Merge mulgrave-w:git/linux-2.6

Conflicts:

	include/linux/blkdev.h

Trivial merge to incorporate tag prototypes.

CREDITS

@@ -2384,6 +2384,13 @@ N: Thomas Molina
 E: tmolina@cablespeed.com
 D: bug fixes, documentation, minor hackery
 
+N: Paul Moore
+E: paul.moore@hp.com
+D: NetLabel author
+S: Hewlett-Packard
+S: 110 Spit Brook Road
+S: Nashua, NH 03062
+
 N: James Morris
 E: jmorris@namei.org
 W: http://namei.org/

Documentation/00-INDEX

@@ -184,6 +184,8 @@ mtrr.txt
 	- how to use PPro Memory Type Range Registers to increase performance.
 nbd.txt
 	- info on a TCP implementation of a network block device.
+netlabel/
+	- directory with information on the NetLabel subsystem.
 networking/
 	- directory with info on various aspects of networking with Linux.
 nfsroot.txt

Documentation/netlabel/00-INDEX

@@ -0,0 +1,10 @@
+00-INDEX
+	- this file.
+cipso_ipv4.txt
+	- documentation on the IPv4 CIPSO protocol engine.
+draft-ietf-cipso-ipsecurity-01.txt
+	- IETF draft of the CIPSO protocol, dated 16 July 1992.
+introduction.txt
+	- NetLabel introduction, READ THIS FIRST.
+lsm_interface.txt
+	- documentation on the NetLabel kernel security module API.

Documentation/netlabel/cipso_ipv4.txt

@@ -0,0 +1,48 @@
+NetLabel CIPSO/IPv4 Protocol Engine
+==============================================================================
+Paul Moore, paul.moore@hp.com
+
+May 17, 2006
+
+ * Overview
+
+The NetLabel CIPSO/IPv4 protocol engine is based on the IETF Commercial IP
+Security Option (CIPSO) draft from July 16, 1992.  A copy of this draft can be
+found in this directory, consult '00-INDEX' for the filename.  While the IETF
+draft never made it to an RFC standard it has become a de-facto standard for
+labeled networking and is used in many trusted operating systems.
+
+ * Outbound Packet Processing
+
+The CIPSO/IPv4 protocol engine applies the CIPSO IP option to packets by
+adding the CIPSO label to the socket.  This causes all packets leaving the
+system through the socket to have the CIPSO IP option applied.  The socket's
+CIPSO label can be changed at any point in time, however, it is recommended
+that it is set upon the socket's creation.  The LSM can set the socket's CIPSO
+label by using the NetLabel security module API; if the NetLabel "domain" is
+configured to use CIPSO for packet labeling then a CIPSO IP option will be
+generated and attached to the socket.
+
+ * Inbound Packet Processing
+
+The CIPSO/IPv4 protocol engine validates every CIPSO IP option it finds at the
+IP layer without any special handling required by the LSM.  However, in order
+to decode and translate the CIPSO label on the packet the LSM must use the
+NetLabel security module API to extract the security attributes of the packet.
+This is typically done at the socket layer using the 'socket_sock_rcv_skb()'
+LSM hook.
+
+ * Label Translation
+
+The CIPSO/IPv4 protocol engine contains a mechanism to translate CIPSO security
+attributes such as sensitivity level and category to values which are
+appropriate for the host.  These mappings are defined as part of a CIPSO
+Domain Of Interpretation (DOI) definition and are configured through the
+NetLabel user space communication layer.  Each DOI definition can have a
+different security attribute mapping table.
+
+ * Label Translation Cache
+
+The NetLabel system provides a framework for caching security attribute
+mappings from the network labels to the corresponding LSM identifiers.  The
+CIPSO/IPv4 protocol engine supports this caching mechanism.

Documentation/netlabel/draft-ietf-cipso-ipsecurity-01.txt

@@ -0,0 +1,791 @@
+IETF CIPSO Working Group
+16 July, 1992
+
+
+
+                 COMMERCIAL IP SECURITY OPTION (CIPSO 2.2)
+
+
+
+1.    Status
+
+This Internet Draft provides the high level specification for a Commercial
+IP Security Option (CIPSO).  This draft reflects the version as approved by
+the CIPSO IETF Working Group.  Distribution of this memo is unlimited.
+
+This document is an Internet Draft.  Internet Drafts are working documents
+of the Internet Engineering Task Force (IETF), its Areas, and its Working
+Groups. Note that other groups may also distribute working documents as
+Internet Drafts.
+
+Internet Drafts are draft documents valid for a maximum of six months.
+Internet Drafts may be updated, replaced, or obsoleted by other documents
+at any time.  It is not appropriate to use Internet Drafts as reference
+material or to cite them other than as a "working draft" or "work in
+progress."
+
+Please check the I-D abstract listing contained in each Internet Draft
+directory to learn the current status of this or any other Internet Draft.
+
+
+
+
+2.    Background
+
+Currently the Internet Protocol includes two security options.  One of
+these options is the DoD Basic Security Option (BSO) (Type 130) which allows
+IP datagrams to be labeled with security classifications.  This option
+provides sixteen security classifications and a variable number of handling
+restrictions.  To handle additional security information, such as security
+categories or compartments, another security option (Type 133) exists and
+is referred to as the DoD Extended Security Option (ESO).  The values for
+the fixed fields within these two options are administered by the Defense
+Information Systems Agency (DISA).
+
+Computer vendors are now building commercial operating systems with
+mandatory access controls and multi-level security.  These systems are
+no longer built specifically for a particular group in the defense or
+intelligence communities.  They are generally available commercial systems
+for use in a variety of government and civil sector environments.
+
+The small number of ESO format codes can not support all the possible
+applications of a commercial security option.  The BSO and ESO were
+designed to only support the United States DoD.  CIPSO has been designed
+to support multiple security policies.  This Internet Draft provides the
+format and procedures required to support a Mandatory Access Control
+security policy.  Support for additional security policies shall be
+defined in future RFCs.
+
+
+
+
+Internet Draft, Expires 15 Jan 93                                 [PAGE 1]
+
+
+
+CIPSO INTERNET DRAFT                                         16 July, 1992
+
+
+
+
+3.    CIPSO Format
+
+Option type: 134 (Class 0, Number 6, Copy on Fragmentation)
+Option length: Variable
+
+This option permits security related information to be passed between
+systems within a single Domain of Interpretation (DOI).  A DOI is a
+collection of systems which agree on the meaning of particular values
+in the security option.  An authority that has been assigned a DOI
+identifier will define a mapping between appropriate CIPSO field values
+and their human readable equivalent.  This authority will distribute that
+mapping to hosts within the authority's domain.  These mappings may be
+sensitive, therefore a DOI authority is not required to make these
+mappings available to anyone other than the systems that are included in
+the DOI.
+
+This option MUST be copied on fragmentation.  This option appears at most
+once in a datagram.  All multi-octet fields in the option are defined to be
+transmitted in network byte order.  The format of this option is as follows:
+
++----------+----------+------//------+-----------//---------+
+| 10000110 | LLLLLLLL | DDDDDDDDDDDD | TTTTTTTTTTTTTTTTTTTT |
++----------+----------+------//------+-----------//---------+
+
+  TYPE=134    OPTION    DOMAIN OF               TAGS
+              LENGTH    INTERPRETATION
+
+
+                Figure 1. CIPSO Format
+
+
+3.1    Type
+
+This field is 1 octet in length.  Its value is 134.
+
+
+3.2    Length
+
+This field is 1 octet in length.  It is the total length of the option
+including the type and length fields.  With the current IP header length
+restriction of 40 octets the value of this field MUST not exceed 40.
+
+
+3.3    Domain of Interpretation Identifier
+
+This field is an unsigned 32 bit integer.  The value 0 is reserved and MUST
+not appear as the DOI identifier in any CIPSO option.  Implementations
+should assume that the DOI identifier field is not aligned on any particular
+byte boundary.
+
+To conserve space in the protocol, security levels and categories are
+represented by numbers rather than their ASCII equivalent.  This requires
+a mapping table within CIPSO hosts to map these numbers to their
+corresponding ASCII representations.  Non-related groups of systems may
+
+
+
+Internet Draft, Expires 15 Jan 93                                 [PAGE 2]
+
+
+
+CIPSO INTERNET DRAFT                                         16 July, 1992
+
+
+
+have their own unique mappings.  For example, one group of systems may
+use the number 5 to represent Unclassified while another group may use the
+number 1 to represent that same security level.  The DOI identifier is used
+to identify which mapping was used for the values within the option.
+
+
+3.4    Tag Types
+
+A common format for passing security related information is necessary
+for interoperability.  CIPSO uses sets of "tags" to contain the security
+information relevant to the data in the IP packet.  Each tag begins with
+a tag type identifier followed by the length of the tag and ends with the
+actual security information to be passed.  All multi-octet fields in a tag
+are defined to be transmitted in network byte order.  Like the DOI
+identifier field in the CIPSO header, implementations should assume that
+all tags, as well as fields within a tag, are not aligned on any particular
+octet boundary.   The tag types defined in this document contain alignment
+bytes to assist alignment of some information, however alignment can not
+be guaranteed if CIPSO is not the first IP option.
+
+CIPSO tag types 0 through 127 are reserved for defining standard tag
+formats.  Their definitions will be published in RFCs.  Tag types whose
+identifiers are greater than 127 are defined by the DOI authority and may
+only be meaningful in certain Domains of Interpretation.  For these tag
+types, implementations will require the DOI identifier as well as the tag
+number to determine the security policy and the format associated with the
+tag.  Use of tag types above 127 are restricted to closed networks where
+interoperability with other networks will not be an issue.  Implementations
+that support a tag type greater than 127 MUST support at least one DOI that
+requires only tag types 1 to 127.
+
+Tag type 0 is reserved. Tag types 1, 2, and 5 are defined in this
+Internet Draft.  Types 3 and 4 are reserved for work in progress.
+The standard format for all current and future CIPSO tags is shown below:
+
++----------+----------+--------//--------+
+| TTTTTTTT | LLLLLLLL | IIIIIIIIIIIIIIII |
++----------+----------+--------//--------+
+    TAG       TAG         TAG
+    TYPE      LENGTH      INFORMATION
+
+    Figure 2:  Standard Tag Format
+
+In the three tag types described in this document, the length and count
+restrictions are based on the current IP limitation of 40 octets for all
+IP options.  If the IP header is later expanded, then the length and count
+restrictions specified in this document may increase to use the full area
+provided for IP options.
+
+
+3.4.1    Tag Type Classes
+
+Tag classes consist of tag types that have common processing requirements
+and support the same security policy.  The three tags defined in this
+Internet Draft belong to the Mandatory Access Control (MAC) Sensitivity
+
+
+
+Internet Draft, Expires 15 Jan 93                                 [PAGE 3]
+
+
+
+CIPSO INTERNET DRAFT                                         16 July, 1992
+
+
+
+class and support the MAC Sensitivity security policy.
+
+
+3.4.2    Tag Type 1
+
+This is referred to as the "bit-mapped" tag type.  Tag type 1 is included
+in the MAC Sensitivity tag type class.  The format of this tag type is as
+follows:
+
++----------+----------+----------+----------+--------//---------+
+| 00000001 | LLLLLLLL | 00000000 | LLLLLLLL | CCCCCCCCCCCCCCCCC |
++----------+----------+----------+----------+--------//---------+
+
+    TAG       TAG      ALIGNMENT  SENSITIVITY    BIT MAP OF
+    TYPE      LENGTH   OCTET      LEVEL          CATEGORIES
+
+            Figure 3. Tag Type 1 Format
+
+
+3.4.2.1    Tag Type
+
+This field is 1 octet in length and has a value of 1.
+
+
+3.4.2.2    Tag Length
+
+This field is 1 octet in length.  It is the total length of the tag type
+including the type and length fields.  With the current IP header length
+restriction of 40 bytes the value within this field is between 4 and 34.
+
+
+3.4.2.3    Alignment Octet
+
+This field is 1 octet in length and always has the value of 0.  Its purpose
+is to align the category bitmap field on an even octet boundary.  This will
+speed many implementations including router implementations.
+
+
+3.4.2.4    Sensitivity Level
+
+This field is 1 octet in length.  Its value is from 0 to 255.  The values
+are ordered with 0 being the minimum value and 255 representing the maximum
+value.
+
+
+3.4.2.5    Bit Map of Categories
+
+The length of this field is variable and ranges from 0 to 30 octets.  This
+provides representation of categories 0 to 239.  The ordering of the bits
+is left to right or MSB to LSB.  For example category 0 is represented by
+the most significant bit of the first byte and category 15 is represented
+by the least significant bit of the second byte.  Figure 4 graphically
+shows this ordering.  Bit N is binary 1 if category N is part of the label
+for the datagram, and bit N is binary 0 if category N is not part of the
+label.  Except for the optimized tag 1 format described in the next section,
+
+
+
+Internet Draft, Expires 15 Jan 93                                 [PAGE 4]
+
+
+
+CIPSO INTERNET DRAFT                                         16 July, 1992
+
+
+
+minimal encoding SHOULD be used resulting in no trailing zero octets in the
+category bitmap.
+
+        octet 0  octet 1  octet 2  octet 3  octet 4  octet 5
+        XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX . . .
+bit     01234567 89111111 11112222 22222233 33333333 44444444
+number             012345 67890123 45678901 23456789 01234567
+
+            Figure 4. Ordering of Bits in Tag 1 Bit Map
+
+
+3.4.2.6    Optimized Tag 1 Format
+
+Routers work most efficiently when processing fixed length fields.  To
+support these routers there is an optimized form of tag type 1.  The format
+does not change.  The only change is to the category bitmap which is set to
+a constant length of 10 octets.  Trailing octets required to fill out the 10
+octets are zero filled.  Ten octets, allowing for 80 categories, was chosen
+because it makes the total length of the CIPSO option 20 octets.  If CIPSO
+is the only option then the option will be full word aligned and additional
+filler octets will not be required.
+
+
+3.4.3    Tag Type 2
+
+This is referred to as the "enumerated" tag type.  It is used to describe
+large but sparsely populated sets of categories.  Tag type 2 is in the MAC
+Sensitivity tag type class.  The format of this tag type is as follows:
+
++----------+----------+----------+----------+-------------//-------------+
+| 00000010 | LLLLLLLL | 00000000 | LLLLLLLL | CCCCCCCCCCCCCCCCCCCCCCCCCC |
++----------+----------+----------+----------+-------------//-------------+
+
+    TAG       TAG      ALIGNMENT  SENSITIVITY         ENUMERATED
+    TYPE      LENGTH   OCTET      LEVEL               CATEGORIES
+
+                Figure 5. Tag Type 2 Format
+
+
+3.4.3.1     Tag Type
+
+This field is one octet in length and has a value of 2.
+
+
+3.4.3.2    Tag Length
+
+This field is 1 octet in length. It is the total length of the tag type
+including the type and length fields.  With the current IP header length
+restriction of 40 bytes the value within this field is between 4 and 34.
+
+
+3.4.3.3    Alignment Octet
+
+This field is 1 octet in length and always has the value of 0.  Its purpose
+is to align the category field on an even octet boundary.  This will
+
+
+
+Internet Draft, Expires 15 Jan 93                                 [PAGE 5]
+
+
+
+CIPSO INTERNET DRAFT                                         16 July, 1992
+
+
+
+speed many implementations including router implementations.
+
+
+3.4.3.4    Sensitivity Level
+
+This field is 1 octet in length. Its value is from 0 to 255.  The values
+are ordered with 0 being the minimum value and 255 representing the
+maximum value.
+
+
+3.4.3.5    Enumerated Categories
+
+In this tag, categories are represented by their actual value rather than
+by their position within a bit field.  The length of each category is 2
+octets.  Up to 15 categories may be represented by this tag.  Valid values
+for categories are 0 to 65534.  Category 65535 is not a valid category
+value.  The categories MUST be listed in ascending order within the tag.
+
+
+3.4.4    Tag Type 5
+
+This is referred to as the "range" tag type.  It is used to represent
+labels where all categories in a range, or set of ranges, are included
+in the sensitivity label.  Tag type 5 is in the MAC Sensitivity tag type
+class.  The format of this tag type is as follows:
+
++----------+----------+----------+----------+------------//-------------+
+| 00000101 | LLLLLLLL | 00000000 | LLLLLLLL |  Top/Bottom | Top/Bottom  |
++----------+----------+----------+----------+------------//-------------+
+
+    TAG       TAG      ALIGNMENT  SENSITIVITY        CATEGORY RANGES
+    TYPE      LENGTH   OCTET      LEVEL
+
+                     Figure 6. Tag Type 5 Format
+
+
+3.4.4.1     Tag Type
+
+This field is one octet in length and has a value of 5.
+
+
+3.4.4.2    Tag Length
+
+This field is 1 octet in length. It is the total length of the tag type
+including the type and length fields.  With the current IP header length
+restriction of 40 bytes the value within this field is between 4 and 34.
+
+
+3.4.4.3    Alignment Octet
+
+This field is 1 octet in length and always has the value of 0.  Its purpose
+is to align the category range field on an even octet boundary.  This will
+speed many implementations including router implementations.
+
+
+
+
+
+Internet Draft, Expires 15 Jan 93                                 [PAGE 6]
+
+
+
+CIPSO INTERNET DRAFT                                         16 July, 1992
+
+
+
+3.4.4.4    Sensitivity Level
+
+This field is 1 octet in length. Its value is from 0 to 255.  The values
+are ordered with 0 being the minimum value and 255 representing the maximum
+value.
+
+
+3.4.4.5    Category Ranges
+
+A category range is a 4 octet field comprised of the 2 octet index of the
+highest numbered category followed by the 2 octet index of the lowest
+numbered category.  These range endpoints are inclusive within the range of
+categories.  All categories within a range are included in the sensitivity
+label.  This tag may contain a maximum of 7 category pairs.  The bottom
+category endpoint for the last pair in the tag MAY be omitted and SHOULD be
+assumed to be 0.  The ranges MUST be non-overlapping and be listed in
+descending order.  Valid values for categories are 0 to 65534.  Category
+65535 is not a valid category value.
+
+
+3.4.5     Minimum Requirements
+
+A CIPSO implementation MUST be capable of generating at least tag type 1 in
+the non-optimized form.  In addition, a CIPSO implementation MUST be able
+to receive any valid tag type 1 even those using the optimized tag type 1
+format.
+
+
+4.    Configuration Parameters
+
+The configuration parameters defined below are required for all CIPSO hosts,
+gateways, and routers that support multiple sensitivity labels.  A CIPSO
+host is defined to be the origination or destination system for an IP
+datagram.  A CIPSO gateway provides IP routing services between two or more
+IP networks and may be required to perform label translations between
+networks.  A CIPSO gateway may be an enhanced CIPSO host or it may just
+provide gateway services with no end system CIPSO capabilities.  A CIPSO
+router is a dedicated IP router that routes IP datagrams between two or more
+IP networks.
+
+An implementation of CIPSO on a host MUST have the capability to reject a
+datagram for reasons that the information contained can not be adequately
+protected by the receiving host or if acceptance may result in violation of
+the host or network security policy.  In addition, a CIPSO gateway or router
+MUST be able to reject datagrams going to networks that can not provide
+adequate protection or may violate the network's security policy.  To
+provide this capability the following minimal set of configuration
+parameters are required for CIPSO implementations:
+
+HOST_LABEL_MAX - This parameter contains the maximum sensitivity label that
+a CIPSO host is authorized to handle.  All datagrams that have a label
+greater than this maximum MUST be rejected by the CIPSO host.  This
+parameter does not apply to CIPSO gateways or routers.  This parameter need
+not be defined explicitly as it can be implicitly derived from the
+PORT_LABEL_MAX parameters for the associated interfaces.
+
+
+
+Internet Draft, Expires 15 Jan 93                                 [PAGE 7]
+
+
+
+CIPSO INTERNET DRAFT                                         16 July, 1992
+
+
+
+
+HOST_LABEL_MIN - This parameter contains the minimum sensitivity label that
+a CIPSO host is authorized to handle.  All datagrams that have a label less
+than this minimum MUST be rejected by the CIPSO host.  This parameter does
+not apply to CIPSO gateways or routers.  This parameter need not be defined
+explicitly as it can be implicitly derived from the PORT_LABEL_MIN
+parameters for the associated interfaces.
+
+PORT_LABEL_MAX - This parameter contains the maximum sensitivity label for
+all datagrams that may exit a particular network interface port.  All
+outgoing datagrams that have a label greater than this maximum MUST be
+rejected by the CIPSO system.  The label within this parameter MUST be
+less than or equal to the label within the HOST_LABEL_MAX parameter.  This
+parameter does not apply to CIPSO hosts that support only one network port.
+
+PORT_LABEL_MIN - This parameter contains the minimum sensitivity label for
+all datagrams that may exit a particular network interface port.  All
+outgoing datagrams that have a label less than this minimum MUST be
+rejected by the CIPSO system.  The label within this parameter MUST be
+greater than or equal to the label within the HOST_LABEL_MIN parameter.
+This parameter does not apply to CIPSO hosts that support only one network
+port.
+
+PORT_DOI - This parameter is used to assign a DOI identifier value to a
+particular network interface port.  All CIPSO labels within datagrams
+going out this port MUST use the specified DOI identifier.  All CIPSO
+hosts and gateways MUST support either this parameter, the NET_DOI
+parameter, or the HOST_DOI parameter.
+
+NET_DOI - This parameter is used to assign a DOI identifier value to a
+particular IP network address.  All CIPSO labels within datagrams destined
+for the particular IP network MUST use the specified DOI identifier.  All
+CIPSO hosts and gateways MUST support either this parameter, the PORT_DOI
+parameter, or the HOST_DOI parameter.
+
+HOST_DOI - This parameter is used to assign a DOI identifier value to a
+particular IP host address.  All CIPSO labels within datagrams destined for
+the particular IP host will use the specified DOI identifier.  All CIPSO
+hosts and gateways MUST support either this parameter, the PORT_DOI
+parameter, or the NET_DOI parameter.
+
+This list represents the minimal set of configuration parameters required
+to be compliant.  Implementors are encouraged to add to this list to
+provide enhanced functionality and control.  For example, many security
+policies may require both incoming and outgoing datagrams be checked against
+the port and host label ranges.
+
+
+4.1    Port Range Parameters
+
+The labels represented by the PORT_LABEL_MAX and PORT_LABEL_MIN parameters
+MAY be in CIPSO or local format.  Some CIPSO systems, such as routers, may
+want to have the range parameters expressed in CIPSO format so that incoming
+labels do not have to be converted to a local format before being compared
+against the range.  If multiple DOIs are supported by one of these CIPSO
+
+
+
+Internet Draft, Expires 15 Jan 93                                 [PAGE 8]
+
+
+
+CIPSO INTERNET DRAFT                                         16 July, 1992
+
+
+
+systems then multiple port range parameters would be needed, one set for
+each DOI supported on a particular port.
+
+The port range will usually represent the total set of labels that may
+exist on the logical network accessed through the corresponding network
+interface.  It may, however, represent a subset of these labels that are
+allowed to enter the CIPSO system.
+
+
+4.2    Single Label CIPSO Hosts
+
+CIPSO implementations that support only one label are not required to
+support the parameters described above.  These limited implementations are
+only required to support a NET_LABEL parameter.  This parameter contains
+the CIPSO label that may be inserted in datagrams that exit the host.  In
+addition, the host MUST reject any incoming datagram that has a label which
+is not equivalent to the NET_LABEL parameter.
+
+
+5.    Handling Procedures
+
+This section describes the processing requirements for incoming and
+outgoing IP datagrams.  Just providing the correct CIPSO label format
+is not enough.  Assumptions will be made by one system on how a
+receiving system will handle the CIPSO label.  Wrong assumptions may
+lead to non-interoperability or even a security incident.  The
+requirements described below represent the minimal set needed for
+interoperability and that provide users some level of confidence.
+Many other requirements could be added to increase user confidence,
+however at the risk of restricting creativity and limiting vendor
+participation.
+
+
+5.1    Input Procedures
+
+All datagrams received through a network port MUST have a security label
+associated with them, either contained in the datagram or assigned to the
+receiving port.  Without this label the host, gateway, or router will not
+have the information it needs to make security decisions.  This security
+label will be obtained from the CIPSO if the option is present in the
+datagram.  See section 4.1.2 for handling procedures for unlabeled
+datagrams.  This label will be compared against the PORT (if appropriate)
+and HOST configuration parameters defined in section 3.
+
+If any field within the CIPSO option, such as the DOI identifier, is not
+recognized the IP datagram is discarded and an ICMP "parameter problem"
+(type 12) is generated and returned.  The ICMP code field is set to "bad
+parameter" (code 0) and the pointer is set to the start of the CIPSO field
+that is unrecognized.
+
+If the contents of the CIPSO are valid but the security label is
+outside of the configured host or port label range, the datagram is
+discarded and an ICMP "destination unreachable" (type 3) is generated
+and returned.  The code field of the ICMP is set to "communication with
+destination network administratively prohibited" (code 9) or to
+
+
+
+Internet Draft, Expires 15 Jan 93                                 [PAGE 9]
+
+
+
+CIPSO INTERNET DRAFT                                         16 July, 1992
+
+
+
+"communication with destination host administratively prohibited"
+(code 10).  The value of the code field used is dependent upon whether
+the originator of the ICMP message is acting as a CIPSO host or a CIPSO
+gateway.  The recipient of the ICMP message MUST be able to handle either
+value.  The same procedure is performed if a CIPSO can not be added to an
+IP packet because it is too large to fit in the IP options area.
+
+If the error is triggered by receipt of an ICMP message, the message
+is discarded and no response is permitted (consistent with general ICMP
+processing rules).
+
+
+5.1.1    Unrecognized tag types
+
+The default condition for any CIPSO implementation is that an
+unrecognized tag type MUST be treated as a "parameter problem" and
+handled as described in section 4.1.  A CIPSO implementation MAY allow
+the system administrator to identify tag types that may safely be
+ignored.  This capability is an allowable enhancement, not a
+requirement.
+
+
+5.1.2    Unlabeled Packets
+
+A network port may be configured to not require a CIPSO label for all
+incoming  datagrams.  For this configuration a CIPSO label must be
+assigned to that network port and associated with all unlabeled IP
+datagrams.  This capability might be used for single level networks or
+networks that have CIPSO and non-CIPSO hosts and the non-CIPSO hosts
+all operate at the same label.
+
+If a CIPSO option is required and none is found, the datagram is
+discarded and an ICMP "parameter problem" (type 12) is generated and
+returned to the originator of the datagram.  The code field of the ICMP
+is set to "option missing" (code 1) and the ICMP pointer is set to 134
+(the value of the option type for the missing CIPSO option).
+
+
+5.2    Output Procedures
+
+A CIPSO option MUST appear only once in a datagram.  Only one tag type
+from the MAC Sensitivity class MAY be included in a CIPSO option.  Given
+the current set of defined tag types, this means that CIPSO labels at
+first will contain only one tag.
+
+All datagrams leaving a CIPSO system MUST meet the following condition:
+
+        PORT_LABEL_MIN <= CIPSO label <= PORT_LABEL_MAX
+
+If this condition is not satisfied the datagram MUST be discarded.
+If the CIPSO system only supports one port, the HOST_LABEL_MIN and the
+HOST_LABEL_MAX parameters MAY be substituted for the PORT parameters in
+the above condition.
+
+The DOI identifier to be used for all outgoing datagrams is configured by
+
+
+
+Internet Draft, Expires 15 Jan 93                                 [PAGE 10]
+
+
+
+CIPSO INTERNET DRAFT                                         16 July, 1992
+
+
+
+the administrator.  If port level DOI identifier assignment is used, then
+the PORT_DOI configuration parameter MUST contain the DOI identifier to
+use.  If network level DOI assignment is used, then the NET_DOI parameter
+MUST contain the DOI identifier to use.  And if host level DOI assignment
+is employed, then the HOST_DOI parameter MUST contain the DOI identifier
+to use.  A CIPSO implementation need only support one level of DOI
+assignment.
+
+
+5.3    DOI Processing Requirements
+
+A CIPSO implementation MUST support at least one DOI and SHOULD support
+multiple DOIs.  System and network administrators are cautioned to
+ensure that at least one DOI is common within an IP network to allow for
+broadcasting of IP datagrams.
+
+CIPSO gateways MUST be capable of translating a CIPSO option from one
+DOI to another when forwarding datagrams between networks.  For
+efficiency purposes this capability is only a desired feature for CIPSO
+routers.
+
+
+5.4    Label of ICMP Messages
+
+The CIPSO label to be used on all outgoing ICMP messages MUST be equivalent
+to the label of the datagram that caused the ICMP message.  If the ICMP was
+generated due to a problem associated with the original CIPSO label then the
+following responses are allowed:
+
+  a.  Use the CIPSO label of the original IP datagram
+  b.  Drop the original datagram with no return message generated
+
+In most cases these options will have the same effect.  If you can not
+interpret the label or if it is outside the label range of your host or
+interface then an ICMP message with the same label will probably not be
+able to exit the system.
+
+
+6.    Assignment of DOI Identifier Numbers                                   =
+
+Requests for assignment of a DOI identifier number should be addressed to
+the Internet Assigned Numbers Authority (IANA).
+
+
+7.    Acknowledgements
+
+Much of the material in this RFC is based on (and copied from) work
+done by Gary Winiger of Sun Microsystems and published as Commercial
+IP Security Option at the INTEROP 89, Commercial IPSO Workshop.
+
+
+8.    Author's Address
+
+To submit mail for distribution to members of the IETF CIPSO Working
+Group, send mail to: cipso@wdl1.wdl.loral.com.
+
+
+
+Internet Draft, Expires 15 Jan 93                                 [PAGE 11]
+
+
+
+CIPSO INTERNET DRAFT                                         16 July, 1992
+
+
+
+
+To be added to or deleted from this distribution, send mail to:
+cipso-request@wdl1.wdl.loral.com.
+
+
+9.    References
+
+RFC 1038, "Draft Revised IP Security Option", M. St. Johns, IETF, January
+1988.
+
+RFC 1108, "U.S. Department of Defense Security Options
+for the Internet Protocol", Stephen Kent, IAB, 1 March, 1991.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Internet Draft, Expires 15 Jan 93                                 [PAGE 12]
+
+
+

Documentation/netlabel/introduction.txt

@@ -0,0 +1,46 @@
+NetLabel Introduction
+==============================================================================
+Paul Moore, paul.moore@hp.com
+
+August 2, 2006
+
+ * Overview
+
+NetLabel is a mechanism which can be used by kernel security modules to attach
+security attributes to outgoing network packets generated from user space
+applications and read security attributes from incoming network packets.  It
+is composed of three main components, the protocol engines, the communication
+layer, and the kernel security module API.
+
+ * Protocol Engines
+
+The protocol engines are responsible for both applying and retrieving the
+network packet's security attributes.  If any translation between the network
+security attributes and those on the host are required then the protocol
+engine will handle those tasks as well.  Other kernel subsystems should
+refrain from calling the protocol engines directly, instead they should use
+the NetLabel kernel security module API described below.
+
+Detailed information about each NetLabel protocol engine can be found in this
+directory, consult '00-INDEX' for filenames.
+
+ * Communication Layer
+
+The communication layer exists to allow NetLabel configuration and monitoring
+from user space.  The NetLabel communication layer uses a message based
+protocol built on top of the Generic NETLINK transport mechanism.  The exact
+formatting of these NetLabel messages as well as the Generic NETLINK family
+names can be found in the the 'net/netlabel/' directory as comments in the
+header files as well as in 'include/net/netlabel.h'.
+
+ * Security Module API
+
+The purpose of the NetLabel security module API is to provide a protocol
+independent interface to the underlying NetLabel protocol engines.  In addition
+to protocol independence, the security module API is designed to be completely
+LSM independent which should allow multiple LSMs to leverage the same code
+base.
+
+Detailed information about the NetLabel security module API can be found in the
+'include/net/netlabel.h' header file as well as the 'lsm_interface.txt' file
+found in this directory.

Documentation/netlabel/lsm_interface.txt

@@ -0,0 +1,47 @@
+NetLabel Linux Security Module Interface
+==============================================================================
+Paul Moore, paul.moore@hp.com
+
+May 17, 2006
+
+ * Overview
+
+NetLabel is a mechanism which can set and retrieve security attributes from
+network packets.  It is intended to be used by LSM developers who want to make
+use of a common code base for several different packet labeling protocols.
+The NetLabel security module API is defined in 'include/net/netlabel.h' but a
+brief overview is given below.
+
+ * NetLabel Security Attributes
+
+Since NetLabel supports multiple different packet labeling protocols and LSMs
+it uses the concept of security attributes to refer to the packet's security
+labels.  The NetLabel security attributes are defined by the
+'netlbl_lsm_secattr' structure in the NetLabel header file.  Internally the
+NetLabel subsystem converts the security attributes to and from the correct
+low-level packet label depending on the NetLabel build time and run time
+configuration.  It is up to the LSM developer to translate the NetLabel
+security attributes into whatever security identifiers are in use for their
+particular LSM.
+
+ * NetLabel LSM Protocol Operations
+
+These are the functions which allow the LSM developer to manipulate the labels
+on outgoing packets as well as read the labels on incoming packets.  Functions
+exist to operate both on sockets as well as the sk_buffs directly.  These high
+level functions are translated into low level protocol operations based on how
+the administrator has configured the NetLabel subsystem.
+
+ * NetLabel Label Mapping Cache Operations
+
+Depending on the exact configuration, translation between the network packet
+label and the internal LSM security identifier can be time consuming.  The
+NetLabel label mapping cache is a caching mechanism which can be used to
+sidestep much of this overhead once a mapping has been established.  Once the
+LSM has received a packet, used NetLabel to decode it's security attributes,
+and translated the security attributes into a LSM internal identifier the LSM
+can use the NetLabel caching functions to associate the LSM internal
+identifier with the network packet's label.  This means that in the future
+when a incoming packet matches a cached value not only are the internal
+NetLabel translation mechanisms bypassed but the LSM translation mechanisms are
+bypassed as well which should result in a significant reduction in overhead.

Documentation/networking/ip-sysctl.txt

@@ -375,6 +375,41 @@ tcp_slow_start_after_idle - BOOLEAN
 	be timed out after an idle period.
 	Default: 1
 
+CIPSOv4 Variables:
+
+cipso_cache_enable - BOOLEAN
+	If set, enable additions to and lookups from the CIPSO label mapping
+	cache.  If unset, additions are ignored and lookups always result in a
+	miss.  However, regardless of the setting the cache is still
+	invalidated when required when means you can safely toggle this on and
+	off and the cache will always be "safe".
+	Default: 1
+
+cipso_cache_bucket_size - INTEGER
+	The CIPSO label cache consists of a fixed size hash table with each
+	hash bucket containing a number of cache entries.  This variable limits
+	the number of entries in each hash bucket; the larger the value the
+	more CIPSO label mappings that can be cached.  When the number of
+	entries in a given hash bucket reaches this limit adding new entries
+	causes the oldest entry in the bucket to be removed to make room.
+	Default: 10
+
+cipso_rbm_optfmt - BOOLEAN
+	Enable the "Optimized Tag 1 Format" as defined in section 3.4.2.6 of
+	the CIPSO draft specification (see Documentation/netlabel for details).
+	This means that when set the CIPSO tag will be padded with empty
+	categories in order to make the packet data 32-bit aligned.
+	Default: 0
+
+cipso_rbm_structvalid - BOOLEAN
+	If set, do a very strict check of the CIPSO option when
+	ip_options_compile() is called.  If unset, relax the checks done during
+	ip_options_compile().  Either way is "safe" as errors are caught else
+	where in the CIPSO processing code but setting this to 0 (False) should
+	result in less work (i.e. it should be faster) but could cause problems
+	with other implementations that require strict checking.
+	Default: 0
+
 IP Variables:
 
 ip_local_port_range - 2 INTEGERS
@@ -730,6 +765,9 @@ conf/all/forwarding - BOOLEAN
 
 	This referred to as global forwarding.
 
+proxy_ndp - BOOLEAN
+	Do proxy ndp.
+
 conf/interface/*:
 	Change special settings per interface.
 

Documentation/networking/secid.txt

@@ -0,0 +1,14 @@
+flowi structure:
+
+The secid member in the flow structure is used in LSMs (e.g. SELinux) to indicate
+the label of the flow. This label of the flow is currently used in selecting
+matching labeled xfrm(s).
+
+If this is an outbound flow, the label is derived from the socket, if any, or
+the incoming packet this flow is being generated as a response to (e.g. tcp
+resets, timewait ack, etc.). It is also conceivable that the label could be
+derived from other sources such as process context, device, etc., in special
+cases, as may be appropriate.
+
+If this is an inbound flow, the label is derived from the IPSec security
+associations, if any, used by the packet.

Documentation/sound/alsa/ALSA-Configuration.txt

@@ -758,6 +758,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
     position_fix - Fix DMA pointer (0 = auto, 1 = none, 2 = POSBUF, 3 = FIFO size)
     single_cmd  - Use single immediate commands to communicate with
 		codecs (for debugging only)
+    disable_msi - Disable Message Signaled Interrupt (MSI)
 
     This module supports one card and autoprobe.
 
