--- /dev/null
+ ========================================
+ GENERIC ASSOCIATIVE ARRAY IMPLEMENTATION
+ ========================================
+
+Contents:
+
+ - Overview.
+
+ - The public API.
+ - Edit script.
+ - Operations table.
+ - Manipulation functions.
+ - Access functions.
+ - Index key form.
+
+ - Internal workings.
+ - Basic internal tree layout.
+ - Shortcuts.
+ - Splitting and collapsing nodes.
+ - Non-recursive iteration.
+ - Simultaneous alteration and iteration.
+
+
+========
+OVERVIEW
+========
+
+This associative array implementation is an object container with the following
+properties:
+
+ (1) Objects are opaque pointers. The implementation does not care where they
+ point (if anywhere) or what they point to (if anything).
+
+ [!] NOTE: Pointers to objects _must_ be zero in the least significant bit.
+
+ (2) Objects do not need to contain linkage blocks for use by the array. This
+ permits an object to be located in multiple arrays simultaneously.
+ Rather, the array is made up of metadata blocks that point to objects.
+
+ (3) Objects require index keys to locate them within the array.
+
+ (4) Index keys must be unique. Inserting an object with the same key as one
+ already in the array will replace the old object.
+
+ (5) Index keys can be of any length and can be of different lengths.
+
+ (6) Index keys should encode the length early on, before any variation due to
+ length is seen.
+
+ (7) Index keys can include a hash to scatter objects throughout the array.
+
+ (8) The array can iterated over. The objects will not necessarily come out in
+ key order.
+
+ (9) The array can be iterated over whilst it is being modified, provided the
+ RCU readlock is being held by the iterator. Note, however, under these
+ circumstances, some objects may be seen more than once. If this is a
+ problem, the iterator should lock against modification. Objects will not
+ be missed, however, unless deleted.
+
+(10) Objects in the array can be looked up by means of their index key.
+
+(11) Objects can be looked up whilst the array is being modified, provided the
+ RCU readlock is being held by the thread doing the look up.
+
+The implementation uses a tree of 16-pointer nodes internally that are indexed
+on each level by nibbles from the index key in the same manner as in a radix
+tree. To improve memory efficiency, shortcuts can be emplaced to skip over
+what would otherwise be a series of single-occupancy nodes. Further, nodes
+pack leaf object pointers into spare space in the node rather than making an
+extra branch until as such time an object needs to be added to a full node.
+
+
+==============
+THE PUBLIC API
+==============
+
+The public API can be found in <linux/assoc_array.h>. The associative array is
+rooted on the following structure:
+
+ struct assoc_array {
+ ...
+ };
+
+The code is selected by enabling CONFIG_ASSOCIATIVE_ARRAY.
+
+
+EDIT SCRIPT
+-----------
+
+The insertion and deletion functions produce an 'edit script' that can later be
+applied to effect the changes without risking ENOMEM. This retains the
+preallocated metadata blocks that will be installed in the internal tree and
+keeps track of the metadata blocks that will be removed from the tree when the
+script is applied.
+
+This is also used to keep track of dead blocks and dead objects after the
+script has been applied so that they can be freed later. The freeing is done
+after an RCU grace period has passed - thus allowing access functions to
+proceed under the RCU read lock.
+
+The script appears as outside of the API as a pointer of the type:
+
+ struct assoc_array_edit;
+
+There are two functions for dealing with the script:
+
+ (1) Apply an edit script.
+
+ void assoc_array_apply_edit(struct assoc_array_edit *edit);
+
+ This will perform the edit functions, interpolating various write barriers
+ to permit accesses under the RCU read lock to continue. The edit script
+ will then be passed to call_rcu() to free it and any dead stuff it points
+ to.
+
+ (2) Cancel an edit script.
+
+ void assoc_array_cancel_edit(struct assoc_array_edit *edit);
+
+ This frees the edit script and all preallocated memory immediately. If
+ this was for insertion, the new object is _not_ released by this function,
+ but must rather be released by the caller.
+
+These functions are guaranteed not to fail.
+
+
+OPERATIONS TABLE
+----------------
+
+Various functions take a table of operations:
+
+ struct assoc_array_ops {
+ ...
+ };
+
+This points to a number of methods, all of which need to be provided:
+
+ (1) Get a chunk of index key from caller data:
+
+ unsigned long (*get_key_chunk)(const void *index_key, int level);
+
+ This should return a chunk of caller-supplied index key starting at the
+ *bit* position given by the level argument. The level argument will be a
+ multiple of ASSOC_ARRAY_KEY_CHUNK_SIZE and the function should return
+ ASSOC_ARRAY_KEY_CHUNK_SIZE bits. No error is possible.
+
+
+ (2) Get a chunk of an object's index key.
+
+ unsigned long (*get_object_key_chunk)(const void *object, int level);
+
+ As the previous function, but gets its data from an object in the array
+ rather than from a caller-supplied index key.
+
+
+ (3) See if this is the object we're looking for.
+
+ bool (*compare_object)(const void *object, const void *index_key);
+
+ Compare the object against an index key and return true if it matches and
+ false if it doesn't.
+
+
+ (4) Diff the index keys of two objects.
+
+ int (*diff_objects)(const void *a, const void *b);
+
+ Return the bit position at which the index keys of two objects differ or
+ -1 if they are the same.
+
+
+ (5) Free an object.
+
+ void (*free_object)(void *object);
+
+ Free the specified object. Note that this may be called an RCU grace
+ period after assoc_array_apply_edit() was called, so synchronize_rcu() may
+ be necessary on module unloading.
+
+
+MANIPULATION FUNCTIONS
+----------------------
+
+There are a number of functions for manipulating an associative array:
+
+ (1) Initialise an associative array.
+
+ void assoc_array_init(struct assoc_array *array);
+
+ This initialises the base structure for an associative array. It can't
+ fail.
+
+
+ (2) Insert/replace an object in an associative array.
+
+ struct assoc_array_edit *
+ assoc_array_insert(struct assoc_array *array,
+ const struct assoc_array_ops *ops,
+ const void *index_key,
+ void *object);
+
+ This inserts the given object into the array. Note that the least
+ significant bit of the pointer must be zero as it's used to type-mark
+ pointers internally.
+
+ If an object already exists for that key then it will be replaced with the
+ new object and the old one will be freed automatically.
+
+ The index_key argument should hold index key information and is
+ passed to the methods in the ops table when they are called.
+
+ This function makes no alteration to the array itself, but rather returns
+ an edit script that must be applied. -ENOMEM is returned in the case of
+ an out-of-memory error.
+
+ The caller should lock exclusively against other modifiers of the array.
+
+
+ (3) Delete an object from an associative array.
+
+ struct assoc_array_edit *
+ assoc_array_delete(struct assoc_array *array,
+ const struct assoc_array_ops *ops,
+ const void *index_key);
+
+ This deletes an object that matches the specified data from the array.
+
+ The index_key argument should hold index key information and is
+ passed to the methods in the ops table when they are called.
+
+ This function makes no alteration to the array itself, but rather returns
+ an edit script that must be applied. -ENOMEM is returned in the case of
+ an out-of-memory error. NULL will be returned if the specified object is
+ not found within the array.
+
+ The caller should lock exclusively against other modifiers of the array.
+
+
+ (4) Delete all objects from an associative array.
+
+ struct assoc_array_edit *
+ assoc_array_clear(struct assoc_array *array,
+ const struct assoc_array_ops *ops);
+
+ This deletes all the objects from an associative array and leaves it
+ completely empty.
+
+ This function makes no alteration to the array itself, but rather returns
+ an edit script that must be applied. -ENOMEM is returned in the case of
+ an out-of-memory error.
+
+ The caller should lock exclusively against other modifiers of the array.
+
+
+ (5) Destroy an associative array, deleting all objects.
+
+ void assoc_array_destroy(struct assoc_array *array,
+ const struct assoc_array_ops *ops);
+
+ This destroys the contents of the associative array and leaves it
+ completely empty. It is not permitted for another thread to be traversing
+ the array under the RCU read lock at the same time as this function is
+ destroying it as no RCU deferral is performed on memory release -
+ something that would require memory to be allocated.
+
+ The caller should lock exclusively against other modifiers and accessors
+ of the array.
+
+
+ (6) Garbage collect an associative array.
+
+ int assoc_array_gc(struct assoc_array *array,
+ const struct assoc_array_ops *ops,
+ bool (*iterator)(void *object, void *iterator_data),
+ void *iterator_data);
+
+ This iterates over the objects in an associative array and passes each one
+ to iterator(). If iterator() returns true, the object is kept. If it
+ returns false, the object will be freed. If the iterator() function
+ returns true, it must perform any appropriate refcount incrementing on the
+ object before returning.
+
+ The internal tree will be packed down if possible as part of the iteration
+ to reduce the number of nodes in it.
+
+ The iterator_data is passed directly to iterator() and is otherwise
+ ignored by the function.
+
+ The function will return 0 if successful and -ENOMEM if there wasn't
+ enough memory.
+
+ It is possible for other threads to iterate over or search the array under
+ the RCU read lock whilst this function is in progress. The caller should
+ lock exclusively against other modifiers of the array.
+
+
+ACCESS FUNCTIONS
+----------------
+
+There are two functions for accessing an associative array:
+
+ (1) Iterate over all the objects in an associative array.
+
+ int assoc_array_iterate(const struct assoc_array *array,
+ int (*iterator)(const void *object,
+ void *iterator_data),
+ void *iterator_data);
+
+ This passes each object in the array to the iterator callback function.
+ iterator_data is private data for that function.
+
+ This may be used on an array at the same time as the array is being
+ modified, provided the RCU read lock is held. Under such circumstances,
+ it is possible for the iteration function to see some objects twice. If
+ this is a problem, then modification should be locked against. The
+ iteration algorithm should not, however, miss any objects.
+
+ The function will return 0 if no objects were in the array or else it will
+ return the result of the last iterator function called. Iteration stops
+ immediately if any call to the iteration function results in a non-zero
+ return.
+
+
+ (2) Find an object in an associative array.
+
+ void *assoc_array_find(const struct assoc_array *array,
+ const struct assoc_array_ops *ops,
+ const void *index_key);
+
+ This walks through the array's internal tree directly to the object
+ specified by the index key..
+
+ This may be used on an array at the same time as the array is being
+ modified, provided the RCU read lock is held.
+
+ The function will return the object if found (and set *_type to the object
+ type) or will return NULL if the object was not found.
+
+
+INDEX KEY FORM
+--------------
+
+The index key can be of any form, but since the algorithms aren't told how long
+the key is, it is strongly recommended that the index key includes its length
+very early on before any variation due to the length would have an effect on
+comparisons.
+
+This will cause leaves with different length keys to scatter away from each
+other - and those with the same length keys to cluster together.
+
+It is also recommended that the index key begin with a hash of the rest of the
+key to maximise scattering throughout keyspace.
+
+The better the scattering, the wider and lower the internal tree will be.
+
+Poor scattering isn't too much of a problem as there are shortcuts and nodes
+can contain mixtures of leaves and metadata pointers.
+
+The index key is read in chunks of machine word. Each chunk is subdivided into
+one nibble (4 bits) per level, so on a 32-bit CPU this is good for 8 levels and
+on a 64-bit CPU, 16 levels. Unless the scattering is really poor, it is
+unlikely that more than one word of any particular index key will have to be
+used.
+
+
+=================
+INTERNAL WORKINGS
+=================
+
+The associative array data structure has an internal tree. This tree is
+constructed of two types of metadata blocks: nodes and shortcuts.
+
+A node is an array of slots. Each slot can contain one of four things:
+
+ (*) A NULL pointer, indicating that the slot is empty.
+
+ (*) A pointer to an object (a leaf).
+
+ (*) A pointer to a node at the next level.
+
+ (*) A pointer to a shortcut.
+
+
+BASIC INTERNAL TREE LAYOUT
+--------------------------
+
+Ignoring shortcuts for the moment, the nodes form a multilevel tree. The index
+key space is strictly subdivided by the nodes in the tree and nodes occur on
+fixed levels. For example:
+
+ Level: 0 1 2 3
+ =============== =============== =============== ===============
+ NODE D
+ NODE B NODE C +------>+---+
+ +------>+---+ +------>+---+ | | 0 |
+ NODE A | | 0 | | | 0 | | +---+
+ +---+ | +---+ | +---+ | : :
+ | 0 | | : : | : : | +---+
+ +---+ | +---+ | +---+ | | f |
+ | 1 |---+ | 3 |---+ | 7 |---+ +---+
+ +---+ +---+ +---+
+ : : : : | 8 |---+
+ +---+ +---+ +---+ | NODE E
+ | e |---+ | f | : : +------>+---+
+ +---+ | +---+ +---+ | 0 |
+ | f | | | f | +---+
+ +---+ | +---+ : :
+ | NODE F +---+
+ +------>+---+ | f |
+ | 0 | NODE G +---+
+ +---+ +------>+---+
+ : : | | 0 |
+ +---+ | +---+
+ | 6 |---+ : :
+ +---+ +---+
+ : : | f |
+ +---+ +---+
+ | f |
+ +---+
+
+In the above example, there are 7 nodes (A-G), each with 16 slots (0-f).
+Assuming no other meta data nodes in the tree, the key space is divided thusly:
+
+ KEY PREFIX NODE
+ ========== ====
+ 137* D
+ 138* E
+ 13[0-69-f]* C
+ 1[0-24-f]* B
+ e6* G
+ e[0-57-f]* F
+ [02-df]* A
+
+So, for instance, keys with the following example index keys will be found in
+the appropriate nodes:
+
+ INDEX KEY PREFIX NODE
+ =============== ======= ====
+ 13694892892489 13 C
+ 13795289025897 137 D
+ 13889dde88793 138 E
+ 138bbb89003093 138 E
+ 1394879524789 12 C
+ 1458952489 1 B
+ 9431809de993ba - A
+ b4542910809cd - A
+ e5284310def98 e F
+ e68428974237 e6 G
+ e7fffcbd443 e F
+ f3842239082 - A
+
+To save memory, if a node can hold all the leaves in its portion of keyspace,
+then the node will have all those leaves in it and will not have any metadata
+pointers - even if some of those leaves would like to be in the same slot.
+
+A node can contain a heterogeneous mix of leaves and metadata pointers.
+Metadata pointers must be in the slots that match their subdivisions of key
+space. The leaves can be in any slot not occupied by a metadata pointer. It
+is guaranteed that none of the leaves in a node will match a slot occupied by a
+metadata pointer. If the metadata pointer is there, any leaf whose key matches
+the metadata key prefix must be in the subtree that the metadata pointer points
+to.
+
+In the above example list of index keys, node A will contain:
+
+ SLOT CONTENT INDEX KEY (PREFIX)
+ ==== =============== ==================
+ 1 PTR TO NODE B 1*
+ any LEAF 9431809de993ba
+ any LEAF b4542910809cd
+ e PTR TO NODE F e*
+ any LEAF f3842239082
+
+and node B:
+
+ 3 PTR TO NODE C 13*
+ any LEAF 1458952489
+
+
+SHORTCUTS
+---------
+
+Shortcuts are metadata records that jump over a piece of keyspace. A shortcut
+is a replacement for a series of single-occupancy nodes ascending through the
+levels. Shortcuts exist to save memory and to speed up traversal.
+
+It is possible for the root of the tree to be a shortcut - say, for example,
+the tree contains at least 17 nodes all with key prefix '1111'. The insertion
+algorithm will insert a shortcut to skip over the '1111' keyspace in a single
+bound and get to the fourth level where these actually become different.
+
+
+SPLITTING AND COLLAPSING NODES
+------------------------------
+
+Each node has a maximum capacity of 16 leaves and metadata pointers. If the
+insertion algorithm finds that it is trying to insert a 17th object into a
+node, that node will be split such that at least two leaves that have a common
+key segment at that level end up in a separate node rooted on that slot for
+that common key segment.
+
+If the leaves in a full node and the leaf that is being inserted are
+sufficiently similar, then a shortcut will be inserted into the tree.
+
+When the number of objects in the subtree rooted at a node falls to 16 or
+fewer, then the subtree will be collapsed down to a single node - and this will
+ripple towards the root if possible.
+
+
+NON-RECURSIVE ITERATION
+-----------------------
+
+Each node and shortcut contains a back pointer to its parent and the number of
+slot in that parent that points to it. None-recursive iteration uses these to
+proceed rootwards through the tree, going to the parent node, slot N + 1 to
+make sure progress is made without the need for a stack.
+
+The backpointers, however, make simultaneous alteration and iteration tricky.
+
+
+SIMULTANEOUS ALTERATION AND ITERATION
+-------------------------------------
+
+There are a number of cases to consider:
+
+ (1) Simple insert/replace. This involves simply replacing a NULL or old
+ matching leaf pointer with the pointer to the new leaf after a barrier.
+ The metadata blocks don't change otherwise. An old leaf won't be freed
+ until after the RCU grace period.
+
+ (2) Simple delete. This involves just clearing an old matching leaf. The
+ metadata blocks don't change otherwise. The old leaf won't be freed until
+ after the RCU grace period.
+
+ (3) Insertion replacing part of a subtree that we haven't yet entered. This
+ may involve replacement of part of that subtree - but that won't affect
+ the iteration as we won't have reached the pointer to it yet and the
+ ancestry blocks are not replaced (the layout of those does not change).
+
+ (4) Insertion replacing nodes that we're actively processing. This isn't a
+ problem as we've passed the anchoring pointer and won't switch onto the
+ new layout until we follow the back pointers - at which point we've
+ already examined the leaves in the replaced node (we iterate over all the
+ leaves in a node before following any of its metadata pointers).
+
+ We might, however, re-see some leaves that have been split out into a new
+ branch that's in a slot further along than we were at.
+
+ (5) Insertion replacing nodes that we're processing a dependent branch of.
+ This won't affect us until we follow the back pointers. Similar to (4).
+
+ (6) Deletion collapsing a branch under us. This doesn't affect us because the
+ back pointers will get us back to the parent of the new node before we
+ could see the new node. The entire collapsed subtree is thrown away
+ unchanged - and will still be rooted on the same slot, so we shouldn't
+ process it a second time as we'll go back to slot + 1.
+
+Note:
+
+ (*) Under some circumstances, we need to simultaneously change the parent
+ pointer and the parent slot pointer on a node (say, for example, we
+ inserted another node before it and moved it up a level). We cannot do
+ this without locking against a read - so we have to replace that node too.
+
+ However, when we're changing a shortcut into a node this isn't a problem
+ as shortcuts only have one slot and so the parent slot number isn't used
+ when traversing backwards over one. This means that it's okay to change
+ the slot number first - provided suitable barriers are used to make sure
+ the parent slot number is read after the back pointer.
+
+Obsolete blocks and leaves are freed up after an RCU grace period has passed,
+so as long as anyone doing walking or iteration holds the RCU read lock, the
+old superstructure should not go away on them.
adt7461 +/-1C TDM Extended Temp Range I.C
at,24c08 i2c serial eeprom (24cxx)
atmel,24c02 i2c serial eeprom (24cxx)
+atmel,at97sc3204t i2c trusted platform module (TPM)
catalyst,24c32 i2c serial eeprom
dallas,ds1307 64 x 8, Serial, I2C Real-Time Clock
dallas,ds1338 I2C RTC with 56-Byte NV RAM
fsl,mma8450 MMA8450Q: Xtrinsic Low-power, 3-axis Xtrinsic Accelerometer
fsl,mpr121 MPR121: Proximity Capacitive Touch Sensor Controller
fsl,sgtl5000 SGTL5000: Ultra Low-Power Audio Codec
+gmt,g751 G751: Digital Temperature Sensor and Thermal Watchdog with Two-Wire Interface
infineon,slb9635tt Infineon SLB9635 (Soft-) I2C TPM (old protocol, max 100khz)
infineon,slb9645tt Infineon SLB9645 I2C TPM (new protocol, max 400khz)
maxim,ds1050 5 Bit Programmable, Pulse-Width Modulator
national,lm75 I2C TEMP SENSOR
national,lm80 Serial Interface ACPI-Compatible Microprocessor System Hardware Monitor
national,lm92 ±0.33°C Accurate, 12-Bit + Sign Temperature Sensor and Thermal Window Comparator with Two-Wire Interface
+nuvoton,npct501 i2c trusted platform module (TPM)
nxp,pca9556 Octal SMBus and I2C registered interface
nxp,pca9557 8-bit I2C-bus and SMBus I/O port with reset
nxp,pcf8563 Real-time clock/calendar
ti,tsc2003 I2C Touch-Screen Controller
ti,tmp102 Low Power Digital Temperature Sensor with SMBUS/Two Wire Serial Interface
ti,tmp275 Digital Temperature Sensor
+winbond,wpct301 i2c trusted platform module (TPM)
See comments at the top of fs/btrfs/check-integrity.c for more info.
+ commit=<seconds>
+ Set the interval of periodic commit, 30 seconds by default. Higher
+ values defer data being synced to permanent storage with obvious
+ consequences when the system crashes. The upper bound is not forced,
+ but a warning is printed if it's more than 300 seconds (5 minutes).
+
compress
compress=<type>
compress-force
Currently this scans a list of several previous tree roots and tries to
use the first readable.
- skip_balance
+ rescan_uuid_tree
+ Force check and rebuild procedure of the UUID tree. This should not
+ normally be needed.
+
+ skip_balance
Skip automatic resume of interrupted balance operation after mount.
May be resumed with "btrfs balance resume."
These include the following tools:
-mkfs.btrfs: create a filesystem
-
-btrfsctl: control program to create snapshots and subvolumes:
+* mkfs.btrfs: create a filesystem
- mount /dev/sda2 /mnt
- btrfsctl -s new_subvol_name /mnt
- btrfsctl -s snapshot_of_default /mnt/default
- btrfsctl -s snapshot_of_new_subvol /mnt/new_subvol_name
- btrfsctl -s snapshot_of_a_snapshot /mnt/snapshot_of_new_subvol
- ls /mnt
- default snapshot_of_a_snapshot snapshot_of_new_subvol
- new_subvol_name snapshot_of_default
+* btrfs: a single tool to manage the filesystems, refer to the manpage for more details
- Snapshots and subvolumes cannot be deleted right now, but you can
- rm -rf all the files and directories inside them.
+* 'btrfsck' or 'btrfs check': do a consistency check of the filesystem
-btrfsck: do a limited check of the FS extent trees.
+Other tools for specific tasks:
-btrfs-debug-tree: print all of the FS metadata in text form. Example:
+* btrfs-convert: in-place conversion from ext2/3/4 filesystems
- btrfs-debug-tree /dev/sda2 >& big_output_file
+* btrfs-image: dump filesystem metadata for debugging
owned by uid=0.
ima_hash= [IMA]
- Format: { "sha1" | "md5" }
+ Format: { md5 | sha1 | rmd160 | sha256 | sha384
+ | sha512 | ... }
default: "sha1"
+ The list of supported hash algorithms is defined
+ in crypto/hash_info.h.
+
ima_tcb [IMA]
Load a policy which meets the needs of the Trusted
Computing Base. This means IMA will measure all
programs exec'd, files mmap'd for exec, and all files
opened for read by uid=0.
+ ima_template= [IMA]
+ Select one of defined IMA measurements template formats.
+ Formats: { "ima" | "ima-ng" }
+ Default: "ima-ng"
+
init= [KNL]
Format: <full_path>
Run specified binary instead of /sbin/init as init
- description of the kernel key retention service.
tomoyo.txt
- documentation on the TOMOYO Linux Security Module.
+IMA-templates.txt
+ - documentation on the template management mechanism for IMA.
--- /dev/null
+ IMA Template Management Mechanism
+
+
+==== INTRODUCTION ====
+
+The original 'ima' template is fixed length, containing the filedata hash
+and pathname. The filedata hash is limited to 20 bytes (md5/sha1).
+The pathname is a null terminated string, limited to 255 characters.
+To overcome these limitations and to add additional file metadata, it is
+necessary to extend the current version of IMA by defining additional
+templates. For example, information that could be possibly reported are
+the inode UID/GID or the LSM labels either of the inode and of the process
+that is accessing it.
+
+However, the main problem to introduce this feature is that, each time
+a new template is defined, the functions that generate and display
+the measurements list would include the code for handling a new format
+and, thus, would significantly grow over the time.
+
+The proposed solution solves this problem by separating the template
+management from the remaining IMA code. The core of this solution is the
+definition of two new data structures: a template descriptor, to determine
+which information should be included in the measurement list; a template
+field, to generate and display data of a given type.
+
+Managing templates with these structures is very simple. To support
+a new data type, developers define the field identifier and implement
+two functions, init() and show(), respectively to generate and display
+measurement entries. Defining a new template descriptor requires
+specifying the template format, a string of field identifiers separated
+by the '|' character. While in the current implementation it is possible
+to define new template descriptors only by adding their definition in the
+template specific code (ima_template.c), in a future version it will be
+possible to register a new template on a running kernel by supplying to IMA
+the desired format string. In this version, IMA initializes at boot time
+all defined template descriptors by translating the format into an array
+of template fields structures taken from the set of the supported ones.
+
+After the initialization step, IMA will call ima_alloc_init_template()
+(new function defined within the patches for the new template management
+mechanism) to generate a new measurement entry by using the template
+descriptor chosen through the kernel configuration or through the newly
+introduced 'ima_template=' kernel command line parameter. It is during this
+phase that the advantages of the new architecture are clearly shown:
+the latter function will not contain specific code to handle a given template
+but, instead, it simply calls the init() method of the template fields
+associated to the chosen template descriptor and store the result (pointer
+to allocated data and data length) in the measurement entry structure.
+
+The same mechanism is employed to display measurements entries.
+The functions ima[_ascii]_measurements_show() retrieve, for each entry,
+the template descriptor used to produce that entry and call the show()
+method for each item of the array of template fields structures.
+
+
+
+==== SUPPORTED TEMPLATE FIELDS AND DESCRIPTORS ====
+
+In the following, there is the list of supported template fields
+('<identifier>': description), that can be used to define new template
+descriptors by adding their identifier to the format string
+(support for more data types will be added later):
+
+ - 'd': the digest of the event (i.e. the digest of a measured file),
+ calculated with the SHA1 or MD5 hash algorithm;
+ - 'n': the name of the event (i.e. the file name), with size up to 255 bytes;
+ - 'd-ng': the digest of the event, calculated with an arbitrary hash
+ algorithm (field format: [<hash algo>:]digest, where the digest
+ prefix is shown only if the hash algorithm is not SHA1 or MD5);
+ - 'n-ng': the name of the event, without size limitations.
+
+
+Below, there is the list of defined template descriptors:
+ - "ima": its format is 'd|n';
+ - "ima-ng" (default): its format is 'd-ng|n-ng'.
+
+
+
+==== USE ====
+
+To specify the template descriptor to be used to generate measurement entries,
+currently the following methods are supported:
+
+ - select a template descriptor among those supported in the kernel
+ configuration ('ima-ng' is the default choice);
+ - specify a template descriptor name from the kernel command line through
+ the 'ima_template=' parameter.
calling processes has a searchable link to the key from one of its
keyrings. There are three functions for dealing with these:
- key_ref_t make_key_ref(const struct key *key,
- unsigned long possession);
+ key_ref_t make_key_ref(const struct key *key, bool possession);
struct key *key_ref_to_ptr(const key_ref_t key_ref);
- unsigned long is_key_possessed(const key_ref_t key_ref);
+ bool is_key_possessed(const key_ref_t key_ref);
The first function constructs a key reference from a key pointer and
- possession information (which must be 0 or 1 and not any other value).
+ possession information (which must be true or false).
The second function retrieves the key pointer from a reference and the
third retrieves the possession flag.
the argument will not be parsed.
-(*) Extra references can be made to a key by calling the following function:
+(*) Extra references can be made to a key by calling one of the following
+ functions:
+ struct key *__key_get(struct key *key);
struct key *key_get(struct key *key);
- These need to be disposed of by calling key_put() when they've been
- finished with. The key pointer passed in will be returned. If the pointer
- is NULL or CONFIG_KEYS is not set then the key will not be dereferenced and
- no increment will take place.
+ Keys so references will need to be disposed of by calling key_put() when
+ they've been finished with. The key pointer passed in will be returned.
+
+ In the case of key_get(), if the pointer is NULL or CONFIG_KEYS is not set
+ then the key will not be dereferenced and no increment will take place.
(*) A key's serial number can be obtained by calling:
buf += " /*\n"
buf += " * Setup default attribute lists for various fabric->tf_cit_tmpl\n"
buf += " */\n"
- buf += " TF_CIT_TMPL(fabric)->tfc_wwn_cit.ct_attrs = " + fabric_mod_name + "_wwn_attrs;\n"
- buf += " TF_CIT_TMPL(fabric)->tfc_tpg_base_cit.ct_attrs = NULL;\n"
- buf += " TF_CIT_TMPL(fabric)->tfc_tpg_attrib_cit.ct_attrs = NULL;\n"
- buf += " TF_CIT_TMPL(fabric)->tfc_tpg_param_cit.ct_attrs = NULL;\n"
- buf += " TF_CIT_TMPL(fabric)->tfc_tpg_np_base_cit.ct_attrs = NULL;\n"
- buf += " TF_CIT_TMPL(fabric)->tfc_tpg_nacl_base_cit.ct_attrs = NULL;\n"
- buf += " TF_CIT_TMPL(fabric)->tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;\n"
- buf += " TF_CIT_TMPL(fabric)->tfc_tpg_nacl_auth_cit.ct_attrs = NULL;\n"
- buf += " TF_CIT_TMPL(fabric)->tfc_tpg_nacl_param_cit.ct_attrs = NULL;\n"
+ buf += " fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = " + fabric_mod_name + "_wwn_attrs;\n"
+ buf += " fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = NULL;\n"
+ buf += " fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL;\n"
+ buf += " fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;\n"
+ buf += " fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;\n"
+ buf += " fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL;\n"
+ buf += " fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;\n"
+ buf += " fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL;\n"
+ buf += " fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL;\n"
buf += " /*\n"
buf += " * Register the fabric for use within TCM\n"
buf += " */\n"
PMD split lock enabling requires pgtable_pmd_page_ctor() call on PMD table
allocation and pgtable_pmd_page_dtor() on freeing.
-Allocation usually happens in pmd_alloc_one(), freeing in pmd_free(), but
-make sure you cover all PMD table allocation / freeing paths: i.e X86_PAE
-preallocate few PMDs on pgd_alloc().
+Allocation usually happens in pmd_alloc_one(), freeing in pmd_free() and
+pmd_free_tlb(), but make sure you cover all PMD table allocation / freeing
+paths: i.e X86_PAE preallocate few PMDs on pgd_alloc().
With everything in place you can set CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK.
F: arch/x86/kernel/cpu/mshyperv.c
F: drivers/hid/hid-hyperv.c
F: drivers/hv/
+F: drivers/input/serio/hyperv-keyboard.c
F: drivers/net/hyperv/
F: drivers/scsi/storvsc_drv.c
F: drivers/video/hyperv_fb.c
M: Stephen Smalley <sds@tycho.nsa.gov>
M: James Morris <james.l.morris@oracle.com>
M: Eric Paris <eparis@parisplace.org>
+M: Paul Moore <paul@paul-moore.com>
L: selinux@tycho.nsa.gov (subscribers-only, general discussion)
W: http://selinuxproject.org
-T: git git://git.infradead.org/users/eparis/selinux.git
+T: git git://git.infradead.org/users/pcmoore/selinux
S: Supported
F: include/linux/selinux*
F: security/selinux/
TPM DEVICE DRIVER
M: Leonidas Da Silva Barbosa <leosilva@linux.vnet.ibm.com>
M: Ashley Lai <ashley@ashleylai.com>
+M: Peter Huewe <peterhuewe@gmx.de>
M: Rajiv Andrade <mail@srajiv.net>
W: http://tpmdd.sourceforge.net
M: Marcel Selhorst <tpmdd@selhorst.net>
XFS FILESYSTEM
P: Silicon Graphics Inc
+M: Dave Chinner <dchinner@fromorbit.com>
M: Ben Myers <bpm@sgi.com>
-M: Alex Elder <elder@kernel.org>
M: xfs@oss.sgi.com
L: xfs@oss.sgi.com
W: http://oss.sgi.com/projects/xfs
VERSION = 3
-PATCHLEVEL = 12
+PATCHLEVEL = 13
SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc1
NAME = One Giant Leap for Frogkind
# *DOCUMENTATION*
select HARDIRQS_SW_RESEND
select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
select HAVE_ARCH_KGDB
- select HAVE_ARCH_SECCOMP_FILTER
+ select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT)
select HAVE_ARCH_TRACEHOOK
select HAVE_BPF_JIT
select HAVE_CONTEXT_TRACKING
bool "Architected timer support"
depends on CPU_V7
select ARM_ARCH_TIMER
+ select GENERIC_CLOCKEVENTS
help
This option enables support for the ARM architected timer
config OABI_COMPAT
bool "Allow old ABI binaries to run with this kernel (EXPERIMENTAL)"
depends on AEABI && !THUMB2_KERNEL
- default y
help
This option preserves the old syscall interface along with the
new (ARM EABI) one. It also provides a compatibility layer to
in memory differs between the legacy ABI and the new ARM EABI
(only for non "thumb" binaries). This option adds a tiny
overhead to all syscalls and produces a slightly larger kernel.
+
+ The seccomp filter system will not be available when this is
+ selected, since there is no way yet to sensibly distinguish
+ between calling conventions during filtering.
+
If you know you'll be using only pure EABI user space then you
can say N here. If this option is not selected and you attempt
to execute a legacy ABI binary then the result will be
UNPREDICTABLE (in fact it can be predicted that it won't work
- at all). If in doubt say Y.
+ at all). If in doubt say N.
config ARCH_HAS_HOLES_MEMORYMODEL
bool
static inline unsigned long __phys_to_virt(phys_addr_t x)
{
unsigned long t;
- __pv_stub(x, t, "sub", __PV_BITS_31_24);
+
+ /*
+ * 'unsigned long' cast discard upper word when
+ * phys_addr_t is 64 bit, and makes sure that inline
+ * assembler expression receives 32 bit argument
+ * in place where 'r' 32 bit operand is expected.
