridden
+	 * on the command line
+	 */
+	if (reboot_default) {
+		dmi_check_system(pci_reboot_dmi_table);
+	}
 	return 0;
 }
 core_initcall(pci_reboot_init);

arch/x86/mm/fault.c

@@ -673,7 +673,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 
 	stackend = end_of_stack(tsk);
 	if (tsk != &init_task && *stackend != STACK_END_MAGIC)
-		printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
+		printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
 
 	tsk->thread.cr2		= address;
 	tsk->thread.trap_no	= 14;
@@ -684,7 +684,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 		sig = 0;
 
 	/* Executive summary in case the body of the oops scrolled away */
-	printk(KERN_EMERG "CR2: %016lx\n", address);
+	printk(KERN_DEFAULT "CR2: %016lx\n", address);
 
 	oops_end(flags, regs, sig);
 }

drivers/block/rbd.c

@@ -380,6 +380,7 @@ static int rbd_get_client(struct rbd_device *rbd_dev, const char *mon_addr,
 	rbdc = __rbd_client_find(opt);
 	if (rbdc) {
 		ceph_destroy_options(opt);
+		kfree(rbd_opts);
 
 		/* using an existing client */
 		kref_get(&rbdc->kref);
@@ -406,15 +407,15 @@ done_err:
 
 /*
  * Destroy ceph client
+ *
+ * Caller must hold node_lock.
  */
 static void rbd_client_release(struct kref *kref)
 {
 	struct rbd_client *rbdc = container_of(kref, struct rbd_client, kref);
 
 	dout("rbd_release_client %p\n", rbdc);
-	spin_lock(&node_lock);
 	list_del(&rbdc->node);
-	spin_unlock(&node_lock);
 
 	ceph_destroy_client(rbdc->client);
 	kfree(rbdc->rbd_opts);
@@ -427,7 +428,9 @@ static void rbd_client_release(struct kref *kref)
  */
 static void rbd_put_client(struct rbd_device *rbd_dev)
 {
+	spin_lock(&node_lock);
 	kref_put(&rbd_dev->rbd_client->kref, rbd_client_release);
+	spin_unlock(&node_lock);
 	rbd_dev->rbd_client = NULL;
 	rbd_dev->client = NULL;
 }

drivers/firewire/ohci.c

@@ -263,6 +263,7 @@ static inline struct fw_ohci *fw_ohci(struct fw_card *card)
 static char ohci_driver_name[] = KBUILD_MODNAME;
 
 #define PCI_DEVICE_ID_AGERE_FW643	0x5901
+#define PCI_DEVICE_ID_CREATIVE_SB1394	0x4001
 #define PCI_DEVICE_ID_JMICRON_JMB38X_FW	0x2380
 #define PCI_DEVICE_ID_TI_TSB12LV22	0x8009
 #define PCI_DEVICE_ID_TI_TSB12LV26	0x8020
@@ -289,6 +290,9 @@ static const struct {
 	{PCI_VENDOR_ID_ATT, PCI_DEVICE_ID_AGERE_FW643, 6,
 		QUIRK_NO_MSI},
 
+	{PCI_VENDOR_ID_CREATIVE, PCI_DEVICE_ID_CREATIVE_SB1394, PCI_ANY_ID,
+		QUIRK_RESET_PACKET},
+
 	{PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB38X_FW, PCI_ANY_ID,
 		QUIRK_NO_MSI},
 
@@ -299,7 +303,7 @@ static const struct {
 		QUIRK_NO_MSI},
 
 	{PCI_VENDOR_ID_RICOH, PCI_ANY_ID, PCI_ANY_ID,
-		QUIRK_CYCLE_TIMER},
+		QUIRK_CYCLE_TIMER | QUIRK_NO_MSI},
 
 	{PCI_VENDOR_ID_TI, PCI_DEVICE_ID_TI_TSB12LV22, PCI_ANY_ID,
 		QUIRK_CYCLE_TIMER | QUIRK_RESET_PACKET | QUIRK_NO_1394A},

drivers/gpu/drm/nouveau/nouveau_bios.h

@@ -54,9 +54,10 @@ struct bit_entry {
 int bit_table(struct drm_device *, u8 id, struct bit_entry *);
 
 enum dcb_gpio_tag {
-	DCB_GPIO_TVDAC0 = 0xc,
+	DCB_GPIO_PANEL_POWER = 0x01,
+	DCB_GPIO_TVDAC0 = 0x0c,
 	DCB_GPIO_TVDAC1 = 0x2d,
-	DCB_GPIO_PWM_FAN = 0x9,
+	DCB_GPIO_PWM_FAN = 0x09,
 	DCB_GPIO_FAN_SENSE = 0x3d,
 	DCB_GPIO_UNUSED = 0xff
 };

drivers/gpu/drm/nouveau/nouveau_display.c

@@ -219,6 +219,16 @@ nouveau_display_init(struct drm_device *dev)
 	if (ret)
 		return ret;
 
+	/* power on internal panel if it's not already.  the init tables of
+	 * some vbios default this to off for some reason, causing the
+	 * panel to not work after resume
+	 */
+	if (nouveau_gpio_func_get(dev, DCB_GPIO_PANEL_POWER) == 0) {
+		nouveau_gpio_func_set(dev, DCB_GPIO_PANEL_POWER, true);
+		msleep(300);
+	}
+
+	/* enable polling for external displays */
 	drm_kms_helper_poll_enable(dev);
 
 	/* enable hotplug interrupts */

drivers/gpu/drm/nouveau/nouveau_drv.c

@@ -124,7 +124,7 @@ MODULE_PARM_DESC(ctxfw, "Use external HUB/GPC ucode (fermi)\n");
 int nouveau_ctxfw;
 module_param_named(ctxfw, nouveau_ctxfw, int, 0400);
 
-MODULE_PARM_DESC(ctxfw, "Santise DCB table according to MXM-SIS\n");
+MODULE_PARM_DESC(mxmdcb, "Santise DCB table according to MXM-SIS\n");
 int nouveau_mxmdcb = 1;
 module_param_named(mxmdcb, nouveau_mxmdcb, int, 0400);
 

drivers/gpu/drm/nouveau/nouveau_gem.c

@@ -379,6 +379,25 @@ retry:
 	return 0;
 }
 
+static int
+validate_sync(struct nouveau_channel *chan, struct nouveau_bo *nvbo)
+{
+	struct nouveau_fence *fence = NULL;
+	int ret = 0;
+
+	spin_lock(&nvbo->bo.bdev->fence_lock);
+	if (nvbo->bo.sync_obj)
+		fence = nouveau_fence_ref(nvbo->bo.sync_obj);
+	spin_unlock(&nvbo->bo.bdev->fence_lock);
+
+	if (fence) {
+		ret = nouveau_fence_sync(fence, chan);
+		nouveau_fence_unref(&fence);
+	}
+
+	return ret;
+}
+
 static int
 validate_list(struct nouveau_channel *chan, struct list_head *list,
 	      struct drm_nouveau_gem_pushbuf_bo *pbbo, uint64_t user_pbbo_ptr)
@@ -393,7 +412,7 @@ validate_list(struct nouveau_channel *chan, struct list_head *list,
 	list_for_each_entry(nvbo, list, entry) {
 		struct drm_nouveau_gem_pushbuf_bo *b = &pbbo[nvbo->pbbo_index];
 
-		ret = nouveau_fence_sync(nvbo->bo.sync_obj, chan);
+		ret = validate_sync(chan, nvbo);
 		if (unlikely(ret)) {
 			NV_ERROR(dev, "fail pre-validate sync\n");
 			return ret;
@@ -416,7 +435,7 @@ validate_list(struct nouveau_channel *chan, struct list_head *list,
 			return ret;
 		}
 
-		ret = nouveau_fence_sync(nvbo->bo.sync_obj, chan);
+		ret = validate_sync(chan, nvbo);
 		if (unlikely(ret)) {
 			NV_ERROR(dev, "fail post-validate sync\n");
 			return ret;

drivers/gpu/drm/nouveau/nouveau_mxm.c

@@ -656,7 +656,16 @@ nouveau_mxm_init(struct drm_device *dev)
 
 	if (mxm_shadow(dev, mxm[0])) {
 		MXM_MSG(dev, "failed to locate valid SIS\n");
+#if 0
+		/* we should, perhaps, fall back to some kind of limited
+		 * mode here if the x86 vbios hasn't already done the
+		 * work for us (so we prevent loading with completely
+		 * whacked vbios tables).
+		 */
 		return -EINVAL;
+#else
+		return 0;
+#endif
 	}
 
 	MXM_MSG(dev, "MXMS Version %d.%d\n",

drivers/gpu/drm/nouveau/nv50_pm.c

@@ -495,9 +495,9 @@ nv50_pm_clocks_pre(struct drm_device *dev, struct nouveau_pm_level *perflvl)
 	struct drm_nouveau_private *dev_priv = dev->dev_private;
 	struct nv50_pm_state *info;
 	struct pll_lims pll;
-	int ret = -EINVAL;
+	int clk, ret = -EINVAL;
 	int N, M, P1, P2;
-	u32 clk, out;
+	u32 out;
 
 	if (dev_priv->chipset == 0xaa ||
 	    dev_priv->chipset == 0xac)

drivers/gpu/drm/radeon/atombios_crtc.c

@@ -1184,7 +1184,7 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 	WREG32(EVERGREEN_GRPH_ENABLE + radeon_crtc->crtc_offset, 1);
 
 	WREG32(EVERGREEN_DESKTOP_HEIGHT + radeon_crtc->crtc_offset,
-	       crtc->mode.vdisplay);
+	       target_fb->height);
 	x &= ~3;
 	y &= ~1;
 	WREG32(EVERGREEN_VIEWPORT_START + radeon_crtc->crtc_offset,
@@ -1353,7 +1353,7 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc,
 	WREG32(AVIVO_D1GRPH_ENABLE + radeon_crtc->crtc_offset, 1);
 
 	WREG32(AVIVO_D1MODE_DESKTOP_HEIGHT + radeon_crtc->crtc_offset,
-	       crtc->mode.vdisplay);
+	       target_fb->height);
 	x &= ~3;
 	y &= ~1;
 	WREG32(AVIVO_D1MODE_VIEWPORT_START + radeon_crtc->crtc_offset,

drivers/gpu/drm/radeon/atombios_dp.c

@@ -564,9 +564,21 @@ int radeon_dp_get_panel_mode(struct drm_encoder *encoder,
 	    ENCODER_OBJECT_ID_NUTMEG)
 		panel_mode = DP_PANEL_MODE_INTERNAL_DP1_MODE;
 	else if (radeon_connector_encoder_get_dp_bridge_encoder_id(connector) ==
-		 ENCODER_OBJECT_ID_TRAVIS)
-		panel_mode = DP_PANEL_MODE_INTERNAL_DP2_MODE;
-	else if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
+		 ENCODER_OBJECT_ID_TRAVIS) {
+		u8 id[6];
+		int i;
+		for (i = 0; i < 6; i++)
+			id[i] = radeon_read_dpcd_reg(radeon_connector, 0x503 + i);
+		if (id[0] == 0x73 &&
+		    id[1] == 0x69 &&
+		    id[2] == 0x76 &&
+		    id[3] == 0x61 &&
+		    id[4] == 0x72 &&
+		    id[5] == 0x54)
+			panel_mode = DP_PANEL_MODE_INTERNAL_DP1_MODE;
+		else
+			panel_mode = DP_PANEL_MODE_INTERNAL_DP2_MODE;
+	} else if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
 		u8 tmp = radeon_read_dpcd_reg(radeon_connector, DP_EDP_CONFIGURATION_CAP);
 		if (tmp & 1)
 			panel_mode = DP_PANEL_MODE_INTERNAL_DP2_MODE;

drivers/gpu/drm/radeon/r600_blit_kms.c

@@ -468,27 +468,42 @@ set_default_state(struct radeon_device *rdev)
 	radeon_ring_write(ring, sq_stack_resource_mgmt_2);
 }
 
+#define I2F_MAX_BITS 15
+#define I2F_MAX_INPUT  ((1 << I2F_MAX_BITS) - 1)
+#define I2F_SHIFT (24 - I2F_MAX_BITS)
+
+/*
+ * Converts unsigned integer into 32-bit IEEE floating point representation.
+ * Conversion is not universal and only works for the range from 0
+ * to 2^I2F_MAX_BITS-1. Currently we only use it with inputs between
+ * 0 and 16384 (inclusive), so I2F_MAX_BITS=15 is enough. If necessary,
+ * I2F_MAX_BITS can be increased, but that will add to the loop iterations
+ * and slow us down. Conversion is done by shifting the input and counting
+ * down until the first 1 reaches bit position 23. The resulting counter
+ * and the shifted input are, respectively, the exponent and the fraction.
+ * The sign is always zero.
+ */
 static uint32_t i2f(uint32_t input)
 {
 	u32 result, i, exponent, fraction;
 
-	if ((input & 0x3fff) == 0)
-		result = 0; /* 0 is a special case */
+	WARN_ON_ONCE(input > I2F_MAX_INPUT);
+
+	if ((input & I2F_MAX_INPUT) == 0)
+		result = 0;
 	else {
-		exponent = 140; /* exponent biased by 127; */
-		fraction = (input & 0x3fff) << 10; /* cheat and only
-						      handle numbers below 2^^15 */
-		for (i = 0; i < 14; i++) {
+		exponent = 126 + I2F_MAX_BITS;
+		fraction = (input & I2F_MAX_INPUT) << I2F_SHIFT;
+
+		for (i = 0; i < I2F_MAX_BITS; i++) {
 			if (fraction & 0x800000)
 				break;
 			else {
-				fraction = fraction << 1; /* keep
-							     shifting left until top bit = 1 */
+				fraction = fraction << 1;
 				exponent = exponent - 1;
 			}
 		}
-		result = exponent << 23 | (fraction & 0x7fffff); /* mask
-								    off top bit; assumed 1 */
+		result = exponent << 23 | (fraction & 0x7fffff);
 	}
 	return result;
 }

drivers/gpu/drm/radeon/radeon_atpx_handler.c

@@ -59,8 +59,9 @@ static int radeon_atrm_call(acpi_handle atrm_handle, uint8_t *bios,
 
 	obj = (union acpi_object *)buffer.pointer;
 	memcpy(bios+offset, obj->buffer.pointer, obj->buffer.length);
+	len = obj->buffer.length;
 	kfree(buffer.pointer);
-	return obj->buffer.length;
+	return len;
 }
 
 bool radeon_atrm_supported(struct pci_dev *pdev)

drivers/gpu/drm/radeon/radeon_device.c

@@ -883,6 +883,8 @@ int radeon_suspend_kms(struct drm_device *dev, pm_message_t state)
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
+	drm_kms_helper_poll_disable(dev);
+
 	/* turn off display hw */
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 		drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
@@ -972,6 +974,8 @@ int radeon_resume_kms(struct drm_device *dev)
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 		drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
 	}
+
+	drm_kms_helper_poll_enable(dev);
 	return 0;
 }
 

drivers/gpu/drm/radeon/radeon_i2c.c

@@ -958,6 +958,7 @@ struct radeon_i2c_chan *radeon_i2c_create_dp(struct drm_device *dev,
 	i2c->rec = *rec;
 	i2c->adapter.owner = THIS_MODULE;
 	i2c->adapter.class = I2C_CLASS_DDC;
+	i2c->adapter.dev.parent = &dev->pdev->dev;
 	i2c->dev = dev;
 	snprintf(i2c->adapter.name, sizeof(i2c->adapter.name),
 		 "Radeon aux bus %s", name);

drivers/infiniband/core/ucma.c

@@ -808,9 +808,12 @@ static ssize_t ucma_accept(struct ucma_file *file, const char __user *inbuf,
 		return PTR_ERR(ctx);
 
 	if (cmd.conn_param.valid) {
-		ctx->uid = cmd.uid;
 		ucma_copy_conn_param(&conn_param, &cmd.conn_param);
+		mutex_lock(&file->mut);
 		ret = rdma_accept(ctx->cm_id, &conn_param);
+		if (!ret)
+			ctx->uid = cmd.uid;
+		mutex_unlock(&file->mut);
 	} else
 		ret = rdma_accept(ctx->cm_id, NULL);
 

drivers/infiniband/core/uverbs_cmd.c

@@ -1485,6 +1485,7 @@ ssize_t ib_uverbs_create_qp(struct ib_uverbs_file *file,
 		qp->event_handler = attr.event_handler;
 		qp->qp_context	  = attr.qp_context;
 		qp->qp_type	  = attr.qp_type;
+		atomic_set(&qp->usecnt, 0);
 		atomic_inc(&pd->usecnt);
 		atomic_inc(&attr.send_cq->usecnt);
 		if (attr.recv_cq)

drivers/infiniband/core/verbs.c

@@ -421,6 +421,7 @@ struct ib_qp *ib_create_qp(struct ib_pd *pd,
 		qp->uobject    = NULL;
 		qp->qp_type    = qp_init_attr->qp_type;
 
+		atomic_set(&qp->usecnt, 0);
 		if (qp_init_attr->qp_type == IB_QPT_XRC_TGT) {
 			qp->event_handler = __ib_shared_qp_event_handler;
 			qp->qp_context = qp;
@@ -430,7 +431,6 @@ struct ib_qp *ib_create_qp(struct ib_pd *pd,
 			qp->xrcd = qp_init_attr->xrcd;
 			atomic_inc(&qp_init_attr->xrcd->usecnt);
 			INIT_LIST_HEAD(&qp->open_list);
-			atomic_set(&qp->usecnt, 0);
 
 			real_qp = qp;
 			qp = __ib_open_qp(real_qp, qp_init_attr->event_handler,

drivers/infiniband/hw/ipath/ipath_fs.c

@@ -89,7 +89,7 @@ static int create_file(const char *name, umode_t mode,
 		error = ipathfs_mknod(parent->d_inode, *dentry,
 				      mode, fops, data);
 	else
-		error = PTR_ERR(dentry);
+		error = PTR_ERR(*dentry);
 	mutex_unlock(&parent->d_inode->i_mutex);
 
 	return error;

drivers/infiniband/hw/mlx4/mad.c

@@ -257,12 +257,9 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 			return IB_MAD_RESULT_SUCCESS;
 
 		/*
-		 * Don't process SMInfo queries or vendor-specific
-		 * MADs -- the SMA can't handle them.
+		 * Don't process SMInfo queries -- the SMA can't handle them.
 		 */
-		if (in_mad->mad_hdr.attr_id == IB_SMP_ATTR_SM_INFO ||
-		    ((in_mad->mad_hdr.attr_id & IB_SMP_ATTR_VENDOR_MASK) ==
-		     IB_SMP_ATTR_VENDOR_MASK))
+		if (in_mad->mad_hdr.attr_id == IB_SMP_ATTR_SM_INFO)
 			return IB_MAD_RESULT_SUCCESS;
 	} else if (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT ||
 		   in_mad->mad_hdr.mgmt_class == MLX4_IB_VENDOR_CLASS1   ||

drivers/infiniband/hw/nes/nes.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 - 2009 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2006 - 2011 Intel Corporation.  All rights reserved.
  * Copyright (c) 2005 Open Grid Computing, Inc. All rights reserved.
  *
  * This software is available to you under a choice of one of two

drivers/infiniband/hw/nes/nes.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 - 2009 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2006 - 2011 Intel Corporation.  All rights reserved.
  * Copyright (c) 2005 Open Grid Computing, Inc. All rights reserved.
  *
  * This software is available to you under a choice of one of two

drivers/infiniband/hw/nes/nes_cm.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 - 2009 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2006 - 2011 Intel Corporation.  All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -233,6 +233,7 @@ static int send_mpa_reject(struct nes_cm_node *cm_node)
 	u8 *start_ptr = &start_addr;
 	u8 **start_buff = &start_ptr;
 	u16 buff_len = 0;
+	struct ietf_mpa_v1 *mpa_frame;
 
 	skb = dev_alloc_skb(MAX_CM_BUFFER);
 	if (!skb) {
@@ -242,6 +243,8 @@ static int send_mpa_reject(struct nes_cm_node *cm_node)
 
 	/* send an MPA reject frame */
 	cm_build_mpa_frame(cm_node, start_buff, &buff_len, NULL, MPA_KEY_REPLY);
+	mpa_frame = (struct ietf_mpa_v1 *)*start_buff;
+	mpa_frame->flags |= IETF_MPA_FLAGS_REJECT;
 	form_cm_frame(skb, cm_node, NULL, 0, *start_buff, buff_len, SET_ACK | SET_FIN);
 
 	cm_node->state = NES_CM_STATE_FIN_WAIT1;
@@ -1360,8 +1363,7 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi
 				if (!memcmp(nesadapter->arp_table[arpindex].mac_addr,
 					    neigh->ha, ETH_ALEN)) {
 					/* Mac address same as in nes_arp_table */
-					ip_rt_put(rt);
-					return rc;
+					goto out;
 				}
 
 				nes_manage_arp_cache(nesvnic->netdev,
@@ -1377,6 +1379,8 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi
 			neigh_event_send(neigh, NULL);
 		}
 	}
+
+out:
 	rcu_read_unlock();
 	ip_rt_put(rt);
 	return rc;

drivers/infiniband/hw/nes/nes_cm.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 - 2009 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2006 - 2011 Intel Corporation.  All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

drivers/infiniband/hw/nes/nes_context.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 - 2009 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2006 - 2011 Intel Corporation.  All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

drivers/infiniband/hw/nes/nes_hw.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 - 2009 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2006 - 2011 Intel Corporation.  All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

drivers/infiniband/hw/nes/nes_hw.h

@@ -1,5 +1,5 @@
 /*
-* Copyright (c) 2006 - 2009 Intel Corporation.  All rights reserved.
+* Copyright (c) 2006 - 2011 Intel Corporation.  All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU

drivers/infiniband/hw/nes/nes_mgt.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 - 2009 Intel-NE, Inc.  All rights reserved.
+ * Copyright (c) 2006 - 2011 Intel-NE, Inc.  All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

drivers/infiniband/hw/nes/nes_mgt.h

@@ -1,5 +1,5 @@
 /*
-* Copyright (c) 2010 Intel-NE, Inc.  All rights reserved.
+* Copyright (c) 2006 - 2011 Intel-NE, Inc.  All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU

drivers/infiniband/hw/nes/nes_nic.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 - 2009 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2006 - 2011 Intel Corporation.  All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

drivers/infiniband/hw/nes/nes_user.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 - 2009 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2006 - 2011 Intel Corporation.  All rights reserved.
  * Copyright (c) 2005 Topspin Communications.  All rights reserved.
  * Copyright (c) 2005 Cisco Systems.  All rights reserved.
  * Copyright (c) 2005 Open Grid Computing, Inc. All rights reserved.

drivers/infiniband/hw/nes/nes_utils.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 - 2009 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2006 - 2011 Intel Corporation.  All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

drivers/infiniband/hw/nes/nes_verbs.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 - 2009 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2006 - 2011 Intel Corporation.  All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -3427,6 +3427,8 @@ static int nes_post_send(struct ib_qp *ibqp, struct ib_send_wr *ib_wr,
 			set_wqe_32bit_value(wqe->wqe_words,
 					    NES_IWARP_SQ_FMR_WQE_LENGTH_LOW_IDX,
 					    ib_wr->wr.fast_reg.length);
+			set_wqe_32bit_value(wqe->wqe_words,
+					    NES_IWARP_SQ_FMR_WQE_LENGTH_HIGH_IDX, 0);
 			set_wqe_32bit_value(wqe->wqe_words,
 					    NES_IWARP_SQ_FMR_WQE_MR_STAG_IDX,
 					    ib_wr->wr.fast_reg.rkey);
@@ -3724,7 +3726,7 @@ static int nes_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *entry)
 						entry->opcode = IB_WC_SEND;
 						break;
 					case NES_IWARP_SQ_OP_LOCINV:
-						entry->opcode = IB_WR_LOCAL_INV;
+						entry->opcode = IB_WC_LOCAL_INV;
 						break;
 					case NES_IWARP_SQ_OP_FAST_REG:
 						entry->opcode = IB_WC_FAST_REG_MR;

drivers/infiniband/hw/nes/nes_verbs.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 - 2009 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2006 - 2011 Intel Corporation.  All rights reserved.
  * Copyright (c) 2005 Open Grid Computing, Inc. All rights reserved.
  *
  * This software is available to you under a choice of one of two

drivers/infiniband/hw/qib/qib_iba6120.c

@@ -2105,7 +2105,7 @@ static void alloc_dummy_hdrq(struct qib_devdata *dd)
 	dd->cspec->dummy_hdrq = dma_alloc_coherent(&dd->pcidev->dev,
 					dd->rcd[0]->rcvhdrq_size,
 					&dd->cspec->dummy_hdrq_phys,
-					GFP_KERNEL | __GFP_COMP);
+					GFP_ATOMIC | __GFP_COMP);
 	if (!dd->cspec->dummy_hdrq) {
 		qib_devinfo(dd->pcidev, "Couldn't allocate dummy hdrq\n");
 		/* fallback to just 0'ing */

drivers/infiniband/hw/qib/qib_pcie.c

@@ -560,7 +560,7 @@ static int qib_tune_pcie_coalesce(struct qib_devdata *dd)
  * BIOS may not set PCIe bus-utilization parameters for best performance.
  * Check and optionally adjust them to maximize our throughput.
  */
-static int qib_pcie_caps = 0x51;
+static int qib_pcie_caps;
 module_param_named(pcie_caps, qib_pcie_caps, int, S_IRUGO);
 MODULE_PARM_DESC(pcie_caps, "Max PCIe tuning: Payload (0..3), ReadReq (4..7)");
 

drivers/staging/media/go7007/go7007-usb.c

@@ -1279,3 +1279,4 @@ static struct usb_driver go7007_usb_driver = {
 };
 
 module_usb_driver(go7007_usb_driver);
+MODULE_LICENSE("GPL v2");

fs/ceph/caps.c

@@ -641,10 +641,10 @@ static int __cap_is_valid(struct ceph_cap *cap)
 	unsigned long ttl;
 	u32 gen;
 
-	spin_lock(&cap->session->s_cap_lock);
+	spin_lock(&cap->session->s_gen_ttl_lock);
 	gen = cap->session->s_cap_gen;
 	ttl = cap->session->s_cap_ttl;
-	spin_unlock(&cap->session->s_cap_lock);
+	spin_unlock(&cap->session->s_gen_ttl_lock);
 
 	if (cap->cap_gen < gen || time_after_eq(jiffies, ttl)) {
 		dout("__cap_is_valid %p cap %p issued %s "

fs/ceph/dir.c

@@ -975,10 +975,10 @@ static int dentry_lease_is_valid(struct dentry *dentry)
 	di = ceph_dentry(dentry);
 	if (di->lease_session) {
 		s = di->lease_session;
-		spin_lock(&s->s_cap_lock);
+		spin_lock(&s->s_gen_ttl_lock);
 		gen = s->s_cap_gen;
 		ttl = s->s_cap_ttl;
-		spin_unlock(&s->s_cap_lock);
+		spin_unlock(&s->s_gen_ttl_lock);
 
 		if (di->lease_gen == gen &&
 		    time_before(jiffies, dentry->d_time) &&

fs/ceph/mds_client.c

@@ -262,6 +262,7 @@ static int parse_reply_info(struct ceph_msg *msg,
 	/* trace */
 	ceph_decode_32_safe(&p, end, len, bad);
 	if (len > 0) {
+		ceph_decode_need(&p, end, len, bad);
 		err = parse_reply_info_trace(&p, p+len, info, features);
 		if (err < 0)
 			goto out_bad;
@@ -270,6 +271,7 @@ static int parse_reply_info(struct ceph_msg *msg,
 	/* extra */
 	ceph_decode_32_safe(&p, end, len, bad);
 	if (len > 0) {
+		ceph_decode_need(&p, end, len, bad);
 		err = parse_reply_info_extra(&p, p+len, info, features);
 		if (err < 0)
 			goto out_bad;
@@ -398,9 +400,11 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 	s->s_con.peer_name.type = CEPH_ENTITY_TYPE_MDS;
 	s->s_con.peer_name.num = cpu_to_le64(mds);
 