@@ -778,11 +779,16 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
 	  6stack-digout	6-jack with a SPDIF out
 	  w810		3-jack
 	  z71v		3-jack (HP shared SPDIF)
-	  asus		3-jack
+	  asus		3-jack (ASUS Mobo)
+	  asus-w1v	ASUS W1V
+	  asus-dig	ASUS with SPDIF out
+	  asus-dig2	ASUS with SPDIF out (using GPIO2)
 	  uniwill	3-jack
 	  F1734		2-jack
 	  lg		LG laptop (m1 express dual)
-	  lg-lw		LG LW20 laptop
+	  lg-lw		LG LW20/LW25 laptop
+	  tcl		TCL S700
+	  clevo		Clevo laptops (m520G, m665n)
 	  test		for testing/debugging purpose, almost all controls can be
 			adjusted.  Appearing only when compiled with
 			$CONFIG_SND_DEBUG=y
@@ -790,6 +796,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
 
 	ALC260
 	  hp		HP machines
+	  hp-3013	HP machines (3013-variant)
 	  fujitsu	Fujitsu S7020
 	  acer		Acer TravelMate
 	  basic		fixed pin assignment (old default model)
@@ -797,24 +804,32 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
 
 	ALC262
 	  fujitsu	Fujitsu Laptop
+	  hp-bpc	HP xw4400/6400/8400/9400 laptops
+	  benq		Benq ED8
 	  basic		fixed pin assignment w/o SPDIF
 	  auto		auto-config reading BIOS (default)
 
 	ALC882/885
 	  3stack-dig	3-jack with SPDIF I/O
 	  6stck-dig	6-jack digital with SPDIF I/O
+	  arima		Arima W820Di1
 	  auto		auto-config reading BIOS (default)
 
 	ALC883/888
 	  3stack-dig	3-jack with SPDIF I/O
 	  6stack-dig	6-jack digital with SPDIF I/O
-	  6stack-dig-demo  6-stack digital for Intel demo board
+	  3stack-6ch    3-jack 6-channel
+	  3stack-6ch-dig 3-jack 6-channel with SPDIF I/O
+	  6stack-dig-demo  6-jack digital for Intel demo board
+	  acer		Acer laptops (Travelmate 3012WTMi, Aspire 5600, etc)
 	  auto		auto-config reading BIOS (default)
 
 	ALC861/660
 	  3stack	3-jack
 	  3stack-dig	3-jack with SPDIF I/O
 	  6stack-dig	6-jack with SPDIF I/O
+	  3stack-660	3-jack (for ALC660)
+	  uniwill-m31	Uniwill M31 laptop
 	  auto		auto-config reading BIOS (default)
 
 	CMI9880
@@ -843,10 +858,21 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
 	  3stack-dig	ditto with SPDIF
 	  laptop	3-jack with hp-jack automute
 	  laptop-dig	ditto with SPDIF
-	  auto		auto-confgi reading BIOS (default)
+	  auto		auto-config reading BIOS (default)
+
+	STAC9200/9205/9220/9221/9254
+	  ref		Reference board
+	  3stack	D945 3stack
+	  5stack	D945 5stack + SPDIF
 
-	STAC7661(?)
+	STAC9227/9228/9229/927x
+	  ref		Reference board
+	  3stack	D965 3stack
+	  5stack	D965 5stack + SPDIF
+
+	STAC9872
 	  vaio		Setup for VAIO FE550G/SZ110
+	  vaio-ar Setup for VAIO AR
 
     If the default configuration doesn't work and one of the above
     matches with your device, report it together with the PCI
@@ -1213,6 +1239,14 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
     
     Module supports only 1 card.  This module has no enable option.
 
+  Module snd-mts64
+  ----------------
+
+    Module for Ego Systems (ESI) Miditerminal 4140
+
+    This module supports multiple devices.
+    Requires parport (CONFIG_PARPORT).
+
   Module snd-nm256
   ----------------
 

Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl

@@ -1054,9 +1054,8 @@
 
       <para>
       For a device which allows hotplugging, you can use
-      <function>snd_card_free_in_thread</function>.  This one will
-      postpone the destruction and wait in a kernel-thread until all
-      devices are closed.
+      <function>snd_card_free_when_closed</function>.  This one will
+      postpone the destruction until all devices are closed.
       </para>
 
     </section>

arch/powerpc/platforms/powermac/feature.c

@@ -1058,8 +1058,8 @@ core99_reset_cpu(struct device_node *node, long param, long value)
 	if (np == NULL)
 		return -ENODEV;
 	for (np = np->child; np != NULL; np = np->sibling) {
-		u32 *num = get_property(np, "reg", NULL);
-		u32 *rst = get_property(np, "soft-reset", NULL);
+		const u32 *num = get_property(np, "reg", NULL);
+		const u32 *rst = get_property(np, "soft-reset", NULL);
 		if (num == NULL || rst == NULL)
 			continue;
 		if (param == *num) {

arch/powerpc/platforms/powermac/smp.c

@@ -702,7 +702,7 @@ static void __init smp_core99_setup(int ncpus)
 	/* GPIO based HW sync on ppc32 Core99 */
 	if (pmac_tb_freeze == NULL && !machine_is_compatible("MacRISC4")) {
 		struct device_node *cpu;
-		u32 *tbprop = NULL;
+		const u32 *tbprop = NULL;
 
 		core99_tb_gpio = KL_GPIO_TB_ENABLE;	/* default value */
 		cpu = of_find_node_by_type(NULL, "cpu");

block/ll_rw_blk.c

@@ -2801,6 +2801,18 @@ long blk_congestion_wait(int rw, long timeout)
 
 EXPORT_SYMBOL(blk_congestion_wait);
 
+/**
+ * blk_congestion_end - wake up sleepers on a congestion queue
+ * @rw: READ or WRITE
+ */
+void blk_congestion_end(int rw)
+{
+	wait_queue_head_t *wqh = &congestion_wqh[rw];
+
+	if (waitqueue_active(wqh))
+		wake_up(wqh);
+}
+
 /*
  * Has to be called with the request spinlock acquired
  */

crypto/hmac.c

@@ -92,13 +92,17 @@ static int hmac_init(struct hash_desc *pdesc)
 	struct hmac_ctx *ctx = align_ptr(ipad + bs * 2 + ds, sizeof(void *));
 	struct hash_desc desc;
 	struct scatterlist tmp;
+	int err;
 
 	desc.tfm = ctx->child;
 	desc.flags = pdesc->flags & CRYPTO_TFM_REQ_MAY_SLEEP;
 	sg_set_buf(&tmp, ipad, bs);
 
-	return unlikely(crypto_hash_init(&desc)) ?:
-	       crypto_hash_update(&desc, &tmp, 1);
+	err = crypto_hash_init(&desc);
+	if (unlikely(err))
+		return err;
+
+	return crypto_hash_update(&desc, &tmp, bs);
 }
 
 static int hmac_update(struct hash_desc *pdesc,
@@ -123,13 +127,17 @@ static int hmac_final(struct hash_desc *pdesc, u8 *out)
 	struct hmac_ctx *ctx = align_ptr(digest + ds, sizeof(void *));
 	struct hash_desc desc;
 	struct scatterlist tmp;
+	int err;
 
 	desc.tfm = ctx->child;
 	desc.flags = pdesc->flags & CRYPTO_TFM_REQ_MAY_SLEEP;
 	sg_set_buf(&tmp, opad, bs + ds);
 
-	return unlikely(crypto_hash_final(&desc, digest)) ?:
-	       crypto_hash_digest(&desc, &tmp, bs + ds, out);
+	err = crypto_hash_final(&desc, digest);
+	if (unlikely(err))
+		return err;
+
+	return crypto_hash_digest(&desc, &tmp, bs + ds, out);
 }
 
 static int hmac_digest(struct hash_desc *pdesc, struct scatterlist *sg,
@@ -145,6 +153,7 @@ static int hmac_digest(struct hash_desc *pdesc, struct scatterlist *sg,
 	struct hash_desc desc;
 	struct scatterlist sg1[2];
 	struct scatterlist sg2[1];
+	int err;
 
 	desc.tfm = ctx->child;
 	desc.flags = pdesc->flags & CRYPTO_TFM_REQ_MAY_SLEEP;
@@ -154,8 +163,11 @@ static int hmac_digest(struct hash_desc *pdesc, struct scatterlist *sg,
 	sg1[1].length = 0;
 	sg_set_buf(sg2, opad, bs + ds);
 
-	return unlikely(crypto_hash_digest(&desc, sg1, nbytes + bs, digest)) ?:
-	       crypto_hash_digest(&desc, sg2, bs + ds, out);
+	err = crypto_hash_digest(&desc, sg1, nbytes + bs, digest);
+	if (unlikely(err))
+		return err;
+
+	return crypto_hash_digest(&desc, sg2, bs + ds, out);
 }
 
 static int hmac_init_tfm(struct crypto_tfm *tfm)

drivers/atm/he.c

@@ -1912,7 +1912,7 @@ he_service_rbrq(struct he_dev *he_dev, int group)
 				skb->tail = skb->data + skb->len;
 #ifdef USE_CHECKSUM_HW
 				if (vcc->vpi == 0 && vcc->vci >= ATM_NOT_RSV_VCI) {
-					skb->ip_summed = CHECKSUM_HW;
+					skb->ip_summed = CHECKSUM_COMPLETE;
 					skb->csum = TCP_CKSUM(skb->data,
 							he_vcc->pdu_len);
 				}

drivers/char/briq_panel.c

@@ -87,7 +87,7 @@ static int briq_panel_release(struct inode *ino, struct file *filep)
 	return 0;
 }
 
-static ssize_t briq_panel_read(struct file *file, char *buf, size_t count,
+static ssize_t briq_panel_read(struct file *file, char __user *buf, size_t count,
 			 loff_t *ppos)
 {
 	unsigned short c;
@@ -135,7 +135,7 @@ static void scroll_vfd( void )
 	vfd_cursor = 20;
 }
 
-static ssize_t briq_panel_write(struct file *file, const char *buf, size_t len,
+static ssize_t briq_panel_write(struct file *file, const char __user *buf, size_t len,
 			  loff_t *ppos)
 {
 	size_t indx = len;
@@ -150,19 +150,22 @@ static ssize_t briq_panel_write(struct file *file, const char *buf, size_t len,
 		return -EBUSY;
 
 	for (;;) {
+		char c;
 		if (!indx)
 			break;
+		if (get_user(c, buf))
+			return -EFAULT;
 		if (esc) {
-			set_led(*buf);
+			set_led(c);
 			esc = 0;
-		} else if (*buf == 27) {
+		} else if (c == 27) {
 			esc = 1;
-		} else if (*buf == 12) {
+		} else if (c == 12) {
 			/* do a form feed */
 			for (i=0; i<40; i++)
 				vfd[i] = ' ';
 			vfd_cursor = 0;
-		} else if (*buf == 10) {
+		} else if (c == 10) {
 			if (vfd_cursor < 20)
 				vfd_cursor = 20;
 			else if (vfd_cursor < 40)
@@ -175,7 +178,7 @@ static ssize_t briq_panel_write(struct file *file, const char *buf, size_t len,
 			/* just a character */
 			if (vfd_cursor > 39)
 				scroll_vfd();
-			vfd[vfd_cursor++] = *buf;
+			vfd[vfd_cursor++] = c;
 		}
 		indx--;
 		buf++;
@@ -202,7 +205,7 @@ static struct miscdevice briq_panel_miscdev = {
 static int __init briq_panel_init(void)
 {
 	struct device_node *root = find_path_device("/");
-	char *machine;
+	const char *machine;
 	int i;
 
 	machine = get_property(root, "model", NULL);

drivers/infiniband/core/mad_priv.h

@@ -38,6 +38,7 @@
 #define __IB_MAD_PRIV_H__
 
 #include <linux/completion.h>
+#include <linux/err.h>
 #include <linux/pci.h>
 #include <linux/workqueue.h>
 #include <rdma/ib_mad.h>

drivers/infiniband/hw/amso1100/c2_provider.c

@@ -49,6 +49,7 @@
 #include <linux/init.h>
 #include <linux/dma-mapping.h>
 #include <linux/if_arp.h>
+#include <linux/vmalloc.h>
 
 #include <asm/io.h>
 #include <asm/irq.h>

drivers/infiniband/hw/amso1100/c2_rnic.c

@@ -50,6 +50,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/mm.h>
 #include <linux/inet.h>
+#include <linux/vmalloc.h>
 
 #include <linux/route.h>
 

drivers/infiniband/hw/ipath/ipath_diag.c

@@ -43,6 +43,7 @@
 
 #include <linux/io.h>
 #include <linux/pci.h>
+#include <linux/vmalloc.h>
 #include <asm/uaccess.h>
 
 #include "ipath_kernel.h"

drivers/mtd/Kconfig

@@ -101,7 +101,7 @@ config MTD_REDBOOT_PARTS_READONLY
 
 config MTD_CMDLINE_PARTS
 	bool "Command line partition table parsing"
-	depends on MTD_PARTITIONS = "y"
+	depends on MTD_PARTITIONS = "y" && MTD = "y"
 	---help---
 	  Allow generic configuration of the MTD partition tables via the kernel
 	  command line. Multiple flash resources are supported for hardware where
@@ -264,7 +264,7 @@ config RFD_FTL
 		http://www.gensw.com/pages/prod/bios/rfd.htm
 
 config SSFDC
-	bool "NAND SSFDC (SmartMedia) read only translation layer"
+	tristate "NAND SSFDC (SmartMedia) read only translation layer"
 	depends on MTD
 	default n
 	help

drivers/mtd/ssfdc.c

@@ -10,7 +10,6 @@
  * published by the Free Software Foundation.
  */
 
-#include <linux/config.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -29,7 +28,7 @@ struct ssfdcr_record {
 	int cis_block;			/* block n. containing CIS/IDI */
 	int erase_size;			/* phys_block_size */
 	unsigned short *logic_block_map; /* all zones (max 8192 phys blocks on
-					    the 128MB) */
+					    the 128MiB) */
 	int map_len;			/* n. phys_blocks on the card */
 };
 
@@ -43,11 +42,11 @@ struct ssfdcr_record {
 #define MAX_LOGIC_BLK_PER_ZONE	1000
 #define MAX_PHYS_BLK_PER_ZONE	1024
 
-#define KB(x)	( (x) * 1024L )
-#define MB(x)	( KB(x) * 1024L )
+#define KiB(x)	( (x) * 1024L )
+#define MiB(x)	( KiB(x) * 1024L )
 
 /** CHS Table
-		1MB	2MB	4MB	8MB	16MB	32MB	64MB	128MB
+		1MiB	2MiB	4MiB	8MiB	16MiB	32MiB	64MiB	128MiB
 NCylinder	125	125	250	250	500	500	500	500
 NHead		4	4	4	4	4	8	8	16
 NSector		4	8	8	16	16	16	32	32
@@ -64,14 +63,14 @@ typedef struct {
 
 /* Must be ordered by size */
 static const chs_entry_t chs_table[] = {
-	{ MB(  1), 125,  4,  4 },
-	{ MB(  2), 125,  4,  8 },
-	{ MB(  4), 250,  4,  8 },
-	{ MB(  8), 250,  4, 16 },
-	{ MB( 16), 500,  4, 16 },
-	{ MB( 32), 500,  8, 16 },
-	{ MB( 64), 500,  8, 32 },
-	{ MB(128), 500, 16, 32 },
+	{ MiB(  1), 125,  4,  4 },
+	{ MiB(  2), 125,  4,  8 },
+	{ MiB(  4), 250,  4,  8 },
+	{ MiB(  8), 250,  4, 16 },
+	{ MiB( 16), 500,  4, 16 },
+	{ MiB( 32), 500,  8, 16 },
+	{ MiB( 64), 500,  8, 32 },
+	{ MiB(128), 500, 16, 32 },
 	{ 0 },
 };
 
@@ -109,25 +108,30 @@ static int get_valid_cis_sector(struct mtd_info *mtd)
 	int ret, k, cis_sector;
 	size_t retlen;
 	loff_t offset;
-	uint8_t sect_buf[SECTOR_SIZE];
+	uint8_t *sect_buf;
+
+	cis_sector = -1;
+
+	sect_buf = kmalloc(SECTOR_SIZE, GFP_KERNEL);
+	if (!sect_buf)
+		goto out;
 
 	/*
 	 * Look for CIS/IDI sector on the first GOOD block (give up after 4 bad
 	 * blocks). If the first good block doesn't contain CIS number the flash
 	 * is not SSFDC formatted
 	 */
-	cis_sector = -1;
 	for (k = 0, offset = 0; k < 4; k++, offset += mtd->erasesize) {
 		if (!mtd->block_isbad(mtd, offset)) {
 			ret = mtd->read(mtd, offset, SECTOR_SIZE, &retlen,
 				sect_buf);
 
 			/* CIS pattern match on the sector buffer */
-			if ( ret < 0 || retlen != SECTOR_SIZE ) {
+			if (ret < 0 || retlen != SECTOR_SIZE) {
 				printk(KERN_WARNING
 					"SSFDC_RO:can't read CIS/IDI sector\n");
-			} else if ( !memcmp(sect_buf, cis_numbers,
-					sizeof(cis_numbers)) ) {
+			} else if (!memcmp(sect_buf, cis_numbers,
+					sizeof(cis_numbers))) {
 				/* Found */
 				cis_sector = (int)(offset >> SECTOR_SHIFT);
 			} else {
@@ -140,6 +144,8 @@ static int get_valid_cis_sector(struct mtd_info *mtd)
 		}
 	}
 
+	kfree(sect_buf);
+ out:
 	return cis_sector;
 }
 
@@ -227,7 +233,7 @@ static int get_logical_address(uint8_t *oob_buf)
 		}
 	}
 
-	if ( !ok )
+	if (!ok)
 		block_address = -2;
 
 	DEBUG(MTD_DEBUG_LEVEL3, "SSFDC_RO: get_logical_address() %d\n",
@@ -245,8 +251,8 @@ static int build_logical_block_map(struct ssfdcr_record *ssfdc)
 	struct mtd_info *mtd = ssfdc->mbd.mtd;
 
 	DEBUG(MTD_DEBUG_LEVEL1, "SSFDC_RO: build_block_map() nblks=%d (%luK)\n",
-		ssfdc->map_len, (unsigned long)ssfdc->map_len *
-		ssfdc->erase_size / 1024 );
+	      ssfdc->map_len,
+	      (unsigned long)ssfdc->map_len * ssfdc->erase_size / 1024);
 
 	/* Scan every physical block, skip CIS block */
 	for (phys_block = ssfdc->cis_block + 1; phys_block < ssfdc->map_len;
@@ -323,21 +329,21 @@ static void ssfdcr_add_mtd(struct mtd_blktrans_ops *tr, struct mtd_info *mtd)
 	/* Set geometry */
 	ssfdc->heads = 16;
 	ssfdc->sectors = 32;
-	get_chs( mtd->size, NULL, &ssfdc->heads, &ssfdc->sectors);
+	get_chs(mtd->size, NULL, &ssfdc->heads, &ssfdc->sectors);
 	ssfdc->cylinders = (unsigned short)((mtd->size >> SECTOR_SHIFT) /
 			((long)ssfdc->sectors * (long)ssfdc->heads));
 
 	DEBUG(MTD_DEBUG_LEVEL1, "SSFDC_RO: using C:%d H:%d S:%d == %ld sects\n",
 		ssfdc->cylinders, ssfdc->heads , ssfdc->sectors,
 		(long)ssfdc->cylinders * (long)ssfdc->heads *
-		(long)ssfdc->sectors );
+		(long)ssfdc->sectors);
 
 	ssfdc->mbd.size = (long)ssfdc->heads * (long)ssfdc->cylinders *
 				(long)ssfdc->sectors;
 
 	/* Allocate logical block map */
-	ssfdc->logic_block_map = kmalloc( sizeof(ssfdc->logic_block_map[0]) *
-						ssfdc->map_len, GFP_KERNEL);
+	ssfdc->logic_block_map = kmalloc(sizeof(ssfdc->logic_block_map[0]) *
+					 ssfdc->map_len, GFP_KERNEL);
 	if (!ssfdc->logic_block_map) {
 		printk(KERN_WARNING
 			"SSFDC_RO: out of memory for data structures\n");
@@ -408,7 +414,7 @@ static int ssfdcr_readsect(struct mtd_blktrans_dev *dev,
 			"SSFDC_RO: ssfdcr_readsect() phys_sect_no=%lu\n",
 			sect_no);
 
-		if (read_physical_sector( ssfdc->mbd.mtd, buf, sect_no ) < 0)
+		if (read_physical_sector(ssfdc->mbd.mtd, buf, sect_no) < 0)
 			return -EIO;
 	} else {
 		memset(buf, 0xff, SECTOR_SIZE);

drivers/net/3c59x.c

@@ -2077,7 +2077,7 @@ boomerang_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	vp->tx_ring[entry].next = 0;
 #if DO_ZEROCOPY
-	if (skb->ip_summed != CHECKSUM_HW)
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
 			vp->tx_ring[entry].status = cpu_to_le32(skb->len | TxIntrUploaded);
 	else
 			vp->tx_ring[entry].status = cpu_to_le32(skb->len | TxIntrUploaded | AddTCPChksum | AddUDPChksum);

drivers/net/8139cp.c

@@ -813,7 +813,7 @@ static int cp_start_xmit (struct sk_buff *skb, struct net_device *dev)
 
 		if (mss)
 			flags |= LargeSend | ((mss & MSSMask) << MSSShift);
-		else if (skb->ip_summed == CHECKSUM_HW) {
+		else if (skb->ip_summed == CHECKSUM_PARTIAL) {
 			const struct iphdr *ip = skb->nh.iph;
 			if (ip->protocol == IPPROTO_TCP)
 				flags |= IPCS | TCPCS;
@@ -867,7 +867,7 @@ static int cp_start_xmit (struct sk_buff *skb, struct net_device *dev)
 			if (mss)
 				ctrl |= LargeSend |
 					((mss & MSSMask) << MSSShift);
-			else if (skb->ip_summed == CHECKSUM_HW) {
+			else if (skb->ip_summed == CHECKSUM_PARTIAL) {
 				if (ip->protocol == IPPROTO_TCP)
 					ctrl |= IPCS | TCPCS;
 				else if (ip->protocol == IPPROTO_UDP)
@@ -898,7 +898,7 @@ static int cp_start_xmit (struct sk_buff *skb, struct net_device *dev)
 		txd->addr = cpu_to_le64(first_mapping);
 		wmb();
 
-		if (skb->ip_summed == CHECKSUM_HW) {
+		if (skb->ip_summed == CHECKSUM_PARTIAL) {
 			if (ip->protocol == IPPROTO_TCP)
 				txd->opts1 = cpu_to_le32(first_eor | first_len |
 							 FirstFrag | DescOwn |

drivers/net/acenic.c

@@ -2040,7 +2040,7 @@ static void ace_rx_int(struct net_device *dev, u32 rxretprd, u32 rxretcsm)
 		 */
 		if (bd_flags & BD_FLG_TCP_UDP_SUM) {
 			skb->csum = htons(csum);
-			skb->ip_summed = CHECKSUM_HW;
+			skb->ip_summed = CHECKSUM_COMPLETE;
 		} else {
 			skb->ip_summed = CHECKSUM_NONE;
 		}
@@ -2511,7 +2511,7 @@ restart:
 
 		mapping = ace_map_tx_skb(ap, skb, skb, idx);
 		flagsize = (skb->len << 16) | (BD_FLG_END);
-		if (skb->ip_summed == CHECKSUM_HW)
+		if (skb->ip_summed == CHECKSUM_PARTIAL)
 			flagsize |= BD_FLG_TCP_UDP_SUM;
 #if ACENIC_DO_VLAN
 		if (vlan_tx_tag_present(skb)) {
@@ -2534,7 +2534,7 @@ restart:
 
 		mapping = ace_map_tx_skb(ap, skb, NULL, idx);
 		flagsize = (skb_headlen(skb) << 16);
-		if (skb->ip_summed == CHECKSUM_HW)
+		if (skb->ip_summed == CHECKSUM_PARTIAL)
 			flagsize |= BD_FLG_TCP_UDP_SUM;
 #if ACENIC_DO_VLAN
 		if (vlan_tx_tag_present(skb)) {
@@ -2560,7 +2560,7 @@ restart:
 					       PCI_DMA_TODEVICE);
 
 			flagsize = (frag->size << 16);
-			if (skb->ip_summed == CHECKSUM_HW)
+			if (skb->ip_summed == CHECKSUM_PARTIAL)
 				flagsize |= BD_FLG_TCP_UDP_SUM;
 			idx = (idx + 1) % ACE_TX_RING_ENTRIES(ap);
 

drivers/net/arcnet/com20020-pci.c

@@ -161,6 +161,7 @@ static struct pci_device_id com20020pci_id_table[] = {
 	{ 0x1571, 0xa204, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ARC_CAN_10MBIT },
 	{ 0x1571, 0xa205, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ARC_CAN_10MBIT },
 	{ 0x1571, 0xa206, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ARC_CAN_10MBIT },
+	{ 0x10B5, 0x9030, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ARC_CAN_10MBIT },
 	{ 0x10B5, 0x9050, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ARC_CAN_10MBIT },
 	{0,}
 };

drivers/net/bnx2.c

@@ -4423,7 +4423,7 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	ring_prod = TX_RING_IDX(prod);
 
 	vlan_tag_flags = 0;
-	if (skb->ip_summed == CHECKSUM_HW) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		vlan_tag_flags |= TX_BD_FLAGS_TCP_UDP_CKSUM;
 	}
 

drivers/net/cassini.c

@@ -2167,7 +2167,7 @@ end_copy_pkt:
 			cas_page_unmap(addr);
 	}
 	skb->csum = ntohs(i ^ 0xffff);
-	skb->ip_summed = CHECKSUM_HW;
+	skb->ip_summed = CHECKSUM_COMPLETE;
 	skb->protocol = eth_type_trans(skb, cp->dev);
 	return len;
 }
@@ -2821,7 +2821,7 @@ static inline int cas_xmit_tx_ringN(struct cas *cp, int ring,
 	}
 
 	ctrl = 0;
-	if (skb->ip_summed == CHECKSUM_HW) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		u64 csum_start_off, csum_stuff_off;
 
 		csum_start_off = (u64) (skb->h.raw - skb->data);

drivers/net/chelsio/sge.c

@@ -1470,9 +1470,9 @@ int t1_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 
 		if (!(adapter->flags & UDP_CSUM_CAPABLE) &&
-		    skb->ip_summed == CHECKSUM_HW &&
+		    skb->ip_summed == CHECKSUM_PARTIAL &&
 		    skb->nh.iph->protocol == IPPROTO_UDP)
-			if (unlikely(skb_checksum_help(skb, 0))) {
+			if (unlikely(skb_checksum_help(skb))) {
 				dev_kfree_skb_any(skb);
 				return NETDEV_TX_OK;
 			}
@@ -1495,11 +1495,11 @@ int t1_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		cpl = (struct cpl_tx_pkt *)__skb_push(skb, sizeof(*cpl));
 		cpl->opcode = CPL_TX_PKT;
 		cpl->ip_csum_dis = 1;    /* SW calculates IP csum */
-		cpl->l4_csum_dis = skb->ip_summed == CHECKSUM_HW ? 0 : 1;
+		cpl->l4_csum_dis = skb->ip_summed == CHECKSUM_PARTIAL ? 0 : 1;
 		/* the length field isn't used so don't bother setting it */
 
-		st->tx_cso += (skb->ip_summed == CHECKSUM_HW);
-		sge->stats.tx_do_cksum += (skb->ip_summed == CHECKSUM_HW);
+		st->tx_cso += (skb->ip_summed == CHECKSUM_PARTIAL);
+		sge->stats.tx_do_cksum += (skb->ip_summed == CHECKSUM_PARTIAL);
 		sge->stats.tx_reg_pkts++;
 	}
 	cpl->iff = dev->if_port;

drivers/net/dl2k.c

@@ -611,7 +611,7 @@ start_xmit (struct sk_buff *skb, struct net_device *dev)
 	txdesc = &np->tx_ring[entry];
 
 #if 0
-	if (skb->ip_summed == CHECKSUM_HW) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		txdesc->status |=
 		    cpu_to_le64 (TCPChecksumEnable | UDPChecksumEnable |
 				 IPChecksumEnable);

drivers/net/e1000/e1000_main.c

@@ -2600,7 +2600,7 @@ e1000_tx_csum(struct e1000_adapter *adapter, struct e1000_tx_ring *tx_ring,
 	unsigned int i;
 	uint8_t css;
 
-	if (likely(skb->ip_summed == CHECKSUM_HW)) {
+	if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
 		css = skb->h.raw - skb->data;
 
 		i = tx_ring->next_to_use;
@@ -2927,11 +2927,11 @@ e1000_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 	}
 
 	/* reserve a descriptor for the offload context */
-	if ((mss) || (skb->ip_summed == CHECKSUM_HW))
+	if ((mss) || (skb->ip_summed == CHECKSUM_PARTIAL))
 		count++;
 	count++;
 #else
-	if (skb->ip_summed == CHECKSUM_HW)
+	if (skb->ip_summed == CHECKSUM_PARTIAL)
 		count++;
 #endif
 
@@ -3608,7 +3608,7 @@ e1000_rx_checksum(struct e1000_adapter *adapter,
 		 */
 		csum = ntohl(csum ^ 0xFFFF);
 		skb->csum = csum;
-		skb->ip_summed = CHECKSUM_HW;
+		skb->ip_summed = CHECKSUM_COMPLETE;
 	}
 	adapter->hw_csum_good++;
 }

drivers/net/forcedeth.c

@@ -1503,7 +1503,8 @@ static int nv_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		tx_flags_extra = NV_TX2_TSO | (skb_shinfo(skb)->gso_size << NV_TX2_TSO_SHIFT);
 	else
 #endif
-	tx_flags_extra = (skb->ip_summed == CHECKSUM_HW ? (NV_TX2_CHECKSUM_L3|NV_TX2_CHECKSUM_L4) : 0);
+	tx_flags_extra = skb->ip_summed == CHECKSUM_PARTIAL ?
+			 NV_TX2_CHECKSUM_L3 | NV_TX2_CHECKSUM_L4 : 0;
 
 	/* vlan tag */
 	if (np->vlangrp && vlan_tx_tag_present(skb)) {

drivers/net/gianfar.c

@@ -947,7 +947,7 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* Set up checksumming */
 	if (likely((dev->features & NETIF_F_IP_CSUM)
-			&& (CHECKSUM_HW == skb->ip_summed))) {
+			&& (CHECKSUM_PARTIAL == skb->ip_summed))) {
 		fcb = gfar_add_fcb(skb, txbdp);
 		status |= TXBD_TOE;
 		gfar_tx_checksum(skb, fcb);

drivers/net/hamachi.c

@@ -1648,7 +1648,7 @@ static int hamachi_rx(struct net_device *dev)
 						* could do the pseudo myself and return
 						* CHECKSUM_UNNECESSARY
 						*/
-						skb->ip_summed = CHECKSUM_HW;
+						skb->ip_summed = CHECKSUM_COMPLETE;
 					}
 				}	
 			}

drivers/net/ibm_emac/ibm_emac_core.c

@@ -1036,7 +1036,7 @@ static inline u16 emac_tx_csum(struct ocp_enet_private *dev,
 			       struct sk_buff *skb)
 {
 #if defined(CONFIG_IBM_EMAC_TAH)
-	if (skb->ip_summed == CHECKSUM_HW) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		++dev->stats.tx_packets_csum;
 		return EMAC_TX_CTRL_TAH_CSUM;
 	}

drivers/net/ioc3-eth.c

@@ -1387,7 +1387,7 @@ static int ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * MAC header which should not be summed and the TCP/UDP pseudo headers
 	 * manually.
 	 */
-	if (skb->ip_summed == CHECKSUM_HW) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		int proto = ntohs(skb->nh.iph->protocol);
 		unsigned int csoff;
 		struct iphdr *ih = skb->nh.iph;

drivers/net/irda/ali-ircc.c

@@ -249,7 +249,7 @@ static void __exit ali_ircc_cleanup(void)
 
 	IRDA_DEBUG(2, "%s(), ---------------- Start ----------------\n", __FUNCTION__);	
 
-	for (i=0; i < 4; i++) {
+	for (i=0; i < ARRAY_SIZE(dev_self); i++) {
 		if (dev_self[i])
 			ali_ircc_close(dev_self[i]);
 	}
@@ -273,6 +273,12 @@ static int ali_ircc_open(int i, chipio_t *info)
 	int err;
 			
 	IRDA_DEBUG(2, "%s(), ---------------- Start ----------------\n", __FUNCTION__);	
+
+	if (i >= ARRAY_SIZE(dev_self)) {
+		IRDA_ERROR("%s(), maximum number of supported chips reached!\n",
+			   __FUNCTION__);
+		return -ENOMEM;
+	}
 	
 	/* Set FIR FIFO and DMA Threshold */
 	if ((ali_ircc_setup(info)) == -1)

drivers/net/irda/irport.c

@@ -1090,7 +1090,7 @@ static int __init irport_init(void)
 {
  	int i;
 
- 	for (i=0; (io[i] < 2000) && (i < 4); i++) {
+ 	for (i=0; (io[i] < 2000) && (i < ARRAY_SIZE(dev_self)); i++) {
  		if (irport_open(i, io[i], irq[i]) != NULL)
  			return 0;
  	}
@@ -1112,7 +1112,7 @@ static void __exit irport_cleanup(void)
 
         IRDA_DEBUG( 4, "%s()\n", __FUNCTION__);
 
-	for (i=0; i < 4; i++) {
+	for (i=0; i < ARRAY_SIZE(dev_self); i++) {
  		if (dev_self[i])
  			irport_close(dev_self[i]);
  	}

drivers/net/irda/via-ircc.c

@@ -279,7 +279,7 @@ static void via_ircc_clean(void)
 
 	IRDA_DEBUG(3, "%s()\n", __FUNCTION__);
 
-	for (i=0; i < 4; i++) {
+	for (i=0; i < ARRAY_SIZE(dev_self); i++) {
 		if (dev_self[i])
 			via_ircc_close(dev_self[i]);
 	}
@@ -327,6 +327,9 @@ static __devinit int via_ircc_open(int i, chipio_t * info, unsigned int id)
 
 	IRDA_DEBUG(3, "%s()\n", __FUNCTION__);
 
+	if (i >= ARRAY_SIZE(dev_self))
+		return -ENOMEM;
+
 	/* Allocate new instance of the driver */
 	dev = alloc_irdadev(sizeof(struct via_ircc_cb));
 	if (dev == NULL) 

drivers/net/irda/w83977af_ir.c

@@ -117,7 +117,7 @@ static int __init w83977af_init(void)
 
 	IRDA_DEBUG(0, "%s()\n", __FUNCTION__ );
 
-	for (i=0; (io[i] < 2000) && (i < 4); i++) { 
+	for (i=0; (io[i] < 2000) && (i < ARRAY_SIZE(dev_self)); i++) {
 		if (w83977af_open(i, io[i], irq[i], dma[i]) == 0)
 			return 0;
 	}
@@ -136,7 +136,7 @@ static void __exit w83977af_cleanup(void)
 
         IRDA_DEBUG(4, "%s()\n", __FUNCTION__ );
 
-	for (i=0; i < 4; i++) {
+	for (i=0; i < ARRAY_SIZE(dev_self); i++) {
 		if (dev_self[i])
 			w83977af_close(dev_self[i]);
 	}

drivers/net/ixgb/ixgb_main.c

@@ -1232,7 +1232,7 @@ ixgb_tx_csum(struct ixgb_adapter *adapter, struct sk_buff *skb)
 	unsigned int i;
 	uint8_t css, cso;
 
-	if(likely(skb->ip_summed == CHECKSUM_HW)) {
+	if(likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
 		css = skb->h.raw - skb->data;
 		cso = (skb->h.raw + skb->csum) - skb->data;
 

drivers/net/mv643xx_eth.c

@@ -1147,7 +1147,7 @@ static void eth_tx_submit_descs_for_skb(struct mv643xx_private *mp,
 	desc->byte_cnt = length;
 	desc->buf_ptr = dma_map_single(NULL, skb->data, length, DMA_TO_DEVICE);
 
-	if (skb->ip_summed == CHECKSUM_HW) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		BUG_ON(skb->protocol != ETH_P_IP);
 
 		cmd_sts |= ETH_GEN_TCP_UDP_CHECKSUM |

drivers/net/myri10ge/myri10ge.c

@@ -930,7 +930,7 @@ static inline void myri10ge_vlan_ip_csum(struct sk_buff *skb, u16 hw_csum)
 	    (vh->h_vlan_encapsulated_proto == htons(ETH_P_IP) ||
 	     vh->h_vlan_encapsulated_proto == htons(ETH_P_IPV6))) {
 		skb->csum = hw_csum;
-		skb->ip_summed = CHECKSUM_HW;
+		skb->ip_summed = CHECKSUM_COMPLETE;
 	}
 }
 