+ */
+ __pv_stub((unsigned long) x, t, "sub", __PV_BITS_31_24);
return t;
}
teq r0, #0x0 @ '0' on actual UP A9 hardware
beq __fixup_smp_on_up @ So its an A9 UP
ldr r0, [r0, #4] @ read SCU Config
+ARM_BE8(rev r0, r0) @ byteswap if big endian
and r0, r0, #0x3 @ number of CPUs
teq r0, #0x0 @ is 1?
movne pc, lr
ldrcc r7, [r4], #4 @ use branch for delay slot
bcc 1b
bx lr
+#else
+#ifdef CONFIG_CPU_ENDIAN_BE8
+ moveq r0, #0x00004000 @ set bit 22, mov to mvn instruction
#else
moveq r0, #0x400000 @ set bit 22, mov to mvn instruction
+#endif
b 2f
1: ldr ip, [r7, r3]
#ifdef CONFIG_CPU_ENDIAN_BE8
tst ip, #0x000f0000 @ check the rotation field
orrne ip, ip, r6, lsl #24 @ mask in offset bits 31-24
biceq ip, ip, #0x00004000 @ clear bit 22
- orreq ip, ip, r0, lsl #24 @ mask in offset bits 7-0
+ orreq ip, ip, r0 @ mask in offset bits 7-0
#else
bic ip, ip, #0x000000ff
tst ip, #0xf00 @ check the rotation field
memcpy(vectors + 0xfe0, vectors + 0xfe8, 4);
}
#else
-static void __init kuser_init(void *vectors)
+static inline void __init kuser_init(void *vectors)
{
}
#endif
return err;
}
+static phys_addr_t kvm_kaddr_to_phys(void *kaddr)
+{
+ if (!is_vmalloc_addr(kaddr)) {
+ BUG_ON(!virt_addr_valid(kaddr));
+ return __pa(kaddr);
+ } else {
+ return page_to_phys(vmalloc_to_page(kaddr)) +
+ offset_in_page(kaddr);
+ }
+}
+
/**
* create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode
* @from: The virtual kernel start address of the range
*/
int create_hyp_mappings(void *from, void *to)
{
- unsigned long phys_addr = virt_to_phys(from);
+ phys_addr_t phys_addr;
+ unsigned long virt_addr;
unsigned long start = KERN_TO_HYP((unsigned long)from);
unsigned long end = KERN_TO_HYP((unsigned long)to);
- /* Check for a valid kernel memory mapping */
- if (!virt_addr_valid(from) || !virt_addr_valid(to - 1))
- return -EINVAL;
+ start = start & PAGE_MASK;
+ end = PAGE_ALIGN(end);
- return __create_hyp_mappings(hyp_pgd, start, end,
- __phys_to_pfn(phys_addr), PAGE_HYP);
+ for (virt_addr = start; virt_addr < end; virt_addr += PAGE_SIZE) {
+ int err;
+
+ phys_addr = kvm_kaddr_to_phys(from + virt_addr - start);
+ err = __create_hyp_mappings(hyp_pgd, virt_addr,
+ virt_addr + PAGE_SIZE,
+ __phys_to_pfn(phys_addr),
+ PAGE_HYP);
+ if (err)
+ return err;
+ }
+
+ return 0;
}
/**
and r3, r0, #31 @ Get bit offset
mov r0, r0, lsr #5
add r1, r1, r0, lsl #2 @ Get word offset
-#if __LINUX_ARM_ARCH__ >= 7
+#if __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
.arch_extension mp
ALT_SMP(W(pldw) [r1])
ALT_UP(W(nop))
mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_WB;
break;
}
- printk("Memory policy: ECC %sabled, Data cache %s\n",
- ecc_mask ? "en" : "dis", cp->policy);
+ pr_info("Memory policy: %sData cache %s\n",
+ ecc_mask ? "ECC enabled, " : "", cp->policy);
for (i = 0; i < ARRAY_SIZE(mem_types); i++) {
struct mem_type *t = &mem_types[i];
#include <asm/mach/arch.h>
#include <asm/cputype.h>
#include <asm/mpu.h>
+#include <asm/procinfo.h>
#include "mm.h"
/* Suspend/resume support: derived from arch/arm/mach-s5pv210/sleep.S */
.globl cpu_v7_suspend_size
-.equ cpu_v7_suspend_size, 4 * 8
+.equ cpu_v7_suspend_size, 4 * 9
#ifdef CONFIG_ARM_CPU_SUSPEND
ENTRY(cpu_v7_do_suspend)
stmfd sp!, {r4 - r10, lr}
stmia r0!, {r4 - r5}
#ifdef CONFIG_MMU
mrc p15, 0, r6, c3, c0, 0 @ Domain ID
+#ifdef CONFIG_ARM_LPAE
+ mrrc p15, 1, r5, r7, c2 @ TTB 1
+#else
mrc p15, 0, r7, c2, c0, 1 @ TTB 1
+#endif
mrc p15, 0, r11, c2, c0, 2 @ TTB control register
#endif
mrc p15, 0, r8, c1, c0, 0 @ Control register
mrc p15, 0, r9, c1, c0, 1 @ Auxiliary control register
mrc p15, 0, r10, c1, c0, 2 @ Co-processor access control
- stmia r0, {r6 - r11}
+ stmia r0, {r5 - r11}
ldmfd sp!, {r4 - r10, pc}
ENDPROC(cpu_v7_do_suspend)
ldmia r0!, {r4 - r5}
mcr p15, 0, r4, c13, c0, 0 @ FCSE/PID
mcr p15, 0, r5, c13, c0, 3 @ User r/o thread ID
- ldmia r0, {r6 - r11}
+ ldmia r0, {r5 - r11}
#ifdef CONFIG_MMU
mcr p15, 0, ip, c8, c7, 0 @ invalidate TLBs
mcr p15, 0, r6, c3, c0, 0 @ Domain ID
-#ifndef CONFIG_ARM_LPAE
+#ifdef CONFIG_ARM_LPAE
+ mcrr p15, 0, r1, ip, c2 @ TTB 0
+ mcrr p15, 1, r5, r7, c2 @ TTB 1
+#else
ALT_SMP(orr r1, r1, #TTB_FLAGS_SMP)
ALT_UP(orr r1, r1, #TTB_FLAGS_UP)
-#endif
mcr p15, 0, r1, c2, c0, 0 @ TTB 0
mcr p15, 0, r7, c2, c0, 1 @ TTB 1
+#endif
mcr p15, 0, r11, c2, c0, 2 @ TTB control register
ldr r4, =PRRR @ PRRR
ldr r5, =NMRR @ NMRR
extern int spinning_secondaries;
extern void cpu_die(void);
+extern int cpu_to_chip_id(int cpu);
#ifdef CONFIG_SMP
}
extern int cpu_to_core_id(int cpu);
-extern int cpu_to_chip_id(int cpu);
/* Since OpenPIC has only 4 IPIs, we use slightly different message numbers.
*
for (i = 0; i < 16; i++)
eeh_ops->read_config(dn, i * 4, 4, &edev->config_space[i]);
+
+ /*
+ * For PCI bridges including root port, we need enable bus
+ * master explicitly. Otherwise, it can't fetch IODA table
+ * entries correctly. So we cache the bit in advance so that
+ * we can restore it after reset, either PHB range or PE range.
+ */
+ if (edev->mode & EEH_DEV_BRIDGE)
+ edev->config_space[1] |= PCI_COMMAND_MASTER;
}
/**
pe = event->pe;
if (pe) {
eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
- pr_info("EEH: Detected PCI bus error on PHB#%d-PE#%x\n",
- pe->phb->global_number, pe->addr);
+ if (pe->type & EEH_PE_PHB)
+ pr_info("EEH: Detected error on PHB#%d\n",
+ pe->phb->global_number);
+ else
+ pr_info("EEH: Detected PCI bus error on "
+ "PHB#%d-PE#%x\n",
+ pe->phb->global_number, pe->addr);
eeh_handle_event(pe);
eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
} else {
printk("MSR: "REG" ", regs->msr);
printbits(regs->msr, msr_bits);
printk(" CR: %08lx XER: %08lx\n", regs->ccr, regs->xer);
-#ifdef CONFIG_PPC64
- printk("SOFTE: %ld\n", regs->softe);
-#endif
trap = TRAP(regs);
if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR))
- printk("CFAR: "REG"\n", regs->orig_gpr3);
- if (trap == 0x300 || trap == 0x600)
+ printk("CFAR: "REG" ", regs->orig_gpr3);
+ if (trap == 0x200 || trap == 0x300 || trap == 0x600)
#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
- printk("DEAR: "REG", ESR: "REG"\n", regs->dar, regs->dsisr);
+ printk("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr);
#else
- printk("DAR: "REG", DSISR: %08lx\n", regs->dar, regs->dsisr);
+ printk("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr);
+#endif
+#ifdef CONFIG_PPC64
+ printk("SOFTE: %ld ", regs->softe);
+#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ if (MSR_TM_ACTIVE(regs->msr))
+ printk("\nPACATMSCRATCH: %016llx ", get_paca()->tm_scratch);
#endif
for (i = 0; i < 32; i++) {
*/
printk("NIP ["REG"] %pS\n", regs->nip, (void *)regs->nip);
printk("LR ["REG"] %pS\n", regs->link, (void *)regs->link);
-#endif
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
- printk("PACATMSCRATCH [%llx]\n", get_paca()->tm_scratch);
#endif
show_stack(current, (unsigned long *) regs->gpr[1]);
if (!user_mode(regs))
return -1;
}
+/**
+ * cpu_to_chip_id - Return the cpus chip-id
+ * @cpu: The logical cpu number.
+ *
+ * Return the value of the ibm,chip-id property corresponding to the given
+ * logical cpu number. If the chip-id can not be found, returns -1.
+ */
+int cpu_to_chip_id(int cpu)
+{
+ struct device_node *np;
+
+ np = of_get_cpu_node(cpu, NULL);
+ if (!np)
+ return -1;
+
+ of_node_put(np);
+ return of_get_ibm_chip_id(np);
+}
+EXPORT_SYMBOL(cpu_to_chip_id);
+
#ifdef CONFIG_PPC_PSERIES
/*
* Fix up the uninitialized fields in a new device node:
if (copy_vsx_to_user(&frame->mc_vsregs, current))
return 1;
msr |= MSR_VSX;
- }
+ } else if (!ctx_has_vsx_region)
+ /*
+ * With a small context structure we can't hold the VSX
+ * registers, hence clear the MSR value to indicate the state
+ * was not saved.
+ */
+ msr &= ~MSR_VSX;
+
+
#endif /* CONFIG_VSX */
#ifdef CONFIG_SPE
/* save spe registers */
return id;
}
-/* Return the value of the chip-id property corresponding
- * to the given logical cpu.
- */
-int cpu_to_chip_id(int cpu)
-{
- struct device_node *np;
-
- np = of_get_cpu_node(cpu, NULL);
- if (!np)
- return -1;
-
- of_node_put(np);
- return of_get_ibm_chip_id(np);
-}
-EXPORT_SYMBOL(cpu_to_chip_id);
-
/* Helper routines for cpu to core mapping */
int cpu_core_index_of_thread(int cpu)
{
if (i == be64_to_cpu(vpa->dtl_idx))
return 0;
while (i < be64_to_cpu(vpa->dtl_idx)) {
- if (dtl_consumer)
- dtl_consumer(dtl, i);
dtb = be64_to_cpu(dtl->timebase);
tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) +
be32_to_cpu(dtl->ready_to_enqueue_time);
}
if (dtb > stop_tb)
break;
+ if (dtl_consumer)
+ dtl_consumer(dtl, i);
stolen += tb_delta;
++i;
++dtl;
/* needed to ensure proper operation of coherent allocations
* later, in case driver doesn't set it explicitly */
- dma_set_mask_and_coherent(&viodev->dev, DMA_BIT_MASK(64));
+ dma_coerce_mask_and_coherent(&viodev->dev, DMA_BIT_MASK(64));
}
/* register with generic device framework */
struct mm_struct *mm = current->mm;
unsigned long addr, len, end;
unsigned long next;
+ unsigned long flags;
pgd_t *pgdp;
int nr = 0;
* So long as we atomically load page table pointers versus teardown,
* we can follow the address down to the the page and take a ref on it.
*/
- local_irq_disable();
+ local_irq_save(flags);
pgdp = pgd_offset(mm, addr);
do {
break;
} while (pgdp++, addr = next, addr != end);
- local_irq_enable();
+ local_irq_restore(flags);
return nr;
}
slice = GET_HIGH_SLICE_INDEX(addr);
*boundary_addr = (slice + end) ?
((slice + end) << SLICE_HIGH_SHIFT) : SLICE_LOW_TOP;
- return !!(available.high_slices & (1u << slice));
+ return !!(available.high_slices & (1ul << slice));
}
}
#include <asm/io.h>
#include <asm/prom.h>
#include <asm/machdep.h>
+#include <asm/smp.h>
struct powernv_rng {
#include <linux/of.h>
#include <asm/archrandom.h>
#include <asm/machdep.h>
+#include <asm/plpar_wrappers.h>
static int pseries_get_random_long(unsigned long *v)
#include <linux/of.h>
#include <linux/smp.h>
#include <linux/time.h>
+#include <linux/of_fdt.h>
#include <asm/machdep.h>
#include <asm/udbg.h>
#include <linux/kernel.h>
#include <linux/of.h>
#include <linux/io.h>
+#include <linux/of_address.h>
#include "wsp.h"
#include <linux/smp.h>
#include <linux/spinlock.h>
#include <linux/types.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
#include <asm/io.h>
#include <asm/irq.h>
#include <linux/of.h>
#include <linux/slab.h>
#include <linux/time.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
#include <asm/reg_a2.h>
#include <asm/irq.h>
#include <linux/of.h>
#include <linux/smp.h>
#include <linux/time.h>
+#include <linux/of_fdt.h>
#include <asm/machdep.h>
#include <asm/udbg.h>
#include <linux/of.h>
#include <linux/spinlock.h>
#include <linux/types.h>
+#include <linux/of_address.h>
#include <asm/cputhreads.h>
#include <asm/reg_a2.h>
#include <linux/smp.h>
#include <linux/delay.h>
#include <linux/time.h>
+#include <linux/of_address.h>
#include <asm/scom.h>
INTEL_I915GM_IDS(gen3_stolen_size),
INTEL_I945G_IDS(gen3_stolen_size),
INTEL_I945GM_IDS(gen3_stolen_size),
- INTEL_VLV_M_IDS(gen3_stolen_size),
- INTEL_VLV_D_IDS(gen3_stolen_size),
+ INTEL_VLV_M_IDS(gen6_stolen_size),
+ INTEL_VLV_D_IDS(gen6_stolen_size),
INTEL_PINEVIEW_IDS(gen3_stolen_size),
INTEL_I965G_IDS(gen3_stolen_size),
INTEL_G33_IDS(gen3_stolen_size),
.get = param_get_bool,
};
-module_param_cb(mmu_audit, &audit_param_ops, &mmu_audit, 0644);
+arch_param_cb(mmu_audit, &audit_param_ops, &mmu_audit, 0644);
#if PAGETABLE_LEVELS > 2
void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
{
+ struct page *page = virt_to_page(pmd);
paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT);
/*
* NOTE! For PAE, any changes to the top page-directory-pointer-table
#ifdef CONFIG_X86_PAE
tlb->need_flush_all = 1;
#endif
- tlb_remove_page(tlb, virt_to_page(pmd));
+ pgtable_pmd_page_dtor(page);
+ tlb_remove_page(tlb, page);
}
#if PAGETABLE_LEVELS > 3
* - Code works, detects all the partitions.
*
************************************************************/
+#include <linux/kernel.h>
#include <linux/crc32.h>
#include <linux/ctype.h>
#include <linux/math64.h>
efi_guid_unparse(&ptes[i].unique_partition_guid, info->uuid);
/* Naively convert UTF16-LE to 7 bits. */
- label_max = min(sizeof(info->volname) - 1,
- sizeof(ptes[i].partition_name));
+ label_max = min(ARRAY_SIZE(info->volname) - 1,
+ ARRAY_SIZE(ptes[i].partition_name));
info->volname[label_max] = 0;
while (label_count < label_max) {
u8 c = ptes[i].partition_name[label_count] & 0xff;
This option enables the user-spaces interface for symmetric
key cipher algorithms.
+config CRYPTO_HASH_INFO
+ bool
+
source "drivers/crypto/Kconfig"
source crypto/asymmetric_keys/Kconfig
obj-$(CONFIG_XOR_BLOCKS) += xor.o
obj-$(CONFIG_ASYNC_CORE) += async_tx/
obj-$(CONFIG_ASYMMETRIC_KEY_TYPE) += asymmetric_keys/
+obj-$(CONFIG_CRYPTO_HASH_INFO) += hash_info.o
else if (len < ds)
msg->msg_flags |= MSG_TRUNC;
- msg->msg_namelen = 0;
-
lock_sock(sk);
if (ctx->more) {
ctx->more = 0;
long copied = 0;
lock_sock(sk);
- msg->msg_namelen = 0;
for (iov = msg->msg_iov, iovlen = msg->msg_iovlen; iovlen > 0;
iovlen--, iov++) {
unsigned long seglen = iov->iov_len;
config ASYMMETRIC_PUBLIC_KEY_SUBTYPE
tristate "Asymmetric public-key crypto algorithm subtype"
select MPILIB
+ select PUBLIC_KEY_ALGO_RSA
+ select CRYPTO_HASH_INFO
help
This option provides support for asymmetric public key type handling.
If signature generation and/or verification are to be used,
config PUBLIC_KEY_ALGO_RSA
tristate "RSA public-key algorithm"
- depends on ASYMMETRIC_PUBLIC_KEY_SUBTYPE
select MPILIB_EXTRA
+ select MPILIB
help
This option enables support for the RSA algorithm (PKCS#1, RFC3447).
.match = asymmetric_key_match,
.destroy = asymmetric_key_destroy,
.describe = asymmetric_key_describe,
+ .def_lookup_type = KEYRING_SEARCH_LOOKUP_ITERATE,
};
EXPORT_SYMBOL_GPL(key_type_asymmetric);
MODULE_LICENSE("GPL");
-const char *const pkey_algo[PKEY_ALGO__LAST] = {
+const char *const pkey_algo_name[PKEY_ALGO__LAST] = {
[PKEY_ALGO_DSA] = "DSA",
[PKEY_ALGO_RSA] = "RSA",
};
-EXPORT_SYMBOL_GPL(pkey_algo);
+EXPORT_SYMBOL_GPL(pkey_algo_name);
-const char *const pkey_hash_algo[PKEY_HASH__LAST] = {
- [PKEY_HASH_MD4] = "md4",
- [PKEY_HASH_MD5] = "md5",
- [PKEY_HASH_SHA1] = "sha1",
- [PKEY_HASH_RIPE_MD_160] = "rmd160",
- [PKEY_HASH_SHA256] = "sha256",
- [PKEY_HASH_SHA384] = "sha384",
- [PKEY_HASH_SHA512] = "sha512",
- [PKEY_HASH_SHA224] = "sha224",
+const struct public_key_algorithm *pkey_algo[PKEY_ALGO__LAST] = {
+#if defined(CONFIG_PUBLIC_KEY_ALGO_RSA) || \
+ defined(CONFIG_PUBLIC_KEY_ALGO_RSA_MODULE)
+ [PKEY_ALGO_RSA] = &RSA_public_key_algorithm,
+#endif
};
-EXPORT_SYMBOL_GPL(pkey_hash_algo);
+EXPORT_SYMBOL_GPL(pkey_algo);
-const char *const pkey_id_type[PKEY_ID_TYPE__LAST] = {
+const char *const pkey_id_type_name[PKEY_ID_TYPE__LAST] = {
[PKEY_ID_PGP] = "PGP",
[PKEY_ID_X509] = "X509",
};
-EXPORT_SYMBOL_GPL(pkey_id_type);
+EXPORT_SYMBOL_GPL(pkey_id_type_name);
/*
* Provide a part of a description of the key for /proc/keys.
if (key)
seq_printf(m, "%s.%s",
- pkey_id_type[key->id_type], key->algo->name);
+ pkey_id_type_name[key->id_type], key->algo->name);
}
/*
/*
* Verify a signature using a public key.
*/
-static int public_key_verify_signature(const struct key *key,
- const struct public_key_signature *sig)
+int public_key_verify_signature(const struct public_key *pk,
+ const struct public_key_signature *sig)
{
- const struct public_key *pk = key->payload.data;
+ const struct public_key_algorithm *algo;
+
+ BUG_ON(!pk);
+ BUG_ON(!pk->mpi[0]);
+ BUG_ON(!pk->mpi[1]);
+ BUG_ON(!sig);
+ BUG_ON(!sig->digest);
+ BUG_ON(!sig->mpi[0]);
+
+ algo = pk->algo;
+ if (!algo) {
+ if (pk->pkey_algo >= PKEY_ALGO__LAST)
+ return -ENOPKG;
+ algo = pkey_algo[pk->pkey_algo];
+ if (!algo)
+ return -ENOPKG;
+ }
- if (!pk->algo->verify_signature)
+ if (!algo->verify_signature)
return -ENOTSUPP;
- if (sig->nr_mpi != pk->algo->n_sig_mpi) {
+ if (sig->nr_mpi != algo->n_sig_mpi) {
pr_debug("Signature has %u MPI not %u\n",
- sig->nr_mpi, pk->algo->n_sig_mpi);
+ sig->nr_mpi, algo->n_sig_mpi);
return -EINVAL;
}
- return pk->algo->verify_signature(pk, sig);
+ return algo->verify_signature(pk, sig);
+}
+EXPORT_SYMBOL_GPL(public_key_verify_signature);
+
+static int public_key_verify_signature_2(const struct key *key,
+ const struct public_key_signature *sig)
+{
+ const struct public_key *pk = key->payload.data;
+ return public_key_verify_signature(pk, sig);
}
/*
.name = "public_key",
.describe = public_key_describe,
.destroy = public_key_destroy,
- .verify_signature = public_key_verify_signature,
+ .verify_signature = public_key_verify_signature_2,
};
EXPORT_SYMBOL_GPL(public_key_subtype);
};
extern const struct public_key_algorithm RSA_public_key_algorithm;
+
+/*
+ * public_key.c
+ */
+extern int public_key_verify_signature(const struct public_key *pk,
+ const struct public_key_signature *sig);
size_t size;
} RSA_ASN1_templates[PKEY_HASH__LAST] = {
#define _(X) { RSA_digest_info_##X, sizeof(RSA_digest_info_##X) }
- [PKEY_HASH_MD5] = _(MD5),
- [PKEY_HASH_SHA1] = _(SHA1),
- [PKEY_HASH_RIPE_MD_160] = _(RIPE_MD_160),
- [PKEY_HASH_SHA256] = _(SHA256),
- [PKEY_HASH_SHA384] = _(SHA384),
- [PKEY_HASH_SHA512] = _(SHA512),
- [PKEY_HASH_SHA224] = _(SHA224),
+ [HASH_ALGO_MD5] = _(MD5),
+ [HASH_ALGO_SHA1] = _(SHA1),
+ [HASH_ALGO_RIPE_MD_160] = _(RIPE_MD_160),
+ [HASH_ALGO_SHA256] = _(SHA256),
+ [HASH_ALGO_SHA384] = _(SHA384),
+ [HASH_ALGO_SHA512] = _(SHA512),
+ [HASH_ALGO_SHA224] = _(SHA224),
#undef _
};
kfree(cert->subject);
kfree(cert->fingerprint);
kfree(cert->authority);
+ kfree(cert->sig.digest);
+ mpi_free(cert->sig.rsa.s);
kfree(cert);
}
}
return -ENOPKG; /* Unsupported combination */
case OID_md4WithRSAEncryption:
- ctx->cert->sig_hash_algo = PKEY_HASH_MD5;
- ctx->cert->sig_pkey_algo = PKEY_ALGO_RSA;
+ ctx->cert->sig.pkey_hash_algo = HASH_ALGO_MD5;
+ ctx->cert->sig.pkey_algo = PKEY_ALGO_RSA;
break;
case OID_sha1WithRSAEncryption:
- ctx->cert->sig_hash_algo = PKEY_HASH_SHA1;
- ctx->cert->sig_pkey_algo = PKEY_ALGO_RSA;
+ ctx->cert->sig.pkey_hash_algo = HASH_ALGO_SHA1;
+ ctx->cert->sig.pkey_algo = PKEY_ALGO_RSA;
break;
case OID_sha256WithRSAEncryption:
- ctx->cert->sig_hash_algo = PKEY_HASH_SHA256;
- ctx->cert->sig_pkey_algo = PKEY_ALGO_RSA;
+ ctx->cert->sig.pkey_hash_algo = HASH_ALGO_SHA256;
+ ctx->cert->sig.pkey_algo = PKEY_ALGO_RSA;
break;
case OID_sha384WithRSAEncryption:
- ctx->cert->sig_hash_algo = PKEY_HASH_SHA384;
- ctx->cert->sig_pkey_algo = PKEY_ALGO_RSA;
+ ctx->cert->sig.pkey_hash_algo = HASH_ALGO_SHA384;
+ ctx->cert->sig.pkey_algo = PKEY_ALGO_RSA;
break;
case OID_sha512WithRSAEncryption:
- ctx->cert->sig_hash_algo = PKEY_HASH_SHA512;
- ctx->cert->sig_pkey_algo = PKEY_ALGO_RSA;
+ ctx->cert->sig.pkey_hash_algo = HASH_ALGO_SHA512;
+ ctx->cert->sig.pkey_algo = PKEY_ALGO_RSA;
break;
case OID_sha224WithRSAEncryption:
- ctx->cert->sig_hash_algo = PKEY_HASH_SHA224;
- ctx->cert->sig_pkey_algo = PKEY_ALGO_RSA;
+ ctx->cert->sig.pkey_hash_algo = HASH_ALGO_SHA224;
+ ctx->cert->sig.pkey_algo = PKEY_ALGO_RSA;
break;
}
return -EINVAL;
}
- ctx->cert->sig = value;
- ctx->cert->sig_size = vlen;
+ ctx->cert->raw_sig = value;
+ ctx->cert->raw_sig_size = vlen;
return 0;
}
if (ctx->last_oid != OID_rsaEncryption)
return -ENOPKG;
- /* There seems to be an extraneous 0 byte on the front of the data */
- ctx->cert->pkey_algo = PKEY_ALGO_RSA;
+ ctx->cert->pub->pkey_algo = PKEY_ALGO_RSA;
+
+ /* Discard the BIT STRING metadata */
ctx->key = value + 1;
ctx->key_size = vlen - 1;
return 0;
* 2 of the Licence, or (at your option) any later version.
*/
+#include <linux/time.h>
#include <crypto/public_key.h>
struct x509_certificate {
char *authority; /* Authority key fingerprint as hex */
struct tm valid_from;
struct tm valid_to;
- enum pkey_algo pkey_algo : 8; /* Public key algorithm */
- enum pkey_algo sig_pkey_algo : 8; /* Signature public key algorithm */
- enum pkey_hash_algo sig_hash_algo : 8; /* Signature hash algorithm */
const void *tbs; /* Signed data */
- size_t tbs_size; /* Size of signed data */
- const void *sig; /* Signature data */
- size_t sig_size; /* Size of sigature */
+ unsigned tbs_size; /* Size of signed data */
+ unsigned raw_sig_size; /* Size of sigature */
+ const void *raw_sig; /* Signature data */
+ struct public_key_signature sig; /* Signature parameters */
};
/*
*/
extern void x509_free_certificate(struct x509_certificate *cert);
extern struct x509_certificate *x509_cert_parse(const void *data, size_t datalen);
+
+/*
+ * x509_public_key.c
+ */
+extern int x509_get_sig_params(struct x509_certificate *cert);
+extern int x509_check_signature(const struct public_key *pub,
+ struct x509_certificate *cert);
#include <linux/asn1_decoder.h>
#include <keys/asymmetric-subtype.h>
#include <keys/asymmetric-parser.h>
+#include <keys/system_keyring.h>
#include <crypto/hash.h>
#include "asymmetric_keys.h"
#include "public_key.h"
#include "x509_parser.h"
-static const
-struct public_key_algorithm *x509_public_key_algorithms[PKEY_ALGO__LAST] = {
- [PKEY_ALGO_DSA] = NULL,
-#if defined(CONFIG_PUBLIC_KEY_ALGO_RSA) || \
- defined(CONFIG_PUBLIC_KEY_ALGO_RSA_MODULE)
- [PKEY_ALGO_RSA] = &RSA_public_key_algorithm,
-#endif
-};
+/*
+ * Find a key in the given keyring by issuer and authority.
+ */
+static struct key *x509_request_asymmetric_key(
+ struct key *keyring,
+ const char *signer, size_t signer_len,
+ const char *authority, size_t auth_len)
+{
+ key_ref_t key;
+ char *id;
+
+ /* Construct an identifier. */
+ id = kmalloc(signer_len + 2 + auth_len + 1, GFP_KERNEL);
+ if (!id)
+ return ERR_PTR(-ENOMEM);
+
+ memcpy(id, signer, signer_len);
+ id[signer_len + 0] = ':';
+ id[signer_len + 1] = ' ';
+ memcpy(id + signer_len + 2, authority, auth_len);
+ id[signer_len + 2 + auth_len] = 0;
+
+ pr_debug("Look up: \"%s\"\n", id);
+
+ key = keyring_search(make_key_ref(keyring, 1),
+ &key_type_asymmetric, id);
+ if (IS_ERR(key))
+ pr_debug("Request for module key '%s' err %ld\n",
+ id, PTR_ERR(key));
+ kfree(id);
+
+ if (IS_ERR(key)) {
+ switch (PTR_ERR(key)) {
+ /* Hide some search errors */
+ case -EACCES:
+ case -ENOTDIR:
+ case -EAGAIN:
+ return ERR_PTR(-ENOKEY);
+ default:
+ return ERR_CAST(key);
+ }
+ }
+
+ pr_devel("<==%s() = 0 [%x]\n", __func__, key_serial(key_ref_to_ptr(key)));
+ return key_ref_to_ptr(key);
+}
/*
- * Check the signature on a certificate using the provided public key
+ * Set up the signature parameters in an X.509 certificate. This involves
+ * digesting the signed data and extracting the signature.
*/
-static int x509_check_signature(const struct public_key *pub,
- const struct x509_certificate *cert)
+int x509_get_sig_params(struct x509_certificate *cert)
{
- struct public_key_signature *sig;
struct crypto_shash *tfm;
struct shash_desc *desc;
size_t digest_size, desc_size;
+ void *digest;
int ret;
pr_devel("==>%s()\n", __func__);
-
+
+ if (cert->sig.rsa.s)
+ return 0;
+
+ cert->sig.rsa.s = mpi_read_raw_data(cert->raw_sig, cert->raw_sig_size);
+ if (!cert->sig.rsa.s)
+ return -ENOMEM;
+ cert->sig.nr_mpi = 1;
+
/* Allocate the hashing algorithm we're going to need and find out how
* big the hash operational data will be.
*/
- tfm = crypto_alloc_shash(pkey_hash_algo[cert->sig_hash_algo], 0, 0);
+ tfm = crypto_alloc_shash(hash_algo_name[cert->sig.pkey_hash_algo], 0, 0);
if (IS_ERR(tfm))
return (PTR_ERR(tfm) == -ENOENT) ? -ENOPKG : PTR_ERR(tfm);
desc_size = crypto_shash_descsize(tfm) + sizeof(*desc);
digest_size = crypto_shash_digestsize(tfm);
- /* We allocate the hash operational data storage on the end of our
- * context data.
+ /* We allocate the hash operational data storage on the end of the
+ * digest storage space.
*/
ret = -ENOMEM;
- sig = kzalloc(sizeof(*sig) + desc_size + digest_size, GFP_KERNEL);
- if (!sig)
- goto error_no_sig;
+ digest = kzalloc(digest_size + desc_size, GFP_KERNEL);
+ if (!digest)
+ goto error;
- sig->pkey_hash_algo = cert->sig_hash_algo;
- sig->digest = (u8 *)sig + sizeof(*sig) + desc_size;
- sig->digest_size = digest_size;
+ cert->sig.digest = digest;
+ cert->sig.digest_size = digest_size;
- desc = (void *)sig + sizeof(*sig);
- desc->tfm = tfm;
- desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+ desc = digest + digest_size;
+ desc->tfm = tfm;
+ desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
ret = crypto_shash_init(desc);
if (ret < 0)
goto error;
+ might_sleep();
+ ret = crypto_shash_finup(desc, cert->tbs, cert->tbs_size, digest);
+error:
+ crypto_free_shash(tfm);
+ pr_devel("<==%s() = %d\n", __func__, ret);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(x509_get_sig_params);
- ret = -ENOMEM;
- sig->rsa.s = mpi_read_raw_data(cert->sig, cert->sig_size);
- if (!sig->rsa.s)
- goto error;
+/*
+ * Check the signature on a certificate using the provided public key
+ */
+int x509_check_signature(const struct public_key *pub,
+ struct x509_certificate *cert)
+{
+ int ret;
- ret = crypto_shash_finup(desc, cert->tbs, cert->tbs_size, sig->digest);
- if (ret < 0)
- goto error_mpi;
+ pr_devel("==>%s()\n", __func__);
- ret = pub->algo->verify_signature(pub, sig);
+ ret = x509_get_sig_params(cert);
+ if (ret < 0)
+ return ret;
+ ret = public_key_verify_signature(pub, &cert->sig);
pr_debug("Cert Verification: %d\n", ret);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(x509_check_signature);
-error_mpi:
- mpi_free(sig->rsa.s);
-error:
- kfree(sig);
-error_no_sig:
- crypto_free_shash(tfm);
+/*
+ * Check the new certificate against the ones in the trust keyring. If one of
+ * those is the signing key and validates the new certificate, then mark the
+ * new certificate as being trusted.
+ *
+ * Return 0 if the new certificate was successfully validated, 1 if we couldn't
+ * find a matching parent certificate in the trusted list and an error if there
+ * is a matching certificate but the signature check fails.