-	spin_lock_init(&s->s_cap_lock);
+	spin_lock_init(&s->s_gen_ttl_lock);
 	s->s_cap_gen = 0;
 	s->s_cap_ttl = 0;
+
+	spin_lock_init(&s->s_cap_lock);
 	s->s_renew_requested = 0;
 	s->s_renew_seq = 0;
 	INIT_LIST_HEAD(&s->s_caps);
@@ -2326,10 +2330,10 @@ static void handle_session(struct ceph_mds_session *session,
 	case CEPH_SESSION_STALE:
 		pr_info("mds%d caps went stale, renewing\n",
 			session->s_mds);
-		spin_lock(&session->s_cap_lock);
+		spin_lock(&session->s_gen_ttl_lock);
 		session->s_cap_gen++;
 		session->s_cap_ttl = 0;
-		spin_unlock(&session->s_cap_lock);
+		spin_unlock(&session->s_gen_ttl_lock);
 		send_renew_caps(mdsc, session);
 		break;
 

fs/ceph/mds_client.h

@@ -117,10 +117,13 @@ struct ceph_mds_session {
 	void             *s_authorizer_buf, *s_authorizer_reply_buf;
 	size_t            s_authorizer_buf_len, s_authorizer_reply_buf_len;
 
-	/* protected by s_cap_lock */
-	spinlock_t        s_cap_lock;
+	/* protected by s_gen_ttl_lock */
+	spinlock_t        s_gen_ttl_lock;
 	u32               s_cap_gen;  /* inc each time we get mds stale msg */
 	unsigned long     s_cap_ttl;  /* when session caps expire */
+
+	/* protected by s_cap_lock */
+	spinlock_t        s_cap_lock;
 	struct list_head  s_caps;     /* all caps issued by this session */
 	int               s_nr_caps, s_trim_caps;
 	int               s_num_cap_releases;

fs/ceph/xattr.c

@@ -111,8 +111,10 @@ static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
 }
 
 static struct ceph_vxattr_cb ceph_file_vxattrs[] = {
+	{ true, "ceph.file.layout", ceph_vxattrcb_layout},
+	/* The following extended attribute name is deprecated */
 	{ true, "ceph.layout", ceph_vxattrcb_layout},
-	{ NULL, NULL }
+	{ true, NULL, NULL }
 };
 
 static struct ceph_vxattr_cb *ceph_inode_vxattrs(struct inode *inode)

fs/lockd/clnt4xdr.c

@@ -598,7 +598,7 @@ static struct rpc_procinfo	nlm4_procedures[] = {
 	PROC(GRANTED_RES,	res,		norep),
 };
 
-struct rpc_version	nlm_version4 = {
+const struct rpc_version nlm_version4 = {
 	.number		= 4,
 	.nrprocs	= ARRAY_SIZE(nlm4_procedures),
 	.procs		= nlm4_procedures,

fs/lockd/clntlock.c

@@ -62,7 +62,8 @@ struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init)
 
 	host = nlmclnt_lookup_host(nlm_init->address, nlm_init->addrlen,
 				   nlm_init->protocol, nlm_version,
-				   nlm_init->hostname, nlm_init->noresvport);
+				   nlm_init->hostname, nlm_init->noresvport,
+				   nlm_init->net);
 	if (host == NULL) {
 		lockd_down();
 		return ERR_PTR(-ENOLCK);

fs/lockd/clntxdr.c

@@ -596,19 +596,19 @@ static struct rpc_procinfo	nlm_procedures[] = {
 	PROC(GRANTED_RES,	res,		norep),
 };
 
-static struct rpc_version	nlm_version1 = {
+static const struct rpc_version	nlm_version1 = {
 		.number		= 1,
 		.nrprocs	= ARRAY_SIZE(nlm_procedures),
 		.procs		= nlm_procedures,
 };
 
-static struct rpc_version	nlm_version3 = {
+static const struct rpc_version	nlm_version3 = {
 		.number		= 3,
 		.nrprocs	= ARRAY_SIZE(nlm_procedures),
 		.procs		= nlm_procedures,
 };
 
-static struct rpc_version	*nlm_versions[] = {
+static const struct rpc_version	*nlm_versions[] = {
 	[1] = &nlm_version1,
 	[3] = &nlm_version3,
 #ifdef CONFIG_LOCKD_V4
@@ -618,7 +618,7 @@ static struct rpc_version	*nlm_versions[] = {
 
 static struct rpc_stat		nlm_rpc_stats;
 
-struct rpc_program		nlm_program = {
+const struct rpc_program	nlm_program = {
 		.name		= "lockd",
 		.number		= NLM_PROGRAM,
 		.nrvers		= ARRAY_SIZE(nlm_versions),

fs/lockd/host.c

@@ -17,6 +17,8 @@
 #include <linux/lockd/lockd.h>
 #include <linux/mutex.h>
 
+#include <linux/sunrpc/svc_xprt.h>
+
 #include <net/ipv6.h>
 
 #define NLMDBG_FACILITY		NLMDBG_HOSTCACHE
@@ -54,6 +56,7 @@ struct nlm_lookup_host_info {
 	const char		*hostname;	/* remote's hostname */
 	const size_t		hostname_len;	/* it's length */
 	const int		noresvport;	/* use non-priv port */
+	struct net		*net;		/* network namespace to bind */
 };
 
 /*
@@ -155,6 +158,7 @@ static struct nlm_host *nlm_alloc_host(struct nlm_lookup_host_info *ni,
 	INIT_LIST_HEAD(&host->h_reclaim);
 	host->h_nsmhandle  = nsm;
 	host->h_addrbuf    = nsm->sm_addrbuf;
+	host->net	   = ni->net;
 
 out:
 	return host;
@@ -206,7 +210,8 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap,
 				     const unsigned short protocol,
 				     const u32 version,
 				     const char *hostname,
-				     int noresvport)
+				     int noresvport,
+				     struct net *net)
 {
 	struct nlm_lookup_host_info ni = {
 		.server		= 0,
@@ -217,6 +222,7 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap,
 		.hostname	= hostname,
 		.hostname_len	= strlen(hostname),
 		.noresvport	= noresvport,
+		.net		= net,
 	};
 	struct hlist_head *chain;
 	struct hlist_node *pos;
@@ -231,6 +237,8 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap,
 
 	chain = &nlm_client_hosts[nlm_hash_address(sap)];
 	hlist_for_each_entry(host, pos, chain, h_hash) {
+		if (host->net != net)
+			continue;
 		if (!rpc_cmp_addr(nlm_addr(host), sap))
 			continue;
 
@@ -318,6 +326,7 @@ struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp,
 	struct nsm_handle *nsm = NULL;
 	struct sockaddr *src_sap = svc_daddr(rqstp);
 	size_t src_len = rqstp->rq_daddrlen;
+	struct net *net = rqstp->rq_xprt->xpt_net;
 	struct nlm_lookup_host_info ni = {
 		.server		= 1,
 		.sap		= svc_addr(rqstp),
@@ -326,6 +335,7 @@ struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp,
 		.version	= rqstp->rq_vers,
 		.hostname	= hostname,
 		.hostname_len	= hostname_len,
+		.net		= net,
 	};
 
 	dprintk("lockd: %s(host='%*s', vers=%u, proto=%s)\n", __func__,
@@ -339,6 +349,8 @@ struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp,
 
 	chain = &nlm_server_hosts[nlm_hash_address(ni.sap)];
 	hlist_for_each_entry(host, pos, chain, h_hash) {
+		if (host->net != net)
+			continue;
 		if (!rpc_cmp_addr(nlm_addr(host), ni.sap))
 			continue;
 
@@ -431,7 +443,7 @@ nlm_bind_host(struct nlm_host *host)
 			.to_retries	= 5U,
 		};
 		struct rpc_create_args args = {
-			.net		= &init_net,
+			.net		= host->net,
 			.protocol	= host->h_proto,
 			.address	= nlm_addr(host),
 			.addrsize	= host->h_addrlen,
@@ -553,12 +565,8 @@ void nlm_host_rebooted(const struct nlm_reboot *info)
 	nsm_release(nsm);
 }
 
-/*
- * Shut down the hosts module.
- * Note that this routine is called only at server shutdown time.
- */
 void
-nlm_shutdown_hosts(void)
+nlm_shutdown_hosts_net(struct net *net)
 {
 	struct hlist_head *chain;
 	struct hlist_node *pos;
@@ -570,6 +578,8 @@ nlm_shutdown_hosts(void)
 	/* First, make all hosts eligible for gc */
 	dprintk("lockd: nuking all hosts...\n");
 	for_each_host(host, pos, chain, nlm_server_hosts) {
+		if (net && host->net != net)
+			continue;
 		host->h_expires = jiffies - 1;
 		if (host->h_rpcclnt) {
 			rpc_shutdown_client(host->h_rpcclnt);
@@ -580,15 +590,29 @@ nlm_shutdown_hosts(void)
 	/* Then, perform a garbage collection pass */
 	nlm_gc_hosts();
 	mutex_unlock(&nlm_host_mutex);
+}
+
+/*
+ * Shut down the hosts module.
+ * Note that this routine is called only at server shutdown time.
+ */
+void
+nlm_shutdown_hosts(void)
+{
+	struct hlist_head *chain;
+	struct hlist_node *pos;
+	struct nlm_host	*host;
+
+	nlm_shutdown_hosts_net(NULL);
 
 	/* complain if any hosts are left */
 	if (nrhosts != 0) {
 		printk(KERN_WARNING "lockd: couldn't shutdown host module!\n");
 		dprintk("lockd: %lu hosts left:\n", nrhosts);
 		for_each_host(host, pos, chain, nlm_server_hosts) {
-			dprintk("       %s (cnt %d use %d exp %ld)\n",
+			dprintk("       %s (cnt %d use %d exp %ld net %p)\n",
 				host->h_name, atomic_read(&host->h_count),
-				host->h_inuse, host->h_expires);
+				host->h_inuse, host->h_expires, host->net);
 		}
 	}
 }

fs/lockd/mon.c

@@ -47,7 +47,7 @@ struct nsm_res {
 	u32			state;
 };
 
-static struct rpc_program	nsm_program;
+static const struct rpc_program	nsm_program;
 static				LIST_HEAD(nsm_handles);
 static				DEFINE_SPINLOCK(nsm_lock);
 
@@ -62,14 +62,14 @@ static inline struct sockaddr *nsm_addr(const struct nsm_handle *nsm)
 	return (struct sockaddr *)&nsm->sm_addr;
 }
 
-static struct rpc_clnt *nsm_create(void)
+static struct rpc_clnt *nsm_create(struct net *net)
 {
 	struct sockaddr_in sin = {
 		.sin_family		= AF_INET,
 		.sin_addr.s_addr	= htonl(INADDR_LOOPBACK),
 	};
 	struct rpc_create_args args = {
-		.net			= &init_net,
+		.net			= net,
 		.protocol		= XPRT_TRANSPORT_UDP,
 		.address		= (struct sockaddr *)&sin,
 		.addrsize		= sizeof(sin),
@@ -83,7 +83,8 @@ static struct rpc_clnt *nsm_create(void)
 	return rpc_create(&args);
 }
 
-static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res)
+static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res,
+			 struct net *net)
 {
 	struct rpc_clnt	*clnt;
 	int		status;
@@ -99,7 +100,7 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res)
 		.rpc_resp	= res,
 	};
 
-	clnt = nsm_create();
+	clnt = nsm_create(net);
 	if (IS_ERR(clnt)) {
 		status = PTR_ERR(clnt);
 		dprintk("lockd: failed to create NSM upcall transport, "
@@ -149,7 +150,7 @@ int nsm_monitor(const struct nlm_host *host)
 	 */
 	nsm->sm_mon_name = nsm_use_hostnames ? nsm->sm_name : nsm->sm_addrbuf;
 
-	status = nsm_mon_unmon(nsm, NSMPROC_MON, &res);
+	status = nsm_mon_unmon(nsm, NSMPROC_MON, &res, host->net);
 	if (unlikely(res.status != 0))
 		status = -EIO;
 	if (unlikely(status < 0)) {
@@ -183,7 +184,7 @@ void nsm_unmonitor(const struct nlm_host *host)
 	 && nsm->sm_monitored && !nsm->sm_sticky) {
 		dprintk("lockd: nsm_unmonitor(%s)\n", nsm->sm_name);
 
-		status = nsm_mon_unmon(nsm, NSMPROC_UNMON, &res);
+		status = nsm_mon_unmon(nsm, NSMPROC_UNMON, &res, host->net);
 		if (res.status != 0)
 			status = -EIO;
 		if (status < 0)
@@ -534,19 +535,19 @@ static struct rpc_procinfo	nsm_procedures[] = {
 	},
 };
 
-static struct rpc_version	nsm_version1 = {
+static const struct rpc_version nsm_version1 = {
 		.number		= 1,
 		.nrprocs	= ARRAY_SIZE(nsm_procedures),
 		.procs		= nsm_procedures
 };
 
-static struct rpc_version *	nsm_version[] = {
+static const struct rpc_version *nsm_version[] = {
 	[1] = &nsm_version1,
 };
 
 static struct rpc_stat		nsm_stats;
 
-static struct rpc_program	nsm_program = {
+static const struct rpc_program nsm_program = {
 		.name		= "statd",
 		.number		= NSM_PROGRAM,
 		.nrvers		= ARRAY_SIZE(nsm_version),

fs/lockd/netns.h

@@ -0,0 +1,12 @@
+#ifndef __LOCKD_NETNS_H__
+#define __LOCKD_NETNS_H__
+
+#include <net/netns/generic.h>
+
+struct lockd_net {
+	unsigned int nlmsvc_users;
+};
+
+extern int lockd_net_id;
+
+#endif

fs/lockd/svc.c

@@ -35,6 +35,8 @@
 #include <linux/lockd/lockd.h>
 #include <linux/nfs.h>
 
+#include "netns.h"
+
 #define NLMDBG_FACILITY		NLMDBG_SVC
 #define LOCKD_BUFSIZE		(1024 + NLMSVC_XDRSIZE)
 #define ALLOWED_SIGS		(sigmask(SIGKILL))
@@ -50,6 +52,8 @@ static struct task_struct	*nlmsvc_task;
 static struct svc_rqst		*nlmsvc_rqst;
 unsigned long			nlmsvc_timeout;
 
+int lockd_net_id;
+
 /*
  * These can be set at insmod time (useful for NFS as root filesystem),
  * and also changed through the sysctl interface.  -- Jamie Lokier, Aug 2003
@@ -189,27 +193,29 @@ lockd(void *vrqstp)
 }
 
 static int create_lockd_listener(struct svc_serv *serv, const char *name,
-				 const int family, const unsigned short port)
+				 struct net *net, const int family,
+				 const unsigned short port)
 {
 	struct svc_xprt *xprt;
 
-	xprt = svc_find_xprt(serv, name, family, 0);
+	xprt = svc_find_xprt(serv, name, net, family, 0);
 	if (xprt == NULL)
-		return svc_create_xprt(serv, name, &init_net, family, port,
+		return svc_create_xprt(serv, name, net, family, port,
 						SVC_SOCK_DEFAULTS);
 	svc_xprt_put(xprt);
 	return 0;
 }
 
-static int create_lockd_family(struct svc_serv *serv, const int family)
+static int create_lockd_family(struct svc_serv *serv, struct net *net,
+			       const int family)
 {
 	int err;
 
-	err = create_lockd_listener(serv, "udp", family, nlm_udpport);
+	err = create_lockd_listener(serv, "udp", net, family, nlm_udpport);
 	if (err < 0)
 		return err;
 
-	return create_lockd_listener(serv, "tcp", family, nlm_tcpport);
+	return create_lockd_listener(serv, "tcp", net, family, nlm_tcpport);
 }
 
 /*
@@ -222,16 +228,16 @@ static int create_lockd_family(struct svc_serv *serv, const int family)
  * Returns zero if all listeners are available; otherwise a
  * negative errno value is returned.
  */
-static int make_socks(struct svc_serv *serv)
+static int make_socks(struct svc_serv *serv, struct net *net)
 {
 	static int warned;
 	int err;
 
-	err = create_lockd_family(serv, PF_INET);
+	err = create_lockd_family(serv, net, PF_INET);
 	if (err < 0)
 		goto out_err;
 
-	err = create_lockd_family(serv, PF_INET6);
+	err = create_lockd_family(serv, net, PF_INET6);
 	if (err < 0 && err != -EAFNOSUPPORT)
 		goto out_err;
 
@@ -245,6 +251,47 @@ out_err:
 	return err;
 }
 
+static int lockd_up_net(struct net *net)
+{
+	struct lockd_net *ln = net_generic(net, lockd_net_id);
+	struct svc_serv *serv = nlmsvc_rqst->rq_server;
+	int error;
+
+	if (ln->nlmsvc_users)
+		return 0;
+
+	error = svc_rpcb_setup(serv, net);
+	if (error)
+		goto err_rpcb;
+
+	error = make_socks(serv, net);
+	if (error < 0)
+		goto err_socks;
+	return 0;
+
+err_socks:
+	svc_rpcb_cleanup(serv, net);
+err_rpcb:
+	return error;
+}
+
+static void lockd_down_net(struct net *net)
+{
+	struct lockd_net *ln = net_generic(net, lockd_net_id);
+	struct svc_serv *serv = nlmsvc_rqst->rq_server;
+
+	if (ln->nlmsvc_users) {
+		if (--ln->nlmsvc_users == 0) {
+			nlm_shutdown_hosts_net(net);
+			svc_shutdown_net(serv, net);
+		}
+	} else {
+		printk(KERN_ERR "lockd_down_net: no users! task=%p, net=%p\n",
+				nlmsvc_task, net);
+		BUG();
+	}
+}
+
 /*
  * Bring up the lockd process if it's not already up.
  */
@@ -252,13 +299,16 @@ int lockd_up(void)
 {
 	struct svc_serv *serv;
 	int		error = 0;
+	struct net *net = current->nsproxy->net_ns;
 
 	mutex_lock(&nlmsvc_mutex);
 	/*
 	 * Check whether we're already up and running.
 	 */
-	if (nlmsvc_rqst)
+	if (nlmsvc_rqst) {
+		error = lockd_up_net(net);
 		goto out;
+	}
 
 	/*
 	 * Sanity check: if there's no pid,
@@ -275,7 +325,7 @@ int lockd_up(void)
 		goto out;
 	}
 
-	error = make_socks(serv);
+	error = make_socks(serv, net);
 	if (error < 0)
 		goto destroy_and_out;
 
@@ -313,8 +363,12 @@ int lockd_up(void)
 destroy_and_out:
 	svc_destroy(serv);
 out:
-	if (!error)
+	if (!error) {
+		struct lockd_net *ln = net_generic(net, lockd_net_id);
+
+		ln->nlmsvc_users++;
 		nlmsvc_users++;
+	}
 	mutex_unlock(&nlmsvc_mutex);
 	return error;
 }
@@ -328,8 +382,10 @@ lockd_down(void)
 {
 	mutex_lock(&nlmsvc_mutex);
 	if (nlmsvc_users) {
-		if (--nlmsvc_users)
+		if (--nlmsvc_users) {
+			lockd_down_net(current->nsproxy->net_ns);
 			goto out;
+		}
 	} else {
 		printk(KERN_ERR "lockd_down: no users! task=%p\n",
 			nlmsvc_task);
@@ -497,24 +553,55 @@ module_param_call(nlm_tcpport, param_set_port, param_get_int,
 module_param(nsm_use_hostnames, bool, 0644);
 module_param(nlm_max_connections, uint, 0644);
 
+static int lockd_init_net(struct net *net)
+{
+	return 0;
+}
+
+static void lockd_exit_net(struct net *net)
+{
+}
+
+static struct pernet_operations lockd_net_ops = {
+	.init = lockd_init_net,
+	.exit = lockd_exit_net,
+	.id = &lockd_net_id,
+	.size = sizeof(struct lockd_net),
+};
+
+
 /*
  * Initialising and terminating the module.
  */
 
 static int __init init_nlm(void)
 {
+	int err;
+
 #ifdef CONFIG_SYSCTL
+	err = -ENOMEM;
 	nlm_sysctl_table = register_sysctl_table(nlm_sysctl_root);
-	return nlm_sysctl_table ? 0 : -ENOMEM;
-#else
+	if (nlm_sysctl_table == NULL)
+		goto err_sysctl;
+#endif
+	err = register_pernet_subsys(&lockd_net_ops);
+	if (err)
+		goto err_pernet;
 	return 0;
+
+err_pernet:
+#ifdef CONFIG_SYSCTL
+	unregister_sysctl_table(nlm_sysctl_table);
 #endif
+err_sysctl:
+	return err;
 }
 
 static void __exit exit_nlm(void)
 {
 	/* FIXME: delete all NLM clients */
 	nlm_shutdown_hosts();
+	unregister_pernet_subsys(&lockd_net_ops);
 #ifdef CONFIG_SYSCTL
 	unregister_sysctl_table(nlm_sysctl_table);
 #endif

fs/lockd/svclock.c

@@ -46,7 +46,6 @@ static void	nlmsvc_remove_block(struct nlm_block *block);
 static int nlmsvc_setgrantargs(struct nlm_rqst *call, struct nlm_lock *lock);
 static void nlmsvc_freegrantargs(struct nlm_rqst *call);
 static const struct rpc_call_ops nlmsvc_grant_ops;
-static const char *nlmdbg_cookie2a(const struct nlm_cookie *cookie);
 
 /*
  * The list of blocked locks to retry
@@ -54,6 +53,35 @@ static const char *nlmdbg_cookie2a(const struct nlm_cookie *cookie);
 static LIST_HEAD(nlm_blocked);
 static DEFINE_SPINLOCK(nlm_blocked_lock);
 
+#ifdef LOCKD_DEBUG
+static const char *nlmdbg_cookie2a(const struct nlm_cookie *cookie)
+{
+	/*
+	 * We can get away with a static buffer because we're only
+	 * called with BKL held.
+	 */
+	static char buf[2*NLM_MAXCOOKIELEN+1];
+	unsigned int i, len = sizeof(buf);
+	char *p = buf;
+
+	len--;	/* allow for trailing \0 */
+	if (len < 3)
+		return "???";
+	for (i = 0 ; i < cookie->len ; i++) {
+		if (len < 2) {
+			strcpy(p-3, "...");
+			break;
+		}
+		sprintf(p, "%02x", cookie->data[i]);
+		p += 2;
+		len -= 2;
+	}
+	*p = '\0';
+
+	return buf;
+}
+#endif
+
 /*
  * Insert a blocked lock into the global list
  */
@@ -935,32 +963,3 @@ nlmsvc_retry_blocked(void)
 
 	return timeout;
 }
-
-#ifdef RPC_DEBUG
-static const char *nlmdbg_cookie2a(const struct nlm_cookie *cookie)
-{
-	/*
-	 * We can get away with a static buffer because we're only
-	 * called with BKL held.
-	 */
-	static char buf[2*NLM_MAXCOOKIELEN+1];
-	unsigned int i, len = sizeof(buf);
-	char *p = buf;
-
-	len--;	/* allow for trailing \0 */
-	if (len < 3)
-		return "???";
-	for (i = 0 ; i < cookie->len ; i++) {
-		if (len < 2) {
-			strcpy(p-3, "...");
-			break;
-		}
-		sprintf(p, "%02x", cookie->data[i]);
-		p += 2;
-		len -= 2;
-	}
-	*p = '\0';
-
-	return buf;
-}
-#endif

fs/logfs/dev_mtd.c

@@ -152,9 +152,6 @@ static struct page *logfs_mtd_find_first_sb(struct super_block *sb, u64 *ofs)
 	filler_t *filler = logfs_mtd_readpage;
 	struct mtd_info *mtd = super->s_mtd;
 
-	if (!mtd_can_have_bb(mtd))
-		return NULL;
-
 	*ofs = 0;
 	while (mtd_block_isbad(mtd, *ofs)) {
 		*ofs += mtd->erasesize;
@@ -172,9 +169,6 @@ static struct page *logfs_mtd_find_last_sb(struct super_block *sb, u64 *ofs)
 	filler_t *filler = logfs_mtd_readpage;
 	struct mtd_info *mtd = super->s_mtd;
 
-	if (!mtd_can_have_bb(mtd))
-		return NULL;
-
 	*ofs = mtd->size - mtd->erasesize;
 	while (mtd_block_isbad(mtd, *ofs)) {
 		*ofs -= mtd->erasesize;

fs/nfs/Kconfig

@@ -64,6 +64,7 @@ config NFS_V4
 	bool "NFS client support for NFS version 4"
 	depends on NFS_FS
 	select SUNRPC_GSS
+	select KEYS
 	help
 	  This option enables support for version 4 of the NFS protocol
 	  (RFC 3530) in the kernel's NFS client.
@@ -98,6 +99,18 @@ config PNFS_OBJLAYOUT
 	depends on NFS_FS && NFS_V4_1 && SCSI_OSD_ULD
 	default m
 
+config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN
+	string "NFSv4.1 Implementation ID Domain"
+	depends on NFS_V4_1
+	default "kernel.org"
+	help
+	  This option defines the domain portion of the implementation ID that
+	  may be sent in the NFS exchange_id operation.  The value must be in
+	  the format of a DNS domain name and should be set to the DNS domain
+	  name of the distribution.
+	  If the NFS client is unchanged from the upstream kernel, this
+	  option should be set to the default "kernel.org".
+
 config ROOT_NFS
 	bool "Root file system on NFS"
 	depends on NFS_FS=y && IP_PNP
@@ -130,16 +143,10 @@ config NFS_USE_KERNEL_DNS
 	bool
 	depends on NFS_V4 && !NFS_USE_LEGACY_DNS
 	select DNS_RESOLVER
-	select KEYS
 	default y
 
-config NFS_USE_NEW_IDMAPPER
-	bool "Use the new idmapper upcall routine"
-	depends on NFS_V4 && KEYS
-	help
-	  Say Y here if you want NFS to use the new idmapper upcall functions.
-	  You will need /sbin/request-key (usually provided by the keyutils
-	  package).  For details, read
-	  <file:Documentation/filesystems/nfs/idmapper.txt>.
-
-	  If you are unsure, say N.
+config NFS_DEBUG
+	bool
+	depends on NFS_FS && SUNRPC_DEBUG
+	select CRC32
+	default y

fs/nfs/blocklayout/blocklayout.c

@@ -46,9 +46,6 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Andy Adamson <andros@citi.umich.edu>");
 MODULE_DESCRIPTION("The NFSv4.1 pNFS Block layout driver");
 
-struct dentry *bl_device_pipe;
-wait_queue_head_t bl_wq;
-
 static void print_page(struct page *page)
 {
 	dprintk("PRINTPAGE page %p\n", page);
@@ -236,12 +233,11 @@ bl_read_pagelist(struct nfs_read_data *rdata)
 	sector_t isect, extent_length = 0;
 	struct parallel_io *par;
 	loff_t f_offset = rdata->args.offset;
-	size_t count = rdata->args.count;
 	struct page **pages = rdata->args.pages;
 	int pg_index = rdata->args.pgbase >> PAGE_CACHE_SHIFT;
 
-	dprintk("%s enter nr_pages %u offset %lld count %Zd\n", __func__,
-	       rdata->npages, f_offset, count);
+	dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__,
+	       rdata->npages, f_offset, (unsigned int)rdata->args.count);
 
 	par = alloc_parallel(rdata);
 	if (!par)
@@ -1025,10 +1021,128 @@ static const struct rpc_pipe_ops bl_upcall_ops = {
 	.destroy_msg	= bl_pipe_destroy_msg,
 };
 