@@ -973,7 +973,7 @@ myri10ge_rx_done(struct myri10ge_priv *mgp, struct myri10ge_rx_buf *rx,
 		if ((skb->protocol == ntohs(ETH_P_IP)) ||
 		    (skb->protocol == ntohs(ETH_P_IPV6))) {
 			skb->csum = ntohs((u16) csum);
-			skb->ip_summed = CHECKSUM_HW;
+			skb->ip_summed = CHECKSUM_COMPLETE;
 		} else
 			myri10ge_vlan_ip_csum(skb, ntohs((u16) csum));
 	}
@@ -1897,13 +1897,13 @@ again:
 	pseudo_hdr_offset = 0;
 	odd_flag = 0;
 	flags = (MXGEFW_FLAGS_NO_TSO | MXGEFW_FLAGS_FIRST);
-	if (likely(skb->ip_summed == CHECKSUM_HW)) {
+	if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
 		cksum_offset = (skb->h.raw - skb->data);
 		pseudo_hdr_offset = (skb->h.raw + skb->csum) - skb->data;
 		/* If the headers are excessively large, then we must
 		 * fall back to a software checksum */
 		if (unlikely(cksum_offset > 255 || pseudo_hdr_offset > 127)) {
-			if (skb_checksum_help(skb, 0))
+			if (skb_checksum_help(skb))
 				goto drop;
 			cksum_offset = 0;
 			pseudo_hdr_offset = 0;

drivers/net/ns83820.c

@@ -1153,7 +1153,7 @@ again:
 	if (!nr_frags)
 		frag = NULL;
 	extsts = 0;
-	if (skb->ip_summed == CHECKSUM_HW) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		extsts |= EXTSTS_IPPKT;
 		if (IPPROTO_TCP == skb->nh.iph->protocol)
 			extsts |= EXTSTS_TCPPKT;

drivers/net/r8169.c

@@ -2169,7 +2169,7 @@ static inline u32 rtl8169_tso_csum(struct sk_buff *skb, struct net_device *dev)
 		if (mss)
 			return LargeSend | ((mss & MSSMask) << MSSShift);
 	}
-	if (skb->ip_summed == CHECKSUM_HW) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		const struct iphdr *ip = skb->nh.iph;
 
 		if (ip->protocol == IPPROTO_TCP)

drivers/net/s2io.c

@@ -3893,7 +3893,7 @@ static int s2io_xmit(struct sk_buff *skb, struct net_device *dev)
 		txdp->Control_1 |= TXD_TCP_LSO_MSS(s2io_tcp_mss(skb));
 	}
 #endif
-	if (skb->ip_summed == CHECKSUM_HW) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		txdp->Control_2 |=
 		    (TXD_TX_CKO_IPV4_EN | TXD_TX_CKO_TCP_EN |
 		     TXD_TX_CKO_UDP_EN);

drivers/net/sk98lin/skge.c

@@ -1559,7 +1559,7 @@ struct sk_buff	*pMessage)	/* pointer to send-message              */
 	pTxd->VDataHigh = (SK_U32) (PhysAddr >> 32);
 	pTxd->pMBuf     = pMessage;
 
-	if (pMessage->ip_summed == CHECKSUM_HW) {
+	if (pMessage->ip_summed == CHECKSUM_PARTIAL) {
 		u16 hdrlen = pMessage->h.raw - pMessage->data;
 		u16 offset = hdrlen + pMessage->csum;
 
@@ -1678,7 +1678,7 @@ struct sk_buff	*pMessage)	/* pointer to send-message              */
 	/* 
 	** Does the HW need to evaluate checksum for TCP or UDP packets? 
 	*/
-	if (pMessage->ip_summed == CHECKSUM_HW) {
+	if (pMessage->ip_summed == CHECKSUM_PARTIAL) {
 		u16 hdrlen = pMessage->h.raw - pMessage->data;
 		u16 offset = hdrlen + pMessage->csum;
 
@@ -2158,7 +2158,7 @@ rx_start:
 
 #ifdef USE_SK_RX_CHECKSUM
 		pMsg->csum = pRxd->TcpSums & 0xffff;
-		pMsg->ip_summed = CHECKSUM_HW;
+		pMsg->ip_summed = CHECKSUM_COMPLETE;
 #else
 		pMsg->ip_summed = CHECKSUM_NONE;
 #endif

drivers/net/skge.c

@@ -2338,7 +2338,7 @@ static int skge_xmit_frame(struct sk_buff *skb, struct net_device *dev)
 	td->dma_lo = map;
 	td->dma_hi = map >> 32;
 
-	if (skb->ip_summed == CHECKSUM_HW) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		int offset = skb->h.raw - skb->data;
 
 		/* This seems backwards, but it is what the sk98lin
@@ -2642,7 +2642,7 @@ static inline struct sk_buff *skge_rx_get(struct skge_port *skge,
 	skb->dev = skge->netdev;
 	if (skge->rx_csum) {
 		skb->csum = csum;
-		skb->ip_summed = CHECKSUM_HW;
+		skb->ip_summed = CHECKSUM_COMPLETE;
 	}
 
 	skb->protocol = eth_type_trans(skb, skge->netdev);

drivers/net/sky2.c

@@ -1163,7 +1163,7 @@ static unsigned tx_le_req(const struct sk_buff *skb)
 	if (skb_is_gso(skb))
 		++count;
 
-	if (skb->ip_summed == CHECKSUM_HW)
+	if (skb->ip_summed == CHECKSUM_PARTIAL)
 		++count;
 
 	return count;
@@ -1272,7 +1272,7 @@ static int sky2_xmit_frame(struct sk_buff *skb, struct net_device *dev)
 #endif
 
 	/* Handle TCP checksum offload */
-	if (skb->ip_summed == CHECKSUM_HW) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		u16 hdr = skb->h.raw - skb->data;
 		u16 offset = hdr + skb->csum;
 
@@ -2000,7 +2000,7 @@ static int sky2_status_intr(struct sky2_hw *hw, int to_do)
 #endif
 		case OP_RXCHKS:
 			skb = sky2->rx_ring[sky2->rx_next].skb;
-			skb->ip_summed = CHECKSUM_HW;
+			skb->ip_summed = CHECKSUM_COMPLETE;
 			skb->csum = le16_to_cpu(status);
 			break;
 

drivers/net/starfire.c

@@ -1230,7 +1230,7 @@ static int start_tx(struct sk_buff *skb, struct net_device *dev)
 	}
 
 #if defined(ZEROCOPY) && defined(HAS_BROKEN_FIRMWARE)
-	if (skb->ip_summed == CHECKSUM_HW) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		if (skb_padto(skb, (skb->len + PADDING_MASK) & ~PADDING_MASK))
 			return NETDEV_TX_OK;
 	}
@@ -1252,7 +1252,7 @@ static int start_tx(struct sk_buff *skb, struct net_device *dev)
 				status |= TxDescIntr;
 				np->reap_tx = 0;
 			}
-			if (skb->ip_summed == CHECKSUM_HW) {
+			if (skb->ip_summed == CHECKSUM_PARTIAL) {
 				status |= TxCalTCP;
 				np->stats.tx_compressed++;
 			}
@@ -1499,7 +1499,7 @@ static int __netdev_rx(struct net_device *dev, int *quota)
 		 * Until then, the printk stays. :-) -Ion
 		 */
 		else if (le16_to_cpu(desc->status2) & 0x0040) {
-			skb->ip_summed = CHECKSUM_HW;
+			skb->ip_summed = CHECKSUM_COMPLETE;
 			skb->csum = le16_to_cpu(desc->csum);
 			printk(KERN_DEBUG "%s: checksum_hw, status2 = %#x\n", dev->name, le16_to_cpu(desc->status2));
 		}

drivers/net/sungem.c

@@ -855,7 +855,7 @@ static int gem_rx(struct gem *gp, int work_to_do)
 		}
 
 		skb->csum = ntohs((status & RXDCTRL_TCPCSUM) ^ 0xffff);
-		skb->ip_summed = CHECKSUM_HW;
+		skb->ip_summed = CHECKSUM_COMPLETE;
 		skb->protocol = eth_type_trans(skb, gp->dev);
 
 		netif_receive_skb(skb);
@@ -1026,7 +1026,7 @@ static int gem_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	unsigned long flags;
 
 	ctrl = 0;
-	if (skb->ip_summed == CHECKSUM_HW) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		u64 csum_start_off, csum_stuff_off;
 
 		csum_start_off = (u64) (skb->h.raw - skb->data);

drivers/net/sunhme.c

@@ -1207,7 +1207,7 @@ static void happy_meal_transceiver_check(struct happy_meal *hp, void __iomem *tr
  * flags, thus:
  *
  * 	skb->csum = rxd->rx_flags & 0xffff;
- * 	skb->ip_summed = CHECKSUM_HW;
+ * 	skb->ip_summed = CHECKSUM_COMPLETE;
  *
  * before sending off the skb to the protocols, and we are good as gold.
  */
@@ -2074,7 +2074,7 @@ static void happy_meal_rx(struct happy_meal *hp, struct net_device *dev)
 
 		/* This card is _fucking_ hot... */
 		skb->csum = ntohs(csum ^ 0xffff);
-		skb->ip_summed = CHECKSUM_HW;
+		skb->ip_summed = CHECKSUM_COMPLETE;
 
 		RXD(("len=%d csum=%4x]", len, csum));
 		skb->protocol = eth_type_trans(skb, dev);
@@ -2268,7 +2268,7 @@ static int happy_meal_start_xmit(struct sk_buff *skb, struct net_device *dev)
  	u32 tx_flags;
 
 	tx_flags = TXFLAG_OWN;
-	if (skb->ip_summed == CHECKSUM_HW) {
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		u32 csum_start_off, csum_stuff_off;
 
 		csum_start_off = (u32) (skb->h.raw - skb->data);

drivers/net/tg3.c

@@ -149,122 +149,67 @@ module_param(tg3_debug, int, 0);
 MODULE_PARM_DESC(tg3_debug, "Tigon3 bitmapped debugging message enable value");
 
 static struct pci_device_id tg3_pci_tbl[] = {
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5700,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5701,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5702,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5703,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5704,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5702FE,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5705,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5705_2,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5705M,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5705M_2,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5702X,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5703X,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5704S,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5702A3,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5703A3,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5782,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5788,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5789,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5901,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5901_2,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5704S_2,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5705F,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5720,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5721,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5750,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5751,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5750M,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5751M,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5751F,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5752,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5752M,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5753,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5753M,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5753F,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5754,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5754M,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5755,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5755M,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5786,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5787,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5787M,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5714,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5714S,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5715,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5715S,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5780,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5780S,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5781,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_SYSKONNECT, PCI_DEVICE_ID_SYSKONNECT_9DXX,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_SYSKONNECT, PCI_DEVICE_ID_SYSKONNECT_9MXX,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_ALTIMA, PCI_DEVICE_ID_ALTIMA_AC1000,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_ALTIMA, PCI_DEVICE_ID_ALTIMA_AC1001,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_ALTIMA, PCI_DEVICE_ID_ALTIMA_AC1003,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_ALTIMA, PCI_DEVICE_ID_ALTIMA_AC9100,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ PCI_VENDOR_ID_APPLE, PCI_DEVICE_ID_APPLE_TIGON3,
-	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
-	{ 0, }
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5700)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5701)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5702)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5703)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5704)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5702FE)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5705)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5705_2)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5705M)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5705M_2)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5702X)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5703X)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5704S)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5702A3)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5703A3)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5782)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5788)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5789)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5901)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5901_2)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5704S_2)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5705F)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5720)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5721)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5750)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5751)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5750M)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5751M)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5751F)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5752)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5752M)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5753)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5753M)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5753F)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5754)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5754M)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5755)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5755M)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5786)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5787)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5787M)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5714)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5714S)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5715)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5715S)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5780)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5780S)},
+	{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_TIGON3_5781)},
+	{PCI_DEVICE(PCI_VENDOR_ID_SYSKONNECT, PCI_DEVICE_ID_SYSKONNECT_9DXX)},
+	{PCI_DEVICE(PCI_VENDOR_ID_SYSKONNECT, PCI_DEVICE_ID_SYSKONNECT_9MXX)},
+	{PCI_DEVICE(PCI_VENDOR_ID_ALTIMA, PCI_DEVICE_ID_ALTIMA_AC1000)},
+	{PCI_DEVICE(PCI_VENDOR_ID_ALTIMA, PCI_DEVICE_ID_ALTIMA_AC1001)},
+	{PCI_DEVICE(PCI_VENDOR_ID_ALTIMA, PCI_DEVICE_ID_ALTIMA_AC1003)},
+	{PCI_DEVICE(PCI_VENDOR_ID_ALTIMA, PCI_DEVICE_ID_ALTIMA_AC9100)},
+	{PCI_DEVICE(PCI_VENDOR_ID_APPLE, PCI_DEVICE_ID_APPLE_TIGON3)},
+	{}
 };
 
 MODULE_DEVICE_TABLE(pci, tg3_pci_tbl);
 
-static struct {
+static const struct {
 	const char string[ETH_GSTRING_LEN];
 } ethtool_stats_keys[TG3_NUM_STATS] = {
 	{ "rx_octets" },
@@ -345,7 +290,7 @@ static struct {
 	{ "nic_tx_threshold_hit" }
 };
 
-static struct {
+static const struct {
 	const char string[ETH_GSTRING_LEN];
 } ethtool_test_keys[TG3_NUM_TEST] = {
 	{ "nvram test     (online) " },
@@ -3851,11 +3796,11 @@ static int tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		skb->h.th->check = 0;
 
 	}
-	else if (skb->ip_summed == CHECKSUM_HW)
+	else if (skb->ip_summed == CHECKSUM_PARTIAL)
 		base_flags |= TXD_FLAG_TCPUDP_CSUM;
 #else
 	mss = 0;
-	if (skb->ip_summed == CHECKSUM_HW)
+	if (skb->ip_summed == CHECKSUM_PARTIAL)
 		base_flags |= TXD_FLAG_TCPUDP_CSUM;
 #endif
 #if TG3_VLAN_TAG_USED
@@ -3981,7 +3926,7 @@ static int tg3_start_xmit_dma_bug(struct sk_buff *skb, struct net_device *dev)
 
 	entry = tp->tx_prod;
 	base_flags = 0;
-	if (skb->ip_summed == CHECKSUM_HW)
+	if (skb->ip_summed == CHECKSUM_PARTIAL)
 		base_flags |= TXD_FLAG_TCPUDP_CSUM;
 #if TG3_TSO_SUPPORT != 0
 	mss = 0;
@@ -4969,7 +4914,7 @@ static int tg3_halt(struct tg3 *tp, int kind, int silent)
 #define TG3_FW_BSS_ADDR		0x08000a70
 #define TG3_FW_BSS_LEN		0x10
 
-static u32 tg3FwText[(TG3_FW_TEXT_LEN / sizeof(u32)) + 1] = {
+static const u32 tg3FwText[(TG3_FW_TEXT_LEN / sizeof(u32)) + 1] = {
 	0x00000000, 0x10000003, 0x00000000, 0x0000000d, 0x0000000d, 0x3c1d0800,
 	0x37bd3ffc, 0x03a0f021, 0x3c100800, 0x26100000, 0x0e000018, 0x00000000,
 	0x0000000d, 0x3c1d0800, 0x37bd3ffc, 0x03a0f021, 0x3c100800, 0x26100034,
@@ -5063,7 +5008,7 @@ static u32 tg3FwText[(TG3_FW_TEXT_LEN / sizeof(u32)) + 1] = {
 	0x27bd0008, 0x03e00008, 0x00000000, 0x00000000, 0x00000000
 };
 
-static u32 tg3FwRodata[(TG3_FW_RODATA_LEN / sizeof(u32)) + 1] = {
+static const u32 tg3FwRodata[(TG3_FW_RODATA_LEN / sizeof(u32)) + 1] = {
 	0x35373031, 0x726c7341, 0x00000000, 0x00000000, 0x53774576, 0x656e7430,
 	0x00000000, 0x726c7045, 0x76656e74, 0x31000000, 0x556e6b6e, 0x45766e74,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x66617461, 0x6c457272,
@@ -5128,13 +5073,13 @@ static int tg3_halt_cpu(struct tg3 *tp, u32 offset)
 struct fw_info {
 	unsigned int text_base;
 	unsigned int text_len;
-	u32 *text_data;
+	const u32 *text_data;
 	unsigned int rodata_base;
 	unsigned int rodata_len;
-	u32 *rodata_data;
+	const u32 *rodata_data;
 	unsigned int data_base;
 	unsigned int data_len;
-	u32 *data_data;
+	const u32 *data_data;
 };
 
 /* tp->lock is held. */
@@ -5266,7 +5211,7 @@ static int tg3_load_5701_a0_firmware_fix(struct tg3 *tp)
 #define TG3_TSO_FW_BSS_ADDR		0x08001b80
 #define TG3_TSO_FW_BSS_LEN		0x894
 
-static u32 tg3TsoFwText[(TG3_TSO_FW_TEXT_LEN / 4) + 1] = {
+static const u32 tg3TsoFwText[(TG3_TSO_FW_TEXT_LEN / 4) + 1] = {
 	0x0e000003, 0x00000000, 0x08001b24, 0x00000000, 0x10000003, 0x00000000,
 	0x0000000d, 0x0000000d, 0x3c1d0800, 0x37bd4000, 0x03a0f021, 0x3c100800,
 	0x26100000, 0x0e000010, 0x00000000, 0x0000000d, 0x27bdffe0, 0x3c04fefe,
@@ -5553,7 +5498,7 @@ static u32 tg3TsoFwText[(TG3_TSO_FW_TEXT_LEN / 4) + 1] = {
 	0xac470014, 0xac4a0018, 0x03e00008, 0xac4b001c, 0x00000000, 0x00000000,
 };
 
-static u32 tg3TsoFwRodata[] = {
+static const u32 tg3TsoFwRodata[] = {
 	0x4d61696e, 0x43707542, 0x00000000, 0x4d61696e, 0x43707541, 0x00000000,
 	0x00000000, 0x00000000, 0x73746b6f, 0x66666c64, 0x496e0000, 0x73746b6f,
 	0x66662a2a, 0x00000000, 0x53774576, 0x656e7430, 0x00000000, 0x00000000,
@@ -5561,7 +5506,7 @@ static u32 tg3TsoFwRodata[] = {
 	0x00000000,
 };
 
-static u32 tg3TsoFwData[] = {
+static const u32 tg3TsoFwData[] = {
 	0x00000000, 0x73746b6f, 0x66666c64, 0x5f76312e, 0x362e3000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
 	0x00000000,
@@ -5583,7 +5528,7 @@ static u32 tg3TsoFwData[] = {
 #define TG3_TSO5_FW_BSS_ADDR		0x00010f50
 #define TG3_TSO5_FW_BSS_LEN		0x88
 
-static u32 tg3Tso5FwText[(TG3_TSO5_FW_TEXT_LEN / 4) + 1] = {
+static const u32 tg3Tso5FwText[(TG3_TSO5_FW_TEXT_LEN / 4) + 1] = {
 	0x0c004003, 0x00000000, 0x00010f04, 0x00000000, 0x10000003, 0x00000000,
 	0x0000000d, 0x0000000d, 0x3c1d0001, 0x37bde000, 0x03a0f021, 0x3c100001,
 	0x26100000, 0x0c004010, 0x00000000, 0x0000000d, 0x27bdffe0, 0x3c04fefe,
@@ -5742,14 +5687,14 @@ static u32 tg3Tso5FwText[(TG3_TSO5_FW_TEXT_LEN / 4) + 1] = {
 	0x00000000, 0x00000000, 0x00000000,
 };
 
-static u32 tg3Tso5FwRodata[(TG3_TSO5_FW_RODATA_LEN / 4) + 1] = {
+static const u32 tg3Tso5FwRodata[(TG3_TSO5_FW_RODATA_LEN / 4) + 1] = {
 	0x4d61696e, 0x43707542, 0x00000000, 0x4d61696e, 0x43707541, 0x00000000,
 	0x00000000, 0x00000000, 0x73746b6f, 0x66666c64, 0x00000000, 0x00000000,
 	0x73746b6f, 0x66666c64, 0x00000000, 0x00000000, 0x66617461, 0x6c457272,
 	0x00000000, 0x00000000, 0x00000000,
 };
 
-static u32 tg3Tso5FwData[(TG3_TSO5_FW_DATA_LEN / 4) + 1] = {
+static const u32 tg3Tso5FwData[(TG3_TSO5_FW_DATA_LEN / 4) + 1] = {
 	0x00000000, 0x73746b6f, 0x66666c64, 0x5f76312e, 0x322e3000, 0x00000000,
 	0x00000000, 0x00000000, 0x00000000,
 };

drivers/net/typhoon.c

@@ -830,7 +830,7 @@ typhoon_start_tx(struct sk_buff *skb, struct net_device *dev)
 	first_txd->addrHi = (u64)((unsigned long) skb) >> 32;
 	first_txd->processFlags = 0;
 
-	if(skb->ip_summed == CHECKSUM_HW) {
+	if(skb->ip_summed == CHECKSUM_PARTIAL) {
 		/* The 3XP will figure out if this is UDP/TCP */
 		first_txd->processFlags |= TYPHOON_TX_PF_TCP_CHKSUM;
 		first_txd->processFlags |= TYPHOON_TX_PF_UDP_CHKSUM;

drivers/net/via-rhine.c

@@ -1230,7 +1230,7 @@ static int rhine_start_tx(struct sk_buff *skb, struct net_device *dev)
 	rp->tx_skbuff[entry] = skb;
 
 	if ((rp->quirks & rqRhineI) &&
-	    (((unsigned long)skb->data & 3) || skb_shinfo(skb)->nr_frags != 0 || skb->ip_summed == CHECKSUM_HW)) {
+	    (((unsigned long)skb->data & 3) || skb_shinfo(skb)->nr_frags != 0 || skb->ip_summed == CHECKSUM_PARTIAL)) {
 		/* Must use alignment buffer. */
 		if (skb->len > PKT_BUF_SZ) {
 			/* packet too long, drop it */

drivers/net/via-velocity.c

@@ -2002,7 +2002,7 @@ static int velocity_xmit(struct sk_buff *skb, struct net_device *dev)
 	 *	Handle hardware checksum
 	 */
 	if ((vptr->flags & VELOCITY_FLAGS_TX_CSUM)
-				 && (skb->ip_summed == CHECKSUM_HW)) {
+				 && (skb->ip_summed == CHECKSUM_PARTIAL)) {
 		struct iphdr *ip = skb->nh.iph;
 		if (ip->protocol == IPPROTO_TCP)
 			td_ptr->tdesc1.TCR |= TCR0_TCPCK;

drivers/video/riva/fbdev.c

@@ -1826,8 +1826,8 @@ static int __devinit riva_get_EDID_OF(struct fb_info *info, struct pci_dev *pd)
 {
 	struct riva_par *par = info->par;
 	struct device_node *dp;
-	unsigned char *pedid = NULL;
-	unsigned char *disptype = NULL;
+	const unsigned char *pedid = NULL;
+	const unsigned char *disptype = NULL;
 	static char *propnames[] = {
 		"DFP,EDID", "LCD,EDID", "EDID", "EDID1", "EDID,B", "EDID,A", NULL };
 	int i;

fs/Kconfig

@@ -1471,8 +1471,8 @@ config NFS_V4
 	  If unsure, say N.
 
 config NFS_DIRECTIO
-	bool "Allow direct I/O on NFS files (EXPERIMENTAL)"
-	depends on NFS_FS && EXPERIMENTAL
+	bool "Allow direct I/O on NFS files"
+	depends on NFS_FS
 	help
 	  This option enables applications to perform uncached I/O on files
 	  in NFS file systems using the O_DIRECT open() flag.  When O_DIRECT

fs/dcache.c

@@ -828,17 +828,19 @@ void d_instantiate(struct dentry *entry, struct inode * inode)
  * (or otherwise set) by the caller to indicate that it is now
  * in use by the dcache.
  */
-struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
+static struct dentry *__d_instantiate_unique(struct dentry *entry,
+					     struct inode *inode)
 {
 	struct dentry *alias;
 	int len = entry->d_name.len;
 	const char *name = entry->d_name.name;
 	unsigned int hash = entry->d_name.hash;
 
-	BUG_ON(!list_empty(&entry->d_alias));
-	spin_lock(&dcache_lock);
-	if (!inode)
-		goto do_negative;
+	if (!inode) {
+		entry->d_inode = NULL;
+		return NULL;
+	}
+
 	list_for_each_entry(alias, &inode->i_dentry, d_alias) {
 		struct qstr *qstr = &alias->d_name;
 
@@ -851,19 +853,35 @@ struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
 		if (memcmp(qstr->name, name, len))
 			continue;
 		dget_locked(alias);
-		spin_unlock(&dcache_lock);
-		BUG_ON(!d_unhashed(alias));
-		iput(inode);
 		return alias;
 	}
+
 	list_add(&entry->d_alias, &inode->i_dentry);
-do_negative:
 	entry->d_inode = inode;
 	fsnotify_d_instantiate(entry, inode);
-	spin_unlock(&dcache_lock);
-	security_d_instantiate(entry, inode);
 	return NULL;
 }
+
+struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
+{
+	struct dentry *result;
+
+	BUG_ON(!list_empty(&entry->d_alias));
+
+	spin_lock(&dcache_lock);
+	result = __d_instantiate_unique(entry, inode);
+	spin_unlock(&dcache_lock);
+
+	if (!result) {
+		security_d_instantiate(entry, inode);
+		return NULL;
+	}
+
+	BUG_ON(!d_unhashed(result));
+	iput(inode);
+	return result;
+}
+
 EXPORT_SYMBOL(d_instantiate_unique);
 
 /**
@@ -1235,6 +1253,11 @@ static void __d_rehash(struct dentry * entry, struct hlist_head *list)
  	hlist_add_head_rcu(&entry->d_hash, list);
 }
 
+static void _d_rehash(struct dentry * entry)
+{
+	__d_rehash(entry, d_hash(entry->d_parent, entry->d_name.hash));
+}
+
 /**
  * d_rehash	- add an entry back to the hash
  * @entry: dentry to add to the hash
@@ -1244,11 +1267,9 @@ static void __d_rehash(struct dentry * entry, struct hlist_head *list)
  
 void d_rehash(struct dentry * entry)
 {
-	struct hlist_head *list = d_hash(entry->d_parent, entry->d_name.hash);
-
 	spin_lock(&dcache_lock);
 	spin_lock(&entry->d_lock);
-	__d_rehash(entry, list);
+	_d_rehash(entry);
 	spin_unlock(&entry->d_lock);
 	spin_unlock(&dcache_lock);
 }
@@ -1386,6 +1407,120 @@ already_unhashed:
 	spin_unlock(&dcache_lock);
 }
 
+/*
+ * Prepare an anonymous dentry for life in the superblock's dentry tree as a
+ * named dentry in place of the dentry to be replaced.
+ */
+static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon)
+{
+	struct dentry *dparent, *aparent;
+
+	switch_names(dentry, anon);
+	do_switch(dentry->d_name.len, anon->d_name.len);
+	do_switch(dentry->d_name.hash, anon->d_name.hash);
+
+	dparent = dentry->d_parent;
+	aparent = anon->d_parent;
+
+	dentry->d_parent = (aparent == anon) ? dentry : aparent;
+	list_del(&dentry->d_u.d_child);
+	if (!IS_ROOT(dentry))
+		list_add(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
+	else
+		INIT_LIST_HEAD(&dentry->d_u.d_child);
+
+	anon->d_parent = (dparent == dentry) ? anon : dparent;
+	list_del(&anon->d_u.d_child);
+	if (!IS_ROOT(anon))
+		list_add(&anon->d_u.d_child, &anon->d_parent->d_subdirs);
+	else
+		INIT_LIST_HEAD(&anon->d_u.d_child);
+
+	anon->d_flags &= ~DCACHE_DISCONNECTED;
+}
+
+/**
+ * d_materialise_unique - introduce an inode into the tree
+ * @dentry: candidate dentry
+ * @inode: inode to bind to the dentry, to which aliases may be attached
+ *
+ * Introduces an dentry into the tree, substituting an extant disconnected
+ * root directory alias in its place if there is one
+ */
+struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
+{
+	struct dentry *alias, *actual;
+
+	BUG_ON(!d_unhashed(dentry));
+
+	spin_lock(&dcache_lock);
+
+	if (!inode) {
+		actual = dentry;
+		dentry->d_inode = NULL;
+		goto found_lock;
+	}
+
+	/* See if a disconnected directory already exists as an anonymous root
+	 * that we should splice into the tree instead */
+	if (S_ISDIR(inode->i_mode) && (alias = __d_find_alias(inode, 1))) {
+		spin_lock(&alias->d_lock);
+
+		/* Is this a mountpoint that we could splice into our tree? */
+		if (IS_ROOT(alias))
+			goto connect_mountpoint;
+
+		if (alias->d_name.len == dentry->d_name.len &&
+		    alias->d_parent == dentry->d_parent &&
+		    memcmp(alias->d_name.name,
+			   dentry->d_name.name,
+			   dentry->d_name.len) == 0)
+			goto replace_with_alias;
+
+		spin_unlock(&alias->d_lock);
+
+		/* Doh! Seem to be aliasing directories for some reason... */
+		dput(alias);
+	}
+
+	/* Add a unique reference */
+	actual = __d_instantiate_unique(dentry, inode);
+	if (!actual)
+		actual = dentry;
+	else if (unlikely(!d_unhashed(actual)))
+		goto shouldnt_be_hashed;
+
+found_lock:
+	spin_lock(&actual->d_lock);
+found:
+	_d_rehash(actual);
+	spin_unlock(&actual->d_lock);
+	spin_unlock(&dcache_lock);
+
+	if (actual == dentry) {
+		security_d_instantiate(dentry, inode);
+		return NULL;
+	}
+
+	iput(inode);
+	return actual;
+
+	/* Convert the anonymous/root alias into an ordinary dentry */
+connect_mountpoint:
+	__d_materialise_dentry(dentry, alias);
+
+	/* Replace the candidate dentry with the alias in the tree */
+replace_with_alias:
+	__d_drop(alias);
+	actual = alias;
+	goto found;
+
+shouldnt_be_hashed:
+	spin_unlock(&dcache_lock);
+	BUG();
+	goto shouldnt_be_hashed;
+}
+
 /**
  * d_path - return the path of a dentry
  * @dentry: dentry to report
@@ -1784,6 +1919,7 @@ EXPORT_SYMBOL(d_instantiate);
 EXPORT_SYMBOL(d_invalidate);
 EXPORT_SYMBOL(d_lookup);
 EXPORT_SYMBOL(d_move);
+EXPORT_SYMBOL_GPL(d_materialise_unique);
 EXPORT_SYMBOL(d_path);
 EXPORT_SYMBOL(d_prune_aliases);
 EXPORT_SYMBOL(d_rehash);

fs/lockd/clntproc.c

@@ -151,11 +151,13 @@ static void nlmclnt_release_lockargs(struct nlm_rqst *req)
 int
 nlmclnt_proc(struct inode *inode, int cmd, struct file_lock *fl)
 {
+	struct rpc_clnt		*client = NFS_CLIENT(inode);
+	struct sockaddr_in	addr;
 	struct nlm_host		*host;
 	struct nlm_rqst		*call;
 	sigset_t		oldset;
 	unsigned long		flags;
-	int			status, proto, vers;
+	int			status, vers;
 
 	vers = (NFS_PROTO(inode)->version == 3) ? 4 : 1;
 	if (NFS_PROTO(inode)->version > 3) {
@@ -163,10 +165,8 @@ nlmclnt_proc(struct inode *inode, int cmd, struct file_lock *fl)
 		return -ENOLCK;
 	}
 
-	/* Retrieve transport protocol from NFS client */
-	proto = NFS_CLIENT(inode)->cl_xprt->prot;
-
-	host = nlmclnt_lookup_host(NFS_ADDR(inode), proto, vers);
+	rpc_peeraddr(client, (struct sockaddr *) &addr, sizeof(addr));
+	host = nlmclnt_lookup_host(&addr, client->cl_xprt->prot, vers);
 	if (host == NULL)
 		return -ENOLCK;
 

fs/lockd/host.c

@@ -26,7 +26,6 @@
 #define NLM_HOST_REBIND		(60 * HZ)
 #define NLM_HOST_EXPIRE		((nrhosts > NLM_HOST_MAX)? 300 * HZ : 120 * HZ)
 #define NLM_HOST_COLLECT	((nrhosts > NLM_HOST_MAX)? 120 * HZ :  60 * HZ)
-#define NLM_HOST_ADDR(sv)	(&(sv)->s_nlmclnt->cl_xprt->addr)
 
 static struct nlm_host *	nlm_hosts[NLM_HOST_NRHASH];
 static unsigned long		next_gc;
@@ -167,7 +166,6 @@ struct rpc_clnt *
 nlm_bind_host(struct nlm_host *host)
 {
 	struct rpc_clnt	*clnt;
-	struct rpc_xprt	*xprt;
 
 	dprintk("lockd: nlm_bind_host(%08x)\n",
 			(unsigned)ntohl(host->h_addr.sin_addr.s_addr));
@@ -179,7 +177,6 @@ nlm_bind_host(struct nlm_host *host)
 	 * RPC rebind is required
 	 */
 	if ((clnt = host->h_rpcclnt) != NULL) {
-		xprt = clnt->cl_xprt;
 		if (time_after_eq(jiffies, host->h_nextrebind)) {
 			rpc_force_rebind(clnt);
 			host->h_nextrebind = jiffies + NLM_HOST_REBIND;
@@ -187,31 +184,37 @@ nlm_bind_host(struct nlm_host *host)
 					host->h_nextrebind - jiffies);
 		}
 	} else {
-		xprt = xprt_create_proto(host->h_proto, &host->h_addr, NULL);
-		if (IS_ERR(xprt))
-			goto forgetit;
-
-		xprt_set_timeout(&xprt->timeout, 5, nlmsvc_timeout);
-		xprt->resvport = 1;	/* NLM requires a reserved port */
-
-		/* Existing NLM servers accept AUTH_UNIX only */
-		clnt = rpc_new_client(xprt, host->h_name, &nlm_program,
-					host->h_version, RPC_AUTH_UNIX);
-		if (IS_ERR(clnt))
-			goto forgetit;
-		clnt->cl_autobind = 1;	/* turn on pmap queries */
-		clnt->cl_softrtry = 1; /* All queries are soft */
-
-		host->h_rpcclnt = clnt;
+		unsigned long increment = nlmsvc_timeout * HZ;
+		struct rpc_timeout timeparms = {
+			.to_initval	= increment,
+			.to_increment	= increment,
+			.to_maxval	= increment * 6UL,
+			.to_retries	= 5U,
+		};
+		struct rpc_create_args args = {
+			.protocol	= host->h_proto,
+			.address	= (struct sockaddr *)&host->h_addr,
+			.addrsize	= sizeof(host->h_addr),
+			.timeout	= &timeparms,
+			.servername	= host->h_name,
+			.program	= &nlm_program,
+			.version	= host->h_version,
+			.authflavor	= RPC_AUTH_UNIX,
+			.flags		= (RPC_CLNT_CREATE_HARDRTRY |
+					   RPC_CLNT_CREATE_AUTOBIND),
+		};
+
+		clnt = rpc_create(&args);
+		if (!IS_ERR(clnt))
+			host->h_rpcclnt = clnt;
+		else {
+			printk("lockd: couldn't create RPC handle for %s\n", host->h_name);
+			clnt = NULL;
+		}
 	}
 
 	mutex_unlock(&host->h_mutex);
 	return clnt;
-
-forgetit:
-	printk("lockd: couldn't create RPC handle for %s\n", host->h_name);
-	mutex_unlock(&host->h_mutex);
-	return NULL;
 }
 
 /*

fs/lockd/mon.c

@@ -109,30 +109,23 @@ nsm_unmonitor(struct nlm_host *host)
 static struct rpc_clnt *
 nsm_create(void)
 {
-	struct rpc_xprt		*xprt;
-	struct rpc_clnt		*clnt;
-	struct sockaddr_in	sin;
-
-	sin.sin_family = AF_INET;
-	sin.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
-	sin.sin_port = 0;
-
-	xprt = xprt_create_proto(IPPROTO_UDP, &sin, NULL);
-	if (IS_ERR(xprt))
-		return (struct rpc_clnt *)xprt;
-	xprt->resvport = 1;	/* NSM requires a reserved port */
-
-	clnt = rpc_create_client(xprt, "localhost",
-				&nsm_program, SM_VERSION,
-				RPC_AUTH_NULL);
-	if (IS_ERR(clnt))
-		goto out_err;
-	clnt->cl_softrtry = 1;
-	clnt->cl_oneshot  = 1;
-	return clnt;
-
-out_err:
-	return clnt;
+	struct sockaddr_in	sin = {
+		.sin_family	= AF_INET,
+		.sin_addr.s_addr = htonl(INADDR_LOOPBACK),
+		.sin_port	= 0,
+	};
+	struct rpc_create_args args = {
+		.protocol	= IPPROTO_UDP,
+		.address	= (struct sockaddr *)&sin,
+		.addrsize	= sizeof(sin),
+		.servername	= "localhost",
+		.program	= &nsm_program,
+		.version	= SM_VERSION,
+		.authflavor	= RPC_AUTH_NULL,
+		.flags		= (RPC_CLNT_CREATE_ONESHOT),
+	};
+
+	return rpc_create(&args);
 }
 
 /*

fs/nfs/Makefile

@@ -4,9 +4,9 @@
 
 obj-$(CONFIG_NFS_FS) += nfs.o
 
-nfs-y 			:= dir.o file.o inode.o super.o nfs2xdr.o pagelist.o \
-			   proc.o read.o symlink.o unlink.o write.o \
-			   namespace.o
+nfs-y 			:= client.o dir.o file.o getroot.o inode.o super.o nfs2xdr.o \
+			   pagelist.o proc.o read.o symlink.o unlink.o \
+			   write.o namespace.o
 nfs-$(CONFIG_ROOT_NFS)	+= nfsroot.o mount_clnt.o      
 nfs-$(CONFIG_NFS_V3)	+= nfs3proc.o nfs3xdr.o
 nfs-$(CONFIG_NFS_V3_ACL)	+= nfs3acl.o

fs/nfs/callback.c

@@ -19,6 +19,7 @@
 
 #include "nfs4_fs.h"
 #include "callback.h"
+#include "internal.h"
 
 #define NFSDBG_FACILITY NFSDBG_CALLBACK
 
@@ -36,6 +37,21 @@ static struct svc_program nfs4_callback_program;
 
 unsigned int nfs_callback_set_tcpport;
 unsigned short nfs_callback_tcpport;
+static const int nfs_set_port_min = 0;
+static const int nfs_set_port_max = 65535;
+
+static int param_set_port(const char *val, struct kernel_param *kp)
+{
+	char *endp;
+	int num = simple_strtol(val, &endp, 0);
+	if (endp == val || *endp || num < nfs_set_port_min || num > nfs_set_port_max)
+		return -EINVAL;
+	*((int *)kp->arg) = num;
+	return 0;
+}
+
+module_param_call(callback_tcpport, param_set_port, param_get_int,
+		 &nfs_callback_set_tcpport, 0644);
 