+ */
+static int x509_validate_trust(struct x509_certificate *cert,
+ struct key *trust_keyring)
+{
+ const struct public_key *pk;
+ struct key *key;
+ int ret = 1;
- pr_devel("<==%s() = %d\n", __func__, ret);
+ key = x509_request_asymmetric_key(trust_keyring,
+ cert->issuer, strlen(cert->issuer),
+ cert->authority,
+ strlen(cert->authority));
+ if (!IS_ERR(key)) {
+ pk = key->payload.data;
+ ret = x509_check_signature(pk, cert);
+ }
return ret;
}
static int x509_key_preparse(struct key_preparsed_payload *prep)
{
struct x509_certificate *cert;
- struct tm now;
size_t srlen, sulen;
char *desc = NULL;
int ret;
pr_devel("Cert Issuer: %s\n", cert->issuer);
pr_devel("Cert Subject: %s\n", cert->subject);
- pr_devel("Cert Key Algo: %s\n", pkey_algo[cert->pkey_algo]);
+
+ if (cert->pub->pkey_algo >= PKEY_ALGO__LAST ||
+ cert->sig.pkey_algo >= PKEY_ALGO__LAST ||
+ cert->sig.pkey_hash_algo >= PKEY_HASH__LAST ||
+ !pkey_algo[cert->pub->pkey_algo] ||
+ !pkey_algo[cert->sig.pkey_algo] ||
+ !hash_algo_name[cert->sig.pkey_hash_algo]) {
+ ret = -ENOPKG;
+ goto error_free_cert;
+ }
+
+ pr_devel("Cert Key Algo: %s\n", pkey_algo_name[cert->pub->pkey_algo]);
pr_devel("Cert Valid From: %04ld-%02d-%02d %02d:%02d:%02d\n",
cert->valid_from.tm_year + 1900, cert->valid_from.tm_mon + 1,
cert->valid_from.tm_mday, cert->valid_from.tm_hour,
cert->valid_to.tm_mday, cert->valid_to.tm_hour,
cert->valid_to.tm_min, cert->valid_to.tm_sec);
pr_devel("Cert Signature: %s + %s\n",
- pkey_algo[cert->sig_pkey_algo],
- pkey_hash_algo[cert->sig_hash_algo]);
+ pkey_algo_name[cert->sig.pkey_algo],
+ hash_algo_name[cert->sig.pkey_hash_algo]);
- if (!cert->fingerprint || !cert->authority) {
- pr_warn("Cert for '%s' must have SubjKeyId and AuthKeyId extensions\n",
+ if (!cert->fingerprint) {
+ pr_warn("Cert for '%s' must have a SubjKeyId extension\n",
cert->subject);
ret = -EKEYREJECTED;
goto error_free_cert;
}
- time_to_tm(CURRENT_TIME.tv_sec, 0, &now);
- pr_devel("Now: %04ld-%02d-%02d %02d:%02d:%02d\n",
- now.tm_year + 1900, now.tm_mon + 1, now.tm_mday,
- now.tm_hour, now.tm_min, now.tm_sec);
- if (now.tm_year < cert->valid_from.tm_year ||
- (now.tm_year == cert->valid_from.tm_year &&
- (now.tm_mon < cert->valid_from.tm_mon ||
- (now.tm_mon == cert->valid_from.tm_mon &&
- (now.tm_mday < cert->valid_from.tm_mday ||
- (now.tm_mday == cert->valid_from.tm_mday &&
- (now.tm_hour < cert->valid_from.tm_hour ||
- (now.tm_hour == cert->valid_from.tm_hour &&
- (now.tm_min < cert->valid_from.tm_min ||
- (now.tm_min == cert->valid_from.tm_min &&
- (now.tm_sec < cert->valid_from.tm_sec
- ))))))))))) {
- pr_warn("Cert %s is not yet valid\n", cert->fingerprint);
- ret = -EKEYREJECTED;
- goto error_free_cert;
- }
- if (now.tm_year > cert->valid_to.tm_year ||
- (now.tm_year == cert->valid_to.tm_year &&
- (now.tm_mon > cert->valid_to.tm_mon ||
- (now.tm_mon == cert->valid_to.tm_mon &&
- (now.tm_mday > cert->valid_to.tm_mday ||
- (now.tm_mday == cert->valid_to.tm_mday &&
- (now.tm_hour > cert->valid_to.tm_hour ||
- (now.tm_hour == cert->valid_to.tm_hour &&
- (now.tm_min > cert->valid_to.tm_min ||
- (now.tm_min == cert->valid_to.tm_min &&
- (now.tm_sec > cert->valid_to.tm_sec
- ))))))))))) {
- pr_warn("Cert %s has expired\n", cert->fingerprint);
- ret = -EKEYEXPIRED;
- goto error_free_cert;
- }
-
- cert->pub->algo = x509_public_key_algorithms[cert->pkey_algo];
+ cert->pub->algo = pkey_algo[cert->pub->pkey_algo];
cert->pub->id_type = PKEY_ID_X509;
- /* Check the signature on the key */
- if (strcmp(cert->fingerprint, cert->authority) == 0) {
- ret = x509_check_signature(cert->pub, cert);
+ /* Check the signature on the key if it appears to be self-signed */
+ if (!cert->authority ||
+ strcmp(cert->fingerprint, cert->authority) == 0) {
+ ret = x509_check_signature(cert->pub, cert); /* self-signed */
if (ret < 0)
goto error_free_cert;
+ } else {
+ ret = x509_validate_trust(cert, system_trusted_keyring);
+ if (!ret)
+ prep->trusted = 1;
}
/* Propose a description */
module_init(x509_key_init);
module_exit(x509_key_exit);
+
+MODULE_DESCRIPTION("X.509 certificate parser");
+MODULE_LICENSE("GPL");
--- /dev/null
+/*
+ * Hash Info: Hash algorithms information
+ *
+ * Copyright (c) 2013 Dmitry Kasatkin <d.kasatkin@samsung.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/export.h>
+#include <crypto/hash_info.h>
+
+const char *const hash_algo_name[HASH_ALGO__LAST] = {
+ [HASH_ALGO_MD4] = "md4",
+ [HASH_ALGO_MD5] = "md5",
+ [HASH_ALGO_SHA1] = "sha1",
+ [HASH_ALGO_RIPE_MD_160] = "rmd160",
+ [HASH_ALGO_SHA256] = "sha256",
+ [HASH_ALGO_SHA384] = "sha384",
+ [HASH_ALGO_SHA512] = "sha512",
+ [HASH_ALGO_SHA224] = "sha224",
+ [HASH_ALGO_RIPE_MD_128] = "rmd128",
+ [HASH_ALGO_RIPE_MD_256] = "rmd256",
+ [HASH_ALGO_RIPE_MD_320] = "rmd320",
+ [HASH_ALGO_WP_256] = "wp256",
+ [HASH_ALGO_WP_384] = "wp384",
+ [HASH_ALGO_WP_512] = "wp512",
+ [HASH_ALGO_TGR_128] = "tgr128",
+ [HASH_ALGO_TGR_160] = "tgr160",
+ [HASH_ALGO_TGR_192] = "tgr192",
+};
+EXPORT_SYMBOL_GPL(hash_algo_name);
+
+const int hash_digest_size[HASH_ALGO__LAST] = {
+ [HASH_ALGO_MD4] = MD5_DIGEST_SIZE,
+ [HASH_ALGO_MD5] = MD5_DIGEST_SIZE,
+ [HASH_ALGO_SHA1] = SHA1_DIGEST_SIZE,
+ [HASH_ALGO_RIPE_MD_160] = RMD160_DIGEST_SIZE,
+ [HASH_ALGO_SHA256] = SHA256_DIGEST_SIZE,
+ [HASH_ALGO_SHA384] = SHA384_DIGEST_SIZE,
+ [HASH_ALGO_SHA512] = SHA512_DIGEST_SIZE,
+ [HASH_ALGO_SHA224] = SHA224_DIGEST_SIZE,
+ [HASH_ALGO_RIPE_MD_128] = RMD128_DIGEST_SIZE,
+ [HASH_ALGO_RIPE_MD_256] = RMD256_DIGEST_SIZE,
+ [HASH_ALGO_RIPE_MD_320] = RMD320_DIGEST_SIZE,
+ [HASH_ALGO_WP_256] = WP256_DIGEST_SIZE,
+ [HASH_ALGO_WP_384] = WP384_DIGEST_SIZE,
+ [HASH_ALGO_WP_512] = WP512_DIGEST_SIZE,
+ [HASH_ALGO_TGR_128] = TGR128_DIGEST_SIZE,
+ [HASH_ALGO_TGR_160] = TGR160_DIGEST_SIZE,
+ [HASH_ALGO_TGR_192] = TGR192_DIGEST_SIZE,
+};
+EXPORT_SYMBOL_GPL(hash_digest_size);
blk_end_request_all(rq, 0);
}
-#if defined(CONFIG_SMP) && defined(CONFIG_USE_GENERIC_SMP_HELPERS)
+#ifdef CONFIG_SMP
static void null_ipi_cmd_end_io(void *data)
{
put_cpu();
}
-#endif /* CONFIG_SMP && CONFIG_USE_GENERIC_SMP_HELPERS */
+#endif /* CONFIG_SMP */
static inline void null_handle_cmd(struct nullb_cmd *cmd)
{
end_cmd(cmd);
break;
case NULL_IRQ_SOFTIRQ:
-#if defined(CONFIG_SMP) && defined(CONFIG_USE_GENERIC_SMP_HELPERS)
+#ifdef CONFIG_SMP
null_cmd_end_ipi(cmd);
#else
end_cmd(cmd);
{
unsigned int i;
-#if !defined(CONFIG_SMP) || !defined(CONFIG_USE_GENERIC_SMP_HELPERS)
+#if !defined(CONFIG_SMP)
if (irqmode == NULL_IRQ_SOFTIRQ) {
pr_warn("null_blk: softirq completions not available.\n");
pr_warn("null_blk: using direct completions.\n");
from within Linux. To compile this driver as a module, choose
M here; the module will be called tpm_tis.
+config TCG_TIS_I2C_ATMEL
+ tristate "TPM Interface Specification 1.2 Interface (I2C - Atmel)"
+ depends on I2C
+ ---help---
+ If you have an Atmel I2C TPM security chip say Yes and it will be
+ accessible from within Linux.
+ To compile this driver as a module, choose M here; the module will
+ be called tpm_tis_i2c_atmel.
+
config TCG_TIS_I2C_INFINEON
tristate "TPM Interface Specification 1.2 Interface (I2C - Infineon)"
depends on I2C
Specification 0.20 say Yes and it will be accessible from within
Linux.
To compile this driver as a module, choose M here; the module
- will be called tpm_tis_i2c_infineon.
+ will be called tpm_i2c_infineon.
+
+config TCG_TIS_I2C_NUVOTON
+ tristate "TPM Interface Specification 1.2 Interface (I2C - Nuvoton)"
+ depends on I2C
+ ---help---
+ If you have a TPM security chip with an I2C interface from
+ Nuvoton Technology Corp. say Yes and it will be accessible
+ from within Linux.
+ To compile this driver as a module, choose M here; the module
+ will be called tpm_i2c_nuvoton.
config TCG_NSC
tristate "National Semiconductor TPM Interface"
as a module, choose M here; the module will be called tpm_ibmvtpm.
config TCG_ST33_I2C
- tristate "STMicroelectronics ST33 I2C TPM"
- depends on I2C
- depends on GPIOLIB
- ---help---
- If you have a TPM security chip from STMicroelectronics working with
- an I2C bus say Yes and it will be accessible from within Linux.
- To compile this driver as a module, choose M here; the module will be
- called tpm_stm_st33_i2c.
+ tristate "STMicroelectronics ST33 I2C TPM"
+ depends on I2C
+ depends on GPIOLIB
+ ---help---
+ If you have a TPM security chip from STMicroelectronics working with
+ an I2C bus say Yes and it will be accessible from within Linux.
+ To compile this driver as a module, choose M here; the module will be
+ called tpm_stm_st33_i2c.
config TCG_XEN
tristate "XEN TPM Interface"
# Makefile for the kernel tpm device drivers.
#
obj-$(CONFIG_TCG_TPM) += tpm.o
+tpm-y := tpm-interface.o
+tpm-$(CONFIG_ACPI) += tpm_ppi.o
+
ifdef CONFIG_ACPI
- obj-$(CONFIG_TCG_TPM) += tpm_bios.o
- tpm_bios-objs += tpm_eventlog.o tpm_acpi.o tpm_ppi.o
+ tpm-y += tpm_eventlog.o tpm_acpi.o
else
ifdef CONFIG_TCG_IBMVTPM
- obj-$(CONFIG_TCG_TPM) += tpm_bios.o
- tpm_bios-objs += tpm_eventlog.o tpm_of.o
+ tpm-y += tpm_eventlog.o tpm_of.o
endif
endif
obj-$(CONFIG_TCG_TIS) += tpm_tis.o
+obj-$(CONFIG_TCG_TIS_I2C_ATMEL) += tpm_i2c_atmel.o
obj-$(CONFIG_TCG_TIS_I2C_INFINEON) += tpm_i2c_infineon.o
+obj-$(CONFIG_TCG_TIS_I2C_NUVOTON) += tpm_i2c_nuvoton.o
obj-$(CONFIG_TCG_NSC) += tpm_nsc.o
obj-$(CONFIG_TCG_ATMEL) += tpm_atmel.o
obj-$(CONFIG_TCG_INFINEON) += tpm_infineon.o
--- /dev/null
+/*
+ * Copyright (C) 2004 IBM Corporation
+ *
+ * Authors:
+ * Leendert van Doorn <leendert@watson.ibm.com>
+ * Dave Safford <safford@watson.ibm.com>
+ * Reiner Sailer <sailer@watson.ibm.com>
+ * Kylene Hall <kjhall@us.ibm.com>
+ *
+ * Maintained by: <tpmdd-devel@lists.sourceforge.net>
+ *
+ * Device driver for TCG/TCPA TPM (trusted platform module).
+ * Specifications at www.trustedcomputinggroup.org
+ *
+ * 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, version 2 of the
+ * License.
+ *
+ * Note, the TPM chip is not interrupt driven (only polling)
+ * and can have very long timeouts (minutes!). Hence the unusual
+ * calls to msleep.
+ *
+ */
+
+#include <linux/poll.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/spinlock.h>
+#include <linux/freezer.h>
+
+#include "tpm.h"
+#include "tpm_eventlog.h"
+
+enum tpm_duration {
+ TPM_SHORT = 0,
+ TPM_MEDIUM = 1,
+ TPM_LONG = 2,
+ TPM_UNDEFINED,
+};
+
+#define TPM_MAX_ORDINAL 243
+#define TSC_MAX_ORDINAL 12
+#define TPM_PROTECTED_COMMAND 0x00
+#define TPM_CONNECTION_COMMAND 0x40
+
+/*
+ * Bug workaround - some TPM's don't flush the most
+ * recently changed pcr on suspend, so force the flush
+ * with an extend to the selected _unused_ non-volatile pcr.
+ */
+static int tpm_suspend_pcr;
+module_param_named(suspend_pcr, tpm_suspend_pcr, uint, 0644);
+MODULE_PARM_DESC(suspend_pcr,
+ "PCR to use for dummy writes to faciltate flush on suspend.");
+
+static LIST_HEAD(tpm_chip_list);
+static DEFINE_SPINLOCK(driver_lock);
+static DECLARE_BITMAP(dev_mask, TPM_NUM_DEVICES);
+
+/*
+ * Array with one entry per ordinal defining the maximum amount
+ * of time the chip could take to return the result. The ordinal
+ * designation of short, medium or long is defined in a table in
+ * TCG Specification TPM Main Part 2 TPM Structures Section 17. The
+ * values of the SHORT, MEDIUM, and LONG durations are retrieved
+ * from the chip during initialization with a call to tpm_get_timeouts.
+ */
+static const u8 tpm_ordinal_duration[TPM_MAX_ORDINAL] = {
+ TPM_UNDEFINED, /* 0 */
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED, /* 5 */
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_SHORT, /* 10 */
+ TPM_SHORT,
+ TPM_MEDIUM,
+ TPM_LONG,
+ TPM_LONG,
+ TPM_MEDIUM, /* 15 */
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_MEDIUM,
+ TPM_LONG,
+ TPM_SHORT, /* 20 */
+ TPM_SHORT,
+ TPM_MEDIUM,
+ TPM_MEDIUM,
+ TPM_MEDIUM,
+ TPM_SHORT, /* 25 */
+ TPM_SHORT,
+ TPM_MEDIUM,
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_MEDIUM, /* 30 */
+ TPM_LONG,
+ TPM_MEDIUM,
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_SHORT, /* 35 */
+ TPM_MEDIUM,
+ TPM_MEDIUM,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_MEDIUM, /* 40 */
+ TPM_LONG,
+ TPM_MEDIUM,
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_SHORT, /* 45 */
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_LONG,
+ TPM_MEDIUM, /* 50 */
+ TPM_MEDIUM,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED, /* 55 */
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_MEDIUM, /* 60 */
+ TPM_MEDIUM,
+ TPM_MEDIUM,
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_MEDIUM, /* 65 */
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_SHORT, /* 70 */
+ TPM_SHORT,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED, /* 75 */
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_LONG, /* 80 */
+ TPM_UNDEFINED,
+ TPM_MEDIUM,
+ TPM_LONG,
+ TPM_SHORT,
+ TPM_UNDEFINED, /* 85 */
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_SHORT, /* 90 */
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_UNDEFINED, /* 95 */
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_MEDIUM, /* 100 */
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED, /* 105 */
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_SHORT, /* 110 */
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_SHORT, /* 115 */
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_LONG, /* 120 */
+ TPM_LONG,
+ TPM_MEDIUM,
+ TPM_UNDEFINED,
+ TPM_SHORT,
+ TPM_SHORT, /* 125 */
+ TPM_SHORT,
+ TPM_LONG,
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_SHORT, /* 130 */
+ TPM_MEDIUM,
+ TPM_UNDEFINED,
+ TPM_SHORT,
+ TPM_MEDIUM,
+ TPM_UNDEFINED, /* 135 */
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_SHORT, /* 140 */
+ TPM_SHORT,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED, /* 145 */
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_SHORT, /* 150 */
+ TPM_MEDIUM,
+ TPM_MEDIUM,
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_UNDEFINED, /* 155 */
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_SHORT, /* 160 */
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED, /* 165 */
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_LONG, /* 170 */
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED, /* 175 */
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_MEDIUM, /* 180 */
+ TPM_SHORT,
+ TPM_MEDIUM,
+ TPM_MEDIUM,
+ TPM_MEDIUM,
+ TPM_MEDIUM, /* 185 */
+ TPM_SHORT,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED, /* 190 */
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED, /* 195 */
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_SHORT, /* 200 */
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_SHORT,
+ TPM_SHORT, /* 205 */
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_MEDIUM, /* 210 */
+ TPM_UNDEFINED,
+ TPM_MEDIUM,
+ TPM_MEDIUM,
+ TPM_MEDIUM,
+ TPM_UNDEFINED, /* 215 */
+ TPM_MEDIUM,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_SHORT,
+ TPM_SHORT, /* 220 */
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_SHORT,
+ TPM_UNDEFINED, /* 225 */
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_SHORT, /* 230 */
+ TPM_LONG,
+ TPM_MEDIUM,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED, /* 235 */
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_UNDEFINED,
+ TPM_SHORT, /* 240 */
+ TPM_UNDEFINED,
+ TPM_MEDIUM,
+};
+
+static void user_reader_timeout(unsigned long ptr)
+{
+ struct tpm_chip *chip = (struct tpm_chip *) ptr;
+
+ schedule_work(&chip->work);
+}
+
+static void timeout_work(struct work_struct *work)
+{
+ struct tpm_chip *chip = container_of(work, struct tpm_chip, work);
+
+ mutex_lock(&chip->buffer_mutex);
+ atomic_set(&chip->data_pending, 0);
+ memset(chip->data_buffer, 0, TPM_BUFSIZE);
+ mutex_unlock(&chip->buffer_mutex);
+}
+
+/*
+ * Returns max number of jiffies to wait
+ */
+unsigned long tpm_calc_ordinal_duration(struct tpm_chip *chip,
+ u32 ordinal)
+{
+ int duration_idx = TPM_UNDEFINED;
+ int duration = 0;
+ u8 category = (ordinal >> 24) & 0xFF;
+
+ if ((category == TPM_PROTECTED_COMMAND && ordinal < TPM_MAX_ORDINAL) ||
+ (category == TPM_CONNECTION_COMMAND && ordinal < TSC_MAX_ORDINAL))
+ duration_idx = tpm_ordinal_duration[ordinal];
+
+ if (duration_idx != TPM_UNDEFINED)
+ duration = chip->vendor.duration[duration_idx];
+ if (duration <= 0)
+ return 2 * 60 * HZ;
+ else
+ return duration;
+}
+EXPORT_SYMBOL_GPL(tpm_calc_ordinal_duration);
+
+/*
+ * Internal kernel interface to transmit TPM commands
+ */
+static ssize_t tpm_transmit(struct tpm_chip *chip, const char *buf,
+ size_t bufsiz)
+{
+ ssize_t rc;
+ u32 count, ordinal;
+ unsigned long stop;
+
+ if (bufsiz > TPM_BUFSIZE)
+ bufsiz = TPM_BUFSIZE;
+
+ count = be32_to_cpu(*((__be32 *) (buf + 2)));
+ ordinal = be32_to_cpu(*((__be32 *) (buf + 6)));
+ if (count == 0)
+ return -ENODATA;
+ if (count > bufsiz) {
+ dev_err(chip->dev,
+ "invalid count value %x %zx\n", count, bufsiz);
+ return -E2BIG;
+ }
+
+ mutex_lock(&chip->tpm_mutex);
+
+ rc = chip->vendor.send(chip, (u8 *) buf, count);
+ if (rc < 0) {
+ dev_err(chip->dev,
+ "tpm_transmit: tpm_send: error %zd\n", rc);
+ goto out;
+ }
+
+ if (chip->vendor.irq)
+ goto out_recv;
+
+ stop = jiffies + tpm_calc_ordinal_duration(chip, ordinal);
+ do {
+ u8 status = chip->vendor.status(chip);
+ if ((status & chip->vendor.req_complete_mask) ==
+ chip->vendor.req_complete_val)
+ goto out_recv;
+
+ if (chip->vendor.req_canceled(chip, status)) {
+ dev_err(chip->dev, "Operation Canceled\n");
+ rc = -ECANCELED;
+ goto out;
+ }
+
+ msleep(TPM_TIMEOUT); /* CHECK */
+ rmb();
+ } while (time_before(jiffies, stop));
+
+ chip->vendor.cancel(chip);
+ dev_err(chip->dev, "Operation Timed out\n");
+ rc = -ETIME;
+ goto out;
+
+out_recv:
+ rc = chip->vendor.recv(chip, (u8 *) buf, bufsiz);
+ if (rc < 0)
+ dev_err(chip->dev,
+ "tpm_transmit: tpm_recv: error %zd\n", rc);
+out:
+ mutex_unlock(&chip->tpm_mutex);
+ return rc;
+}
+
+#define TPM_DIGEST_SIZE 20
+#define TPM_RET_CODE_IDX 6
+
+enum tpm_capabilities {
+ TPM_CAP_FLAG = cpu_to_be32(4),
+ TPM_CAP_PROP = cpu_to_be32(5),
+ CAP_VERSION_1_1 = cpu_to_be32(0x06),
+ CAP_VERSION_1_2 = cpu_to_be32(0x1A)
+};
+
+enum tpm_sub_capabilities {
+ TPM_CAP_PROP_PCR = cpu_to_be32(0x101),
+ TPM_CAP_PROP_MANUFACTURER = cpu_to_be32(0x103),
+ TPM_CAP_FLAG_PERM = cpu_to_be32(0x108),
+ TPM_CAP_FLAG_VOL = cpu_to_be32(0x109),
+ TPM_CAP_PROP_OWNER = cpu_to_be32(0x111),
+ TPM_CAP_PROP_TIS_TIMEOUT = cpu_to_be32(0x115),
+ TPM_CAP_PROP_TIS_DURATION = cpu_to_be32(0x120),
+
+};
+
+static ssize_t transmit_cmd(struct tpm_chip *chip, struct tpm_cmd_t *cmd,
+ int len, const char *desc)
+{
+ int err;
+
+ len = tpm_transmit(chip, (u8 *) cmd, len);
+ if (len < 0)
+ return len;
+ else if (len < TPM_HEADER_SIZE)
+ return -EFAULT;
+
+ err = be32_to_cpu(cmd->header.out.return_code);
+ if (err != 0 && desc)
+ dev_err(chip->dev, "A TPM error (%d) occurred %s\n", err, desc);
+
+ return err;
+}
+
+#define TPM_INTERNAL_RESULT_SIZE 200
+#define TPM_TAG_RQU_COMMAND cpu_to_be16(193)
+#define TPM_ORD_GET_CAP cpu_to_be32(101)
+#define TPM_ORD_GET_RANDOM cpu_to_be32(70)
+
+static const struct tpm_input_header tpm_getcap_header = {
+ .tag = TPM_TAG_RQU_COMMAND,
+ .length = cpu_to_be32(22),
+ .ordinal = TPM_ORD_GET_CAP
+};
+
+ssize_t tpm_getcap(struct device *dev, __be32 subcap_id, cap_t *cap,
+ const char *desc)
+{
+ struct tpm_cmd_t tpm_cmd;
+ int rc;
+ struct tpm_chip *chip = dev_get_drvdata(dev);
+
+ tpm_cmd.header.in = tpm_getcap_header;
+ if (subcap_id == CAP_VERSION_1_1 || subcap_id == CAP_VERSION_1_2) {
+ tpm_cmd.params.getcap_in.cap = subcap_id;
+ /*subcap field not necessary */
+ tpm_cmd.params.getcap_in.subcap_size = cpu_to_be32(0);
+ tpm_cmd.header.in.length -= cpu_to_be32(sizeof(__be32));
+ } else {
+ if (subcap_id == TPM_CAP_FLAG_PERM ||
+ subcap_id == TPM_CAP_FLAG_VOL)
+ tpm_cmd.params.getcap_in.cap = TPM_CAP_FLAG;
+ else
+ tpm_cmd.params.getcap_in.cap = TPM_CAP_PROP;
+ tpm_cmd.params.getcap_in.subcap_size = cpu_to_be32(4);
+ tpm_cmd.params.getcap_in.subcap = subcap_id;
+ }
+ rc = transmit_cmd(chip, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE, desc);
+ if (!rc)
+ *cap = tpm_cmd.params.getcap_out.cap;
+ return rc;
+}
+
+void tpm_gen_interrupt(struct tpm_chip *chip)
+{
+ struct tpm_cmd_t tpm_cmd;
+ ssize_t rc;
+
+ tpm_cmd.header.in = tpm_getcap_header;
+ tpm_cmd.params.getcap_in.cap = TPM_CAP_PROP;
+ tpm_cmd.params.getcap_in.subcap_size = cpu_to_be32(4);
+ tpm_cmd.params.getcap_in.subcap = TPM_CAP_PROP_TIS_TIMEOUT;
+
+ rc = transmit_cmd(chip, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE,
+ "attempting to determine the timeouts");
+}
+EXPORT_SYMBOL_GPL(tpm_gen_interrupt);
+
+#define TPM_ORD_STARTUP cpu_to_be32(153)
+#define TPM_ST_CLEAR cpu_to_be16(1)
+#define TPM_ST_STATE cpu_to_be16(2)
+#define TPM_ST_DEACTIVATED cpu_to_be16(3)
+static const struct tpm_input_header tpm_startup_header = {
+ .tag = TPM_TAG_RQU_COMMAND,
+ .length = cpu_to_be32(12),
+ .ordinal = TPM_ORD_STARTUP
+};
+
+static int tpm_startup(struct tpm_chip *chip, __be16 startup_type)
+{
+ struct tpm_cmd_t start_cmd;
+ start_cmd.header.in = tpm_startup_header;
+ start_cmd.params.startup_in.startup_type = startup_type;
+ return transmit_cmd(chip, &start_cmd, TPM_INTERNAL_RESULT_SIZE,
+ "attempting to start the TPM");
+}
+
+int tpm_get_timeouts(struct tpm_chip *chip)
+{
+ struct tpm_cmd_t tpm_cmd;
+ struct timeout_t *timeout_cap;
+ struct duration_t *duration_cap;
+ ssize_t rc;
+ u32 timeout;
+ unsigned int scale = 1;
+
+ tpm_cmd.header.in = tpm_getcap_header;
+ tpm_cmd.params.getcap_in.cap = TPM_CAP_PROP;
+ tpm_cmd.params.getcap_in.subcap_size = cpu_to_be32(4);
+ tpm_cmd.params.getcap_in.subcap = TPM_CAP_PROP_TIS_TIMEOUT;
+ rc = transmit_cmd(chip, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE, NULL);
+
+ if (rc == TPM_ERR_INVALID_POSTINIT) {
+ /* The TPM is not started, we are the first to talk to it.
+ Execute a startup command. */
+ dev_info(chip->dev, "Issuing TPM_STARTUP");
+ if (tpm_startup(chip, TPM_ST_CLEAR))
+ return rc;
+
+ tpm_cmd.header.in = tpm_getcap_header;
+ tpm_cmd.params.getcap_in.cap = TPM_CAP_PROP;
+ tpm_cmd.params.getcap_in.subcap_size = cpu_to_be32(4);
+ tpm_cmd.params.getcap_in.subcap = TPM_CAP_PROP_TIS_TIMEOUT;
+ rc = transmit_cmd(chip, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE,
+ NULL);
+ }
+ if (rc) {
+ dev_err(chip->dev,
+ "A TPM error (%zd) occurred attempting to determine the timeouts\n",
+ rc);
+ goto duration;
+ }
+
+ if (be32_to_cpu(tpm_cmd.header.out.return_code) != 0 ||
+ be32_to_cpu(tpm_cmd.header.out.length)
+ != sizeof(tpm_cmd.header.out) + sizeof(u32) + 4 * sizeof(u32))
+ return -EINVAL;
+
+ timeout_cap = &tpm_cmd.params.getcap_out.cap.timeout;
+ /* Don't overwrite default if value is 0 */
+ timeout = be32_to_cpu(timeout_cap->a);
+ if (timeout && timeout < 1000) {
+ /* timeouts in msec rather usec */
+ scale = 1000;
+ chip->vendor.timeout_adjusted = true;
+ }
+ if (timeout)
+ chip->vendor.timeout_a = usecs_to_jiffies(timeout * scale);
+ timeout = be32_to_cpu(timeout_cap->b);
+ if (timeout)
+ chip->vendor.timeout_b = usecs_to_jiffies(timeout * scale);
+ timeout = be32_to_cpu(timeout_cap->c);
+ if (timeout)
+ chip->vendor.timeout_c = usecs_to_jiffies(timeout * scale);
+ timeout = be32_to_cpu(timeout_cap->d);
+ if (timeout)
+ chip->vendor.timeout_d = usecs_to_jiffies(timeout * scale);
+
+duration:
+ tpm_cmd.header.in = tpm_getcap_header;
+ tpm_cmd.params.getcap_in.cap = TPM_CAP_PROP;
+ tpm_cmd.params.getcap_in.subcap_size = cpu_to_be32(4);
+ tpm_cmd.params.getcap_in.subcap = TPM_CAP_PROP_TIS_DURATION;
+
+ rc = transmit_cmd(chip, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE,
+ "attempting to determine the durations");
+ if (rc)
+ return rc;
+
+ if (be32_to_cpu(tpm_cmd.header.out.return_code) != 0 ||
+ be32_to_cpu(tpm_cmd.header.out.length)
+ != sizeof(tpm_cmd.header.out) + sizeof(u32) + 3 * sizeof(u32))
+ return -EINVAL;
+
+ duration_cap = &tpm_cmd.params.getcap_out.cap.duration;
+ chip->vendor.duration[TPM_SHORT] =
+ usecs_to_jiffies(be32_to_cpu(duration_cap->tpm_short));
+ chip->vendor.duration[TPM_MEDIUM] =
+ usecs_to_jiffies(be32_to_cpu(duration_cap->tpm_medium));
+ chip->vendor.duration[TPM_LONG] =
+ usecs_to_jiffies(be32_to_cpu(duration_cap->tpm_long));
+
+ /* The Broadcom BCM0102 chipset in a Dell Latitude D820 gets the above
+ * value wrong and apparently reports msecs rather than usecs. So we
+ * fix up the resulting too-small TPM_SHORT value to make things work.
+ * We also scale the TPM_MEDIUM and -_LONG values by 1000.
+ */
+ if (chip->vendor.duration[TPM_SHORT] < (HZ / 100)) {
+ chip->vendor.duration[TPM_SHORT] = HZ;
+ chip->vendor.duration[TPM_MEDIUM] *= 1000;
+ chip->vendor.duration[TPM_LONG] *= 1000;
+ chip->vendor.duration_adjusted = true;
+ dev_info(chip->dev, "Adjusting TPM timeout parameters.");
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(tpm_get_timeouts);
+
+#define TPM_ORD_CONTINUE_SELFTEST 83
+#define CONTINUE_SELFTEST_RESULT_SIZE 10
+
+static struct tpm_input_header continue_selftest_header = {
+ .tag = TPM_TAG_RQU_COMMAND,
+ .length = cpu_to_be32(10),
+ .ordinal = cpu_to_be32(TPM_ORD_CONTINUE_SELFTEST),
+};
+
+/**
+ * tpm_continue_selftest -- run TPM's selftest
+ * @chip: TPM chip to use
+ *
+ * Returns 0 on success, < 0 in case of fatal error or a value > 0 representing
+ * a TPM error code.
+ */
+static int tpm_continue_selftest(struct tpm_chip *chip)
+{
+ int rc;
+ struct tpm_cmd_t cmd;
+
+ cmd.header.in = continue_selftest_header;
+ rc = transmit_cmd(chip, &cmd, CONTINUE_SELFTEST_RESULT_SIZE,
+ "continue selftest");
+ return rc;
+}
+
+ssize_t tpm_show_enabled(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ cap_t cap;
+ ssize_t rc;
+
+ rc = tpm_getcap(dev, TPM_CAP_FLAG_PERM, &cap,
+ "attempting to determine the permanent enabled state");
+ if (rc)
+ return 0;
+
+ rc = sprintf(buf, "%d\n", !cap.perm_flags.disable);
+ return rc;
+}
+EXPORT_SYMBOL_GPL(tpm_show_enabled);
+
+ssize_t tpm_show_active(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ cap_t cap;
+ ssize_t rc;
+
+ rc = tpm_getcap(dev, TPM_CAP_FLAG_PERM, &cap,
+ "attempting to determine the permanent active state");
+ if (rc)
+ return 0;
+
+ rc = sprintf(buf, "%d\n", !cap.perm_flags.deactivated);
+ return rc;
+}
+EXPORT_SYMBOL_GPL(tpm_show_active);
+
+ssize_t tpm_show_owned(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ cap_t cap;
+ ssize_t rc;
+
+ rc = tpm_getcap(dev, TPM_CAP_PROP_OWNER, &cap,
+ "attempting to determine the owner state");
+ if (rc)
+ return 0;
+
+ rc = sprintf(buf, "%d\n", cap.owned);
+ return rc;
+}
+EXPORT_SYMBOL_GPL(tpm_show_owned);
+
+ssize_t tpm_show_temp_deactivated(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ cap_t cap;
+ ssize_t rc;
+
+ rc = tpm_getcap(dev, TPM_CAP_FLAG_VOL, &cap,
+ "attempting to determine the temporary state");
+ if (rc)
+ return 0;
+
+ rc = sprintf(buf, "%d\n", cap.stclear_flags.deactivated);
+ return rc;
+}
+EXPORT_SYMBOL_GPL(tpm_show_temp_deactivated);
+
+/*
+ * tpm_chip_find_get - return tpm_chip for given chip number
+ */
+static struct tpm_chip *tpm_chip_find_get(int chip_num)
+{
+ struct tpm_chip *pos, *chip = NULL;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(pos, &tpm_chip_list, list) {
+ if (chip_num != TPM_ANY_NUM && chip_num != pos->dev_num)
+ continue;
+
+ if (try_module_get(pos->dev->driver->owner)) {
+ chip = pos;
+ break;
+ }
+ }
+ rcu_read_unlock();
+ return chip;
+}
+
+#define TPM_ORDINAL_PCRREAD cpu_to_be32(21)
+#define READ_PCR_RESULT_SIZE 30
+static struct tpm_input_header pcrread_header = {
+ .tag = TPM_TAG_RQU_COMMAND,
+ .length = cpu_to_be32(14),
+ .ordinal = TPM_ORDINAL_PCRREAD
+};
+
+static int __tpm_pcr_read(struct tpm_chip *chip, int pcr_idx, u8 *res_buf)
+{
+ int rc;
+ struct tpm_cmd_t cmd;
+
+ cmd.header.in = pcrread_header;
+ cmd.params.pcrread_in.pcr_idx = cpu_to_be32(pcr_idx);
+ rc = transmit_cmd(chip, &cmd, READ_PCR_RESULT_SIZE,
+ "attempting to read a pcr value");
+
+ if (rc == 0)
+ memcpy(res_buf, cmd.params.pcrread_out.pcr_result,
+ TPM_DIGEST_SIZE);
+ return rc;
+}
+
+/**
+ * tpm_pcr_read - read a pcr value
+ * @chip_num: tpm idx # or ANY
+ * @pcr_idx: pcr idx to retrieve
+ * @res_buf: TPM_PCR value
+ * size of res_buf is 20 bytes (or NULL if you don't care)
+ *
+ * The TPM driver should be built-in, but for whatever reason it
+ * isn't, protect against the chip disappearing, by incrementing
+ * the module usage count.