+static struct dentry *nfs4blocklayout_register_sb(struct super_block *sb,
+					    struct rpc_pipe *pipe)
+{
+	struct dentry *dir, *dentry;
+
+	dir = rpc_d_lookup_sb(sb, NFS_PIPE_DIRNAME);
+	if (dir == NULL)
+		return ERR_PTR(-ENOENT);
+	dentry = rpc_mkpipe_dentry(dir, "blocklayout", NULL, pipe);
+	dput(dir);
+	return dentry;
+}
+
+static void nfs4blocklayout_unregister_sb(struct super_block *sb,
+					  struct rpc_pipe *pipe)
+{
+	if (pipe->dentry)
+		rpc_unlink(pipe->dentry);
+}
+
+static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
+			   void *ptr)
+{
+	struct super_block *sb = ptr;
+	struct net *net = sb->s_fs_info;
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+	struct dentry *dentry;
+	int ret = 0;
+
+	if (!try_module_get(THIS_MODULE))
+		return 0;
+
+	if (nn->bl_device_pipe == NULL) {
+		module_put(THIS_MODULE);
+		return 0;
+	}
+
+	switch (event) {
+	case RPC_PIPEFS_MOUNT:
+		dentry = nfs4blocklayout_register_sb(sb, nn->bl_device_pipe);
+		if (IS_ERR(dentry)) {
+			ret = PTR_ERR(dentry);
+			break;
+		}
+		nn->bl_device_pipe->dentry = dentry;
+		break;
+	case RPC_PIPEFS_UMOUNT:
+		if (nn->bl_device_pipe->dentry)
+			nfs4blocklayout_unregister_sb(sb, nn->bl_device_pipe);
+		break;
+	default:
+		ret = -ENOTSUPP;
+		break;
+	}
+	module_put(THIS_MODULE);
+	return ret;
+}
+
+static struct notifier_block nfs4blocklayout_block = {
+	.notifier_call = rpc_pipefs_event,
+};
+
+static struct dentry *nfs4blocklayout_register_net(struct net *net,
+						   struct rpc_pipe *pipe)
+{
+	struct super_block *pipefs_sb;
+	struct dentry *dentry;
+
+	pipefs_sb = rpc_get_sb_net(net);
+	if (!pipefs_sb)
+		return NULL;
+	dentry = nfs4blocklayout_register_sb(pipefs_sb, pipe);
+	rpc_put_sb_net(net);
+	return dentry;
+}
+
+static void nfs4blocklayout_unregister_net(struct net *net,
+					   struct rpc_pipe *pipe)
+{
+	struct super_block *pipefs_sb;
+
+	pipefs_sb = rpc_get_sb_net(net);
+	if (pipefs_sb) {
+		nfs4blocklayout_unregister_sb(pipefs_sb, pipe);
+		rpc_put_sb_net(net);
+	}
+}
+
+static int nfs4blocklayout_net_init(struct net *net)
+{
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+	struct dentry *dentry;
+
+	init_waitqueue_head(&nn->bl_wq);
+	nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0);
+	if (IS_ERR(nn->bl_device_pipe))
+		return PTR_ERR(nn->bl_device_pipe);
+	dentry = nfs4blocklayout_register_net(net, nn->bl_device_pipe);
+	if (IS_ERR(dentry)) {
+		rpc_destroy_pipe_data(nn->bl_device_pipe);
+		return PTR_ERR(dentry);
+	}
+	nn->bl_device_pipe->dentry = dentry;
+	return 0;
+}
+
+static void nfs4blocklayout_net_exit(struct net *net)
+{
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+	nfs4blocklayout_unregister_net(net, nn->bl_device_pipe);
+	rpc_destroy_pipe_data(nn->bl_device_pipe);
+	nn->bl_device_pipe = NULL;
+}
+
+static struct pernet_operations nfs4blocklayout_net_ops = {
+	.init = nfs4blocklayout_net_init,
+	.exit = nfs4blocklayout_net_exit,
+};
+
 static int __init nfs4blocklayout_init(void)
 {
-	struct vfsmount *mnt;
-	struct path path;
 	int ret;
 
 	dprintk("%s: NFSv4 Block Layout Driver Registering...\n", __func__);
@@ -1037,32 +1151,17 @@ static int __init nfs4blocklayout_init(void)
 	if (ret)
 		goto out;
 
-	init_waitqueue_head(&bl_wq);
-
-	mnt = rpc_get_mount();
-	if (IS_ERR(mnt)) {
-		ret = PTR_ERR(mnt);
+	ret = rpc_pipefs_notifier_register(&nfs4blocklayout_block);
+	if (ret)
 		goto out_remove;
-	}
-
-	ret = vfs_path_lookup(mnt->mnt_root,
-			      mnt,
-			      NFS_PIPE_DIRNAME, 0, &path);
+	ret = register_pernet_subsys(&nfs4blocklayout_net_ops);
 	if (ret)
-		goto out_putrpc;
-
-	bl_device_pipe = rpc_mkpipe(path.dentry, "blocklayout", NULL,
-				    &bl_upcall_ops, 0);
-	path_put(&path);
-	if (IS_ERR(bl_device_pipe)) {
-		ret = PTR_ERR(bl_device_pipe);
-		goto out_putrpc;
-	}
+		goto out_notifier;
 out:
 	return ret;
 
-out_putrpc:
-	rpc_put_mount();
+out_notifier:
+	rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
 out_remove:
 	pnfs_unregister_layoutdriver(&blocklayout_type);
 	return ret;
@@ -1073,9 +1172,9 @@ static void __exit nfs4blocklayout_exit(void)
 	dprintk("%s: NFSv4 Block Layout Driver Unregistering...\n",
 	       __func__);
 
+	rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
+	unregister_pernet_subsys(&nfs4blocklayout_net_ops);
 	pnfs_unregister_layoutdriver(&blocklayout_type);
-	rpc_unlink(bl_device_pipe);
-	rpc_put_mount();
 }
 
 MODULE_ALIAS("nfs-layouttype4-3");

fs/nfs/blocklayout/blocklayout.h

@@ -37,6 +37,7 @@
 #include <linux/sunrpc/rpc_pipe_fs.h>
 
 #include "../pnfs.h"
+#include "../netns.h"
 
 #define PAGE_CACHE_SECTORS (PAGE_CACHE_SIZE >> SECTOR_SHIFT)
 #define PAGE_CACHE_SECTOR_SHIFT (PAGE_CACHE_SHIFT - SECTOR_SHIFT)
@@ -50,6 +51,7 @@ struct pnfs_block_dev {
 	struct list_head		bm_node;
 	struct nfs4_deviceid		bm_mdevid;    /* associated devid */
 	struct block_device		*bm_mdev;     /* meta device itself */
+	struct net			*net;
 };
 
 enum exstate4 {
@@ -151,9 +153,9 @@ BLK_LSEG2EXT(struct pnfs_layout_segment *lseg)
 	return BLK_LO2EXT(lseg->pls_layout);
 }
 
-struct bl_dev_msg {
-	int32_t status;
-	uint32_t major, minor;
+struct bl_pipe_msg {
+	struct rpc_pipe_msg msg;
+	wait_queue_head_t *bl_wq;
 };
 
 struct bl_msg_hdr {
@@ -161,9 +163,6 @@ struct bl_msg_hdr {
 	u16 totallen; /* length of entire message, including hdr itself */
 };
 
-extern struct dentry *bl_device_pipe;
-extern wait_queue_head_t bl_wq;
-
 #define BL_DEVICE_UMOUNT               0x0 /* Umount--delete devices */
 #define BL_DEVICE_MOUNT                0x1 /* Mount--create devices*/
 #define BL_DEVICE_REQUEST_INIT         0x0 /* Start request */

fs/nfs/blocklayout/blocklayoutdev.c

@@ -46,7 +46,7 @@ static int decode_sector_number(__be32 **rp, sector_t *sp)
 
 	*rp = xdr_decode_hyper(*rp, &s);
 	if (s & 0x1ff) {
-		printk(KERN_WARNING "%s: sector not aligned\n", __func__);
+		printk(KERN_WARNING "NFS: %s: sector not aligned\n", __func__);
 		return -1;
 	}
 	*sp = s >> SECTOR_SHIFT;
@@ -79,27 +79,30 @@ int nfs4_blkdev_put(struct block_device *bdev)
 	return blkdev_put(bdev, FMODE_READ);
 }
 
-static struct bl_dev_msg bl_mount_reply;
-
 ssize_t bl_pipe_downcall(struct file *filp, const char __user *src,
 			 size_t mlen)
 {
+	struct nfs_net *nn = net_generic(filp->f_dentry->d_sb->s_fs_info,
+					 nfs_net_id);
+
 	if (mlen != sizeof (struct bl_dev_msg))
 		return -EINVAL;
 
-	if (copy_from_user(&bl_mount_reply, src, mlen) != 0)
+	if (copy_from_user(&nn->bl_mount_reply, src, mlen) != 0)
 		return -EFAULT;
 
-	wake_up(&bl_wq);
+	wake_up(&nn->bl_wq);
 
 	return mlen;
 }
 
 void bl_pipe_destroy_msg(struct rpc_pipe_msg *msg)
 {
+	struct bl_pipe_msg *bl_pipe_msg = container_of(msg, struct bl_pipe_msg, msg);
+
 	if (msg->errno >= 0)
 		return;
-	wake_up(&bl_wq);
+	wake_up(bl_pipe_msg->bl_wq);
 }
 
 /*
@@ -111,29 +114,33 @@ nfs4_blk_decode_device(struct nfs_server *server,
 {
 	struct pnfs_block_dev *rv;
 	struct block_device *bd = NULL;
-	struct rpc_pipe_msg msg;
+	struct bl_pipe_msg bl_pipe_msg;
+	struct rpc_pipe_msg *msg = &bl_pipe_msg.msg;
 	struct bl_msg_hdr bl_msg = {
 		.type = BL_DEVICE_MOUNT,
 		.totallen = dev->mincount,
 	};
 	uint8_t *dataptr;
 	DECLARE_WAITQUEUE(wq, current);
-	struct bl_dev_msg *reply = &bl_mount_reply;
 	int offset, len, i, rc;
+	struct net *net = server->nfs_client->net;
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+	struct bl_dev_msg *reply = &nn->bl_mount_reply;
 
 	dprintk("%s CREATING PIPEFS MESSAGE\n", __func__);
 	dprintk("%s: deviceid: %s, mincount: %d\n", __func__, dev->dev_id.data,
 		dev->mincount);
 
-	memset(&msg, 0, sizeof(msg));
-	msg.data = kzalloc(sizeof(bl_msg) + dev->mincount, GFP_NOFS);
-	if (!msg.data) {
+	bl_pipe_msg.bl_wq = &nn->bl_wq;
+	memset(msg, 0, sizeof(*msg));
+	msg->data = kzalloc(sizeof(bl_msg) + dev->mincount, GFP_NOFS);
+	if (!msg->data) {
 		rv = ERR_PTR(-ENOMEM);
 		goto out;
 	}
 
-	memcpy(msg.data, &bl_msg, sizeof(bl_msg));
-	dataptr = (uint8_t *) msg.data;
+	memcpy(msg->data, &bl_msg, sizeof(bl_msg));
+	dataptr = (uint8_t *) msg->data;
 	len = dev->mincount;
 	offset = sizeof(bl_msg);
 	for (i = 0; len > 0; i++) {
@@ -142,13 +149,13 @@ nfs4_blk_decode_device(struct nfs_server *server,
 		len -= PAGE_CACHE_SIZE;
 		offset += PAGE_CACHE_SIZE;
 	}
-	msg.len = sizeof(bl_msg) + dev->mincount;
+	msg->len = sizeof(bl_msg) + dev->mincount;
 
 	dprintk("%s CALLING USERSPACE DAEMON\n", __func__);
-	add_wait_queue(&bl_wq, &wq);
-	rc = rpc_queue_upcall(bl_device_pipe->d_inode, &msg);
+	add_wait_queue(&nn->bl_wq, &wq);
+	rc = rpc_queue_upcall(nn->bl_device_pipe, msg);
 	if (rc < 0) {
-		remove_wait_queue(&bl_wq, &wq);
+		remove_wait_queue(&nn->bl_wq, &wq);
 		rv = ERR_PTR(rc);
 		goto out;
 	}
@@ -156,7 +163,7 @@ nfs4_blk_decode_device(struct nfs_server *server,
 	set_current_state(TASK_UNINTERRUPTIBLE);
 	schedule();
 	__set_current_state(TASK_RUNNING);
-	remove_wait_queue(&bl_wq, &wq);
+	remove_wait_queue(&nn->bl_wq, &wq);
 
 	if (reply->status != BL_DEVICE_REQUEST_PROC) {
 		dprintk("%s failed to open device: %d\n",
@@ -181,13 +188,14 @@ nfs4_blk_decode_device(struct nfs_server *server,
 
 	rv->bm_mdev = bd;
 	memcpy(&rv->bm_mdevid, &dev->dev_id, sizeof(struct nfs4_deviceid));
+	rv->net = net;
 	dprintk("%s Created device %s with bd_block_size %u\n",
 		__func__,
 		bd->bd_disk->disk_name,
 		bd->bd_block_size);
 
 out:
-	kfree(msg.data);
+	kfree(msg->data);
 	return rv;
 }
 

fs/nfs/blocklayout/blocklayoutdm.c

@@ -38,9 +38,10 @@
 
 #define NFSDBG_FACILITY         NFSDBG_PNFS_LD
 
-static void dev_remove(dev_t dev)
+static void dev_remove(struct net *net, dev_t dev)
 {
-	struct rpc_pipe_msg msg;
+	struct bl_pipe_msg bl_pipe_msg;
+	struct rpc_pipe_msg *msg = &bl_pipe_msg.msg;
 	struct bl_dev_msg bl_umount_request;
 	struct bl_msg_hdr bl_msg = {
 		.type = BL_DEVICE_UMOUNT,
@@ -48,36 +49,38 @@ static void dev_remove(dev_t dev)
 	};
 	uint8_t *dataptr;
 	DECLARE_WAITQUEUE(wq, current);
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
 
 	dprintk("Entering %s\n", __func__);
 
-	memset(&msg, 0, sizeof(msg));
-	msg.data = kzalloc(1 + sizeof(bl_umount_request), GFP_NOFS);
-	if (!msg.data)
+	bl_pipe_msg.bl_wq = &nn->bl_wq;
+	memset(msg, 0, sizeof(*msg));
+	msg->data = kzalloc(1 + sizeof(bl_umount_request), GFP_NOFS);
+	if (!msg->data)
 		goto out;
 
 	memset(&bl_umount_request, 0, sizeof(bl_umount_request));
 	bl_umount_request.major = MAJOR(dev);
 	bl_umount_request.minor = MINOR(dev);
 
-	memcpy(msg.data, &bl_msg, sizeof(bl_msg));
-	dataptr = (uint8_t *) msg.data;
+	memcpy(msg->data, &bl_msg, sizeof(bl_msg));
+	dataptr = (uint8_t *) msg->data;
 	memcpy(&dataptr[sizeof(bl_msg)], &bl_umount_request, sizeof(bl_umount_request));
-	msg.len = sizeof(bl_msg) + bl_msg.totallen;
+	msg->len = sizeof(bl_msg) + bl_msg.totallen;
 
-	add_wait_queue(&bl_wq, &wq);
-	if (rpc_queue_upcall(bl_device_pipe->d_inode, &msg) < 0) {
-		remove_wait_queue(&bl_wq, &wq);
+	add_wait_queue(&nn->bl_wq, &wq);
+	if (rpc_queue_upcall(nn->bl_device_pipe, msg) < 0) {
+		remove_wait_queue(&nn->bl_wq, &wq);
 		goto out;
 	}
 
 	set_current_state(TASK_UNINTERRUPTIBLE);
 	schedule();
 	__set_current_state(TASK_RUNNING);
-	remove_wait_queue(&bl_wq, &wq);
+	remove_wait_queue(&nn->bl_wq, &wq);
 
 out:
-	kfree(msg.data);
+	kfree(msg->data);
 }
 
 /*
@@ -90,10 +93,10 @@ static void nfs4_blk_metadev_release(struct pnfs_block_dev *bdev)
 	dprintk("%s Releasing\n", __func__);
 	rv = nfs4_blkdev_put(bdev->bm_mdev);
 	if (rv)
-		printk(KERN_ERR "%s nfs4_blkdev_put returns %d\n",
+		printk(KERN_ERR "NFS: %s nfs4_blkdev_put returns %d\n",
 				__func__, rv);
 
-	dev_remove(bdev->bm_mdev->bd_dev);
+	dev_remove(bdev->net, bdev->bm_mdev->bd_dev);
 }
 
 void bl_free_block_dev(struct pnfs_block_dev *bdev)

fs/nfs/blocklayout/extents.c

@@ -147,7 +147,7 @@ static int _preload_range(struct pnfs_inval_markings *marks,
 	count = (int)(end - start) / (int)tree->mtt_step_size;
 
 	/* Pre-malloc what memory we might need */
-	storage = kmalloc(sizeof(*storage) * count, GFP_NOFS);
+	storage = kcalloc(count, sizeof(*storage), GFP_NOFS);
 	if (!storage)
 		return -ENOMEM;
 	for (i = 0; i < count; i++) {

fs/nfs/cache_lib.c

@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/sunrpc/cache.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
+#include <net/net_namespace.h>
 
 #include "cache_lib.h"
 
@@ -111,30 +112,54 @@ int nfs_cache_wait_for_upcall(struct nfs_cache_defer_req *dreq)
 	return 0;
 }
 
-int nfs_cache_register(struct cache_detail *cd)
+int nfs_cache_register_sb(struct super_block *sb, struct cache_detail *cd)
 {
-	struct vfsmount *mnt;
-	struct path path;
 	int ret;
+	struct dentry *dir;
 
-	mnt = rpc_get_mount();
-	if (IS_ERR(mnt))
-		return PTR_ERR(mnt);
-	ret = vfs_path_lookup(mnt->mnt_root, mnt, "/cache", 0, &path);
-	if (ret)
-		goto err;
-	ret = sunrpc_cache_register_pipefs(path.dentry, cd->name, 0600, cd);
-	path_put(&path);
-	if (!ret)
-		return ret;
-err:
-	rpc_put_mount();
+	dir = rpc_d_lookup_sb(sb, "cache");
+	BUG_ON(dir == NULL);
+	ret = sunrpc_cache_register_pipefs(dir, cd->name, 0600, cd);
+	dput(dir);
 	return ret;
 }
 
-void nfs_cache_unregister(struct cache_detail *cd)
+int nfs_cache_register_net(struct net *net, struct cache_detail *cd)
 {
-	sunrpc_cache_unregister_pipefs(cd);
-	rpc_put_mount();
+	struct super_block *pipefs_sb;
+	int ret = 0;
+
+	pipefs_sb = rpc_get_sb_net(net);
+	if (pipefs_sb) {
+		ret = nfs_cache_register_sb(pipefs_sb, cd);
+		rpc_put_sb_net(net);
+	}
+	return ret;
+}
+
+void nfs_cache_unregister_sb(struct super_block *sb, struct cache_detail *cd)
+{
+	if (cd->u.pipefs.dir)
+		sunrpc_cache_unregister_pipefs(cd);
+}
+
+void nfs_cache_unregister_net(struct net *net, struct cache_detail *cd)
+{
+	struct super_block *pipefs_sb;
+
+	pipefs_sb = rpc_get_sb_net(net);
+	if (pipefs_sb) {
+		nfs_cache_unregister_sb(pipefs_sb, cd);
+		rpc_put_sb_net(net);
+	}
+}
+
+void nfs_cache_init(struct cache_detail *cd)
+{
+	sunrpc_init_cache_detail(cd);
 }
 
+void nfs_cache_destroy(struct cache_detail *cd)
+{
+	sunrpc_destroy_cache_detail(cd);
+}

fs/nfs/cache_lib.h

@@ -23,5 +23,11 @@ extern struct nfs_cache_defer_req *nfs_cache_defer_req_alloc(void);
 extern void nfs_cache_defer_req_put(struct nfs_cache_defer_req *dreq);
 extern int nfs_cache_wait_for_upcall(struct nfs_cache_defer_req *dreq);
 
-extern int nfs_cache_register(struct cache_detail *cd);
-extern void nfs_cache_unregister(struct cache_detail *cd);
+extern void nfs_cache_init(struct cache_detail *cd);
+extern void nfs_cache_destroy(struct cache_detail *cd);
+extern int nfs_cache_register_net(struct net *net, struct cache_detail *cd);
+extern void nfs_cache_unregister_net(struct net *net, struct cache_detail *cd);
+extern int nfs_cache_register_sb(struct super_block *sb,
+				 struct cache_detail *cd);
+extern void nfs_cache_unregister_sb(struct super_block *sb,
+				    struct cache_detail *cd);

fs/nfs/callback.c

@@ -85,7 +85,7 @@ nfs4_callback_svc(void *vrqstp)
 		}
 		if (err < 0) {
 			if (err != preverr) {
-				printk(KERN_WARNING "%s: unexpected error "
+				printk(KERN_WARNING "NFS: %s: unexpected error "
 					"from svc_recv (%d)\n", __func__, err);
 				preverr = err;
 			}
@@ -101,12 +101,12 @@ nfs4_callback_svc(void *vrqstp)
 /*
  * Prepare to bring up the NFSv4 callback service
  */
-struct svc_rqst *
-nfs4_callback_up(struct svc_serv *serv)
+static struct svc_rqst *
+nfs4_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt)
 {
 	int ret;
 
-	ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET,
+	ret = svc_create_xprt(serv, "tcp", xprt->xprt_net, PF_INET,
 				nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
 	if (ret <= 0)
 		goto out_err;
@@ -114,7 +114,7 @@ nfs4_callback_up(struct svc_serv *serv)
 	dprintk("NFS: Callback listener port = %u (af %u)\n",
 			nfs_callback_tcpport, PF_INET);
 
-	ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET6,
+	ret = svc_create_xprt(serv, "tcp", xprt->xprt_net, PF_INET6,
 				nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
 	if (ret > 0) {
 		nfs_callback_tcpport6 = ret;
@@ -172,7 +172,7 @@ nfs41_callback_svc(void *vrqstp)
 /*
  * Bring up the NFSv4.1 callback service
  */
-struct svc_rqst *
+static struct svc_rqst *
 nfs41_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt)
 {
 	struct svc_rqst *rqstp;
@@ -183,7 +183,7 @@ nfs41_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt)
 	 * fore channel connection.
 	 * Returns the input port (0) and sets the svc_serv bc_xprt on success
 	 */
-	ret = svc_create_xprt(serv, "tcp-bc", &init_net, PF_INET, 0,
+	ret = svc_create_xprt(serv, "tcp-bc", xprt->xprt_net, PF_INET, 0,
 			      SVC_SOCK_ANONYMOUS);
 	if (ret < 0) {
 		rqstp = ERR_PTR(ret);
@@ -269,7 +269,7 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt)
 					serv, xprt, &rqstp, &callback_svc);
 	if (!minorversion_setup) {
 		/* v4.0 callback setup */
-		rqstp = nfs4_callback_up(serv);
+		rqstp = nfs4_callback_up(serv, xprt);
 		callback_svc = nfs4_callback_svc;
 	}
 
@@ -332,7 +332,6 @@ void nfs_callback_down(int minorversion)
 int
 check_gss_callback_principal(struct nfs_client *clp, struct svc_rqst *rqstp)
 {
-	struct rpc_clnt *r = clp->cl_rpcclient;
 	char *p = svc_gss_principal(rqstp);
 
 	if (rqstp->rq_authop->flavour != RPC_AUTH_GSS)
@@ -353,7 +352,7 @@ check_gss_callback_principal(struct nfs_client *clp, struct svc_rqst *rqstp)
 	if (memcmp(p, "nfs@", 4) != 0)
 		return 0;
 	p += 4;
-	if (strcmp(p, r->cl_server) != 0)
+	if (strcmp(p, clp->cl_hostname) != 0)
 		return 0;
 	return 1;
 }

fs/nfs/callback.h

@@ -38,7 +38,8 @@ enum nfs4_callback_opnum {
 struct cb_process_state {
 	__be32			drc_status;
 	struct nfs_client	*clp;
-	int			slotid;
+	u32			slotid;
+	struct net		*net;
 };
 
 struct cb_compound_hdr_arg {

fs/nfs/callback_proc.c

@@ -8,6 +8,7 @@
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
 #include <linux/slab.h>
+#include <linux/rcupdate.h>
 #include "nfs4_fs.h"
 #include "callback.h"
 #include "delegation.h"
@@ -33,7 +34,7 @@ __be32 nfs4_callback_getattr(struct cb_getattrargs *args,
 	res->bitmap[0] = res->bitmap[1] = 0;
 	res->status = htonl(NFS4ERR_BADHANDLE);
 
-	dprintk("NFS: GETATTR callback request from %s\n",
+	dprintk_rcu("NFS: GETATTR callback request from %s\n",
 		rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR));
 
 	inode = nfs_delegation_find_inode(cps->clp, &args->fh);
@@ -73,7 +74,7 @@ __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy,
 	if (!cps->clp) /* Always set for v4.0. Set in cb_sequence for v4.1 */
 		goto out;
 
-	dprintk("NFS: RECALL callback request from %s\n",
+	dprintk_rcu("NFS: RECALL callback request from %s\n",
 		rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR));
 
 	res = htonl(NFS4ERR_BADHANDLE);
@@ -86,8 +87,7 @@ __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy,
 		res = 0;
 		break;
 	case -ENOENT:
-		if (res != 0)
-			res = htonl(NFS4ERR_BAD_STATEID);
+		res = htonl(NFS4ERR_BAD_STATEID);
 		break;
 	default:
 		res = htonl(NFS4ERR_RESOURCE);
@@ -98,52 +98,64 @@ out:
 	return res;
 }
 
-int nfs4_validate_delegation_stateid(struct nfs_delegation *delegation, const nfs4_stateid *stateid)
-{
-	if (delegation == NULL || memcmp(delegation->stateid.data, stateid->data,
-					 sizeof(delegation->stateid.data)) != 0)
-		return 0;
-	return 1;
-}
-
 #if defined(CONFIG_NFS_V4_1)
 
-static u32 initiate_file_draining(struct nfs_client *clp,
-				  struct cb_layoutrecallargs *args)
+/*
+ * Lookup a layout by filehandle.
+ *
+ * Note: gets a refcount on the layout hdr and on its respective inode.
+ * Caller must put the layout hdr and the inode.
+ *
+ * TODO: keep track of all layouts (and delegations) in a hash table
+ * hashed by filehandle.
+ */
+static struct pnfs_layout_hdr * get_layout_by_fh_locked(struct nfs_client *clp, struct nfs_fh *fh)
 {
 	struct nfs_server *server;
-	struct pnfs_layout_hdr *lo;
 	struct inode *ino;
-	bool found = false;
-	u32 rv = NFS4ERR_NOMATCHING_LAYOUT;
-	LIST_HEAD(free_me_list);
+	struct pnfs_layout_hdr *lo;
 
-	spin_lock(&clp->cl_lock);
-	rcu_read_lock();
 	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
 		list_for_each_entry(lo, &server->layouts, plh_layouts) {
-			if (nfs_compare_fh(&args->cbl_fh,
-					   &NFS_I(lo->plh_inode)->fh))
+			if (nfs_compare_fh(fh, &NFS_I(lo->plh_inode)->fh))
 				continue;
 			ino = igrab(lo->plh_inode);
 			if (!ino)
 				continue;
-			found = true;
-			/* Without this, layout can be freed as soon
-			 * as we release cl_lock.
-			 */
 			get_layout_hdr(lo);
-			break;
+			return lo;
 		}
-		if (found)
-			break;
 	}
+
+	return NULL;
+}
+
+static struct pnfs_layout_hdr * get_layout_by_fh(struct nfs_client *clp, struct nfs_fh *fh)
+{
+	struct pnfs_layout_hdr *lo;
+
+	spin_lock(&clp->cl_lock);
+	rcu_read_lock();
+	lo = get_layout_by_fh_locked(clp, fh);
 	rcu_read_unlock();
 	spin_unlock(&clp->cl_lock);
 
-	if (!found)
+	return lo;
+}
+
+static u32 initiate_file_draining(struct nfs_client *clp,
+				  struct cb_layoutrecallargs *args)
+{
+	struct inode *ino;
+	struct pnfs_layout_hdr *lo;
+	u32 rv = NFS4ERR_NOMATCHING_LAYOUT;
+	LIST_HEAD(free_me_list);
+
+	lo = get_layout_by_fh(clp, &args->cbl_fh);
+	if (!lo)
 		return NFS4ERR_NOMATCHING_LAYOUT;
 
+	ino = lo->plh_inode;
 	spin_lock(&ino->i_lock);
 	if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) ||
 	    mark_matching_lsegs_invalid(lo, &free_me_list,
@@ -213,17 +225,13 @@ static u32 initiate_bulk_draining(struct nfs_client *clp,
 static u32 do_callback_layoutrecall(struct nfs_client *clp,
 				    struct cb_layoutrecallargs *args)
 {
-	u32 res = NFS4ERR_DELAY;
+	u32 res;
 
 	dprintk("%s enter, type=%i\n", __func__, args->cbl_recall_type);
-	if (test_and_set_bit(NFS4CLNT_LAYOUTRECALL, &clp->cl_state))
-		goto out;
 	if (args->cbl_recall_type == RETURN_FILE)
 		res = initiate_file_draining(clp, args);
 	else
 		res = initiate_bulk_draining(clp, args);
-	clear_bit(NFS4CLNT_LAYOUTRECALL, &clp->cl_state);
-out:
 	dprintk("%s returning %i\n", __func__, res);
 	return res;
 