 /*
  * This is the callback kernel thread.
@@ -134,10 +150,8 @@ out_err:
 /*
  * Kill the server process if it is not already up.
  */
-int nfs_callback_down(void)
+void nfs_callback_down(void)
 {
-	int ret = 0;
-
 	lock_kernel();
 	mutex_lock(&nfs_callback_mutex);
 	nfs_callback_info.users--;
@@ -149,20 +163,19 @@ int nfs_callback_down(void)
 	} while (wait_for_completion_timeout(&nfs_callback_info.stopped, 5*HZ) == 0);
 	mutex_unlock(&nfs_callback_mutex);
 	unlock_kernel();
-	return ret;
 }
 
 static int nfs_callback_authenticate(struct svc_rqst *rqstp)
 {
-	struct in_addr *addr = &rqstp->rq_addr.sin_addr;
-	struct nfs4_client *clp;
+	struct sockaddr_in *addr = &rqstp->rq_addr;
+	struct nfs_client *clp;
 
 	/* Don't talk to strangers */
-	clp = nfs4_find_client(addr);
+	clp = nfs_find_client(addr, 4);
 	if (clp == NULL)
 		return SVC_DROP;
-	dprintk("%s: %u.%u.%u.%u NFSv4 callback!\n", __FUNCTION__, NIPQUAD(addr));
-	nfs4_put_client(clp);
+	dprintk("%s: %u.%u.%u.%u NFSv4 callback!\n", __FUNCTION__, NIPQUAD(addr->sin_addr));
+	nfs_put_client(clp);
 	switch (rqstp->rq_authop->flavour) {
 		case RPC_AUTH_NULL:
 			if (rqstp->rq_proc != CB_NULL)

fs/nfs/callback.h

@@ -62,8 +62,13 @@ struct cb_recallargs {
 extern unsigned nfs4_callback_getattr(struct cb_getattrargs *args, struct cb_getattrres *res);
 extern unsigned nfs4_callback_recall(struct cb_recallargs *args, void *dummy);
 
+#ifdef CONFIG_NFS_V4
 extern int nfs_callback_up(void);
-extern int nfs_callback_down(void);
+extern void nfs_callback_down(void);
+#else
+#define nfs_callback_up()	(0)
+#define nfs_callback_down()	do {} while(0)
+#endif
 
 extern unsigned int nfs_callback_set_tcpport;
 extern unsigned short nfs_callback_tcpport;

fs/nfs/callback_proc.c

@@ -10,19 +10,20 @@
 #include "nfs4_fs.h"
 #include "callback.h"
 #include "delegation.h"
+#include "internal.h"
 
 #define NFSDBG_FACILITY NFSDBG_CALLBACK
  
 unsigned nfs4_callback_getattr(struct cb_getattrargs *args, struct cb_getattrres *res)
 {
-	struct nfs4_client *clp;
+	struct nfs_client *clp;
 	struct nfs_delegation *delegation;
 	struct nfs_inode *nfsi;
 	struct inode *inode;
 	
 	res->bitmap[0] = res->bitmap[1] = 0;
 	res->status = htonl(NFS4ERR_BADHANDLE);
-	clp = nfs4_find_client(&args->addr->sin_addr);
+	clp = nfs_find_client(args->addr, 4);
 	if (clp == NULL)
 		goto out;
 	inode = nfs_delegation_find_inode(clp, &args->fh);
@@ -48,7 +49,7 @@ out_iput:
 	up_read(&nfsi->rwsem);
 	iput(inode);
 out_putclient:
-	nfs4_put_client(clp);
+	nfs_put_client(clp);
 out:
 	dprintk("%s: exit with status = %d\n", __FUNCTION__, ntohl(res->status));
 	return res->status;
@@ -56,12 +57,12 @@ out:
 
 unsigned nfs4_callback_recall(struct cb_recallargs *args, void *dummy)
 {
-	struct nfs4_client *clp;
+	struct nfs_client *clp;
 	struct inode *inode;
 	unsigned res;
 	
 	res = htonl(NFS4ERR_BADHANDLE);
-	clp = nfs4_find_client(&args->addr->sin_addr);
+	clp = nfs_find_client(args->addr, 4);
 	if (clp == NULL)
 		goto out;
 	inode = nfs_delegation_find_inode(clp, &args->fh);
@@ -80,7 +81,7 @@ unsigned nfs4_callback_recall(struct cb_recallargs *args, void *dummy)
 	}
 	iput(inode);
 out_putclient:
-	nfs4_put_client(clp);
+	nfs_put_client(clp);
 out:
 	dprintk("%s: exit with status = %d\n", __FUNCTION__, ntohl(res));
 	return res;

fs/nfs/client.c

@@ -0,0 +1,1448 @@
+/* client.c: NFS client sharing and management code
+ *
+ * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+#include <linux/time.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/stat.h>
+#include <linux/errno.h>
+#include <linux/unistd.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/stats.h>
+#include <linux/sunrpc/metrics.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_mount.h>
+#include <linux/nfs4_mount.h>
+#include <linux/lockd/bind.h>
+#include <linux/smp_lock.h>
+#include <linux/seq_file.h>
+#include <linux/mount.h>
+#include <linux/nfs_idmap.h>
+#include <linux/vfs.h>
+#include <linux/inet.h>
+#include <linux/nfs_xdr.h>
+
+#include <asm/system.h>
+
+#include "nfs4_fs.h"
+#include "callback.h"
+#include "delegation.h"
+#include "iostat.h"
+#include "internal.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);
+
+/*
+ * RPC cruft for NFS
+ */
+static struct rpc_version *nfs_version[5] = {
+	[2]			= &nfs_version2,
+#ifdef CONFIG_NFS_V3
+	[3]			= &nfs_version3,
+#endif
+#ifdef CONFIG_NFS_V4
+	[4]			= &nfs_version4,
+#endif
+};
+
+struct rpc_program nfs_program = {
+	.name			= "nfs",
+	.number			= NFS_PROGRAM,
+	.nrvers			= ARRAY_SIZE(nfs_version),
+	.version		= nfs_version,
+	.stats			= &nfs_rpcstat,
+	.pipe_dir_name		= "/nfs",
+};
+
+struct rpc_stat nfs_rpcstat = {
+	.program		= &nfs_program
+};
+
+
+#ifdef CONFIG_NFS_V3_ACL
+static struct rpc_stat		nfsacl_rpcstat = { &nfsacl_program };
+static struct rpc_version *	nfsacl_version[] = {
+	[3]			= &nfsacl_version3,
+};
+
+struct rpc_program		nfsacl_program = {
+	.name			= "nfsacl",
+	.number			= NFS_ACL_PROGRAM,
+	.nrvers			= ARRAY_SIZE(nfsacl_version),
+	.version		= nfsacl_version,
+	.stats			= &nfsacl_rpcstat,
+};
+#endif  /* CONFIG_NFS_V3_ACL */
+
+/*
+ * Allocate a shared client record
+ *
+ * Since these are allocated/deallocated very rarely, we don't
+ * bother putting them in a slab cache...
+ */
+static struct nfs_client *nfs_alloc_client(const char *hostname,
+					   const struct sockaddr_in *addr,
+					   int nfsversion)
+{
+	struct nfs_client *clp;
+	int error;
+
+	if ((clp = kzalloc(sizeof(*clp), GFP_KERNEL)) == NULL)
+		goto error_0;
+
+	error = rpciod_up();
+	if (error < 0) {
+		dprintk("%s: couldn't start rpciod! Error = %d\n",
+				__FUNCTION__, error);
+		goto error_1;
+	}
+	__set_bit(NFS_CS_RPCIOD, &clp->cl_res_state);
+
+	if (nfsversion == 4) {
+		if (nfs_callback_up() < 0)
+			goto error_2;
+		__set_bit(NFS_CS_CALLBACK, &clp->cl_res_state);
+	}
+
+	atomic_set(&clp->cl_count, 1);
+	clp->cl_cons_state = NFS_CS_INITING;
+
+	clp->cl_nfsversion = nfsversion;
+	memcpy(&clp->cl_addr, addr, sizeof(clp->cl_addr));
+
+	if (hostname) {
+		clp->cl_hostname = kstrdup(hostname, GFP_KERNEL);
+		if (!clp->cl_hostname)
+			goto error_3;
+	}
+
+	INIT_LIST_HEAD(&clp->cl_superblocks);
+	clp->cl_rpcclient = ERR_PTR(-EINVAL);
+
+#ifdef CONFIG_NFS_V4
+	init_rwsem(&clp->cl_sem);
+	INIT_LIST_HEAD(&clp->cl_delegations);
+	INIT_LIST_HEAD(&clp->cl_state_owners);
+	INIT_LIST_HEAD(&clp->cl_unused);
+	spin_lock_init(&clp->cl_lock);
+	INIT_WORK(&clp->cl_renewd, nfs4_renew_state, clp);
+	rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client");
+	clp->cl_boot_time = CURRENT_TIME;
+	clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
+#endif
+
+	return clp;
+
+error_3:
+	if (__test_and_clear_bit(NFS_CS_CALLBACK, &clp->cl_res_state))
+		nfs_callback_down();
+error_2:
+	rpciod_down();
+	__clear_bit(NFS_CS_RPCIOD, &clp->cl_res_state);
+error_1:
+	kfree(clp);
+error_0:
+	return NULL;
+}
+
+static void nfs4_shutdown_client(struct nfs_client *clp)
+{
+#ifdef CONFIG_NFS_V4
+	if (__test_and_clear_bit(NFS_CS_RENEWD, &clp->cl_res_state))
+		nfs4_kill_renewd(clp);
+	while (!list_empty(&clp->cl_unused)) {
+		struct nfs4_state_owner *sp;
+
+		sp = list_entry(clp->cl_unused.next,
+				struct nfs4_state_owner,
+				so_list);
+		list_del(&sp->so_list);
+		kfree(sp);
+	}
+	BUG_ON(!list_empty(&clp->cl_state_owners));
+	if (__test_and_clear_bit(NFS_CS_IDMAP, &clp->cl_res_state))
+		nfs_idmap_delete(clp);
+#endif
+}
+
+/*
+ * Destroy a shared client record
+ */
+static void nfs_free_client(struct nfs_client *clp)
+{
+	dprintk("--> nfs_free_client(%d)\n", clp->cl_nfsversion);
+
+	nfs4_shutdown_client(clp);
+
+	/* -EIO all pending I/O */
+	if (!IS_ERR(clp->cl_rpcclient))
+		rpc_shutdown_client(clp->cl_rpcclient);
+
+	if (__test_and_clear_bit(NFS_CS_CALLBACK, &clp->cl_res_state))
+		nfs_callback_down();
+
+	if (__test_and_clear_bit(NFS_CS_RPCIOD, &clp->cl_res_state))
+		rpciod_down();
+
+	kfree(clp->cl_hostname);
+	kfree(clp);
+
+	dprintk("<-- nfs_free_client()\n");
+}
+
+/*
+ * Release a reference to a shared client record
+ */
+void nfs_put_client(struct nfs_client *clp)
+{
+	if (!clp)
+		return;
+
+	dprintk("--> nfs_put_client({%d})\n", atomic_read(&clp->cl_count));
+
+	if (atomic_dec_and_lock(&clp->cl_count, &nfs_client_lock)) {
+		list_del(&clp->cl_share_link);
+		spin_unlock(&nfs_client_lock);
+
+		BUG_ON(!list_empty(&clp->cl_superblocks));
+
+		nfs_free_client(clp);
+	}
+}
+
+/*
+ * Find a client by address
+ * - caller must hold nfs_client_lock
+ */
+static struct nfs_client *__nfs_find_client(const struct sockaddr_in *addr, int nfsversion)
+{
+	struct nfs_client *clp;
+
+	list_for_each_entry(clp, &nfs_client_list, cl_share_link) {
+		/* Different NFS versions cannot share the same nfs_client */
+		if (clp->cl_nfsversion != nfsversion)
+			continue;
+
+		if (memcmp(&clp->cl_addr.sin_addr, &addr->sin_addr,
+			   sizeof(clp->cl_addr.sin_addr)) != 0)
+			continue;
+
+		if (clp->cl_addr.sin_port == addr->sin_port)
+			goto found;
+	}
+
+	return NULL;
+
+found:
+	atomic_inc(&clp->cl_count);
+	return clp;
+}
+
+/*
+ * Find a client by IP address and protocol version
+ * - returns NULL if no such client
+ */
+struct nfs_client *nfs_find_client(const struct sockaddr_in *addr, int nfsversion)
+{
+	struct nfs_client *clp;
+
+	spin_lock(&nfs_client_lock);
+	clp = __nfs_find_client(addr, nfsversion);
+	spin_unlock(&nfs_client_lock);
+
+	BUG_ON(clp && clp->cl_cons_state == 0);
+
+	return clp;
+}
+
+/*
+ * Look up a client by IP address and protocol version
+ * - creates a new record if one doesn't yet exist
+ */
+static struct nfs_client *nfs_get_client(const char *hostname,
+					 const struct sockaddr_in *addr,
+					 int nfsversion)
+{
+	struct nfs_client *clp, *new = NULL;
+	int error;
+
+	dprintk("--> nfs_get_client(%s,"NIPQUAD_FMT":%d,%d)\n",
+		hostname ?: "", NIPQUAD(addr->sin_addr),
+		addr->sin_port, nfsversion);
+
+	/* see if the client already exists */
+	do {
+		spin_lock(&nfs_client_lock);
+
+		clp = __nfs_find_client(addr, nfsversion);
+		if (clp)
+			goto found_client;
+		if (new)
+			goto install_client;
+
+		spin_unlock(&nfs_client_lock);
+
+		new = nfs_alloc_client(hostname, addr, nfsversion);
+	} while (new);
+
+	return ERR_PTR(-ENOMEM);
+
+	/* 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);
+	dprintk("--> nfs_get_client() = %p [new]\n", clp);
+	return clp;
+
+	/* found an existing client
+	 * - make sure it's ready before returning
+	 */
+found_client:
+	spin_unlock(&nfs_client_lock);
+
+	if (new)
+		nfs_free_client(new);
+
+	if (clp->cl_cons_state == NFS_CS_INITING) {
+		DECLARE_WAITQUEUE(myself, current);
+
+		add_wait_queue(&nfs_client_active_wq, &myself);
+
+		for (;;) {
+			set_current_state(TASK_INTERRUPTIBLE);
+			if (signal_pending(current) ||
+			    clp->cl_cons_state > NFS_CS_READY)
+				break;
+			schedule();
+		}
+
+		remove_wait_queue(&nfs_client_active_wq, &myself);
+
+		if (signal_pending(current)) {
+			nfs_put_client(clp);
+			return ERR_PTR(-ERESTARTSYS);
+		}
+	}
+
+	if (clp->cl_cons_state < NFS_CS_READY) {
+		error = clp->cl_cons_state;
+		nfs_put_client(clp);
+		return ERR_PTR(error);
+	}
+
+	BUG_ON(clp->cl_cons_state != NFS_CS_READY);
+
+	dprintk("--> nfs_get_client() = %p [share]\n", clp);
+	return clp;
+}
+
+/*
+ * Mark a server as ready or failed
+ */
+static void nfs_mark_client_ready(struct nfs_client *clp, int state)
+{
+	clp->cl_cons_state = state;
+	wake_up_all(&nfs_client_active_wq);
+}
+
+/*
+ * Initialise the timeout values for a connection
+ */
+static void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
+				    unsigned int timeo, unsigned int retrans)
+{
+	to->to_initval = timeo * HZ / 10;
+	to->to_retries = retrans;
+	if (!to->to_retries)
+		to->to_retries = 2;
+
+	switch (proto) {
+	case IPPROTO_TCP:
+		if (!to->to_initval)
+			to->to_initval = 60 * HZ;
+		if (to->to_initval > NFS_MAX_TCP_TIMEOUT)
+			to->to_initval = NFS_MAX_TCP_TIMEOUT;
+		to->to_increment = to->to_initval;
+		to->to_maxval = to->to_initval + (to->to_increment * to->to_retries);
+		to->to_exponential = 0;
+		break;
+	case IPPROTO_UDP:
+	default:
+		if (!to->to_initval)
+			to->to_initval = 11 * HZ / 10;
+		if (to->to_initval > NFS_MAX_UDP_TIMEOUT)
+			to->to_initval = NFS_MAX_UDP_TIMEOUT;
+		to->to_maxval = NFS_MAX_UDP_TIMEOUT;
+		to->to_exponential = 1;
+		break;
+	}
+}
+
+/*
+ * Create an RPC client handle
+ */
+static int nfs_create_rpc_client(struct nfs_client *clp, int proto,
+						unsigned int timeo,
+						unsigned int retrans,
+						rpc_authflavor_t flavor)
+{
+	struct rpc_timeout	timeparms;
+	struct rpc_clnt		*clnt = NULL;
+	struct rpc_create_args args = {
+		.protocol	= proto,
+		.address	= (struct sockaddr *)&clp->cl_addr,
+		.addrsize	= sizeof(clp->cl_addr),
+		.timeout	= &timeparms,
+		.servername	= clp->cl_hostname,
+		.program	= &nfs_program,
+		.version	= clp->rpc_ops->version,
+		.authflavor	= flavor,
+	};
+
+	if (!IS_ERR(clp->cl_rpcclient))
+		return 0;
+
+	nfs_init_timeout_values(&timeparms, proto, timeo, retrans);
+	clp->retrans_timeo = timeparms.to_initval;
+	clp->retrans_count = timeparms.to_retries;
+
+	clnt = rpc_create(&args);
+	if (IS_ERR(clnt)) {
+		dprintk("%s: cannot create RPC client. Error = %ld\n",
+				__FUNCTION__, PTR_ERR(clnt));
+		return PTR_ERR(clnt);
+	}
+
+	clp->cl_rpcclient = clnt;
+	return 0;
+}
+
+/*
+ * Version 2 or 3 client destruction
+ */
+static void nfs_destroy_server(struct nfs_server *server)
+{
+	if (!IS_ERR(server->client_acl))
+		rpc_shutdown_client(server->client_acl);
+
+	if (!(server->flags & NFS_MOUNT_NONLM))
+		lockd_down();	/* release rpc.lockd */
+}
+
+/*
+ * Version 2 or 3 lockd setup
+ */
+static int nfs_start_lockd(struct nfs_server *server)
+{
+	int error = 0;
+
+	if (server->nfs_client->cl_nfsversion > 3)
+		goto out;
+	if (server->flags & NFS_MOUNT_NONLM)
+		goto out;
+	error = lockd_up();
+	if (error < 0)
+		server->flags |= NFS_MOUNT_NONLM;
+	else
+		server->destroy = nfs_destroy_server;
+out:
+	return error;
+}
+
+/*
+ * Initialise an NFSv3 ACL client connection
+ */
+#ifdef CONFIG_NFS_V3_ACL
+static void nfs_init_server_aclclient(struct nfs_server *server)
+{
+	if (server->nfs_client->cl_nfsversion != 3)
+		goto out_noacl;
+	if (server->flags & NFS_MOUNT_NOACL)
+		goto out_noacl;
+
+	server->client_acl = rpc_bind_new_program(server->client, &nfsacl_program, 3);
+	if (IS_ERR(server->client_acl))
+		goto out_noacl;
+
+	/* No errors! Assume that Sun nfsacls are supported */
+	server->caps |= NFS_CAP_ACLS;
+	return;
+
+out_noacl:
+	server->caps &= ~NFS_CAP_ACLS;
+}
+#else
+static inline void nfs_init_server_aclclient(struct nfs_server *server)
+{
+	server->flags &= ~NFS_MOUNT_NOACL;
+	server->caps &= ~NFS_CAP_ACLS;
+}
+#endif
+
+/*
+ * Create a general RPC client
+ */
+static int nfs_init_server_rpcclient(struct nfs_server *server, rpc_authflavor_t pseudoflavour)
+{
+	struct nfs_client *clp = server->nfs_client;
+
+	server->client = rpc_clone_client(clp->cl_rpcclient);
+	if (IS_ERR(server->client)) {
+		dprintk("%s: couldn't create rpc_client!\n", __FUNCTION__);
+		return PTR_ERR(server->client);
+	}
+
+	if (pseudoflavour != clp->cl_rpcclient->cl_auth->au_flavor) {
+		struct rpc_auth *auth;
+
+		auth = rpcauth_create(pseudoflavour, server->client);
+		if (IS_ERR(auth)) {
+			dprintk("%s: couldn't create credcache!\n", __FUNCTION__);
+			return PTR_ERR(auth);
+		}
+	}
+	server->client->cl_softrtry = 0;
+	if (server->flags & NFS_MOUNT_SOFT)
+		server->client->cl_softrtry = 1;
+
+	server->client->cl_intr = 0;
+	if (server->flags & NFS4_MOUNT_INTR)
+		server->client->cl_intr = 1;
+
+	return 0;
+}
+
+/*
+ * Initialise an NFS2 or NFS3 client
+ */
+static int nfs_init_client(struct nfs_client *clp, const struct nfs_mount_data *data)
+{
+	int proto = (data->flags & NFS_MOUNT_TCP) ? IPPROTO_TCP : IPPROTO_UDP;
+	int error;
+
+	if (clp->cl_cons_state == NFS_CS_READY) {
+		/* the client is already initialised */
+		dprintk("<-- nfs_init_client() = 0 [already %p]\n", clp);
+		return 0;
+	}
+
+	/* Check NFS protocol revision and initialize RPC op vector */
+	clp->rpc_ops = &nfs_v2_clientops;
+#ifdef CONFIG_NFS_V3
+	if (clp->cl_nfsversion == 3)
+		clp->rpc_ops = &nfs_v3_clientops;
+#endif
+	/*
+	 * Create a client RPC handle for doing FSSTAT with UNIX auth only
+	 * - RFC 2623, sec 2.3.2
+	 */
+	error = nfs_create_rpc_client(clp, proto, data->timeo, data->retrans,
+			RPC_AUTH_UNIX);
+	if (error < 0)
+		goto error;
+	nfs_mark_client_ready(clp, NFS_CS_READY);
+	return 0;
+
+error:
+	nfs_mark_client_ready(clp, error);
+	dprintk("<-- nfs_init_client() = xerror %d\n", error);
+	return error;
+}
+
+/*
+ * Create a version 2 or 3 client
+ */
+static int nfs_init_server(struct nfs_server *server, const struct nfs_mount_data *data)
+{
+	struct nfs_client *clp;
+	int error, nfsvers = 2;
+
+	dprintk("--> nfs_init_server()\n");
+
+#ifdef CONFIG_NFS_V3
+	if (data->flags & NFS_MOUNT_VER3)
+		nfsvers = 3;
+#endif
+
+	/* Allocate or find a client reference we can use */
+	clp = nfs_get_client(data->hostname, &data->addr, nfsvers);
+	if (IS_ERR(clp)) {
+		dprintk("<-- nfs_init_server() = error %ld\n", PTR_ERR(clp));
+		return PTR_ERR(clp);
+	}
+
+	error = nfs_init_client(clp, data);
+	if (error < 0)
+		goto error;
+
+	server->nfs_client = clp;
+
+	/* Initialise the client representation from the mount data */
+	server->flags = data->flags & NFS_MOUNT_FLAGMASK;
+
+	if (data->rsize)
+		server->rsize = nfs_block_size(data->rsize, NULL);
+	if (data->wsize)
+		server->wsize = nfs_block_size(data->wsize, NULL);
+
+	server->acregmin = data->acregmin * HZ;
+	server->acregmax = data->acregmax * HZ;
+	server->acdirmin = data->acdirmin * HZ;
+	server->acdirmax = data->acdirmax * HZ;
+
+	/* Start lockd here, before we might error out */
+	error = nfs_start_lockd(server);
+	if (error < 0)
+		goto error;
+
+	error = nfs_init_server_rpcclient(server, data->pseudoflavor);
+	if (error < 0)
+		goto error;
+
+	server->namelen  = data->namlen;
+	/* Create a client RPC handle for the NFSv3 ACL management interface */
+	nfs_init_server_aclclient(server);
+	if (clp->cl_nfsversion == 3) {
+		if (server->namelen == 0 || server->namelen > NFS3_MAXNAMLEN)
+			server->namelen = NFS3_MAXNAMLEN;
+		server->caps |= NFS_CAP_READDIRPLUS;
+	} else {
+		if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN)
+			server->namelen = NFS2_MAXNAMLEN;
+	}
+
+	dprintk("<-- nfs_init_server() = 0 [new %p]\n", clp);
+	return 0;
+
+error:
+	server->nfs_client = NULL;
+	nfs_put_client(clp);
+	dprintk("<-- nfs_init_server() = xerror %d\n", error);
+	return error;
+}
+
+/*
+ * Load up the server record from information gained in an fsinfo record
+ */
+static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *fsinfo)
+{
+	unsigned long max_rpc_payload;
+
+	/* Work out a lot of parameters */
+	if (server->rsize == 0)
+		server->rsize = nfs_block_size(fsinfo->rtpref, NULL);
+	if (server->wsize == 0)
+		server->wsize = nfs_block_size(fsinfo->wtpref, NULL);
+
+	if (fsinfo->rtmax >= 512 && server->rsize > fsinfo->rtmax)
+		server->rsize = nfs_block_size(fsinfo->rtmax, NULL);
+	if (fsinfo->wtmax >= 512 && server->wsize > fsinfo->wtmax)
+		server->wsize = nfs_block_size(fsinfo->wtmax, NULL);
+
+	max_rpc_payload = nfs_block_size(rpc_max_payload(server->client), NULL);
+	if (server->rsize > max_rpc_payload)
+		server->rsize = max_rpc_payload;
+	if (server->rsize > NFS_MAX_FILE_IO_SIZE)
+		server->rsize = NFS_MAX_FILE_IO_SIZE;
+	server->rpages = (server->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD;
+
+	if (server->wsize > max_rpc_payload)
+		server->wsize = max_rpc_payload;
+	if (server->wsize > NFS_MAX_FILE_IO_SIZE)
+		server->wsize = NFS_MAX_FILE_IO_SIZE;
+	server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
+
+	server->dtsize = nfs_block_size(fsinfo->dtpref, NULL);
+	if (server->dtsize > PAGE_CACHE_SIZE)
+		server->dtsize = PAGE_CACHE_SIZE;
+	if (server->dtsize > server->rsize)
+		server->dtsize = server->rsize;
+
+	if (server->flags & NFS_MOUNT_NOAC) {
+		server->acregmin = server->acregmax = 0;
+		server->acdirmin = server->acdirmax = 0;
+	}
+
+	server->maxfilesize = fsinfo->maxfilesize;
+
+	/* We're airborne Set socket buffersize */
+	rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100);
+}
+
+/*
+ * Probe filesystem information, including the FSID on v2/v3
+ */
+static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs_fattr *fattr)
+{
+	struct nfs_fsinfo fsinfo;
+	struct nfs_client *clp = server->nfs_client;
+	int error;
+
+	dprintk("--> nfs_probe_fsinfo()\n");
+
+	if (clp->rpc_ops->set_capabilities != NULL) {
+		error = clp->rpc_ops->set_capabilities(server, mntfh);
+		if (error < 0)
+			goto out_error;
+	}
+
+	fsinfo.fattr = fattr;
+	nfs_fattr_init(fattr);
+	error = clp->rpc_ops->fsinfo(server, mntfh, &fsinfo);
+	if (error < 0)
+		goto out_error;
+
+	nfs_server_set_fsinfo(server, &fsinfo);
+
+	/* Get some general file system info */
+	if (server->namelen == 0) {
+		struct nfs_pathconf pathinfo;
+
+		pathinfo.fattr = fattr;
+		nfs_fattr_init(fattr);
+
+		if (clp->rpc_ops->pathconf(server, mntfh, &pathinfo) >= 0)
+			server->namelen = pathinfo.max_namelen;
+	}
+
+	dprintk("<-- nfs_probe_fsinfo() = 0\n");
+	return 0;
+
+out_error:
+	dprintk("nfs_probe_fsinfo: error = %d\n", -error);
+	return error;
+}
+
+/*
+ * Copy useful information when duplicating a server record
+ */
+static void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *source)
+{
+	target->flags = source->flags;
+	target->acregmin = source->acregmin;
+	target->acregmax = source->acregmax;
+	target->acdirmin = source->acdirmin;
+	target->acdirmax = source->acdirmax;
+	target->caps = source->caps;
+}
+
+/*
+ * Allocate and initialise a server record
+ */
+static struct nfs_server *nfs_alloc_server(void)
+{
+	struct nfs_server *server;
+
+	server = kzalloc(sizeof(struct nfs_server), GFP_KERNEL);
+	if (!server)
+		return NULL;
+
+	server->client = server->client_acl = ERR_PTR(-EINVAL);
+
+	/* Zero out the NFS state stuff */
+	INIT_LIST_HEAD(&server->client_link);
+	INIT_LIST_HEAD(&server->master_link);
+
+	server->io_stats = nfs_alloc_iostats();
+	if (!server->io_stats) {
+		kfree(server);
+		return NULL;
+	}
+
+	return server;
+}
+
+/*
+ * Free up a server record
+ */
+void nfs_free_server(struct nfs_server *server)
+{
+	dprintk("--> nfs_free_server()\n");
+
+	spin_lock(&nfs_client_lock);
+	list_del(&server->client_link);
+	list_del(&server->master_link);
+	spin_unlock(&nfs_client_lock);
+
+	if (server->destroy != NULL)
+		server->destroy(server);
+	if (!IS_ERR(server->client))
+		rpc_shutdown_client(server->client);
+
+	nfs_put_client(server->nfs_client);
+
+	nfs_free_iostats(server->io_stats);
+	kfree(server);
+	nfs_release_automount_timer();
+	dprintk("<-- nfs_free_server()\n");
+}
+
+/*
+ * Create a version 2 or 3 volume record
+ * - keyed on server and FSID
+ */
+struct nfs_server *nfs_create_server(const struct nfs_mount_data *data,
+				     struct nfs_fh *mntfh)
+{
+	struct nfs_server *server;
+	struct nfs_fattr fattr;
+	int error;
+
+	server = nfs_alloc_server();
+	if (!server)
+		return ERR_PTR(-ENOMEM);
+
+	/* Get a client representation */
+	error = nfs_init_server(server, data);
+	if (error < 0)
+		goto error;
+
+	BUG_ON(!server->nfs_client);
+	BUG_ON(!server->nfs_client->rpc_ops);
+	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
+
+	/* Probe the root fh to retrieve its FSID */
+	error = nfs_probe_fsinfo(server, mntfh, &fattr);
+	if (error < 0)
+		goto error;
+	if (!(fattr.valid & NFS_ATTR_FATTR)) {
+		error = server->nfs_client->rpc_ops->getattr(server, mntfh, &fattr);
+		if (error < 0) {
+			dprintk("nfs_create_server: getattr error = %d\n", -error);
+			goto error;
+		}
+	}
+	memcpy(&server->fsid, &fattr.fsid, sizeof(server->fsid));
+
+	dprintk("Server FSID: %llx:%llx\n",
+		(unsigned long long) server->fsid.major,
+		(unsigned long long) server->fsid.minor);
+
+	BUG_ON(!server->nfs_client);
+	BUG_ON(!server->nfs_client->rpc_ops);
+	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
+
+	spin_lock(&nfs_client_lock);
+	list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks);
+	list_add_tail(&server->master_link, &nfs_volume_list);
+	spin_unlock(&nfs_client_lock);
+
+	server->mount_time = jiffies;
+	return server;
+
+error:
+	nfs_free_server(server);
+	return ERR_PTR(error);
+}
+
+#ifdef CONFIG_NFS_V4
+/*
+ * Initialise an NFS4 client record
+ */
+static int nfs4_init_client(struct nfs_client *clp,
+		int proto, int timeo, int retrans,
+		rpc_authflavor_t authflavour)
+{
+	int error;
+
+	if (clp->cl_cons_state == NFS_CS_READY) {
+		/* the client is initialised already */
+		dprintk("<-- nfs4_init_client() = 0 [already %p]\n", clp);
+		return 0;
+	}
+
+	/* Check NFS protocol revision and initialize RPC op vector */
+	clp->rpc_ops = &nfs_v4_clientops;
+
+	error = nfs_create_rpc_client(clp, proto, timeo, retrans, authflavour);
+	if (error < 0)
+		goto error;
+
+	error = nfs_idmap_new(clp);
+	if (error < 0) {
+		dprintk("%s: failed to create idmapper. Error = %d\n",
+			__FUNCTION__, error);
+		goto error;
+	}
+	__set_bit(NFS_CS_IDMAP, &clp->cl_res_state);
+
+	nfs_mark_client_ready(clp, NFS_CS_READY);
+	return 0;
+
+error:
+	nfs_mark_client_ready(clp, error);
+	dprintk("<-- nfs4_init_client() = xerror %d\n", error);
+	return error;
+}
+
+/*
+ * Set up an NFS4 client
+ */
+static int nfs4_set_client(struct nfs_server *server,
+		const char *hostname, const struct sockaddr_in *addr,
+		rpc_authflavor_t authflavour,
+		int proto, int timeo, int retrans)
+{
+	struct nfs_client *clp;
+	int error;
+
+	dprintk("--> nfs4_set_client()\n");
+
+	/* Allocate or find a client reference we can use */
+	clp = nfs_get_client(hostname, addr, 4);
+	if (IS_ERR(clp)) {
+		error = PTR_ERR(clp);
+		goto error;
+	}
+	error = nfs4_init_client(clp, proto, timeo, retrans, authflavour);
+	if (error < 0)
+		goto error_put;
+
+	server->nfs_client = clp;
+	dprintk("<-- nfs4_set_client() = 0 [new %p]\n", clp);
+	return 0;
+
+error_put:
+	nfs_put_client(clp);
+error:
+	dprintk("<-- nfs4_set_client() = xerror %d\n", error);
+	return error;
+}
+
+/*
+ * Create a version 4 volume record
+ */
+static int nfs4_init_server(struct nfs_server *server,
+		const struct nfs4_mount_data *data, rpc_authflavor_t authflavour)
+{
+	int error;
+
+	dprintk("--> nfs4_init_server()\n");
+
+	/* Initialise the client representation from the mount data */
+	server->flags = data->flags & NFS_MOUNT_FLAGMASK;
+	server->caps |= NFS_CAP_ATOMIC_OPEN;
+
+	if (data->rsize)
+		server->rsize = nfs_block_size(data->rsize, NULL);
+	if (data->wsize)
+		server->wsize = nfs_block_size(data->wsize, NULL);
+
+	server->acregmin = data->acregmin * HZ;
+	server->acregmax = data->acregmax * HZ;
+	server->acdirmin = data->acdirmin * HZ;
+	server->acdirmax = data->acdirmax * HZ;
+
+	error = nfs_init_server_rpcclient(server, authflavour);
+
+	/* Done */
+	dprintk("<-- nfs4_init_server() = %d\n", error);
+	return error;
+}
+
+/*
+ * Create a version 4 volume record
+ * - keyed on server and FSID
+ */
+struct nfs_server *nfs4_create_server(const struct nfs4_mount_data *data,
+				      const char *hostname,
+				      const struct sockaddr_in *addr,
+				      const char *mntpath,
+				      const char *ip_addr,
+				      rpc_authflavor_t authflavour,
+				      struct nfs_fh *mntfh)
+{
+	struct nfs_fattr fattr;
+	struct nfs_server *server;
+	int error;
+
+	dprintk("--> nfs4_create_server()\n");
+
+	server = nfs_alloc_server();
+	if (!server)
+		return ERR_PTR(-ENOMEM);
+
+	/* Get a client record */
+	error = nfs4_set_client(server, hostname, addr, authflavour,
+			data->proto, data->timeo, data->retrans);
+	if (error < 0)
+		goto error;
+
+	/* set up the general RPC client */
+	error = nfs4_init_server(server, data, authflavour);
+	if (error < 0)
+		goto error;
+
+	BUG_ON(!server->nfs_client);
+	BUG_ON(!server->nfs_client->rpc_ops);
+	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
+
+	/* Probe the root fh to retrieve its FSID */
+	error = nfs4_path_walk(server, mntfh, mntpath);
+	if (error < 0)
+		goto error;
+
+	dprintk("Server FSID: %llx:%llx\n",
+		(unsigned long long) server->fsid.major,
+		(unsigned long long) server->fsid.minor);
+	dprintk("Mount FH: %d\n", mntfh->size);
+
+	error = nfs_probe_fsinfo(server, mntfh, &fattr);
+	if (error < 0)
+		goto error;
+
+	BUG_ON(!server->nfs_client);
+	BUG_ON(!server->nfs_client->rpc_ops);
+	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
+
+	spin_lock(&nfs_client_lock);
+	list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks);
+	list_add_tail(&server->master_link, &nfs_volume_list);
+	spin_unlock(&nfs_client_lock);
+
+	server->mount_time = jiffies;
+	dprintk("<-- nfs4_create_server() = %p\n", server);
+	return server;
+
+error:
+	nfs_free_server(server);
+	dprintk("<-- nfs4_create_server() = error %d\n", error);
+	return ERR_PTR(error);
+}
+
+/*
+ * Create an NFS4 referral server record
+ */
+struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
+					       struct nfs_fh *fh)
+{
+	struct nfs_client *parent_client;
+	struct nfs_server *server, *parent_server;
+	struct nfs_fattr fattr;
+	int error;
+
+	dprintk("--> nfs4_create_referral_server()\n");
+
+	server = nfs_alloc_server();
+	if (!server)
+		return ERR_PTR(-ENOMEM);
+
+	parent_server = NFS_SB(data->sb);
+	parent_client = parent_server->nfs_client;
+
+	/* Get a client representation.
+	 * Note: NFSv4 always uses TCP, */
+	error = nfs4_set_client(server, data->hostname, data->addr,
+			data->authflavor,
+			parent_server->client->cl_xprt->prot,
+			parent_client->retrans_timeo,
+			parent_client->retrans_count);
+	if (error < 0)
+		goto error;
+
+	/* Initialise the client representation from the parent server */
+	nfs_server_copy_userdata(server, parent_server);
+	server->caps |= NFS_CAP_ATOMIC_OPEN;
+
+	error = nfs_init_server_rpcclient(server, data->authflavor);
+	if (error < 0)
+		goto error;
+
+	BUG_ON(!server->nfs_client);
+	BUG_ON(!server->nfs_client->rpc_ops);
+	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
+
+	/* probe the filesystem info for this server filesystem */
+	error = nfs_probe_fsinfo(server, fh, &fattr);
+	if (error < 0)
+		goto error;
+
+	dprintk("Referral FSID: %llx:%llx\n",
+		(unsigned long long) server->fsid.major,
+		(unsigned long long) server->fsid.minor);
+
+	spin_lock(&nfs_client_lock);
+	list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks);
+	list_add_tail(&server->master_link, &nfs_volume_list);
+	spin_unlock(&nfs_client_lock);
+
+	server->mount_time = jiffies;
+
+	dprintk("<-- nfs_create_referral_server() = %p\n", server);
+	return server;
+
+error:
+	nfs_free_server(server);
+	dprintk("<-- nfs4_create_referral_server() = error %d\n", error);
+	return ERR_PTR(error);
+}
+
+#endif /* CONFIG_NFS_V4 */
+
+/*
+ * Clone an NFS2, NFS3 or NFS4 server record
+ */
+struct nfs_server *nfs_clone_server(struct nfs_server *source,
+				    struct nfs_fh *fh,
+				    struct nfs_fattr *fattr)
+{
+	struct nfs_server *server;
+	struct nfs_fattr fattr_fsinfo;
+	int error;
+
+	dprintk("--> nfs_clone_server(,%llx:%llx,)\n",
+		(unsigned long long) fattr->fsid.major,
+		(unsigned long long) fattr->fsid.minor);
+
+	server = nfs_alloc_server();
+	if (!server)
+		return ERR_PTR(-ENOMEM);
+
+	/* Copy data from the source */
+	server->nfs_client = source->nfs_client;
+	atomic_inc(&server->nfs_client->cl_count);
+	nfs_server_copy_userdata(server, source);
+
+	server->fsid = fattr->fsid;
+
+	error = nfs_init_server_rpcclient(server, source->client->cl_auth->au_flavor);
+	if (error < 0)
+		goto out_free_server;
+	if (!IS_ERR(source->client_acl))
+		nfs_init_server_aclclient(server);
+
+	/* probe the filesystem info for this server filesystem */
+	error = nfs_probe_fsinfo(server, fh, &fattr_fsinfo);
+	if (error < 0)
+		goto out_free_server;
+
+	dprintk("Cloned FSID: %llx:%llx\n",
+		(unsigned long long) server->fsid.major,
+		(unsigned long long) server->fsid.minor);
+
+	error = nfs_start_lockd(server);
+	if (error < 0)
+		goto out_free_server;
+
+	spin_lock(&nfs_client_lock);
+	list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks);
+	list_add_tail(&server->master_link, &nfs_volume_list);
+	spin_unlock(&nfs_client_lock);
+
+	server->mount_time = jiffies;
+
+	dprintk("<-- nfs_clone_server() = %p\n", server);
+	return server;
+
+out_free_server:
+	nfs_free_server(server);
+	dprintk("<-- nfs_clone_server() = error %d\n", error);
+	return ERR_PTR(error);
+}
+
+#ifdef CONFIG_PROC_FS
+static struct proc_dir_entry *proc_fs_nfs;
+
+static int nfs_server_list_open(struct inode *inode, struct file *file);
+static void *nfs_server_list_start(struct seq_file *p, loff_t *pos);
+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);
+static int nfs_server_list_show(struct seq_file *m, void *v);
+
+static struct seq_operations nfs_server_list_ops = {
+	.start	= nfs_server_list_start,
+	.next	= nfs_server_list_next,
+	.stop	= nfs_server_list_stop,
+	.show	= nfs_server_list_show,
+};
+
+static struct file_operations nfs_server_list_fops = {
+	.open		= nfs_server_list_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static int nfs_volume_list_open(struct inode *inode, struct file *file);
+static void *nfs_volume_list_start(struct seq_file *p, loff_t *pos);
+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);
+static int nfs_volume_list_show(struct seq_file *m, void *v);
+
+static struct seq_operations nfs_volume_list_ops = {
+	.start	= nfs_volume_list_start,
+	.next	= nfs_volume_list_next,
+	.stop	= nfs_volume_list_stop,
+	.show	= nfs_volume_list_show,
+};
+
+static struct file_operations nfs_volume_list_fops = {
+	.open		= nfs_volume_list_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+/*
+ * open "/proc/fs/nfsfs/servers" which provides a summary of servers with which
+ * we're dealing
+ */
+static int nfs_server_list_open(struct inode *inode, struct file *file)
+{
+	struct seq_file *m;
+	int ret;
+
+	ret = seq_open(file, &nfs_server_list_ops);
+	if (ret < 0)
+		return ret;
+
+	m = file->private_data;
+	m->private = PDE(inode)->data;
+
+	return 0;
+}
+
+/*
+ * set up the iterator to start reading from the server list and return the first item
+ */
+static void *nfs_server_list_start(struct seq_file *m, loff_t *_pos)
+{
+	struct list_head *_p;
+	loff_t pos = *_pos;
+
+	/* lock the list against modification */
+	spin_lock(&nfs_client_lock);
+
+	/* allow for the header line */
+	if (!pos)
+		return SEQ_START_TOKEN;
+	pos--;
+
+	/* find the n'th element in the list */
+	list_for_each(_p, &nfs_client_list)
+		if (!pos--)
+			break;
+
+	return _p != &nfs_client_list ? _p : NULL;
+}
+
+/*
+ * move to next server
+ */
+static void *nfs_server_list_next(struct seq_file *p, void *v, loff_t *pos)
+{
+	struct list_head *_p;
+
+	(*pos)++;
+
+	_p = v;
+	_p = (v == SEQ_START_TOKEN) ? nfs_client_list.next : _p->next;
+
+	return _p != &nfs_client_list ? _p : NULL;
+}
+
+/*
+ * clean up after reading from the transports list
+ */
+static void nfs_server_list_stop(struct seq_file *p, void *v)
+{
+	spin_unlock(&nfs_client_lock);
+}
+
+/*
+ * display a header line followed by a load of call lines
+ */
+static int nfs_server_list_show(struct seq_file *m, void *v)
+{
+	struct nfs_client *clp;
+
+	/* display header on line 1 */
+	if (v == SEQ_START_TOKEN) {
+		seq_puts(m, "NV SERVER   PORT USE HOSTNAME\n");
+		return 0;
+	}
+
+	/* display one transport per line on subsequent lines */
+	clp = list_entry(v, struct nfs_client, cl_share_link);
+
+	seq_printf(m, "v%d %02x%02x%02x%02x %4hx %3d %s\n",
+		   clp->cl_nfsversion,
+		   NIPQUAD(clp->cl_addr.sin_addr),
+		   ntohs(clp->cl_addr.sin_port),
+		   atomic_read(&clp->cl_count),
+		   clp->cl_hostname);
+
+	return 0;
+}
+
+/*
+ * open "/proc/fs/nfsfs/volumes" which provides a summary of extant volumes
+ */
+static int nfs_volume_list_open(struct inode *inode, struct file *file)
+{
+	struct seq_file *m;
+	int ret;
+
+	ret = seq_open(file, &nfs_volume_list_ops);
+	if (ret < 0)
+		return ret;
+
+	m = file->private_data;
+	m->private = PDE(inode)->data;
+
+	return 0;
+}
+
+/*
+ * set up the iterator to start reading from the volume list and return the first item
+ */
+static void *nfs_volume_list_start(struct seq_file *m, loff_t *_pos)
+{
+	struct list_head *_p;
+	loff_t pos = *_pos;
+
+	/* lock the list against modification */
+	spin_lock(&nfs_client_lock);
+
+	/* allow for the header line */
+	if (!pos)
+		return SEQ_START_TOKEN;
+	pos--;
+
+	/* find the n'th element in the list */
+	list_for_each(_p, &nfs_volume_list)
+		if (!pos--)
+			break;
+
+	return _p != &nfs_volume_list ? _p : NULL;
+}
+
+/*
+ * move to next volume
+ */
+static void *nfs_volume_list_next(struct seq_file *p, void *v, loff_t *pos)
+{
+	struct list_head *_p;
+
+	(*pos)++;
+
+	_p = v;
+	_p = (v == SEQ_START_TOKEN) ? nfs_volume_list.next : _p->next;
+
+	return _p != &nfs_volume_list ? _p : NULL;
+}
+
+/*
+ * clean up after reading from the transports list
+ */
+static void nfs_volume_list_stop(struct seq_file *p, void *v)
+{
+	spin_unlock(&nfs_client_lock);
+}
+
+/*
+ * display a header line followed by a load of call lines
+ */
+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];
+
+	/* display header on line 1 */
+	if (v == SEQ_START_TOKEN) {
+		seq_puts(m, "NV SERVER   PORT DEV     FSID\n");
+		return 0;
+	}
+	/* display one transport per line on subsequent lines */
+	server = list_entry(v, struct nfs_server, master_link);
+	clp = server->nfs_client;
+
+	snprintf(dev, 8, "%u:%u",
+		 MAJOR(server->s_dev), MINOR(server->s_dev));
+
+	snprintf(fsid, 17, "%llx:%llx",
+		 (unsigned long long) server->fsid.major,
+		 (unsigned long long) server->fsid.minor);
+
+	seq_printf(m, "v%d %02x%02x%02x%02x %4hx %-7s %-17s\n",
+		   clp->cl_nfsversion,
+		   NIPQUAD(clp->cl_addr.sin_addr),
+		   ntohs(clp->cl_addr.sin_port),
+		   dev,
+		   fsid);
+
+	return 0;
+}
+
+/*
+ * initialise the /proc/fs/nfsfs/ directory
+ */
+int __init nfs_fs_proc_init(void)
+{
+	struct proc_dir_entry *p;
+
+	proc_fs_nfs = proc_mkdir("nfsfs", proc_root_fs);
+	if (!proc_fs_nfs)
+		goto error_0;
+
+	proc_fs_nfs->owner = THIS_MODULE;
+
+	/* a file of servers with which we're dealing */
+	p = create_proc_entry("servers", S_IFREG|S_IRUGO, proc_fs_nfs);
+	if (!p)
+		goto error_1;
+
+	p->proc_fops = &nfs_server_list_fops;
+	p->owner = THIS_MODULE;
+
+	/* a file of volumes that we have mounted */
+	p = create_proc_entry("volumes", S_IFREG|S_IRUGO, proc_fs_nfs);
+	if (!p)
+		goto error_2;
+
+	p->proc_fops = &nfs_volume_list_fops;
+	p->owner = THIS_MODULE;
+	return 0;
+
+error_2:
+	remove_proc_entry("servers", proc_fs_nfs);
+error_1:
+	remove_proc_entry("nfsfs", proc_root_fs);
+error_0:
+	return -ENOMEM;
+}
+
+/*
+ * clean up the /proc/fs/nfsfs/ directory
+ */
+void nfs_fs_proc_exit(void)
+{
+	remove_proc_entry("volumes", proc_fs_nfs);
+	remove_proc_entry("servers", proc_fs_nfs);
+	remove_proc_entry("nfsfs", proc_root_fs);
+}
+
+#endif /* CONFIG_PROC_FS */