+ */
+int tpm_pcr_read(u32 chip_num, int pcr_idx, u8 *res_buf)
+{
+ struct tpm_chip *chip;
+ int rc;
+
+ chip = tpm_chip_find_get(chip_num);
+ if (chip == NULL)
+ return -ENODEV;
+ rc = __tpm_pcr_read(chip, pcr_idx, res_buf);
+ tpm_chip_put(chip);
+ return rc;
+}
+EXPORT_SYMBOL_GPL(tpm_pcr_read);
+
+/**
+ * tpm_pcr_extend - extend pcr value with hash
+ * @chip_num: tpm idx # or AN&
+ * @pcr_idx: pcr idx to extend
+ * @hash: hash value used to extend pcr value
+ *
+ * The TPM driver should be built-in, but for whatever reason it
+ * isn't, protect against the chip disappearing, by incrementing
+ * the module usage count.
+ */
+#define TPM_ORD_PCR_EXTEND cpu_to_be32(20)
+#define EXTEND_PCR_RESULT_SIZE 34
+static struct tpm_input_header pcrextend_header = {
+ .tag = TPM_TAG_RQU_COMMAND,
+ .length = cpu_to_be32(34),
+ .ordinal = TPM_ORD_PCR_EXTEND
+};
+
+int tpm_pcr_extend(u32 chip_num, int pcr_idx, const u8 *hash)
+{
+ struct tpm_cmd_t cmd;
+ int rc;
+ struct tpm_chip *chip;
+
+ chip = tpm_chip_find_get(chip_num);
+ if (chip == NULL)
+ return -ENODEV;
+
+ cmd.header.in = pcrextend_header;
+ cmd.params.pcrextend_in.pcr_idx = cpu_to_be32(pcr_idx);
+ memcpy(cmd.params.pcrextend_in.hash, hash, TPM_DIGEST_SIZE);
+ rc = transmit_cmd(chip, &cmd, EXTEND_PCR_RESULT_SIZE,
+ "attempting extend a PCR value");
+
+ tpm_chip_put(chip);
+ return rc;
+}
+EXPORT_SYMBOL_GPL(tpm_pcr_extend);
+
+/**
+ * tpm_do_selftest - have the TPM continue its selftest and wait until it
+ * can receive further commands
+ * @chip: TPM chip to use
+ *
+ * Returns 0 on success, < 0 in case of fatal error or a value > 0 representing
+ * a TPM error code.
+ */
+int tpm_do_selftest(struct tpm_chip *chip)
+{
+ int rc;
+ unsigned int loops;
+ unsigned int delay_msec = 100;
+ unsigned long duration;
+ struct tpm_cmd_t cmd;
+
+ duration = tpm_calc_ordinal_duration(chip, TPM_ORD_CONTINUE_SELFTEST);
+
+ loops = jiffies_to_msecs(duration) / delay_msec;
+
+ rc = tpm_continue_selftest(chip);
+ /* This may fail if there was no TPM driver during a suspend/resume
+ * cycle; some may return 10 (BAD_ORDINAL), others 28 (FAILEDSELFTEST)
+ */
+ if (rc)
+ return rc;
+
+ do {
+ /* Attempt to read a PCR value */
+ cmd.header.in = pcrread_header;
+ cmd.params.pcrread_in.pcr_idx = cpu_to_be32(0);
+ rc = tpm_transmit(chip, (u8 *) &cmd, READ_PCR_RESULT_SIZE);
+ /* Some buggy TPMs will not respond to tpm_tis_ready() for
+ * around 300ms while the self test is ongoing, keep trying
+ * until the self test duration expires. */
+ if (rc == -ETIME) {
+ dev_info(chip->dev, HW_ERR "TPM command timed out during continue self test");
+ msleep(delay_msec);
+ continue;
+ }
+
+ if (rc < TPM_HEADER_SIZE)
+ return -EFAULT;
+
+ rc = be32_to_cpu(cmd.header.out.return_code);
+ if (rc == TPM_ERR_DISABLED || rc == TPM_ERR_DEACTIVATED) {
+ dev_info(chip->dev,
+ "TPM is disabled/deactivated (0x%X)\n", rc);
+ /* TPM is disabled and/or deactivated; driver can
+ * proceed and TPM does handle commands for
+ * suspend/resume correctly
+ */
+ return 0;
+ }
+ if (rc != TPM_WARN_DOING_SELFTEST)
+ return rc;
+ msleep(delay_msec);
+ } while (--loops > 0);
+
+ return rc;
+}
+EXPORT_SYMBOL_GPL(tpm_do_selftest);
+
+int tpm_send(u32 chip_num, void *cmd, size_t buflen)
+{
+ struct tpm_chip *chip;
+ int rc;
+
+ chip = tpm_chip_find_get(chip_num);
+ if (chip == NULL)
+ return -ENODEV;
+
+ rc = transmit_cmd(chip, cmd, buflen, "attempting tpm_cmd");
+
+ tpm_chip_put(chip);
+ return rc;
+}
+EXPORT_SYMBOL_GPL(tpm_send);
+
+ssize_t tpm_show_pcrs(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ cap_t cap;
+ u8 digest[TPM_DIGEST_SIZE];
+ ssize_t rc;
+ int i, j, num_pcrs;
+ char *str = buf;
+ struct tpm_chip *chip = dev_get_drvdata(dev);
+
+ rc = tpm_getcap(dev, TPM_CAP_PROP_PCR, &cap,
+ "attempting to determine the number of PCRS");
+ if (rc)
+ return 0;
+
+ num_pcrs = be32_to_cpu(cap.num_pcrs);
+ for (i = 0; i < num_pcrs; i++) {
+ rc = __tpm_pcr_read(chip, i, digest);
+ if (rc)
+ break;
+ str += sprintf(str, "PCR-%02d: ", i);
+ for (j = 0; j < TPM_DIGEST_SIZE; j++)
+ str += sprintf(str, "%02X ", digest[j]);
+ str += sprintf(str, "\n");
+ }
+ return str - buf;
+}
+EXPORT_SYMBOL_GPL(tpm_show_pcrs);
+
+#define READ_PUBEK_RESULT_SIZE 314
+#define TPM_ORD_READPUBEK cpu_to_be32(124)
+static struct tpm_input_header tpm_readpubek_header = {
+ .tag = TPM_TAG_RQU_COMMAND,
+ .length = cpu_to_be32(30),
+ .ordinal = TPM_ORD_READPUBEK
+};
+
+ssize_t tpm_show_pubek(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ u8 *data;
+ struct tpm_cmd_t tpm_cmd;
+ ssize_t err;
+ int i, rc;
+ char *str = buf;
+
+ struct tpm_chip *chip = dev_get_drvdata(dev);
+
+ tpm_cmd.header.in = tpm_readpubek_header;
+ err = transmit_cmd(chip, &tpm_cmd, READ_PUBEK_RESULT_SIZE,
+ "attempting to read the PUBEK");
+ if (err)
+ goto out;
+
+ /*
+ ignore header 10 bytes
+ algorithm 32 bits (1 == RSA )
+ encscheme 16 bits
+ sigscheme 16 bits
+ parameters (RSA 12->bytes: keybit, #primes, expbit)
+ keylenbytes 32 bits
+ 256 byte modulus
+ ignore checksum 20 bytes
+ */
+ data = tpm_cmd.params.readpubek_out_buffer;
+ str +=
+ sprintf(str,
+ "Algorithm: %02X %02X %02X %02X\n"
+ "Encscheme: %02X %02X\n"
+ "Sigscheme: %02X %02X\n"
+ "Parameters: %02X %02X %02X %02X "
+ "%02X %02X %02X %02X "
+ "%02X %02X %02X %02X\n"
+ "Modulus length: %d\n"
+ "Modulus:\n",
+ data[0], data[1], data[2], data[3],
+ data[4], data[5],
+ data[6], data[7],
+ data[12], data[13], data[14], data[15],
+ data[16], data[17], data[18], data[19],
+ data[20], data[21], data[22], data[23],
+ be32_to_cpu(*((__be32 *) (data + 24))));
+
+ for (i = 0; i < 256; i++) {
+ str += sprintf(str, "%02X ", data[i + 28]);
+ if ((i + 1) % 16 == 0)
+ str += sprintf(str, "\n");
+ }
+out:
+ rc = str - buf;
+ return rc;
+}
+EXPORT_SYMBOL_GPL(tpm_show_pubek);
+
+
+ssize_t tpm_show_caps(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ cap_t cap;
+ ssize_t rc;
+ char *str = buf;
+
+ rc = tpm_getcap(dev, TPM_CAP_PROP_MANUFACTURER, &cap,
+ "attempting to determine the manufacturer");
+ if (rc)
+ return 0;
+ str += sprintf(str, "Manufacturer: 0x%x\n",
+ be32_to_cpu(cap.manufacturer_id));
+
+ /* Try to get a TPM version 1.2 TPM_CAP_VERSION_INFO */
+ rc = tpm_getcap(dev, CAP_VERSION_1_2, &cap,
+ "attempting to determine the 1.2 version");
+ if (!rc) {
+ str += sprintf(str,
+ "TCG version: %d.%d\nFirmware version: %d.%d\n",
+ cap.tpm_version_1_2.Major,
+ cap.tpm_version_1_2.Minor,
+ cap.tpm_version_1_2.revMajor,
+ cap.tpm_version_1_2.revMinor);
+ } else {
+ /* Otherwise just use TPM_STRUCT_VER */
+ rc = tpm_getcap(dev, CAP_VERSION_1_1, &cap,
+ "attempting to determine the 1.1 version");
+ if (rc)
+ return 0;
+ str += sprintf(str,
+ "TCG version: %d.%d\nFirmware version: %d.%d\n",
+ cap.tpm_version.Major,
+ cap.tpm_version.Minor,
+ cap.tpm_version.revMajor,
+ cap.tpm_version.revMinor);
+ }
+
+ return str - buf;
+}
+EXPORT_SYMBOL_GPL(tpm_show_caps);
+
+ssize_t tpm_show_durations(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct tpm_chip *chip = dev_get_drvdata(dev);
+
+ if (chip->vendor.duration[TPM_LONG] == 0)
+ return 0;
+
+ return sprintf(buf, "%d %d %d [%s]\n",
+ jiffies_to_usecs(chip->vendor.duration[TPM_SHORT]),
+ jiffies_to_usecs(chip->vendor.duration[TPM_MEDIUM]),
+ jiffies_to_usecs(chip->vendor.duration[TPM_LONG]),
+ chip->vendor.duration_adjusted
+ ? "adjusted" : "original");
+}
+EXPORT_SYMBOL_GPL(tpm_show_durations);
+
+ssize_t tpm_show_timeouts(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct tpm_chip *chip = dev_get_drvdata(dev);
+
+ return sprintf(buf, "%d %d %d %d [%s]\n",
+ jiffies_to_usecs(chip->vendor.timeout_a),
+ jiffies_to_usecs(chip->vendor.timeout_b),
+ jiffies_to_usecs(chip->vendor.timeout_c),
+ jiffies_to_usecs(chip->vendor.timeout_d),
+ chip->vendor.timeout_adjusted
+ ? "adjusted" : "original");
+}
+EXPORT_SYMBOL_GPL(tpm_show_timeouts);
+
+ssize_t tpm_store_cancel(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct tpm_chip *chip = dev_get_drvdata(dev);
+ if (chip == NULL)
+ return 0;
+
+ chip->vendor.cancel(chip);
+ return count;
+}
+EXPORT_SYMBOL_GPL(tpm_store_cancel);
+
+static bool wait_for_tpm_stat_cond(struct tpm_chip *chip, u8 mask,
+ bool check_cancel, bool *canceled)
+{
+ u8 status = chip->vendor.status(chip);
+
+ *canceled = false;
+ if ((status & mask) == mask)
+ return true;
+ if (check_cancel && chip->vendor.req_canceled(chip, status)) {
+ *canceled = true;
+ return true;
+ }
+ return false;
+}
+
+int wait_for_tpm_stat(struct tpm_chip *chip, u8 mask, unsigned long timeout,
+ wait_queue_head_t *queue, bool check_cancel)
+{
+ unsigned long stop;
+ long rc;
+ u8 status;
+ bool canceled = false;
+
+ /* check current status */
+ status = chip->vendor.status(chip);
+ if ((status & mask) == mask)
+ return 0;
+
+ stop = jiffies + timeout;
+
+ if (chip->vendor.irq) {
+again:
+ timeout = stop - jiffies;
+ if ((long)timeout <= 0)
+ return -ETIME;
+ rc = wait_event_interruptible_timeout(*queue,
+ wait_for_tpm_stat_cond(chip, mask, check_cancel,
+ &canceled),
+ timeout);
+ if (rc > 0) {
+ if (canceled)
+ return -ECANCELED;
+ return 0;
+ }
+ if (rc == -ERESTARTSYS && freezing(current)) {
+ clear_thread_flag(TIF_SIGPENDING);
+ goto again;
+ }
+ } else {
+ do {
+ msleep(TPM_TIMEOUT);
+ status = chip->vendor.status(chip);
+ if ((status & mask) == mask)
+ return 0;
+ } while (time_before(jiffies, stop));
+ }
+ return -ETIME;
+}
+EXPORT_SYMBOL_GPL(wait_for_tpm_stat);
+/*
+ * Device file system interface to the TPM
+ *
+ * It's assured that the chip will be opened just once,
+ * by the check of is_open variable, which is protected
+ * by driver_lock.
+ */
+int tpm_open(struct inode *inode, struct file *file)
+{
+ struct miscdevice *misc = file->private_data;
+ struct tpm_chip *chip = container_of(misc, struct tpm_chip,
+ vendor.miscdev);
+
+ if (test_and_set_bit(0, &chip->is_open)) {
+ dev_dbg(chip->dev, "Another process owns this TPM\n");
+ return -EBUSY;
+ }
+
+ chip->data_buffer = kzalloc(TPM_BUFSIZE, GFP_KERNEL);
+ if (chip->data_buffer == NULL) {
+ clear_bit(0, &chip->is_open);
+ return -ENOMEM;
+ }
+
+ atomic_set(&chip->data_pending, 0);
+
+ file->private_data = chip;
+ get_device(chip->dev);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(tpm_open);
+
+/*
+ * Called on file close
+ */
+int tpm_release(struct inode *inode, struct file *file)
+{
+ struct tpm_chip *chip = file->private_data;
+
+ del_singleshot_timer_sync(&chip->user_read_timer);
+ flush_work(&chip->work);
+ file->private_data = NULL;
+ atomic_set(&chip->data_pending, 0);
+ kzfree(chip->data_buffer);
+ clear_bit(0, &chip->is_open);
+ put_device(chip->dev);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(tpm_release);
+
+ssize_t tpm_write(struct file *file, const char __user *buf,
+ size_t size, loff_t *off)
+{
+ struct tpm_chip *chip = file->private_data;
+ size_t in_size = size;
+ ssize_t out_size;
+
+ /* cannot perform a write until the read has cleared
+ either via tpm_read or a user_read_timer timeout.
+ This also prevents splitted buffered writes from blocking here.
+ */
+ if (atomic_read(&chip->data_pending) != 0)
+ return -EBUSY;
+
+ if (in_size > TPM_BUFSIZE)
+ return -E2BIG;
+
+ mutex_lock(&chip->buffer_mutex);
+
+ if (copy_from_user
+ (chip->data_buffer, (void __user *) buf, in_size)) {
+ mutex_unlock(&chip->buffer_mutex);
+ return -EFAULT;
+ }
+
+ /* atomic tpm command send and result receive */
+ out_size = tpm_transmit(chip, chip->data_buffer, TPM_BUFSIZE);
+ if (out_size < 0) {
+ mutex_unlock(&chip->buffer_mutex);
+ return out_size;
+ }
+
+ atomic_set(&chip->data_pending, out_size);
+ mutex_unlock(&chip->buffer_mutex);
+
+ /* Set a timeout by which the reader must come claim the result */
+ mod_timer(&chip->user_read_timer, jiffies + (60 * HZ));
+
+ return in_size;
+}
+EXPORT_SYMBOL_GPL(tpm_write);
+
+ssize_t tpm_read(struct file *file, char __user *buf,
+ size_t size, loff_t *off)
+{
+ struct tpm_chip *chip = file->private_data;
+ ssize_t ret_size;
+ int rc;
+
+ del_singleshot_timer_sync(&chip->user_read_timer);
+ flush_work(&chip->work);
+ ret_size = atomic_read(&chip->data_pending);
+ if (ret_size > 0) { /* relay data */
+ ssize_t orig_ret_size = ret_size;
+ if (size < ret_size)
+ ret_size = size;
+
+ mutex_lock(&chip->buffer_mutex);
+ rc = copy_to_user(buf, chip->data_buffer, ret_size);
+ memset(chip->data_buffer, 0, orig_ret_size);
+ if (rc)
+ ret_size = -EFAULT;
+
+ mutex_unlock(&chip->buffer_mutex);
+ }
+
+ atomic_set(&chip->data_pending, 0);
+
+ return ret_size;
+}
+EXPORT_SYMBOL_GPL(tpm_read);
+
+void tpm_remove_hardware(struct device *dev)
+{
+ struct tpm_chip *chip = dev_get_drvdata(dev);
+
+ if (chip == NULL) {
+ dev_err(dev, "No device data found\n");
+ return;
+ }
+
+ spin_lock(&driver_lock);
+ list_del_rcu(&chip->list);
+ spin_unlock(&driver_lock);
+ synchronize_rcu();
+
+ misc_deregister(&chip->vendor.miscdev);
+ sysfs_remove_group(&dev->kobj, chip->vendor.attr_group);
+ tpm_remove_ppi(&dev->kobj);
+ tpm_bios_log_teardown(chip->bios_dir);
+
+ /* write it this way to be explicit (chip->dev == dev) */
+ put_device(chip->dev);
+}
+EXPORT_SYMBOL_GPL(tpm_remove_hardware);
+
+#define TPM_ORD_SAVESTATE cpu_to_be32(152)
+#define SAVESTATE_RESULT_SIZE 10
+
+static struct tpm_input_header savestate_header = {
+ .tag = TPM_TAG_RQU_COMMAND,
+ .length = cpu_to_be32(10),
+ .ordinal = TPM_ORD_SAVESTATE
+};
+
+/*
+ * We are about to suspend. Save the TPM state
+ * so that it can be restored.
+ */
+int tpm_pm_suspend(struct device *dev)
+{
+ struct tpm_chip *chip = dev_get_drvdata(dev);
+ struct tpm_cmd_t cmd;
+ int rc, try;
+
+ u8 dummy_hash[TPM_DIGEST_SIZE] = { 0 };
+
+ if (chip == NULL)
+ return -ENODEV;
+
+ /* for buggy tpm, flush pcrs with extend to selected dummy */
+ if (tpm_suspend_pcr) {
+ cmd.header.in = pcrextend_header;
+ cmd.params.pcrextend_in.pcr_idx = cpu_to_be32(tpm_suspend_pcr);
+ memcpy(cmd.params.pcrextend_in.hash, dummy_hash,
+ TPM_DIGEST_SIZE);
+ rc = transmit_cmd(chip, &cmd, EXTEND_PCR_RESULT_SIZE,
+ "extending dummy pcr before suspend");
+ }
+
+ /* now do the actual savestate */
+ for (try = 0; try < TPM_RETRY; try++) {
+ cmd.header.in = savestate_header;
+ rc = transmit_cmd(chip, &cmd, SAVESTATE_RESULT_SIZE, NULL);
+
+ /*
+ * If the TPM indicates that it is too busy to respond to
+ * this command then retry before giving up. It can take
+ * several seconds for this TPM to be ready.
+ *
+ * This can happen if the TPM has already been sent the
+ * SaveState command before the driver has loaded. TCG 1.2
+ * specification states that any communication after SaveState
+ * may cause the TPM to invalidate previously saved state.
+ */
+ if (rc != TPM_WARN_RETRY)
+ break;
+ msleep(TPM_TIMEOUT_RETRY);
+ }
+
+ if (rc)
+ dev_err(chip->dev,
+ "Error (%d) sending savestate before suspend\n", rc);
+ else if (try > 0)
+ dev_warn(chip->dev, "TPM savestate took %dms\n",
+ try * TPM_TIMEOUT_RETRY);
+
+ return rc;
+}
+EXPORT_SYMBOL_GPL(tpm_pm_suspend);
+
+/*
+ * Resume from a power safe. The BIOS already restored
+ * the TPM state.
+ */
+int tpm_pm_resume(struct device *dev)
+{
+ struct tpm_chip *chip = dev_get_drvdata(dev);
+
+ if (chip == NULL)
+ return -ENODEV;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(tpm_pm_resume);
+
+#define TPM_GETRANDOM_RESULT_SIZE 18
+static struct tpm_input_header tpm_getrandom_header = {
+ .tag = TPM_TAG_RQU_COMMAND,
+ .length = cpu_to_be32(14),
+ .ordinal = TPM_ORD_GET_RANDOM
+};
+
+/**
+ * tpm_get_random() - Get random bytes from the tpm's RNG
+ * @chip_num: A specific chip number for the request or TPM_ANY_NUM
+ * @out: destination buffer for the random bytes
+ * @max: the max number of bytes to write to @out
+ *
+ * Returns < 0 on error and the number of bytes read on success
+ */
+int tpm_get_random(u32 chip_num, u8 *out, size_t max)
+{
+ struct tpm_chip *chip;
+ struct tpm_cmd_t tpm_cmd;
+ u32 recd, num_bytes = min_t(u32, max, TPM_MAX_RNG_DATA);
+ int err, total = 0, retries = 5;
+ u8 *dest = out;
+
+ chip = tpm_chip_find_get(chip_num);
+ if (chip == NULL)
+ return -ENODEV;
+
+ if (!out || !num_bytes || max > TPM_MAX_RNG_DATA)
+ return -EINVAL;
+
+ do {
+ tpm_cmd.header.in = tpm_getrandom_header;
+ tpm_cmd.params.getrandom_in.num_bytes = cpu_to_be32(num_bytes);
+
+ err = transmit_cmd(chip, &tpm_cmd,
+ TPM_GETRANDOM_RESULT_SIZE + num_bytes,
+ "attempting get random");
+ if (err)
+ break;
+
+ recd = be32_to_cpu(tpm_cmd.params.getrandom_out.rng_data_len);
+ memcpy(dest, tpm_cmd.params.getrandom_out.rng_data, recd);
+
+ dest += recd;
+ total += recd;
+ num_bytes -= recd;
+ } while (retries-- && total < max);
+
+ return total ? total : -EIO;
+}
+EXPORT_SYMBOL_GPL(tpm_get_random);
+
+/* In case vendor provided release function, call it too.*/
+
+void tpm_dev_vendor_release(struct tpm_chip *chip)
+{
+ if (!chip)
+ return;
+
+ if (chip->vendor.release)
+ chip->vendor.release(chip->dev);
+
+ clear_bit(chip->dev_num, dev_mask);
+}
+EXPORT_SYMBOL_GPL(tpm_dev_vendor_release);
+
+
+/*
+ * Once all references to platform device are down to 0,
+ * release all allocated structures.
+ */
+void tpm_dev_release(struct device *dev)
+{
+ struct tpm_chip *chip = dev_get_drvdata(dev);
+
+ if (!chip)
+ return;
+
+ tpm_dev_vendor_release(chip);
+
+ chip->release(dev);
+ kfree(chip);
+}
+EXPORT_SYMBOL_GPL(tpm_dev_release);
+
+/*
+ * Called from tpm_<specific>.c probe function only for devices
+ * the driver has determined it should claim. Prior to calling
+ * this function the specific probe function has called pci_enable_device
+ * upon errant exit from this function specific probe function should call
+ * pci_disable_device
+ */
+struct tpm_chip *tpm_register_hardware(struct device *dev,
+ const struct tpm_vendor_specific *entry)
+{
+ struct tpm_chip *chip;
+
+ /* Driver specific per-device data */
+ chip = kzalloc(sizeof(*chip), GFP_KERNEL);
+
+ if (chip == NULL)
+ return NULL;
+
+ mutex_init(&chip->buffer_mutex);
+ mutex_init(&chip->tpm_mutex);
+ INIT_LIST_HEAD(&chip->list);
+
+ INIT_WORK(&chip->work, timeout_work);
+
+ setup_timer(&chip->user_read_timer, user_reader_timeout,
+ (unsigned long)chip);
+
+ memcpy(&chip->vendor, entry, sizeof(struct tpm_vendor_specific));
+
+ chip->dev_num = find_first_zero_bit(dev_mask, TPM_NUM_DEVICES);
+
+ if (chip->dev_num >= TPM_NUM_DEVICES) {
+ dev_err(dev, "No available tpm device numbers\n");
+ goto out_free;
+ } else if (chip->dev_num == 0)
+ chip->vendor.miscdev.minor = TPM_MINOR;
+ else
+ chip->vendor.miscdev.minor = MISC_DYNAMIC_MINOR;
+
+ set_bit(chip->dev_num, dev_mask);
+
+ scnprintf(chip->devname, sizeof(chip->devname), "%s%d", "tpm",
+ chip->dev_num);
+ chip->vendor.miscdev.name = chip->devname;
+
+ chip->vendor.miscdev.parent = dev;
+ chip->dev = get_device(dev);
+ chip->release = dev->release;
+ dev->release = tpm_dev_release;
+ dev_set_drvdata(dev, chip);
+
+ if (misc_register(&chip->vendor.miscdev)) {
+ dev_err(chip->dev,
+ "unable to misc_register %s, minor %d\n",
+ chip->vendor.miscdev.name,
+ chip->vendor.miscdev.minor);
+ goto put_device;
+ }
+
+ if (sysfs_create_group(&dev->kobj, chip->vendor.attr_group)) {
+ misc_deregister(&chip->vendor.miscdev);
+ goto put_device;
+ }
+
+ if (tpm_add_ppi(&dev->kobj)) {
+ misc_deregister(&chip->vendor.miscdev);
+ goto put_device;
+ }
+
+ chip->bios_dir = tpm_bios_log_setup(chip->devname);
+
+ /* Make chip available */
+ spin_lock(&driver_lock);
+ list_add_rcu(&chip->list, &tpm_chip_list);
+ spin_unlock(&driver_lock);
+
+ return chip;
+
+put_device:
+ put_device(chip->dev);
+out_free:
+ kfree(chip);
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(tpm_register_hardware);
+
+MODULE_AUTHOR("Leendert van Doorn (leendert@watson.ibm.com)");
+MODULE_DESCRIPTION("TPM Driver");
+MODULE_VERSION("2.0");
+MODULE_LICENSE("GPL");
+++ /dev/null
-/*
- * Copyright (C) 2004 IBM Corporation
- *
- * Authors:
- * Leendert van Doorn <leendert@watson.ibm.com>
- * Dave Safford <safford@watson.ibm.com>
- * Reiner Sailer <sailer@watson.ibm.com>
- * Kylene Hall <kjhall@us.ibm.com>
- *
- * Maintained by: <tpmdd-devel@lists.sourceforge.net>
- *
- * Device driver for TCG/TCPA TPM (trusted platform module).
- * Specifications at www.trustedcomputinggroup.org
- *
- * 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, version 2 of the
- * License.
- *
- * Note, the TPM chip is not interrupt driven (only polling)
- * and can have very long timeouts (minutes!). Hence the unusual
- * calls to msleep.
- *
- */
-
-#include <linux/poll.h>
-#include <linux/slab.h>
-#include <linux/mutex.h>
-#include <linux/spinlock.h>
-#include <linux/freezer.h>
-
-#include "tpm.h"
-#include "tpm_eventlog.h"
-
-enum tpm_duration {
- TPM_SHORT = 0,
- TPM_MEDIUM = 1,
- TPM_LONG = 2,
- TPM_UNDEFINED,
-};
-
-#define TPM_MAX_ORDINAL 243
-#define TSC_MAX_ORDINAL 12
-#define TPM_PROTECTED_COMMAND 0x00
-#define TPM_CONNECTION_COMMAND 0x40
-
-/*
- * Bug workaround - some TPM's don't flush the most
- * recently changed pcr on suspend, so force the flush
- * with an extend to the selected _unused_ non-volatile pcr.
- */
-static int tpm_suspend_pcr;
-module_param_named(suspend_pcr, tpm_suspend_pcr, uint, 0644);
-MODULE_PARM_DESC(suspend_pcr,
- "PCR to use for dummy writes to faciltate flush on suspend.");
-
-static LIST_HEAD(tpm_chip_list);
-static DEFINE_SPINLOCK(driver_lock);
-static DECLARE_BITMAP(dev_mask, TPM_NUM_DEVICES);
-
-/*
- * Array with one entry per ordinal defining the maximum amount
- * of time the chip could take to return the result. The ordinal
- * designation of short, medium or long is defined in a table in
- * TCG Specification TPM Main Part 2 TPM Structures Section 17. The
- * values of the SHORT, MEDIUM, and LONG durations are retrieved
- * from the chip during initialization with a call to tpm_get_timeouts.