@@ -303,21 +311,6 @@ out:
 	return res;
 }
 
-int nfs41_validate_delegation_stateid(struct nfs_delegation *delegation, const nfs4_stateid *stateid)
-{
-	if (delegation == NULL)
-		return 0;
-
-	if (stateid->stateid.seqid != 0)
-		return 0;
-	if (memcmp(&delegation->stateid.stateid.other,
-		   &stateid->stateid.other,
-		   NFS4_STATEID_OTHER_SIZE))
-		return 0;
-
-	return 1;
-}
-
 /*
  * Validate the sequenceID sent by the server.
  * Return success if the sequenceID is one more than what we last saw on
@@ -441,7 +434,7 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
 	int i;
 	__be32 status = htonl(NFS4ERR_BADSESSION);
 
-	clp = nfs4_find_client_sessionid(args->csa_addr, &args->csa_sessionid);
+	clp = nfs4_find_client_sessionid(cps->net, args->csa_addr, &args->csa_sessionid);
 	if (clp == NULL)
 		goto out;
 
@@ -517,7 +510,7 @@ __be32 nfs4_callback_recallany(struct cb_recallanyargs *args, void *dummy,
 	if (!cps->clp) /* set in cb_sequence */
 		goto out;
 
-	dprintk("NFS: RECALL_ANY callback request from %s\n",
+	dprintk_rcu("NFS: RECALL_ANY callback request from %s\n",
 		rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR));
 
 	status = cpu_to_be32(NFS4ERR_INVAL);
@@ -552,7 +545,7 @@ __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, void *dummy,
 	if (!cps->clp) /* set in cb_sequence */
 		goto out;
 
-	dprintk("NFS: CB_RECALL_SLOT request from %s target max slots %d\n",
+	dprintk_rcu("NFS: CB_RECALL_SLOT request from %s target max slots %d\n",
 		rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR),
 		args->crsa_target_max_slots);
 

fs/nfs/callback_xdr.c

@@ -9,6 +9,8 @@
 #include <linux/sunrpc/svc.h>
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
+#include <linux/ratelimit.h>
+#include <linux/printk.h>
 #include <linux/slab.h>
 #include <linux/sunrpc/bc_xprt.h>
 #include "nfs4_fs.h"
@@ -73,7 +75,7 @@ static __be32 *read_buf(struct xdr_stream *xdr, int nbytes)
 
 	p = xdr_inline_decode(xdr, nbytes);
 	if (unlikely(p == NULL))
-		printk(KERN_WARNING "NFSv4 callback reply buffer overflowed!\n");
+		printk(KERN_WARNING "NFS: NFSv4 callback reply buffer overflowed!\n");
 	return p;
 }
 
@@ -138,10 +140,10 @@ static __be32 decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
 {
 	__be32 *p;
 
-	p = read_buf(xdr, 16);
+	p = read_buf(xdr, NFS4_STATEID_SIZE);
 	if (unlikely(p == NULL))
 		return htonl(NFS4ERR_RESOURCE);
-	memcpy(stateid->data, p, 16);
+	memcpy(stateid, p, NFS4_STATEID_SIZE);
 	return 0;
 }
 
@@ -155,7 +157,7 @@ static __be32 decode_compound_hdr_arg(struct xdr_stream *xdr, struct cb_compound
 		return status;
 	/* We do not like overly long tags! */
 	if (hdr->taglen > CB_OP_TAGLEN_MAXSZ - 12) {
-		printk("NFSv4 CALLBACK %s: client sent tag of length %u\n",
+		printk("NFS: NFSv4 CALLBACK %s: client sent tag of length %u\n",
 				__func__, hdr->taglen);
 		return htonl(NFS4ERR_RESOURCE);
 	}
@@ -167,7 +169,7 @@ static __be32 decode_compound_hdr_arg(struct xdr_stream *xdr, struct cb_compound
 	if (hdr->minorversion <= 1) {
 		hdr->cb_ident = ntohl(*p++); /* ignored by v4.1 */
 	} else {
-		printk(KERN_WARNING "%s: NFSv4 server callback with "
+		pr_warn_ratelimited("NFS: %s: NFSv4 server callback with "
 			"illegal minor version %u!\n",
 			__func__, hdr->minorversion);
 		return htonl(NFS4ERR_MINOR_VERS_MISMATCH);
@@ -759,14 +761,14 @@ static void nfs4_callback_free_slot(struct nfs4_session *session)
 	 * Let the state manager know callback processing done.
 	 * A single slot, so highest used slotid is either 0 or -1
 	 */
-	tbl->highest_used_slotid = -1;
+	tbl->highest_used_slotid = NFS4_NO_SLOT;
 	nfs4_check_drain_bc_complete(session);
 	spin_unlock(&tbl->slot_tbl_lock);
 }
 
 static void nfs4_cb_free_slot(struct cb_process_state *cps)
 {
-	if (cps->slotid != -1)
+	if (cps->slotid != NFS4_NO_SLOT)
 		nfs4_callback_free_slot(cps->clp->cl_session);
 }
 
@@ -860,7 +862,8 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 	struct cb_process_state cps = {
 		.drc_status = 0,
 		.clp = NULL,
-		.slotid = -1,
+		.slotid = NFS4_NO_SLOT,
+		.net = rqstp->rq_xprt->xpt_net,
 	};
 	unsigned int nops = 0;
 
@@ -876,7 +879,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 		return rpc_garbage_args;
 
 	if (hdr_arg.minorversion == 0) {
-		cps.clp = nfs4_find_client_ident(hdr_arg.cb_ident);
+		cps.clp = nfs4_find_client_ident(rqstp->rq_xprt->xpt_net, hdr_arg.cb_ident);
 		if (!cps.clp || !check_gss_callback_principal(cps.clp, rqstp))
 			return rpc_drop_reply;
 	}

fs/nfs/client.c

@@ -39,6 +39,8 @@
 #include <net/ipv6.h>
 #include <linux/nfs_xdr.h>
 #include <linux/sunrpc/bc_xprt.h>
+#include <linux/nsproxy.h>
+#include <linux/pid_namespace.h>
 
 #include <asm/system.h>
 
@@ -49,15 +51,12 @@
 #include "internal.h"
 #include "fscache.h"
 #include "pnfs.h"
+#include "netns.h"
 
 #define NFSDBG_FACILITY		NFSDBG_CLIENT
 
-static DEFINE_SPINLOCK(nfs_client_lock);
-static LIST_HEAD(nfs_client_list);
-static LIST_HEAD(nfs_volume_list);
 static DECLARE_WAIT_QUEUE_HEAD(nfs_client_active_wq);
 #ifdef CONFIG_NFS_V4
-static DEFINE_IDR(cb_ident_idr); /* Protected by nfs_client_lock */
 
 /*
  * Get a unique NFSv4.0 callback identifier which will be used
@@ -66,15 +65,16 @@ static DEFINE_IDR(cb_ident_idr); /* Protected by nfs_client_lock */
 static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion)
 {
 	int ret = 0;
+	struct nfs_net *nn = net_generic(clp->net, nfs_net_id);
 
 	if (clp->rpc_ops->version != 4 || minorversion != 0)
 		return ret;
 retry:
-	if (!idr_pre_get(&cb_ident_idr, GFP_KERNEL))
+	if (!idr_pre_get(&nn->cb_ident_idr, GFP_KERNEL))
 		return -ENOMEM;
-	spin_lock(&nfs_client_lock);
-	ret = idr_get_new(&cb_ident_idr, clp, &clp->cl_cb_ident);
-	spin_unlock(&nfs_client_lock);
+	spin_lock(&nn->nfs_client_lock);
+	ret = idr_get_new(&nn->cb_ident_idr, clp, &clp->cl_cb_ident);
+	spin_unlock(&nn->nfs_client_lock);
 	if (ret == -EAGAIN)
 		goto retry;
 	return ret;
@@ -89,7 +89,7 @@ static bool nfs4_disable_idmapping = true;
 /*
  * RPC cruft for NFS
  */
-static struct rpc_version *nfs_version[5] = {
+static const struct rpc_version *nfs_version[5] = {
 	[2]			= &nfs_version2,
 #ifdef CONFIG_NFS_V3
 	[3]			= &nfs_version3,
@@ -99,7 +99,7 @@ static struct rpc_version *nfs_version[5] = {
 #endif
 };
 
-struct rpc_program nfs_program = {
+const struct rpc_program nfs_program = {
 	.name			= "nfs",
 	.number			= NFS_PROGRAM,
 	.nrvers			= ARRAY_SIZE(nfs_version),
@@ -115,11 +115,11 @@ struct rpc_stat nfs_rpcstat = {
 
 #ifdef CONFIG_NFS_V3_ACL
 static struct rpc_stat		nfsacl_rpcstat = { &nfsacl_program };
-static struct rpc_version *	nfsacl_version[] = {
+static const struct rpc_version *nfsacl_version[] = {
 	[3]			= &nfsacl_version3,
 };
 
-struct rpc_program		nfsacl_program = {
+const struct rpc_program nfsacl_program = {
 	.name			= "nfsacl",
 	.number			= NFS_ACL_PROGRAM,
 	.nrvers			= ARRAY_SIZE(nfsacl_version),
@@ -135,6 +135,7 @@ struct nfs_client_initdata {
 	const struct nfs_rpc_ops *rpc_ops;
 	int proto;
 	u32 minorversion;
+	struct net *net;
 };
 
 /*
@@ -171,6 +172,7 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 	clp->cl_rpcclient = ERR_PTR(-EINVAL);
 
 	clp->cl_proto = cl_init->proto;
+	clp->net = get_net(cl_init->net);
 
 #ifdef CONFIG_NFS_V4
 	err = nfs_get_cb_ident_idr(clp, cl_init->minorversion);
@@ -202,8 +204,11 @@ error_0:
 #ifdef CONFIG_NFS_V4_1
 static void nfs4_shutdown_session(struct nfs_client *clp)
 {
-	if (nfs4_has_session(clp))
+	if (nfs4_has_session(clp)) {
+		nfs4_deviceid_purge_client(clp);
 		nfs4_destroy_session(clp->cl_session);
+	}
+
 }
 #else /* CONFIG_NFS_V4_1 */
 static void nfs4_shutdown_session(struct nfs_client *clp)
@@ -233,16 +238,20 @@ static void nfs4_shutdown_client(struct nfs_client *clp)
 }
 
 /* idr_remove_all is not needed as all id's are removed by nfs_put_client */
-void nfs_cleanup_cb_ident_idr(void)
+void nfs_cleanup_cb_ident_idr(struct net *net)
 {
-	idr_destroy(&cb_ident_idr);
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+	idr_destroy(&nn->cb_ident_idr);
 }
 
 /* nfs_client_lock held */
 static void nfs_cb_idr_remove_locked(struct nfs_client *clp)
 {
+	struct nfs_net *nn = net_generic(clp->net, nfs_net_id);
+
 	if (clp->cl_cb_ident)
-		idr_remove(&cb_ident_idr, clp->cl_cb_ident);
+		idr_remove(&nn->cb_ident_idr, clp->cl_cb_ident);
 }
 
 static void pnfs_init_server(struct nfs_server *server)
@@ -260,7 +269,7 @@ static void nfs4_shutdown_client(struct nfs_client *clp)
 {
 }
 
-void nfs_cleanup_cb_ident_idr(void)
+void nfs_cleanup_cb_ident_idr(struct net *net)
 {
 }
 
@@ -292,10 +301,10 @@ static void nfs_free_client(struct nfs_client *clp)
 	if (clp->cl_machine_cred != NULL)
 		put_rpccred(clp->cl_machine_cred);
 
-	nfs4_deviceid_purge_client(clp);
-
+	put_net(clp->net);
 	kfree(clp->cl_hostname);
 	kfree(clp->server_scope);
+	kfree(clp->impl_id);
 	kfree(clp);
 
 	dprintk("<-- nfs_free_client()\n");
@@ -306,15 +315,18 @@ static void nfs_free_client(struct nfs_client *clp)
  */
 void nfs_put_client(struct nfs_client *clp)
 {
+	struct nfs_net *nn;
+
 	if (!clp)
 		return;
 
 	dprintk("--> nfs_put_client({%d})\n", atomic_read(&clp->cl_count));
+	nn = net_generic(clp->net, nfs_net_id);
 
-	if (atomic_dec_and_lock(&clp->cl_count, &nfs_client_lock)) {
+	if (atomic_dec_and_lock(&clp->cl_count, &nn->nfs_client_lock)) {
 		list_del(&clp->cl_share_link);
 		nfs_cb_idr_remove_locked(clp);
-		spin_unlock(&nfs_client_lock);
+		spin_unlock(&nn->nfs_client_lock);
 
 		BUG_ON(!list_empty(&clp->cl_superblocks));
 
@@ -392,6 +404,7 @@ static int nfs_sockaddr_cmp_ip4(const struct sockaddr *sa1,
 		(sin1->sin_port == sin2->sin_port);
 }
 
+#if defined(CONFIG_NFS_V4_1)
 /*
  * Test if two socket addresses represent the same actual socket,
  * by comparing (only) relevant fields, excluding the port number.
@@ -410,6 +423,7 @@ static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
 	}
 	return 0;
 }
+#endif /* CONFIG_NFS_V4_1 */
 
 /*
  * Test if two socket addresses represent the same actual socket,
@@ -430,10 +444,10 @@ static int nfs_sockaddr_cmp(const struct sockaddr *sa1,
 	return 0;
 }
 
+#if defined(CONFIG_NFS_V4_1)
 /* Common match routine for v4.0 and v4.1 callback services */
-bool
-nfs4_cb_match_client(const struct sockaddr *addr, struct nfs_client *clp,
-		     u32 minorversion)
+static bool nfs4_cb_match_client(const struct sockaddr *addr,
+		struct nfs_client *clp, u32 minorversion)
 {
 	struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr;
 
@@ -453,6 +467,7 @@ nfs4_cb_match_client(const struct sockaddr *addr, struct nfs_client *clp,
 
 	return true;
 }
+#endif /* CONFIG_NFS_V4_1 */
 
 /*
  * Find an nfs_client on the list that matches the initialisation data
@@ -462,8 +477,9 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
 {
 	struct nfs_client *clp;
 	const struct sockaddr *sap = data->addr;
+	struct nfs_net *nn = net_generic(data->net, nfs_net_id);
 
-	list_for_each_entry(clp, &nfs_client_list, cl_share_link) {
+	list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
 	        const struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr;
 		/* Don't match clients that failed to initialise properly */
 		if (clp->cl_cons_state < 0)
@@ -501,13 +517,14 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
 {
 	struct nfs_client *clp, *new = NULL;
 	int error;
+	struct nfs_net *nn = net_generic(cl_init->net, nfs_net_id);
 
 	dprintk("--> nfs_get_client(%s,v%u)\n",
 		cl_init->hostname ?: "", cl_init->rpc_ops->version);
 
 	/* see if the client already exists */
 	do {
-		spin_lock(&nfs_client_lock);
+		spin_lock(&nn->nfs_client_lock);
 
 		clp = nfs_match_client(cl_init);
 		if (clp)
@@ -515,7 +532,7 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
 		if (new)
 			goto install_client;
 
-		spin_unlock(&nfs_client_lock);
+		spin_unlock(&nn->nfs_client_lock);
 
 		new = nfs_alloc_client(cl_init);
 	} while (!IS_ERR(new));
@@ -526,8 +543,8 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
 	/* install a new client and return with it unready */
 install_client:
 	clp = new;
-	list_add(&clp->cl_share_link, &nfs_client_list);
-	spin_unlock(&nfs_client_lock);
+	list_add(&clp->cl_share_link, &nn->nfs_client_list);
+	spin_unlock(&nn->nfs_client_lock);
 
 	error = cl_init->rpc_ops->init_client(clp, timeparms, ip_addr,
 					      authflavour, noresvport);
@@ -542,7 +559,7 @@ install_client:
 	 * - make sure it's ready before returning
 	 */
 found_client:
-	spin_unlock(&nfs_client_lock);
+	spin_unlock(&nn->nfs_client_lock);
 
 	if (new)
 		nfs_free_client(new);
@@ -642,7 +659,7 @@ static int nfs_create_rpc_client(struct nfs_client *clp,
 {
 	struct rpc_clnt		*clnt = NULL;
 	struct rpc_create_args args = {
-		.net		= &init_net,
+		.net		= clp->net,
 		.protocol	= clp->cl_proto,
 		.address	= (struct sockaddr *)&clp->cl_addr,
 		.addrsize	= clp->cl_addrlen,
@@ -696,6 +713,7 @@ static int nfs_start_lockd(struct nfs_server *server)
 		.nfs_version	= clp->rpc_ops->version,
 		.noresvport	= server->flags & NFS_MOUNT_NORESVPORT ?
 					1 : 0,
+		.net		= clp->net,
 	};
 
 	if (nlm_init.nfs_version > 3)
@@ -831,6 +849,7 @@ static int nfs_init_server(struct nfs_server *server,
 		.addrlen = data->nfs_server.addrlen,
 		.rpc_ops = &nfs_v2_clientops,
 		.proto = data->nfs_server.protocol,
+		.net = data->net,
 	};
 	struct rpc_timeout timeparms;
 	struct nfs_client *clp;
@@ -1029,25 +1048,30 @@ static void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_serve
 static void nfs_server_insert_lists(struct nfs_server *server)
 {
 	struct nfs_client *clp = server->nfs_client;
+	struct nfs_net *nn = net_generic(clp->net, nfs_net_id);
 
-	spin_lock(&nfs_client_lock);
+	spin_lock(&nn->nfs_client_lock);
 	list_add_tail_rcu(&server->client_link, &clp->cl_superblocks);
-	list_add_tail(&server->master_link, &nfs_volume_list);
+	list_add_tail(&server->master_link, &nn->nfs_volume_list);
 	clear_bit(NFS_CS_STOP_RENEW, &clp->cl_res_state);
-	spin_unlock(&nfs_client_lock);
+	spin_unlock(&nn->nfs_client_lock);
 
 }
 
 static void nfs_server_remove_lists(struct nfs_server *server)
 {
 	struct nfs_client *clp = server->nfs_client;
+	struct nfs_net *nn;
 
-	spin_lock(&nfs_client_lock);
+	if (clp == NULL)
+		return;
+	nn = net_generic(clp->net, nfs_net_id);
+	spin_lock(&nn->nfs_client_lock);
 	list_del_rcu(&server->client_link);
-	if (clp && list_empty(&clp->cl_superblocks))
+	if (list_empty(&clp->cl_superblocks))
 		set_bit(NFS_CS_STOP_RENEW, &clp->cl_res_state);
 	list_del(&server->master_link);
-	spin_unlock(&nfs_client_lock);
+	spin_unlock(&nn->nfs_client_lock);
 
 	synchronize_rcu();
 }
@@ -1086,6 +1110,8 @@ static struct nfs_server *nfs_alloc_server(void)
 		return NULL;
 	}
 
+	ida_init(&server->openowner_id);
+	ida_init(&server->lockowner_id);
 	pnfs_init_server(server);
 
 	return server;
@@ -1111,6 +1137,8 @@ void nfs_free_server(struct nfs_server *server)
 
 	nfs_put_client(server->nfs_client);
 
+	ida_destroy(&server->lockowner_id);
+	ida_destroy(&server->openowner_id);
 	nfs_free_iostats(server->io_stats);
 	bdi_destroy(&server->backing_dev_info);
 	kfree(server);
@@ -1186,48 +1214,22 @@ error:
 }
 
 #ifdef CONFIG_NFS_V4
-/*
- * NFSv4.0 callback thread helper
- *
- * Find a client by IP address, protocol version, and minorversion
- *
- * Called from the pg_authenticate method. The callback identifier
- * is not used as it has not been decoded.
- *
- * Returns NULL if no such client
- */
-struct nfs_client *
-nfs4_find_client_no_ident(const struct sockaddr *addr)
-{
-	struct nfs_client *clp;
-
-	spin_lock(&nfs_client_lock);
-	list_for_each_entry(clp, &nfs_client_list, cl_share_link) {
-		if (nfs4_cb_match_client(addr, clp, 0) == false)
-			continue;
-		atomic_inc(&clp->cl_count);
-		spin_unlock(&nfs_client_lock);
-		return clp;
-	}
-	spin_unlock(&nfs_client_lock);
-	return NULL;
-}
-
 /*
  * NFSv4.0 callback thread helper
  *
  * Find a client by callback identifier
  */
 struct nfs_client *
-nfs4_find_client_ident(int cb_ident)
+nfs4_find_client_ident(struct net *net, int cb_ident)
 {
 	struct nfs_client *clp;
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
 
-	spin_lock(&nfs_client_lock);
-	clp = idr_find(&cb_ident_idr, cb_ident);
+	spin_lock(&nn->nfs_client_lock);
+	clp = idr_find(&nn->cb_ident_idr, cb_ident);
 	if (clp)
 		atomic_inc(&clp->cl_count);
-	spin_unlock(&nfs_client_lock);
+	spin_unlock(&nn->nfs_client_lock);
 	return clp;
 }
 
@@ -1240,13 +1242,14 @@ nfs4_find_client_ident(int cb_ident)
  * Returns NULL if no such client
  */
 struct nfs_client *
-nfs4_find_client_sessionid(const struct sockaddr *addr,
+nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
 			   struct nfs4_sessionid *sid)
 {
 	struct nfs_client *clp;
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
 
-	spin_lock(&nfs_client_lock);
-	list_for_each_entry(clp, &nfs_client_list, cl_share_link) {
+	spin_lock(&nn->nfs_client_lock);
+	list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
 		if (nfs4_cb_match_client(addr, clp, 1) == false)
 			continue;
 
@@ -1259,17 +1262,17 @@ nfs4_find_client_sessionid(const struct sockaddr *addr,
 			continue;
 
 		atomic_inc(&clp->cl_count);
-		spin_unlock(&nfs_client_lock);
+		spin_unlock(&nn->nfs_client_lock);
 		return clp;
 	}
-	spin_unlock(&nfs_client_lock);
+	spin_unlock(&nn->nfs_client_lock);
 	return NULL;
 }
 
 #else /* CONFIG_NFS_V4_1 */
 
 struct nfs_client *
-nfs4_find_client_sessionid(const struct sockaddr *addr,
+nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
 			   struct nfs4_sessionid *sid)
 {
 	return NULL;
@@ -1284,16 +1287,18 @@ static int nfs4_init_callback(struct nfs_client *clp)
 	int error;
 
 	if (clp->rpc_ops->version == 4) {
+		struct rpc_xprt *xprt;
+
+		xprt = rcu_dereference_raw(clp->cl_rpcclient->cl_xprt);
+
 		if (nfs4_has_session(clp)) {
-			error = xprt_setup_backchannel(
-						clp->cl_rpcclient->cl_xprt,
+			error = xprt_setup_backchannel(xprt,
 						NFS41_BC_MIN_CALLBACKS);
 			if (error < 0)
 				return error;
 		}
 
-		error = nfs_callback_up(clp->cl_mvops->minor_version,
-					clp->cl_rpcclient->cl_xprt);
+		error = nfs_callback_up(clp->cl_mvops->minor_version, xprt);
 		if (error < 0) {
 			dprintk("%s: failed to start callback. Error = %d\n",
 				__func__, error);
@@ -1344,6 +1349,7 @@ int nfs4_init_client(struct nfs_client *clp,
 		     rpc_authflavor_t authflavour,
 		     int noresvport)
 {
+	char buf[INET6_ADDRSTRLEN + 1];
 	int error;
 
 	if (clp->cl_cons_state == NFS_CS_READY) {
@@ -1359,6 +1365,20 @@ int nfs4_init_client(struct nfs_client *clp,
 				      1, noresvport);
 	if (error < 0)
 		goto error;
+
+	/* If no clientaddr= option was specified, find a usable cb address */
+	if (ip_addr == NULL) {
+		struct sockaddr_storage cb_addr;
+		struct sockaddr *sap = (struct sockaddr *)&cb_addr;
+
+		error = rpc_localaddr(clp->cl_rpcclient, sap, sizeof(cb_addr));
+		if (error < 0)
+			goto error;
+		error = rpc_ntop(sap, buf, sizeof(buf));
+		if (error < 0)
+			goto error;
+		ip_addr = (const char *)buf;
+	}
 	strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr));
 
 	error = nfs_idmap_new(clp);
@@ -1393,7 +1413,7 @@ static int nfs4_set_client(struct nfs_server *server,
 		const char *ip_addr,
 		rpc_authflavor_t authflavour,
 		int proto, const struct rpc_timeout *timeparms,
-		u32 minorversion)
+		u32 minorversion, struct net *net)
 {
 	struct nfs_client_initdata cl_init = {
 		.hostname = hostname,
@@ -1402,6 +1422,7 @@ static int nfs4_set_client(struct nfs_server *server,
 		.rpc_ops = &nfs_v4_clientops,
 		.proto = proto,
 		.minorversion = minorversion,
+		.net = net,
 	};
 	struct nfs_client *clp;
 	int error;
@@ -1453,6 +1474,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 		.rpc_ops = &nfs_v4_clientops,
 		.proto = ds_proto,
 		.minorversion = mds_clp->cl_minorversion,
+		.net = mds_clp->net,
 	};
 	struct rpc_timeout ds_timeout = {
 		.to_initval = 15 * HZ,
@@ -1580,7 +1602,8 @@ static int nfs4_init_server(struct nfs_server *server,
 			data->auth_flavors[0],
 			data->nfs_server.protocol,
 			&timeparms,
-			data->minorversion);
+			data->minorversion,
+			data->net);
 	if (error < 0)
 		goto error;
 
@@ -1675,9 +1698,10 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
 				data->addrlen,
 				parent_client->cl_ipaddr,
 				data->authflavor,
-				parent_server->client->cl_xprt->prot,
+				rpc_protocol(parent_server->client),
 				parent_server->client->cl_timeout,
-				parent_client->cl_mvops->minor_version);
+				parent_client->cl_mvops->minor_version,
+				parent_client->net);
 	if (error < 0)
 		goto error;
 
@@ -1770,6 +1794,18 @@ out_free_server:
 	return ERR_PTR(error);
 }
 
+void nfs_clients_init(struct net *net)
+{
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+	INIT_LIST_HEAD(&nn->nfs_client_list);
+	INIT_LIST_HEAD(&nn->nfs_volume_list);
+#ifdef CONFIG_NFS_V4
+	idr_init(&nn->cb_ident_idr);
+#endif
+	spin_lock_init(&nn->nfs_client_lock);
+}
+
 #ifdef CONFIG_PROC_FS
 static struct proc_dir_entry *proc_fs_nfs;
 
@@ -1823,13 +1859,15 @@ static int nfs_server_list_open(struct inode *inode, struct file *file)
 {
 	struct seq_file *m;
 	int ret;
+	struct pid_namespace *pid_ns = file->f_dentry->d_sb->s_fs_info;
+	struct net *net = pid_ns->child_reaper->nsproxy->net_ns;
 
 	ret = seq_open(file, &nfs_server_list_ops);
 	if (ret < 0)
 		return ret;
 
 	m = file->private_data;
-	m->private = PDE(inode)->data;
+	m->private = net;
 
 	return 0;
 }
@@ -1839,9 +1877,11 @@ static int nfs_server_list_open(struct inode *inode, struct file *file)
  */
 static void *nfs_server_list_start(struct seq_file *m, loff_t *_pos)
 {
+	struct nfs_net *nn = net_generic(m->private, nfs_net_id);
+
 	/* lock the list against modification */
-	spin_lock(&nfs_client_lock);
-	return seq_list_start_head(&nfs_client_list, *_pos);
+	spin_lock(&nn->nfs_client_lock);
+	return seq_list_start_head(&nn->nfs_client_list, *_pos);
 }
 
 /*
@@ -1849,7 +1889,9 @@ static void *nfs_server_list_start(struct seq_file *m, loff_t *_pos)
  */
 static void *nfs_server_list_next(struct seq_file *p, void *v, loff_t *pos)
 {
-	return seq_list_next(v, &nfs_client_list, pos);
+	struct nfs_net *nn = net_generic(p->private, nfs_net_id);
+
+	return seq_list_next(v, &nn->nfs_client_list, pos);
 }
 