fs/nfs/delegation.c

@@ -18,6 +18,7 @@
 
 #include "nfs4_fs.h"
 #include "delegation.h"
+#include "internal.h"
 
 static struct nfs_delegation *nfs_alloc_delegation(void)
 {
@@ -52,7 +53,7 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_
 			case -NFS4ERR_EXPIRED:
 				/* kill_proc(fl->fl_pid, SIGLOST, 1); */
 			case -NFS4ERR_STALE_CLIENTID:
-				nfs4_schedule_state_recovery(NFS_SERVER(inode)->nfs4_state);
+				nfs4_schedule_state_recovery(NFS_SERVER(inode)->nfs_client);
 				goto out_err;
 		}
 	}
@@ -114,7 +115,7 @@ void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, st
  */
 int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res)
 {
-	struct nfs4_client *clp = NFS_SERVER(inode)->nfs4_state;
+	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_delegation *delegation;
 	int status = 0;
@@ -145,7 +146,7 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
 					sizeof(delegation->stateid)) != 0 ||
 				delegation->type != nfsi->delegation->type) {
 			printk("%s: server %u.%u.%u.%u, handed out a duplicate delegation!\n",
-					__FUNCTION__, NIPQUAD(clp->cl_addr));
+					__FUNCTION__, NIPQUAD(clp->cl_addr.sin_addr));
 			status = -EIO;
 		}
 	}
@@ -176,7 +177,7 @@ static void nfs_msync_inode(struct inode *inode)
  */
 int __nfs_inode_return_delegation(struct inode *inode)
 {
-	struct nfs4_client *clp = NFS_SERVER(inode)->nfs4_state;
+	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_delegation *delegation;
 	int res = 0;
@@ -208,7 +209,7 @@ int __nfs_inode_return_delegation(struct inode *inode)
  */
 void nfs_return_all_delegations(struct super_block *sb)
 {
-	struct nfs4_client *clp = NFS_SB(sb)->nfs4_state;
+	struct nfs_client *clp = NFS_SB(sb)->nfs_client;
 	struct nfs_delegation *delegation;
 	struct inode *inode;
 
@@ -232,7 +233,7 @@ restart:
 
 int nfs_do_expire_all_delegations(void *ptr)
 {
-	struct nfs4_client *clp = ptr;
+	struct nfs_client *clp = ptr;
 	struct nfs_delegation *delegation;
 	struct inode *inode;
 
@@ -254,11 +255,11 @@ restart:
 	}
 out:
 	spin_unlock(&clp->cl_lock);
-	nfs4_put_client(clp);
+	nfs_put_client(clp);
 	module_put_and_exit(0);
 }
 
-void nfs_expire_all_delegations(struct nfs4_client *clp)
+void nfs_expire_all_delegations(struct nfs_client *clp)
 {
 	struct task_struct *task;
 
@@ -266,17 +267,17 @@ void nfs_expire_all_delegations(struct nfs4_client *clp)
 	atomic_inc(&clp->cl_count);
 	task = kthread_run(nfs_do_expire_all_delegations, clp,
 			"%u.%u.%u.%u-delegreturn",
-			NIPQUAD(clp->cl_addr));
+			NIPQUAD(clp->cl_addr.sin_addr));
 	if (!IS_ERR(task))
 		return;
-	nfs4_put_client(clp);
+	nfs_put_client(clp);
 	module_put(THIS_MODULE);
 }
 
 /*
  * Return all delegations following an NFS4ERR_CB_PATH_DOWN error.
  */
-void nfs_handle_cb_pathdown(struct nfs4_client *clp)
+void nfs_handle_cb_pathdown(struct nfs_client *clp)
 {
 	struct nfs_delegation *delegation;
 	struct inode *inode;
@@ -299,7 +300,7 @@ restart:
 
 struct recall_threadargs {
 	struct inode *inode;
-	struct nfs4_client *clp;
+	struct nfs_client *clp;
 	const nfs4_stateid *stateid;
 
 	struct completion started;
@@ -310,7 +311,7 @@ static int recall_thread(void *data)
 {
 	struct recall_threadargs *args = (struct recall_threadargs *)data;
 	struct inode *inode = igrab(args->inode);
-	struct nfs4_client *clp = NFS_SERVER(inode)->nfs4_state;
+	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_delegation *delegation;
 
@@ -371,7 +372,7 @@ out_module_put:
 /*
  * Retrieve the inode associated with a delegation
  */
-struct inode *nfs_delegation_find_inode(struct nfs4_client *clp, const struct nfs_fh *fhandle)
+struct inode *nfs_delegation_find_inode(struct nfs_client *clp, const struct nfs_fh *fhandle)
 {
 	struct nfs_delegation *delegation;
 	struct inode *res = NULL;
@@ -389,7 +390,7 @@ struct inode *nfs_delegation_find_inode(struct nfs4_client *clp, const struct nf
 /*
  * Mark all delegations as needing to be reclaimed
  */
-void nfs_delegation_mark_reclaim(struct nfs4_client *clp)
+void nfs_delegation_mark_reclaim(struct nfs_client *clp)
 {
 	struct nfs_delegation *delegation;
 	spin_lock(&clp->cl_lock);
@@ -401,7 +402,7 @@ void nfs_delegation_mark_reclaim(struct nfs4_client *clp)
 /*
  * Reap all unclaimed delegations after reboot recovery is done
  */
-void nfs_delegation_reap_unclaimed(struct nfs4_client *clp)
+void nfs_delegation_reap_unclaimed(struct nfs_client *clp)
 {
 	struct nfs_delegation *delegation, *n;
 	LIST_HEAD(head);
@@ -423,7 +424,7 @@ void nfs_delegation_reap_unclaimed(struct nfs4_client *clp)
 
 int nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode)
 {
-	struct nfs4_client *clp = NFS_SERVER(inode)->nfs4_state;
+	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_delegation *delegation;
 	int res = 0;

fs/nfs/delegation.h

@@ -29,13 +29,13 @@ void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, st
 int __nfs_inode_return_delegation(struct inode *inode);
 int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid);
 
-struct inode *nfs_delegation_find_inode(struct nfs4_client *clp, const struct nfs_fh *fhandle);
+struct inode *nfs_delegation_find_inode(struct nfs_client *clp, const struct nfs_fh *fhandle);
 void nfs_return_all_delegations(struct super_block *sb);
-void nfs_expire_all_delegations(struct nfs4_client *clp);
-void nfs_handle_cb_pathdown(struct nfs4_client *clp);
+void nfs_expire_all_delegations(struct nfs_client *clp);
+void nfs_handle_cb_pathdown(struct nfs_client *clp);
 
-void nfs_delegation_mark_reclaim(struct nfs4_client *clp);
-void nfs_delegation_reap_unclaimed(struct nfs4_client *clp);
+void nfs_delegation_mark_reclaim(struct nfs_client *clp);
+void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
 
 /* NFSv4 delegation-related procedures */
 int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid);

fs/nfs/dir.c

@@ -30,7 +30,9 @@
 #include <linux/nfs_mount.h>
 #include <linux/pagemap.h>
 #include <linux/smp_lock.h>
+#include <linux/pagevec.h>
 #include <linux/namei.h>
+#include <linux/mount.h>
 
 #include "nfs4_fs.h"
 #include "delegation.h"
@@ -870,14 +872,14 @@ int nfs_is_exclusive_create(struct inode *dir, struct nameidata *nd)
 	return (nd->intent.open.flags & O_EXCL) != 0;
 }
 
-static inline int nfs_reval_fsid(struct inode *dir,
-		struct nfs_fh *fh, struct nfs_fattr *fattr)
+static inline int nfs_reval_fsid(struct vfsmount *mnt, struct inode *dir,
+				 struct nfs_fh *fh, struct nfs_fattr *fattr)
 {
 	struct nfs_server *server = NFS_SERVER(dir);
 
 	if (!nfs_fsid_equal(&server->fsid, &fattr->fsid))
 		/* Revalidate fsid on root dir */
-		return __nfs_revalidate_inode(server, dir->i_sb->s_root->d_inode);
+		return __nfs_revalidate_inode(server, mnt->mnt_root->d_inode);
 	return 0;
 }
 
@@ -902,9 +904,15 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
 
 	lock_kernel();
 
-	/* If we're doing an exclusive create, optimize away the lookup */
-	if (nfs_is_exclusive_create(dir, nd))
-		goto no_entry;
+	/*
+	 * If we're doing an exclusive create, optimize away the lookup
+	 * but don't hash the dentry.
+	 */
+	if (nfs_is_exclusive_create(dir, nd)) {
+		d_instantiate(dentry, NULL);
+		res = NULL;
+		goto out_unlock;
+	}
 
 	error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, &fhandle, &fattr);
 	if (error == -ENOENT)
@@ -913,7 +921,7 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
 		res = ERR_PTR(error);
 		goto out_unlock;
 	}
-	error = nfs_reval_fsid(dir, &fhandle, &fattr);
+	error = nfs_reval_fsid(nd->mnt, dir, &fhandle, &fattr);
 	if (error < 0) {
 		res = ERR_PTR(error);
 		goto out_unlock;
@@ -922,8 +930,9 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
 	res = (struct dentry *)inode;
 	if (IS_ERR(res))
 		goto out_unlock;
+
 no_entry:
-	res = d_add_unique(dentry, inode);
+	res = d_materialise_unique(dentry, inode);
 	if (res != NULL)
 		dentry = res;
 	nfs_renew_times(dentry);
@@ -1117,11 +1126,13 @@ static struct dentry *nfs_readdir_lookup(nfs_readdir_descriptor_t *desc)
 		dput(dentry);
 		return NULL;
 	}
-	alias = d_add_unique(dentry, inode);
+
+	alias = d_materialise_unique(dentry, inode);
 	if (alias != NULL) {
 		dput(dentry);
 		dentry = alias;
 	}
+
 	nfs_renew_times(dentry);
 	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 	return dentry;
@@ -1143,23 +1154,22 @@ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle,
 		struct inode *dir = dentry->d_parent->d_inode;
 		error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr);
 		if (error)
-			goto out_err;
+			return error;
 	}
 	if (!(fattr->valid & NFS_ATTR_FATTR)) {
 		struct nfs_server *server = NFS_SB(dentry->d_sb);
-		error = server->rpc_ops->getattr(server, fhandle, fattr);
+		error = server->nfs_client->rpc_ops->getattr(server, fhandle, fattr);
 		if (error < 0)
-			goto out_err;
+			return error;
 	}
 	inode = nfs_fhget(dentry->d_sb, fhandle, fattr);
 	error = PTR_ERR(inode);
 	if (IS_ERR(inode))
-		goto out_err;
+		return error;
 	d_instantiate(dentry, inode);
+	if (d_unhashed(dentry))
+		d_rehash(dentry);
 	return 0;
-out_err:
-	d_drop(dentry);
-	return error;
 }
 
 /*
@@ -1440,48 +1450,82 @@ static int nfs_unlink(struct inode *dir, struct dentry *dentry)
 	return error;
 }
 
-static int
-nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
+/*
+ * To create a symbolic link, most file systems instantiate a new inode,
+ * add a page to it containing the path, then write it out to the disk
+ * using prepare_write/commit_write.
+ *
+ * Unfortunately the NFS client can't create the in-core inode first
+ * because it needs a file handle to create an in-core inode (see
+ * fs/nfs/inode.c:nfs_fhget).  We only have a file handle *after* the
+ * symlink request has completed on the server.
+ *
+ * So instead we allocate a raw page, copy the symname into it, then do
+ * the SYMLINK request with the page as the buffer.  If it succeeds, we
+ * now have a new file handle and can instantiate an in-core NFS inode
+ * and move the raw page into its mapping.
+ */
+static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
 {
+	struct pagevec lru_pvec;
+	struct page *page;
+	char *kaddr;
 	struct iattr attr;
-	struct nfs_fattr sym_attr;
-	struct nfs_fh sym_fh;
-	struct qstr qsymname;
+	unsigned int pathlen = strlen(symname);
 	int error;
 
 	dfprintk(VFS, "NFS: symlink(%s/%ld, %s, %s)\n", dir->i_sb->s_id,
 		dir->i_ino, dentry->d_name.name, symname);
 
-#ifdef NFS_PARANOIA
-if (dentry->d_inode)
-printk("nfs_proc_symlink: %s/%s not negative!\n",
-dentry->d_parent->d_name.name, dentry->d_name.name);
-#endif
-	/*
-	 * Fill in the sattr for the call.
- 	 * Note: SunOS 4.1.2 crashes if the mode isn't initialized!
-	 */
-	attr.ia_valid = ATTR_MODE;
-	attr.ia_mode = S_IFLNK | S_IRWXUGO;
+	if (pathlen > PAGE_SIZE)
+		return -ENAMETOOLONG;
 
-	qsymname.name = symname;
-	qsymname.len  = strlen(symname);
+	attr.ia_mode = S_IFLNK | S_IRWXUGO;
+	attr.ia_valid = ATTR_MODE;
 
 	lock_kernel();
+
+	page = alloc_page(GFP_KERNEL);
+	if (!page) {
+		unlock_kernel();
+		return -ENOMEM;
+	}
+
+	kaddr = kmap_atomic(page, KM_USER0);
+	memcpy(kaddr, symname, pathlen);
+	if (pathlen < PAGE_SIZE)
+		memset(kaddr + pathlen, 0, PAGE_SIZE - pathlen);
+	kunmap_atomic(kaddr, KM_USER0);
+
 	nfs_begin_data_update(dir);
-	error = NFS_PROTO(dir)->symlink(dir, &dentry->d_name, &qsymname,
-					  &attr, &sym_fh, &sym_attr);
+	error = NFS_PROTO(dir)->symlink(dir, dentry, page, pathlen, &attr);
 	nfs_end_data_update(dir);
-	if (!error) {
-		error = nfs_instantiate(dentry, &sym_fh, &sym_attr);
-	} else {
-		if (error == -EEXIST)
-			printk("nfs_proc_symlink: %s/%s already exists??\n",
-			       dentry->d_parent->d_name.name, dentry->d_name.name);
+	if (error != 0) {
+		dfprintk(VFS, "NFS: symlink(%s/%ld, %s, %s) error %d\n",
+			dir->i_sb->s_id, dir->i_ino,
+			dentry->d_name.name, symname, error);
 		d_drop(dentry);
+		__free_page(page);
+		unlock_kernel();
+		return error;
 	}
+
+	/*
+	 * No big deal if we can't add this page to the page cache here.
+	 * READLINK will get the missing page from the server if needed.
+	 */
+	pagevec_init(&lru_pvec, 0);
+	if (!add_to_page_cache(page, dentry->d_inode->i_mapping, 0,
+							GFP_KERNEL)) {
+		if (!pagevec_add(&lru_pvec, page))
+			__pagevec_lru_add(&lru_pvec);
+		SetPageUptodate(page);
+		unlock_page(page);
+	} else
+		__free_page(page);
+
 	unlock_kernel();
-	return error;
+	return 0;
 }
 
 static int 
@@ -1638,35 +1682,211 @@ out:
 	return error;
 }
 
+static DEFINE_SPINLOCK(nfs_access_lru_lock);
+static LIST_HEAD(nfs_access_lru_list);
+static atomic_long_t nfs_access_nr_entries;
+
+static void nfs_access_free_entry(struct nfs_access_entry *entry)
+{
+	put_rpccred(entry->cred);
+	kfree(entry);
+	smp_mb__before_atomic_dec();
+	atomic_long_dec(&nfs_access_nr_entries);
+	smp_mb__after_atomic_dec();
+}
+
+int nfs_access_cache_shrinker(int nr_to_scan, gfp_t gfp_mask)
+{
+	LIST_HEAD(head);
+	struct nfs_inode *nfsi;
+	struct nfs_access_entry *cache;
+
+	spin_lock(&nfs_access_lru_lock);
+restart:
+	list_for_each_entry(nfsi, &nfs_access_lru_list, access_cache_inode_lru) {
+		struct inode *inode;
+
+		if (nr_to_scan-- == 0)
+			break;
+		inode = igrab(&nfsi->vfs_inode);
+		if (inode == NULL)
+			continue;
+		spin_lock(&inode->i_lock);
+		if (list_empty(&nfsi->access_cache_entry_lru))
+			goto remove_lru_entry;
+		cache = list_entry(nfsi->access_cache_entry_lru.next,
+				struct nfs_access_entry, lru);
+		list_move(&cache->lru, &head);
+		rb_erase(&cache->rb_node, &nfsi->access_cache);
+		if (!list_empty(&nfsi->access_cache_entry_lru))
+			list_move_tail(&nfsi->access_cache_inode_lru,
+					&nfs_access_lru_list);
+		else {
+remove_lru_entry:
+			list_del_init(&nfsi->access_cache_inode_lru);
+			clear_bit(NFS_INO_ACL_LRU_SET, &nfsi->flags);
+		}
+		spin_unlock(&inode->i_lock);
+		iput(inode);
+		goto restart;
+	}
+	spin_unlock(&nfs_access_lru_lock);
+	while (!list_empty(&head)) {
+		cache = list_entry(head.next, struct nfs_access_entry, lru);
+		list_del(&cache->lru);
+		nfs_access_free_entry(cache);
+	}
+	return (atomic_long_read(&nfs_access_nr_entries) / 100) * sysctl_vfs_cache_pressure;
+}
+
+static void __nfs_access_zap_cache(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+	struct rb_root *root_node = &nfsi->access_cache;
+	struct rb_node *n, *dispose = NULL;
+	struct nfs_access_entry *entry;
+
+	/* Unhook entries from the cache */
+	while ((n = rb_first(root_node)) != NULL) {
+		entry = rb_entry(n, struct nfs_access_entry, rb_node);
+		rb_erase(n, root_node);
+		list_del(&entry->lru);
+		n->rb_left = dispose;
+		dispose = n;
+	}
+	nfsi->cache_validity &= ~NFS_INO_INVALID_ACCESS;
+	spin_unlock(&inode->i_lock);
+
+	/* Now kill them all! */
+	while (dispose != NULL) {
+		n = dispose;
+		dispose = n->rb_left;
+		nfs_access_free_entry(rb_entry(n, struct nfs_access_entry, rb_node));
+	}
+}
+
+void nfs_access_zap_cache(struct inode *inode)
+{
+	/* Remove from global LRU init */
+	if (test_and_clear_bit(NFS_INO_ACL_LRU_SET, &NFS_FLAGS(inode))) {
+		spin_lock(&nfs_access_lru_lock);
+		list_del_init(&NFS_I(inode)->access_cache_inode_lru);
+		spin_unlock(&nfs_access_lru_lock);
+	}
+
+	spin_lock(&inode->i_lock);
+	/* This will release the spinlock */
+	__nfs_access_zap_cache(inode);
+}
+
+static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, struct rpc_cred *cred)
+{
+	struct rb_node *n = NFS_I(inode)->access_cache.rb_node;
+	struct nfs_access_entry *entry;
+
+	while (n != NULL) {
+		entry = rb_entry(n, struct nfs_access_entry, rb_node);
+
+		if (cred < entry->cred)
+			n = n->rb_left;
+		else if (cred > entry->cred)
+			n = n->rb_right;
+		else
+			return entry;
+	}
+	return NULL;
+}
+
 int nfs_access_get_cached(struct inode *inode, struct rpc_cred *cred, struct nfs_access_entry *res)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
-	struct nfs_access_entry *cache = &nfsi->cache_access;
+	struct nfs_access_entry *cache;
+	int err = -ENOENT;
 
-	if (cache->cred != cred
-			|| time_after(jiffies, cache->jiffies + NFS_ATTRTIMEO(inode))
-			|| (nfsi->cache_validity & NFS_INO_INVALID_ACCESS))
-		return -ENOENT;
-	memcpy(res, cache, sizeof(*res));
-	return 0;
+	spin_lock(&inode->i_lock);
+	if (nfsi->cache_validity & NFS_INO_INVALID_ACCESS)
+		goto out_zap;
+	cache = nfs_access_search_rbtree(inode, cred);
+	if (cache == NULL)
+		goto out;
+	if (time_after(jiffies, cache->jiffies + NFS_ATTRTIMEO(inode)))
+		goto out_stale;
+	res->jiffies = cache->jiffies;
+	res->cred = cache->cred;
+	res->mask = cache->mask;
+	list_move_tail(&cache->lru, &nfsi->access_cache_entry_lru);
+	err = 0;
+out:
+	spin_unlock(&inode->i_lock);
+	return err;
+out_stale:
+	rb_erase(&cache->rb_node, &nfsi->access_cache);
+	list_del(&cache->lru);
+	spin_unlock(&inode->i_lock);
+	nfs_access_free_entry(cache);
+	return -ENOENT;
+out_zap:
+	/* This will release the spinlock */
+	__nfs_access_zap_cache(inode);
+	return -ENOENT;
 }
 
-void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set)
+static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry *set)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
-	struct nfs_access_entry *cache = &nfsi->cache_access;
+	struct rb_root *root_node = &nfsi->access_cache;
+	struct rb_node **p = &root_node->rb_node;
+	struct rb_node *parent = NULL;
+	struct nfs_access_entry *entry;
 