- */
-static const u8 tpm_ordinal_duration[TPM_MAX_ORDINAL] = {
- TPM_UNDEFINED, /* 0 */
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED, /* 5 */
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_SHORT, /* 10 */
- TPM_SHORT,
- TPM_MEDIUM,
- TPM_LONG,
- TPM_LONG,
- TPM_MEDIUM, /* 15 */
- TPM_SHORT,
- TPM_SHORT,
- TPM_MEDIUM,
- TPM_LONG,
- TPM_SHORT, /* 20 */
- TPM_SHORT,
- TPM_MEDIUM,
- TPM_MEDIUM,
- TPM_MEDIUM,
- TPM_SHORT, /* 25 */
- TPM_SHORT,
- TPM_MEDIUM,
- TPM_SHORT,
- TPM_SHORT,
- TPM_MEDIUM, /* 30 */
- TPM_LONG,
- TPM_MEDIUM,
- TPM_SHORT,
- TPM_SHORT,
- TPM_SHORT, /* 35 */
- TPM_MEDIUM,
- TPM_MEDIUM,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_MEDIUM, /* 40 */
- TPM_LONG,
- TPM_MEDIUM,
- TPM_SHORT,
- TPM_SHORT,
- TPM_SHORT, /* 45 */
- TPM_SHORT,
- TPM_SHORT,
- TPM_SHORT,
- TPM_LONG,
- TPM_MEDIUM, /* 50 */
- TPM_MEDIUM,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED, /* 55 */
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_MEDIUM, /* 60 */
- TPM_MEDIUM,
- TPM_MEDIUM,
- TPM_SHORT,
- TPM_SHORT,
- TPM_MEDIUM, /* 65 */
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_SHORT, /* 70 */
- TPM_SHORT,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED, /* 75 */
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_LONG, /* 80 */
- TPM_UNDEFINED,
- TPM_MEDIUM,
- TPM_LONG,
- TPM_SHORT,
- TPM_UNDEFINED, /* 85 */
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_SHORT, /* 90 */
- TPM_SHORT,
- TPM_SHORT,
- TPM_SHORT,
- TPM_SHORT,
- TPM_UNDEFINED, /* 95 */
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_MEDIUM, /* 100 */
- TPM_SHORT,
- TPM_SHORT,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED, /* 105 */
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_SHORT, /* 110 */
- TPM_SHORT,
- TPM_SHORT,
- TPM_SHORT,
- TPM_SHORT,
- TPM_SHORT, /* 115 */
- TPM_SHORT,
- TPM_SHORT,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_LONG, /* 120 */
- TPM_LONG,
- TPM_MEDIUM,
- TPM_UNDEFINED,
- TPM_SHORT,
- TPM_SHORT, /* 125 */
- TPM_SHORT,
- TPM_LONG,
- TPM_SHORT,
- TPM_SHORT,
- TPM_SHORT, /* 130 */
- TPM_MEDIUM,
- TPM_UNDEFINED,
- TPM_SHORT,
- TPM_MEDIUM,
- TPM_UNDEFINED, /* 135 */
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_SHORT, /* 140 */
- TPM_SHORT,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED, /* 145 */
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_SHORT, /* 150 */
- TPM_MEDIUM,
- TPM_MEDIUM,
- TPM_SHORT,
- TPM_SHORT,
- TPM_UNDEFINED, /* 155 */
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_SHORT, /* 160 */
- TPM_SHORT,
- TPM_SHORT,
- TPM_SHORT,
- TPM_UNDEFINED,
- TPM_UNDEFINED, /* 165 */
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_LONG, /* 170 */
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED, /* 175 */
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_MEDIUM, /* 180 */
- TPM_SHORT,
- TPM_MEDIUM,
- TPM_MEDIUM,
- TPM_MEDIUM,
- TPM_MEDIUM, /* 185 */
- TPM_SHORT,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED, /* 190 */
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED, /* 195 */
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_SHORT, /* 200 */
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_SHORT,
- TPM_SHORT, /* 205 */
- TPM_SHORT,
- TPM_SHORT,
- TPM_SHORT,
- TPM_SHORT,
- TPM_MEDIUM, /* 210 */
- TPM_UNDEFINED,
- TPM_MEDIUM,
- TPM_MEDIUM,
- TPM_MEDIUM,
- TPM_UNDEFINED, /* 215 */
- TPM_MEDIUM,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_SHORT,
- TPM_SHORT, /* 220 */
- TPM_SHORT,
- TPM_SHORT,
- TPM_SHORT,
- TPM_SHORT,
- TPM_UNDEFINED, /* 225 */
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_SHORT, /* 230 */
- TPM_LONG,
- TPM_MEDIUM,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED, /* 235 */
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_UNDEFINED,
- TPM_SHORT, /* 240 */
- TPM_UNDEFINED,
- TPM_MEDIUM,
-};
-
-static void user_reader_timeout(unsigned long ptr)
-{
- struct tpm_chip *chip = (struct tpm_chip *) ptr;
-
- schedule_work(&chip->work);
-}
-
-static void timeout_work(struct work_struct *work)
-{
- struct tpm_chip *chip = container_of(work, struct tpm_chip, work);
-
- mutex_lock(&chip->buffer_mutex);
- atomic_set(&chip->data_pending, 0);
- memset(chip->data_buffer, 0, TPM_BUFSIZE);
- mutex_unlock(&chip->buffer_mutex);
-}
-
-/*
- * Returns max number of jiffies to wait
- */
-unsigned long tpm_calc_ordinal_duration(struct tpm_chip *chip,
- u32 ordinal)
-{
- int duration_idx = TPM_UNDEFINED;
- int duration = 0;
- u8 category = (ordinal >> 24) & 0xFF;
-
- if ((category == TPM_PROTECTED_COMMAND && ordinal < TPM_MAX_ORDINAL) ||
- (category == TPM_CONNECTION_COMMAND && ordinal < TSC_MAX_ORDINAL))
- duration_idx = tpm_ordinal_duration[ordinal];
-
- if (duration_idx != TPM_UNDEFINED)
- duration = chip->vendor.duration[duration_idx];
- if (duration <= 0)
- return 2 * 60 * HZ;
- else
- return duration;
-}
-EXPORT_SYMBOL_GPL(tpm_calc_ordinal_duration);
-
-/*
- * Internal kernel interface to transmit TPM commands
- */
-static ssize_t tpm_transmit(struct tpm_chip *chip, const char *buf,
- size_t bufsiz)
-{
- ssize_t rc;
- u32 count, ordinal;
- unsigned long stop;
-
- if (bufsiz > TPM_BUFSIZE)
- bufsiz = TPM_BUFSIZE;
-
- count = be32_to_cpu(*((__be32 *) (buf + 2)));
- ordinal = be32_to_cpu(*((__be32 *) (buf + 6)));
- if (count == 0)
- return -ENODATA;
- if (count > bufsiz) {
- dev_err(chip->dev,
- "invalid count value %x %zx \n", count, bufsiz);
- return -E2BIG;
- }
-
- mutex_lock(&chip->tpm_mutex);
-
- if ((rc = chip->vendor.send(chip, (u8 *) buf, count)) < 0) {
- dev_err(chip->dev,
- "tpm_transmit: tpm_send: error %zd\n", rc);
- goto out;
- }
-
- if (chip->vendor.irq)
- goto out_recv;
-
- stop = jiffies + tpm_calc_ordinal_duration(chip, ordinal);
- do {
- u8 status = chip->vendor.status(chip);
- if ((status & chip->vendor.req_complete_mask) ==
- chip->vendor.req_complete_val)
- goto out_recv;
-
- if (chip->vendor.req_canceled(chip, status)) {
- dev_err(chip->dev, "Operation Canceled\n");
- rc = -ECANCELED;
- goto out;
- }
-
- msleep(TPM_TIMEOUT); /* CHECK */
- rmb();
- } while (time_before(jiffies, stop));
-
- chip->vendor.cancel(chip);
- dev_err(chip->dev, "Operation Timed out\n");
- rc = -ETIME;
- goto out;
-
-out_recv:
- rc = chip->vendor.recv(chip, (u8 *) buf, bufsiz);
- if (rc < 0)
- dev_err(chip->dev,
- "tpm_transmit: tpm_recv: error %zd\n", rc);
-out:
- mutex_unlock(&chip->tpm_mutex);
- return rc;
-}
-
-#define TPM_DIGEST_SIZE 20
-#define TPM_RET_CODE_IDX 6
-
-enum tpm_capabilities {
- TPM_CAP_FLAG = cpu_to_be32(4),
- TPM_CAP_PROP = cpu_to_be32(5),
- CAP_VERSION_1_1 = cpu_to_be32(0x06),
- CAP_VERSION_1_2 = cpu_to_be32(0x1A)
-};
-
-enum tpm_sub_capabilities {
- TPM_CAP_PROP_PCR = cpu_to_be32(0x101),
- TPM_CAP_PROP_MANUFACTURER = cpu_to_be32(0x103),
- TPM_CAP_FLAG_PERM = cpu_to_be32(0x108),
- TPM_CAP_FLAG_VOL = cpu_to_be32(0x109),
- TPM_CAP_PROP_OWNER = cpu_to_be32(0x111),
- TPM_CAP_PROP_TIS_TIMEOUT = cpu_to_be32(0x115),
- TPM_CAP_PROP_TIS_DURATION = cpu_to_be32(0x120),
-
-};
-
-static ssize_t transmit_cmd(struct tpm_chip *chip, struct tpm_cmd_t *cmd,
- int len, const char *desc)
-{
- int err;
-
- len = tpm_transmit(chip,(u8 *) cmd, len);
- if (len < 0)
- return len;
- else if (len < TPM_HEADER_SIZE)
- return -EFAULT;
-
- err = be32_to_cpu(cmd->header.out.return_code);
- if (err != 0 && desc)
- dev_err(chip->dev, "A TPM error (%d) occurred %s\n", err, desc);
-
- return err;
-}
-
-#define TPM_INTERNAL_RESULT_SIZE 200
-#define TPM_TAG_RQU_COMMAND cpu_to_be16(193)
-#define TPM_ORD_GET_CAP cpu_to_be32(101)
-#define TPM_ORD_GET_RANDOM cpu_to_be32(70)
-
-static const struct tpm_input_header tpm_getcap_header = {
- .tag = TPM_TAG_RQU_COMMAND,
- .length = cpu_to_be32(22),
- .ordinal = TPM_ORD_GET_CAP
-};
-
-ssize_t tpm_getcap(struct device *dev, __be32 subcap_id, cap_t *cap,
- const char *desc)
-{
- struct tpm_cmd_t tpm_cmd;
- int rc;
- struct tpm_chip *chip = dev_get_drvdata(dev);
-
- tpm_cmd.header.in = tpm_getcap_header;
- if (subcap_id == CAP_VERSION_1_1 || subcap_id == CAP_VERSION_1_2) {
- tpm_cmd.params.getcap_in.cap = subcap_id;
- /*subcap field not necessary */
- tpm_cmd.params.getcap_in.subcap_size = cpu_to_be32(0);
- tpm_cmd.header.in.length -= cpu_to_be32(sizeof(__be32));
- } else {
- if (subcap_id == TPM_CAP_FLAG_PERM ||
- subcap_id == TPM_CAP_FLAG_VOL)
- tpm_cmd.params.getcap_in.cap = TPM_CAP_FLAG;
- else
- tpm_cmd.params.getcap_in.cap = TPM_CAP_PROP;
- tpm_cmd.params.getcap_in.subcap_size = cpu_to_be32(4);
- tpm_cmd.params.getcap_in.subcap = subcap_id;
- }
- rc = transmit_cmd(chip, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE, desc);
- if (!rc)
- *cap = tpm_cmd.params.getcap_out.cap;
- return rc;
-}
-
-void tpm_gen_interrupt(struct tpm_chip *chip)
-{
- struct tpm_cmd_t tpm_cmd;
- ssize_t rc;
-
- tpm_cmd.header.in = tpm_getcap_header;
- tpm_cmd.params.getcap_in.cap = TPM_CAP_PROP;
- tpm_cmd.params.getcap_in.subcap_size = cpu_to_be32(4);
- tpm_cmd.params.getcap_in.subcap = TPM_CAP_PROP_TIS_TIMEOUT;
-
- rc = transmit_cmd(chip, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE,
- "attempting to determine the timeouts");
-}
-EXPORT_SYMBOL_GPL(tpm_gen_interrupt);
-
-#define TPM_ORD_STARTUP cpu_to_be32(153)
-#define TPM_ST_CLEAR cpu_to_be16(1)
-#define TPM_ST_STATE cpu_to_be16(2)
-#define TPM_ST_DEACTIVATED cpu_to_be16(3)
-static const struct tpm_input_header tpm_startup_header = {
- .tag = TPM_TAG_RQU_COMMAND,
- .length = cpu_to_be32(12),
- .ordinal = TPM_ORD_STARTUP
-};
-
-static int tpm_startup(struct tpm_chip *chip, __be16 startup_type)
-{
- struct tpm_cmd_t start_cmd;
- start_cmd.header.in = tpm_startup_header;
- start_cmd.params.startup_in.startup_type = startup_type;
- return transmit_cmd(chip, &start_cmd, TPM_INTERNAL_RESULT_SIZE,
- "attempting to start the TPM");
-}
-
-int tpm_get_timeouts(struct tpm_chip *chip)
-{
- struct tpm_cmd_t tpm_cmd;
- struct timeout_t *timeout_cap;
- struct duration_t *duration_cap;
- ssize_t rc;
- u32 timeout;
- unsigned int scale = 1;
-
- tpm_cmd.header.in = tpm_getcap_header;
- tpm_cmd.params.getcap_in.cap = TPM_CAP_PROP;
- tpm_cmd.params.getcap_in.subcap_size = cpu_to_be32(4);
- tpm_cmd.params.getcap_in.subcap = TPM_CAP_PROP_TIS_TIMEOUT;
- rc = transmit_cmd(chip, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE, NULL);
-
- if (rc == TPM_ERR_INVALID_POSTINIT) {
- /* The TPM is not started, we are the first to talk to it.
- Execute a startup command. */
- dev_info(chip->dev, "Issuing TPM_STARTUP");
- if (tpm_startup(chip, TPM_ST_CLEAR))
- return rc;
-
- tpm_cmd.header.in = tpm_getcap_header;
- tpm_cmd.params.getcap_in.cap = TPM_CAP_PROP;
- tpm_cmd.params.getcap_in.subcap_size = cpu_to_be32(4);
- tpm_cmd.params.getcap_in.subcap = TPM_CAP_PROP_TIS_TIMEOUT;
- rc = transmit_cmd(chip, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE,
- NULL);
- }
- if (rc) {
- dev_err(chip->dev,
- "A TPM error (%zd) occurred attempting to determine the timeouts\n",
- rc);
- goto duration;
- }
-
- if (be32_to_cpu(tpm_cmd.header.out.return_code) != 0 ||
- be32_to_cpu(tpm_cmd.header.out.length)
- != sizeof(tpm_cmd.header.out) + sizeof(u32) + 4 * sizeof(u32))
- return -EINVAL;
-
- timeout_cap = &tpm_cmd.params.getcap_out.cap.timeout;
- /* Don't overwrite default if value is 0 */
- timeout = be32_to_cpu(timeout_cap->a);
- if (timeout && timeout < 1000) {
- /* timeouts in msec rather usec */
- scale = 1000;
- chip->vendor.timeout_adjusted = true;
- }
- if (timeout)
- chip->vendor.timeout_a = usecs_to_jiffies(timeout * scale);
- timeout = be32_to_cpu(timeout_cap->b);
- if (timeout)
- chip->vendor.timeout_b = usecs_to_jiffies(timeout * scale);
- timeout = be32_to_cpu(timeout_cap->c);
- if (timeout)
- chip->vendor.timeout_c = usecs_to_jiffies(timeout * scale);
- timeout = be32_to_cpu(timeout_cap->d);
- if (timeout)
- chip->vendor.timeout_d = usecs_to_jiffies(timeout * scale);
-
-duration:
- tpm_cmd.header.in = tpm_getcap_header;
- tpm_cmd.params.getcap_in.cap = TPM_CAP_PROP;
- tpm_cmd.params.getcap_in.subcap_size = cpu_to_be32(4);
- tpm_cmd.params.getcap_in.subcap = TPM_CAP_PROP_TIS_DURATION;
-
- rc = transmit_cmd(chip, &tpm_cmd, TPM_INTERNAL_RESULT_SIZE,
- "attempting to determine the durations");
- if (rc)
- return rc;
-
- if (be32_to_cpu(tpm_cmd.header.out.return_code) != 0 ||
- be32_to_cpu(tpm_cmd.header.out.length)
- != sizeof(tpm_cmd.header.out) + sizeof(u32) + 3 * sizeof(u32))
- return -EINVAL;
-
- duration_cap = &tpm_cmd.params.getcap_out.cap.duration;
- chip->vendor.duration[TPM_SHORT] =
- usecs_to_jiffies(be32_to_cpu(duration_cap->tpm_short));
- chip->vendor.duration[TPM_MEDIUM] =
- usecs_to_jiffies(be32_to_cpu(duration_cap->tpm_medium));
- chip->vendor.duration[TPM_LONG] =
- usecs_to_jiffies(be32_to_cpu(duration_cap->tpm_long));
-
- /* The Broadcom BCM0102 chipset in a Dell Latitude D820 gets the above
- * value wrong and apparently reports msecs rather than usecs. So we
- * fix up the resulting too-small TPM_SHORT value to make things work.
- * We also scale the TPM_MEDIUM and -_LONG values by 1000.
- */
- if (chip->vendor.duration[TPM_SHORT] < (HZ / 100)) {
- chip->vendor.duration[TPM_SHORT] = HZ;
- chip->vendor.duration[TPM_MEDIUM] *= 1000;
- chip->vendor.duration[TPM_LONG] *= 1000;
- chip->vendor.duration_adjusted = true;
- dev_info(chip->dev, "Adjusting TPM timeout parameters.");
- }
- return 0;
-}
-EXPORT_SYMBOL_GPL(tpm_get_timeouts);
-
-#define TPM_ORD_CONTINUE_SELFTEST 83
-#define CONTINUE_SELFTEST_RESULT_SIZE 10
-
-static struct tpm_input_header continue_selftest_header = {
- .tag = TPM_TAG_RQU_COMMAND,
- .length = cpu_to_be32(10),
- .ordinal = cpu_to_be32(TPM_ORD_CONTINUE_SELFTEST),
-};
-
-/**
- * tpm_continue_selftest -- run TPM's selftest
- * @chip: TPM chip to use
- *
- * Returns 0 on success, < 0 in case of fatal error or a value > 0 representing
- * a TPM error code.
- */
-static int tpm_continue_selftest(struct tpm_chip *chip)
-{
- int rc;
- struct tpm_cmd_t cmd;
-
- cmd.header.in = continue_selftest_header;
- rc = transmit_cmd(chip, &cmd, CONTINUE_SELFTEST_RESULT_SIZE,
- "continue selftest");
- return rc;
-}
-
-ssize_t tpm_show_enabled(struct device * dev, struct device_attribute * attr,
- char *buf)
-{
- cap_t cap;
- ssize_t rc;
-
- rc = tpm_getcap(dev, TPM_CAP_FLAG_PERM, &cap,
- "attempting to determine the permanent enabled state");
- if (rc)
- return 0;
-
- rc = sprintf(buf, "%d\n", !cap.perm_flags.disable);
- return rc;
-}
-EXPORT_SYMBOL_GPL(tpm_show_enabled);
-
-ssize_t tpm_show_active(struct device * dev, struct device_attribute * attr,
- char *buf)
-{
- cap_t cap;
- ssize_t rc;
-
- rc = tpm_getcap(dev, TPM_CAP_FLAG_PERM, &cap,
- "attempting to determine the permanent active state");
- if (rc)
- return 0;
-
- rc = sprintf(buf, "%d\n", !cap.perm_flags.deactivated);
- return rc;
-}
-EXPORT_SYMBOL_GPL(tpm_show_active);
-
-ssize_t tpm_show_owned(struct device * dev, struct device_attribute * attr,
- char *buf)
-{
- cap_t cap;
- ssize_t rc;
-
- rc = tpm_getcap(dev, TPM_CAP_PROP_OWNER, &cap,
- "attempting to determine the owner state");
- if (rc)
- return 0;
-
- rc = sprintf(buf, "%d\n", cap.owned);
- return rc;
-}
-EXPORT_SYMBOL_GPL(tpm_show_owned);
-
-ssize_t tpm_show_temp_deactivated(struct device * dev,
- struct device_attribute * attr, char *buf)
-{
- cap_t cap;
- ssize_t rc;
-
- rc = tpm_getcap(dev, TPM_CAP_FLAG_VOL, &cap,
- "attempting to determine the temporary state");
- if (rc)
- return 0;
-
- rc = sprintf(buf, "%d\n", cap.stclear_flags.deactivated);
- return rc;
-}
-EXPORT_SYMBOL_GPL(tpm_show_temp_deactivated);
-
-/*
- * tpm_chip_find_get - return tpm_chip for given chip number
- */
-static struct tpm_chip *tpm_chip_find_get(int chip_num)
-{
- struct tpm_chip *pos, *chip = NULL;
-
- rcu_read_lock();
- list_for_each_entry_rcu(pos, &tpm_chip_list, list) {
- if (chip_num != TPM_ANY_NUM && chip_num != pos->dev_num)
- continue;
-
- if (try_module_get(pos->dev->driver->owner)) {
- chip = pos;
- break;
- }
- }
- rcu_read_unlock();
- return chip;
-}
-
-#define TPM_ORDINAL_PCRREAD cpu_to_be32(21)
-#define READ_PCR_RESULT_SIZE 30
-static struct tpm_input_header pcrread_header = {
- .tag = TPM_TAG_RQU_COMMAND,
- .length = cpu_to_be32(14),
- .ordinal = TPM_ORDINAL_PCRREAD
-};
-
-static int __tpm_pcr_read(struct tpm_chip *chip, int pcr_idx, u8 *res_buf)
-{
- int rc;
- struct tpm_cmd_t cmd;
-
- cmd.header.in = pcrread_header;
- cmd.params.pcrread_in.pcr_idx = cpu_to_be32(pcr_idx);
- rc = transmit_cmd(chip, &cmd, READ_PCR_RESULT_SIZE,
- "attempting to read a pcr value");
-
- if (rc == 0)
- memcpy(res_buf, cmd.params.pcrread_out.pcr_result,
- TPM_DIGEST_SIZE);
- return rc;
-}
-
-/**
- * tpm_pcr_read - read a pcr value
- * @chip_num: tpm idx # or ANY
- * @pcr_idx: pcr idx to retrieve
- * @res_buf: TPM_PCR value
- * size of res_buf is 20 bytes (or NULL if you don't care)
- *
- * The TPM driver should be built-in, but for whatever reason it
- * isn't, protect against the chip disappearing, by incrementing
- * the module usage count.
- */
-int tpm_pcr_read(u32 chip_num, int pcr_idx, u8 *res_buf)
-{
- struct tpm_chip *chip;
- int rc;
-
- chip = tpm_chip_find_get(chip_num);
- if (chip == NULL)
- return -ENODEV;
- rc = __tpm_pcr_read(chip, pcr_idx, res_buf);
- tpm_chip_put(chip);
- return rc;
-}
-EXPORT_SYMBOL_GPL(tpm_pcr_read);
-
-/**
- * tpm_pcr_extend - extend pcr value with hash
- * @chip_num: tpm idx # or AN&
- * @pcr_idx: pcr idx to extend
- * @hash: hash value used to extend pcr value
- *
- * The TPM driver should be built-in, but for whatever reason it
- * isn't, protect against the chip disappearing, by incrementing
- * the module usage count.
- */
-#define TPM_ORD_PCR_EXTEND cpu_to_be32(20)
-#define EXTEND_PCR_RESULT_SIZE 34
-static struct tpm_input_header pcrextend_header = {
- .tag = TPM_TAG_RQU_COMMAND,
- .length = cpu_to_be32(34),
- .ordinal = TPM_ORD_PCR_EXTEND
-};
-
-int tpm_pcr_extend(u32 chip_num, int pcr_idx, const u8 *hash)
-{
- struct tpm_cmd_t cmd;
- int rc;
- struct tpm_chip *chip;
-
- chip = tpm_chip_find_get(chip_num);
- if (chip == NULL)
- return -ENODEV;
-
- cmd.header.in = pcrextend_header;
- cmd.params.pcrextend_in.pcr_idx = cpu_to_be32(pcr_idx);
- memcpy(cmd.params.pcrextend_in.hash, hash, TPM_DIGEST_SIZE);
- rc = transmit_cmd(chip, &cmd, EXTEND_PCR_RESULT_SIZE,
- "attempting extend a PCR value");
-
- tpm_chip_put(chip);
- return rc;
-}
-EXPORT_SYMBOL_GPL(tpm_pcr_extend);
-
-/**
- * tpm_do_selftest - have the TPM continue its selftest and wait until it
- * can receive further commands
- * @chip: TPM chip to use
- *
- * Returns 0 on success, < 0 in case of fatal error or a value > 0 representing
- * a TPM error code.
- */
-int tpm_do_selftest(struct tpm_chip *chip)
-{
- int rc;
- unsigned int loops;
- unsigned int delay_msec = 100;
- unsigned long duration;
- struct tpm_cmd_t cmd;
-
- duration = tpm_calc_ordinal_duration(chip,
- TPM_ORD_CONTINUE_SELFTEST);
-
- loops = jiffies_to_msecs(duration) / delay_msec;
-
- rc = tpm_continue_selftest(chip);
- /* This may fail if there was no TPM driver during a suspend/resume
- * cycle; some may return 10 (BAD_ORDINAL), others 28 (FAILEDSELFTEST)
- */
- if (rc)
- return rc;
-
- do {
- /* Attempt to read a PCR value */
- cmd.header.in = pcrread_header;
- cmd.params.pcrread_in.pcr_idx = cpu_to_be32(0);
- rc = tpm_transmit(chip, (u8 *) &cmd, READ_PCR_RESULT_SIZE);
- /* Some buggy TPMs will not respond to tpm_tis_ready() for
- * around 300ms while the self test is ongoing, keep trying
- * until the self test duration expires. */
- if (rc == -ETIME) {
- dev_info(chip->dev, HW_ERR "TPM command timed out during continue self test");
- msleep(delay_msec);
- continue;
- }
-
- if (rc < TPM_HEADER_SIZE)
- return -EFAULT;
-
- rc = be32_to_cpu(cmd.header.out.return_code);
- if (rc == TPM_ERR_DISABLED || rc == TPM_ERR_DEACTIVATED) {
- dev_info(chip->dev,
- "TPM is disabled/deactivated (0x%X)\n", rc);
- /* TPM is disabled and/or deactivated; driver can
- * proceed and TPM does handle commands for
- * suspend/resume correctly
- */
- return 0;
- }
- if (rc != TPM_WARN_DOING_SELFTEST)
- return rc;
- msleep(delay_msec);
- } while (--loops > 0);
-
- return rc;
-}
-EXPORT_SYMBOL_GPL(tpm_do_selftest);
-
-int tpm_send(u32 chip_num, void *cmd, size_t buflen)
-{
- struct tpm_chip *chip;
- int rc;
-
- chip = tpm_chip_find_get(chip_num);
- if (chip == NULL)
- return -ENODEV;
-
- rc = transmit_cmd(chip, cmd, buflen, "attempting tpm_cmd");
-
- tpm_chip_put(chip);
- return rc;
-}
-EXPORT_SYMBOL_GPL(tpm_send);
-
-ssize_t tpm_show_pcrs(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- cap_t cap;
- u8 digest[TPM_DIGEST_SIZE];
- ssize_t rc;
- int i, j, num_pcrs;
- char *str = buf;
- struct tpm_chip *chip = dev_get_drvdata(dev);
-
- rc = tpm_getcap(dev, TPM_CAP_PROP_PCR, &cap,
- "attempting to determine the number of PCRS");
- if (rc)
- return 0;
-
- num_pcrs = be32_to_cpu(cap.num_pcrs);
- for (i = 0; i < num_pcrs; i++) {
- rc = __tpm_pcr_read(chip, i, digest);
- if (rc)
- break;
- str += sprintf(str, "PCR-%02d: ", i);
- for (j = 0; j < TPM_DIGEST_SIZE; j++)
- str += sprintf(str, "%02X ", digest[j]);
- str += sprintf(str, "\n");
- }
- return str - buf;
-}
-EXPORT_SYMBOL_GPL(tpm_show_pcrs);
-
-#define READ_PUBEK_RESULT_SIZE 314
-#define TPM_ORD_READPUBEK cpu_to_be32(124)
-static struct tpm_input_header tpm_readpubek_header = {
- .tag = TPM_TAG_RQU_COMMAND,
- .length = cpu_to_be32(30),
- .ordinal = TPM_ORD_READPUBEK
-};
-
-ssize_t tpm_show_pubek(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- u8 *data;
- struct tpm_cmd_t tpm_cmd;
- ssize_t err;
- int i, rc;
- char *str = buf;
-
- struct tpm_chip *chip = dev_get_drvdata(dev);
-
- tpm_cmd.header.in = tpm_readpubek_header;
- err = transmit_cmd(chip, &tpm_cmd, READ_PUBEK_RESULT_SIZE,
- "attempting to read the PUBEK");
- if (err)
- goto out;
-
- /*
- ignore header 10 bytes
- algorithm 32 bits (1 == RSA )
- encscheme 16 bits
- sigscheme 16 bits
- parameters (RSA 12->bytes: keybit, #primes, expbit)
- keylenbytes 32 bits
- 256 byte modulus
- ignore checksum 20 bytes
- */
- data = tpm_cmd.params.readpubek_out_buffer;
- str +=
- sprintf(str,
- "Algorithm: %02X %02X %02X %02X\n"
- "Encscheme: %02X %02X\n"
- "Sigscheme: %02X %02X\n"
- "Parameters: %02X %02X %02X %02X "
- "%02X %02X %02X %02X "
- "%02X %02X %02X %02X\n"
- "Modulus length: %d\n"
- "Modulus:\n",
- data[0], data[1], data[2], data[3],
- data[4], data[5],
- data[6], data[7],
- data[12], data[13], data[14], data[15],
- data[16], data[17], data[18], data[19],
- data[20], data[21], data[22], data[23],
- be32_to_cpu(*((__be32 *) (data + 24))));
-
- for (i = 0; i < 256; i++) {
- str += sprintf(str, "%02X ", data[i + 28]);
- if ((i + 1) % 16 == 0)
- str += sprintf(str, "\n");
- }
-out:
- rc = str - buf;
- return rc;
-}
-EXPORT_SYMBOL_GPL(tpm_show_pubek);
-
-
-ssize_t tpm_show_caps(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- cap_t cap;
- ssize_t rc;
- char *str = buf;
-
- rc = tpm_getcap(dev, TPM_CAP_PROP_MANUFACTURER, &cap,
- "attempting to determine the manufacturer");
- if (rc)
- return 0;
- str += sprintf(str, "Manufacturer: 0x%x\n",
- be32_to_cpu(cap.manufacturer_id));
-
- rc = tpm_getcap(dev, CAP_VERSION_1_1, &cap,
- "attempting to determine the 1.1 version");
- if (rc)
- return 0;
- str += sprintf(str,
- "TCG version: %d.%d\nFirmware version: %d.%d\n",
- cap.tpm_version.Major, cap.tpm_version.Minor,
- cap.tpm_version.revMajor, cap.tpm_version.revMinor);
- return str - buf;
-}
-EXPORT_SYMBOL_GPL(tpm_show_caps);
-
-ssize_t tpm_show_caps_1_2(struct device * dev,
- struct device_attribute * attr, char *buf)
-{
- cap_t cap;
- ssize_t rc;
- char *str = buf;
-
- rc = tpm_getcap(dev, TPM_CAP_PROP_MANUFACTURER, &cap,
- "attempting to determine the manufacturer");
- if (rc)
- return 0;
- str += sprintf(str, "Manufacturer: 0x%x\n",
- be32_to_cpu(cap.manufacturer_id));
- rc = tpm_getcap(dev, CAP_VERSION_1_2, &cap,
- "attempting to determine the 1.2 version");
- if (rc)
- return 0;
- str += sprintf(str,
- "TCG version: %d.%d\nFirmware version: %d.%d\n",
- cap.tpm_version_1_2.Major, cap.tpm_version_1_2.Minor,
- cap.tpm_version_1_2.revMajor,
- cap.tpm_version_1_2.revMinor);
- return str - buf;
-}
-EXPORT_SYMBOL_GPL(tpm_show_caps_1_2);
-
-ssize_t tpm_show_durations(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- struct tpm_chip *chip = dev_get_drvdata(dev);
-
- if (chip->vendor.duration[TPM_LONG] == 0)
- return 0;
-
- return sprintf(buf, "%d %d %d [%s]\n",
- jiffies_to_usecs(chip->vendor.duration[TPM_SHORT]),
- jiffies_to_usecs(chip->vendor.duration[TPM_MEDIUM]),
- jiffies_to_usecs(chip->vendor.duration[TPM_LONG]),
- chip->vendor.duration_adjusted
- ? "adjusted" : "original");
-}
-EXPORT_SYMBOL_GPL(tpm_show_durations);
-
-ssize_t tpm_show_timeouts(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- struct tpm_chip *chip = dev_get_drvdata(dev);
-
- return sprintf(buf, "%d %d %d %d [%s]\n",
- jiffies_to_usecs(chip->vendor.timeout_a),
- jiffies_to_usecs(chip->vendor.timeout_b),
- jiffies_to_usecs(chip->vendor.timeout_c),
- jiffies_to_usecs(chip->vendor.timeout_d),
- chip->vendor.timeout_adjusted
- ? "adjusted" : "original");
-}
-EXPORT_SYMBOL_GPL(tpm_show_timeouts);
-
-ssize_t tpm_store_cancel(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct tpm_chip *chip = dev_get_drvdata(dev);
- if (chip == NULL)
- return 0;
-
- chip->vendor.cancel(chip);
- return count;
-}
-EXPORT_SYMBOL_GPL(tpm_store_cancel);
-
-static bool wait_for_tpm_stat_cond(struct tpm_chip *chip, u8 mask, bool check_cancel,
- bool *canceled)
-{
- u8 status = chip->vendor.status(chip);
-
- *canceled = false;
- if ((status & mask) == mask)
- return true;
- if (check_cancel && chip->vendor.req_canceled(chip, status)) {
- *canceled = true;
- return true;
- }
- return false;
-}
-
-int wait_for_tpm_stat(struct tpm_chip *chip, u8 mask, unsigned long timeout,
- wait_queue_head_t *queue, bool check_cancel)
-{
- unsigned long stop;
- long rc;
- u8 status;
- bool canceled = false;
-
- /* check current status */
- status = chip->vendor.status(chip);
- if ((status & mask) == mask)
- return 0;
-
- stop = jiffies + timeout;
-
- if (chip->vendor.irq) {
-again:
- timeout = stop - jiffies;
- if ((long)timeout <= 0)
- return -ETIME;
- rc = wait_event_interruptible_timeout(*queue,
- wait_for_tpm_stat_cond(chip, mask, check_cancel,
- &canceled),
- timeout);
- if (rc > 0) {
- if (canceled)
- return -ECANCELED;
- return 0;
- }
- if (rc == -ERESTARTSYS && freezing(current)) {
- clear_thread_flag(TIF_SIGPENDING);
- goto again;
- }
- } else {
- do {
- msleep(TPM_TIMEOUT);
- status = chip->vendor.status(chip);
- if ((status & mask) == mask)
- return 0;
- } while (time_before(jiffies, stop));
- }
- return -ETIME;
-}
-EXPORT_SYMBOL_GPL(wait_for_tpm_stat);
-/*
- * Device file system interface to the TPM
- *
- * It's assured that the chip will be opened just once,
- * by the check of is_open variable, which is protected
- * by driver_lock.
- */
-int tpm_open(struct inode *inode, struct file *file)
-{
- int minor = iminor(inode);
- struct tpm_chip *chip = NULL, *pos;
-
- rcu_read_lock();
- list_for_each_entry_rcu(pos, &tpm_chip_list, list) {
- if (pos->vendor.miscdev.minor == minor) {
- chip = pos;
- get_device(chip->dev);
- break;
- }
- }
- rcu_read_unlock();
-
- if (!chip)
- return -ENODEV;
-
- if (test_and_set_bit(0, &chip->is_open)) {
- dev_dbg(chip->dev, "Another process owns this TPM\n");
- put_device(chip->dev);
- return -EBUSY;
- }
-
- chip->data_buffer = kzalloc(TPM_BUFSIZE, GFP_KERNEL);
- if (chip->data_buffer == NULL) {
- clear_bit(0, &chip->is_open);
- put_device(chip->dev);
- return -ENOMEM;
- }
-
- atomic_set(&chip->data_pending, 0);
-
- file->private_data = chip;
- return 0;
-}
-EXPORT_SYMBOL_GPL(tpm_open);
-
-/*
- * Called on file close
- */
-int tpm_release(struct inode *inode, struct file *file)
-{
- struct tpm_chip *chip = file->private_data;
-
- del_singleshot_timer_sync(&chip->user_read_timer);
- flush_work(&chip->work);
- file->private_data = NULL;
- atomic_set(&chip->data_pending, 0);
- kzfree(chip->data_buffer);
- clear_bit(0, &chip->is_open);
- put_device(chip->dev);
- return 0;
-}
-EXPORT_SYMBOL_GPL(tpm_release);
-
-ssize_t tpm_write(struct file *file, const char __user *buf,
- size_t size, loff_t *off)
-{
- struct tpm_chip *chip = file->private_data;
- size_t in_size = size;
- ssize_t out_size;
-
- /* cannot perform a write until the read has cleared
- either via tpm_read or a user_read_timer timeout.
- This also prevents splitted buffered writes from blocking here.
- */
- if (atomic_read(&chip->data_pending) != 0)
- return -EBUSY;
-
- if (in_size > TPM_BUFSIZE)
- return -E2BIG;
-
- mutex_lock(&chip->buffer_mutex);
-
- if (copy_from_user
- (chip->data_buffer, (void __user *) buf, in_size)) {
- mutex_unlock(&chip->buffer_mutex);
- return -EFAULT;
- }
-
- /* atomic tpm command send and result receive */
- out_size = tpm_transmit(chip, chip->data_buffer, TPM_BUFSIZE);
- if (out_size < 0) {
- mutex_unlock(&chip->buffer_mutex);
- return out_size;
- }
-
- atomic_set(&chip->data_pending, out_size);
- mutex_unlock(&chip->buffer_mutex);
-
- /* Set a timeout by which the reader must come claim the result */
- mod_timer(&chip->user_read_timer, jiffies + (60 * HZ));
-
- return in_size;
-}
-EXPORT_SYMBOL_GPL(tpm_write);
-
-ssize_t tpm_read(struct file *file, char __user *buf,
- size_t size, loff_t *off)
-{
- struct tpm_chip *chip = file->private_data;
- ssize_t ret_size;
- int rc;
-
- del_singleshot_timer_sync(&chip->user_read_timer);
- flush_work(&chip->work);
- ret_size = atomic_read(&chip->data_pending);
- if (ret_size > 0) { /* relay data */
- ssize_t orig_ret_size = ret_size;
- if (size < ret_size)
- ret_size = size;
-
- mutex_lock(&chip->buffer_mutex);
- rc = copy_to_user(buf, chip->data_buffer, ret_size);
- memset(chip->data_buffer, 0, orig_ret_size);
- if (rc)
- ret_size = -EFAULT;
-
- mutex_unlock(&chip->buffer_mutex);
- }
-
- atomic_set(&chip->data_pending, 0);
-
- return ret_size;
-}
-EXPORT_SYMBOL_GPL(tpm_read);
-
-void tpm_remove_hardware(struct device *dev)
-{
- struct tpm_chip *chip = dev_get_drvdata(dev);
-
- if (chip == NULL) {
- dev_err(dev, "No device data found\n");
- return;
- }
-
- spin_lock(&driver_lock);
- list_del_rcu(&chip->list);
- spin_unlock(&driver_lock);
- synchronize_rcu();
-
- misc_deregister(&chip->vendor.miscdev);
- sysfs_remove_group(&dev->kobj, chip->vendor.attr_group);
- tpm_remove_ppi(&dev->kobj);
- tpm_bios_log_teardown(chip->bios_dir);
-
- /* write it this way to be explicit (chip->dev == dev) */
- put_device(chip->dev);
-}
-EXPORT_SYMBOL_GPL(tpm_remove_hardware);
-
-#define TPM_ORD_SAVESTATE cpu_to_be32(152)
-#define SAVESTATE_RESULT_SIZE 10
-
-static struct tpm_input_header savestate_header = {
- .tag = TPM_TAG_RQU_COMMAND,
- .length = cpu_to_be32(10),
- .ordinal = TPM_ORD_SAVESTATE
-};
-
-/*
- * We are about to suspend. Save the TPM state
- * so that it can be restored.