 /*
@@ -1857,7 +1899,9 @@ static void *nfs_server_list_next(struct seq_file *p, void *v, loff_t *pos)
  */
 static void nfs_server_list_stop(struct seq_file *p, void *v)
 {
-	spin_unlock(&nfs_client_lock);
+	struct nfs_net *nn = net_generic(p->private, nfs_net_id);
+
+	spin_unlock(&nn->nfs_client_lock);
 }
 
 /*
@@ -1866,9 +1910,10 @@ static void nfs_server_list_stop(struct seq_file *p, void *v)
 static int nfs_server_list_show(struct seq_file *m, void *v)
 {
 	struct nfs_client *clp;
+	struct nfs_net *nn = net_generic(m->private, nfs_net_id);
 
 	/* display header on line 1 */
-	if (v == &nfs_client_list) {
+	if (v == &nn->nfs_client_list) {
 		seq_puts(m, "NV SERVER   PORT USE HOSTNAME\n");
 		return 0;
 	}
@@ -1880,12 +1925,14 @@ static int nfs_server_list_show(struct seq_file *m, void *v)
 	if (clp->cl_cons_state != NFS_CS_READY)
 		return 0;
 
+	rcu_read_lock();
 	seq_printf(m, "v%u %s %s %3d %s\n",
 		   clp->rpc_ops->version,
 		   rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_ADDR),
 		   rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_PORT),
 		   atomic_read(&clp->cl_count),
 		   clp->cl_hostname);
+	rcu_read_unlock();
 
 	return 0;
 }
@@ -1897,13 +1944,15 @@ static int nfs_volume_list_open(struct inode *inode, struct file *file)
 {
 	struct seq_file *m;
 	int ret;
+	struct pid_namespace *pid_ns = file->f_dentry->d_sb->s_fs_info;
+	struct net *net = pid_ns->child_reaper->nsproxy->net_ns;
 
 	ret = seq_open(file, &nfs_volume_list_ops);
 	if (ret < 0)
 		return ret;
 
 	m = file->private_data;
-	m->private = PDE(inode)->data;
+	m->private = net;
 
 	return 0;
 }
@@ -1913,9 +1962,11 @@ static int nfs_volume_list_open(struct inode *inode, struct file *file)
  */
 static void *nfs_volume_list_start(struct seq_file *m, loff_t *_pos)
 {
+	struct nfs_net *nn = net_generic(m->private, nfs_net_id);
+
 	/* lock the list against modification */
-	spin_lock(&nfs_client_lock);
-	return seq_list_start_head(&nfs_volume_list, *_pos);
+	spin_lock(&nn->nfs_client_lock);
+	return seq_list_start_head(&nn->nfs_volume_list, *_pos);
 }
 
 /*
@@ -1923,7 +1974,9 @@ static void *nfs_volume_list_start(struct seq_file *m, loff_t *_pos)
  */
 static void *nfs_volume_list_next(struct seq_file *p, void *v, loff_t *pos)
 {
-	return seq_list_next(v, &nfs_volume_list, pos);
+	struct nfs_net *nn = net_generic(p->private, nfs_net_id);
+
+	return seq_list_next(v, &nn->nfs_volume_list, pos);
 }
 
 /*
@@ -1931,7 +1984,9 @@ static void *nfs_volume_list_next(struct seq_file *p, void *v, loff_t *pos)
  */
 static void nfs_volume_list_stop(struct seq_file *p, void *v)
 {
-	spin_unlock(&nfs_client_lock);
+	struct nfs_net *nn = net_generic(p->private, nfs_net_id);
+
+	spin_unlock(&nn->nfs_client_lock);
 }
 
 /*
@@ -1942,9 +1997,10 @@ static int nfs_volume_list_show(struct seq_file *m, void *v)
 	struct nfs_server *server;
 	struct nfs_client *clp;
 	char dev[8], fsid[17];
+	struct nfs_net *nn = net_generic(m->private, nfs_net_id);
 
 	/* display header on line 1 */
-	if (v == &nfs_volume_list) {
+	if (v == &nn->nfs_volume_list) {
 		seq_puts(m, "NV SERVER   PORT DEV     FSID              FSC\n");
 		return 0;
 	}
@@ -1959,6 +2015,7 @@ static int nfs_volume_list_show(struct seq_file *m, void *v)
 		 (unsigned long long) server->fsid.major,
 		 (unsigned long long) server->fsid.minor);
 
+	rcu_read_lock();
 	seq_printf(m, "v%u %s %s %-7s %-17s %s\n",
 		   clp->rpc_ops->version,
 		   rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_ADDR),
@@ -1966,6 +2023,7 @@ static int nfs_volume_list_show(struct seq_file *m, void *v)
 		   dev,
 		   fsid,
 		   nfs_server_fscache_state(server));
+	rcu_read_unlock();
 
 	return 0;
 }

fs/nfs/delegation.c

@@ -105,7 +105,7 @@ again:
 			continue;
 		if (!test_bit(NFS_DELEGATED_STATE, &state->flags))
 			continue;
-		if (memcmp(state->stateid.data, stateid->data, sizeof(state->stateid.data)) != 0)
+		if (!nfs4_stateid_match(&state->stateid, stateid))
 			continue;
 		get_nfs_open_context(ctx);
 		spin_unlock(&inode->i_lock);
@@ -139,8 +139,7 @@ void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred,
 	if (delegation != NULL) {
 		spin_lock(&delegation->lock);
 		if (delegation->inode != NULL) {
-			memcpy(delegation->stateid.data, res->delegation.data,
-			       sizeof(delegation->stateid.data));
+			nfs4_stateid_copy(&delegation->stateid, &res->delegation);
 			delegation->type = res->delegation_type;
 			delegation->maxsize = res->maxsize;
 			oldcred = delegation->cred;
@@ -236,8 +235,7 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
 	delegation = kmalloc(sizeof(*delegation), GFP_NOFS);
 	if (delegation == NULL)
 		return -ENOMEM;
-	memcpy(delegation->stateid.data, res->delegation.data,
-			sizeof(delegation->stateid.data));
+	nfs4_stateid_copy(&delegation->stateid, &res->delegation);
 	delegation->type = res->delegation_type;
 	delegation->maxsize = res->maxsize;
 	delegation->change_attr = inode->i_version;
@@ -250,19 +248,22 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
 	old_delegation = rcu_dereference_protected(nfsi->delegation,
 					lockdep_is_held(&clp->cl_lock));
 	if (old_delegation != NULL) {
-		if (memcmp(&delegation->stateid, &old_delegation->stateid,
-					sizeof(old_delegation->stateid)) == 0 &&
+		if (nfs4_stateid_match(&delegation->stateid,
+					&old_delegation->stateid) &&
 				delegation->type == old_delegation->type) {
 			goto out;
 		}
 		/*
 		 * Deal with broken servers that hand out two
 		 * delegations for the same file.
+		 * Allow for upgrades to a WRITE delegation, but
+		 * nothing else.
 		 */
 		dfprintk(FILE, "%s: server %s handed out "
 				"a duplicate delegation!\n",
 				__func__, clp->cl_hostname);
-		if (delegation->type <= old_delegation->type) {
+		if (delegation->type == old_delegation->type ||
+		    !(delegation->type & FMODE_WRITE)) {
 			freeme = delegation;
 			delegation = NULL;
 			goto out;
@@ -455,17 +456,24 @@ static void nfs_client_mark_return_all_delegation_types(struct nfs_client *clp,
 	rcu_read_unlock();
 }
 
-static void nfs_client_mark_return_all_delegations(struct nfs_client *clp)
-{
-	nfs_client_mark_return_all_delegation_types(clp, FMODE_READ|FMODE_WRITE);
-}
-
 static void nfs_delegation_run_state_manager(struct nfs_client *clp)
 {
 	if (test_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state))
 		nfs4_schedule_state_manager(clp);
 }
 
+void nfs_remove_bad_delegation(struct inode *inode)
+{
+	struct nfs_delegation *delegation;
+
+	delegation = nfs_detach_delegation(NFS_I(inode), NFS_SERVER(inode));
+	if (delegation) {
+		nfs_inode_find_state_and_recover(inode, &delegation->stateid);
+		nfs_free_delegation(delegation);
+	}
+}
+EXPORT_SYMBOL_GPL(nfs_remove_bad_delegation);
+
 /**
  * nfs_expire_all_delegation_types
  * @clp: client to process
@@ -488,18 +496,6 @@ void nfs_expire_all_delegations(struct nfs_client *clp)
 	nfs_expire_all_delegation_types(clp, FMODE_READ|FMODE_WRITE);
 }
 
-/**
- * nfs_handle_cb_pathdown - return all delegations after NFS4ERR_CB_PATH_DOWN
- * @clp: client to process
- *
- */
-void nfs_handle_cb_pathdown(struct nfs_client *clp)
-{
-	if (clp == NULL)
-		return;
-	nfs_client_mark_return_all_delegations(clp);
-}
-
 static void nfs_mark_return_unreferenced_delegations(struct nfs_server *server)
 {
 	struct nfs_delegation *delegation;
@@ -531,7 +527,7 @@ void nfs_expire_unreferenced_delegations(struct nfs_client *clp)
 /**
  * nfs_async_inode_return_delegation - asynchronously return a delegation
  * @inode: inode to process
- * @stateid: state ID information from CB_RECALL arguments
+ * @stateid: state ID information
  *
  * Returns zero on success, or a negative errno value.
  */
@@ -545,7 +541,7 @@ int nfs_async_inode_return_delegation(struct inode *inode,
 	rcu_read_lock();
 	delegation = rcu_dereference(NFS_I(inode)->delegation);
 
-	if (!clp->cl_mvops->validate_stateid(delegation, stateid)) {
+	if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) {
 		rcu_read_unlock();
 		return -ENOENT;
 	}
@@ -684,21 +680,25 @@ int nfs_delegations_present(struct nfs_client *clp)
  * nfs4_copy_delegation_stateid - Copy inode's state ID information
  * @dst: stateid data structure to fill in
  * @inode: inode to check
+ * @flags: delegation type requirement
  *
- * Returns one and fills in "dst->data" * if inode had a delegation,
- * otherwise zero is returned.
+ * Returns "true" and fills in "dst->data" * if inode had a delegation,
+ * otherwise "false" is returned.
  */
-int nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode)
+bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode,
+		fmode_t flags)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_delegation *delegation;
-	int ret = 0;
+	bool ret;
 
+	flags &= FMODE_READ|FMODE_WRITE;
 	rcu_read_lock();
 	delegation = rcu_dereference(nfsi->delegation);
-	if (delegation != NULL) {
-		memcpy(dst->data, delegation->stateid.data, sizeof(dst->data));
-		ret = 1;
+	ret = (delegation != NULL && (delegation->type & flags) == flags);
+	if (ret) {
+		nfs4_stateid_copy(dst, &delegation->stateid);
+		nfs_mark_delegation_referenced(delegation);
 	}
 	rcu_read_unlock();
 	return ret;

fs/nfs/delegation.h

@@ -42,9 +42,9 @@ void nfs_super_return_all_delegations(struct super_block *sb);
 void nfs_expire_all_delegations(struct nfs_client *clp);
 void nfs_expire_all_delegation_types(struct nfs_client *clp, fmode_t flags);
 void nfs_expire_unreferenced_delegations(struct nfs_client *clp);
-void nfs_handle_cb_pathdown(struct nfs_client *clp);
 int nfs_client_return_marked_delegations(struct nfs_client *clp);
 int nfs_delegations_present(struct nfs_client *clp);
+void nfs_remove_bad_delegation(struct inode *inode);
 
 void nfs_delegation_mark_reclaim(struct nfs_client *clp);
 void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
@@ -53,7 +53,7 @@ void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
 int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync);
 int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid);
 int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl);
-int nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode);
+bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, fmode_t flags);
 
 void nfs_mark_delegation_referenced(struct nfs_delegation *delegation);
 int nfs_have_delegation(struct inode *inode, fmode_t flags);

fs/nfs/dir.c

@@ -207,7 +207,7 @@ struct nfs_cache_array_entry {
 };
 
 struct nfs_cache_array {
-	unsigned int size;
+	int size;
 	int eof_index;
 	u64 last_cookie;
 	struct nfs_cache_array_entry array[0];
@@ -1429,6 +1429,7 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
 	}
 
 	open_flags = nd->intent.open.flags;
+	attr.ia_valid = 0;
 
 	ctx = create_nfs_open_context(dentry, open_flags);
 	res = ERR_CAST(ctx);
@@ -1437,11 +1438,14 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
 
 	if (nd->flags & LOOKUP_CREATE) {
 		attr.ia_mode = nd->intent.open.create_mode;
-		attr.ia_valid = ATTR_MODE;
+		attr.ia_valid |= ATTR_MODE;
 		attr.ia_mode &= ~current_umask();
-	} else {
+	} else
 		open_flags &= ~(O_EXCL | O_CREAT);
-		attr.ia_valid = 0;
+
+	if (open_flags & O_TRUNC) {
+		attr.ia_valid |= ATTR_SIZE;
+		attr.ia_size = 0;
 	}
 
 	/* Open the file on the server */
@@ -1495,6 +1499,7 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
 	struct inode *inode;
 	struct inode *dir;
 	struct nfs_open_context *ctx;
+	struct iattr attr;
 	int openflags, ret = 0;
 
 	if (nd->flags & LOOKUP_RCU)
@@ -1523,19 +1528,27 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
 	/* We cannot do exclusive creation on a positive dentry */
 	if ((openflags & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL))
 		goto no_open_dput;
-	/* We can't create new files, or truncate existing ones here */
-	openflags &= ~(O_CREAT|O_EXCL|O_TRUNC);
+	/* We can't create new files here */
+	openflags &= ~(O_CREAT|O_EXCL);
 
 	ctx = create_nfs_open_context(dentry, openflags);
 	ret = PTR_ERR(ctx);
 	if (IS_ERR(ctx))
 		goto out;
+
+	attr.ia_valid = 0;
+	if (openflags & O_TRUNC) {
+		attr.ia_valid |= ATTR_SIZE;
+		attr.ia_size = 0;
+		nfs_wb_all(inode);
+	}
+
 	/*
 	 * Note: we're not holding inode->i_mutex and so may be racing with
 	 * operations that change the directory. We therefore save the
 	 * change attribute *before* we do the RPC call.
 	 */
-	inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, NULL);
+	inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr);
 	if (IS_ERR(inode)) {
 		ret = PTR_ERR(inode);
 		switch (ret) {

fs/nfs/direct.c

@@ -265,9 +265,7 @@ static void nfs_direct_read_release(void *calldata)
 }
 
 static const struct rpc_call_ops nfs_read_direct_ops = {
-#if defined(CONFIG_NFS_V4_1)
 	.rpc_call_prepare = nfs_read_prepare,
-#endif /* CONFIG_NFS_V4_1 */
 	.rpc_call_done = nfs_direct_read_result,
 	.rpc_release = nfs_direct_read_release,
 };
@@ -554,9 +552,7 @@ static void nfs_direct_commit_release(void *calldata)
 }
 
 static const struct rpc_call_ops nfs_commit_direct_ops = {
-#if defined(CONFIG_NFS_V4_1)
 	.rpc_call_prepare = nfs_write_prepare,
-#endif /* CONFIG_NFS_V4_1 */
 	.rpc_call_done = nfs_direct_commit_result,
 	.rpc_release = nfs_direct_commit_release,
 };
@@ -696,9 +692,7 @@ out_unlock:
 }
 
 static const struct rpc_call_ops nfs_write_direct_ops = {
-#if defined(CONFIG_NFS_V4_1)
 	.rpc_call_prepare = nfs_write_prepare,
-#endif /* CONFIG_NFS_V4_1 */
 	.rpc_call_done = nfs_direct_write_result,
 	.rpc_release = nfs_direct_write_release,
 };

fs/nfs/dns_resolve.c

@@ -10,8 +10,9 @@
 
 #include <linux/sunrpc/clnt.h>
 #include <linux/dns_resolver.h>
+#include "dns_resolve.h"
 
-ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
+ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen,
 		struct sockaddr *sa, size_t salen)
 {
 	ssize_t ret;
@@ -20,7 +21,7 @@ ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
 
 	ip_len = dns_query(NULL, name, namelen, NULL, &ip_addr, NULL);
 	if (ip_len > 0)
-		ret = rpc_pton(ip_addr, ip_len, sa, salen);
+		ret = rpc_pton(net, ip_addr, ip_len, sa, salen);
 	else
 		ret = -ESRCH;
 	kfree(ip_addr);
@@ -40,15 +41,15 @@ ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/cache.h>
 #include <linux/sunrpc/svcauth.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
 
 #include "dns_resolve.h"
 #include "cache_lib.h"
+#include "netns.h"
 
 #define NFS_DNS_HASHBITS 4
 #define NFS_DNS_HASHTBL_SIZE (1 << NFS_DNS_HASHBITS)
 
-static struct cache_head *nfs_dns_table[NFS_DNS_HASHTBL_SIZE];
-
 struct nfs_dns_ent {
 	struct cache_head h;
 
@@ -224,7 +225,7 @@ static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen)
 	len = qword_get(&buf, buf1, sizeof(buf1));
 	if (len <= 0)
 		goto out;
-	key.addrlen = rpc_pton(buf1, len,
+	key.addrlen = rpc_pton(cd->net, buf1, len,
 			(struct sockaddr *)&key.addr,
 			sizeof(key.addr));
 
@@ -259,21 +260,6 @@ out:
 	return ret;
 }
 
-static struct cache_detail nfs_dns_resolve = {
-	.owner = THIS_MODULE,
-	.hash_size = NFS_DNS_HASHTBL_SIZE,
-	.hash_table = nfs_dns_table,
-	.name = "dns_resolve",
-	.cache_put = nfs_dns_ent_put,
-	.cache_upcall = nfs_dns_upcall,
-	.cache_parse = nfs_dns_parse,
-	.cache_show = nfs_dns_show,
-	.match = nfs_dns_match,
-	.init = nfs_dns_ent_init,
-	.update = nfs_dns_ent_update,
-	.alloc = nfs_dns_ent_alloc,
-};
-
 static int do_cache_lookup(struct cache_detail *cd,
 		struct nfs_dns_ent *key,
 		struct nfs_dns_ent **item,
@@ -336,8 +322,8 @@ out:
 	return ret;
 }
 
-ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
-		struct sockaddr *sa, size_t salen)
+ssize_t nfs_dns_resolve_name(struct net *net, char *name,
+		size_t namelen, struct sockaddr *sa, size_t salen)
 {
 	struct nfs_dns_ent key = {
 		.hostname = name,
@@ -345,28 +331,118 @@ ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
 	};
 	struct nfs_dns_ent *item = NULL;
 	ssize_t ret;
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
 
-	ret = do_cache_lookup_wait(&nfs_dns_resolve, &key, &item);
+	ret = do_cache_lookup_wait(nn->nfs_dns_resolve, &key, &item);
 	if (ret == 0) {
 		if (salen >= item->addrlen) {
 			memcpy(sa, &item->addr, item->addrlen);
 			ret = item->addrlen;
 		} else
 			ret = -EOVERFLOW;
-		cache_put(&item->h, &nfs_dns_resolve);
+		cache_put(&item->h, nn->nfs_dns_resolve);
 	} else if (ret == -ENOENT)
 		ret = -ESRCH;
 	return ret;
 }
 
+int nfs_dns_resolver_cache_init(struct net *net)
+{
+	int err = -ENOMEM;
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+	struct cache_detail *cd;
+	struct cache_head **tbl;
+
+	cd = kzalloc(sizeof(struct cache_detail), GFP_KERNEL);
+	if (cd == NULL)
+		goto err_cd;
+
+	tbl = kzalloc(NFS_DNS_HASHTBL_SIZE * sizeof(struct cache_head *),
+			GFP_KERNEL);
+	if (tbl == NULL)
+		goto err_tbl;
+
+	cd->owner = THIS_MODULE,
+	cd->hash_size = NFS_DNS_HASHTBL_SIZE,
+	cd->hash_table = tbl,
+	cd->name = "dns_resolve",
+	cd->cache_put = nfs_dns_ent_put,
+	cd->cache_upcall = nfs_dns_upcall,
+	cd->cache_parse = nfs_dns_parse,
+	cd->cache_show = nfs_dns_show,
+	cd->match = nfs_dns_match,
+	cd->init = nfs_dns_ent_init,
+	cd->update = nfs_dns_ent_update,
+	cd->alloc = nfs_dns_ent_alloc,
+
+	nfs_cache_init(cd);
+	err = nfs_cache_register_net(net, cd);
+	if (err)
+		goto err_reg;
+	nn->nfs_dns_resolve = cd;
+	return 0;
+
+err_reg:
+	nfs_cache_destroy(cd);
+	kfree(cd->hash_table);
+err_tbl:
+	kfree(cd);
+err_cd:
+	return err;
+}
+
+void nfs_dns_resolver_cache_destroy(struct net *net)
+{
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+	struct cache_detail *cd = nn->nfs_dns_resolve;
+
+	nfs_cache_unregister_net(net, cd);
+	nfs_cache_destroy(cd);
+	kfree(cd->hash_table);
+	kfree(cd);
+}
+
+static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
+			   void *ptr)
+{
+	struct super_block *sb = ptr;
+	struct net *net = sb->s_fs_info;
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+	struct cache_detail *cd = nn->nfs_dns_resolve;
+	int ret = 0;
+
+	if (cd == NULL)
+		return 0;
+
+	if (!try_module_get(THIS_MODULE))
+		return 0;
+
+	switch (event) {
+	case RPC_PIPEFS_MOUNT:
+		ret = nfs_cache_register_sb(sb, cd);
+		break;
+	case RPC_PIPEFS_UMOUNT:
+		nfs_cache_unregister_sb(sb, cd);
+		break;
+	default:
+		ret = -ENOTSUPP;
+		break;
+	}
+	module_put(THIS_MODULE);
+	return ret;
+}
+
+static struct notifier_block nfs_dns_resolver_block = {
+	.notifier_call	= rpc_pipefs_event,
+};
+
 int nfs_dns_resolver_init(void)
 {
-	return nfs_cache_register(&nfs_dns_resolve);
+	return rpc_pipefs_notifier_register(&nfs_dns_resolver_block);
 }
 
 void nfs_dns_resolver_destroy(void)
 {
-	nfs_cache_unregister(&nfs_dns_resolve);
+	rpc_pipefs_notifier_unregister(&nfs_dns_resolver_block);
 }
-
 #endif

fs/nfs/dns_resolve.h

@@ -15,12 +15,22 @@ static inline int nfs_dns_resolver_init(void)
 
 static inline void nfs_dns_resolver_destroy(void)
 {}
+
+static inline int nfs_dns_resolver_cache_init(struct net *net)
+{
+	return 0;
+}
+
+static inline void nfs_dns_resolver_cache_destroy(struct net *net)
+{}
 #else
 extern int nfs_dns_resolver_init(void);
 extern void nfs_dns_resolver_destroy(void);
+extern int nfs_dns_resolver_cache_init(struct net *net);
+extern void nfs_dns_resolver_cache_destroy(struct net *net);
 #endif
 
-extern ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
-		struct sockaddr *sa, size_t salen);
+extern ssize_t nfs_dns_resolve_name(struct net *net, char *name,
+		size_t namelen,	struct sockaddr *sa, size_t salen);
 
 #endif

fs/nfs/file.c

@@ -530,6 +530,8 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (mapping != dentry->d_inode->i_mapping)
 		goto out_unlock;
 
+	wait_on_page_writeback(page);
+
 	pagelen = nfs_page_length(page);
 	if (pagelen == 0)
 		goto out_unlock;

fs/nfs/fscache.c

@@ -327,7 +327,7 @@ void nfs_fscache_reset_inode_cookie(struct inode *inode)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_server *nfss = NFS_SERVER(inode);
-	struct fscache_cookie *old = nfsi->fscache;
+	NFS_IFDEBUG(struct fscache_cookie *old = nfsi->fscache);
 
 	nfs_fscache_inode_lock(inode);
 	if (nfsi->fscache) {

fs/nfs/idmap.c

@@ -34,11 +34,29 @@
  *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 #include <linux/types.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
+#include <linux/parser.h>
+#include <linux/fs.h>
 #include <linux/nfs_idmap.h>
+#include <net/net_namespace.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
 #include <linux/nfs_fs.h>
+#include <linux/nfs_fs_sb.h>
+#include <linux/key.h>
+#include <linux/keyctl.h>
+#include <linux/key-type.h>
+#include <keys/user-type.h>
+#include <linux/module.h>
+
+#include "internal.h"
+#include "netns.h"
+
+#define NFS_UINT_MAXLEN 11
+
+/* Default cache timeout is 10 minutes */
+unsigned int nfs_idmap_cache_timeout = 600;
+static const struct cred *id_resolver_cache;
+static struct key_type key_type_id_resolver_legacy;
+
 
 /**
  * nfs_fattr_init_names - initialise the nfs_fattr owner_name/group_name fields
@@ -142,24 +160,7 @@ static int nfs_map_numeric_to_string(__u32 id, char *buf, size_t buflen)
 	return snprintf(buf, buflen, "%u", id);
 }
 
-#ifdef CONFIG_NFS_USE_NEW_IDMAPPER
-
-#include <linux/cred.h>
-#include <linux/sunrpc/sched.h>
-#include <linux/nfs4.h>
-#include <linux/nfs_fs_sb.h>
-#include <linux/keyctl.h>
-#include <linux/key-type.h>
-#include <linux/rcupdate.h>
-#include <linux/err.h>
-
-#include <keys/user-type.h>
-
-#define NFS_UINT_MAXLEN 11
-
-const struct cred *id_resolver_cache;
-
-struct key_type key_type_id_resolver = {
+static struct key_type key_type_id_resolver = {
 	.name		= "id_resolver",
 	.instantiate	= user_instantiate,
 	.match		= user_match,
@@ -169,13 +170,14 @@ struct key_type key_type_id_resolver = {
 	.read		= user_read,
 };
 
-int nfs_idmap_init(void)
+static int nfs_idmap_init_keyring(void)
 {
 	struct cred *cred;
 	struct key *keyring;
 	int ret = 0;
 
-	printk(KERN_NOTICE "Registering the %s key type\n", key_type_id_resolver.name);
+	printk(KERN_NOTICE "NFS: Registering the %s key type\n",
+		key_type_id_resolver.name);
 
 	cred = prepare_kernel_cred(NULL);
 	if (!cred)
@@ -210,7 +212,7 @@ failed_put_cred:
 	return ret;
 }
 
-void nfs_idmap_quit(void)
+static void nfs_idmap_quit_keyring(void)
 {
 	key_revoke(id_resolver_cache->thread_keyring);
 	unregister_key_type(&key_type_id_resolver);
@@ -245,8 +247,10 @@ static ssize_t nfs_idmap_get_desc(const char *name, size_t namelen,
 	return desclen;
 }
 
-static ssize_t nfs_idmap_request_key(const char *name, size_t namelen,
-		const char *type, void *data, size_t data_size)
+static ssize_t nfs_idmap_request_key(struct key_type *key_type,
+				     const char *name, size_t namelen,
+				     const char *type, void *data,
+				     size_t data_size, struct idmap *idmap)
 {
 	const struct cred *saved_cred;
 	struct key *rkey;
@@ -259,8 +263,12 @@ static ssize_t nfs_idmap_request_key(const char *name, size_t namelen,
 		goto out;
 
 	saved_cred = override_creds(id_resolver_cache);
-	rkey = request_key(&key_type_id_resolver, desc, "");
+	if (idmap)
+		rkey = request_key_with_auxdata(key_type, desc, "", 0, idmap);
+	else
+		rkey = request_key(&key_type_id_resolver, desc, "");
 	revert_creds(saved_cred);
+
 	kfree(desc);
 	if (IS_ERR(rkey)) {
 		ret = PTR_ERR(rkey);
@@ -293,31 +301,46 @@ out:
 	return ret;
 }
 
+static ssize_t nfs_idmap_get_key(const char *name, size_t namelen,
+				 const char *type, void *data,
+				 size_t data_size, struct idmap *idmap)
+{
+	ssize_t ret = nfs_idmap_request_key(&key_type_id_resolver,
+					    name, namelen, type, data,
+					    data_size, NULL);
+	if (ret < 0) {
+		ret = nfs_idmap_request_key(&key_type_id_resolver_legacy,
+					    name, namelen, type, data,
+					    data_size, idmap);
+	}
+	return ret;
+}
 