-	if (cache->cred != set->cred) {
-		if (cache->cred)
-			put_rpccred(cache->cred);
-		cache->cred = get_rpccred(set->cred);
-	}
-	/* FIXME: replace current access_cache BKL reliance with inode->i_lock */
 	spin_lock(&inode->i_lock);
-	nfsi->cache_validity &= ~NFS_INO_INVALID_ACCESS;
+	while (*p != NULL) {
+		parent = *p;
+		entry = rb_entry(parent, struct nfs_access_entry, rb_node);
+
+		if (set->cred < entry->cred)
+			p = &parent->rb_left;
+		else if (set->cred > entry->cred)
+			p = &parent->rb_right;
+		else
+			goto found;
+	}
+	rb_link_node(&set->rb_node, parent, p);
+	rb_insert_color(&set->rb_node, root_node);
+	list_add_tail(&set->lru, &nfsi->access_cache_entry_lru);
 	spin_unlock(&inode->i_lock);
+	return;
+found:
+	rb_replace_node(parent, &set->rb_node, root_node);
+	list_add_tail(&set->lru, &nfsi->access_cache_entry_lru);
+	list_del(&entry->lru);
+	spin_unlock(&inode->i_lock);
+	nfs_access_free_entry(entry);
+}
+
+void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set)
+{
+	struct nfs_access_entry *cache = kmalloc(sizeof(*cache), GFP_KERNEL);
+	if (cache == NULL)
+		return;
+	RB_CLEAR_NODE(&cache->rb_node);
 	cache->jiffies = set->jiffies;
+	cache->cred = get_rpccred(set->cred);
 	cache->mask = set->mask;
+
+	nfs_access_add_rbtree(inode, cache);
+
+	/* Update accounting */
+	smp_mb__before_atomic_inc();
+	atomic_long_inc(&nfs_access_nr_entries);
+	smp_mb__after_atomic_inc();
+
+	/* Add inode to global LRU list */
+	if (!test_and_set_bit(NFS_INO_ACL_LRU_SET, &NFS_FLAGS(inode))) {
+		spin_lock(&nfs_access_lru_lock);
+		list_add_tail(&NFS_I(inode)->access_cache_inode_lru, &nfs_access_lru_list);
+		spin_unlock(&nfs_access_lru_lock);
+	}
 }
 
 static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)

fs/nfs/file.c

@@ -111,7 +111,7 @@ nfs_file_open(struct inode *inode, struct file *filp)
 
 	nfs_inc_stats(inode, NFSIOS_VFSOPEN);
 	lock_kernel();
-	res = NFS_SERVER(inode)->rpc_ops->file_open(inode, filp);
+	res = NFS_PROTO(inode)->file_open(inode, filp);
 	unlock_kernel();
 	return res;
 }
@@ -157,7 +157,7 @@ force_reval:
 static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
 {
 	/* origin == SEEK_END => we must revalidate the cached file length */
-	if (origin == 2) {
+	if (origin == SEEK_END) {
 		struct inode *inode = filp->f_mapping->host;
 		int retval = nfs_revalidate_file_size(inode, filp);
 		if (retval < 0)

fs/nfs/getroot.c

@@ -0,0 +1,311 @@
+/* getroot.c: get the root dentry for an NFS mount
+ *
+ * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+#include <linux/time.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/stat.h>
+#include <linux/errno.h>
+#include <linux/unistd.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/stats.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_mount.h>
+#include <linux/nfs4_mount.h>
+#include <linux/lockd/bind.h>
+#include <linux/smp_lock.h>
+#include <linux/seq_file.h>
+#include <linux/mount.h>
+#include <linux/nfs_idmap.h>
+#include <linux/vfs.h>
+#include <linux/namei.h>
+#include <linux/namespace.h>
+#include <linux/security.h>
+
+#include <asm/system.h>
+#include <asm/uaccess.h>
+
+#include "nfs4_fs.h"
+#include "delegation.h"
+#include "internal.h"
+
+#define NFSDBG_FACILITY		NFSDBG_CLIENT
+#define NFS_PARANOIA 1
+
+/*
+ * get an NFS2/NFS3 root dentry from the root filehandle
+ */
+struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh)
+{
+	struct nfs_server *server = NFS_SB(sb);
+	struct nfs_fsinfo fsinfo;
+	struct nfs_fattr fattr;
+	struct dentry *mntroot;
+	struct inode *inode;
+	int error;
+
+	/* create a dummy root dentry with dummy inode for this superblock */
+	if (!sb->s_root) {
+		struct nfs_fh dummyfh;
+		struct dentry *root;
+		struct inode *iroot;
+
+		memset(&dummyfh, 0, sizeof(dummyfh));
+		memset(&fattr, 0, sizeof(fattr));
+		nfs_fattr_init(&fattr);
+		fattr.valid = NFS_ATTR_FATTR;
+		fattr.type = NFDIR;
+		fattr.mode = S_IFDIR | S_IRUSR | S_IWUSR;
+		fattr.nlink = 2;
+
+		iroot = nfs_fhget(sb, &dummyfh, &fattr);
+		if (IS_ERR(iroot))
+			return ERR_PTR(PTR_ERR(iroot));
+
+		root = d_alloc_root(iroot);
+		if (!root) {
+			iput(iroot);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		sb->s_root = root;
+	}
+
+	/* get the actual root for this mount */
+	fsinfo.fattr = &fattr;
+
+	error = server->nfs_client->rpc_ops->getroot(server, mntfh, &fsinfo);
+	if (error < 0) {
+		dprintk("nfs_get_root: getattr error = %d\n", -error);
+		return ERR_PTR(error);
+	}
+
+	inode = nfs_fhget(sb, mntfh, fsinfo.fattr);
+	if (IS_ERR(inode)) {
+		dprintk("nfs_get_root: get root inode failed\n");
+		return ERR_PTR(PTR_ERR(inode));
+	}
+
+	/* root dentries normally start off anonymous and get spliced in later
+	 * if the dentry tree reaches them; however if the dentry already
+	 * exists, we'll pick it up at this point and use it as the root
+	 */
+	mntroot = d_alloc_anon(inode);
+	if (!mntroot) {
+		iput(inode);
+		dprintk("nfs_get_root: get root dentry failed\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	security_d_instantiate(mntroot, inode);
+
+	if (!mntroot->d_op)
+		mntroot->d_op = server->nfs_client->rpc_ops->dentry_ops;
+
+	return mntroot;
+}
+
+#ifdef CONFIG_NFS_V4
+
+/*
+ * Do a simple pathwalk from the root FH of the server to the nominated target
+ * of the mountpoint
+ * - give error on symlinks
+ * - give error on ".." occurring in the path
+ * - follow traversals
+ */
+int nfs4_path_walk(struct nfs_server *server,
+		   struct nfs_fh *mntfh,
+		   const char *path)
+{
+	struct nfs_fsinfo fsinfo;
+	struct nfs_fattr fattr;
+	struct nfs_fh lastfh;
+	struct qstr name;
+	int ret;
+	//int referral_count = 0;
+
+	dprintk("--> nfs4_path_walk(,,%s)\n", path);
+
+	fsinfo.fattr = &fattr;
+	nfs_fattr_init(&fattr);
+
+	if (*path++ != '/') {
+		dprintk("nfs4_get_root: Path does not begin with a slash\n");
+		return -EINVAL;
+	}
+
+	/* Start by getting the root filehandle from the server */
+	ret = server->nfs_client->rpc_ops->getroot(server, mntfh, &fsinfo);
+	if (ret < 0) {
+		dprintk("nfs4_get_root: getroot error = %d\n", -ret);
+		return ret;
+	}
+
+	if (fattr.type != NFDIR) {
+		printk(KERN_ERR "nfs4_get_root:"
+		       " getroot encountered non-directory\n");
+		return -ENOTDIR;
+	}
+
+	if (fattr.valid & NFS_ATTR_FATTR_V4_REFERRAL) {
+		printk(KERN_ERR "nfs4_get_root:"
+		       " getroot obtained referral\n");
+		return -EREMOTE;
+	}
+
+next_component:
+	dprintk("Next: %s\n", path);
+
+	/* extract the next bit of the path */
+	if (!*path)
+		goto path_walk_complete;
+
+	name.name = path;
+	while (*path && *path != '/')
+		path++;
+	name.len = path - (const char *) name.name;
+
+eat_dot_dir:
+	while (*path == '/')
+		path++;
+
+	if (path[0] == '.' && (path[1] == '/' || !path[1])) {
+		path += 2;
+		goto eat_dot_dir;
+	}
+
+	if (path[0] == '.' && path[1] == '.' && (path[2] == '/' || !path[2])
+	    ) {
+		printk(KERN_ERR "nfs4_get_root:"
+		       " Mount path contains reference to \"..\"\n");
+		return -EINVAL;
+	}
+
+	/* lookup the next FH in the sequence */
+	memcpy(&lastfh, mntfh, sizeof(lastfh));
+
+	dprintk("LookupFH: %*.*s [%s]\n", name.len, name.len, name.name, path);
+
+	ret = server->nfs_client->rpc_ops->lookupfh(server, &lastfh, &name,
+						    mntfh, &fattr);
+	if (ret < 0) {
+		dprintk("nfs4_get_root: getroot error = %d\n", -ret);
+		return ret;
+	}
+
+	if (fattr.type != NFDIR) {
+		printk(KERN_ERR "nfs4_get_root:"
+		       " lookupfh encountered non-directory\n");
+		return -ENOTDIR;
+	}
+
+	if (fattr.valid & NFS_ATTR_FATTR_V4_REFERRAL) {
+		printk(KERN_ERR "nfs4_get_root:"
+		       " lookupfh obtained referral\n");
+		return -EREMOTE;
+	}
+
+	goto next_component;
+
+path_walk_complete:
+	memcpy(&server->fsid, &fattr.fsid, sizeof(server->fsid));
+	dprintk("<-- nfs4_path_walk() = 0\n");
+	return 0;
+}
+
+/*
+ * get an NFS4 root dentry from the root filehandle
+ */
+struct dentry *nfs4_get_root(struct super_block *sb, struct nfs_fh *mntfh)
+{
+	struct nfs_server *server = NFS_SB(sb);
+	struct nfs_fattr fattr;
+	struct dentry *mntroot;
+	struct inode *inode;
+	int error;
+
+	dprintk("--> nfs4_get_root()\n");
+
+	/* create a dummy root dentry with dummy inode for this superblock */
+	if (!sb->s_root) {
+		struct nfs_fh dummyfh;
+		struct dentry *root;
+		struct inode *iroot;
+
+		memset(&dummyfh, 0, sizeof(dummyfh));
+		memset(&fattr, 0, sizeof(fattr));
+		nfs_fattr_init(&fattr);
+		fattr.valid = NFS_ATTR_FATTR;
+		fattr.type = NFDIR;
+		fattr.mode = S_IFDIR | S_IRUSR | S_IWUSR;
+		fattr.nlink = 2;
+
+		iroot = nfs_fhget(sb, &dummyfh, &fattr);
+		if (IS_ERR(iroot))
+			return ERR_PTR(PTR_ERR(iroot));
+
+		root = d_alloc_root(iroot);
+		if (!root) {
+			iput(iroot);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		sb->s_root = root;
+	}
+
+	/* get the info about the server and filesystem */
+	error = nfs4_server_capabilities(server, mntfh);
+	if (error < 0) {
+		dprintk("nfs_get_root: getcaps error = %d\n",
+			-error);
+		return ERR_PTR(error);
+	}
+
+	/* get the actual root for this mount */
+	error = server->nfs_client->rpc_ops->getattr(server, mntfh, &fattr);
+	if (error < 0) {
+		dprintk("nfs_get_root: getattr error = %d\n", -error);
+		return ERR_PTR(error);
+	}
+
+	inode = nfs_fhget(sb, mntfh, &fattr);
+	if (IS_ERR(inode)) {
+		dprintk("nfs_get_root: get root inode failed\n");
+		return ERR_PTR(PTR_ERR(inode));
+	}
+
+	/* root dentries normally start off anonymous and get spliced in later
+	 * if the dentry tree reaches them; however if the dentry already
+	 * exists, we'll pick it up at this point and use it as the root
+	 */
+	mntroot = d_alloc_anon(inode);
+	if (!mntroot) {
+		iput(inode);
+		dprintk("nfs_get_root: get root dentry failed\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	security_d_instantiate(mntroot, inode);
+
+	if (!mntroot->d_op)
+		mntroot->d_op = server->nfs_client->rpc_ops->dentry_ops;
+
+	dprintk("<-- nfs4_get_root()\n");
+	return mntroot;
+}
+
+#endif /* CONFIG_NFS_V4 */

fs/nfs/idmap.c

@@ -57,6 +57,20 @@
 /* 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;
@@ -70,7 +84,6 @@ struct idmap_hashtable {
 };
 
 struct idmap {
-	char                  idmap_path[48];
 	struct dentry        *idmap_dentry;
 	wait_queue_head_t     idmap_wq;
 	struct idmap_msg      idmap_im;
@@ -94,24 +107,23 @@ static struct rpc_pipe_ops idmap_upcall_ops = {
         .destroy_msg    = idmap_pipe_destroy_msg,
 };
 
-void
-nfs_idmap_new(struct nfs4_client *clp)
+int
+nfs_idmap_new(struct nfs_client *clp)
 {
 	struct idmap *idmap;
+	int error;
 
-	if (clp->cl_idmap != NULL)
-		return;
-        if ((idmap = kzalloc(sizeof(*idmap), GFP_KERNEL)) == NULL)
-                return;
+	BUG_ON(clp->cl_idmap != NULL);
 
-	snprintf(idmap->idmap_path, sizeof(idmap->idmap_path),
-	    "%s/idmap", clp->cl_rpcclient->cl_pathname);
+        if ((idmap = kzalloc(sizeof(*idmap), GFP_KERNEL)) == NULL)
+                return -ENOMEM;
 
-        idmap->idmap_dentry = rpc_mkpipe(idmap->idmap_path,
+        idmap->idmap_dentry = rpc_mkpipe(clp->cl_rpcclient->cl_dentry, "idmap",
 	    idmap, &idmap_upcall_ops, 0);
         if (IS_ERR(idmap->idmap_dentry)) {
+		error = PTR_ERR(idmap->idmap_dentry);
 		kfree(idmap);
-		return;
+		return error;
 	}
 
         mutex_init(&idmap->idmap_lock);
@@ -121,10 +133,11 @@ nfs_idmap_new(struct nfs4_client *clp)
 	idmap->idmap_group_hash.h_type = IDMAP_TYPE_GROUP;
 
 	clp->cl_idmap = idmap;
+	return 0;
 }
 
 void
-nfs_idmap_delete(struct nfs4_client *clp)
+nfs_idmap_delete(struct nfs_client *clp)
 {
 	struct idmap *idmap = clp->cl_idmap;
 
@@ -477,27 +490,27 @@ static unsigned int fnvhash32(const void *buf, size_t buflen)
 	return (hash);
 }
 
-int nfs_map_name_to_uid(struct nfs4_client *clp, const char *name, size_t namelen, __u32 *uid)
+int nfs_map_name_to_uid(struct nfs_client *clp, const char *name, size_t namelen, __u32 *uid)
 {
 	struct idmap *idmap = clp->cl_idmap;
 
 	return nfs_idmap_id(idmap, &idmap->idmap_user_hash, name, namelen, uid);
 }
 
-int nfs_map_group_to_gid(struct nfs4_client *clp, const char *name, size_t namelen, __u32 *uid)
+int nfs_map_group_to_gid(struct nfs_client *clp, const char *name, size_t namelen, __u32 *uid)
 {
 	struct idmap *idmap = clp->cl_idmap;
 
 	return nfs_idmap_id(idmap, &idmap->idmap_group_hash, name, namelen, uid);
 }
 
-int nfs_map_uid_to_name(struct nfs4_client *clp, __u32 uid, char *buf)
+int nfs_map_uid_to_name(struct nfs_client *clp, __u32 uid, char *buf)
 {
 	struct idmap *idmap = clp->cl_idmap;
 
 	return nfs_idmap_name(idmap, &idmap->idmap_user_hash, uid, buf);
 }
-int nfs_map_gid_to_group(struct nfs4_client *clp, __u32 uid, char *buf)
+int nfs_map_gid_to_group(struct nfs_client *clp, __u32 uid, char *buf)
 {
 	struct idmap *idmap = clp->cl_idmap;
 

fs/nfs/inode.c

@@ -76,19 +76,14 @@ int nfs_write_inode(struct inode *inode, int sync)
 
 void nfs_clear_inode(struct inode *inode)
 {
-	struct nfs_inode *nfsi = NFS_I(inode);
-	struct rpc_cred *cred;
-
 	/*
 	 * The following should never happen...
 	 */
 	BUG_ON(nfs_have_writebacks(inode));
-	BUG_ON (!list_empty(&nfsi->open_files));
+	BUG_ON(!list_empty(&NFS_I(inode)->open_files));
+	BUG_ON(atomic_read(&NFS_I(inode)->data_updates) != 0);
 	nfs_zap_acl_cache(inode);
-	cred = nfsi->cache_access.cred;
-	if (cred)
-		put_rpccred(cred);
-	BUG_ON(atomic_read(&nfsi->data_updates) != 0);
+	nfs_access_zap_cache(inode);
 }
 
 /**
@@ -242,13 +237,13 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		/* Why so? Because we want revalidate for devices/FIFOs, and
 		 * that's precisely what we have in nfs_file_inode_operations.
 		 */
-		inode->i_op = NFS_SB(sb)->rpc_ops->file_inode_ops;
+		inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->file_inode_ops;
 		if (S_ISREG(inode->i_mode)) {
 			inode->i_fop = &nfs_file_operations;
 			inode->i_data.a_ops = &nfs_file_aops;
 			inode->i_data.backing_dev_info = &NFS_SB(sb)->backing_dev_info;
 		} else if (S_ISDIR(inode->i_mode)) {
-			inode->i_op = NFS_SB(sb)->rpc_ops->dir_inode_ops;
+			inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops;
 			inode->i_fop = &nfs_dir_operations;
 			if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS)
 			    && fattr->size <= NFS_LIMIT_READDIRPLUS)
@@ -290,7 +285,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
 		nfsi->attrtimeo_timestamp = jiffies;
 		memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
-		nfsi->cache_access.cred = NULL;
+		nfsi->access_cache = RB_ROOT;
 
 		unlock_new_inode(inode);
 	} else
@@ -722,13 +717,11 @@ void nfs_end_data_update(struct inode *inode)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 
-	if (!nfs_have_delegation(inode, FMODE_READ)) {
-		/* Directories and symlinks: invalidate page cache */
-		if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) {
-			spin_lock(&inode->i_lock);
-			nfsi->cache_validity |= NFS_INO_INVALID_DATA;
-			spin_unlock(&inode->i_lock);
-		}
+	/* Directories: invalidate page cache */
+	if (S_ISDIR(inode->i_mode)) {
+		spin_lock(&inode->i_lock);
+		nfsi->cache_validity |= NFS_INO_INVALID_DATA;
+		spin_unlock(&inode->i_lock);
 	}
 	nfsi->cache_change_attribute = jiffies;
 	atomic_dec(&nfsi->data_updates);
@@ -847,6 +840,12 @@ int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr)
  *
  * After an operation that has changed the inode metadata, mark the
  * attribute cache as being invalid, then try to update it.
+ *
+ * NB: if the server didn't return any post op attributes, this
+ * function will force the retrieval of attributes before the next
+ * NFS request.  Thus it should be used only for operations that
+ * are expected to change one or more attributes, to avoid
+ * unnecessary NFS requests and trips through nfs_update_inode().
  */
 int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 {
@@ -1025,7 +1024,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
  out_fileid:
 	printk(KERN_ERR "NFS: server %s error: fileid changed\n"
 		"fsid %s: expected fileid 0x%Lx, got 0x%Lx\n",
-		NFS_SERVER(inode)->hostname, inode->i_sb->s_id,
+		NFS_SERVER(inode)->nfs_client->cl_hostname, inode->i_sb->s_id,
 		(long long)nfsi->fileid, (long long)fattr->fileid);
 	goto out_err;
 }
@@ -1109,6 +1108,8 @@ static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags)
 		INIT_LIST_HEAD(&nfsi->dirty);
 		INIT_LIST_HEAD(&nfsi->commit);
 		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);
 		atomic_set(&nfsi->data_updates, 0);
 		nfsi->ndirty = 0;
@@ -1144,6 +1145,10 @@ static int __init init_nfs_fs(void)
 {
 	int err;
 
+	err = nfs_fs_proc_init();
+	if (err)
+		goto out5;
+
 	err = nfs_init_nfspagecache();
 	if (err)
 		goto out4;
@@ -1184,6 +1189,8 @@ out2:
 out3:
 	nfs_destroy_nfspagecache();
 out4:
+	nfs_fs_proc_exit();
+out5:
 	return err;
 }
 
@@ -1198,6 +1205,7 @@ static void __exit exit_nfs_fs(void)
 	rpc_proc_unregister("nfs");
 #endif
 	unregister_nfs_fs();
+	nfs_fs_proc_exit();
 }
 
 /* Not quite true; I just maintain it */

fs/nfs/internal.h

@@ -4,6 +4,18 @@
 
 #include <linux/mount.h>
 
+struct nfs_string;
+struct nfs_mount_data;
+struct nfs4_mount_data;
+
+/* Maximum number of readahead requests
+ * FIXME: this should really be a sysctl so that users may tune it to suit
+ *        their needs. People that do NFS over a slow network, might for
+ *        instance want to reduce it to something closer to 1 for improved
+ *        interactive response.
+ */
+#define NFS_MAX_READAHEAD	(RPC_DEF_SLOT_TABLE - 1)
+
 struct nfs_clone_mount {
 	const struct super_block *sb;
 	const struct dentry *dentry;
@@ -15,7 +27,40 @@ struct nfs_clone_mount {
 	rpc_authflavor_t authflavor;
 };
 
-/* namespace-nfs4.c */
+/* client.c */
+extern struct rpc_program nfs_program;
+
+extern void nfs_put_client(struct nfs_client *);
+extern struct nfs_client *nfs_find_client(const struct sockaddr_in *, int);
+extern struct nfs_server *nfs_create_server(const struct nfs_mount_data *,
+					    struct nfs_fh *);
+extern struct nfs_server *nfs4_create_server(const struct nfs4_mount_data *,
+					     const char *,
+					     const struct sockaddr_in *,
+					     const char *,
+					     const char *,
+					     rpc_authflavor_t,
+					     struct nfs_fh *);
+extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *,
+						      struct nfs_fh *);
+extern void nfs_free_server(struct nfs_server *server);
+extern struct nfs_server *nfs_clone_server(struct nfs_server *,
+					   struct nfs_fh *,
+					   struct nfs_fattr *);
+#ifdef CONFIG_PROC_FS
+extern int __init nfs_fs_proc_init(void);
+extern void nfs_fs_proc_exit(void);
+#else
+static inline int nfs_fs_proc_init(void)
+{
+	return 0;
+}
+static inline void nfs_fs_proc_exit(void)
+{
+}
+#endif
+
+/* nfs4namespace.c */
 #ifdef CONFIG_NFS_V4
 extern struct vfsmount *nfs_do_refmount(const struct vfsmount *mnt_parent, struct dentry *dentry);
 #else
@@ -46,6 +91,7 @@ extern void nfs_destroy_directcache(void);
 #endif
 
 /* nfs2xdr.c */
+extern int nfs_stat_to_errno(int);
 extern struct rpc_procinfo nfs_procedures[];
 extern u32 * nfs_decode_dirent(u32 *, struct nfs_entry *, int);
 
@@ -54,8 +100,9 @@ extern struct rpc_procinfo nfs3_procedures[];
 extern u32 *nfs3_decode_dirent(u32 *, struct nfs_entry *, int);
 
 /* nfs4xdr.c */
-extern int nfs_stat_to_errno(int);
+#ifdef CONFIG_NFS_V4
 extern u32 *nfs4_decode_dirent(u32 *p, struct nfs_entry *entry, int plus);
+#endif
 
 /* nfs4proc.c */
 #ifdef CONFIG_NFS_V4
@@ -66,6 +113,9 @@ extern int nfs4_proc_fs_locations(struct inode *dir, struct dentry *dentry,
 				  struct page *page);
 #endif
 
+/* dir.c */
+extern int nfs_access_cache_shrinker(int nr_to_scan, gfp_t gfp_mask);
+
 /* inode.c */
 extern struct inode *nfs_alloc_inode(struct super_block *sb);
 extern void nfs_destroy_inode(struct inode *);
@@ -76,10 +126,10 @@ extern void nfs4_clear_inode(struct inode *);
 #endif
 
 /* super.c */
-extern struct file_system_type nfs_referral_nfs4_fs_type;
-extern struct file_system_type clone_nfs_fs_type;
+extern struct file_system_type nfs_xdev_fs_type;
 #ifdef CONFIG_NFS_V4
-extern struct file_system_type clone_nfs4_fs_type;
+extern struct file_system_type nfs4_xdev_fs_type;
+extern struct file_system_type nfs4_referral_fs_type;
 #endif
 
 extern struct rpc_stat nfs_rpcstat;
@@ -88,30 +138,30 @@ extern int __init register_nfs_fs(void);
 extern void __exit unregister_nfs_fs(void);
 
 /* namespace.c */
-extern char *nfs_path(const char *base, const struct dentry *dentry,
+extern char *nfs_path(const char *base,
+		      const struct dentry *droot,
+		      const struct dentry *dentry,
 		      char *buffer, ssize_t buflen);
 
-/*
- * Determine the mount path as a string
- */
-static inline char *
-nfs4_path(const struct dentry *dentry, char *buffer, ssize_t buflen)
-{
+/* getroot.c */
+extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *);
 #ifdef CONFIG_NFS_V4
-	return nfs_path(NFS_SB(dentry->d_sb)->mnt_path, dentry, buffer, buflen);
-#else
-	return NULL;
+extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *);
+
+extern int nfs4_path_walk(struct nfs_server *server,
+			  struct nfs_fh *mntfh,
+			  const char *path);
 #endif
-}
 
 /*
  * Determine the device name as a string
  */
 static inline char *nfs_devname(const struct vfsmount *mnt_parent,
-			 const struct dentry *dentry,
-			 char *buffer, ssize_t buflen)
+				const struct dentry *dentry,
+				char *buffer, ssize_t buflen)
 {
-	return nfs_path(mnt_parent->mnt_devname, dentry, buffer, buflen);
+	return nfs_path(mnt_parent->mnt_devname, mnt_parent->mnt_root,
+			dentry, buffer, buflen);
 }
 
 /*
@@ -167,20 +217,3 @@ void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize)
 	if (sb->s_maxbytes > MAX_LFS_FILESIZE || sb->s_maxbytes <= 0)
 		sb->s_maxbytes = MAX_LFS_FILESIZE;
 }
-
-/*
- * Check if the string represents a "valid" IPv4 address
- */
-static inline int valid_ipaddr4(const char *buf)
-{
-	int rc, count, in[4];
-
-	rc = sscanf(buf, "%d.%d.%d.%d", &in[0], &in[1], &in[2], &in[3]);
-	if (rc != 4)
-		return -EINVAL;
-	for (count = 0; count < 4; count++) {
-		if (in[count] > 255)
-			return -EINVAL;
-	}
-	return 0;
-}

fs/nfs/mount_clnt.c

@@ -14,7 +14,6 @@
 #include <linux/net.h>
 #include <linux/in.h>
 #include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/xprt.h>
 #include <linux/sunrpc/sched.h>
 #include <linux/nfs_fs.h>
 
@@ -77,22 +76,19 @@ static struct rpc_clnt *
 mnt_create(char *hostname, struct sockaddr_in *srvaddr, int version,
 		int protocol)
 {
-	struct rpc_xprt	*xprt;
-	struct rpc_clnt	*clnt;
-
-	xprt = xprt_create_proto(protocol, srvaddr, NULL);
-	if (IS_ERR(xprt))
-		return (struct rpc_clnt *)xprt;
-
-	clnt = rpc_create_client(xprt, hostname,
-				&mnt_program, version,
-				RPC_AUTH_UNIX);
-	if (!IS_ERR(clnt)) {
-		clnt->cl_softrtry = 1;
-		clnt->cl_oneshot  = 1;
-		clnt->cl_intr = 1;
-	}
-	return clnt;
+	struct rpc_create_args args = {
+		.protocol	= protocol,
+		.address	= (struct sockaddr *)srvaddr,
+		.addrsize	= sizeof(*srvaddr),
+		.servername	= hostname,
+		.program	= &mnt_program,
+		.version	= version,
+		.authflavor	= RPC_AUTH_UNIX,
+		.flags		= (RPC_CLNT_CREATE_ONESHOT |
+				   RPC_CLNT_CREATE_INTR),
+	};
+
+	return rpc_create(&args);
 }
 
 /*

fs/nfs/namespace.c

@@ -2,6 +2,7 @@
  * linux/fs/nfs/namespace.c
  *
  * Copyright (C) 2005 Trond Myklebust <Trond.Myklebust@netapp.com>
+ * - Modified by David Howells <dhowells@redhat.com>
  *
  * NFS namespace
  */
@@ -28,6 +29,7 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ;
 /*
  * nfs_path - reconstruct the path given an arbitrary dentry
  * @base - arbitrary string to prepend to the path
+ * @droot - pointer to root dentry for mountpoint
  * @dentry - pointer to dentry
  * @buffer - result buffer
  * @buflen - length of buffer
@@ -38,7 +40,9 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ;
  * This is mainly for use in figuring out the path on the
  * server side when automounting on top of an existing partition.
  */
-char *nfs_path(const char *base, const struct dentry *dentry,
+char *nfs_path(const char *base,
+	       const struct dentry *droot,
+	       const struct dentry *dentry,
 	       char *buffer, ssize_t buflen)
 {
 	char *end = buffer+buflen;
@@ -47,7 +51,7 @@ char *nfs_path(const char *base, const struct dentry *dentry,
 	*--end = '\0';
 	buflen--;
 	spin_lock(&dcache_lock);
-	while (!IS_ROOT(dentry)) {
+	while (!IS_ROOT(dentry) && dentry != droot) {
 		namelen = dentry->d_name.len;
 		buflen -= namelen + 1;
 		if (buflen < 0)
@@ -96,15 +100,18 @@ static void * nfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
 	struct nfs_fattr fattr;
 	int err;
 
+	dprintk("--> nfs_follow_mountpoint()\n");
+
 	BUG_ON(IS_ROOT(dentry));
 	dprintk("%s: enter\n", __FUNCTION__);
 	dput(nd->dentry);
 	nd->dentry = dget(dentry);
-	if (d_mountpoint(nd->dentry))
-		goto out_follow;
+
 	/* Look it up again */
 	parent = dget_parent(nd->dentry);
-	err = server->rpc_ops->lookup(parent->d_inode, &nd->dentry->d_name, &fh, &fattr);
+	err = server->nfs_client->rpc_ops->lookup(parent->d_inode,
+						  &nd->dentry->d_name,
+						  &fh, &fattr);
 	dput(parent);
 	if (err != 0)
 		goto out_err;
@@ -132,6 +139,8 @@ static void * nfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
 	schedule_delayed_work(&nfs_automount_task, nfs_mountpoint_expiry_timeout);
 out:
 	dprintk("%s: done, returned %d\n", __FUNCTION__, err);
+
+	dprintk("<-- nfs_follow_mountpoint() = %d\n", err);
 	return ERR_PTR(err);
 out_err:
 	path_release(nd);
@@ -172,22 +181,23 @@ void nfs_release_automount_timer(void)
 /*
  * Clone a mountpoint of the appropriate type
  */
-static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server, char *devname,
+static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server,
+					   const char *devname,
 					   struct nfs_clone_mount *mountdata)
 {
 #ifdef CONFIG_NFS_V4
 	struct vfsmount *mnt = NULL;
-	switch (server->rpc_ops->version) {
+	switch (server->nfs_client->cl_nfsversion) {
 		case 2:
 		case 3:
-			mnt = vfs_kern_mount(&clone_nfs_fs_type, 0, devname, mountdata);
+			mnt = vfs_kern_mount(&nfs_xdev_fs_type, 0, devname, mountdata);
 			break;
 		case 4:
-			mnt = vfs_kern_mount(&clone_nfs4_fs_type, 0, devname, mountdata);
+			mnt = vfs_kern_mount(&nfs4_xdev_fs_type, 0, devname, mountdata);
 	}
 	return mnt;
 #else
-	return vfs_kern_mount(&clone_nfs_fs_type, 0, devname, mountdata);
+	return vfs_kern_mount(&nfs_xdev_fs_type, 0, devname, mountdata);
 #endif
 }
 
@@ -213,6 +223,8 @@ struct vfsmount *nfs_do_submount(const struct vfsmount *mnt_parent,
 	char *page = (char *) __get_free_page(GFP_USER);
 	char *devname;
 
+	dprintk("--> nfs_do_submount()\n");
+
 	dprintk("%s: submounting on %s/%s\n", __FUNCTION__,
 			dentry->d_parent->d_name.name,
 			dentry->d_name.name);
@@ -227,5 +239,7 @@ free_page:
 	free_page((unsigned long)page);
 out:
 	dprintk("%s: done\n", __FUNCTION__);
+
+	dprintk("<-- nfs_do_submount() = %p\n", mnt);
 	return mnt;
 }

fs/nfs/nfs2xdr.c

@@ -51,7 +51,7 @@
 #define NFS_createargs_sz	(NFS_diropargs_sz+NFS_sattr_sz)
 #define NFS_renameargs_sz	(NFS_diropargs_sz+NFS_diropargs_sz)
 #define NFS_linkargs_sz		(NFS_fhandle_sz+NFS_diropargs_sz)
-#define NFS_symlinkargs_sz	(NFS_diropargs_sz+NFS_path_sz+NFS_sattr_sz)
+#define NFS_symlinkargs_sz	(NFS_diropargs_sz+1+NFS_sattr_sz)
 #define NFS_readdirargs_sz	(NFS_fhandle_sz+2)
 
 #define NFS_attrstat_sz		(1+NFS_fattr_sz)
@@ -351,11 +351,26 @@ nfs_xdr_linkargs(struct rpc_rqst *req, u32 *p, struct nfs_linkargs *args)
 static int
 nfs_xdr_symlinkargs(struct rpc_rqst *req, u32 *p, struct nfs_symlinkargs *args)
 {
+	struct xdr_buf *sndbuf = &req->rq_snd_buf;
+	size_t pad;
+
 	p = xdr_encode_fhandle(p, args->fromfh);
 	p = xdr_encode_array(p, args->fromname, args->fromlen);
-	p = xdr_encode_array(p, args->topath, args->tolen);
+	*p++ = htonl(args->pathlen);
+	sndbuf->len = xdr_adjust_iovec(sndbuf->head, p);
+
+	xdr_encode_pages(sndbuf, args->pages, 0, args->pathlen);
+
+	/*
+	 * xdr_encode_pages may have added a few bytes to ensure the
+	 * pathname ends on a 4-byte boundary.  Start encoding the
+	 * attributes after the pad bytes.
+	 */
+	pad = sndbuf->tail->iov_len;
+	if (pad > 0)
+		p++;
 	p = xdr_encode_sattr(p, args->sattr);
-	req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+	sndbuf->len += xdr_adjust_iovec(sndbuf->tail, p) - pad;
 	return 0;
 }
 

fs/nfs/nfs3proc.c

@@ -81,7 +81,7 @@ do_proc_get_root(struct rpc_clnt *client, struct nfs_fh *fhandle,
 }
 
 /*
- * Bare-bones access to getattr: this is for nfs_read_super.
+ * Bare-bones access to getattr: this is for nfs_get_root/nfs_get_sb
  */
 static int
 nfs3_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
@@ -90,8 +90,8 @@ nfs3_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
 	int	status;
 
 	status = do_proc_get_root(server->client, fhandle, info);
-	if (status && server->client_sys != server->client)
-		status = do_proc_get_root(server->client_sys, fhandle, info);
+	if (status && server->nfs_client->cl_rpcclient != server->client)
+		status = do_proc_get_root(server->nfs_client->cl_rpcclient, fhandle, info);
 	return status;
 }
 
@@ -544,23 +544,23 @@ nfs3_proc_link(struct inode *inode, struct inode *dir, struct qstr *name)
 }
 
 static int
-nfs3_proc_symlink(struct inode *dir, struct qstr *name, struct qstr *path,
-		  struct iattr *sattr, struct nfs_fh *fhandle,
-		  struct nfs_fattr *fattr)
+nfs3_proc_symlink(struct inode *dir, struct dentry *dentry, struct page *page,
+		  unsigned int len, struct iattr *sattr)
 {
-	struct nfs_fattr	dir_attr;
+	struct nfs_fh fhandle;
+	struct nfs_fattr fattr, dir_attr;
 	struct nfs3_symlinkargs	arg = {
 		.fromfh		= NFS_FH(dir),
-		.fromname	= name->name,
-		.fromlen	= name->len,
-		.topath		= path->name,
-		.tolen		= path->len,
+		.fromname	= dentry->d_name.name,
+		.fromlen	= dentry->d_name.len,
+		.pages		= &page,
+		.pathlen	= len,
 		.sattr		= sattr
 	};
 	struct nfs3_diropres	res = {
 		.dir_attr	= &dir_attr,
-		.fh		= fhandle,
-		.fattr		= fattr
+		.fh		= &fhandle,
+		.fattr		= &fattr
 	};
 	struct rpc_message msg = {
 		.rpc_proc	= &nfs3_procedures[NFS3PROC_SYMLINK],
@@ -569,13 +569,19 @@ nfs3_proc_symlink(struct inode *dir, struct qstr *name, struct qstr *path,
 	};
 	int			status;
 
-	if (path->len > NFS3_MAXPATHLEN)
+	if (len > NFS3_MAXPATHLEN)
 		return -ENAMETOOLONG;
-	dprintk("NFS call  symlink %s -> %s\n", name->name, path->name);
+
+	dprintk("NFS call  symlink %s\n", dentry->d_name.name);
+
 	nfs_fattr_init(&dir_attr);
-	nfs_fattr_init(fattr);
+	nfs_fattr_init(&fattr);
 	status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
 	nfs_post_op_update_inode(dir, &dir_attr);
+	if (status != 0)
+		goto out;
+	status = nfs_instantiate(dentry, &fhandle, &fattr);
+out:
 	dprintk("NFS reply symlink: %d\n", status);
 	return status;
 }
@@ -785,7 +791,7 @@ nfs3_proc_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle,
 
 	dprintk("NFS call  fsinfo\n");
 	nfs_fattr_init(info->fattr);
-	status = rpc_call_sync(server->client_sys, &msg, 0);
+	status = rpc_call_sync(server->nfs_client->cl_rpcclient, &msg, 0);
 	dprintk("NFS reply fsinfo: %d\n", status);
 	return status;
 }
@@ -886,7 +892,7 @@ nfs3_proc_lock(struct file *filp, int cmd, struct file_lock *fl)
 	return nlmclnt_proc(filp->f_dentry->d_inode, cmd, fl);
 }
 
-struct nfs_rpc_ops	nfs_v3_clientops = {
+const struct nfs_rpc_ops nfs_v3_clientops = {
 	.version	= 3,			/* protocol version */
 	.dentry_ops	= &nfs_dentry_operations,
 	.dir_inode_ops	= &nfs3_dir_inode_operations,

fs/nfs/nfs3xdr.c

@@ -56,7 +56,7 @@
 #define NFS3_writeargs_sz	(NFS3_fh_sz+5)
 #define NFS3_createargs_sz	(NFS3_diropargs_sz+NFS3_sattr_sz)
 #define NFS3_mkdirargs_sz	(NFS3_diropargs_sz+NFS3_sattr_sz)
-#define NFS3_symlinkargs_sz	(NFS3_diropargs_sz+NFS3_path_sz+NFS3_sattr_sz)
+#define NFS3_symlinkargs_sz	(NFS3_diropargs_sz+1+NFS3_sattr_sz)
 #define NFS3_mknodargs_sz	(NFS3_diropargs_sz+2+NFS3_sattr_sz)
 #define NFS3_renameargs_sz	(NFS3_diropargs_sz+NFS3_diropargs_sz)
 #define NFS3_linkargs_sz		(NFS3_fh_sz+NFS3_diropargs_sz)
@@ -398,8 +398,11 @@ nfs3_xdr_symlinkargs(struct rpc_rqst *req, u32 *p, struct nfs3_symlinkargs *args
 	p = xdr_encode_fhandle(p, args->fromfh);
 	p = xdr_encode_array(p, args->fromname, args->fromlen);
 	p = xdr_encode_sattr(p, args->sattr);
-	p = xdr_encode_array(p, args->topath, args->tolen);
+	*p++ = htonl(args->pathlen);
 	req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+
+	/* Copy the page */
+	xdr_encode_pages(&req->rq_snd_buf, args->pages, 0, args->pathlen);
 	return 0;
 }
 

fs/nfs/nfs4_fs.h

@@ -42,55 +42,6 @@ enum nfs4_client_state {
 	NFS4CLNT_LEASE_EXPIRED,
 };
 
-/*
- * The nfs4_client identifies our client state to the server.
- */
-struct nfs4_client {
-	struct list_head	cl_servers;	/* Global list of servers */
-	struct in_addr		cl_addr;	/* Server identifier */
-	u64			cl_clientid;	/* constant */
-	nfs4_verifier		cl_confirm;
-	unsigned long		cl_state;
-
-	u32			cl_lockowner_id;
-
-	/*
-	 * The following rwsem ensures exclusive access to the server
-	 * while we recover the state following a lease expiration.
-	 */
-	struct rw_semaphore	cl_sem;
-
-	struct list_head	cl_delegations;
-	struct list_head	cl_state_owners;
-	struct list_head	cl_unused;
-	int			cl_nunused;
-	spinlock_t		cl_lock;
-	atomic_t		cl_count;
-
-	struct rpc_clnt *	cl_rpcclient;
-
-	struct list_head	cl_superblocks;	/* List of nfs_server structs */
-
-	unsigned long		cl_lease_time;
-	unsigned long		cl_last_renewal;
-	struct work_struct	cl_renewd;
-	struct work_struct	cl_recoverd;
-
-	struct rpc_wait_queue	cl_rpcwaitq;
-
-	/* used for the setclientid verifier */
-	struct timespec		cl_boot_time;
-
-	/* idmapper */
-	struct idmap *		cl_idmap;
-
-	/* Our own IP address, as a null-terminated string.
-	 * This is used to generate the clientid, and the callback address.
-	 */
-	char			cl_ipaddr[16];
-	unsigned char		cl_id_uniquifier;
-};
-
 /*
  * struct rpc_sequence ensures that RPC calls are sent in the exact
  * order that they appear on the list.
@@ -127,7 +78,7 @@ static inline void nfs_confirm_seqid(struct nfs_seqid_counter *seqid, int status
 struct nfs4_state_owner {
 	spinlock_t	     so_lock;
 	struct list_head     so_list;	 /* per-clientid list of state_owners */
-	struct nfs4_client   *so_client;
+	struct nfs_client    *so_client;
 	u32                  so_id;      /* 32-bit identifier, unique */
 	atomic_t	     so_count;
 