- */
-int tpm_pm_suspend(struct device *dev)
-{
- struct tpm_chip *chip = dev_get_drvdata(dev);
- struct tpm_cmd_t cmd;
- int rc, try;
-
- u8 dummy_hash[TPM_DIGEST_SIZE] = { 0 };
-
- if (chip == NULL)
- return -ENODEV;
-
- /* for buggy tpm, flush pcrs with extend to selected dummy */
- if (tpm_suspend_pcr) {
- cmd.header.in = pcrextend_header;
- cmd.params.pcrextend_in.pcr_idx = cpu_to_be32(tpm_suspend_pcr);
- memcpy(cmd.params.pcrextend_in.hash, dummy_hash,
- TPM_DIGEST_SIZE);
- rc = transmit_cmd(chip, &cmd, EXTEND_PCR_RESULT_SIZE,
- "extending dummy pcr before suspend");
- }
-
- /* now do the actual savestate */
- for (try = 0; try < TPM_RETRY; try++) {
- cmd.header.in = savestate_header;
- rc = transmit_cmd(chip, &cmd, SAVESTATE_RESULT_SIZE, NULL);
-
- /*
- * If the TPM indicates that it is too busy to respond to
- * this command then retry before giving up. It can take
- * several seconds for this TPM to be ready.
- *
- * This can happen if the TPM has already been sent the
- * SaveState command before the driver has loaded. TCG 1.2
- * specification states that any communication after SaveState
- * may cause the TPM to invalidate previously saved state.
- */
- if (rc != TPM_WARN_RETRY)
- break;
- msleep(TPM_TIMEOUT_RETRY);
- }
-
- if (rc)
- dev_err(chip->dev,
- "Error (%d) sending savestate before suspend\n", rc);
- else if (try > 0)
- dev_warn(chip->dev, "TPM savestate took %dms\n",
- try * TPM_TIMEOUT_RETRY);
-
- return rc;
-}
-EXPORT_SYMBOL_GPL(tpm_pm_suspend);
-
-/*
- * Resume from a power safe. The BIOS already restored
- * the TPM state.
- */
-int tpm_pm_resume(struct device *dev)
-{
- struct tpm_chip *chip = dev_get_drvdata(dev);
-
- if (chip == NULL)
- return -ENODEV;
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(tpm_pm_resume);
-
-#define TPM_GETRANDOM_RESULT_SIZE 18
-static struct tpm_input_header tpm_getrandom_header = {
- .tag = TPM_TAG_RQU_COMMAND,
- .length = cpu_to_be32(14),
- .ordinal = TPM_ORD_GET_RANDOM
-};
-
-/**
- * tpm_get_random() - Get random bytes from the tpm's RNG
- * @chip_num: A specific chip number for the request or TPM_ANY_NUM
- * @out: destination buffer for the random bytes
- * @max: the max number of bytes to write to @out
- *
- * Returns < 0 on error and the number of bytes read on success
- */
-int tpm_get_random(u32 chip_num, u8 *out, size_t max)
-{
- struct tpm_chip *chip;
- struct tpm_cmd_t tpm_cmd;
- u32 recd, num_bytes = min_t(u32, max, TPM_MAX_RNG_DATA);
- int err, total = 0, retries = 5;
- u8 *dest = out;
-
- chip = tpm_chip_find_get(chip_num);
- if (chip == NULL)
- return -ENODEV;
-
- if (!out || !num_bytes || max > TPM_MAX_RNG_DATA)
- return -EINVAL;
-
- do {
- tpm_cmd.header.in = tpm_getrandom_header;
- tpm_cmd.params.getrandom_in.num_bytes = cpu_to_be32(num_bytes);
-
- err = transmit_cmd(chip, &tpm_cmd,
- TPM_GETRANDOM_RESULT_SIZE + num_bytes,
- "attempting get random");
- if (err)
- break;
-
- recd = be32_to_cpu(tpm_cmd.params.getrandom_out.rng_data_len);
- memcpy(dest, tpm_cmd.params.getrandom_out.rng_data, recd);
-
- dest += recd;
- total += recd;
- num_bytes -= recd;
- } while (retries-- && total < max);
-
- return total ? total : -EIO;
-}
-EXPORT_SYMBOL_GPL(tpm_get_random);
-
-/* In case vendor provided release function, call it too.*/
-
-void tpm_dev_vendor_release(struct tpm_chip *chip)
-{
- if (!chip)
- return;
-
- if (chip->vendor.release)
- chip->vendor.release(chip->dev);
-
- clear_bit(chip->dev_num, dev_mask);
- kfree(chip->vendor.miscdev.name);
-}
-EXPORT_SYMBOL_GPL(tpm_dev_vendor_release);
-
-
-/*
- * Once all references to platform device are down to 0,
- * release all allocated structures.
- */
-void tpm_dev_release(struct device *dev)
-{
- struct tpm_chip *chip = dev_get_drvdata(dev);
-
- if (!chip)
- return;
-
- tpm_dev_vendor_release(chip);
-
- chip->release(dev);
- kfree(chip);
-}
-EXPORT_SYMBOL_GPL(tpm_dev_release);
-
-/*
- * Called from tpm_<specific>.c probe function only for devices
- * the driver has determined it should claim. Prior to calling
- * this function the specific probe function has called pci_enable_device
- * upon errant exit from this function specific probe function should call
- * pci_disable_device
- */
-struct tpm_chip *tpm_register_hardware(struct device *dev,
- const struct tpm_vendor_specific *entry)
-{
-#define DEVNAME_SIZE 7
-
- char *devname;
- struct tpm_chip *chip;
-
- /* Driver specific per-device data */
- chip = kzalloc(sizeof(*chip), GFP_KERNEL);
- devname = kmalloc(DEVNAME_SIZE, GFP_KERNEL);
-
- if (chip == NULL || devname == NULL)
- goto out_free;
-
- mutex_init(&chip->buffer_mutex);
- mutex_init(&chip->tpm_mutex);
- INIT_LIST_HEAD(&chip->list);
-
- INIT_WORK(&chip->work, timeout_work);
-
- setup_timer(&chip->user_read_timer, user_reader_timeout,
- (unsigned long)chip);
-
- memcpy(&chip->vendor, entry, sizeof(struct tpm_vendor_specific));
-
- chip->dev_num = find_first_zero_bit(dev_mask, TPM_NUM_DEVICES);
-
- if (chip->dev_num >= TPM_NUM_DEVICES) {
- dev_err(dev, "No available tpm device numbers\n");
- goto out_free;
- } else if (chip->dev_num == 0)
- chip->vendor.miscdev.minor = TPM_MINOR;
- else
- chip->vendor.miscdev.minor = MISC_DYNAMIC_MINOR;
-
- set_bit(chip->dev_num, dev_mask);
-
- scnprintf(devname, DEVNAME_SIZE, "%s%d", "tpm", chip->dev_num);
- chip->vendor.miscdev.name = devname;
-
- chip->vendor.miscdev.parent = dev;
- chip->dev = get_device(dev);
- chip->release = dev->release;
- dev->release = tpm_dev_release;
- dev_set_drvdata(dev, chip);
-
- if (misc_register(&chip->vendor.miscdev)) {
- dev_err(chip->dev,
- "unable to misc_register %s, minor %d\n",
- chip->vendor.miscdev.name,
- chip->vendor.miscdev.minor);
- goto put_device;
- }
-
- if (sysfs_create_group(&dev->kobj, chip->vendor.attr_group)) {
- misc_deregister(&chip->vendor.miscdev);
- goto put_device;
- }
-
- if (tpm_add_ppi(&dev->kobj)) {
- misc_deregister(&chip->vendor.miscdev);
- goto put_device;
- }
-
- chip->bios_dir = tpm_bios_log_setup(devname);
-
- /* Make chip available */
- spin_lock(&driver_lock);
- list_add_rcu(&chip->list, &tpm_chip_list);
- spin_unlock(&driver_lock);
-
- return chip;
-
-put_device:
- put_device(chip->dev);
-out_free:
- kfree(chip);
- kfree(devname);
- return NULL;
-}
-EXPORT_SYMBOL_GPL(tpm_register_hardware);
-
-MODULE_AUTHOR("Leendert van Doorn (leendert@watson.ibm.com)");
-MODULE_DESCRIPTION("TPM Driver");
-MODULE_VERSION("2.0");
-MODULE_LICENSE("GPL");
char *);
extern ssize_t tpm_show_caps(struct device *, struct device_attribute *attr,
char *);
-extern ssize_t tpm_show_caps_1_2(struct device *, struct device_attribute *attr,
- char *);
extern ssize_t tpm_store_cancel(struct device *, struct device_attribute *attr,
const char *, size_t);
extern ssize_t tpm_show_enabled(struct device *, struct device_attribute *attr,
struct device *dev; /* Device stuff */
int dev_num; /* /dev/tpm# */
+ char devname[7];
unsigned long is_open; /* only one allowed */
int time_expired;
have_region =
(atmel_request_region
- (tpm_atmel.base, region_size, "tpm_atmel0") == NULL) ? 0 : 1;
+ (base, region_size, "tpm_atmel0") == NULL) ? 0 : 1;
pdev = platform_device_register_simple("tpm_atmel", -1, NULL, 0);
if (IS_ERR(pdev)) {
out:
return NULL;
}
-EXPORT_SYMBOL_GPL(tpm_bios_log_setup);
void tpm_bios_log_teardown(struct dentry **lst)
{
for (i = 0; i < 3; i++)
securityfs_remove(lst[i]);
}
-EXPORT_SYMBOL_GPL(tpm_bios_log_teardown);
-MODULE_LICENSE("GPL");
--- /dev/null
+/*
+ * ATMEL I2C TPM AT97SC3204T
+ *
+ * Copyright (C) 2012 V Lab Technologies
+ * Teddy Reed <teddy@prosauce.org>
+ * Copyright (C) 2013, Obsidian Research Corp.
+ * Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
+ * Device driver for ATMEL I2C TPMs.
+ *
+ * Teddy Reed determined the basic I2C command flow, unlike other I2C TPM
+ * devices the raw TCG formatted TPM command data is written via I2C and then
+ * raw TCG formatted TPM command data is returned via I2C.
+ *
+ * TGC status/locality/etc functions seen in the LPC implementation do not
+ * seem to be present.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see http://www.gnu.org/licenses/>.
+ */
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/slab.h>
+#include <linux/i2c.h>
+#include "tpm.h"
+
+#define I2C_DRIVER_NAME "tpm_i2c_atmel"
+
+#define TPM_I2C_SHORT_TIMEOUT 750 /* ms */
+#define TPM_I2C_LONG_TIMEOUT 2000 /* 2 sec */
+
+#define ATMEL_STS_OK 1
+
+struct priv_data {
+ size_t len;
+ /* This is the amount we read on the first try. 25 was chosen to fit a
+ * fair number of read responses in the buffer so a 2nd retry can be
+ * avoided in small message cases. */
+ u8 buffer[sizeof(struct tpm_output_header) + 25];
+};
+
+static int i2c_atmel_send(struct tpm_chip *chip, u8 *buf, size_t len)
+{
+ struct priv_data *priv = chip->vendor.priv;
+ struct i2c_client *client = to_i2c_client(chip->dev);
+ s32 status;
+
+ priv->len = 0;
+
+ if (len <= 2)
+ return -EIO;
+
+ status = i2c_master_send(client, buf, len);
+
+ dev_dbg(chip->dev,
+ "%s(buf=%*ph len=%0zx) -> sts=%d\n", __func__,
+ (int)min_t(size_t, 64, len), buf, len, status);
+ return status;
+}
+
+static int i2c_atmel_recv(struct tpm_chip *chip, u8 *buf, size_t count)
+{
+ struct priv_data *priv = chip->vendor.priv;
+ struct i2c_client *client = to_i2c_client(chip->dev);
+ struct tpm_output_header *hdr =
+ (struct tpm_output_header *)priv->buffer;
+ u32 expected_len;
+ int rc;
+
+ if (priv->len == 0)
+ return -EIO;
+
+ /* Get the message size from the message header, if we didn't get the
+ * whole message in read_status then we need to re-read the
+ * message. */
+ expected_len = be32_to_cpu(hdr->length);
+ if (expected_len > count)
+ return -ENOMEM;
+
+ if (priv->len >= expected_len) {
+ dev_dbg(chip->dev,
+ "%s early(buf=%*ph count=%0zx) -> ret=%d\n", __func__,
+ (int)min_t(size_t, 64, expected_len), buf, count,
+ expected_len);
+ memcpy(buf, priv->buffer, expected_len);
+ return expected_len;
+ }
+
+ rc = i2c_master_recv(client, buf, expected_len);
+ dev_dbg(chip->dev,
+ "%s reread(buf=%*ph count=%0zx) -> ret=%d\n", __func__,
+ (int)min_t(size_t, 64, expected_len), buf, count,
+ expected_len);
+ return rc;
+}
+
+static void i2c_atmel_cancel(struct tpm_chip *chip)
+{
+ dev_err(chip->dev, "TPM operation cancellation was requested, but is not supported");
+}
+
+static u8 i2c_atmel_read_status(struct tpm_chip *chip)
+{
+ struct priv_data *priv = chip->vendor.priv;
+ struct i2c_client *client = to_i2c_client(chip->dev);
+ int rc;
+
+ /* The TPM fails the I2C read until it is ready, so we do the entire
+ * transfer here and buffer it locally. This way the common code can
+ * properly handle the timeouts. */
+ priv->len = 0;
+ memset(priv->buffer, 0, sizeof(priv->buffer));
+
+
+ /* Once the TPM has completed the command the command remains readable
+ * until another command is issued. */
+ rc = i2c_master_recv(client, priv->buffer, sizeof(priv->buffer));
+ dev_dbg(chip->dev,
+ "%s: sts=%d", __func__, rc);
+ if (rc <= 0)
+ return 0;
+
+ priv->len = rc;
+
+ return ATMEL_STS_OK;
+}
+
+static const struct file_operations i2c_atmel_ops = {
+ .owner = THIS_MODULE,
+ .llseek = no_llseek,
+ .open = tpm_open,
+ .read = tpm_read,
+ .write = tpm_write,
+ .release = tpm_release,
+};
+
+static DEVICE_ATTR(pubek, S_IRUGO, tpm_show_pubek, NULL);
+static DEVICE_ATTR(pcrs, S_IRUGO, tpm_show_pcrs, NULL);
+static DEVICE_ATTR(enabled, S_IRUGO, tpm_show_enabled, NULL);
+static DEVICE_ATTR(active, S_IRUGO, tpm_show_active, NULL);
+static DEVICE_ATTR(owned, S_IRUGO, tpm_show_owned, NULL);
+static DEVICE_ATTR(temp_deactivated, S_IRUGO, tpm_show_temp_deactivated, NULL);
+static DEVICE_ATTR(caps, S_IRUGO, tpm_show_caps, NULL);
+static DEVICE_ATTR(cancel, S_IWUSR | S_IWGRP, NULL, tpm_store_cancel);
+static DEVICE_ATTR(durations, S_IRUGO, tpm_show_durations, NULL);
+static DEVICE_ATTR(timeouts, S_IRUGO, tpm_show_timeouts, NULL);
+
+static struct attribute *i2c_atmel_attrs[] = {
+ &dev_attr_pubek.attr,
+ &dev_attr_pcrs.attr,
+ &dev_attr_enabled.attr,
+ &dev_attr_active.attr,
+ &dev_attr_owned.attr,
+ &dev_attr_temp_deactivated.attr,
+ &dev_attr_caps.attr,
+ &dev_attr_cancel.attr,
+ &dev_attr_durations.attr,
+ &dev_attr_timeouts.attr,
+ NULL,
+};
+
+static struct attribute_group i2c_atmel_attr_grp = {
+ .attrs = i2c_atmel_attrs
+};
+
+static bool i2c_atmel_req_canceled(struct tpm_chip *chip, u8 status)
+{
+ return 0;
+}
+
+static const struct tpm_vendor_specific i2c_atmel = {
+ .status = i2c_atmel_read_status,
+ .recv = i2c_atmel_recv,
+ .send = i2c_atmel_send,
+ .cancel = i2c_atmel_cancel,
+ .req_complete_mask = ATMEL_STS_OK,
+ .req_complete_val = ATMEL_STS_OK,
+ .req_canceled = i2c_atmel_req_canceled,
+ .attr_group = &i2c_atmel_attr_grp,
+ .miscdev.fops = &i2c_atmel_ops,
+};
+
+static int i2c_atmel_probe(struct i2c_client *client,
+ const struct i2c_device_id *id)
+{
+ int rc;
+ struct tpm_chip *chip;
+ struct device *dev = &client->dev;
+
+ if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C))
+ return -ENODEV;
+
+ chip = tpm_register_hardware(dev, &i2c_atmel);
+ if (!chip) {
+ dev_err(dev, "%s() error in tpm_register_hardware\n", __func__);
+ return -ENODEV;
+ }
+
+ chip->vendor.priv = devm_kzalloc(dev, sizeof(struct priv_data),
+ GFP_KERNEL);
+
+ /* Default timeouts */
+ chip->vendor.timeout_a = msecs_to_jiffies(TPM_I2C_SHORT_TIMEOUT);
+ chip->vendor.timeout_b = msecs_to_jiffies(TPM_I2C_LONG_TIMEOUT);
+ chip->vendor.timeout_c = msecs_to_jiffies(TPM_I2C_SHORT_TIMEOUT);
+ chip->vendor.timeout_d = msecs_to_jiffies(TPM_I2C_SHORT_TIMEOUT);
+ chip->vendor.irq = 0;
+
+ /* There is no known way to probe for this device, and all version
+ * information seems to be read via TPM commands. Thus we rely on the
+ * TPM startup process in the common code to detect the device. */
+ if (tpm_get_timeouts(chip)) {
+ rc = -ENODEV;
+ goto out_err;
+ }
+
+ if (tpm_do_selftest(chip)) {
+ rc = -ENODEV;
+ goto out_err;
+ }
+
+ return 0;
+
+out_err:
+ tpm_dev_vendor_release(chip);
+ tpm_remove_hardware(chip->dev);
+ return rc;
+}
+
+static int i2c_atmel_remove(struct i2c_client *client)
+{
+ struct device *dev = &(client->dev);
+ struct tpm_chip *chip = dev_get_drvdata(dev);
+
+ if (chip)
+ tpm_dev_vendor_release(chip);
+ tpm_remove_hardware(dev);
+ kfree(chip);
+ return 0;
+}
+
+static const struct i2c_device_id i2c_atmel_id[] = {
+ {I2C_DRIVER_NAME, 0},
+ {}
+};
+MODULE_DEVICE_TABLE(i2c, i2c_atmel_id);
+
+#ifdef CONFIG_OF
+static const struct of_device_id i2c_atmel_of_match[] = {
+ {.compatible = "atmel,at97sc3204t"},
+ {},
+};
+MODULE_DEVICE_TABLE(of, i2c_atmel_of_match);
+#endif
+
+static SIMPLE_DEV_PM_OPS(i2c_atmel_pm_ops, tpm_pm_suspend, tpm_pm_resume);
+
+static struct i2c_driver i2c_atmel_driver = {
+ .id_table = i2c_atmel_id,
+ .probe = i2c_atmel_probe,
+ .remove = i2c_atmel_remove,
+ .driver = {
+ .name = I2C_DRIVER_NAME,
+ .owner = THIS_MODULE,
+ .pm = &i2c_atmel_pm_ops,
+ .of_match_table = of_match_ptr(i2c_atmel_of_match),
+ },
+};
+
+module_i2c_driver(i2c_atmel_driver);
+
+MODULE_AUTHOR("Jason Gunthorpe <jgunthorpe@obsidianresearch.com>");
+MODULE_DESCRIPTION("Atmel TPM I2C Driver");
+MODULE_LICENSE("GPL");
static DEVICE_ATTR(active, S_IRUGO, tpm_show_active, NULL);
static DEVICE_ATTR(owned, S_IRUGO, tpm_show_owned, NULL);
static DEVICE_ATTR(temp_deactivated, S_IRUGO, tpm_show_temp_deactivated, NULL);
-static DEVICE_ATTR(caps, S_IRUGO, tpm_show_caps_1_2, NULL);
+static DEVICE_ATTR(caps, S_IRUGO, tpm_show_caps, NULL);
static DEVICE_ATTR(cancel, S_IWUSR | S_IWGRP, NULL, tpm_store_cancel);
static DEVICE_ATTR(durations, S_IRUGO, tpm_show_durations, NULL);
static DEVICE_ATTR(timeouts, S_IRUGO, tpm_show_timeouts, NULL);
chip->dev->release = NULL;
chip->release = NULL;
tpm_dev.client = NULL;
- dev_set_drvdata(chip->dev, chip);
out_err:
return rc;
}
chip->dev->release = NULL;
chip->release = NULL;
tpm_dev.client = NULL;
- dev_set_drvdata(chip->dev, chip);
return 0;
}
--- /dev/null
+/******************************************************************************
+ * Nuvoton TPM I2C Device Driver Interface for WPCT301/NPCT501,
+ * based on the TCG TPM Interface Spec version 1.2.
+ * Specifications at www.trustedcomputinggroup.org
+ *
+ * Copyright (C) 2011, Nuvoton Technology Corporation.
+ * Dan Morav <dan.morav@nuvoton.com>
+ * Copyright (C) 2013, Obsidian Research Corp.
+ * Jason Gunthorpe <jgunthorpe@obsidianresearch.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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see http://www.gnu.org/licenses/>.
+ *
+ * Nuvoton contact information: APC.Support@nuvoton.com
+ *****************************************************************************/
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/wait.h>
+#include <linux/i2c.h>
+#include "tpm.h"
+
+/* I2C interface offsets */
+#define TPM_STS 0x00
+#define TPM_BURST_COUNT 0x01
+#define TPM_DATA_FIFO_W 0x20
+#define TPM_DATA_FIFO_R 0x40
+#define TPM_VID_DID_RID 0x60
+/* TPM command header size */
+#define TPM_HEADER_SIZE 10
+#define TPM_RETRY 5
+/*
+ * I2C bus device maximum buffer size w/o counting I2C address or command
+ * i.e. max size required for I2C write is 34 = addr, command, 32 bytes data
+ */
+#define TPM_I2C_MAX_BUF_SIZE 32
+#define TPM_I2C_RETRY_COUNT 32
+#define TPM_I2C_BUS_DELAY 1 /* msec */
+#define TPM_I2C_RETRY_DELAY_SHORT 2 /* msec */
+#define TPM_I2C_RETRY_DELAY_LONG 10 /* msec */
+
+#define I2C_DRIVER_NAME "tpm_i2c_nuvoton"
+
+struct priv_data {
+ unsigned int intrs;
+};
+
+static s32 i2c_nuvoton_read_buf(struct i2c_client *client, u8 offset, u8 size,
+ u8 *data)
+{
+ s32 status;
+
+ status = i2c_smbus_read_i2c_block_data(client, offset, size, data);
+ dev_dbg(&client->dev,
+ "%s(offset=%u size=%u data=%*ph) -> sts=%d\n", __func__,
+ offset, size, (int)size, data, status);
+ return status;
+}
+
+static s32 i2c_nuvoton_write_buf(struct i2c_client *client, u8 offset, u8 size,
+ u8 *data)
+{
+ s32 status;
+
+ status = i2c_smbus_write_i2c_block_data(client, offset, size, data);
+ dev_dbg(&client->dev,
+ "%s(offset=%u size=%u data=%*ph) -> sts=%d\n", __func__,
+ offset, size, (int)size, data, status);
+ return status;
+}
+
+#define TPM_STS_VALID 0x80
+#define TPM_STS_COMMAND_READY 0x40
+#define TPM_STS_GO 0x20
+#define TPM_STS_DATA_AVAIL 0x10
+#define TPM_STS_EXPECT 0x08
+#define TPM_STS_RESPONSE_RETRY 0x02
+#define TPM_STS_ERR_VAL 0x07 /* bit2...bit0 reads always 0 */
+
+#define TPM_I2C_SHORT_TIMEOUT 750 /* ms */
+#define TPM_I2C_LONG_TIMEOUT 2000 /* 2 sec */
+
+/* read TPM_STS register */
+static u8 i2c_nuvoton_read_status(struct tpm_chip *chip)
+{
+ struct i2c_client *client = to_i2c_client(chip->dev);
+ s32 status;
+ u8 data;
+
+ status = i2c_nuvoton_read_buf(client, TPM_STS, 1, &data);
+ if (status <= 0) {
+ dev_err(chip->dev, "%s() error return %d\n", __func__,
+ status);
+ data = TPM_STS_ERR_VAL;
+ }
+
+ return data;
+}
+
+/* write byte to TPM_STS register */
+static s32 i2c_nuvoton_write_status(struct i2c_client *client, u8 data)
+{
+ s32 status;
+ int i;
+
+ /* this causes the current command to be aborted */
+ for (i = 0, status = -1; i < TPM_I2C_RETRY_COUNT && status < 0; i++) {
+ status = i2c_nuvoton_write_buf(client, TPM_STS, 1, &data);
+ msleep(TPM_I2C_BUS_DELAY);
+ }
+ return status;
+}
+
+/* write commandReady to TPM_STS register */
+static void i2c_nuvoton_ready(struct tpm_chip *chip)
+{
+ struct i2c_client *client = to_i2c_client(chip->dev);
+ s32 status;
+
+ /* this causes the current command to be aborted */
+ status = i2c_nuvoton_write_status(client, TPM_STS_COMMAND_READY);
+ if (status < 0)
+ dev_err(chip->dev,
+ "%s() fail to write TPM_STS.commandReady\n", __func__);
+}
+
+/* read burstCount field from TPM_STS register
+ * return -1 on fail to read */
+static int i2c_nuvoton_get_burstcount(struct i2c_client *client,
+ struct tpm_chip *chip)
+{
+ unsigned long stop = jiffies + chip->vendor.timeout_d;
+ s32 status;
+ int burst_count = -1;
+ u8 data;
+
+ /* wait for burstcount to be non-zero */
+ do {
+ /* in I2C burstCount is 1 byte */
+ status = i2c_nuvoton_read_buf(client, TPM_BURST_COUNT, 1,
+ &data);
+ if (status > 0 && data > 0) {
+ burst_count = min_t(u8, TPM_I2C_MAX_BUF_SIZE, data);
+ break;
+ }
+ msleep(TPM_I2C_BUS_DELAY);
+ } while (time_before(jiffies, stop));
+
+ return burst_count;
+}
+
+/*
+ * WPCT301/NPCT501 SINT# supports only dataAvail
+ * any call to this function which is not waiting for dataAvail will
+ * set queue to NULL to avoid waiting for interrupt
+ */
+static bool i2c_nuvoton_check_status(struct tpm_chip *chip, u8 mask, u8 value)
+{
+ u8 status = i2c_nuvoton_read_status(chip);
+ return (status != TPM_STS_ERR_VAL) && ((status & mask) == value);
+}
+
+static int i2c_nuvoton_wait_for_stat(struct tpm_chip *chip, u8 mask, u8 value,
+ u32 timeout, wait_queue_head_t *queue)
+{
+ if (chip->vendor.irq && queue) {
+ s32 rc;
+ DEFINE_WAIT(wait);
+ struct priv_data *priv = chip->vendor.priv;
+ unsigned int cur_intrs = priv->intrs;
+
+ enable_irq(chip->vendor.irq);
+ rc = wait_event_interruptible_timeout(*queue,
+ cur_intrs != priv->intrs,
+ timeout);
+ if (rc > 0)
+ return 0;
+ /* At this point we know that the SINT pin is asserted, so we
+ * do not need to do i2c_nuvoton_check_status */
+ } else {
+ unsigned long ten_msec, stop;
+ bool status_valid;
+
+ /* check current status */
+ status_valid = i2c_nuvoton_check_status(chip, mask, value);
+ if (status_valid)
+ return 0;
+
+ /* use polling to wait for the event */
+ ten_msec = jiffies + msecs_to_jiffies(TPM_I2C_RETRY_DELAY_LONG);
+ stop = jiffies + timeout;
+ do {
+ if (time_before(jiffies, ten_msec))
+ msleep(TPM_I2C_RETRY_DELAY_SHORT);
+ else
+ msleep(TPM_I2C_RETRY_DELAY_LONG);
+ status_valid = i2c_nuvoton_check_status(chip, mask,
+ value);
+ if (status_valid)
+ return 0;
+ } while (time_before(jiffies, stop));
+ }
+ dev_err(chip->dev, "%s(%02x, %02x) -> timeout\n", __func__, mask,
+ value);
+ return -ETIMEDOUT;
+}
+
+/* wait for dataAvail field to be set in the TPM_STS register */
+static int i2c_nuvoton_wait_for_data_avail(struct tpm_chip *chip, u32 timeout,
+ wait_queue_head_t *queue)
+{
+ return i2c_nuvoton_wait_for_stat(chip,
+ TPM_STS_DATA_AVAIL | TPM_STS_VALID,
+ TPM_STS_DATA_AVAIL | TPM_STS_VALID,
+ timeout, queue);
+}
+
+/* Read @count bytes into @buf from TPM_RD_FIFO register */
+static int i2c_nuvoton_recv_data(struct i2c_client *client,
+ struct tpm_chip *chip, u8 *buf, size_t count)
+{
+ s32 rc;
+ int burst_count, bytes2read, size = 0;
+
+ while (size < count &&
+ i2c_nuvoton_wait_for_data_avail(chip,
+ chip->vendor.timeout_c,
+ &chip->vendor.read_queue) == 0) {
+ burst_count = i2c_nuvoton_get_burstcount(client, chip);
+ if (burst_count < 0) {
+ dev_err(chip->dev,
+ "%s() fail to read burstCount=%d\n", __func__,
+ burst_count);
+ return -EIO;
+ }
+ bytes2read = min_t(size_t, burst_count, count - size);
+ rc = i2c_nuvoton_read_buf(client, TPM_DATA_FIFO_R,
+ bytes2read, &buf[size]);
+ if (rc < 0) {
+ dev_err(chip->dev,
+ "%s() fail on i2c_nuvoton_read_buf()=%d\n",
+ __func__, rc);
+ return -EIO;
+ }
+ dev_dbg(chip->dev, "%s(%d):", __func__, bytes2read);
+ size += bytes2read;
+ }
+
+ return size;
+}
+
+/* Read TPM command results */
+static int i2c_nuvoton_recv(struct tpm_chip *chip, u8 *buf, size_t count)
+{
+ struct device *dev = chip->dev;
+ struct i2c_client *client = to_i2c_client(dev);
+ s32 rc;
+ int expected, status, burst_count, retries, size = 0;
+
+ if (count < TPM_HEADER_SIZE) {
+ i2c_nuvoton_ready(chip); /* return to idle */
+ dev_err(dev, "%s() count < header size\n", __func__);
+ return -EIO;
+ }
+ for (retries = 0; retries < TPM_RETRY; retries++) {
+ if (retries > 0) {
+ /* if this is not the first trial, set responseRetry */
+ i2c_nuvoton_write_status(client,
+ TPM_STS_RESPONSE_RETRY);
+ }
+ /*
+ * read first available (> 10 bytes), including:
+ * tag, paramsize, and result
+ */
+ status = i2c_nuvoton_wait_for_data_avail(
+ chip, chip->vendor.timeout_c, &chip->vendor.read_queue);
+ if (status != 0) {
+ dev_err(dev, "%s() timeout on dataAvail\n", __func__);
+ size = -ETIMEDOUT;
+ continue;
+ }
+ burst_count = i2c_nuvoton_get_burstcount(client, chip);
+ if (burst_count < 0) {
+ dev_err(dev, "%s() fail to get burstCount\n", __func__);
+ size = -EIO;
+ continue;
+ }
+ size = i2c_nuvoton_recv_data(client, chip, buf,
+ burst_count);
+ if (size < TPM_HEADER_SIZE) {
+ dev_err(dev, "%s() fail to read header\n", __func__);
+ size = -EIO;
+ continue;
+ }
+ /*
+ * convert number of expected bytes field from big endian 32 bit
+ * to machine native
+ */
+ expected = be32_to_cpu(*(__be32 *) (buf + 2));
+ if (expected > count) {
+ dev_err(dev, "%s() expected > count\n", __func__);
+ size = -EIO;
+ continue;
+ }
+ rc = i2c_nuvoton_recv_data(client, chip, &buf[size],
+ expected - size);
+ size += rc;
+ if (rc < 0 || size < expected) {
+ dev_err(dev, "%s() fail to read remainder of result\n",
+ __func__);
+ size = -EIO;
+ continue;
+ }
+ if (i2c_nuvoton_wait_for_stat(
+ chip, TPM_STS_VALID | TPM_STS_DATA_AVAIL,
+ TPM_STS_VALID, chip->vendor.timeout_c,
+ NULL)) {
+ dev_err(dev, "%s() error left over data\n", __func__);
+ size = -ETIMEDOUT;
+ continue;
+ }
+ break;
+ }
+ i2c_nuvoton_ready(chip);
+ dev_dbg(chip->dev, "%s() -> %d\n", __func__, size);
+ return size;
+}
+
+/*
+ * Send TPM command.