 /* ID -> Name */
-static ssize_t nfs_idmap_lookup_name(__u32 id, const char *type, char *buf, size_t buflen)
+static ssize_t nfs_idmap_lookup_name(__u32 id, const char *type, char *buf,
+				     size_t buflen, struct idmap *idmap)
 {
 	char id_str[NFS_UINT_MAXLEN];
 	int id_len;
 	ssize_t ret;
 
 	id_len = snprintf(id_str, sizeof(id_str), "%u", id);
-	ret = nfs_idmap_request_key(id_str, id_len, type, buf, buflen);
+	ret = nfs_idmap_get_key(id_str, id_len, type, buf, buflen, idmap);
 	if (ret < 0)
 		return -EINVAL;
 	return ret;
 }
 
 /* Name -> ID */
-static int nfs_idmap_lookup_id(const char *name, size_t namelen,
-				const char *type, __u32 *id)
+static int nfs_idmap_lookup_id(const char *name, size_t namelen, const char *type,
+			       __u32 *id, struct idmap *idmap)
 {
 	char id_str[NFS_UINT_MAXLEN];
 	long id_long;
 	ssize_t data_size;
 	int ret = 0;
 
-	data_size = nfs_idmap_request_key(name, namelen, type, id_str, NFS_UINT_MAXLEN);
+	data_size = nfs_idmap_get_key(name, namelen, type, id_str, NFS_UINT_MAXLEN, idmap);
 	if (data_size <= 0) {
 		ret = -EINVAL;
 	} else {
@@ -327,114 +350,103 @@ static int nfs_idmap_lookup_id(const char *name, size_t namelen,
 	return ret;
 }
 
-int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid)
-{
-	if (nfs_map_string_to_numeric(name, namelen, uid))
-		return 0;
-	return nfs_idmap_lookup_id(name, namelen, "uid", uid);
-}
-
-int nfs_map_group_to_gid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *gid)
-{
-	if (nfs_map_string_to_numeric(name, namelen, gid))
-		return 0;
-	return nfs_idmap_lookup_id(name, namelen, "gid", gid);
-}
-
-int nfs_map_uid_to_name(const struct nfs_server *server, __u32 uid, char *buf, size_t buflen)
-{
-	int ret = -EINVAL;
-
-	if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
-		ret = nfs_idmap_lookup_name(uid, "user", buf, buflen);
-	if (ret < 0)
-		ret = nfs_map_numeric_to_string(uid, buf, buflen);
-	return ret;
-}
-int nfs_map_gid_to_group(const struct nfs_server *server, __u32 gid, char *buf, size_t buflen)
-{
-	int ret = -EINVAL;
+/* idmap classic begins here */
+module_param(nfs_idmap_cache_timeout, int, 0644);
 
-	if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
-		ret = nfs_idmap_lookup_name(gid, "group", buf, buflen);
-	if (ret < 0)
-		ret = nfs_map_numeric_to_string(gid, buf, buflen);
-	return ret;
-}
-
-#else  /* CONFIG_NFS_USE_NEW_IDMAPPER not defined */
-
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/init.h>
-#include <linux/socket.h>
-#include <linux/in.h>
-#include <linux/sched.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/workqueue.h>
-#include <linux/sunrpc/rpc_pipe_fs.h>
-
-#include <linux/nfs_fs.h>
-
-#include "nfs4_fs.h"
-
-#define IDMAP_HASH_SZ          128
-
-/* Default cache timeout is 10 minutes */
-unsigned int nfs_idmap_cache_timeout = 600 * HZ;
-
-static int param_set_idmap_timeout(const char *val, struct kernel_param *kp)
-{
-	char *endp;
-	int num = simple_strtol(val, &endp, 0);
-	int jif = num * HZ;
-	if (endp == val || *endp || num < 0 || jif < num)
-		return -EINVAL;
-	*((int *)kp->arg) = jif;
-	return 0;
-}
-
-module_param_call(idmap_cache_timeout, param_set_idmap_timeout, param_get_int,
-		 &nfs_idmap_cache_timeout, 0644);
-
-struct idmap_hashent {
-	unsigned long		ih_expires;
-	__u32			ih_id;
-	size_t			ih_namelen;
-	char			ih_name[IDMAP_NAMESZ];
+struct idmap {
+	struct rpc_pipe		*idmap_pipe;
+	struct key_construction	*idmap_key_cons;
 };
 
-struct idmap_hashtable {
-	__u8			h_type;
-	struct idmap_hashent	h_entries[IDMAP_HASH_SZ];
+enum {
+	Opt_find_uid, Opt_find_gid, Opt_find_user, Opt_find_group, Opt_find_err
 };
 
-struct idmap {
-	struct dentry		*idmap_dentry;
-	wait_queue_head_t	idmap_wq;
-	struct idmap_msg	idmap_im;
-	struct mutex		idmap_lock;	/* Serializes upcalls */
-	struct mutex		idmap_im_lock;	/* Protects the hashtable */
-	struct idmap_hashtable	idmap_user_hash;
-	struct idmap_hashtable	idmap_group_hash;
+static const match_table_t nfs_idmap_tokens = {
+	{ Opt_find_uid, "uid:%s" },
+	{ Opt_find_gid, "gid:%s" },
+	{ Opt_find_user, "user:%s" },
+	{ Opt_find_group, "group:%s" },
+	{ Opt_find_err, NULL }
 };
 
+static int nfs_idmap_legacy_upcall(struct key_construction *, const char *, void *);
 static ssize_t idmap_pipe_downcall(struct file *, const char __user *,
 				   size_t);
 static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *);
 
-static unsigned int fnvhash32(const void *, size_t);
-
 static const struct rpc_pipe_ops idmap_upcall_ops = {
 	.upcall		= rpc_pipe_generic_upcall,
 	.downcall	= idmap_pipe_downcall,
 	.destroy_msg	= idmap_pipe_destroy_msg,
 };
 
+static struct key_type key_type_id_resolver_legacy = {
+	.name		= "id_resolver",
+	.instantiate	= user_instantiate,
+	.match		= user_match,
+	.revoke		= user_revoke,
+	.destroy	= user_destroy,
+	.describe	= user_describe,
+	.read		= user_read,
+	.request_key	= nfs_idmap_legacy_upcall,
+};
+
+static void __nfs_idmap_unregister(struct rpc_pipe *pipe)
+{
+	if (pipe->dentry)
+		rpc_unlink(pipe->dentry);
+}
+
+static int __nfs_idmap_register(struct dentry *dir,
+				     struct idmap *idmap,
+				     struct rpc_pipe *pipe)
+{
+	struct dentry *dentry;
+
+	dentry = rpc_mkpipe_dentry(dir, "idmap", idmap, pipe);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+	pipe->dentry = dentry;
+	return 0;
+}
+
+static void nfs_idmap_unregister(struct nfs_client *clp,
+				      struct rpc_pipe *pipe)
+{
+	struct net *net = clp->net;
+	struct super_block *pipefs_sb;
+
+	pipefs_sb = rpc_get_sb_net(net);
+	if (pipefs_sb) {
+		__nfs_idmap_unregister(pipe);
+		rpc_put_sb_net(net);
+	}
+}
+
+static int nfs_idmap_register(struct nfs_client *clp,
+				   struct idmap *idmap,
+				   struct rpc_pipe *pipe)
+{
+	struct net *net = clp->net;
+	struct super_block *pipefs_sb;
+	int err = 0;
+
+	pipefs_sb = rpc_get_sb_net(net);
+	if (pipefs_sb) {
+		if (clp->cl_rpcclient->cl_dentry)
+			err = __nfs_idmap_register(clp->cl_rpcclient->cl_dentry,
+						   idmap, pipe);
+		rpc_put_sb_net(net);
+	}
+	return err;
+}
+
 int
 nfs_idmap_new(struct nfs_client *clp)
 {
 	struct idmap *idmap;
+	struct rpc_pipe *pipe;
 	int error;
 
 	BUG_ON(clp->cl_idmap != NULL);
@@ -443,19 +455,19 @@ nfs_idmap_new(struct nfs_client *clp)
 	if (idmap == NULL)
 		return -ENOMEM;
 
-	idmap->idmap_dentry = rpc_mkpipe(clp->cl_rpcclient->cl_path.dentry,
-			"idmap", idmap, &idmap_upcall_ops, 0);
-	if (IS_ERR(idmap->idmap_dentry)) {
-		error = PTR_ERR(idmap->idmap_dentry);
+	pipe = rpc_mkpipe_data(&idmap_upcall_ops, 0);
+	if (IS_ERR(pipe)) {
+		error = PTR_ERR(pipe);
 		kfree(idmap);
 		return error;
 	}
-
-	mutex_init(&idmap->idmap_lock);
-	mutex_init(&idmap->idmap_im_lock);
-	init_waitqueue_head(&idmap->idmap_wq);
-	idmap->idmap_user_hash.h_type = IDMAP_TYPE_USER;
-	idmap->idmap_group_hash.h_type = IDMAP_TYPE_GROUP;
+	error = nfs_idmap_register(clp, idmap, pipe);
+	if (error) {
+		rpc_destroy_pipe_data(pipe);
+		kfree(idmap);
+		return error;
+	}
+	idmap->idmap_pipe = pipe;
 
 	clp->cl_idmap = idmap;
 	return 0;
@@ -468,211 +480,220 @@ nfs_idmap_delete(struct nfs_client *clp)
 
 	if (!idmap)
 		return;
-	rpc_unlink(idmap->idmap_dentry);
+	nfs_idmap_unregister(clp, idmap->idmap_pipe);
+	rpc_destroy_pipe_data(idmap->idmap_pipe);
 	clp->cl_idmap = NULL;
 	kfree(idmap);
 }
 
-/*
- * Helper routines for manipulating the hashtable
- */
-static inline struct idmap_hashent *
-idmap_name_hash(struct idmap_hashtable* h, const char *name, size_t len)
-{
-	return &h->h_entries[fnvhash32(name, len) % IDMAP_HASH_SZ];
-}
-
-static struct idmap_hashent *
-idmap_lookup_name(struct idmap_hashtable *h, const char *name, size_t len)
+static int __rpc_pipefs_event(struct nfs_client *clp, unsigned long event,
+			      struct super_block *sb)
 {
-	struct idmap_hashent *he = idmap_name_hash(h, name, len);
+	int err = 0;
 
-	if (he->ih_namelen != len || memcmp(he->ih_name, name, len) != 0)
-		return NULL;
-	if (time_after(jiffies, he->ih_expires))
-		return NULL;
-	return he;
+	switch (event) {
+	case RPC_PIPEFS_MOUNT:
+		BUG_ON(clp->cl_rpcclient->cl_dentry == NULL);
+		err = __nfs_idmap_register(clp->cl_rpcclient->cl_dentry,
+						clp->cl_idmap,
+						clp->cl_idmap->idmap_pipe);
+		break;
+	case RPC_PIPEFS_UMOUNT:
+		if (clp->cl_idmap->idmap_pipe) {
+			struct dentry *parent;
+
+			parent = clp->cl_idmap->idmap_pipe->dentry->d_parent;
+			__nfs_idmap_unregister(clp->cl_idmap->idmap_pipe);
+			/*
+			 * Note: This is a dirty hack. SUNRPC hook has been
+			 * called already but simple_rmdir() call for the
+			 * directory returned with error because of idmap pipe
+			 * inside. Thus now we have to remove this directory
+			 * here.
+			 */
+			if (rpc_rmdir(parent))
+				printk(KERN_ERR "NFS: %s: failed to remove "
+					"clnt dir!\n", __func__);
+		}
+		break;
+	default:
+		printk(KERN_ERR "NFS: %s: unknown event: %ld\n", __func__,
+			event);
+		return -ENOTSUPP;
+	}
+	return err;
+}
+
+static struct nfs_client *nfs_get_client_for_event(struct net *net, int event)
+{
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+	struct dentry *cl_dentry;
+	struct nfs_client *clp;
+
+	spin_lock(&nn->nfs_client_lock);
+	list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
+		if (clp->rpc_ops != &nfs_v4_clientops)
+			continue;
+		cl_dentry = clp->cl_idmap->idmap_pipe->dentry;
+		if (((event == RPC_PIPEFS_MOUNT) && cl_dentry) ||
+		    ((event == RPC_PIPEFS_UMOUNT) && !cl_dentry))
+			continue;
+		atomic_inc(&clp->cl_count);
+		spin_unlock(&nn->nfs_client_lock);
+		return clp;
+	}
+	spin_unlock(&nn->nfs_client_lock);
+	return NULL;
 }
 
-static inline struct idmap_hashent *
-idmap_id_hash(struct idmap_hashtable* h, __u32 id)
+static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
+			    void *ptr)
 {
-	return &h->h_entries[fnvhash32(&id, sizeof(id)) % IDMAP_HASH_SZ];
-}
+	struct super_block *sb = ptr;
+	struct nfs_client *clp;
+	int error = 0;
 
-static struct idmap_hashent *
-idmap_lookup_id(struct idmap_hashtable *h, __u32 id)
-{
-	struct idmap_hashent *he = idmap_id_hash(h, id);
-	if (he->ih_id != id || he->ih_namelen == 0)
-		return NULL;
-	if (time_after(jiffies, he->ih_expires))
-		return NULL;
-	return he;
+	while ((clp = nfs_get_client_for_event(sb->s_fs_info, event))) {
+		error = __rpc_pipefs_event(clp, event, sb);
+		nfs_put_client(clp);
+		if (error)
+			break;
+	}
+	return error;
 }
 
-/*
- * Routines for allocating new entries in the hashtable.
- * For now, we just have 1 entry per bucket, so it's all
- * pretty trivial.
- */
-static inline struct idmap_hashent *
-idmap_alloc_name(struct idmap_hashtable *h, char *name, size_t len)
-{
-	return idmap_name_hash(h, name, len);
-}
+#define PIPEFS_NFS_PRIO		1
+
+static struct notifier_block nfs_idmap_block = {
+	.notifier_call	= rpc_pipefs_event,
+	.priority	= SUNRPC_PIPEFS_NFS_PRIO,
+};
 
-static inline struct idmap_hashent *
-idmap_alloc_id(struct idmap_hashtable *h, __u32 id)
+int nfs_idmap_init(void)
 {
-	return idmap_id_hash(h, id);
+	int ret;
+	ret = nfs_idmap_init_keyring();
+	if (ret != 0)
+		goto out;
+	ret = rpc_pipefs_notifier_register(&nfs_idmap_block);
+	if (ret != 0)
+		nfs_idmap_quit_keyring();
+out:
+	return ret;
 }
 
-static void
-idmap_update_entry(struct idmap_hashent *he, const char *name,
-		size_t namelen, __u32 id)
+void nfs_idmap_quit(void)
 {
-	he->ih_id = id;
-	memcpy(he->ih_name, name, namelen);
-	he->ih_name[namelen] = '\0';
-	he->ih_namelen = namelen;
-	he->ih_expires = jiffies + nfs_idmap_cache_timeout;
+	rpc_pipefs_notifier_unregister(&nfs_idmap_block);
+	nfs_idmap_quit_keyring();
 }
 
-/*
- * Name -> ID
- */
-static int
-nfs_idmap_id(struct idmap *idmap, struct idmap_hashtable *h,
-		const char *name, size_t namelen, __u32 *id)
+static int nfs_idmap_prepare_message(char *desc, struct idmap_msg *im,
+				     struct rpc_pipe_msg *msg)
 {
-	struct rpc_pipe_msg msg;
-	struct idmap_msg *im;
-	struct idmap_hashent *he;
-	DECLARE_WAITQUEUE(wq, current);
-	int ret = -EIO;
-
-	im = &idmap->idmap_im;
-
-	/*
-	 * String sanity checks
-	 * Note that the userland daemon expects NUL terminated strings
-	 */
-	for (;;) {
-		if (namelen == 0)
-			return -EINVAL;
-		if (name[namelen-1] != '\0')
-			break;
-		namelen--;
-	}
-	if (namelen >= IDMAP_NAMESZ)
-		return -EINVAL;
+	substring_t substr;
+	int token, ret;
 
-	mutex_lock(&idmap->idmap_lock);
-	mutex_lock(&idmap->idmap_im_lock);
-
-	he = idmap_lookup_name(h, name, namelen);
-	if (he != NULL) {
-		*id = he->ih_id;
-		ret = 0;
-		goto out;
-	}
+	memset(im,  0, sizeof(*im));
+	memset(msg, 0, sizeof(*msg));
 
-	memset(im, 0, sizeof(*im));
-	memcpy(im->im_name, name, namelen);
+	im->im_type = IDMAP_TYPE_GROUP;
+	token = match_token(desc, nfs_idmap_tokens, &substr);
 
-	im->im_type = h->h_type;
-	im->im_conv = IDMAP_CONV_NAMETOID;
+	switch (token) {
+	case Opt_find_uid:
+		im->im_type = IDMAP_TYPE_USER;
+	case Opt_find_gid:
+		im->im_conv = IDMAP_CONV_NAMETOID;
+		ret = match_strlcpy(im->im_name, &substr, IDMAP_NAMESZ);
+		break;
 
-	memset(&msg, 0, sizeof(msg));
-	msg.data = im;
-	msg.len = sizeof(*im);
+	case Opt_find_user:
+		im->im_type = IDMAP_TYPE_USER;
+	case Opt_find_group:
+		im->im_conv = IDMAP_CONV_IDTONAME;
+		ret = match_int(&substr, &im->im_id);
+		break;
 
-	add_wait_queue(&idmap->idmap_wq, &wq);
-	if (rpc_queue_upcall(idmap->idmap_dentry->d_inode, &msg) < 0) {
-		remove_wait_queue(&idmap->idmap_wq, &wq);
+	default:
+		ret = -EINVAL;
 		goto out;
 	}
 
-	set_current_state(TASK_UNINTERRUPTIBLE);
-	mutex_unlock(&idmap->idmap_im_lock);
-	schedule();
-	__set_current_state(TASK_RUNNING);
-	remove_wait_queue(&idmap->idmap_wq, &wq);
-	mutex_lock(&idmap->idmap_im_lock);
+	msg->data = im;
+	msg->len  = sizeof(struct idmap_msg);
 
-	if (im->im_status & IDMAP_STATUS_SUCCESS) {
-		*id = im->im_id;
-		ret = 0;
-	}
-
- out:
-	memset(im, 0, sizeof(*im));
-	mutex_unlock(&idmap->idmap_im_lock);
-	mutex_unlock(&idmap->idmap_lock);
+out:
 	return ret;
 }
 
-/*
- * ID -> Name
- */
-static int
-nfs_idmap_name(struct idmap *idmap, struct idmap_hashtable *h,
-		__u32 id, char *name)
+static int nfs_idmap_legacy_upcall(struct key_construction *cons,
+				   const char *op,
+				   void *aux)
 {
-	struct rpc_pipe_msg msg;
+	struct rpc_pipe_msg *msg;
 	struct idmap_msg *im;
-	struct idmap_hashent *he;
-	DECLARE_WAITQUEUE(wq, current);
-	int ret = -EIO;
-	unsigned int len;
-
-	im = &idmap->idmap_im;
+	struct idmap *idmap = (struct idmap *)aux;
+	struct key *key = cons->key;
+	int ret;
 
-	mutex_lock(&idmap->idmap_lock);
-	mutex_lock(&idmap->idmap_im_lock);
+	/* msg and im are freed in idmap_pipe_destroy_msg */
+	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
+	if (IS_ERR(msg)) {
+		ret = PTR_ERR(msg);
+		goto out0;
+	}
 
-	he = idmap_lookup_id(h, id);
-	if (he) {
-		memcpy(name, he->ih_name, he->ih_namelen);
-		ret = he->ih_namelen;
-		goto out;
+	im = kmalloc(sizeof(*im), GFP_KERNEL);
+	if (IS_ERR(im)) {
+		ret = PTR_ERR(im);
+		goto out1;
 	}
 
-	memset(im, 0, sizeof(*im));
-	im->im_type = h->h_type;
-	im->im_conv = IDMAP_CONV_IDTONAME;
-	im->im_id = id;
+	ret = nfs_idmap_prepare_message(key->description, im, msg);
+	if (ret < 0)
+		goto out2;
 
-	memset(&msg, 0, sizeof(msg));
-	msg.data = im;
-	msg.len = sizeof(*im);
+	idmap->idmap_key_cons = cons;
 
-	add_wait_queue(&idmap->idmap_wq, &wq);
+	ret = rpc_queue_upcall(idmap->idmap_pipe, msg);
+	if (ret < 0)
+		goto out2;
 
-	if (rpc_queue_upcall(idmap->idmap_dentry->d_inode, &msg) < 0) {
-		remove_wait_queue(&idmap->idmap_wq, &wq);
-		goto out;
-	}
+	return ret;
+
+out2:
+	kfree(im);
+out1:
+	kfree(msg);
+out0:
+	key_revoke(cons->key);
+	key_revoke(cons->authkey);
+	return ret;
+}
+
+static int nfs_idmap_instantiate(struct key *key, struct key *authkey, char *data)
+{
+	return key_instantiate_and_link(key, data, strlen(data) + 1,
+					id_resolver_cache->thread_keyring,
+					authkey);
+}
 
-	set_current_state(TASK_UNINTERRUPTIBLE);
-	mutex_unlock(&idmap->idmap_im_lock);
-	schedule();
-	__set_current_state(TASK_RUNNING);
-	remove_wait_queue(&idmap->idmap_wq, &wq);
-	mutex_lock(&idmap->idmap_im_lock);
-
-	if (im->im_status & IDMAP_STATUS_SUCCESS) {
-		if ((len = strnlen(im->im_name, IDMAP_NAMESZ)) == 0)
-			goto out;
-		memcpy(name, im->im_name, len);
-		ret = len;
+static int nfs_idmap_read_message(struct idmap_msg *im, struct key *key, struct key *authkey)
+{
+	char id_str[NFS_UINT_MAXLEN];
+	int ret = -EINVAL;
+
+	switch (im->im_conv) {
+	case IDMAP_CONV_NAMETOID:
+		sprintf(id_str, "%d", im->im_id);
+		ret = nfs_idmap_instantiate(key, authkey, id_str);
+		break;
+	case IDMAP_CONV_IDTONAME:
+		ret = nfs_idmap_instantiate(key, authkey, im->im_name);
+		break;
 	}
 
- out:
-	memset(im, 0, sizeof(*im));
-	mutex_unlock(&idmap->idmap_im_lock);
-	mutex_unlock(&idmap->idmap_lock);
 	return ret;
 }
 
@@ -681,115 +702,51 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 {
 	struct rpc_inode *rpci = RPC_I(filp->f_path.dentry->d_inode);
 	struct idmap *idmap = (struct idmap *)rpci->private;
-	struct idmap_msg im_in, *im = &idmap->idmap_im;
-	struct idmap_hashtable *h;
-	struct idmap_hashent *he = NULL;
+	struct key_construction *cons = idmap->idmap_key_cons;
+	struct idmap_msg im;
 	size_t namelen_in;
 	int ret;
 
-	if (mlen != sizeof(im_in))
-		return -ENOSPC;
-
-	if (copy_from_user(&im_in, src, mlen) != 0)
-		return -EFAULT;
-
-	mutex_lock(&idmap->idmap_im_lock);
-
-	ret = mlen;
-	im->im_status = im_in.im_status;
-	/* If we got an error, terminate now, and wake up pending upcalls */
-	if (!(im_in.im_status & IDMAP_STATUS_SUCCESS)) {
-		wake_up(&idmap->idmap_wq);
+	if (mlen != sizeof(im)) {
+		ret = -ENOSPC;
 		goto out;
 	}
 
-	/* Sanity checking of strings */
-	ret = -EINVAL;
-	namelen_in = strnlen(im_in.im_name, IDMAP_NAMESZ);
-	if (namelen_in == 0 || namelen_in == IDMAP_NAMESZ)
+	if (copy_from_user(&im, src, mlen) != 0) {
+		ret = -EFAULT;
 		goto out;
+	}
 
-	switch (im_in.im_type) {
-		case IDMAP_TYPE_USER:
-			h = &idmap->idmap_user_hash;
-			break;
-		case IDMAP_TYPE_GROUP:
-			h = &idmap->idmap_group_hash;
-			break;
-		default:
-			goto out;
+	if (!(im.im_status & IDMAP_STATUS_SUCCESS)) {
+		ret = mlen;
+		complete_request_key(idmap->idmap_key_cons, -ENOKEY);
+		goto out_incomplete;
 	}
 
-	switch (im_in.im_conv) {
-	case IDMAP_CONV_IDTONAME:
-		/* Did we match the current upcall? */
-		if (im->im_conv == IDMAP_CONV_IDTONAME
-				&& im->im_type == im_in.im_type
-				&& im->im_id == im_in.im_id) {
-			/* Yes: copy string, including the terminating '\0'  */
-			memcpy(im->im_name, im_in.im_name, namelen_in);
-			im->im_name[namelen_in] = '\0';
-			wake_up(&idmap->idmap_wq);
-		}
-		he = idmap_alloc_id(h, im_in.im_id);
-		break;
-	case IDMAP_CONV_NAMETOID:
-		/* Did we match the current upcall? */
-		if (im->im_conv == IDMAP_CONV_NAMETOID
-				&& im->im_type == im_in.im_type
-				&& strnlen(im->im_name, IDMAP_NAMESZ) == namelen_in
-				&& memcmp(im->im_name, im_in.im_name, namelen_in) == 0) {
-			im->im_id = im_in.im_id;
-			wake_up(&idmap->idmap_wq);
-		}
-		he = idmap_alloc_name(h, im_in.im_name, namelen_in);
-		break;
-	default:
+	namelen_in = strnlen(im.im_name, IDMAP_NAMESZ);
+	if (namelen_in == 0 || namelen_in == IDMAP_NAMESZ) {
+		ret = -EINVAL;
 		goto out;
 	}
 
-	/* If the entry is valid, also copy it to the cache */
-	if (he != NULL)
-		idmap_update_entry(he, im_in.im_name, namelen_in, im_in.im_id);
-	ret = mlen;
+	ret = nfs_idmap_read_message(&im, cons->key, cons->authkey);
+	if (ret >= 0) {
+		key_set_timeout(cons->key, nfs_idmap_cache_timeout);
+		ret = mlen;
+	}
+
 out:
-	mutex_unlock(&idmap->idmap_im_lock);
+	complete_request_key(idmap->idmap_key_cons, ret);
+out_incomplete:
 	return ret;
 }
 
 static void
 idmap_pipe_destroy_msg(struct rpc_pipe_msg *msg)
 {
-	struct idmap_msg *im = msg->data;
-	struct idmap *idmap = container_of(im, struct idmap, idmap_im); 
-
-	if (msg->errno >= 0)
-		return;
-	mutex_lock(&idmap->idmap_im_lock);
-	im->im_status = IDMAP_STATUS_LOOKUPFAIL;
-	wake_up(&idmap->idmap_wq);
-	mutex_unlock(&idmap->idmap_im_lock);
-}
-
-/* 
- * Fowler/Noll/Vo hash
- *    http://www.isthe.com/chongo/tech/comp/fnv/
- */
-
-#define FNV_P_32 ((unsigned int)0x01000193) /* 16777619 */
-#define FNV_1_32 ((unsigned int)0x811c9dc5) /* 2166136261 */
-
-static unsigned int fnvhash32(const void *buf, size_t buflen)
-{
-	const unsigned char *p, *end = (const unsigned char *)buf + buflen;
-	unsigned int hash = FNV_1_32;
-
-	for (p = buf; p < end; p++) {
-		hash *= FNV_P_32;
-		hash ^= (unsigned int)*p;
-	}
-
-	return hash;
+	/* Free memory allocated in nfs_idmap_legacy_upcall() */
+	kfree(msg->data);
+	kfree(msg);
 }
 
 int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid)
@@ -798,16 +755,16 @@ int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_
 
 	if (nfs_map_string_to_numeric(name, namelen, uid))
 		return 0;
-	return nfs_idmap_id(idmap, &idmap->idmap_user_hash, name, namelen, uid);
+	return nfs_idmap_lookup_id(name, namelen, "uid", uid, idmap);
 }
 
-int nfs_map_group_to_gid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid)
+int nfs_map_group_to_gid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *gid)
 {
 	struct idmap *idmap = server->nfs_client->cl_idmap;
 