@@ -210,10 +161,10 @@ extern ssize_t nfs4_listxattr(struct dentry *, char *, size_t);
 
 /* nfs4proc.c */
 extern int nfs4_map_errors(int err);
-extern int nfs4_proc_setclientid(struct nfs4_client *, u32, unsigned short, struct rpc_cred *);
-extern int nfs4_proc_setclientid_confirm(struct nfs4_client *, struct rpc_cred *);
-extern int nfs4_proc_async_renew(struct nfs4_client *, struct rpc_cred *);
-extern int nfs4_proc_renew(struct nfs4_client *, struct rpc_cred *);
+extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *);
+extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct rpc_cred *);
+extern int nfs4_proc_async_renew(struct nfs_client *, struct rpc_cred *);
+extern int nfs4_proc_renew(struct nfs_client *, struct rpc_cred *);
 extern int nfs4_do_close(struct inode *inode, struct nfs4_state *state);
 extern struct dentry *nfs4_atomic_open(struct inode *, struct dentry *, struct nameidata *);
 extern int nfs4_open_revalidate(struct inode *, struct dentry *, int, struct nameidata *);
@@ -231,19 +182,14 @@ extern const u32 nfs4_fsinfo_bitmap[2];
 extern const u32 nfs4_fs_locations_bitmap[2];
 
 /* nfs4renewd.c */
-extern void nfs4_schedule_state_renewal(struct nfs4_client *);
+extern void nfs4_schedule_state_renewal(struct nfs_client *);
 extern void nfs4_renewd_prepare_shutdown(struct nfs_server *);
-extern void nfs4_kill_renewd(struct nfs4_client *);
+extern void nfs4_kill_renewd(struct nfs_client *);
 extern void nfs4_renew_state(void *);
 
 /* nfs4state.c */
-extern void init_nfsv4_state(struct nfs_server *);
-extern void destroy_nfsv4_state(struct nfs_server *);
-extern struct nfs4_client *nfs4_get_client(struct in_addr *);
-extern void nfs4_put_client(struct nfs4_client *clp);
-extern struct nfs4_client *nfs4_find_client(struct in_addr *);
-struct rpc_cred *nfs4_get_renew_cred(struct nfs4_client *clp);
-extern u32 nfs4_alloc_lockowner_id(struct nfs4_client *);
+struct rpc_cred *nfs4_get_renew_cred(struct nfs_client *clp);
+extern u32 nfs4_alloc_lockowner_id(struct nfs_client *);
 
 extern struct nfs4_state_owner * nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *);
 extern void nfs4_put_state_owner(struct nfs4_state_owner *);
@@ -252,7 +198,7 @@ extern struct nfs4_state * nfs4_get_open_state(struct inode *, struct nfs4_state
 extern void nfs4_put_open_state(struct nfs4_state *);
 extern void nfs4_close_state(struct nfs4_state *, mode_t);
 extern void nfs4_state_set_mode_locked(struct nfs4_state *, mode_t);
-extern void nfs4_schedule_state_recovery(struct nfs4_client *);
+extern void nfs4_schedule_state_recovery(struct nfs_client *);
 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);
@@ -276,10 +222,6 @@ extern struct svc_version nfs4_callback_version1;
 
 #else
 
-#define init_nfsv4_state(server)  do { } while (0)
-#define destroy_nfsv4_state(server)       do { } while (0)
-#define nfs4_put_state_owner(inode, owner) do { } while (0)
-#define nfs4_put_open_state(state) do { } while (0)
 #define nfs4_close_state(a, b) do { } while (0)
 
 #endif /* CONFIG_NFS_V4 */

fs/nfs/nfs4namespace.c

@@ -2,6 +2,7 @@
  * linux/fs/nfs/nfs4namespace.c
  *
  * Copyright (C) 2005 Trond Myklebust <Trond.Myklebust@netapp.com>
+ * - Modified by David Howells <dhowells@redhat.com>
  *
  * NFSv4 namespace
  */
@@ -23,7 +24,7 @@
 /*
  * Check if fs_root is valid
  */
-static inline char *nfs4_pathname_string(struct nfs4_pathname *pathname,
+static inline char *nfs4_pathname_string(const struct nfs4_pathname *pathname,
 					 char *buffer, ssize_t buflen)
 {
 	char *end = buffer + buflen;
@@ -34,7 +35,7 @@ static inline char *nfs4_pathname_string(struct nfs4_pathname *pathname,
 
 	n = pathname->ncomponents;
 	while (--n >= 0) {
-		struct nfs4_string *component = &pathname->components[n];
+		const struct nfs4_string *component = &pathname->components[n];
 		buflen -= component->len + 1;
 		if (buflen < 0)
 			goto Elong;
@@ -47,6 +48,68 @@ Elong:
 	return ERR_PTR(-ENAMETOOLONG);
 }
 
+/*
+ * Determine the mount path as a string
+ */
+static char *nfs4_path(const struct vfsmount *mnt_parent,
+		       const struct dentry *dentry,
+		       char *buffer, ssize_t buflen)
+{
+	const char *srvpath;
+
+	srvpath = strchr(mnt_parent->mnt_devname, ':');
+	if (srvpath)
+		srvpath++;
+	else
+		srvpath = mnt_parent->mnt_devname;
+
+	return nfs_path(srvpath, mnt_parent->mnt_root, dentry, buffer, buflen);
+}
+
+/*
+ * Check that fs_locations::fs_root [RFC3530 6.3] is a prefix for what we
+ * believe to be the server path to this dentry
+ */
+static int nfs4_validate_fspath(const struct vfsmount *mnt_parent,
+				const struct dentry *dentry,
+				const struct nfs4_fs_locations *locations,
+				char *page, char *page2)
+{
+	const char *path, *fs_path;
+
+	path = nfs4_path(mnt_parent, dentry, page, PAGE_SIZE);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+
+	fs_path = nfs4_pathname_string(&locations->fs_path, page2, PAGE_SIZE);
+	if (IS_ERR(fs_path))
+		return PTR_ERR(fs_path);
+
+	if (strncmp(path, fs_path, strlen(fs_path)) != 0) {
+		dprintk("%s: path %s does not begin with fsroot %s\n",
+			__FUNCTION__, path, fs_path);
+		return -ENOENT;
+	}
+
+	return 0;
+}
+
+/*
+ * Check if the string represents a "valid" IPv4 address
+ */
+static inline int valid_ipaddr4(const char *buf)
+{
+	int rc, count, in[4];
+
+	rc = sscanf(buf, "%d.%d.%d.%d", &in[0], &in[1], &in[2], &in[3]);
+	if (rc != 4)
+		return -EINVAL;
+	for (count = 0; count < 4; count++) {
+		if (in[count] > 255)
+			return -EINVAL;
+	}
+	return 0;
+}
 
 /**
  * nfs_follow_referral - set up mountpoint when hitting a referral on moved error
@@ -60,7 +123,7 @@ Elong:
  */
 static struct vfsmount *nfs_follow_referral(const struct vfsmount *mnt_parent,
 					    const struct dentry *dentry,
-					    struct nfs4_fs_locations *locations)
+					    const struct nfs4_fs_locations *locations)
 {
 	struct vfsmount *mnt = ERR_PTR(-ENOENT);
 	struct nfs_clone_mount mountdata = {
@@ -68,10 +131,9 @@ static struct vfsmount *nfs_follow_referral(const struct vfsmount *mnt_parent,
 		.dentry = dentry,
 		.authflavor = NFS_SB(mnt_parent->mnt_sb)->client->cl_auth->au_flavor,
 	};
-	char *page, *page2;
-	char *path, *fs_path;
+	char *page = NULL, *page2 = NULL;
 	char *devname;
-	int loc, s;
+	int loc, s, error;
 
 	if (locations == NULL || locations->nlocations <= 0)
 		goto out;
@@ -79,36 +141,30 @@ static struct vfsmount *nfs_follow_referral(const struct vfsmount *mnt_parent,
 	dprintk("%s: referral at %s/%s\n", __FUNCTION__,
 		dentry->d_parent->d_name.name, dentry->d_name.name);
 
-	/* Ensure fs path is a prefix of current dentry path */
 	page = (char *) __get_free_page(GFP_USER);
-	if (page == NULL)
+	if (!page)
 		goto out;
+
 	page2 = (char *) __get_free_page(GFP_USER);
-	if (page2 == NULL)
+	if (!page2)
 		goto out;
 
-	path = nfs4_path(dentry, page, PAGE_SIZE);
-	if (IS_ERR(path))
-		goto out_free;
-
-	fs_path = nfs4_pathname_string(&locations->fs_path, page2, PAGE_SIZE);
-	if (IS_ERR(fs_path))
-		goto out_free;
-
-	if (strncmp(path, fs_path, strlen(fs_path)) != 0) {
-		dprintk("%s: path %s does not begin with fsroot %s\n", __FUNCTION__, path, fs_path);
-		goto out_free;
+	/* Ensure fs path is a prefix of current dentry path */
+	error = nfs4_validate_fspath(mnt_parent, dentry, locations, page, page2);
+	if (error < 0) {
+		mnt = ERR_PTR(error);
+		goto out;
 	}
 
 	devname = nfs_devname(mnt_parent, dentry, page, PAGE_SIZE);
 	if (IS_ERR(devname)) {
 		mnt = (struct vfsmount *)devname;
-		goto out_free;
+		goto out;
 	}
 
 	loc = 0;
 	while (loc < locations->nlocations && IS_ERR(mnt)) {
-		struct nfs4_fs_location *location = &locations->locations[loc];
+		const struct nfs4_fs_location *location = &locations->locations[loc];
 		char *mnt_path;
 
 		if (location == NULL || location->nservers <= 0 ||
@@ -140,7 +196,7 @@ static struct vfsmount *nfs_follow_referral(const struct vfsmount *mnt_parent,
 			addr.sin_port = htons(NFS_PORT);
 			mountdata.addr = &addr;
 
-			mnt = vfs_kern_mount(&nfs_referral_nfs4_fs_type, 0, devname, &mountdata);
+			mnt = vfs_kern_mount(&nfs4_referral_fs_type, 0, devname, &mountdata);
 			if (!IS_ERR(mnt)) {
 				break;
 			}
@@ -149,10 +205,9 @@ static struct vfsmount *nfs_follow_referral(const struct vfsmount *mnt_parent,
 		loc++;
 	}
 
-out_free:
-	free_page((unsigned long)page);
-	free_page((unsigned long)page2);
 out:
+	free_page((unsigned long) page);
+	free_page((unsigned long) page2);
 	dprintk("%s: done\n", __FUNCTION__);
 	return mnt;
 }
@@ -165,7 +220,7 @@ out:
  */
 struct vfsmount *nfs_do_refmount(const struct vfsmount *mnt_parent, struct dentry *dentry)
 {
-	struct vfsmount *mnt = ERR_PTR(-ENOENT);
+	struct vfsmount *mnt = ERR_PTR(-ENOMEM);
 	struct dentry *parent;
 	struct nfs4_fs_locations *fs_locations = NULL;
 	struct page *page;
@@ -183,11 +238,16 @@ struct vfsmount *nfs_do_refmount(const struct vfsmount *mnt_parent, struct dentr
 		goto out_free;
 
 	/* Get locations */
+	mnt = ERR_PTR(-ENOENT);
+
 	parent = dget_parent(dentry);
-	dprintk("%s: getting locations for %s/%s\n", __FUNCTION__, parent->d_name.name, dentry->d_name.name);
+	dprintk("%s: getting locations for %s/%s\n",
+		__FUNCTION__, parent->d_name.name, dentry->d_name.name);
+
 	err = nfs4_proc_fs_locations(parent->d_inode, dentry, fs_locations, page);
 	dput(parent);
-	if (err != 0 || fs_locations->nlocations <= 0 ||
+	if (err != 0 ||
+	    fs_locations->nlocations <= 0 ||
 	    fs_locations->fs_path.ncomponents <= 0)
 		goto out_free;
 

fs/nfs/nfs4proc.c

@@ -55,7 +55,7 @@
 
 #define NFSDBG_FACILITY		NFSDBG_PROC
 
-#define NFS4_POLL_RETRY_MIN	(1*HZ)
+#define NFS4_POLL_RETRY_MIN	(HZ/10)
 #define NFS4_POLL_RETRY_MAX	(15*HZ)
 
 struct nfs4_opendata;
@@ -64,7 +64,7 @@ static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinf
 static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *);
 static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry);
 static int nfs4_handle_exception(const struct nfs_server *server, int errorcode, struct nfs4_exception *exception);
-static int nfs4_wait_clnt_recover(struct rpc_clnt *clnt, struct nfs4_client *clp);
+static int nfs4_wait_clnt_recover(struct rpc_clnt *clnt, struct nfs_client *clp);
 
 /* Prevent leaks of NFSv4 errors into userland */
 int nfs4_map_errors(int err)
@@ -195,7 +195,7 @@ static void nfs4_setup_readdir(u64 cookie, u32 *verifier, struct dentry *dentry,
 
 static void renew_lease(const struct nfs_server *server, unsigned long timestamp)
 {
-	struct nfs4_client *clp = server->nfs4_state;
+	struct nfs_client *clp = server->nfs_client;
 	spin_lock(&clp->cl_lock);
 	if (time_before(clp->cl_last_renewal,timestamp))
 		clp->cl_last_renewal = timestamp;
@@ -252,7 +252,7 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
 	atomic_inc(&sp->so_count);
 	p->o_arg.fh = NFS_FH(dir);
 	p->o_arg.open_flags = flags,
-	p->o_arg.clientid = server->nfs4_state->cl_clientid;
+	p->o_arg.clientid = server->nfs_client->cl_clientid;
 	p->o_arg.id = sp->so_id;
 	p->o_arg.name = &dentry->d_name;
 	p->o_arg.server = server;
@@ -550,7 +550,7 @@ int nfs4_open_delegation_recall(struct dentry *dentry, struct nfs4_state *state)
 			case -NFS4ERR_STALE_STATEID:
 			case -NFS4ERR_EXPIRED:
 				/* Don't recall a delegation if it was lost */
-				nfs4_schedule_state_recovery(server->nfs4_state);
+				nfs4_schedule_state_recovery(server->nfs_client);
 				return err;
 		}
 		err = nfs4_handle_exception(server, err, &exception);
@@ -758,7 +758,7 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
 	}
 	nfs_confirm_seqid(&data->owner->so_seqid, 0);
 	if (!(o_res->f_attr->valid & NFS_ATTR_FATTR))
-		return server->rpc_ops->getattr(server, &o_res->fh, o_res->f_attr);
+		return server->nfs_client->rpc_ops->getattr(server, &o_res->fh, o_res->f_attr);
 	return 0;
 }
 
@@ -792,11 +792,18 @@ out:
 
 int nfs4_recover_expired_lease(struct nfs_server *server)
 {
-	struct nfs4_client *clp = server->nfs4_state;
+	struct nfs_client *clp = server->nfs_client;
+	int ret;
 
-	if (test_and_clear_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
+	for (;;) {
+		ret = nfs4_wait_clnt_recover(server->client, clp);
+		if (ret != 0)
+			return ret;
+		if (!test_and_clear_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
+			break;
 		nfs4_schedule_state_recovery(clp);
-	return nfs4_wait_clnt_recover(server->client, clp);
+	}
+	return 0;
 }
 
 /*
@@ -867,7 +874,7 @@ static int _nfs4_open_delegated(struct inode *inode, int flags, struct rpc_cred
 {
 	struct nfs_delegation *delegation;
 	struct nfs_server *server = NFS_SERVER(inode);
-	struct nfs4_client *clp = server->nfs4_state;
+	struct nfs_client *clp = server->nfs_client;
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs4_state_owner *sp = NULL;
 	struct nfs4_state *state = NULL;
@@ -953,7 +960,7 @@ static int _nfs4_do_open(struct inode *dir, struct dentry *dentry, int flags, st
 	struct nfs4_state_owner  *sp;
 	struct nfs4_state     *state = NULL;
 	struct nfs_server       *server = NFS_SERVER(dir);
-	struct nfs4_client *clp = server->nfs4_state;
+	struct nfs_client *clp = server->nfs_client;
 	struct nfs4_opendata *opendata;
 	int                     status;
 
@@ -1133,7 +1140,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 			break;
 		case -NFS4ERR_STALE_STATEID:
 		case -NFS4ERR_EXPIRED:
-			nfs4_schedule_state_recovery(server->nfs4_state);
+			nfs4_schedule_state_recovery(server->nfs_client);
 			break;
 		default:
 			if (nfs4_async_handle_error(task, server) == -EAGAIN) {
@@ -1268,7 +1275,7 @@ nfs4_atomic_open(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
 		BUG_ON(nd->intent.open.flags & O_CREAT);
 	}
 
-	cred = rpcauth_lookupcred(NFS_SERVER(dir)->client->cl_auth, 0);
+	cred = rpcauth_lookupcred(NFS_CLIENT(dir)->cl_auth, 0);
 	if (IS_ERR(cred))
 		return (struct dentry *)cred;
 	state = nfs4_do_open(dir, dentry, nd->intent.open.flags, &attr, cred);
@@ -1291,7 +1298,7 @@ nfs4_open_revalidate(struct inode *dir, struct dentry *dentry, int openflags, st
 	struct rpc_cred *cred;
 	struct nfs4_state *state;
 
-	cred = rpcauth_lookupcred(NFS_SERVER(dir)->client->cl_auth, 0);
+	cred = rpcauth_lookupcred(NFS_CLIENT(dir)->cl_auth, 0);
 	if (IS_ERR(cred))
 		return PTR_ERR(cred);
 	state = nfs4_open_delegated(dentry->d_inode, openflags, cred);
@@ -1393,70 +1400,19 @@ static int nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle,
 	return err;
 }
 
+/*
+ * get the file handle for the "/" directory on the server
+ */
 static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
-		struct nfs_fsinfo *info)
+			      struct nfs_fsinfo *info)
 {
-	struct nfs_fattr *	fattr = info->fattr;
-	unsigned char *		p;
-	struct qstr		q;
-	struct nfs4_lookup_arg args = {
-		.dir_fh = fhandle,
-		.name = &q,
-		.bitmask = nfs4_fattr_bitmap,
-	};
-	struct nfs4_lookup_res res = {
-		.server = server,
-		.fattr = fattr,
-		.fh = fhandle,
-	};
-	struct rpc_message msg = {
-		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LOOKUP],
-		.rpc_argp = &args,
-		.rpc_resp = &res,
-	};
 	int status;
 
-	/*
-	 * Now we do a separate LOOKUP for each component of the mount path.
-	 * The LOOKUPs are done separately so that we can conveniently
-	 * catch an ERR_WRONGSEC if it occurs along the way...
-	 */
 	status = nfs4_lookup_root(server, fhandle, info);
-	if (status)
-		goto out;
-
-	p = server->mnt_path;
-	for (;;) {
-		struct nfs4_exception exception = { };
-
-		while (*p == '/')
-			p++;
-		if (!*p)
-			break;
-		q.name = p;
-		while (*p && (*p != '/'))
-			p++;
-		q.len = p - q.name;
-
-		do {
-			nfs_fattr_init(fattr);
-			status = nfs4_handle_exception(server,
-					rpc_call_sync(server->client, &msg, 0),
-					&exception);
-		} while (exception.retry);
-		if (status == 0)
-			continue;
-		if (status == -ENOENT) {
-			printk(KERN_NOTICE "NFS: mount path %s does not exist!\n", server->mnt_path);
-			printk(KERN_NOTICE "NFS: suggestion: try mounting '/' instead.\n");
-		}
-		break;
-	}
 	if (status == 0)
 		status = nfs4_server_capabilities(server, fhandle);
 	if (status == 0)
 		status = nfs4_do_fsinfo(server, fhandle, info);
-out:
 	return nfs4_map_errors(status);
 }
 
@@ -1565,7 +1521,7 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 
 	nfs_fattr_init(fattr);
 	
-	cred = rpcauth_lookupcred(NFS_SERVER(inode)->client->cl_auth, 0);
+	cred = rpcauth_lookupcred(NFS_CLIENT(inode)->cl_auth, 0);
 	if (IS_ERR(cred))
 		return PTR_ERR(cred);
 
@@ -1583,6 +1539,52 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 	return status;
 }
 
+static int _nfs4_proc_lookupfh(struct nfs_server *server, struct nfs_fh *dirfh,
+		struct qstr *name, struct nfs_fh *fhandle,
+		struct nfs_fattr *fattr)
+{
+	int		       status;
+	struct nfs4_lookup_arg args = {
+		.bitmask = server->attr_bitmask,
+		.dir_fh = dirfh,
+		.name = name,
+	};
+	struct nfs4_lookup_res res = {
+		.server = server,
+		.fattr = fattr,
+		.fh = fhandle,
+	};
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LOOKUP],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+	};
+
+	nfs_fattr_init(fattr);
+
+	dprintk("NFS call  lookupfh %s\n", name->name);
+	status = rpc_call_sync(server->client, &msg, 0);
+	dprintk("NFS reply lookupfh: %d\n", status);
+	if (status == -NFS4ERR_MOVED)
+		status = -EREMOTE;
+	return status;
+}
+
+static int nfs4_proc_lookupfh(struct nfs_server *server, struct nfs_fh *dirfh,
+			      struct qstr *name, struct nfs_fh *fhandle,
+			      struct nfs_fattr *fattr)
+{
+	struct nfs4_exception exception = { };
+	int err;
+	do {
+		err = nfs4_handle_exception(server,
+				_nfs4_proc_lookupfh(server, dirfh, name,
+						    fhandle, fattr),
+				&exception);
+	} while (exception.retry);
+	return err;
+}
+
 static int _nfs4_proc_lookup(struct inode *dir, struct qstr *name,
 		struct nfs_fh *fhandle, struct nfs_fattr *fattr)
 {
@@ -1881,7 +1883,7 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
 	struct rpc_cred *cred;
 	int status = 0;
 
-	cred = rpcauth_lookupcred(NFS_SERVER(dir)->client->cl_auth, 0);
+	cred = rpcauth_lookupcred(NFS_CLIENT(dir)->cl_auth, 0);
 	if (IS_ERR(cred)) {
 		status = PTR_ERR(cred);
 		goto out;
@@ -2089,24 +2091,24 @@ static int nfs4_proc_link(struct inode *inode, struct inode *dir, struct qstr *n
 	return err;
 }
 
-static int _nfs4_proc_symlink(struct inode *dir, struct qstr *name,
-		struct qstr *path, struct iattr *sattr, struct nfs_fh *fhandle,
-		struct nfs_fattr *fattr)
+static int _nfs4_proc_symlink(struct inode *dir, struct dentry *dentry,
+		struct page *page, unsigned int len, struct iattr *sattr)
 {
 	struct nfs_server *server = NFS_SERVER(dir);
-	struct nfs_fattr dir_fattr;
+	struct nfs_fh fhandle;
+	struct nfs_fattr fattr, dir_fattr;
 	struct nfs4_create_arg arg = {
 		.dir_fh = NFS_FH(dir),
 		.server = server,
-		.name = name,
+		.name = &dentry->d_name,
 		.attrs = sattr,
 		.ftype = NF4LNK,
 		.bitmask = server->attr_bitmask,
 	};
 	struct nfs4_create_res res = {
 		.server = server,
-		.fh = fhandle,
-		.fattr = fattr,
+		.fh = &fhandle,
+		.fattr = &fattr,
 		.dir_fattr = &dir_fattr,
 	};
 	struct rpc_message msg = {
@@ -2116,29 +2118,32 @@ static int _nfs4_proc_symlink(struct inode *dir, struct qstr *name,
 	};
 	int			status;
 
-	if (path->len > NFS4_MAXPATHLEN)
+	if (len > NFS4_MAXPATHLEN)
 		return -ENAMETOOLONG;
-	arg.u.symlink = path;
-	nfs_fattr_init(fattr);
+
+	arg.u.symlink.pages = &page;
+	arg.u.symlink.len = len;
+	nfs_fattr_init(&fattr);
 	nfs_fattr_init(&dir_fattr);
 	
 	status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
-	if (!status)
+	if (!status) {
 		update_changeattr(dir, &res.dir_cinfo);
-	nfs_post_op_update_inode(dir, res.dir_fattr);
+		nfs_post_op_update_inode(dir, res.dir_fattr);
+		status = nfs_instantiate(dentry, &fhandle, &fattr);
+	}
 	return status;
 }
 
-static int nfs4_proc_symlink(struct inode *dir, struct qstr *name,
-		struct qstr *path, struct iattr *sattr, struct nfs_fh *fhandle,
-		struct nfs_fattr *fattr)
+static int nfs4_proc_symlink(struct inode *dir, struct dentry *dentry,
+		struct page *page, unsigned int len, struct iattr *sattr)
 {
 	struct nfs4_exception exception = { };
 	int err;
 	do {
 		err = nfs4_handle_exception(NFS_SERVER(dir),
-				_nfs4_proc_symlink(dir, name, path, sattr,
-					fhandle, fattr),
+				_nfs4_proc_symlink(dir, dentry, page,
+							len, sattr),
 				&exception);
 	} while (exception.retry);
 	return err;
@@ -2521,7 +2526,7 @@ static void nfs4_proc_commit_setup(struct nfs_write_data *data, int how)
  */
 static void nfs4_renew_done(struct rpc_task *task, void *data)
 {
-	struct nfs4_client *clp = (struct nfs4_client *)task->tk_msg.rpc_argp;
+	struct nfs_client *clp = (struct nfs_client *)task->tk_msg.rpc_argp;
 	unsigned long timestamp = (unsigned long)data;
 
 	if (task->tk_status < 0) {
@@ -2543,7 +2548,7 @@ static const struct rpc_call_ops nfs4_renew_ops = {
 	.rpc_call_done = nfs4_renew_done,
 };
 
-int nfs4_proc_async_renew(struct nfs4_client *clp, struct rpc_cred *cred)
+int nfs4_proc_async_renew(struct nfs_client *clp, struct rpc_cred *cred)
 {
 	struct rpc_message msg = {
 		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_RENEW],
@@ -2555,7 +2560,7 @@ int nfs4_proc_async_renew(struct nfs4_client *clp, struct rpc_cred *cred)
 			&nfs4_renew_ops, (void *)jiffies);
 }
 
-int nfs4_proc_renew(struct nfs4_client *clp, struct rpc_cred *cred)
+int nfs4_proc_renew(struct nfs_client *clp, struct rpc_cred *cred)
 {
 	struct rpc_message msg = {
 		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_RENEW],
@@ -2770,7 +2775,7 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 		return -EOPNOTSUPP;
 	nfs_inode_return_delegation(inode);
 	buf_to_pages(buf, buflen, arg.acl_pages, &arg.acl_pgbase);
-	ret = rpc_call_sync(NFS_SERVER(inode)->client, &msg, 0);
+	ret = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
 	if (ret == 0)
 		nfs4_write_cached_acl(inode, buf, buflen);
 	return ret;
@@ -2791,7 +2796,7 @@ static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen
 static int
 nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server)
 {
-	struct nfs4_client *clp = server->nfs4_state;
+	struct nfs_client *clp = server->nfs_client;
 
 	if (!clp || task->tk_status >= 0)
 		return 0;
@@ -2828,7 +2833,7 @@ static int nfs4_wait_bit_interruptible(void *word)
 	return 0;
 }
 
-static int nfs4_wait_clnt_recover(struct rpc_clnt *clnt, struct nfs4_client *clp)
+static int nfs4_wait_clnt_recover(struct rpc_clnt *clnt, struct nfs_client *clp)
 {
 	sigset_t oldset;
 	int res;
@@ -2871,7 +2876,7 @@ static int nfs4_delay(struct rpc_clnt *clnt, long *timeout)
  */
 int nfs4_handle_exception(const struct nfs_server *server, int errorcode, struct nfs4_exception *exception)
 {
-	struct nfs4_client *clp = server->nfs4_state;
+	struct nfs_client *clp = server->nfs_client;
 	int ret = errorcode;
 
 	exception->retry = 0;
@@ -2886,6 +2891,7 @@ int nfs4_handle_exception(const struct nfs_server *server, int errorcode, struct
 			if (ret == 0)
 				exception->retry = 1;
 			break;
+		case -NFS4ERR_FILE_OPEN:
 		case -NFS4ERR_GRACE:
 		case -NFS4ERR_DELAY:
 			ret = nfs4_delay(server->client, &exception->timeout);
@@ -2898,7 +2904,7 @@ int nfs4_handle_exception(const struct nfs_server *server, int errorcode, struct
 	return nfs4_map_errors(ret);
 }
 
-int nfs4_proc_setclientid(struct nfs4_client *clp, u32 program, unsigned short port, struct rpc_cred *cred)
+int nfs4_proc_setclientid(struct nfs_client *clp, u32 program, unsigned short port, struct rpc_cred *cred)
 {
 	nfs4_verifier sc_verifier;
 	struct nfs4_setclientid setclientid = {
@@ -2922,7 +2928,7 @@ int nfs4_proc_setclientid(struct nfs4_client *clp, u32 program, unsigned short p
 	for(;;) {
 		setclientid.sc_name_len = scnprintf(setclientid.sc_name,
 				sizeof(setclientid.sc_name), "%s/%u.%u.%u.%u %s %u",
-				clp->cl_ipaddr, NIPQUAD(clp->cl_addr.s_addr),
+				clp->cl_ipaddr, NIPQUAD(clp->cl_addr.sin_addr),
 				cred->cr_ops->cr_name,
 				clp->cl_id_uniquifier);
 		setclientid.sc_netid_len = scnprintf(setclientid.sc_netid,
@@ -2945,7 +2951,7 @@ int nfs4_proc_setclientid(struct nfs4_client *clp, u32 program, unsigned short p
 	return status;
 }
 
-static int _nfs4_proc_setclientid_confirm(struct nfs4_client *clp, struct rpc_cred *cred)
+static int _nfs4_proc_setclientid_confirm(struct nfs_client *clp, struct rpc_cred *cred)
 {
 	struct nfs_fsinfo fsinfo;
 	struct rpc_message msg = {
@@ -2969,7 +2975,7 @@ static int _nfs4_proc_setclientid_confirm(struct nfs4_client *clp, struct rpc_cr
 	return status;
 }
 
-int nfs4_proc_setclientid_confirm(struct nfs4_client *clp, struct rpc_cred *cred)
+int nfs4_proc_setclientid_confirm(struct nfs_client *clp, struct rpc_cred *cred)
 {
 	long timeout;
 	int err;
@@ -3077,7 +3083,7 @@ int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4
 		switch (err) {
 			case -NFS4ERR_STALE_STATEID:
 			case -NFS4ERR_EXPIRED:
-				nfs4_schedule_state_recovery(server->nfs4_state);
+				nfs4_schedule_state_recovery(server->nfs_client);
 			case 0:
 				return 0;
 		}
@@ -3106,7 +3112,7 @@ static int _nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock
 {
 	struct inode *inode = state->inode;
 	struct nfs_server *server = NFS_SERVER(inode);
-	struct nfs4_client *clp = server->nfs4_state;
+	struct nfs_client *clp = server->nfs_client;
 	struct nfs_lockt_args arg = {
 		.fh = NFS_FH(inode),
 		.fl = request,
@@ -3231,7 +3237,7 @@ static void nfs4_locku_done(struct rpc_task *task, void *data)
 			break;
 		case -NFS4ERR_STALE_STATEID:
 		case -NFS4ERR_EXPIRED:
-			nfs4_schedule_state_recovery(calldata->server->nfs4_state);
+			nfs4_schedule_state_recovery(calldata->server->nfs_client);
 			break;
 		default:
 			if (nfs4_async_handle_error(task, calldata->server) == -EAGAIN) {
@@ -3343,7 +3349,7 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl,
 	if (p->arg.lock_seqid == NULL)
 		goto out_free;
 	p->arg.lock_stateid = &lsp->ls_stateid;
-	p->arg.lock_owner.clientid = server->nfs4_state->cl_clientid;
+	p->arg.lock_owner.clientid = server->nfs_client->cl_clientid;
 	p->arg.lock_owner.id = lsp->ls_id;
 	p->lsp = lsp;
 	atomic_inc(&lsp->ls_count);
@@ -3513,7 +3519,7 @@ static int nfs4_lock_expired(struct nfs4_state *state, struct file_lock *request
 
 static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock *request)
 {
-	struct nfs4_client *clp = state->owner->so_client;
+	struct nfs_client *clp = state->owner->so_client;
 	unsigned char fl_flags = request->fl_flags;
 	int status;
 
@@ -3715,7 +3721,7 @@ static struct inode_operations nfs4_file_inode_operations = {
 	.listxattr	= nfs4_listxattr,
 };
 
-struct nfs_rpc_ops	nfs_v4_clientops = {
+const struct nfs_rpc_ops nfs_v4_clientops = {
 	.version	= 4,			/* protocol version */
 	.dentry_ops	= &nfs4_dentry_operations,
 	.dir_inode_ops	= &nfs4_dir_inode_operations,
@@ -3723,6 +3729,7 @@ struct nfs_rpc_ops	nfs_v4_clientops = {
 	.getroot	= nfs4_proc_get_root,
 	.getattr	= nfs4_proc_getattr,
 	.setattr	= nfs4_proc_setattr,
+	.lookupfh	= nfs4_proc_lookupfh,
 	.lookup		= nfs4_proc_lookup,
 	.access		= nfs4_proc_access,
 	.readlink	= nfs4_proc_readlink,
@@ -3743,6 +3750,7 @@ struct nfs_rpc_ops	nfs_v4_clientops = {
 	.statfs		= nfs4_proc_statfs,
 	.fsinfo		= nfs4_proc_fsinfo,
 	.pathconf	= nfs4_proc_pathconf,
+	.set_capabilities = nfs4_server_capabilities,
 	.decode_dirent	= nfs4_decode_dirent,
 	.read_setup	= nfs4_proc_read_setup,
 	.read_done	= nfs4_read_done,

fs/nfs/nfs4renewd.c

@@ -61,7 +61,7 @@
 void
 nfs4_renew_state(void *data)
 {
-	struct nfs4_client *clp = (struct nfs4_client *)data;
+	struct nfs_client *clp = (struct nfs_client *)data;
 	struct rpc_cred *cred;
 	long lease, timeout;
 	unsigned long last, now;
@@ -108,7 +108,7 @@ out:
 
 /* Must be called with clp->cl_sem locked for writes */
 void
-nfs4_schedule_state_renewal(struct nfs4_client *clp)
+nfs4_schedule_state_renewal(struct nfs_client *clp)
 {
 	long timeout;
 
@@ -121,32 +121,20 @@ nfs4_schedule_state_renewal(struct nfs4_client *clp)
 			__FUNCTION__, (timeout + HZ - 1) / HZ);
 	cancel_delayed_work(&clp->cl_renewd);
 	schedule_delayed_work(&clp->cl_renewd, timeout);
+	set_bit(NFS_CS_RENEWD, &clp->cl_res_state);
 	spin_unlock(&clp->cl_lock);
 }
 
 void
 nfs4_renewd_prepare_shutdown(struct nfs_server *server)
 {
-	struct nfs4_client *clp = server->nfs4_state;
-
-	if (!clp)
-		return;
 	flush_scheduled_work();
-	down_write(&clp->cl_sem);
-	if (!list_empty(&server->nfs4_siblings))
-		list_del_init(&server->nfs4_siblings);
-	up_write(&clp->cl_sem);
 }
 
-/* Must be called with clp->cl_sem locked for writes */
 void
-nfs4_kill_renewd(struct nfs4_client *clp)
+nfs4_kill_renewd(struct nfs_client *clp)
 {
 	down_read(&clp->cl_sem);
-	if (!list_empty(&clp->cl_superblocks)) {
-		up_read(&clp->cl_sem);
-		return;
-	}
 	cancel_delayed_work(&clp->cl_renewd);
 	up_read(&clp->cl_sem);
 	flush_scheduled_work();

fs/nfs/nfs4state.c

@@ -50,149 +50,15 @@
 #include "nfs4_fs.h"
 #include "callback.h"
 #include "delegation.h"
+#include "internal.h"
 
 #define OPENOWNER_POOL_SIZE	8
 
 const nfs4_stateid zero_stateid;
 
-static DEFINE_SPINLOCK(state_spinlock);
 static LIST_HEAD(nfs4_clientid_list);
 