+ *
+ * If interrupts are used (signaled by an irq set in the vendor structure)
+ * tpm.c can skip polling for the data to be available as the interrupt is
+ * waited for here
+ */
+static int i2c_nuvoton_send(struct tpm_chip *chip, u8 *buf, size_t len)
+{
+ struct device *dev = chip->dev;
+ struct i2c_client *client = to_i2c_client(dev);
+ u32 ordinal;
+ size_t count = 0;
+ int burst_count, bytes2write, retries, rc = -EIO;
+
+ for (retries = 0; retries < TPM_RETRY; retries++) {
+ i2c_nuvoton_ready(chip);
+ if (i2c_nuvoton_wait_for_stat(chip, TPM_STS_COMMAND_READY,
+ TPM_STS_COMMAND_READY,
+ chip->vendor.timeout_b, NULL)) {
+ dev_err(dev, "%s() timeout on commandReady\n",
+ __func__);
+ rc = -EIO;
+ continue;
+ }
+ rc = 0;
+ while (count < len - 1) {
+ burst_count = i2c_nuvoton_get_burstcount(client,
+ chip);
+ if (burst_count < 0) {
+ dev_err(dev, "%s() fail get burstCount\n",
+ __func__);
+ rc = -EIO;
+ break;
+ }
+ bytes2write = min_t(size_t, burst_count,
+ len - 1 - count);
+ rc = i2c_nuvoton_write_buf(client, TPM_DATA_FIFO_W,
+ bytes2write, &buf[count]);
+ if (rc < 0) {
+ dev_err(dev, "%s() fail i2cWriteBuf\n",
+ __func__);
+ break;
+ }
+ dev_dbg(dev, "%s(%d):", __func__, bytes2write);
+ count += bytes2write;
+ rc = i2c_nuvoton_wait_for_stat(chip,
+ TPM_STS_VALID |
+ TPM_STS_EXPECT,
+ TPM_STS_VALID |
+ TPM_STS_EXPECT,
+ chip->vendor.timeout_c,
+ NULL);
+ if (rc < 0) {
+ dev_err(dev, "%s() timeout on Expect\n",
+ __func__);
+ rc = -ETIMEDOUT;
+ break;
+ }
+ }
+ if (rc < 0)
+ continue;
+
+ /* write last byte */
+ rc = i2c_nuvoton_write_buf(client, TPM_DATA_FIFO_W, 1,
+ &buf[count]);
+ if (rc < 0) {
+ dev_err(dev, "%s() fail to write last byte\n",
+ __func__);
+ rc = -EIO;
+ continue;
+ }
+ dev_dbg(dev, "%s(last): %02x", __func__, buf[count]);
+ rc = i2c_nuvoton_wait_for_stat(chip,
+ TPM_STS_VALID | TPM_STS_EXPECT,
+ TPM_STS_VALID,
+ chip->vendor.timeout_c, NULL);
+ if (rc) {
+ dev_err(dev, "%s() timeout on Expect to clear\n",
+ __func__);
+ rc = -ETIMEDOUT;
+ continue;
+ }
+ break;
+ }
+ if (rc < 0) {
+ /* retries == TPM_RETRY */
+ i2c_nuvoton_ready(chip);
+ return rc;
+ }
+ /* execute the TPM command */
+ rc = i2c_nuvoton_write_status(client, TPM_STS_GO);
+ if (rc < 0) {
+ dev_err(dev, "%s() fail to write Go\n", __func__);
+ i2c_nuvoton_ready(chip);
+ return rc;
+ }
+ ordinal = be32_to_cpu(*((__be32 *) (buf + 6)));
+ rc = i2c_nuvoton_wait_for_data_avail(chip,
+ tpm_calc_ordinal_duration(chip,
+ ordinal),
+ &chip->vendor.read_queue);
+ if (rc) {
+ dev_err(dev, "%s() timeout command duration\n", __func__);
+ i2c_nuvoton_ready(chip);
+ return rc;
+ }
+
+ dev_dbg(dev, "%s() -> %zd\n", __func__, len);
+ return len;
+}
+
+static bool i2c_nuvoton_req_canceled(struct tpm_chip *chip, u8 status)
+{
+ return (status == TPM_STS_COMMAND_READY);
+}
+
+static const struct file_operations i2c_nuvoton_ops = {
+ .owner = THIS_MODULE,
+ .llseek = no_llseek,
+ .open = tpm_open,
+ .read = tpm_read,
+ .write = tpm_write,
+ .release = tpm_release,
+};
+
+static DEVICE_ATTR(pubek, S_IRUGO, tpm_show_pubek, NULL);
+static DEVICE_ATTR(pcrs, S_IRUGO, tpm_show_pcrs, NULL);
+static DEVICE_ATTR(enabled, S_IRUGO, tpm_show_enabled, NULL);
+static DEVICE_ATTR(active, S_IRUGO, tpm_show_active, NULL);
+static DEVICE_ATTR(owned, S_IRUGO, tpm_show_owned, NULL);
+static DEVICE_ATTR(temp_deactivated, S_IRUGO, tpm_show_temp_deactivated, NULL);
+static DEVICE_ATTR(caps, S_IRUGO, tpm_show_caps, NULL);
+static DEVICE_ATTR(cancel, S_IWUSR | S_IWGRP, NULL, tpm_store_cancel);
+static DEVICE_ATTR(durations, S_IRUGO, tpm_show_durations, NULL);
+static DEVICE_ATTR(timeouts, S_IRUGO, tpm_show_timeouts, NULL);
+
+static struct attribute *i2c_nuvoton_attrs[] = {
+ &dev_attr_pubek.attr,
+ &dev_attr_pcrs.attr,
+ &dev_attr_enabled.attr,
+ &dev_attr_active.attr,
+ &dev_attr_owned.attr,
+ &dev_attr_temp_deactivated.attr,
+ &dev_attr_caps.attr,
+ &dev_attr_cancel.attr,
+ &dev_attr_durations.attr,
+ &dev_attr_timeouts.attr,
+ NULL,
+};
+
+static struct attribute_group i2c_nuvoton_attr_grp = {
+ .attrs = i2c_nuvoton_attrs
+};
+
+static const struct tpm_vendor_specific tpm_i2c = {
+ .status = i2c_nuvoton_read_status,
+ .recv = i2c_nuvoton_recv,
+ .send = i2c_nuvoton_send,
+ .cancel = i2c_nuvoton_ready,
+ .req_complete_mask = TPM_STS_DATA_AVAIL | TPM_STS_VALID,
+ .req_complete_val = TPM_STS_DATA_AVAIL | TPM_STS_VALID,
+ .req_canceled = i2c_nuvoton_req_canceled,
+ .attr_group = &i2c_nuvoton_attr_grp,
+ .miscdev.fops = &i2c_nuvoton_ops,
+};
+
+/* The only purpose for the handler is to signal to any waiting threads that
+ * the interrupt is currently being asserted. The driver does not do any
+ * processing triggered by interrupts, and the chip provides no way to mask at
+ * the source (plus that would be slow over I2C). Run the IRQ as a one-shot,
+ * this means it cannot be shared. */
+static irqreturn_t i2c_nuvoton_int_handler(int dummy, void *dev_id)
+{
+ struct tpm_chip *chip = dev_id;
+ struct priv_data *priv = chip->vendor.priv;
+
+ priv->intrs++;
+ wake_up(&chip->vendor.read_queue);
+ disable_irq_nosync(chip->vendor.irq);
+ return IRQ_HANDLED;
+}
+
+static int get_vid(struct i2c_client *client, u32 *res)
+{
+ static const u8 vid_did_rid_value[] = { 0x50, 0x10, 0xfe };
+ u32 temp;
+ s32 rc;
+
+ if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_BYTE_DATA))
+ return -ENODEV;
+ rc = i2c_nuvoton_read_buf(client, TPM_VID_DID_RID, 4, (u8 *)&temp);
+ if (rc < 0)
+ return rc;
+
+ /* check WPCT301 values - ignore RID */
+ if (memcmp(&temp, vid_did_rid_value, sizeof(vid_did_rid_value))) {
+ /*
+ * f/w rev 2.81 has an issue where the VID_DID_RID is not
+ * reporting the right value. so give it another chance at
+ * offset 0x20 (FIFO_W).
+ */
+ rc = i2c_nuvoton_read_buf(client, TPM_DATA_FIFO_W, 4,
+ (u8 *) (&temp));
+ if (rc < 0)
+ return rc;
+
+ /* check WPCT301 values - ignore RID */
+ if (memcmp(&temp, vid_did_rid_value,
+ sizeof(vid_did_rid_value)))
+ return -ENODEV;
+ }
+
+ *res = temp;
+ return 0;
+}
+
+static int i2c_nuvoton_probe(struct i2c_client *client,
+ const struct i2c_device_id *id)
+{
+ int rc;
+ struct tpm_chip *chip;
+ struct device *dev = &client->dev;
+ u32 vid = 0;
+
+ rc = get_vid(client, &vid);
+ if (rc)
+ return rc;
+
+ dev_info(dev, "VID: %04X DID: %02X RID: %02X\n", (u16) vid,
+ (u8) (vid >> 16), (u8) (vid >> 24));
+
+ chip = tpm_register_hardware(dev, &tpm_i2c);
+ if (!chip) {
+ dev_err(dev, "%s() error in tpm_register_hardware\n", __func__);
+ return -ENODEV;
+ }
+
+ chip->vendor.priv = devm_kzalloc(dev, sizeof(struct priv_data),
+ GFP_KERNEL);
+ init_waitqueue_head(&chip->vendor.read_queue);
+ init_waitqueue_head(&chip->vendor.int_queue);
+
+ /* Default timeouts */
+ chip->vendor.timeout_a = msecs_to_jiffies(TPM_I2C_SHORT_TIMEOUT);
+ chip->vendor.timeout_b = msecs_to_jiffies(TPM_I2C_LONG_TIMEOUT);
+ chip->vendor.timeout_c = msecs_to_jiffies(TPM_I2C_SHORT_TIMEOUT);
+ chip->vendor.timeout_d = msecs_to_jiffies(TPM_I2C_SHORT_TIMEOUT);
+
+ /*
+ * I2C intfcaps (interrupt capabilitieis) in the chip are hard coded to:
+ * TPM_INTF_INT_LEVEL_LOW | TPM_INTF_DATA_AVAIL_INT
+ * The IRQ should be set in the i2c_board_info (which is done
+ * automatically in of_i2c_register_devices, for device tree users */
+ chip->vendor.irq = client->irq;
+
+ if (chip->vendor.irq) {
+ dev_dbg(dev, "%s() chip-vendor.irq\n", __func__);
+ rc = devm_request_irq(dev, chip->vendor.irq,
+ i2c_nuvoton_int_handler,
+ IRQF_TRIGGER_LOW,
+ chip->vendor.miscdev.name,
+ chip);
+ if (rc) {
+ dev_err(dev, "%s() Unable to request irq: %d for use\n",
+ __func__, chip->vendor.irq);
+ chip->vendor.irq = 0;
+ } else {
+ /* Clear any pending interrupt */
+ i2c_nuvoton_ready(chip);
+ /* - wait for TPM_STS==0xA0 (stsValid, commandReady) */
+ rc = i2c_nuvoton_wait_for_stat(chip,
+ TPM_STS_COMMAND_READY,
+ TPM_STS_COMMAND_READY,
+ chip->vendor.timeout_b,
+ NULL);
+ if (rc == 0) {
+ /*
+ * TIS is in ready state
+ * write dummy byte to enter reception state
+ * TPM_DATA_FIFO_W <- rc (0)
+ */
+ rc = i2c_nuvoton_write_buf(client,
+ TPM_DATA_FIFO_W,
+ 1, (u8 *) (&rc));
+ if (rc < 0)
+ goto out_err;
+ /* TPM_STS <- 0x40 (commandReady) */
+ i2c_nuvoton_ready(chip);
+ } else {
+ /*
+ * timeout_b reached - command was
+ * aborted. TIS should now be in idle state -
+ * only TPM_STS_VALID should be set
+ */
+ if (i2c_nuvoton_read_status(chip) !=
+ TPM_STS_VALID) {
+ rc = -EIO;
+ goto out_err;
+ }
+ }
+ }
+ }
+
+ if (tpm_get_timeouts(chip)) {
+ rc = -ENODEV;
+ goto out_err;
+ }
+
+ if (tpm_do_selftest(chip)) {
+ rc = -ENODEV;
+ goto out_err;
+ }
+
+ return 0;
+
+out_err:
+ tpm_dev_vendor_release(chip);
+ tpm_remove_hardware(chip->dev);
+ return rc;
+}
+
+static int i2c_nuvoton_remove(struct i2c_client *client)
+{
+ struct device *dev = &(client->dev);
+ struct tpm_chip *chip = dev_get_drvdata(dev);
+
+ if (chip)
+ tpm_dev_vendor_release(chip);
+ tpm_remove_hardware(dev);
+ kfree(chip);
+ return 0;
+}
+
+
+static const struct i2c_device_id i2c_nuvoton_id[] = {
+ {I2C_DRIVER_NAME, 0},
+ {}
+};
+MODULE_DEVICE_TABLE(i2c, i2c_nuvoton_id);
+
+#ifdef CONFIG_OF
+static const struct of_device_id i2c_nuvoton_of_match[] = {
+ {.compatible = "nuvoton,npct501"},
+ {.compatible = "winbond,wpct301"},
+ {},
+};
+MODULE_DEVICE_TABLE(of, i2c_nuvoton_of_match);
+#endif
+
+static SIMPLE_DEV_PM_OPS(i2c_nuvoton_pm_ops, tpm_pm_suspend, tpm_pm_resume);
+
+static struct i2c_driver i2c_nuvoton_driver = {
+ .id_table = i2c_nuvoton_id,
+ .probe = i2c_nuvoton_probe,
+ .remove = i2c_nuvoton_remove,
+ .driver = {
+ .name = I2C_DRIVER_NAME,
+ .owner = THIS_MODULE,
+ .pm = &i2c_nuvoton_pm_ops,
+ .of_match_table = of_match_ptr(i2c_nuvoton_of_match),
+ },
+};
+
+module_i2c_driver(i2c_nuvoton_driver);
+
+MODULE_AUTHOR("Dan Morav (dan.morav@nuvoton.com)");
+MODULE_DESCRIPTION("Nuvoton TPM I2C Driver");
+MODULE_LICENSE("GPL");
static DEVICE_ATTR(active, S_IRUGO, tpm_show_active, NULL);
static DEVICE_ATTR(owned, S_IRUGO, tpm_show_owned, NULL);
static DEVICE_ATTR(temp_deactivated, S_IRUGO, tpm_show_temp_deactivated, NULL);
-static DEVICE_ATTR(caps, S_IRUGO, tpm_show_caps_1_2, NULL);
+static DEVICE_ATTR(caps, S_IRUGO, tpm_show_caps, NULL);
static DEVICE_ATTR(cancel, S_IWUSR | S_IWGRP, NULL, tpm_store_cancel);
static struct attribute *stm_tpm_attrs[] = {
tpm_get_timeouts(chip);
- i2c_set_clientdata(client, chip);
-
dev_info(chip->dev, "TPM I2C Initialized\n");
return 0;
_irq_set:
#ifdef CONFIG_PM_SLEEP
/*
* tpm_st33_i2c_pm_suspend suspend the TPM device
- * Added: Work around when suspend and no tpm application is running, suspend
- * may fail because chip->data_buffer is not set (only set in tpm_open in Linux
- * TPM core)
* @param: client, the i2c_client drescription (TPM I2C description).
* @param: mesg, the power management message.
* @return: 0 in case of success.
*/
static int tpm_st33_i2c_pm_suspend(struct device *dev)
{
- struct tpm_chip *chip = dev_get_drvdata(dev);
struct st33zp24_platform_data *pin_infos = dev->platform_data;
int ret = 0;
if (power_mgt) {
gpio_set_value(pin_infos->io_lpcpd, 0);
} else {
- if (chip->data_buffer == NULL)
- chip->data_buffer = pin_infos->tpm_i2c_buffer[0];
ret = tpm_pm_suspend(dev);
}
return ret;
TPM_STS_VALID) == TPM_STS_VALID,
chip->vendor.timeout_b);
} else {
- if (chip->data_buffer == NULL)
- chip->data_buffer = pin_infos->tpm_i2c_buffer[0];
ret = tpm_pm_resume(dev);
if (!ret)
tpm_do_selftest(chip);
if (count < len) {
dev_err(ibmvtpm->dev,
- "Invalid size in recv: count=%ld, crq_size=%d\n",
+ "Invalid size in recv: count=%zd, crq_size=%d\n",
count, len);
return -EIO;
}
if (count > ibmvtpm->rtce_size) {
dev_err(ibmvtpm->dev,
- "Invalid size in send: count=%ld, rtce_size=%d\n",
+ "Invalid size in send: count=%zd, rtce_size=%d\n",
count, ibmvtpm->rtce_size);
return -EIO;
}
static DEVICE_ATTR(owned, S_IRUGO, tpm_show_owned, NULL);
static DEVICE_ATTR(temp_deactivated, S_IRUGO, tpm_show_temp_deactivated,
NULL);
-static DEVICE_ATTR(caps, S_IRUGO, tpm_show_caps_1_2, NULL);
+static DEVICE_ATTR(caps, S_IRUGO, tpm_show_caps, NULL);
static DEVICE_ATTR(cancel, S_IWUSR | S_IWGRP, NULL, tpm_store_cancel);
static DEVICE_ATTR(durations, S_IRUGO, tpm_show_durations, NULL);
static DEVICE_ATTR(timeouts, S_IRUGO, tpm_show_timeouts, NULL);
{
return sysfs_create_group(parent, &ppi_attr_grp);
}
-EXPORT_SYMBOL_GPL(tpm_add_ppi);
void tpm_remove_ppi(struct kobject *parent)
{
sysfs_remove_group(parent, &ppi_attr_grp);
}
-EXPORT_SYMBOL_GPL(tpm_remove_ppi);
-
-MODULE_LICENSE("GPL");
static DEVICE_ATTR(owned, S_IRUGO, tpm_show_owned, NULL);
static DEVICE_ATTR(temp_deactivated, S_IRUGO, tpm_show_temp_deactivated,
NULL);
-static DEVICE_ATTR(caps, S_IRUGO, tpm_show_caps_1_2, NULL);
+static DEVICE_ATTR(caps, S_IRUGO, tpm_show_caps, NULL);
static DEVICE_ATTR(cancel, S_IWUSR | S_IWGRP, NULL, tpm_store_cancel);
static DEVICE_ATTR(durations, S_IRUGO, tpm_show_durations, NULL);
static DEVICE_ATTR(timeouts, S_IRUGO, tpm_show_timeouts, NULL);
tpm_get_timeouts(priv->chip);
- dev_set_drvdata(&dev->dev, priv->chip);
-
return rv;
}
}
EXPORT_SYMBOL(drm_sysfs_hotplug_event);
+static void drm_sysfs_release(struct device *dev)
+{
+ kfree(dev);
+}
+
/**
* drm_sysfs_device_add - adds a class device to sysfs for a character driver
* @dev: DRM device to be added
int drm_sysfs_device_add(struct drm_minor *minor)
{
char *minor_str;
+ int r;
if (minor->type == DRM_MINOR_CONTROL)
minor_str = "controlD%d";
else
minor_str = "card%d";
- minor->kdev = device_create(drm_class, minor->dev->dev,
- MKDEV(DRM_MAJOR, minor->index),
- minor, minor_str, minor->index);
- if (IS_ERR(minor->kdev)) {
- DRM_ERROR("device create failed %ld\n", PTR_ERR(minor->kdev));
- return PTR_ERR(minor->kdev);
+ minor->kdev = kzalloc(sizeof(*minor->kdev), GFP_KERNEL);
+ if (!minor->dev) {
+ r = -ENOMEM;
+ goto error;
}
+
+ device_initialize(minor->kdev);
+ minor->kdev->devt = MKDEV(DRM_MAJOR, minor->index);
+ minor->kdev->class = drm_class;
+ minor->kdev->type = &drm_sysfs_device_minor;
+ minor->kdev->parent = minor->dev->dev;
+ minor->kdev->release = drm_sysfs_release;
+ dev_set_drvdata(minor->kdev, minor);
+
+ r = dev_set_name(minor->kdev, minor_str, minor->index);
+ if (r < 0)
+ goto error;
+
+ r = device_add(minor->kdev);
+ if (r < 0)
+ goto error;
+
return 0;
+
+error:
+ DRM_ERROR("device create failed %d\n", r);
+ put_device(minor->kdev);
+ return r;
}
/**
void drm_sysfs_device_remove(struct drm_minor *minor)
{
if (minor->kdev)
- device_destroy(drm_class, MKDEV(DRM_MAJOR, minor->index));
+ device_unregister(minor->kdev);
minor->kdev = NULL;
}
g2d_userptr->npages,
g2d_userptr->vma);
+ exynos_gem_put_vma(g2d_userptr->vma);
+
if (!g2d_userptr->out_of_list)
list_del_init(&g2d_userptr->list);
#define HAS_POWER_WELL(dev) (IS_HASWELL(dev) || IS_BROADWELL(dev))
#define HAS_FPGA_DBG_UNCLAIMED(dev) (INTEL_INFO(dev)->has_fpga_dbg)
#define HAS_PSR(dev) (IS_HASWELL(dev) || IS_BROADWELL(dev))
+#define HAS_PC8(dev) (IS_HASWELL(dev)) /* XXX HSW:ULX */
#define INTEL_PCH_DEVICE_ID_MASK 0xff00
#define INTEL_PCH_IBX_DEVICE_ID_TYPE 0x3b00
/* Default to using SSC */
dev_priv->vbt.lvds_use_ssc = 1;
- dev_priv->vbt.lvds_ssc_freq = intel_bios_ssc_frequency(dev, 1);
+ /*
+ * Core/SandyBridge/IvyBridge use alternative (120MHz) reference
+ * clock for LVDS.
+ */
+ dev_priv->vbt.lvds_ssc_freq = intel_bios_ssc_frequency(dev,
+ !HAS_PCH_SPLIT(dev));
DRM_DEBUG_KMS("Set default to SSC at %dMHz\n", dev_priv->vbt.lvds_ssc_freq);
for (port = PORT_A; port < I915_MAX_PORTS; port++) {
default:
break;
}
+
+ if (encoder->type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp_bpp &&
+ pipe_config->pipe_bpp > dev_priv->vbt.edp_bpp) {
+ /*
+ * This is a big fat ugly hack.
+ *
+ * Some machines in UEFI boot mode provide us a VBT that has 18
+ * bpp and 1.62 GHz link bandwidth for eDP, which for reasons
+ * unknown we fail to light up. Yet the same BIOS boots up with
+ * 24 bpp and 2.7 GHz link. Use the same bpp as the BIOS uses as
+ * max, not what it tells us to use.
+ *
+ * Note: This will still be broken if the eDP panel is not lit
+ * up by the BIOS, and thus we can't get the mode at module
+ * load.
+ */
+ DRM_DEBUG_KMS("pipe has %d bpp for eDP panel, overriding BIOS-provided max %d bpp\n",
+ pipe_config->pipe_bpp, dev_priv->vbt.edp_bpp);
+ dev_priv->vbt.edp_bpp = pipe_config->pipe_bpp;
+ }
}
static void intel_ddi_destroy(struct drm_encoder *encoder)
void hsw_enable_package_c8(struct drm_i915_private *dev_priv)
{
+ if (!HAS_PC8(dev_priv->dev))
+ return;
+
mutex_lock(&dev_priv->pc8.lock);
__hsw_enable_package_c8(dev_priv);
mutex_unlock(&dev_priv->pc8.lock);
void hsw_disable_package_c8(struct drm_i915_private *dev_priv)
{
+ if (!HAS_PC8(dev_priv->dev))
+ return;
+
mutex_lock(&dev_priv->pc8.lock);
__hsw_disable_package_c8(dev_priv);
mutex_unlock(&dev_priv->pc8.lock);
struct drm_i915_private *dev_priv = dev->dev_private;
bool allow;
+ if (!HAS_PC8(dev_priv->dev))
+ return;
+
if (!i915_enable_pc8)
return;
static void hsw_package_c8_gpu_idle(struct drm_i915_private *dev_priv)
{
+ if (!HAS_PC8(dev_priv->dev))
+ return;
+
+ mutex_lock(&dev_priv->pc8.lock);
if (!dev_priv->pc8.gpu_idle) {
dev_priv->pc8.gpu_idle = true;
- hsw_enable_package_c8(dev_priv);
+ __hsw_enable_package_c8(dev_priv);
}
+ mutex_unlock(&dev_priv->pc8.lock);
}
static void hsw_package_c8_gpu_busy(struct drm_i915_private *dev_priv)
{
+ if (!HAS_PC8(dev_priv->dev))
+ return;
+
+ mutex_lock(&dev_priv->pc8.lock);
if (dev_priv->pc8.gpu_idle) {
dev_priv->pc8.gpu_idle = false;
- hsw_disable_package_c8(dev_priv);
+ __hsw_disable_package_c8(dev_priv);
}
+ mutex_unlock(&dev_priv->pc8.lock);
}
#define for_each_power_domain(domain, mask) \
intel_crtc->cursor_visible = visible;
}
/* and commit changes on next vblank */
+ POSTING_READ(CURCNTR(pipe));
I915_WRITE(CURBASE(pipe), base);
+ POSTING_READ(CURBASE(pipe));
}
static void ivb_update_cursor(struct drm_crtc *crtc, u32 base)
intel_crtc->cursor_visible = visible;
}
/* and commit changes on next vblank */
+ POSTING_READ(CURCNTR_IVB(pipe));
I915_WRITE(CURBASE_IVB(pipe), base);
+ POSTING_READ(CURBASE_IVB(pipe));
}
/* If no-part of the cursor is visible on the framebuffer, then the GPU may hang... */
enum pipe pipe;
if (encoder->base.crtc != &crtc->base)
continue;
- if (encoder->get_config &&
- encoder->get_hw_state(encoder, &pipe))
+ if (encoder->get_hw_state(encoder, &pipe))
encoder->get_config(encoder, &pipe_config);
}
if (encoder->get_hw_state(encoder, &pipe)) {
crtc = to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
encoder->base.crtc = &crtc->base;
- if (encoder->get_config)
- encoder->get_config(encoder, &crtc->config);
+ encoder->get_config(encoder, &crtc->config);
} else {
encoder->base.crtc = NULL;
}
* ensure that we have vdd while we switch off the panel. */
ironlake_edp_panel_vdd_on(intel_dp);
ironlake_edp_backlight_off(intel_dp);
- intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
+ intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
ironlake_edp_panel_off(intel_dp);
/* cpu edp my only be disable _after_ the cpu pipe/plane is disabled. */
&to_intel_crtc(enabled)->config.adjusted_mode;
int clock = adjusted_mode->crtc_clock;
int htotal = adjusted_mode->htotal;
- int hdisplay = to_intel_crtc(crtc)->config.pipe_src_w;
+ int hdisplay = to_intel_crtc(enabled)->config.pipe_src_w;
int pixel_size = enabled->fb->bits_per_pixel / 8;
unsigned long line_time_us;
int entries;
I915_WRITE(GEN6_RC_SLEEP, 0);
I915_WRITE(GEN6_RC1e_THRESHOLD, 1000);
- if (INTEL_INFO(dev)->gen <= 6 || IS_IVYBRIDGE(dev))
+ if (IS_IVYBRIDGE(dev))
I915_WRITE(GEN6_RC6_THRESHOLD, 125000);
else
I915_WRITE(GEN6_RC6_THRESHOLD, 50000);
}
+static void
+intel_tv_get_config(struct intel_encoder *encoder,
+ struct intel_crtc_config *pipe_config)
+{
+ pipe_config->adjusted_mode.crtc_clock = pipe_config->port_clock;
+}
+
static bool
intel_tv_compute_config(struct intel_encoder *encoder,
struct intel_crtc_config *pipe_config)
DRM_MODE_ENCODER_TVDAC);
intel_encoder->compute_config = intel_tv_compute_config;
+ intel_encoder->get_config = intel_tv_get_config;
intel_encoder->mode_set = intel_tv_mode_set;
intel_encoder->enable = intel_enable_tv;
intel_encoder->disable = intel_disable_tv;
spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
}
+static void intel_uncore_forcewake_reset(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ if (IS_VALLEYVIEW(dev)) {
+ vlv_force_wake_reset(dev_priv);
+ } else if (INTEL_INFO(dev)->gen >= 6) {
+ __gen6_gt_force_wake_reset(dev_priv);
+ if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
+ __gen6_gt_force_wake_mt_reset(dev_priv);
+ }
+}
+
void intel_uncore_early_sanitize(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
dev_priv->ellc_size = 128;
DRM_INFO("Found %zuMB of eLLC\n", dev_priv->ellc_size);
}
-}
-static void intel_uncore_forcewake_reset(struct drm_device *dev)
-{
- struct drm_i915_private *dev_priv = dev->dev_private;
-
- if (IS_VALLEYVIEW(dev)) {
- vlv_force_wake_reset(dev_priv);
- } else if (INTEL_INFO(dev)->gen >= 6) {
- __gen6_gt_force_wake_reset(dev_priv);
- if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
- __gen6_gt_force_wake_mt_reset(dev_priv);
- }
+ intel_uncore_forcewake_reset(dev);
}
void intel_uncore_sanitize(struct drm_device *dev)
return -EINVAL;
}
args.ucRegIndex = buf[0];
- if (num > 1)
- memcpy(&out, &buf[1], num - 1);
+ if (num > 1) {
+ num--;
+ memcpy(&out, &buf[1], num);
+ }
args.lpI2CDataOut = cpu_to_le16(out);
} else {
if (num > ATOM_MAX_HW_I2C_READ) {
* cik_mm_rdoorbell - read a doorbell dword
*
* @rdev: radeon_device pointer
- * @offset: byte offset into the aperture
+ * @index: doorbell index
*
* Returns the value in the doorbell aperture at the
- * requested offset (CIK).
+ * requested doorbell index (CIK).
*/
-u32 cik_mm_rdoorbell(struct radeon_device *rdev, u32 offset)
+u32 cik_mm_rdoorbell(struct radeon_device *rdev, u32 index)
{
- if (offset < rdev->doorbell.size) {
- return readl(((void __iomem *)rdev->doorbell.ptr) + offset);
+ if (index < rdev->doorbell.num_doorbells) {
+ return readl(rdev->doorbell.ptr + index);
} else {
- DRM_ERROR("reading beyond doorbell aperture: 0x%08x!\n", offset);
+ DRM_ERROR("reading beyond doorbell aperture: 0x%08x!\n", index);
return 0;
}
}
* cik_mm_wdoorbell - write a doorbell dword
*
* @rdev: radeon_device pointer
- * @offset: byte offset into the aperture
+ * @index: doorbell index
* @v: value to write
*
* Writes @v to the doorbell aperture at the
- * requested offset (CIK).
+ * requested doorbell index (CIK).
*/
-void cik_mm_wdoorbell(struct radeon_device *rdev, u32 offset, u32 v)
+void cik_mm_wdoorbell(struct radeon_device *rdev, u32 index, u32 v)
{
- if (offset < rdev->doorbell.size) {
- writel(v, ((void __iomem *)rdev->doorbell.ptr) + offset);
+ if (index < rdev->doorbell.num_doorbells) {
+ writel(v, rdev->doorbell.ptr + index);
} else {
- DRM_ERROR("writing beyond doorbell aperture: 0x%08x!\n", offset);
+ DRM_ERROR("writing beyond doorbell aperture: 0x%08x!\n", index);
}
}
gb_tile_moden = 0;
break;
}
+ rdev->config.cik.macrotile_mode_array[reg_offset] = gb_tile_moden;
WREG32(GB_MACROTILE_MODE0 + (reg_offset * 4), gb_tile_moden);
}
} else if (num_pipe_configs == 4) {
gb_tile_moden = 0;
break;
}
+ rdev->config.cik.macrotile_mode_array[reg_offset] = gb_tile_moden;
WREG32(GB_MACROTILE_MODE0 + (reg_offset * 4), gb_tile_moden);
}
} else if (num_pipe_configs == 2) {
gb_tile_moden = 0;
break;
}
+ rdev->config.cik.macrotile_mode_array[reg_offset] = gb_tile_moden;
WREG32(GB_MACROTILE_MODE0 + (reg_offset * 4), gb_tile_moden);
}
} else
radeon_ring_write(ring, 0);
}
-void cik_semaphore_ring_emit(struct radeon_device *rdev,
+bool cik_semaphore_ring_emit(struct radeon_device *rdev,
struct radeon_ring *ring,
struct radeon_semaphore *semaphore,
bool emit_wait)
{
+/* TODO: figure out why semaphore cause lockups */
+#if 0
uint64_t addr = semaphore->gpu_addr;
unsigned sel = emit_wait ? PACKET3_SEM_SEL_WAIT : PACKET3_SEM_SEL_SIGNAL;
radeon_ring_write(ring, PACKET3(PACKET3_MEM_SEMAPHORE, 1));
radeon_ring_write(ring, addr & 0xffffffff);
radeon_ring_write(ring, (upper_32_bits(addr) & 0xffff) | sel);
+
+ return true;
+#else
+ return false;
+#endif
}
/**
return r;
}
- if (radeon_fence_need_sync(*fence, ring->idx)) {
- radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
- ring->idx);
- radeon_fence_note_sync(*fence, ring->idx);
- } else {
- radeon_semaphore_free(rdev, &sem, NULL);
- }
+ radeon_semaphore_sync_to(sem, *fence);
+ radeon_semaphore_sync_rings(rdev, sem, ring->idx);
for (i = 0; i < num_loops; i++) {
cur_size_in_bytes = size_in_bytes;
struct radeon_ring *ring)
{
rdev->wb.wb[ring->wptr_offs/4] = cpu_to_le32(ring->wptr);
- WDOORBELL32(ring->doorbell_offset, ring->wptr);
+ WDOORBELL32(ring->doorbell_index, ring->wptr);
}
/**
return r;
}
- /* doorbell offset */
- rdev->ring[idx].doorbell_offset =
- (rdev->ring[idx].doorbell_page_num * PAGE_SIZE) + 0;
-
/* init the mqd struct */
memset(buf, 0, sizeof(struct bonaire_mqd));
RREG32(CP_HQD_PQ_DOORBELL_CONTROL);
mqd->queue_state.cp_hqd_pq_doorbell_control &= ~DOORBELL_OFFSET_MASK;
mqd->queue_state.cp_hqd_pq_doorbell_control |=
- DOORBELL_OFFSET(rdev->ring[idx].doorbell_offset / 4);
+ DOORBELL_OFFSET(rdev->ring[idx].doorbell_index);
mqd->queue_state.cp_hqd_pq_doorbell_control |= DOORBELL_EN;
mqd->queue_state.cp_hqd_pq_doorbell_control &=
~(DOORBELL_SOURCE | DOORBELL_HIT);
ring = &rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX];
ring->ring_obj = NULL;
r600_ring_init(rdev, ring, 1024 * 1024);
- r = radeon_doorbell_get(rdev, &ring->doorbell_page_num);
+ r = radeon_doorbell_get(rdev, &ring->doorbell_index);
if (r)
return r;
ring = &rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX];
ring->ring_obj = NULL;
r600_ring_init(rdev, ring, 1024 * 1024);
- r = radeon_doorbell_get(rdev, &ring->doorbell_page_num);
+ r = radeon_doorbell_get(rdev, &ring->doorbell_index);
if (r)
return r;
* Add a DMA semaphore packet to the ring wait on or signal
* other rings (CIK).