-	if (nfs_map_string_to_numeric(name, namelen, uid))
+	if (nfs_map_string_to_numeric(name, namelen, gid))
 		return 0;
-	return nfs_idmap_id(idmap, &idmap->idmap_group_hash, name, namelen, uid);
+	return nfs_idmap_lookup_id(name, namelen, "gid", gid, idmap);
 }
 
 int nfs_map_uid_to_name(const struct nfs_server *server, __u32 uid, char *buf, size_t buflen)
@@ -816,21 +773,19 @@ int nfs_map_uid_to_name(const struct nfs_server *server, __u32 uid, char *buf, s
 	int ret = -EINVAL;
 
 	if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
-		ret = nfs_idmap_name(idmap, &idmap->idmap_user_hash, uid, buf);
+		ret = nfs_idmap_lookup_name(uid, "user", buf, buflen, idmap);
 	if (ret < 0)
 		ret = nfs_map_numeric_to_string(uid, buf, buflen);
 	return ret;
 }
-int nfs_map_gid_to_group(const struct nfs_server *server, __u32 uid, char *buf, size_t buflen)
+int nfs_map_gid_to_group(const struct nfs_server *server, __u32 gid, char *buf, size_t buflen)
 {
 	struct idmap *idmap = server->nfs_client->cl_idmap;
 	int ret = -EINVAL;
 
 	if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
-		ret = nfs_idmap_name(idmap, &idmap->idmap_group_hash, uid, buf);
+		ret = nfs_idmap_lookup_name(gid, "group", buf, buflen, idmap);
 	if (ret < 0)
-		ret = nfs_map_numeric_to_string(uid, buf, buflen);
+		ret = nfs_map_numeric_to_string(gid, buf, buflen);
 	return ret;
 }
-
-#endif /* CONFIG_NFS_USE_NEW_IDMAPPER */

fs/nfs/inode.c

@@ -39,6 +39,7 @@
 #include <linux/slab.h>
 #include <linux/compat.h>
 #include <linux/freezer.h>
+#include <linux/crc32.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -51,6 +52,7 @@
 #include "fscache.h"
 #include "dns_resolve.h"
 #include "pnfs.h"
+#include "netns.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
 
@@ -388,9 +390,10 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		unlock_new_inode(inode);
 	} else
 		nfs_refresh_inode(inode, fattr);
-	dprintk("NFS: nfs_fhget(%s/%Ld ct=%d)\n",
+	dprintk("NFS: nfs_fhget(%s/%Ld fh_crc=0x%08x ct=%d)\n",
 		inode->i_sb->s_id,
 		(long long)NFS_FILEID(inode),
+		nfs_display_fhandle_hash(fh),
 		atomic_read(&inode->i_count));
 
 out:
@@ -401,7 +404,7 @@ out_no_inode:
 	goto out;
 }
 
-#define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE)
+#define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE|ATTR_OPEN)
 
 int
 nfs_setattr(struct dentry *dentry, struct iattr *attr)
@@ -423,7 +426,7 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
 
 	/* Optimization: if the end result is no change, don't RPC */
 	attr->ia_valid &= NFS_VALID_ATTRS;
-	if ((attr->ia_valid & ~ATTR_FILE) == 0)
+	if ((attr->ia_valid & ~(ATTR_FILE|ATTR_OPEN)) == 0)
 		return 0;
 
 	/* Write all dirty data */
@@ -1044,6 +1047,67 @@ struct nfs_fh *nfs_alloc_fhandle(void)
 	return fh;
 }
 
+#ifdef NFS_DEBUG
+/*
+ * _nfs_display_fhandle_hash - calculate the crc32 hash for the filehandle
+ *                             in the same way that wireshark does
+ *
+ * @fh: file handle
+ *
+ * For debugging only.
+ */
+u32 _nfs_display_fhandle_hash(const struct nfs_fh *fh)
+{
+	/* wireshark uses 32-bit AUTODIN crc and does a bitwise
+	 * not on the result */
+	return ~crc32(0xFFFFFFFF, &fh->data[0], fh->size);
+}
+
+/*
+ * _nfs_display_fhandle - display an NFS file handle on the console
+ *
+ * @fh: file handle to display
+ * @caption: display caption
+ *
+ * For debugging only.
+ */
+void _nfs_display_fhandle(const struct nfs_fh *fh, const char *caption)
+{
+	unsigned short i;
+
+	if (fh == NULL || fh->size == 0) {
+		printk(KERN_DEFAULT "%s at %p is empty\n", caption, fh);
+		return;
+	}
+
+	printk(KERN_DEFAULT "%s at %p is %u bytes, crc: 0x%08x:\n",
+	       caption, fh, fh->size, _nfs_display_fhandle_hash(fh));
+	for (i = 0; i < fh->size; i += 16) {
+		__be32 *pos = (__be32 *)&fh->data[i];
+
+		switch ((fh->size - i - 1) >> 2) {
+		case 0:
+			printk(KERN_DEFAULT " %08x\n",
+				be32_to_cpup(pos));
+			break;
+		case 1:
+			printk(KERN_DEFAULT " %08x %08x\n",
+				be32_to_cpup(pos), be32_to_cpup(pos + 1));
+			break;
+		case 2:
+			printk(KERN_DEFAULT " %08x %08x %08x\n",
+				be32_to_cpup(pos), be32_to_cpup(pos + 1),
+				be32_to_cpup(pos + 2));
+			break;
+		default:
+			printk(KERN_DEFAULT " %08x %08x %08x %08x\n",
+				be32_to_cpup(pos), be32_to_cpup(pos + 1),
+				be32_to_cpup(pos + 2), be32_to_cpup(pos + 3));
+		}
+	}
+}
+#endif
+
 /**
  * nfs_inode_attrs_need_update - check if the inode attributes need updating
  * @inode - pointer to inode
@@ -1211,8 +1275,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	unsigned long now = jiffies;
 	unsigned long save_cache_validity;
 
-	dfprintk(VFS, "NFS: %s(%s/%ld ct=%d info=0x%x)\n",
+	dfprintk(VFS, "NFS: %s(%s/%ld fh_crc=0x%08x ct=%d info=0x%x)\n",
 			__func__, inode->i_sb->s_id, inode->i_ino,
+			nfs_display_fhandle_hash(NFS_FH(inode)),
 			atomic_read(&inode->i_count), fattr->valid);
 
 	if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
@@ -1406,7 +1471,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	/*
 	 * Big trouble! The inode has become a different object.
 	 */
-	printk(KERN_DEBUG "%s: inode %ld mode changed, %07o to %07o\n",
+	printk(KERN_DEBUG "NFS: %s: inode %ld mode changed, %07o to %07o\n",
 			__func__, inode->i_ino, inode->i_mode, fattr->mode);
  out_err:
 	/*
@@ -1495,7 +1560,7 @@ static void init_once(void *foo)
 	INIT_LIST_HEAD(&nfsi->open_files);
 	INIT_LIST_HEAD(&nfsi->access_cache_entry_lru);
 	INIT_LIST_HEAD(&nfsi->access_cache_inode_lru);
-	INIT_RADIX_TREE(&nfsi->nfs_page_tree, GFP_ATOMIC);
+	INIT_LIST_HEAD(&nfsi->commit_list);
 	nfsi->npages = 0;
 	nfsi->ncommit = 0;
 	atomic_set(&nfsi->silly_count, 1);
@@ -1552,6 +1617,28 @@ static void nfsiod_stop(void)
 	destroy_workqueue(wq);
 }
 
+int nfs_net_id;
+EXPORT_SYMBOL_GPL(nfs_net_id);
+
+static int nfs_net_init(struct net *net)
+{
+	nfs_clients_init(net);
+	return nfs_dns_resolver_cache_init(net);
+}
+
+static void nfs_net_exit(struct net *net)
+{
+	nfs_dns_resolver_cache_destroy(net);
+	nfs_cleanup_cb_ident_idr(net);
+}
+
+static struct pernet_operations nfs_net_ops = {
+	.init = nfs_net_init,
+	.exit = nfs_net_exit,
+	.id   = &nfs_net_id,
+	.size = sizeof(struct nfs_net),
+};
+
 /*
  * Initialize NFS
  */
@@ -1561,9 +1648,13 @@ static int __init init_nfs_fs(void)
 
 	err = nfs_idmap_init();
 	if (err < 0)
-		goto out9;
+		goto out10;
 
 	err = nfs_dns_resolver_init();
+	if (err < 0)
+		goto out9;
+
+	err = register_pernet_subsys(&nfs_net_ops);
 	if (err < 0)
 		goto out8;
 
@@ -1600,14 +1691,14 @@ static int __init init_nfs_fs(void)
 		goto out0;
 
 #ifdef CONFIG_PROC_FS
-	rpc_proc_register(&nfs_rpcstat);
+	rpc_proc_register(&init_net, &nfs_rpcstat);
 #endif
 	if ((err = register_nfs_fs()) != 0)
 		goto out;
 	return 0;
 out:
 #ifdef CONFIG_PROC_FS
-	rpc_proc_unregister("nfs");
+	rpc_proc_unregister(&init_net, "nfs");
 #endif
 	nfs_destroy_directcache();
 out0:
@@ -1625,10 +1716,12 @@ out5:
 out6:
 	nfs_fscache_unregister();
 out7:
-	nfs_dns_resolver_destroy();
+	unregister_pernet_subsys(&nfs_net_ops);
 out8:
-	nfs_idmap_quit();
+	nfs_dns_resolver_destroy();
 out9:
+	nfs_idmap_quit();
+out10:
 	return err;
 }
 
@@ -1640,12 +1733,12 @@ static void __exit exit_nfs_fs(void)
 	nfs_destroy_inodecache();
 	nfs_destroy_nfspagecache();
 	nfs_fscache_unregister();
+	unregister_pernet_subsys(&nfs_net_ops);
 	nfs_dns_resolver_destroy();
 	nfs_idmap_quit();
 #ifdef CONFIG_PROC_FS
-	rpc_proc_unregister("nfs");
+	rpc_proc_unregister(&init_net, "nfs");
 #endif
-	nfs_cleanup_cb_ident_idr();
 	unregister_nfs_fs();
 	nfs_fs_proc_exit();
 	nfsiod_stop();

fs/nfs/internal.h

@@ -123,6 +123,7 @@ struct nfs_parsed_mount_data {
 	} nfs_server;
 
 	struct security_mnt_opts lsm_opts;
+	struct net		*net;
 };
 
 /* mount_clnt.c */
@@ -137,20 +138,22 @@ struct nfs_mount_request {
 	int			noresvport;
 	unsigned int		*auth_flav_len;
 	rpc_authflavor_t	*auth_flavs;
+	struct net		*net;
 };
 
 extern int nfs_mount(struct nfs_mount_request *info);
 extern void nfs_umount(const struct nfs_mount_request *info);
 
 /* client.c */
-extern struct rpc_program nfs_program;
+extern const struct rpc_program nfs_program;
+extern void nfs_clients_init(struct net *net);
 
-extern void nfs_cleanup_cb_ident_idr(void);
+extern void nfs_cleanup_cb_ident_idr(struct net *);
 extern void nfs_put_client(struct nfs_client *);
-extern struct nfs_client *nfs4_find_client_no_ident(const struct sockaddr *);
-extern struct nfs_client *nfs4_find_client_ident(int);
+extern struct nfs_client *nfs4_find_client_ident(struct net *, int);
 extern struct nfs_client *
-nfs4_find_client_sessionid(const struct sockaddr *, struct nfs4_sessionid *);
+nfs4_find_client_sessionid(struct net *, const struct sockaddr *,
+				struct nfs4_sessionid *);
 extern struct nfs_server *nfs_create_server(
 					const struct nfs_parsed_mount_data *,
 					struct nfs_fh *);
@@ -329,6 +332,8 @@ void nfs_retry_commit(struct list_head *page_list,
 void nfs_commit_clear_lock(struct nfs_inode *nfsi);
 void nfs_commitdata_release(void *data);
 void nfs_commit_release_pages(struct nfs_write_data *data);
+void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *head);
+void nfs_request_remove_commit_list(struct nfs_page *req);
 
 #ifdef CONFIG_MIGRATION
 extern int nfs_migrate_page(struct address_space *,

fs/nfs/mount_clnt.c

@@ -16,7 +16,7 @@
 #include <linux/nfs_fs.h>
 #include "internal.h"
 
-#ifdef RPC_DEBUG
+#ifdef NFS_DEBUG
 # define NFSDBG_FACILITY	NFSDBG_MOUNT
 #endif
 
@@ -67,7 +67,7 @@ enum {
 	MOUNTPROC3_EXPORT	= 5,
 };
 
-static struct rpc_program	mnt_program;
+static const struct rpc_program mnt_program;
 
 /*
  * Defined by OpenGroup XNFS Version 3W, chapter 8
@@ -153,7 +153,7 @@ int nfs_mount(struct nfs_mount_request *info)
 		.rpc_resp	= &result,
 	};
 	struct rpc_create_args args = {
-		.net		= &init_net,
+		.net		= info->net,
 		.protocol	= info->protocol,
 		.address	= info->sap,
 		.addrsize	= info->salen,
@@ -225,7 +225,7 @@ void nfs_umount(const struct nfs_mount_request *info)
 		.to_retries = 2,
 	};
 	struct rpc_create_args args = {
-		.net		= &init_net,
+		.net		= info->net,
 		.protocol	= IPPROTO_UDP,
 		.address	= info->sap,
 		.addrsize	= info->salen,
@@ -488,19 +488,19 @@ static struct rpc_procinfo mnt3_procedures[] = {
 };
 
 
-static struct rpc_version mnt_version1 = {
+static const struct rpc_version mnt_version1 = {
 	.number		= 1,
 	.nrprocs	= ARRAY_SIZE(mnt_procedures),
 	.procs		= mnt_procedures,
 };
 
-static struct rpc_version mnt_version3 = {
+static const struct rpc_version mnt_version3 = {
 	.number		= 3,
 	.nrprocs	= ARRAY_SIZE(mnt3_procedures),
 	.procs		= mnt3_procedures,
 };
 
-static struct rpc_version *mnt_version[] = {
+static const struct rpc_version *mnt_version[] = {
 	NULL,
 	&mnt_version1,
 	NULL,
@@ -509,7 +509,7 @@ static struct rpc_version *mnt_version[] = {
 
 static struct rpc_stat mnt_stats;
 
-static struct rpc_program mnt_program = {
+static const struct rpc_program mnt_program = {
 	.name		= "mount",
 	.number		= NFS_MNT_PROGRAM,
 	.nrvers		= ARRAY_SIZE(mnt_version),

fs/nfs/namespace.c

@@ -276,7 +276,10 @@ out:
 	nfs_free_fattr(fattr);
 	nfs_free_fhandle(fh);
 out_nofree:
-	dprintk("<-- nfs_follow_mountpoint() = %p\n", mnt);
+	if (IS_ERR(mnt))
+		dprintk("<-- %s(): error %ld\n", __func__, PTR_ERR(mnt));
+	else
+		dprintk("<-- %s() = %p\n", __func__, mnt);
 	return mnt;
 }
 

fs/nfs/netns.h

@@ -0,0 +1,27 @@
+#ifndef __NFS_NETNS_H__
+#define __NFS_NETNS_H__
+
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+
+struct bl_dev_msg {
+	int32_t status;
+	uint32_t major, minor;
+};
+
+struct nfs_net {
+	struct cache_detail *nfs_dns_resolve;
+	struct rpc_pipe *bl_device_pipe;
+	struct bl_dev_msg bl_mount_reply;
+	wait_queue_head_t bl_wq;
+	struct list_head nfs_client_list;
+	struct list_head nfs_volume_list;
+#ifdef CONFIG_NFS_V4
+	struct idr cb_ident_idr; /* Protected by nfs_client_lock */
+#endif
+	spinlock_t nfs_client_lock;
+};
+
+extern int nfs_net_id;
+
+#endif

fs/nfs/nfs2xdr.c

@@ -1150,7 +1150,7 @@ struct rpc_procinfo	nfs_procedures[] = {
 	PROC(STATFS,	fhandle,	statfsres,	0),
 };
 
-struct rpc_version		nfs_version2 = {
+const struct rpc_version nfs_version2 = {
 	.number			= 2,
 	.nrprocs		= ARRAY_SIZE(nfs_procedures),
 	.procs			= nfs_procedures

fs/nfs/nfs3acl.c

@@ -192,7 +192,7 @@ struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type)
 		.pages = pages,
 	};
 	struct nfs3_getaclres res = {
-		0
+		NULL,
 	};
 	struct rpc_message msg = {
 		.rpc_argp	= &args,

fs/nfs/nfs3proc.c

@@ -428,6 +428,11 @@ nfs3_proc_unlink_setup(struct rpc_message *msg, struct inode *dir)
 	msg->rpc_proc = &nfs3_procedures[NFS3PROC_REMOVE];
 }
 
+static void nfs3_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data)
+{
+	rpc_call_start(task);
+}
+
 static int
 nfs3_proc_unlink_done(struct rpc_task *task, struct inode *dir)
 {
@@ -445,6 +450,11 @@ nfs3_proc_rename_setup(struct rpc_message *msg, struct inode *dir)
 	msg->rpc_proc = &nfs3_procedures[NFS3PROC_RENAME];
 }
 
+static void nfs3_proc_rename_rpc_prepare(struct rpc_task *task, struct nfs_renamedata *data)
+{
+	rpc_call_start(task);
+}
+
 static int
 nfs3_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
 		      struct inode *new_dir)
@@ -814,6 +824,11 @@ static void nfs3_proc_read_setup(struct nfs_read_data *data, struct rpc_message
 	msg->rpc_proc = &nfs3_procedures[NFS3PROC_READ];
 }
 
+static void nfs3_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
+{
+	rpc_call_start(task);
+}
+
 static int nfs3_write_done(struct rpc_task *task, struct nfs_write_data *data)
 {
 	if (nfs3_async_handle_jukebox(task, data->inode))
@@ -828,6 +843,11 @@ static void nfs3_proc_write_setup(struct nfs_write_data *data, struct rpc_messag
 	msg->rpc_proc = &nfs3_procedures[NFS3PROC_WRITE];
 }
 
+static void nfs3_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
+{
+	rpc_call_start(task);
+}
+
 static int nfs3_commit_done(struct rpc_task *task, struct nfs_write_data *data)
 {
 	if (nfs3_async_handle_jukebox(task, data->inode))
@@ -864,9 +884,11 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.create		= nfs3_proc_create,
 	.remove		= nfs3_proc_remove,
 	.unlink_setup	= nfs3_proc_unlink_setup,
+	.unlink_rpc_prepare = nfs3_proc_unlink_rpc_prepare,
 	.unlink_done	= nfs3_proc_unlink_done,
 	.rename		= nfs3_proc_rename,
 	.rename_setup	= nfs3_proc_rename_setup,
+	.rename_rpc_prepare = nfs3_proc_rename_rpc_prepare,
 	.rename_done	= nfs3_proc_rename_done,
 	.link		= nfs3_proc_link,
 	.symlink	= nfs3_proc_symlink,
@@ -879,8 +901,10 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.pathconf	= nfs3_proc_pathconf,
 	.decode_dirent	= nfs3_decode_dirent,
 	.read_setup	= nfs3_proc_read_setup,
+	.read_rpc_prepare = nfs3_proc_read_rpc_prepare,
 	.read_done	= nfs3_read_done,
 	.write_setup	= nfs3_proc_write_setup,
+	.write_rpc_prepare = nfs3_proc_write_rpc_prepare,
 	.write_done	= nfs3_write_done,
 	.commit_setup	= nfs3_proc_commit_setup,
 	.commit_done	= nfs3_commit_done,

fs/nfs/nfs3xdr.c

@@ -2461,7 +2461,7 @@ struct rpc_procinfo	nfs3_procedures[] = {
 	PROC(COMMIT,		commit,		commit,		5),
 };
 
-struct rpc_version		nfs_version3 = {
+const struct rpc_version nfs_version3 = {
 	.number			= 3,
 	.nrprocs		= ARRAY_SIZE(nfs3_procedures),
 	.procs			= nfs3_procedures
@@ -2489,7 +2489,7 @@ static struct rpc_procinfo	nfs3_acl_procedures[] = {
 	},
 };
 
-struct rpc_version		nfsacl_version3 = {
+const struct rpc_version nfsacl_version3 = {
 	.number			= 3,
 	.nrprocs		= sizeof(nfs3_acl_procedures)/
 				  sizeof(nfs3_acl_procedures[0]),

fs/nfs/nfs4_fs.h

@@ -20,7 +20,6 @@ enum nfs4_client_state {
 	NFS4CLNT_RECLAIM_REBOOT,
 	NFS4CLNT_RECLAIM_NOGRACE,
 	NFS4CLNT_DELEGRETURN,
-	NFS4CLNT_LAYOUTRECALL,
 	NFS4CLNT_SESSION_RESET,
 	NFS4CLNT_RECALL_SLOT,
 	NFS4CLNT_LEASE_CONFIRM,
@@ -44,7 +43,7 @@ struct nfs4_minor_version_ops {
 			struct nfs4_sequence_args *args,
 			struct nfs4_sequence_res *res,
 			int cache_reply);
-	int	(*validate_stateid)(struct nfs_delegation *,
+	bool	(*match_stateid)(const nfs4_stateid *,
 			const nfs4_stateid *);
 	int	(*find_root_sec)(struct nfs_server *, struct nfs_fh *,
 			struct nfs_fsinfo *);
@@ -53,26 +52,25 @@ struct nfs4_minor_version_ops {
 	const struct nfs4_state_maintenance_ops *state_renewal_ops;
 };
 
-/*
- * struct rpc_sequence ensures that RPC calls are sent in the exact
- * order that they appear on the list.
- */
-struct rpc_sequence {
-	struct rpc_wait_queue	wait;	/* RPC call delay queue */
-	spinlock_t lock;		/* Protects the list */
-	struct list_head list;		/* Defines sequence of RPC calls */
+struct nfs_unique_id {
+	struct rb_node rb_node;
+	__u64 id;
 };
 
 #define NFS_SEQID_CONFIRMED 1
 struct nfs_seqid_counter {
-	struct rpc_sequence *sequence;
+	int owner_id;
 	int flags;
 	u32 counter;
+	spinlock_t lock;		/* Protects the list */
+	struct list_head list;		/* Defines sequence of RPC calls */
+	struct rpc_wait_queue	wait;	/* RPC call delay queue */
 };
 
 struct nfs_seqid {
 	struct nfs_seqid_counter *sequence;
 	struct list_head list;
+	struct rpc_task *task;
 };
 
 static inline void nfs_confirm_seqid(struct nfs_seqid_counter *seqid, int status)
@@ -81,18 +79,12 @@ static inline void nfs_confirm_seqid(struct nfs_seqid_counter *seqid, int status
 		seqid->flags |= NFS_SEQID_CONFIRMED;
 }
 
-struct nfs_unique_id {
-	struct rb_node rb_node;
-	__u64 id;
-};
-
 /*
  * NFS4 state_owners and lock_owners are simply labels for ordered
  * sequences of RPC calls. Their sole purpose is to provide once-only
  * semantics by allowing the server to identify replayed requests.
  */
 struct nfs4_state_owner {
-	struct nfs_unique_id so_owner_id;
 	struct nfs_server    *so_server;
 	struct list_head     so_lru;
 	unsigned long        so_expires;
@@ -105,7 +97,6 @@ struct nfs4_state_owner {
 	unsigned long	     so_flags;
 	struct list_head     so_states;
 	struct nfs_seqid_counter so_seqid;
-	struct rpc_sequence  so_sequence;
 };
 
 enum {
@@ -146,8 +137,6 @@ struct nfs4_lock_state {
 #define NFS_LOCK_INITIALIZED 1
 	int			ls_flags;
 	struct nfs_seqid_counter	ls_seqid;
-	struct rpc_sequence	ls_sequence;
-	struct nfs_unique_id	ls_id;
 	nfs4_stateid		ls_stateid;
 	atomic_t		ls_count;
 	struct nfs4_lock_owner	ls_owner;
@@ -193,6 +182,7 @@ struct nfs4_exception {
 	long timeout;
 	int retry;
 	struct nfs4_state *state;
+	struct inode *inode;
 };
 
 struct nfs4_state_recovery_ops {
@@ -224,7 +214,7 @@ extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, boo
 extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle);
 extern int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name,
 		struct nfs4_fs_locations *fs_locations, struct page *page);
-extern void nfs4_release_lockowner(const struct nfs4_lock_state *);
+extern int nfs4_release_lockowner(struct nfs4_lock_state *);
 extern const struct xattr_handler *nfs4_xattr_handlers[];
 
 #if defined(CONFIG_NFS_V4_1)
@@ -233,12 +223,13 @@ static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *ser
 	return server->nfs_client->cl_session;
 }
 
+extern bool nfs4_set_task_privileged(struct rpc_task *task, void *dummy);
 extern int nfs4_setup_sequence(const struct nfs_server *server,
 		struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
-		int cache_reply, struct rpc_task *task);
+		struct rpc_task *task);
 extern int nfs41_setup_sequence(struct nfs4_session *session,
 		struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
-		int cache_reply, struct rpc_task *task);
+		struct rpc_task *task);
 extern void nfs4_destroy_session(struct nfs4_session *session);
 extern struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp);
 extern int nfs4_proc_create_session(struct nfs_client *);
@@ -269,7 +260,7 @@ static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *ser
 
 static inline int nfs4_setup_sequence(const struct nfs_server *server,
 		struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
-		int cache_reply, struct rpc_task *task)
+		struct rpc_task *task)
 {
 	return 0;
 }
@@ -319,7 +310,7 @@ static inline void nfs4_schedule_session_recovery(struct nfs4_session *session)
 }
 #endif /* CONFIG_NFS_V4_1 */
 
-extern struct nfs4_state_owner * nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *);
+extern struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *, gfp_t);
 extern void nfs4_put_state_owner(struct nfs4_state_owner *);
 extern void nfs4_purge_state_owners(struct nfs_server *);
 extern struct nfs4_state * nfs4_get_open_state(struct inode *, struct nfs4_state_owner *);
@@ -327,6 +318,8 @@ extern void nfs4_put_open_state(struct nfs4_state *);
 extern void nfs4_close_state(struct nfs4_state *, fmode_t);
 extern void nfs4_close_sync(struct nfs4_state *, fmode_t);
 extern void nfs4_state_set_mode_locked(struct nfs4_state *, fmode_t);
+extern void nfs_inode_find_state_and_recover(struct inode *inode,
+		const nfs4_stateid *stateid);
 extern void nfs4_schedule_lease_recovery(struct nfs_client *);
 extern void nfs4_schedule_state_manager(struct nfs_client *);
 extern void nfs4_schedule_path_down_recovery(struct nfs_client *clp);
@@ -337,7 +330,8 @@ extern void nfs41_handle_server_scope(struct nfs_client *,
 				      struct server_scope **);
 extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp);
 extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl);
-extern void nfs4_copy_stateid(nfs4_stateid *, struct nfs4_state *, fl_owner_t, pid_t);
+extern void nfs4_select_rw_stateid(nfs4_stateid *, struct nfs4_state *,
+		fmode_t, fl_owner_t, pid_t);
 
 extern struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_mask);
 extern int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task);
@@ -346,6 +340,8 @@ extern void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid);
 extern void nfs_release_seqid(struct nfs_seqid *seqid);
 extern void nfs_free_seqid(struct nfs_seqid *seqid);
 
+extern void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp);
+
 extern const nfs4_stateid zero_stateid;
 
 /* nfs4xdr.c */
@@ -357,6 +353,16 @@ struct nfs4_mount_data;
 extern struct svc_version nfs4_callback_version1;
 extern struct svc_version nfs4_callback_version4;
 
+static inline void nfs4_stateid_copy(nfs4_stateid *dst, const nfs4_stateid *src)
+{
+	memcpy(dst, src, sizeof(*dst));
+}
+
+static inline bool nfs4_stateid_match(const nfs4_stateid *dst, const nfs4_stateid *src)
+{
+	return memcmp(dst, src, sizeof(*dst)) == 0;
+}
+
 #else
 
 #define nfs4_close_state(a, b) do { } while (0)

fs/nfs/nfs4filelayout.c

@@ -33,7 +33,10 @@
 #include <linux/nfs_page.h>
 #include <linux/module.h>
 
+#include <linux/sunrpc/metrics.h>
+
 #include "internal.h"
+#include "delegation.h"
 #include "nfs4filelayout.h"
 