-void
-init_nfsv4_state(struct nfs_server *server)
-{
-	server->nfs4_state = NULL;
-	INIT_LIST_HEAD(&server->nfs4_siblings);
-}
-
-void
-destroy_nfsv4_state(struct nfs_server *server)
-{
-	kfree(server->mnt_path);
-	server->mnt_path = NULL;
-	if (server->nfs4_state) {
-		nfs4_put_client(server->nfs4_state);
-		server->nfs4_state = NULL;
-	}
-}
-
-/*
- * nfs4_get_client(): returns an empty client structure
- * nfs4_put_client(): drops reference to client structure
- *
- * Since these are allocated/deallocated very rarely, we don't
- * bother putting them in a slab cache...
- */
-static struct nfs4_client *
-nfs4_alloc_client(struct in_addr *addr)
-{
-	struct nfs4_client *clp;
-
-	if (nfs_callback_up() < 0)
-		return NULL;
-	if ((clp = kzalloc(sizeof(*clp), GFP_KERNEL)) == NULL) {
-		nfs_callback_down();
-		return NULL;
-	}
-	memcpy(&clp->cl_addr, addr, sizeof(clp->cl_addr));
-	init_rwsem(&clp->cl_sem);
-	INIT_LIST_HEAD(&clp->cl_delegations);
-	INIT_LIST_HEAD(&clp->cl_state_owners);
-	INIT_LIST_HEAD(&clp->cl_unused);
-	spin_lock_init(&clp->cl_lock);
-	atomic_set(&clp->cl_count, 1);
-	INIT_WORK(&clp->cl_renewd, nfs4_renew_state, clp);
-	INIT_LIST_HEAD(&clp->cl_superblocks);
-	rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS4 client");
-	clp->cl_rpcclient = ERR_PTR(-EINVAL);
-	clp->cl_boot_time = CURRENT_TIME;
-	clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
-	return clp;
-}
-
-static void
-nfs4_free_client(struct nfs4_client *clp)
-{
-	struct nfs4_state_owner *sp;
-
-	while (!list_empty(&clp->cl_unused)) {
-		sp = list_entry(clp->cl_unused.next,
-				struct nfs4_state_owner,
-				so_list);
-		list_del(&sp->so_list);
-		kfree(sp);
-	}
-	BUG_ON(!list_empty(&clp->cl_state_owners));
-	nfs_idmap_delete(clp);
-	if (!IS_ERR(clp->cl_rpcclient))
-		rpc_shutdown_client(clp->cl_rpcclient);
-	kfree(clp);
-	nfs_callback_down();
-}
-
-static struct nfs4_client *__nfs4_find_client(struct in_addr *addr)
-{
-	struct nfs4_client *clp;
-	list_for_each_entry(clp, &nfs4_clientid_list, cl_servers) {
-		if (memcmp(&clp->cl_addr, addr, sizeof(clp->cl_addr)) == 0) {
-			atomic_inc(&clp->cl_count);
-			return clp;
-		}
-	}
-	return NULL;
-}
-
-struct nfs4_client *nfs4_find_client(struct in_addr *addr)
-{
-	struct nfs4_client *clp;
-	spin_lock(&state_spinlock);
-	clp = __nfs4_find_client(addr);
-	spin_unlock(&state_spinlock);
-	return clp;
-}
-
-struct nfs4_client *
-nfs4_get_client(struct in_addr *addr)
-{
-	struct nfs4_client *clp, *new = NULL;
-
-	spin_lock(&state_spinlock);
-	for (;;) {
-		clp = __nfs4_find_client(addr);
-		if (clp != NULL)
-			break;
-		clp = new;
-		if (clp != NULL) {
-			list_add(&clp->cl_servers, &nfs4_clientid_list);
-			new = NULL;
-			break;
-		}
-		spin_unlock(&state_spinlock);
-		new = nfs4_alloc_client(addr);
-		spin_lock(&state_spinlock);
-		if (new == NULL)
-			break;
-	}
-	spin_unlock(&state_spinlock);
-	if (new)
-		nfs4_free_client(new);
-	return clp;
-}
-
-void
-nfs4_put_client(struct nfs4_client *clp)
-{
-	if (!atomic_dec_and_lock(&clp->cl_count, &state_spinlock))
-		return;
-	list_del(&clp->cl_servers);
-	spin_unlock(&state_spinlock);
-	BUG_ON(!list_empty(&clp->cl_superblocks));
-	rpc_wake_up(&clp->cl_rpcwaitq);
-	nfs4_kill_renewd(clp);
-	nfs4_free_client(clp);
-}
-
-static int nfs4_init_client(struct nfs4_client *clp, struct rpc_cred *cred)
+static int nfs4_init_client(struct nfs_client *clp, struct rpc_cred *cred)
 {
 	int status = nfs4_proc_setclientid(clp, NFS4_CALLBACK,
 			nfs_callback_tcpport, cred);
@@ -204,13 +70,13 @@ static int nfs4_init_client(struct nfs4_client *clp, struct rpc_cred *cred)
 }
 
 u32
-nfs4_alloc_lockowner_id(struct nfs4_client *clp)
+nfs4_alloc_lockowner_id(struct nfs_client *clp)
 {
 	return clp->cl_lockowner_id ++;
 }
 
 static struct nfs4_state_owner *
-nfs4_client_grab_unused(struct nfs4_client *clp, struct rpc_cred *cred)
+nfs4_client_grab_unused(struct nfs_client *clp, struct rpc_cred *cred)
 {
 	struct nfs4_state_owner *sp = NULL;
 
@@ -224,7 +90,7 @@ nfs4_client_grab_unused(struct nfs4_client *clp, struct rpc_cred *cred)
 	return sp;
 }
 
-struct rpc_cred *nfs4_get_renew_cred(struct nfs4_client *clp)
+struct rpc_cred *nfs4_get_renew_cred(struct nfs_client *clp)
 {
 	struct nfs4_state_owner *sp;
 	struct rpc_cred *cred = NULL;
@@ -238,7 +104,7 @@ struct rpc_cred *nfs4_get_renew_cred(struct nfs4_client *clp)
 	return cred;
 }
 
-struct rpc_cred *nfs4_get_setclientid_cred(struct nfs4_client *clp)
+struct rpc_cred *nfs4_get_setclientid_cred(struct nfs_client *clp)
 {
 	struct nfs4_state_owner *sp;
 
@@ -251,7 +117,7 @@ struct rpc_cred *nfs4_get_setclientid_cred(struct nfs4_client *clp)
 }
 
 static struct nfs4_state_owner *
-nfs4_find_state_owner(struct nfs4_client *clp, struct rpc_cred *cred)
+nfs4_find_state_owner(struct nfs_client *clp, struct rpc_cred *cred)
 {
 	struct nfs4_state_owner *sp, *res = NULL;
 
@@ -294,7 +160,7 @@ nfs4_alloc_state_owner(void)
 void
 nfs4_drop_state_owner(struct nfs4_state_owner *sp)
 {
-	struct nfs4_client *clp = sp->so_client;
+	struct nfs_client *clp = sp->so_client;
 	spin_lock(&clp->cl_lock);
 	list_del_init(&sp->so_list);
 	spin_unlock(&clp->cl_lock);
@@ -306,7 +172,7 @@ nfs4_drop_state_owner(struct nfs4_state_owner *sp)
  */
 struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *server, struct rpc_cred *cred)
 {
-	struct nfs4_client *clp = server->nfs4_state;
+	struct nfs_client *clp = server->nfs_client;
 	struct nfs4_state_owner *sp, *new;
 
 	get_rpccred(cred);
@@ -337,7 +203,7 @@ struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *server, struct
  */
 void nfs4_put_state_owner(struct nfs4_state_owner *sp)
 {
-	struct nfs4_client *clp = sp->so_client;
+	struct nfs_client *clp = sp->so_client;
 	struct rpc_cred *cred = sp->so_cred;
 
 	if (!atomic_dec_and_lock(&sp->so_count, &clp->cl_lock))
@@ -540,7 +406,7 @@ __nfs4_find_lock_state(struct nfs4_state *state, fl_owner_t fl_owner)
 static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, fl_owner_t fl_owner)
 {
 	struct nfs4_lock_state *lsp;
-	struct nfs4_client *clp = state->owner->so_client;
+	struct nfs_client *clp = state->owner->so_client;
 
 	lsp = kzalloc(sizeof(*lsp), GFP_KERNEL);
 	if (lsp == NULL)
@@ -752,7 +618,7 @@ out:
 
 static int reclaimer(void *);
 
-static inline void nfs4_clear_recover_bit(struct nfs4_client *clp)
+static inline void nfs4_clear_recover_bit(struct nfs_client *clp)
 {
 	smp_mb__before_clear_bit();
 	clear_bit(NFS4CLNT_STATE_RECOVER, &clp->cl_state);
@@ -764,25 +630,25 @@ static inline void nfs4_clear_recover_bit(struct nfs4_client *clp)
 /*
  * State recovery routine
  */
-static void nfs4_recover_state(struct nfs4_client *clp)
+static void nfs4_recover_state(struct nfs_client *clp)
 {
 	struct task_struct *task;
 
 	__module_get(THIS_MODULE);
 	atomic_inc(&clp->cl_count);
 	task = kthread_run(reclaimer, clp, "%u.%u.%u.%u-reclaim",
-			NIPQUAD(clp->cl_addr));
+			NIPQUAD(clp->cl_addr.sin_addr));
 	if (!IS_ERR(task))
 		return;
 	nfs4_clear_recover_bit(clp);
-	nfs4_put_client(clp);
+	nfs_put_client(clp);
 	module_put(THIS_MODULE);
 }
 
 /*
  * Schedule a state recovery attempt
  */
-void nfs4_schedule_state_recovery(struct nfs4_client *clp)
+void nfs4_schedule_state_recovery(struct nfs_client *clp)
 {
 	if (!clp)
 		return;
@@ -879,7 +745,7 @@ out_err:
 	return status;
 }
 
-static void nfs4_state_mark_reclaim(struct nfs4_client *clp)
+static void nfs4_state_mark_reclaim(struct nfs_client *clp)
 {
 	struct nfs4_state_owner *sp;
 	struct nfs4_state *state;
@@ -903,7 +769,7 @@ static void nfs4_state_mark_reclaim(struct nfs4_client *clp)
 
 static int reclaimer(void *ptr)
 {
-	struct nfs4_client *clp = ptr;
+	struct nfs_client *clp = ptr;
 	struct nfs4_state_owner *sp;
 	struct nfs4_state_recovery_ops *ops;
 	struct rpc_cred *cred;
@@ -970,12 +836,12 @@ out:
 	if (status == -NFS4ERR_CB_PATH_DOWN)
 		nfs_handle_cb_pathdown(clp);
 	nfs4_clear_recover_bit(clp);
-	nfs4_put_client(clp);
+	nfs_put_client(clp);
 	module_put_and_exit(0);
 	return 0;
 out_error:
 	printk(KERN_WARNING "Error: state recovery failed on NFSv4 server %u.%u.%u.%u with error %d\n",
-				NIPQUAD(clp->cl_addr.s_addr), -status);
+				NIPQUAD(clp->cl_addr.sin_addr), -status);
 	set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
 	goto out;
 }

fs/nfs/nfs4xdr.c

@@ -58,7 +58,7 @@
 /* Mapping from NFS error code to "errno" error code. */
 #define errno_NFSERR_IO		EIO
 
-static int nfs_stat_to_errno(int);
+static int nfs4_stat_to_errno(int);
 
 /* NFSv4 COMPOUND tags are only wanted for debugging purposes */
 #ifdef DEBUG
@@ -128,7 +128,7 @@ static int nfs_stat_to_errno(int);
 #define decode_link_maxsz	(op_decode_hdr_maxsz + 5)
 #define encode_symlink_maxsz	(op_encode_hdr_maxsz + \
 				1 + nfs4_name_maxsz + \
-				nfs4_path_maxsz + \
+				1 + \
 				nfs4_fattr_maxsz)
 #define decode_symlink_maxsz	(op_decode_hdr_maxsz + 8)
 #define encode_create_maxsz	(op_encode_hdr_maxsz + \
@@ -529,7 +529,7 @@ static int encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const s
 	if (iap->ia_valid & ATTR_MODE)
 		len += 4;
 	if (iap->ia_valid & ATTR_UID) {
-		owner_namelen = nfs_map_uid_to_name(server->nfs4_state, iap->ia_uid, owner_name);
+		owner_namelen = nfs_map_uid_to_name(server->nfs_client, iap->ia_uid, owner_name);
 		if (owner_namelen < 0) {
 			printk(KERN_WARNING "nfs: couldn't resolve uid %d to string\n",
 			       iap->ia_uid);
@@ -541,7 +541,7 @@ static int encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const s
 		len += 4 + (XDR_QUADLEN(owner_namelen) << 2);
 	}
 	if (iap->ia_valid & ATTR_GID) {
-		owner_grouplen = nfs_map_gid_to_group(server->nfs4_state, iap->ia_gid, owner_group);
+		owner_grouplen = nfs_map_gid_to_group(server->nfs_client, iap->ia_gid, owner_group);
 		if (owner_grouplen < 0) {
 			printk(KERN_WARNING "nfs4: couldn't resolve gid %d to string\n",
 			       iap->ia_gid);
@@ -673,9 +673,9 @@ static int encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg *c
 
 	switch (create->ftype) {
 	case NF4LNK:
-		RESERVE_SPACE(4 + create->u.symlink->len);
-		WRITE32(create->u.symlink->len);
-		WRITEMEM(create->u.symlink->name, create->u.symlink->len);
+		RESERVE_SPACE(4);
+		WRITE32(create->u.symlink.len);
+		xdr_write_pages(xdr, create->u.symlink.pages, 0, create->u.symlink.len);
 		break;
 
 	case NF4BLK: case NF4CHR:
@@ -1160,7 +1160,7 @@ static int encode_rename(struct xdr_stream *xdr, const struct qstr *oldname, con
 	return 0;
 }
 
-static int encode_renew(struct xdr_stream *xdr, const struct nfs4_client *client_stateid)
+static int encode_renew(struct xdr_stream *xdr, const struct nfs_client *client_stateid)
 {
 	uint32_t *p;
 
@@ -1246,7 +1246,7 @@ static int encode_setclientid(struct xdr_stream *xdr, const struct nfs4_setclien
 	return 0;
 }
 
-static int encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs4_client *client_state)
+static int encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs_client *client_state)
 {
         uint32_t *p;
 
@@ -1945,7 +1945,7 @@ static int nfs4_xdr_enc_server_caps(struct rpc_rqst *req, uint32_t *p, const str
 /*
  * a RENEW request
  */
-static int nfs4_xdr_enc_renew(struct rpc_rqst *req, uint32_t *p, struct nfs4_client *clp)
+static int nfs4_xdr_enc_renew(struct rpc_rqst *req, uint32_t *p, struct nfs_client *clp)
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
@@ -1975,7 +1975,7 @@ static int nfs4_xdr_enc_setclientid(struct rpc_rqst *req, uint32_t *p, struct nf
 /*
  * a SETCLIENTID_CONFIRM request
  */
-static int nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req, uint32_t *p, struct nfs4_client *clp)
+static int nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req, uint32_t *p, struct nfs_client *clp)
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
@@ -2127,12 +2127,12 @@ static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
 	}
 	READ32(nfserr);
 	if (nfserr != NFS_OK)
-		return -nfs_stat_to_errno(nfserr);
+		return -nfs4_stat_to_errno(nfserr);
 	return 0;
 }
 
 /* Dummy routine */
-static int decode_ace(struct xdr_stream *xdr, void *ace, struct nfs4_client *clp)
+static int decode_ace(struct xdr_stream *xdr, void *ace, struct nfs_client *clp)
 {
 	uint32_t *p;
 	unsigned int strlen;
@@ -2636,7 +2636,7 @@ static int decode_attr_nlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t
 	return 0;
 }
 
-static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs4_client *clp, int32_t *uid)
+static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, int32_t *uid)
 {
 	uint32_t len, *p;
 
@@ -2660,7 +2660,7 @@ static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nf
 	return 0;
 }
 
-static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs4_client *clp, int32_t *gid)
+static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, int32_t *gid)
 {
 	uint32_t len, *p;
 
@@ -3051,9 +3051,9 @@ static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, cons
 	fattr->mode |= fmode;
 	if ((status = decode_attr_nlink(xdr, bitmap, &fattr->nlink)) != 0)
 		goto xdr_error;
-	if ((status = decode_attr_owner(xdr, bitmap, server->nfs4_state, &fattr->uid)) != 0)
+	if ((status = decode_attr_owner(xdr, bitmap, server->nfs_client, &fattr->uid)) != 0)
 		goto xdr_error;
-	if ((status = decode_attr_group(xdr, bitmap, server->nfs4_state, &fattr->gid)) != 0)
+	if ((status = decode_attr_group(xdr, bitmap, server->nfs_client, &fattr->gid)) != 0)
 		goto xdr_error;
 	if ((status = decode_attr_rdev(xdr, bitmap, &fattr->rdev)) != 0)
 		goto xdr_error;
@@ -3254,7 +3254,7 @@ static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res)
 			if (decode_space_limit(xdr, &res->maxsize) < 0)
 				return -EIO;
 	}
-	return decode_ace(xdr, NULL, res->server->nfs4_state);
+	return decode_ace(xdr, NULL, res->server->nfs_client);
 }
 
 static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res)
@@ -3565,7 +3565,7 @@ static int decode_setattr(struct xdr_stream *xdr, struct nfs_setattrres *res)
 	return 0;
 }
 
-static int decode_setclientid(struct xdr_stream *xdr, struct nfs4_client *clp)
+static int decode_setclientid(struct xdr_stream *xdr, struct nfs_client *clp)
 {
 	uint32_t *p;
 	uint32_t opnum;
@@ -3598,7 +3598,7 @@ static int decode_setclientid(struct xdr_stream *xdr, struct nfs4_client *clp)
 		READ_BUF(len);
 		return -NFSERR_CLID_INUSE;
 	} else
-		return -nfs_stat_to_errno(nfserr);
+		return -nfs4_stat_to_errno(nfserr);
 
 	return 0;
 }
@@ -4256,7 +4256,7 @@ static int nfs4_xdr_dec_fsinfo(struct rpc_rqst *req, uint32_t *p, struct nfs_fsi
 	if (!status)
 		status = decode_fsinfo(&xdr, fsinfo);
 	if (!status)
-		status = -nfs_stat_to_errno(hdr.status);
+		status = -nfs4_stat_to_errno(hdr.status);
 	return status;
 }
 
@@ -4335,7 +4335,7 @@ static int nfs4_xdr_dec_renew(struct rpc_rqst *rqstp, uint32_t *p, void *dummy)
  * a SETCLIENTID request
  */
 static int nfs4_xdr_dec_setclientid(struct rpc_rqst *req, uint32_t *p,
-		struct nfs4_client *clp)
+		struct nfs_client *clp)
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr;
@@ -4346,7 +4346,7 @@ static int nfs4_xdr_dec_setclientid(struct rpc_rqst *req, uint32_t *p,
 	if (!status)
 		status = decode_setclientid(&xdr, clp);
 	if (!status)
-		status = -nfs_stat_to_errno(hdr.status);
+		status = -nfs4_stat_to_errno(hdr.status);
 	return status;
 }
 
@@ -4368,7 +4368,7 @@ static int nfs4_xdr_dec_setclientid_confirm(struct rpc_rqst *req, uint32_t *p, s
 	if (!status)
 		status = decode_fsinfo(&xdr, fsinfo);
 	if (!status)
-		status = -nfs_stat_to_errno(hdr.status);
+		status = -nfs4_stat_to_errno(hdr.status);
 	return status;
 }
 
@@ -4521,7 +4521,7 @@ static struct {
  * This one is used jointly by NFSv2 and NFSv3.
  */
 static int
-nfs_stat_to_errno(int stat)
+nfs4_stat_to_errno(int stat)
 {
 	int i;
 	for (i = 0; nfs_errtbl[i].stat != -1; i++) {

fs/nfs/proc.c

@@ -66,14 +66,14 @@ nfs_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
 
 	dprintk("%s: call getattr\n", __FUNCTION__);
 	nfs_fattr_init(fattr);
-	status = rpc_call_sync(server->client_sys, &msg, 0);
+	status = rpc_call_sync(server->nfs_client->cl_rpcclient, &msg, 0);
 	dprintk("%s: reply getattr: %d\n", __FUNCTION__, status);
 	if (status)
 		return status;
 	dprintk("%s: call statfs\n", __FUNCTION__);
 	msg.rpc_proc = &nfs_procedures[NFSPROC_STATFS];
 	msg.rpc_resp = &fsinfo;
-	status = rpc_call_sync(server->client_sys, &msg, 0);
+	status = rpc_call_sync(server->nfs_client->cl_rpcclient, &msg, 0);
 	dprintk("%s: reply statfs: %d\n", __FUNCTION__, status);
 	if (status)
 		return status;
@@ -425,16 +425,17 @@ nfs_proc_link(struct inode *inode, struct inode *dir, struct qstr *name)
 }
 
 static int
-nfs_proc_symlink(struct inode *dir, struct qstr *name, struct qstr *path,
-		 struct iattr *sattr, struct nfs_fh *fhandle,
-		 struct nfs_fattr *fattr)
+nfs_proc_symlink(struct inode *dir, struct dentry *dentry, struct page *page,
+		 unsigned int len, struct iattr *sattr)
 {
+	struct nfs_fh fhandle;
+	struct nfs_fattr fattr;
 	struct nfs_symlinkargs	arg = {
 		.fromfh		= NFS_FH(dir),
-		.fromname	= name->name,
-		.fromlen	= name->len,
-		.topath		= path->name,
-		.tolen		= path->len,
+		.fromname	= dentry->d_name.name,
+		.fromlen	= dentry->d_name.len,
+		.pages		= &page,
+		.pathlen	= len,
 		.sattr		= sattr
 	};
 	struct rpc_message msg = {
@@ -443,13 +444,25 @@ nfs_proc_symlink(struct inode *dir, struct qstr *name, struct qstr *path,
 	};
 	int			status;
 
-	if (path->len > NFS2_MAXPATHLEN)
+	if (len > NFS2_MAXPATHLEN)
 		return -ENAMETOOLONG;
-	dprintk("NFS call  symlink %s -> %s\n", name->name, path->name);
-	nfs_fattr_init(fattr);
-	fhandle->size = 0;
+
+	dprintk("NFS call  symlink %s\n", dentry->d_name.name);
+
 	status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
 	nfs_mark_for_revalidate(dir);
+
+	/*
+	 * V2 SYMLINK requests don't return any attributes.  Setting the
+	 * filehandle size to zero indicates to nfs_instantiate that it
+	 * should fill in the data with a LOOKUP call on the wire.
+	 */
+	if (status == 0) {
+		nfs_fattr_init(&fattr);
+		fhandle.size = 0;
+		status = nfs_instantiate(dentry, &fhandle, &fattr);
+	}
+
 	dprintk("NFS reply symlink: %d\n", status);
 	return status;
 }
@@ -671,7 +684,7 @@ nfs_proc_lock(struct file *filp, int cmd, struct file_lock *fl)
 }
 
 
-struct nfs_rpc_ops	nfs_v2_clientops = {
+const struct nfs_rpc_ops nfs_v2_clientops = {
 	.version	= 2,		       /* protocol version */
 	.dentry_ops	= &nfs_dentry_operations,
 	.dir_inode_ops	= &nfs_dir_inode_operations,

fs/nfs/read.c

@@ -171,7 +171,7 @@ static int nfs_readpage_sync(struct nfs_open_context *ctx, struct inode *inode,
 		rdata->args.offset = page_offset(page) + rdata->args.pgbase;
 
 		dprintk("NFS: nfs_proc_read(%s, (%s/%Ld), %Lu, %u)\n",
-			NFS_SERVER(inode)->hostname,
+			NFS_SERVER(inode)->nfs_client->cl_hostname,
 			inode->i_sb->s_id,
 			(long long)NFS_FILEID(inode),
 			(unsigned long long)rdata->args.pgbase,
@@ -568,8 +568,13 @@ int nfs_readpage_result(struct rpc_task *task, struct nfs_read_data *data)
 
 	nfs_add_stats(data->inode, NFSIOS_SERVERREADBYTES, resp->count);
 
-	/* Is this a short read? */
-	if (task->tk_status >= 0 && resp->count < argp->count && !resp->eof) {
+	if (task->tk_status < 0) {
+		if (task->tk_status == -ESTALE) {
+			set_bit(NFS_INO_STALE, &NFS_FLAGS(data->inode));
+			nfs_mark_for_revalidate(data->inode);
+		}
+	} else if (resp->count < argp->count && !resp->eof) {
+		/* This is a short read! */
 		nfs_inc_stats(data->inode, NFSIOS_SHORTREAD);
 		/* Has the server at least made some progress? */
 		if (resp->count != 0) {
@@ -616,6 +621,10 @@ int nfs_readpage(struct file *file, struct page *page)
 	if (error)
 		goto out_error;
 
+	error = -ESTALE;
+	if (NFS_STALE(inode))
+		goto out_error;
+
 	if (file == NULL) {
 		ctx = nfs_find_open_context(inode, NULL, FMODE_READ);
 		if (ctx == NULL)
@@ -678,7 +687,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 	};
 	struct inode *inode = mapping->host;
 	struct nfs_server *server = NFS_SERVER(inode);
-	int ret;
+	int ret = -ESTALE;
 
 	dprintk("NFS: nfs_readpages (%s/%Ld %d)\n",
 			inode->i_sb->s_id,
@@ -686,6 +695,9 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 			nr_pages);
 	nfs_inc_stats(inode, NFSIOS_VFSREADPAGES);
 
+	if (NFS_STALE(inode))
+		goto out;
+
 	if (filp == NULL) {
 		desc.ctx = nfs_find_open_context(inode, NULL, FMODE_READ);
 		if (desc.ctx == NULL)
@@ -701,6 +713,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 			ret = err;
 	}
 	put_nfs_open_context(desc.ctx);
+out:
 	return ret;
 }
 

fs/nfs/write.c

@@ -396,6 +396,7 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 out:
 	clear_bit(BDI_write_congested, &bdi->state);
 	wake_up_all(&nfs_write_congestion);
+	writeback_congestion_end();
 	return err;
 }
 
@@ -1252,7 +1253,13 @@ int nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 	dprintk("NFS: %4d nfs_writeback_done (status %d)\n",
 		task->tk_pid, task->tk_status);
 
-	/* Call the NFS version-specific code */
+	/*
+	 * ->write_done will attempt to use post-op attributes to detect
+	 * conflicting writes by other clients.  A strict interpretation
+	 * of close-to-open would allow us to continue caching even if
+	 * another writer had changed the file, but some applications
+	 * depend on tighter cache coherency when writing.
+	 */
 	status = NFS_PROTO(data->inode)->write_done(task, data);
 	if (status != 0)
 		return status;
@@ -1273,7 +1280,7 @@ int nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 		if (time_before(complain, jiffies)) {
 			dprintk("NFS: faulty NFS server %s:"
 				" (committed = %d) != (stable = %d)\n",
-				NFS_SERVER(data->inode)->hostname,
+				NFS_SERVER(data->inode)->nfs_client->cl_hostname,
 				resp->verf->committed, argp->stable);
 			complain = jiffies + 300 * HZ;
 		}

fs/nfsd/nfs4callback.c

@@ -375,16 +375,28 @@ nfsd4_probe_callback(struct nfs4_client *clp)
 {
 	struct sockaddr_in	addr;
 	struct nfs4_callback    *cb = &clp->cl_callback;
-	struct rpc_timeout	timeparms;
-	struct rpc_xprt *	xprt;
+	struct rpc_timeout	timeparms = {
+		.to_initval	= (NFSD_LEASE_TIME/4) * HZ,
+		.to_retries	= 5,
+		.to_maxval	= (NFSD_LEASE_TIME/2) * HZ,
+		.to_exponential	= 1,
+	};
 	struct rpc_program *	program = &cb->cb_program;
-	struct rpc_stat *	stat = &cb->cb_stat;
-	struct rpc_clnt *	clnt;
+	struct rpc_create_args args = {
+		.protocol	= IPPROTO_TCP,
+		.address	= (struct sockaddr *)&addr,
+		.addrsize	= sizeof(addr),
+		.timeout	= &timeparms,
+		.servername	= clp->cl_name.data,
+		.program	= program,
+		.version	= nfs_cb_version[1]->number,
+		.authflavor	= RPC_AUTH_UNIX,	/* XXX: need AUTH_GSS... */
+		.flags		= (RPC_CLNT_CREATE_NOPING),
+	};
 	struct rpc_message msg = {
 		.rpc_proc       = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL],
 		.rpc_argp       = clp,
 	};
-	char                    hostname[32];
 	int status;
 
 	if (atomic_read(&cb->cb_set))
@@ -396,51 +408,27 @@ nfsd4_probe_callback(struct nfs4_client *clp)
 	addr.sin_port = htons(cb->cb_port);
 	addr.sin_addr.s_addr = htonl(cb->cb_addr);
 
-	/* Initialize timeout */
-	timeparms.to_initval = (NFSD_LEASE_TIME/4) * HZ;
-	timeparms.to_retries = 0;
-	timeparms.to_maxval = (NFSD_LEASE_TIME/2) * HZ;
-	timeparms.to_exponential = 1;
-
-	/* Create RPC transport */
-	xprt = xprt_create_proto(IPPROTO_TCP, &addr, &timeparms);
-	if (IS_ERR(xprt)) {
-		dprintk("NFSD: couldn't create callback transport!\n");
-		goto out_err;
-	}
-
 	/* Initialize rpc_program */
 	program->name = "nfs4_cb";
 	program->number = cb->cb_prog;
 	program->nrvers = ARRAY_SIZE(nfs_cb_version);
 	program->version = nfs_cb_version;
-	program->stats = stat;
+	program->stats = &cb->cb_stat;
 
 	/* Initialize rpc_stat */
-	memset(stat, 0, sizeof(struct rpc_stat));
-	stat->program = program;
-
-	/* Create RPC client
- 	 *
-	 * XXX AUTH_UNIX only - need AUTH_GSS....
-	 */
-	sprintf(hostname, "%u.%u.%u.%u", NIPQUAD(addr.sin_addr.s_addr));
-	clnt = rpc_new_client(xprt, hostname, program, 1, RPC_AUTH_UNIX);
-	if (IS_ERR(clnt)) {
+	memset(program->stats, 0, sizeof(cb->cb_stat));
+	program->stats->program = program;
+
+	/* Create RPC client */
+	cb->cb_client = rpc_create(&args);
+	if (!cb->cb_client) {
 		dprintk("NFSD: couldn't create callback client\n");
 		goto out_err;
 	}
-	clnt->cl_intr = 0;
-	clnt->cl_softrtry = 1;
 
 	/* Kick rpciod, put the call on the wire. */
-
-	if (rpciod_up() != 0) {
-		dprintk("nfsd: couldn't start rpciod for callbacks!\n");
+	if (rpciod_up() != 0)
 		goto out_clnt;
-	}
-
-	cb->cb_client = clnt;
 
 	/* the task holds a reference to the nfs4_client struct */
 	atomic_inc(&clp->cl_count);
@@ -448,7 +436,7 @@ nfsd4_probe_callback(struct nfs4_client *clp)
 	msg.rpc_cred = nfsd4_lookupcred(clp,0);
 	if (IS_ERR(msg.rpc_cred))
 		goto out_rpciod;
-	status = rpc_call_async(clnt, &msg, RPC_TASK_ASYNC, &nfs4_cb_null_ops, NULL);
+	status = rpc_call_async(cb->cb_client, &msg, RPC_TASK_ASYNC, &nfs4_cb_null_ops, NULL);
 	put_rpccred(msg.rpc_cred);
 
 	if (status != 0) {
@@ -462,7 +450,7 @@ out_rpciod:
 	rpciod_down();
 	cb->cb_client = NULL;
 out_clnt:
-	rpc_shutdown_client(clnt);
+	rpc_shutdown_client(cb->cb_client);
 out_err:
 	dprintk("NFSD: warning: no callback path to client %.*s\n",
 		(int)clp->cl_name.len, clp->cl_name.data);

include/asm-ppc/ibm4xx.h

@@ -86,7 +86,7 @@ void ppc4xx_init(unsigned long r3, unsigned long r4, unsigned long r5,
 #define PCI_DRAM_OFFSET	0
 #endif
 
-#elif CONFIG_44x
+#elif defined(CONFIG_44x)
 
 #if defined(CONFIG_BAMBOO)
 #include <platforms/4xx/bamboo.h>

include/linux/blkdev.h

@@ -748,6 +748,7 @@ extern void blk_queue_invalidate_tags(request_queue_t *);
 extern long blk_congestion_wait(int rw, long timeout);
 extern struct blk_queue_tag *blk_init_tags(int);
 extern void blk_free_tags(struct blk_queue_tag *);
+extern void blk_congestion_end(int rw);
 
 extern void blk_rq_bio_prep(request_queue_t *, struct request *, struct bio *);
 extern int blkdev_issue_flush(struct block_device *, sector_t *);

include/linux/bootmem.h

@@ -114,7 +114,7 @@ extern void *__init alloc_large_system_hash(const char *tablename,
 #else
 #define HASHDIST_DEFAULT 0
 #endif
-extern int __initdata hashdist;		/* Distribute hashes across NUMA nodes? */
+extern int hashdist;		/* Distribute hashes across NUMA nodes? */
 
 
 #endif /* _LINUX_BOOTMEM_H */

include/linux/dcache.h

@@ -221,6 +221,7 @@ static inline int dname_external(struct dentry *dentry)
  */
 extern void d_instantiate(struct dentry *, struct inode *);
 extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *);
+extern struct dentry * d_materialise_unique(struct dentry *, struct inode *);
 extern void d_delete(struct dentry *);
 
 /* allocate/de-allocate */

include/linux/dccp.h

@@ -438,6 +438,7 @@ struct dccp_ackvec;
  * @dccps_role - Role of this sock, one of %dccp_role
  * @dccps_ndp_count - number of Non Data Packets since last data packet
  * @dccps_hc_rx_ackvec - rx half connection ack vector
+ * @dccps_xmit_timer - timer for when CCID is not ready to send
  */
 struct dccp_sock {
 	/* inet_connection_sock has to be the first member of dccp_sock */
@@ -470,6 +471,7 @@ struct dccp_sock {
 	enum dccp_role			dccps_role:2;
 	__u8				dccps_hc_rx_insert_options:1;
 	__u8				dccps_hc_tx_insert_options:1;
+	struct timer_list		dccps_xmit_timer;
 };
  
 static inline struct dccp_sock *dccp_sk(const struct sock *sk)

include/linux/fib_rules.h

@@ -0,0 +1,65 @@
+#ifndef __LINUX_FIB_RULES_H
+#define __LINUX_FIB_RULES_H
+
+#include <linux/types.h>
+#include <linux/rtnetlink.h>
+
+/* rule is permanent, and cannot be deleted */
+#define FIB_RULE_PERMANENT	1
+
+struct fib_rule_hdr
+{
+	__u8		family;
+	__u8		dst_len;
+	__u8		src_len;
+	__u8		tos;
+
+	__u8		table;
+	__u8		res1;	/* reserved */
+	__u8		res2;	/* reserved */
+	__u8		action;
+
+	__u32		flags;
+};
+
+enum
+{
+	FRA_UNSPEC,
+	FRA_DST,	/* destination address */
+	FRA_SRC,	/* source address */
+	FRA_IFNAME,	/* interface name */
+	FRA_UNUSED1,
+	FRA_UNUSED2,
+	FRA_PRIORITY,	/* priority/preference */
+	FRA_UNUSED3,
+	FRA_UNUSED4,
+	FRA_UNUSED5,
+	FRA_FWMARK,	/* netfilter mark */
+	FRA_FLOW,	/* flow/class id */
+	FRA_UNUSED6,
+	FRA_UNUSED7,
+	FRA_UNUSED8,
+	FRA_TABLE,	/* Extended table id */
+	FRA_FWMASK,	/* mask for netfilter mark */
+	__FRA_MAX
+};
+
+#define FRA_MAX (__FRA_MAX - 1)
+
+enum
+{
+	FR_ACT_UNSPEC,
+	FR_ACT_TO_TBL,		/* Pass to fixed table */
+	FR_ACT_RES1,
+	FR_ACT_RES2,
+	FR_ACT_RES3,
+	FR_ACT_RES4,
+	FR_ACT_BLACKHOLE,	/* Drop without notification */
+	FR_ACT_UNREACHABLE,	/* Drop with ENETUNREACH */
+	FR_ACT_PROHIBIT,	/* Drop with EACCES */
+	__FR_ACT_MAX,
+};
+
+#define FR_ACT_MAX (__FR_ACT_MAX - 1)
+
+#endif

include/linux/filter.h

@@ -25,10 +25,10 @@
  
 struct sock_filter	/* Filter block */
 {
-        __u16	code;   /* Actual filter code */
-        __u8	jt;	/* Jump true */
-        __u8	jf;	/* Jump false */
-        __u32	k;      /* Generic multiuse field */
+	__u16	code;   /* Actual filter code */
+	__u8	jt;	/* Jump true */
+	__u8	jf;	/* Jump false */
+	__u32	k;      /* Generic multiuse field */
 };
 
 struct sock_fprog	/* Required for SO_ATTACH_FILTER. */
@@ -41,8 +41,9 @@ struct sock_fprog	/* Required for SO_ATTACH_FILTER. */
 struct sk_filter
 {
 	atomic_t		refcnt;
-        unsigned int         	len;	/* Number of filter blocks */
-        struct sock_filter     	insns[0];
+	unsigned int         	len;	/* Number of filter blocks */
+	struct rcu_head		rcu;
+	struct sock_filter     	insns[0];
 };
 
 static inline unsigned int sk_filter_len(struct sk_filter *fp)

include/linux/genetlink.h

@@ -16,6 +16,8 @@ struct genlmsghdr {
 
 #define GENL_HDRLEN	NLMSG_ALIGN(sizeof(struct genlmsghdr))
 
+#define GENL_ADMIN_PERM		0x01
+
 /*
  * List of reserved static generic netlink identifiers:
  */
@@ -43,9 +45,25 @@ enum {
 	CTRL_ATTR_UNSPEC,
 	CTRL_ATTR_FAMILY_ID,
 	CTRL_ATTR_FAMILY_NAME,
+	CTRL_ATTR_VERSION,
+	CTRL_ATTR_HDRSIZE,
+	CTRL_ATTR_MAXATTR,
+	CTRL_ATTR_OPS,
 	__CTRL_ATTR_MAX,
 };
 
 #define CTRL_ATTR_MAX (__CTRL_ATTR_MAX - 1)
 
+enum {
+	CTRL_ATTR_OP_UNSPEC,
+	CTRL_ATTR_OP_ID,
+	CTRL_ATTR_OP_FLAGS,
+	CTRL_ATTR_OP_POLICY,
+	CTRL_ATTR_OP_DOIT,
+	CTRL_ATTR_OP_DUMPIT,
+	__CTRL_ATTR_OP_MAX,
+};
+
+#define CTRL_ATTR_OP_MAX (__CTRL_ATTR_OP_MAX - 1)
+
 #endif	/* __LINUX_GENERIC_NETLINK_H */