 #define NFSDBG_FACILITY         NFSDBG_PNFS_LD
@@ -84,12 +87,27 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 					 struct nfs_client *clp,
 					 int *reset)
 {
+	struct nfs_server *mds_server = NFS_SERVER(state->inode);
+	struct nfs_client *mds_client = mds_server->nfs_client;
+
 	if (task->tk_status >= 0)
 		return 0;
-
 	*reset = 0;
 
 	switch (task->tk_status) {
+	/* MDS state errors */
+	case -NFS4ERR_DELEG_REVOKED:
+	case -NFS4ERR_ADMIN_REVOKED:
+	case -NFS4ERR_BAD_STATEID:
+		nfs_remove_bad_delegation(state->inode);
+	case -NFS4ERR_OPENMODE:
+		nfs4_schedule_stateid_recovery(mds_server, state);
+		goto wait_on_recovery;
+	case -NFS4ERR_EXPIRED:
+		nfs4_schedule_stateid_recovery(mds_server, state);
+		nfs4_schedule_lease_recovery(mds_client);
+		goto wait_on_recovery;
+	/* DS session errors */
 	case -NFS4ERR_BADSESSION:
 	case -NFS4ERR_BADSLOT:
 	case -NFS4ERR_BAD_HIGH_SLOT:
@@ -115,8 +133,14 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 		*reset = 1;
 		break;
 	}
+out:
 	task->tk_status = 0;
 	return -EAGAIN;
+wait_on_recovery:
+	rpc_sleep_on(&mds_client->cl_rpcwaitq, task, NULL);
+	if (test_bit(NFS4CLNT_MANAGER_RUNNING, &mds_client->cl_state) == 0)
+		rpc_wake_up_queued_task(&mds_client->cl_rpcwaitq, task);
+	goto out;
 }
 
 /* NFS_PROTO call done callback routines */
@@ -173,7 +197,7 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data)
 
 	if (nfs41_setup_sequence(rdata->ds_clp->cl_session,
 				&rdata->args.seq_args, &rdata->res.seq_res,
-				0, task))
+				task))
 		return;
 
 	rpc_call_start(task);
@@ -189,10 +213,18 @@ static void filelayout_read_call_done(struct rpc_task *task, void *data)
 	rdata->mds_ops->rpc_call_done(task, data);
 }
 
+static void filelayout_read_count_stats(struct rpc_task *task, void *data)
+{
+	struct nfs_read_data *rdata = (struct nfs_read_data *)data;
+
+	rpc_count_iostats(task, NFS_SERVER(rdata->inode)->client->cl_metrics);
+}
+
 static void filelayout_read_release(void *data)
 {
 	struct nfs_read_data *rdata = (struct nfs_read_data *)data;
 
+	put_lseg(rdata->lseg);
 	rdata->mds_ops->rpc_release(data);
 }
 
@@ -254,7 +286,7 @@ static void filelayout_write_prepare(struct rpc_task *task, void *data)
 
 	if (nfs41_setup_sequence(wdata->ds_clp->cl_session,
 				&wdata->args.seq_args, &wdata->res.seq_res,
-				0, task))
+				task))
 		return;
 
 	rpc_call_start(task);
@@ -268,10 +300,18 @@ static void filelayout_write_call_done(struct rpc_task *task, void *data)
 	wdata->mds_ops->rpc_call_done(task, data);
 }
 
+static void filelayout_write_count_stats(struct rpc_task *task, void *data)
+{
+	struct nfs_write_data *wdata = (struct nfs_write_data *)data;
+
+	rpc_count_iostats(task, NFS_SERVER(wdata->inode)->client->cl_metrics);
+}
+
 static void filelayout_write_release(void *data)
 {
 	struct nfs_write_data *wdata = (struct nfs_write_data *)data;
 
+	put_lseg(wdata->lseg);
 	wdata->mds_ops->rpc_release(data);
 }
 
@@ -282,24 +322,28 @@ static void filelayout_commit_release(void *data)
 	nfs_commit_release_pages(wdata);
 	if (atomic_dec_and_test(&NFS_I(wdata->inode)->commits_outstanding))
 		nfs_commit_clear_lock(NFS_I(wdata->inode));
+	put_lseg(wdata->lseg);
 	nfs_commitdata_release(wdata);
 }
 
-struct rpc_call_ops filelayout_read_call_ops = {
+static const struct rpc_call_ops filelayout_read_call_ops = {
 	.rpc_call_prepare = filelayout_read_prepare,
 	.rpc_call_done = filelayout_read_call_done,
+	.rpc_count_stats = filelayout_read_count_stats,
 	.rpc_release = filelayout_read_release,
 };
 
-struct rpc_call_ops filelayout_write_call_ops = {
+static const struct rpc_call_ops filelayout_write_call_ops = {
 	.rpc_call_prepare = filelayout_write_prepare,
 	.rpc_call_done = filelayout_write_call_done,
+	.rpc_count_stats = filelayout_write_count_stats,
 	.rpc_release = filelayout_write_release,
 };
 
-struct rpc_call_ops filelayout_commit_call_ops = {
+static const struct rpc_call_ops filelayout_commit_call_ops = {
 	.rpc_call_prepare = filelayout_write_prepare,
 	.rpc_call_done = filelayout_write_call_done,
+	.rpc_count_stats = filelayout_write_count_stats,
 	.rpc_release = filelayout_commit_release,
 };
 
@@ -367,7 +411,8 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync)
 	idx = nfs4_fl_calc_ds_index(lseg, j);
 	ds = nfs4_fl_prepare_ds(lseg, idx);
 	if (!ds) {
-		printk(KERN_ERR "%s: prepare_ds failed, use MDS\n", __func__);
+		printk(KERN_ERR "NFS: %s: prepare_ds failed, use MDS\n",
+			__func__);
 		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
 		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
 		return PNFS_NOT_ATTEMPTED;
@@ -575,7 +620,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 			goto out_err_free;
 		fl->fh_array[i]->size = be32_to_cpup(p++);
 		if (sizeof(struct nfs_fh) < fl->fh_array[i]->size) {
-			printk(KERN_ERR "Too big fh %d received %d\n",
+			printk(KERN_ERR "NFS: Too big fh %d received %d\n",
 			       i, fl->fh_array[i]->size);
 			goto out_err_free;
 		}
@@ -640,14 +685,16 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
 		int size = (fl->stripe_type == STRIPE_SPARSE) ?
 			fl->dsaddr->ds_num : fl->dsaddr->stripe_count;
 
-		fl->commit_buckets = kcalloc(size, sizeof(struct list_head), gfp_flags);
+		fl->commit_buckets = kcalloc(size, sizeof(struct nfs4_fl_commit_bucket), gfp_flags);
 		if (!fl->commit_buckets) {
 			filelayout_free_lseg(&fl->generic_hdr);
 			return NULL;
 		}
 		fl->number_of_buckets = size;
-		for (i = 0; i < size; i++)
-			INIT_LIST_HEAD(&fl->commit_buckets[i]);
+		for (i = 0; i < size; i++) {
+			INIT_LIST_HEAD(&fl->commit_buckets[i].written);
+			INIT_LIST_HEAD(&fl->commit_buckets[i].committing);
+		}
 	}
 	return &fl->generic_hdr;
 }
@@ -679,7 +726,7 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 	return (p_stripe == r_stripe);
 }
 
-void
+static void
 filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 			struct nfs_page *req)
 {
@@ -696,7 +743,7 @@ filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 		nfs_pageio_reset_read_mds(pgio);
 }
 
-void
+static void
 filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 			 struct nfs_page *req)
 {
@@ -725,11 +772,6 @@ static const struct nfs_pageio_ops filelayout_pg_write_ops = {
 	.pg_doio = pnfs_generic_pg_writepages,
 };
 
-static bool filelayout_mark_pnfs_commit(struct pnfs_layout_segment *lseg)
-{
-	return !FILELAYOUT_LSEG(lseg)->commit_through_mds;
-}
-
 static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j)
 {
 	if (fl->stripe_type == STRIPE_SPARSE)
@@ -738,13 +780,49 @@ static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j)
 		return j;
 }
 
-struct list_head *filelayout_choose_commit_list(struct nfs_page *req)
+/* The generic layer is about to remove the req from the commit list.
+ * If this will make the bucket empty, it will need to put the lseg reference.
+ */
+static void
+filelayout_clear_request_commit(struct nfs_page *req)
+{
+	struct pnfs_layout_segment *freeme = NULL;
+	struct inode *inode = req->wb_context->dentry->d_inode;
+
+	spin_lock(&inode->i_lock);
+	if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags))
+		goto out;
+	if (list_is_singular(&req->wb_list)) {
+		struct inode *inode = req->wb_context->dentry->d_inode;
+		struct pnfs_layout_segment *lseg;
+
+		/* From here we can find the bucket, but for the moment,
+		 * since there is only one relevant lseg...
+		 */
+		list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) {
+			if (lseg->pls_range.iomode == IOMODE_RW) {
+				freeme = lseg;
+				break;
+			}
+		}
+	}
+out:
+	nfs_request_remove_commit_list(req);
+	spin_unlock(&inode->i_lock);
+	put_lseg(freeme);
+}
+
+static struct list_head *
+filelayout_choose_commit_list(struct nfs_page *req,
+			      struct pnfs_layout_segment *lseg)
 {
-	struct pnfs_layout_segment *lseg = req->wb_commit_lseg;
 	struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
 	u32 i, j;
 	struct list_head *list;
 
+	if (fl->commit_through_mds)
+		return &NFS_I(req->wb_context->dentry->d_inode)->commit_list;
+
 	/* Note that we are calling nfs4_fl_calc_j_index on each page
 	 * that ends up being committed to a data server.  An attractive
 	 * alternative is to add a field to nfs_write_data and nfs_page
@@ -754,14 +832,30 @@ struct list_head *filelayout_choose_commit_list(struct nfs_page *req)
 	j = nfs4_fl_calc_j_index(lseg,
 				 (loff_t)req->wb_index << PAGE_CACHE_SHIFT);
 	i = select_bucket_index(fl, j);
-	list = &fl->commit_buckets[i];
+	list = &fl->commit_buckets[i].written;
 	if (list_empty(list)) {
-		/* Non-empty buckets hold a reference on the lseg */
+		/* Non-empty buckets hold a reference on the lseg.  That ref
+		 * is normally transferred to the COMMIT call and released
+		 * there.  It could also be released if the last req is pulled
+		 * off due to a rewrite, in which case it will be done in
+		 * filelayout_remove_commit_req
+		 */
 		get_lseg(lseg);
 	}
+	set_bit(PG_COMMIT_TO_DS, &req->wb_flags);
 	return list;
 }
 
+static void
+filelayout_mark_request_commit(struct nfs_page *req,
+		struct pnfs_layout_segment *lseg)
+{
+	struct list_head *list;
+
+	list = filelayout_choose_commit_list(req, lseg);
+	nfs_request_add_commit_list(req, list);
+}
+
 static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i)
 {
 	struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg);
@@ -797,11 +891,12 @@ static int filelayout_initiate_commit(struct nfs_write_data *data, int how)
 	idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
 	ds = nfs4_fl_prepare_ds(lseg, idx);
 	if (!ds) {
-		printk(KERN_ERR "%s: prepare_ds failed, use MDS\n", __func__);
+		printk(KERN_ERR "NFS: %s: prepare_ds failed, use MDS\n",
+			__func__);
 		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
 		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
 		prepare_to_resend_writes(data);
-		data->mds_ops->rpc_release(data);
+		filelayout_commit_release(data);
 		return -EAGAIN;
 	}
 	dprintk("%s ino %lu, how %d\n", __func__, data->inode->i_ino, how);
@@ -817,24 +912,87 @@ static int filelayout_initiate_commit(struct nfs_write_data *data, int how)
 /*
  * This is only useful while we are using whole file layouts.
  */
-static struct pnfs_layout_segment *find_only_write_lseg(struct inode *inode)
+static struct pnfs_layout_segment *
+find_only_write_lseg_locked(struct inode *inode)
 {
-	struct pnfs_layout_segment *lseg, *rv = NULL;
+	struct pnfs_layout_segment *lseg;
 
-	spin_lock(&inode->i_lock);
 	list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list)
 		if (lseg->pls_range.iomode == IOMODE_RW)
-			rv = get_lseg(lseg);
+			return lseg;
+	return NULL;
+}
+
+static struct pnfs_layout_segment *find_only_write_lseg(struct inode *inode)
+{
+	struct pnfs_layout_segment *rv;
+
+	spin_lock(&inode->i_lock);
+	rv = find_only_write_lseg_locked(inode);
+	if (rv)
+		get_lseg(rv);
 	spin_unlock(&inode->i_lock);
 	return rv;
 }
 
-static int alloc_ds_commits(struct inode *inode, struct list_head *list)
+static int
+filelayout_scan_ds_commit_list(struct nfs4_fl_commit_bucket *bucket, int max,
+		spinlock_t *lock)
+{
+	struct list_head *src = &bucket->written;
+	struct list_head *dst = &bucket->committing;
+	struct nfs_page *req, *tmp;
+	int ret = 0;
+
+	list_for_each_entry_safe(req, tmp, src, wb_list) {
+		if (!nfs_lock_request(req))
+			continue;
+		if (cond_resched_lock(lock))
+			list_safe_reset_next(req, tmp, wb_list);
+		nfs_request_remove_commit_list(req);
+		clear_bit(PG_COMMIT_TO_DS, &req->wb_flags);
+		nfs_list_add_request(req, dst);
+		ret++;
+		if (ret == max)
+			break;
+	}
+	return ret;
+}
+
+/* Move reqs from written to committing lists, returning count of number moved.
+ * Note called with i_lock held.
+ */
+static int filelayout_scan_commit_lists(struct inode *inode, int max,
+		spinlock_t *lock)
+{
+	struct pnfs_layout_segment *lseg;
+	struct nfs4_filelayout_segment *fl;
+	int i, rv = 0, cnt;
+
+	lseg = find_only_write_lseg_locked(inode);
+	if (!lseg)
+		goto out_done;
+	fl = FILELAYOUT_LSEG(lseg);
+	if (fl->commit_through_mds)
+		goto out_done;
+	for (i = 0; i < fl->number_of_buckets && max != 0; i++) {
+		cnt = filelayout_scan_ds_commit_list(&fl->commit_buckets[i],
+				max, lock);
+		max -= cnt;
+		rv += cnt;
+	}
+out_done:
+	return rv;
+}
+
+static unsigned int
+alloc_ds_commits(struct inode *inode, struct list_head *list)
 {
 	struct pnfs_layout_segment *lseg;
 	struct nfs4_filelayout_segment *fl;
 	struct nfs_write_data *data;
 	int i, j;
+	unsigned int nreq = 0;
 
 	/* Won't need this when non-whole file layout segments are supported
 	 * instead we will use a pnfs_layout_hdr structure */
@@ -843,28 +1001,27 @@ static int alloc_ds_commits(struct inode *inode, struct list_head *list)
 		return 0;
 	fl = FILELAYOUT_LSEG(lseg);
 	for (i = 0; i < fl->number_of_buckets; i++) {
-		if (list_empty(&fl->commit_buckets[i]))
+		if (list_empty(&fl->commit_buckets[i].committing))
 			continue;
 		data = nfs_commitdata_alloc();
 		if (!data)
-			goto out_bad;
+			break;
 		data->ds_commit_index = i;
 		data->lseg = lseg;
 		list_add(&data->pages, list);
+		nreq++;
 	}
-	put_lseg(lseg);
-	return 0;
 
-out_bad:
+	/* Clean up on error */
 	for (j = i; j < fl->number_of_buckets; j++) {
-		if (list_empty(&fl->commit_buckets[i]))
+		if (list_empty(&fl->commit_buckets[i].committing))
 			continue;
-		nfs_retry_commit(&fl->commit_buckets[i], lseg);
+		nfs_retry_commit(&fl->commit_buckets[i].committing, lseg);
 		put_lseg(lseg);  /* associated with emptying bucket */
 	}
 	put_lseg(lseg);
 	/* Caller will clean up entries put on list */
-	return -ENOMEM;
+	return nreq;
 }
 
 /* This follows nfs_commit_list pretty closely */
@@ -874,40 +1031,40 @@ filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
 {
 	struct nfs_write_data	*data, *tmp;
 	LIST_HEAD(list);
+	unsigned int nreq = 0;
 
 	if (!list_empty(mds_pages)) {
 		data = nfs_commitdata_alloc();
-		if (!data)
-			goto out_bad;
-		data->lseg = NULL;
-		list_add(&data->pages, &list);
+		if (data != NULL) {
+			data->lseg = NULL;
+			list_add(&data->pages, &list);
+			nreq++;
+		} else
+			nfs_retry_commit(mds_pages, NULL);
 	}
 
-	if (alloc_ds_commits(inode, &list))
-		goto out_bad;
+	nreq += alloc_ds_commits(inode, &list);
+
+	if (nreq == 0) {
+		nfs_commit_clear_lock(NFS_I(inode));
+		goto out;
+	}
+
+	atomic_add(nreq, &NFS_I(inode)->commits_outstanding);
 
 	list_for_each_entry_safe(data, tmp, &list, pages) {
 		list_del_init(&data->pages);
-		atomic_inc(&NFS_I(inode)->commits_outstanding);
 		if (!data->lseg) {
 			nfs_init_commit(data, mds_pages, NULL);
 			nfs_initiate_commit(data, NFS_CLIENT(inode),
 					    data->mds_ops, how);
 		} else {
-			nfs_init_commit(data, &FILELAYOUT_LSEG(data->lseg)->commit_buckets[data->ds_commit_index], data->lseg);
+			nfs_init_commit(data, &FILELAYOUT_LSEG(data->lseg)->commit_buckets[data->ds_commit_index].committing, data->lseg);
 			filelayout_initiate_commit(data, how);
 		}
 	}
-	return 0;
- out_bad:
-	list_for_each_entry_safe(data, tmp, &list, pages) {
-		nfs_retry_commit(&data->pages, data->lseg);
-		list_del_init(&data->pages);
-		nfs_commit_free(data);
-	}
-	nfs_retry_commit(mds_pages, NULL);
-	nfs_commit_clear_lock(NFS_I(inode));
-	return -ENOMEM;
+out:
+	return PNFS_ATTEMPTED;
 }
 
 static void
@@ -924,8 +1081,9 @@ static struct pnfs_layoutdriver_type filelayout_type = {
 	.free_lseg		= filelayout_free_lseg,
 	.pg_read_ops		= &filelayout_pg_read_ops,
 	.pg_write_ops		= &filelayout_pg_write_ops,
-	.mark_pnfs_commit	= filelayout_mark_pnfs_commit,
-	.choose_commit_list	= filelayout_choose_commit_list,
+	.mark_request_commit	= filelayout_mark_request_commit,
+	.clear_request_commit	= filelayout_clear_request_commit,
+	.scan_commit_lists	= filelayout_scan_commit_lists,
 	.commit_pagelist	= filelayout_commit_pagelist,
 	.read_pagelist		= filelayout_read_pagelist,
 	.write_pagelist		= filelayout_write_pagelist,

fs/nfs/nfs4filelayout.h

@@ -74,6 +74,11 @@ struct nfs4_file_layout_dsaddr {
 	struct nfs4_pnfs_ds		*ds_list[1];
 };
 
+struct nfs4_fl_commit_bucket {
+	struct list_head written;
+	struct list_head committing;
+};
+
 struct nfs4_filelayout_segment {
 	struct pnfs_layout_segment generic_hdr;
 	u32 stripe_type;
@@ -84,7 +89,7 @@ struct nfs4_filelayout_segment {
 	struct nfs4_file_layout_dsaddr *dsaddr; /* Point to GETDEVINFO data */
 	unsigned int num_fh;
 	struct nfs_fh **fh_array;
-	struct list_head *commit_buckets; /* Sort commits to ds */
+	struct nfs4_fl_commit_bucket *commit_buckets; /* Sort commits to ds */
 	int number_of_buckets;
 };
 

fs/nfs/nfs4filelayoutdev.c

@@ -45,7 +45,7 @@
  *   - incremented when a device id maps a data server already in the cache.
  *   - decremented when deviceid is removed from the cache.
  */
-DEFINE_SPINLOCK(nfs4_ds_cache_lock);
+static DEFINE_SPINLOCK(nfs4_ds_cache_lock);
 static LIST_HEAD(nfs4_data_server_cache);
 
 /* Debug routines */
@@ -108,58 +108,40 @@ same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2)
 	return false;
 }
 
-/*
- * Lookup DS by addresses.  The first matching address returns true.
- * nfs4_ds_cache_lock is held
- */
-static struct nfs4_pnfs_ds *
-_data_server_lookup_locked(struct list_head *dsaddrs)
+static bool
+_same_data_server_addrs_locked(const struct list_head *dsaddrs1,
+			       const struct list_head *dsaddrs2)
 {
-	struct nfs4_pnfs_ds *ds;
 	struct nfs4_pnfs_ds_addr *da1, *da2;
 
-	list_for_each_entry(da1, dsaddrs, da_node) {
-		list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) {
-			list_for_each_entry(da2, &ds->ds_addrs, da_node) {
-				if (same_sockaddr(
-					(struct sockaddr *)&da1->da_addr,
-					(struct sockaddr *)&da2->da_addr))
-					return ds;
-			}
-		}
+	/* step through both lists, comparing as we go */
+	for (da1 = list_first_entry(dsaddrs1, typeof(*da1), da_node),
+	     da2 = list_first_entry(dsaddrs2, typeof(*da2), da_node);
+	     da1 != NULL && da2 != NULL;
+	     da1 = list_entry(da1->da_node.next, typeof(*da1), da_node),
+	     da2 = list_entry(da2->da_node.next, typeof(*da2), da_node)) {
+		if (!same_sockaddr((struct sockaddr *)&da1->da_addr,
+				   (struct sockaddr *)&da2->da_addr))
+			return false;
 	}
-	return NULL;
+	if (da1 == NULL && da2 == NULL)
+		return true;
+
+	return false;
 }
 
 /*
- * Compare two lists of addresses.
+ * Lookup DS by addresses.  nfs4_ds_cache_lock is held
  */
-static bool
-_data_server_match_all_addrs_locked(struct list_head *dsaddrs1,
-				    struct list_head *dsaddrs2)
+static struct nfs4_pnfs_ds *
+_data_server_lookup_locked(const struct list_head *dsaddrs)
 {
-	struct nfs4_pnfs_ds_addr *da1, *da2;
-	size_t count1 = 0,
-	       count2 = 0;
-
-	list_for_each_entry(da1, dsaddrs1, da_node)
-		count1++;
-
-	list_for_each_entry(da2, dsaddrs2, da_node) {
-		bool found = false;
-		count2++;
-		list_for_each_entry(da1, dsaddrs1, da_node) {
-			if (same_sockaddr((struct sockaddr *)&da1->da_addr,
-				(struct sockaddr *)&da2->da_addr)) {
-				found = true;
-				break;
-			}
-		}
-		if (!found)
-			return false;
-	}
+	struct nfs4_pnfs_ds *ds;
 
-	return (count1 == count2);
+	list_for_each_entry(ds, &nfs4_data_server_cache, ds_node)
+		if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs))
+			return ds;
+	return NULL;
 }
 
 /*
@@ -356,11 +338,6 @@ nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
 		dprintk("%s add new data server %s\n", __func__,
 			ds->ds_remotestr);
 	} else {
-		if (!_data_server_match_all_addrs_locked(&tmp_ds->ds_addrs,
-							 dsaddrs)) {
-			dprintk("%s:  multipath address mismatch: %s != %s",
-				__func__, tmp_ds->ds_remotestr, remotestr);
-		}
 		kfree(remotestr);
 		kfree(ds);
 		atomic_inc(&tmp_ds->ds_count);
@@ -378,7 +355,7 @@ out:
  * Currently only supports ipv4, ipv6 and one multi-path address.
  */
 static struct nfs4_pnfs_ds_addr *
-decode_ds_addr(struct xdr_stream *streamp, gfp_t gfp_flags)
+decode_ds_addr(struct net *net, struct xdr_stream *streamp, gfp_t gfp_flags)
 {
 	struct nfs4_pnfs_ds_addr *da = NULL;
 	char *buf, *portstr;
@@ -457,7 +434,7 @@ decode_ds_addr(struct xdr_stream *streamp, gfp_t gfp_flags)
 
 	INIT_LIST_HEAD(&da->da_node);
 
-	if (!rpc_pton(buf, portstr-buf, (struct sockaddr *)&da->da_addr,
+	if (!rpc_pton(net, buf, portstr-buf, (struct sockaddr *)&da->da_addr,
 		      sizeof(da->da_addr))) {
 		dprintk("%s: error parsing address %s\n", __func__, buf);
 		goto out_free_da;
@@ -554,7 +531,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
 	cnt = be32_to_cpup(p);
 	dprintk("%s stripe count  %d\n", __func__, cnt);
 	if (cnt > NFS4_PNFS_MAX_STRIPE_CNT) {
-		printk(KERN_WARNING "%s: stripe count %d greater than "
+		printk(KERN_WARNING "NFS: %s: stripe count %d greater than "
 		       "supported maximum %d\n", __func__,
 			cnt, NFS4_PNFS_MAX_STRIPE_CNT);
 		goto out_err_free_scratch;
@@ -585,7 +562,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
 	num = be32_to_cpup(p);
 	dprintk("%s ds_num %u\n", __func__, num);
 	if (num > NFS4_PNFS_MAX_MULTI_CNT) {
-		printk(KERN_WARNING "%s: multipath count %d greater than "
+		printk(KERN_WARNING "NFS: %s: multipath count %d greater than "
 			"supported maximum %d\n", __func__,
 			num, NFS4_PNFS_MAX_MULTI_CNT);
 		goto out_err_free_stripe_indices;
@@ -593,7 +570,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
 
 	/* validate stripe indices are all < num */
 	if (max_stripe_index >= num) {
-		printk(KERN_WARNING "%s: stripe index %u >= num ds %u\n",
+		printk(KERN_WARNING "NFS: %s: stripe index %u >= num ds %u\n",
 			__func__, max_stripe_index, num);
 		goto out_err_free_stripe_indices;
 	}
@@ -625,7 +602,8 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
 
 		mp_count = be32_to_cpup(p); /* multipath count */
 		for (j = 0; j < mp_count; j++) {
-			da = decode_ds_addr(&stream, gfp_flags);
+			da = decode_ds_addr(NFS_SERVER(ino)->nfs_client->net,
+					    &stream, gfp_flags);
 			if (da)
 				list_add_tail(&da->da_node, &dsaddrs);
 		}
@@ -686,7 +664,7 @@ decode_and_add_device(struct inode *inode, struct pnfs_device *dev, gfp_t gfp_fl
 
 	new = decode_device(inode, dev, gfp_flags);
 	if (!new) {
-		printk(KERN_WARNING "%s: Could not decode or add device\n",
+		printk(KERN_WARNING "NFS: %s: Could not decode or add device\n",
 			__func__);
 		return NULL;
 	}
@@ -835,7 +813,7 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 	struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx];
 
 	if (ds == NULL) {
-		printk(KERN_ERR "%s: No data server for offset index %d\n",
+		printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
 			__func__, ds_idx);
 		return NULL;
 	}

fs/nfs/nfs4namespace.c

@@ -94,13 +94,14 @@ static int nfs4_validate_fspath(struct dentry *dentry,
 }
 
 static size_t nfs_parse_server_name(char *string, size_t len,
-		struct sockaddr *sa, size_t salen)
+		struct sockaddr *sa, size_t salen, struct nfs_server *server)
 {
+	struct net *net = rpc_net_ns(server->client);
 	ssize_t ret;
 
-	ret = rpc_pton(string, len, sa, salen);
+	ret = rpc_pton(net, string, len, sa, salen);
 	if (ret == 0) {
-		ret = nfs_dns_resolve_name(string, len, sa, salen);
+		ret = nfs_dns_resolve_name(net, string, len, sa, salen);
 		if (ret < 0)
 			ret = 0;
 	}
@@ -137,7 +138,8 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
 			continue;
 
 		mountdata->addrlen = nfs_parse_server_name(buf->data, buf->len,
-				mountdata->addr, addr_bufsize);
+				mountdata->addr, addr_bufsize,
+				NFS_SB(mountdata->sb));
 		if (mountdata->addrlen == 0)
 			continue;