*/
-void cik_sdma_semaphore_ring_emit(struct radeon_device *rdev,
+bool cik_sdma_semaphore_ring_emit(struct radeon_device *rdev,
struct radeon_ring *ring,
struct radeon_semaphore *semaphore,
bool emit_wait)
radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SEMAPHORE, 0, extra_bits));
radeon_ring_write(ring, addr & 0xfffffff8);
radeon_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
+
+ return true;
}
/**
return r;
}
- if (radeon_fence_need_sync(*fence, ring->idx)) {
- radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
- ring->idx);
- radeon_fence_note_sync(*fence, ring->idx);
- } else {
- radeon_semaphore_free(rdev, &sem, NULL);
- }
+ radeon_semaphore_sync_to(sem, *fence);
+ radeon_semaphore_sync_rings(rdev, sem, ring->idx);
for (i = 0; i < num_loops; i++) {
cur_size_in_bytes = size_in_bytes;
static int cypress_pcie_performance_request(struct radeon_device *rdev,
u8 perf_req, bool advertise)
{
+#if defined(CONFIG_ACPI)
struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev);
+#endif
u32 tmp;
udelay(10);
return r;
}
- if (radeon_fence_need_sync(*fence, ring->idx)) {
- radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
- ring->idx);
- radeon_fence_note_sync(*fence, ring->idx);
- } else {
- radeon_semaphore_free(rdev, &sem, NULL);
- }
+ radeon_semaphore_sync_to(sem, *fence);
+ radeon_semaphore_sync_rings(rdev, sem, ring->idx);
for (i = 0; i < num_loops; i++) {
cur_size_in_dw = size_in_dw;
static int ni_pcie_performance_request(struct radeon_device *rdev,
u8 perf_req, bool advertise)
{
+#if defined(CONFIG_ACPI)
struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev);
-#if defined(CONFIG_ACPI)
if ((perf_req == PCIE_PERF_REQ_PECI_GEN1) ||
(perf_req == PCIE_PERF_REQ_PECI_GEN2)) {
if (eg_pi->pcie_performance_request_registered == false)
radeon_ring_write(ring, RADEON_SW_INT_FIRE);
}
-void r100_semaphore_ring_emit(struct radeon_device *rdev,
+bool r100_semaphore_ring_emit(struct radeon_device *rdev,
struct radeon_ring *ring,
struct radeon_semaphore *semaphore,
bool emit_wait)
{
/* Unused on older asics, since we don't have semaphores or multiple rings */
BUG();
+ return false;
}
int r100_copy_blit(struct radeon_device *rdev,
}
}
-void r600_semaphore_ring_emit(struct radeon_device *rdev,
+bool r600_semaphore_ring_emit(struct radeon_device *rdev,
struct radeon_ring *ring,
struct radeon_semaphore *semaphore,
bool emit_wait)
radeon_ring_write(ring, PACKET3(PACKET3_MEM_SEMAPHORE, 1));
radeon_ring_write(ring, addr & 0xffffffff);
radeon_ring_write(ring, (upper_32_bits(addr) & 0xff) | sel);
+
+ return true;
}
/**
return r;
}
- if (radeon_fence_need_sync(*fence, ring->idx)) {
- radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
- ring->idx);
- radeon_fence_note_sync(*fence, ring->idx);
- } else {
- radeon_semaphore_free(rdev, &sem, NULL);
- }
+ radeon_semaphore_sync_to(sem, *fence);
+ radeon_semaphore_sync_rings(rdev, sem, ring->idx);
radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
radeon_ring_write(ring, (WAIT_UNTIL - PACKET3_SET_CONFIG_REG_OFFSET) >> 2);
* Add a DMA semaphore packet to the ring wait on or signal
* other rings (r6xx-SI).
*/
-void r600_dma_semaphore_ring_emit(struct radeon_device *rdev,
+bool r600_dma_semaphore_ring_emit(struct radeon_device *rdev,
struct radeon_ring *ring,
struct radeon_semaphore *semaphore,
bool emit_wait)
radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_SEMAPHORE, 0, s, 0));
radeon_ring_write(ring, addr & 0xfffffffc);
radeon_ring_write(ring, upper_32_bits(addr) & 0xff);
+
+ return true;
}
/**
return r;
}
- if (radeon_fence_need_sync(*fence, ring->idx)) {
- radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
- ring->idx);
- radeon_fence_note_sync(*fence, ring->idx);
- } else {
- radeon_semaphore_free(rdev, &sem, NULL);
- }
+ radeon_semaphore_sync_to(sem, *fence);
+ radeon_semaphore_sync_rings(rdev, sem, ring->idx);
for (i = 0; i < num_loops; i++) {
cur_size_in_dw = size_in_dw;
void radeon_fence_process(struct radeon_device *rdev, int ring);
bool radeon_fence_signaled(struct radeon_fence *fence);
int radeon_fence_wait(struct radeon_fence *fence, bool interruptible);
+int radeon_fence_wait_locked(struct radeon_fence *fence);
int radeon_fence_wait_next_locked(struct radeon_device *rdev, int ring);
int radeon_fence_wait_empty_locked(struct radeon_device *rdev, int ring);
int radeon_fence_wait_any(struct radeon_device *rdev,
struct radeon_sa_bo *sa_bo;
signed waiters;
uint64_t gpu_addr;
+ struct radeon_fence *sync_to[RADEON_NUM_RINGS];
};
int radeon_semaphore_create(struct radeon_device *rdev,
struct radeon_semaphore **semaphore);
-void radeon_semaphore_emit_signal(struct radeon_device *rdev, int ring,
+bool radeon_semaphore_emit_signal(struct radeon_device *rdev, int ring,
struct radeon_semaphore *semaphore);
-void radeon_semaphore_emit_wait(struct radeon_device *rdev, int ring,
+bool radeon_semaphore_emit_wait(struct radeon_device *rdev, int ring,
struct radeon_semaphore *semaphore);
+void radeon_semaphore_sync_to(struct radeon_semaphore *semaphore,
+ struct radeon_fence *fence);
int radeon_semaphore_sync_rings(struct radeon_device *rdev,
struct radeon_semaphore *semaphore,
- int signaler, int waiter);
+ int waiting_ring);
void radeon_semaphore_free(struct radeon_device *rdev,
struct radeon_semaphore **semaphore,
struct radeon_fence *fence);
/*
* GPU doorbell structures, functions & helpers
*/
+#define RADEON_MAX_DOORBELLS 1024 /* Reserve at most 1024 doorbell slots for radeon-owned rings. */
+
struct radeon_doorbell {
- u32 num_pages;
- bool free[1024];
/* doorbell mmio */
- resource_size_t base;
- resource_size_t size;
- void __iomem *ptr;
+ resource_size_t base;
+ resource_size_t size;
+ u32 __iomem *ptr;
+ u32 num_doorbells; /* Number of doorbells actually reserved for radeon. */
+ unsigned long used[DIV_ROUND_UP(RADEON_MAX_DOORBELLS, BITS_PER_LONG)];
};
int radeon_doorbell_get(struct radeon_device *rdev, u32 *page);
struct radeon_fence *fence;
struct radeon_vm *vm;
bool is_const_ib;
- struct radeon_fence *sync_to[RADEON_NUM_RINGS];
struct radeon_semaphore *semaphore;
};
u32 pipe;
u32 queue;
struct radeon_bo *mqd_obj;
- u32 doorbell_page_num;
- u32 doorbell_offset;
+ u32 doorbell_index;
unsigned wptr_offs;
};
struct radeon_ib *ib, struct radeon_vm *vm,
unsigned size);
void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib *ib);
-void radeon_ib_sync_to(struct radeon_ib *ib, struct radeon_fence *fence);
int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib,
struct radeon_ib *const_ib);
int radeon_ib_pool_init(struct radeon_device *rdev);
/* command emmit functions */
void (*ib_execute)(struct radeon_device *rdev, struct radeon_ib *ib);
void (*emit_fence)(struct radeon_device *rdev, struct radeon_fence *fence);
- void (*emit_semaphore)(struct radeon_device *rdev, struct radeon_ring *cp,
+ bool (*emit_semaphore)(struct radeon_device *rdev, struct radeon_ring *cp,
struct radeon_semaphore *semaphore, bool emit_wait);
void (*vm_flush)(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
unsigned tile_config;
uint32_t tile_mode_array[32];
+ uint32_t macrotile_mode_array[16];
};
union radeon_asic_config {
u32 r100_io_rreg(struct radeon_device *rdev, u32 reg);
void r100_io_wreg(struct radeon_device *rdev, u32 reg, u32 v);
-u32 cik_mm_rdoorbell(struct radeon_device *rdev, u32 offset);
-void cik_mm_wdoorbell(struct radeon_device *rdev, u32 offset, u32 v);
+u32 cik_mm_rdoorbell(struct radeon_device *rdev, u32 index);
+void cik_mm_wdoorbell(struct radeon_device *rdev, u32 index, u32 v);
/*
* Cast helper
#define RREG32_IO(reg) r100_io_rreg(rdev, (reg))
#define WREG32_IO(reg, v) r100_io_wreg(rdev, (reg), (v))
-#define RDOORBELL32(offset) cik_mm_rdoorbell(rdev, (offset))
-#define WDOORBELL32(offset, v) cik_mm_wdoorbell(rdev, (offset), (v))
+#define RDOORBELL32(index) cik_mm_rdoorbell(rdev, (index))
+#define WDOORBELL32(index, v) cik_mm_wdoorbell(rdev, (index), (v))
/*
* Indirect registers accessor
.bandwidth_update = &dce8_bandwidth_update,
.get_vblank_counter = &evergreen_get_vblank_counter,
.wait_for_vblank = &dce4_wait_for_vblank,
+ .set_backlight_level = &atombios_set_backlight_level,
+ .get_backlight_level = &atombios_get_backlight_level,
.hdmi_enable = &evergreen_hdmi_enable,
.hdmi_setmode = &evergreen_hdmi_setmode,
},
.bandwidth_update = &dce8_bandwidth_update,
.get_vblank_counter = &evergreen_get_vblank_counter,
.wait_for_vblank = &dce4_wait_for_vblank,
+ .set_backlight_level = &atombios_set_backlight_level,
+ .get_backlight_level = &atombios_get_backlight_level,
.hdmi_enable = &evergreen_hdmi_enable,
.hdmi_setmode = &evergreen_hdmi_setmode,
},
int r100_irq_process(struct radeon_device *rdev);
void r100_fence_ring_emit(struct radeon_device *rdev,
struct radeon_fence *fence);
-void r100_semaphore_ring_emit(struct radeon_device *rdev,
+bool r100_semaphore_ring_emit(struct radeon_device *rdev,
struct radeon_ring *cp,
struct radeon_semaphore *semaphore,
bool emit_wait);
int r600_dma_cs_parse(struct radeon_cs_parser *p);
void r600_fence_ring_emit(struct radeon_device *rdev,
struct radeon_fence *fence);
-void r600_semaphore_ring_emit(struct radeon_device *rdev,
+bool r600_semaphore_ring_emit(struct radeon_device *rdev,
struct radeon_ring *cp,
struct radeon_semaphore *semaphore,
bool emit_wait);
void r600_dma_fence_ring_emit(struct radeon_device *rdev,
struct radeon_fence *fence);
-void r600_dma_semaphore_ring_emit(struct radeon_device *rdev,
+bool r600_dma_semaphore_ring_emit(struct radeon_device *rdev,
struct radeon_ring *ring,
struct radeon_semaphore *semaphore,
bool emit_wait);
*/
void cayman_fence_ring_emit(struct radeon_device *rdev,
struct radeon_fence *fence);
-void cayman_uvd_semaphore_emit(struct radeon_device *rdev,
- struct radeon_ring *ring,
- struct radeon_semaphore *semaphore,
- bool emit_wait);
void cayman_pcie_gart_tlb_flush(struct radeon_device *rdev);
int cayman_init(struct radeon_device *rdev);
void cayman_fini(struct radeon_device *rdev);
int cik_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk);
void cik_sdma_fence_ring_emit(struct radeon_device *rdev,
struct radeon_fence *fence);
-void cik_sdma_semaphore_ring_emit(struct radeon_device *rdev,
+bool cik_sdma_semaphore_ring_emit(struct radeon_device *rdev,
struct radeon_ring *ring,
struct radeon_semaphore *semaphore,
bool emit_wait);
struct radeon_fence *fence);
void cik_fence_compute_ring_emit(struct radeon_device *rdev,
struct radeon_fence *fence);
-void cik_semaphore_ring_emit(struct radeon_device *rdev,
+bool cik_semaphore_ring_emit(struct radeon_device *rdev,
struct radeon_ring *cp,
struct radeon_semaphore *semaphore,
bool emit_wait);
int uvd_v1_0_ring_test(struct radeon_device *rdev, struct radeon_ring *ring);
int uvd_v1_0_ib_test(struct radeon_device *rdev, struct radeon_ring *ring);
-void uvd_v1_0_semaphore_emit(struct radeon_device *rdev,
+bool uvd_v1_0_semaphore_emit(struct radeon_device *rdev,
struct radeon_ring *ring,
struct radeon_semaphore *semaphore,
bool emit_wait);
struct radeon_fence *fence);
/* uvd v3.1 */
-void uvd_v3_1_semaphore_emit(struct radeon_device *rdev,
+bool uvd_v3_1_semaphore_emit(struct radeon_device *rdev,
struct radeon_ring *ring,
struct radeon_semaphore *semaphore,
bool emit_wait);
if (!p->relocs[i].robj)
continue;
- radeon_ib_sync_to(&p->ib, p->relocs[i].robj->tbo.sync_obj);
+ radeon_semaphore_sync_to(p->ib.semaphore,
+ p->relocs[i].robj->tbo.sync_obj);
}
}
goto out;
}
radeon_cs_sync_rings(parser);
- radeon_ib_sync_to(&parser->ib, vm->fence);
- radeon_ib_sync_to(&parser->ib, radeon_vm_grab_id(
- rdev, vm, parser->ring));
+ radeon_semaphore_sync_to(parser->ib.semaphore, vm->fence);
+ radeon_semaphore_sync_to(parser->ib.semaphore,
+ radeon_vm_grab_id(rdev, vm, parser->ring));
if ((rdev->family >= CHIP_TAHITI) &&
(parser->chunk_const_ib_idx != -1)) {
*/
int radeon_doorbell_init(struct radeon_device *rdev)
{
- int i;
-
/* doorbell bar mapping */
rdev->doorbell.base = pci_resource_start(rdev->pdev, 2);
rdev->doorbell.size = pci_resource_len(rdev->pdev, 2);
- /* limit to 4 MB for now */
- if (rdev->doorbell.size > (4 * 1024 * 1024))
- rdev->doorbell.size = 4 * 1024 * 1024;
+ rdev->doorbell.num_doorbells = min_t(u32, rdev->doorbell.size / sizeof(u32), RADEON_MAX_DOORBELLS);
+ if (rdev->doorbell.num_doorbells == 0)
+ return -EINVAL;
- rdev->doorbell.ptr = ioremap(rdev->doorbell.base, rdev->doorbell.size);
+ rdev->doorbell.ptr = ioremap(rdev->doorbell.base, rdev->doorbell.num_doorbells * sizeof(u32));
if (rdev->doorbell.ptr == NULL) {
return -ENOMEM;
}
DRM_INFO("doorbell mmio base: 0x%08X\n", (uint32_t)rdev->doorbell.base);
DRM_INFO("doorbell mmio size: %u\n", (unsigned)rdev->doorbell.size);
- rdev->doorbell.num_pages = rdev->doorbell.size / PAGE_SIZE;
+ memset(&rdev->doorbell.used, 0, sizeof(rdev->doorbell.used));
- for (i = 0; i < rdev->doorbell.num_pages; i++) {
- rdev->doorbell.free[i] = true;
- }
return 0;
}
}
/**
- * radeon_doorbell_get - Allocate a doorbell page
+ * radeon_doorbell_get - Allocate a doorbell entry
*
* @rdev: radeon_device pointer
- * @doorbell: doorbell page number
+ * @doorbell: doorbell index
*
- * Allocate a doorbell page for use by the driver (all asics).
+ * Allocate a doorbell for use by the driver (all asics).
* Returns 0 on success or -EINVAL on failure.
*/
int radeon_doorbell_get(struct radeon_device *rdev, u32 *doorbell)
{
- int i;
-
- for (i = 0; i < rdev->doorbell.num_pages; i++) {
- if (rdev->doorbell.free[i]) {
- rdev->doorbell.free[i] = false;
- *doorbell = i;
- return 0;
- }
+ unsigned long offset = find_first_zero_bit(rdev->doorbell.used, rdev->doorbell.num_doorbells);
+ if (offset < rdev->doorbell.num_doorbells) {
+ __set_bit(offset, rdev->doorbell.used);
+ *doorbell = offset;
+ return 0;
+ } else {
+ return -EINVAL;
}
- return -EINVAL;
}
/**
- * radeon_doorbell_free - Free a doorbell page
+ * radeon_doorbell_free - Free a doorbell entry
*
* @rdev: radeon_device pointer
- * @doorbell: doorbell page number
+ * @doorbell: doorbell index
*
- * Free a doorbell page allocated for use by the driver (all asics)
+ * Free a doorbell allocated for use by the driver (all asics)
*/
void radeon_doorbell_free(struct radeon_device *rdev, u32 doorbell)
{
- if (doorbell < rdev->doorbell.num_pages)
- rdev->doorbell.free[doorbell] = true;
+ if (doorbell < rdev->doorbell.num_doorbells)
+ __clear_bit(doorbell, rdev->doorbell.used);
}
/*
* 2.32.0 - new info request for rings working
* 2.33.0 - Add SI tiling mode array query
* 2.34.0 - Add CIK tiling mode array query
+ * 2.35.0 - Add CIK macrotile mode array query
*/
#define KMS_DRIVER_MAJOR 2
-#define KMS_DRIVER_MINOR 34
+#define KMS_DRIVER_MINOR 35
#define KMS_DRIVER_PATCHLEVEL 0
int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
int radeon_driver_unload_kms(struct drm_device *dev);
return 0;
}
+/**
+ * radeon_fence_wait_locked - wait for a fence to signal
+ *
+ * @fence: radeon fence object
+ *
+ * Wait for the requested fence to signal (all asics).
+ * Returns 0 if the fence has passed, error for all other cases.
+ */
+int radeon_fence_wait_locked(struct radeon_fence *fence)
+{
+ uint64_t seq[RADEON_NUM_RINGS] = {};
+ int r;
+
+ if (fence == NULL) {
+ WARN(1, "Querying an invalid fence : %p !\n", fence);
+ return -EINVAL;
+ }
+
+ seq[fence->ring] = fence->seq;
+ if (seq[fence->ring] == RADEON_FENCE_SIGNALED_SEQ)
+ return 0;
+
+ r = radeon_fence_wait_seq(fence->rdev, seq, false, false);
+ if (r)
+ return r;
+
+ fence->seq = RADEON_FENCE_SIGNALED_SEQ;
+ return 0;
+}
+
/**
* radeon_fence_wait_next_locked - wait for the next fence to signal
*
radeon_asic_vm_set_page(rdev, &ib, vm->pd_gpu_addr,
0, pd_entries, 0, 0);
- radeon_ib_sync_to(&ib, vm->fence);
+ radeon_semaphore_sync_to(ib.semaphore, vm->fence);
r = radeon_ib_schedule(rdev, &ib, NULL);
if (r) {
radeon_ib_free(rdev, &ib);
return -ENOMEM;
r = radeon_ib_get(rdev, R600_RING_TYPE_DMA_INDEX, &ib, NULL, ndw * 4);
+ if (r)
+ return r;
ib.length_dw = 0;
r = radeon_vm_update_pdes(rdev, vm, &ib, bo_va->soffset, bo_va->eoffset);
radeon_vm_update_ptes(rdev, vm, &ib, bo_va->soffset, bo_va->eoffset,
addr, radeon_vm_page_flags(bo_va->flags));
- radeon_ib_sync_to(&ib, vm->fence);
+ radeon_semaphore_sync_to(ib.semaphore, vm->fence);
r = radeon_ib_schedule(rdev, &ib, NULL);
if (r) {
radeon_ib_free(rdev, &ib);
break;
case RADEON_INFO_BACKEND_MAP:
if (rdev->family >= CHIP_BONAIRE)
- return -EINVAL;
+ *value = rdev->config.cik.backend_map;
else if (rdev->family >= CHIP_TAHITI)
*value = rdev->config.si.backend_map;
else if (rdev->family >= CHIP_CAYMAN)
return -EINVAL;
}
break;
+ case RADEON_INFO_CIK_MACROTILE_MODE_ARRAY:
+ if (rdev->family >= CHIP_BONAIRE) {
+ value = rdev->config.cik.macrotile_mode_array;
+ value_size = sizeof(uint32_t)*16;
+ } else {
+ DRM_DEBUG_KMS("macrotile mode array is cik+ only!\n");
+ return -EINVAL;
+ }
+ break;
case RADEON_INFO_SI_CP_DMA_COMPUTE:
*value = 1;
break;
/* Pin framebuffer & get tilling informations */
obj = radeon_fb->obj;
rbo = gem_to_radeon_bo(obj);
+retry:
r = radeon_bo_reserve(rbo, false);
if (unlikely(r != 0))
return r;
&base);
if (unlikely(r != 0)) {
radeon_bo_unreserve(rbo);
+
+ /* On old GPU like RN50 with little vram pining can fails because
+ * current fb is taking all space needed. So instead of unpining
+ * the old buffer after pining the new one, first unpin old one
+ * and then retry pining new one.
+ *
+ * As only master can set mode only master can pin and it is
+ * unlikely the master client will race with itself especialy
+ * on those old gpu with single crtc.
+ *
+ * We don't shutdown the display controller because new buffer
+ * will end up in same spot.
+ */
+ if (!atomic && fb && fb != crtc->fb) {
+ struct radeon_bo *old_rbo;
+ unsigned long nsize, osize;
+
+ old_rbo = gem_to_radeon_bo(to_radeon_framebuffer(fb)->obj);
+ osize = radeon_bo_size(old_rbo);
+ nsize = radeon_bo_size(rbo);
+ if (nsize <= osize && !radeon_bo_reserve(old_rbo, false)) {
+ radeon_bo_unpin(old_rbo);
+ radeon_bo_unreserve(old_rbo);
+ fb = NULL;
+ goto retry;
+ }
+ }
return -EINVAL;
}
radeon_bo_get_tiling_flags(rbo, &tiling_flags, NULL);
case CHIP_RS780:
case CHIP_RS880:
case CHIP_CAYMAN:
- case CHIP_ARUBA:
case CHIP_BONAIRE:
case CHIP_KABINI:
case CHIP_KAVERI:
case CHIP_BARTS:
case CHIP_TURKS:
case CHIP_CAICOS:
+ case CHIP_ARUBA:
case CHIP_TAHITI:
case CHIP_PITCAIRN:
case CHIP_VERDE:
struct radeon_ib *ib, struct radeon_vm *vm,
unsigned size)
{
- int i, r;
+ int r;
r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo, &ib->sa_bo, size, 256, true);
if (r) {
ib->gpu_addr = radeon_sa_bo_gpu_addr(ib->sa_bo);
}
ib->is_const_ib = false;
- for (i = 0; i < RADEON_NUM_RINGS; ++i)
- ib->sync_to[i] = NULL;
return 0;
}
radeon_fence_unref(&ib->fence);
}
-/**
- * radeon_ib_sync_to - sync to fence before executing the IB
- *
- * @ib: IB object to add fence to
- * @fence: fence to sync to
- *
- * Sync to the fence before executing the IB
- */
-void radeon_ib_sync_to(struct radeon_ib *ib, struct radeon_fence *fence)
-{
- struct radeon_fence *other;
-
- if (!fence)
- return;
-
- other = ib->sync_to[fence->ring];
- ib->sync_to[fence->ring] = radeon_fence_later(fence, other);
-}
-
/**
* radeon_ib_schedule - schedule an IB (Indirect Buffer) on the ring
*
struct radeon_ib *const_ib)
{
struct radeon_ring *ring = &rdev->ring[ib->ring];
- bool need_sync = false;
- int i, r = 0;
+ int r = 0;
if (!ib->length_dw || !ring->ready) {
/* TODO: Nothings in the ib we should report. */
dev_err(rdev->dev, "scheduling IB failed (%d).\n", r);
return r;
}
- for (i = 0; i < RADEON_NUM_RINGS; ++i) {
- struct radeon_fence *fence = ib->sync_to[i];
- if (radeon_fence_need_sync(fence, ib->ring)) {
- need_sync = true;
- radeon_semaphore_sync_rings(rdev, ib->semaphore,
- fence->ring, ib->ring);
- radeon_fence_note_sync(fence, ib->ring);
- }
- }
- /* immediately free semaphore when we don't need to sync */
- if (!need_sync) {
- radeon_semaphore_free(rdev, &ib->semaphore, NULL);
+
+ /* sync with other rings */
+ r = radeon_semaphore_sync_rings(rdev, ib->semaphore, ib->ring);
+ if (r) {
+ dev_err(rdev->dev, "failed to sync rings (%d)\n", r);
+ radeon_ring_unlock_undo(rdev, ring);
+ return r;
}
+
/* if we can't remember our last VM flush then flush now! */
/* XXX figure out why we have to flush for every IB */
if (ib->vm /*&& !ib->vm->last_flush*/) {
*/
#include <drm/drmP.h>
#include "radeon.h"
-
+#include "radeon_trace.h"
int radeon_semaphore_create(struct radeon_device *rdev,
struct radeon_semaphore **semaphore)
{
- int r;
+ int i, r;
*semaphore = kmalloc(sizeof(struct radeon_semaphore), GFP_KERNEL);
if (*semaphore == NULL) {
(*semaphore)->waiters = 0;
(*semaphore)->gpu_addr = radeon_sa_bo_gpu_addr((*semaphore)->sa_bo);
*((uint64_t*)radeon_sa_bo_cpu_addr((*semaphore)->sa_bo)) = 0;
+
+ for (i = 0; i < RADEON_NUM_RINGS; ++i)
+ (*semaphore)->sync_to[i] = NULL;
+
return 0;
}
-void radeon_semaphore_emit_signal(struct radeon_device *rdev, int ring,
+bool radeon_semaphore_emit_signal(struct radeon_device *rdev, int ridx,
struct radeon_semaphore *semaphore)
{
- --semaphore->waiters;
- radeon_semaphore_ring_emit(rdev, ring, &rdev->ring[ring], semaphore, false);
+ struct radeon_ring *ring = &rdev->ring[ridx];
+
+ trace_radeon_semaphore_signale(ridx, semaphore);
+
+ if (radeon_semaphore_ring_emit(rdev, ridx, ring, semaphore, false)) {
+ --semaphore->waiters;
+
+ /* for debugging lockup only, used by sysfs debug files */
+ ring->last_semaphore_signal_addr = semaphore->gpu_addr;
+ return true;
+ }
+ return false;
}
-void radeon_semaphore_emit_wait(struct radeon_device *rdev, int ring,
+bool radeon_semaphore_emit_wait(struct radeon_device *rdev, int ridx,
struct radeon_semaphore *semaphore)
{
- ++semaphore->waiters;
- radeon_semaphore_ring_emit(rdev, ring, &rdev->ring[ring], semaphore, true);
+ struct radeon_ring *ring = &rdev->ring[ridx];
+
+ trace_radeon_semaphore_wait(ridx, semaphore);
+
+ if (radeon_semaphore_ring_emit(rdev, ridx, ring, semaphore, true)) {
+ ++semaphore->waiters;
+
+ /* for debugging lockup only, used by sysfs debug files */
+ ring->last_semaphore_wait_addr = semaphore->gpu_addr;
+ return true;
+ }
+ return false;
+}
+
+/**
+ * radeon_semaphore_sync_to - use the semaphore to sync to a fence
+ *
+ * @semaphore: semaphore object to add fence to
+ * @fence: fence to sync to
+ *
+ * Sync to the fence using this semaphore object
+ */
+void radeon_semaphore_sync_to(struct radeon_semaphore *semaphore,
+ struct radeon_fence *fence)
+{
+ struct radeon_fence *other;
+
+ if (!fence)
+ return;
+
+ other = semaphore->sync_to[fence->ring];
+ semaphore->sync_to[fence->ring] = radeon_fence_later(fence, other);
}
-/* caller must hold ring lock */
+/**
+ * radeon_semaphore_sync_rings - sync ring to all registered fences
+ *
+ * @rdev: radeon_device pointer
+ * @semaphore: semaphore object to use for sync
+ * @ring: ring that needs sync
+ *
+ * Ensure that all registered fences are signaled before letting
+ * the ring continue. The caller must hold the ring lock.
+ */
int radeon_semaphore_sync_rings(struct radeon_device *rdev,
struct radeon_semaphore *semaphore,
- int signaler, int waiter)
+ int ring)
{
- int r;
+ int i, r;
- /* no need to signal and wait on the same ring */
- if (signaler == waiter) {
- return 0;
- }
+ for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+ struct radeon_fence *fence = semaphore->sync_to[i];
- /* prevent GPU deadlocks */
- if (!rdev->ring[signaler].ready) {
- dev_err(rdev->dev, "Trying to sync to a disabled ring!");
- return -EINVAL;
- }
+ /* check if we really need to sync */
+ if (!radeon_fence_need_sync(fence, ring))
+ continue;
- r = radeon_ring_alloc(rdev, &rdev->ring[signaler], 8);
- if (r) {
- return r;
- }
- radeon_semaphore_emit_signal(rdev, signaler, semaphore);
- radeon_ring_commit(rdev, &rdev->ring[signaler]);
+ /* prevent GPU deadlocks */
+ if (!rdev->ring[i].ready) {
+ dev_err(rdev->dev, "Syncing to a disabled ring!");
+ return -EINVAL;
+ }
- /* we assume caller has already allocated space on waiters ring */
- radeon_semaphore_emit_wait(rdev, waiter, semaphore);
+ /* allocate enough space for sync command */
+ r = radeon_ring_alloc(rdev, &rdev->ring[i], 16);
+ if (r) {
+ return r;
+ }
- /* for debugging lockup only, used by sysfs debug files */
- rdev->ring[signaler].last_semaphore_signal_addr = semaphore->gpu_addr;
- rdev->ring[waiter].last_semaphore_wait_addr = semaphore->gpu_addr;
+ /* emit the signal semaphore */
+ if (!radeon_semaphore_emit_signal(rdev, i, semaphore)) {
+ /* signaling wasn't successful wait manually */
+ radeon_ring_undo(&rdev->ring[i]);
+ radeon_fence_wait_locked(fence);
+ continue;
+ }
+
+ /* we assume caller has already allocated space on waiters ring */
+ if (!radeon_semaphore_emit_wait(rdev, ring, semaphore)) {
+ /* waiting wasn't successful wait manually */
+ radeon_ring_undo(&rdev->ring[i]);
+ radeon_fence_wait_locked(fence);
+ continue;
+ }
+
+ radeon_ring_commit(rdev, &rdev->ring[i]);
+ radeon_fence_note_sync(fence, ring);
+ }
return 0;
}
TP_ARGS(dev, seqno)
);
+DECLARE_EVENT_CLASS(radeon_semaphore_request,
+
+ TP_PROTO(int ring, struct radeon_semaphore *sem),
+
+ TP_ARGS(ring, sem),
+
+ TP_STRUCT__entry(
+ __field(int, ring)
+ __field(signed, waiters)
+ __field(uint64_t, gpu_addr)
+ ),
+
+ TP_fast_assign(
+ __entry->ring = ring;
+ __entry->waiters = sem->waiters;
+ __entry->gpu_addr = sem->gpu_addr;
+ ),
+
+ TP_printk("ring=%u, waiters=%d, addr=%010Lx", __entry->ring,
+ __entry->waiters, __entry->gpu_addr)
+);
+
+DEFINE_EVENT(radeon_semaphore_request, radeon_semaphore_signale,
+
+ TP_PROTO(int ring, struct radeon_semaphore *sem),
+
+ TP_ARGS(ring, sem)
+);
+
+DEFINE_EVENT(radeon_semaphore_request, radeon_semaphore_wait,
+
+ TP_PROTO(int ring, struct radeon_semaphore *sem),
+
+ TP_ARGS(ring, sem)
+);
+
#endif
/* This part must be outside protection */
return r;
}
- if (radeon_fence_need_sync(*fence, ring->idx)) {
- radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
- ring->idx);
- radeon_fence_note_sync(*fence, ring->idx);
- } else {
- radeon_semaphore_free(rdev, &sem, NULL);
- }
+ radeon_semaphore_sync_to(sem, *fence);
+ radeon_semaphore_sync_rings(rdev, sem, ring->idx);
for (i = 0; i < num_loops; i++) {
cur_size_in_dw = size_in_dw;
return r;
}
- if (radeon_fence_need_sync(*fence, ring->idx)) {
- radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
- ring->idx);
- radeon_fence_note_sync(*fence, ring->idx);
- } else {
- radeon_semaphore_free(rdev, &sem, NULL);
- }
+ radeon_semaphore_sync_to(sem, *fence);
+ radeon_semaphore_sync_rings(rdev, sem, ring->idx);
for (i = 0; i < num_loops; i++) {
cur_size_in_bytes = size_in_bytes;
pi->enable_sclk_ds = true;
pi->enable_gfx_power_gating = true;
pi->enable_gfx_clock_gating = true;
- pi->enable_mg_clock_gating = true;
- pi->enable_gfx_dynamic_mgpg = true; /* ??? */
- pi->override_dynamic_mgpg = true;
+ pi->enable_mg_clock_gating = false;
+ pi->enable_gfx_dynamic_mgpg = false;
+ pi->override_dynamic_mgpg = false;
pi->enable_auto_thermal_throttling = true;
pi->voltage_drop_in_dce = false; /* need to restructure dpm/modeset interaction */
pi->uvd_dpm = true; /* ??? */
*
* Emit a semaphore command (either wait or signal) to the UVD ring.
*/
-void uvd_v1_0_semaphore_emit(struct radeon_device *rdev,
+bool uvd_v1_0_semaphore_emit(struct radeon_device *rdev,
struct radeon_ring *ring,
struct radeon_semaphore *semaphore,
bool emit_wait)
radeon_ring_write(ring, PACKET0(UVD_SEMA_CMD, 0));
radeon_ring_write(ring, emit_wait ? 1 : 0);
+
+ return true;
}
/**
*
* Emit a semaphore command (either wait or signal) to the UVD ring.
*/
-void uvd_v3_1_semaphore_emit(struct radeon_device *rdev,
+bool uvd_v3_1_semaphore_emit(struct radeon_device *rdev,
struct radeon_ring *ring,
struct radeon_semaphore *semaphore,
bool emit_wait)
radeon_ring_write(ring, PACKET0(UVD_SEMA_CMD, 0));
radeon_ring_write(ring, 0x80 | (emit_wait ? 1 : 0));
+
+ return true;
}
atomic_dec(&bo->glob->bo_count);
if (bo->resv == &bo->ttm_resv)
reservation_object_fini(&bo->ttm_resv);
-
+ mutex_destroy(&bo->wu_mutex);
if (bo->destroy)
bo->destroy(bo);
else {
INIT_LIST_HEAD(&bo->ddestroy);
INIT_LIST_HEAD(&bo->swap);
INIT_LIST_HEAD(&bo->io_reserve_lru);
+ mutex_init(&bo->wu_mutex);
bo->bdev = bdev;
bo->glob = bdev->glob;
bo->type = type;
;
}
EXPORT_SYMBOL(ttm_bo_swapout_all);
+
+/**
+ * ttm_bo_wait_unreserved - interruptible wait for a buffer object to become
+ * unreserved
+ *
+ * @bo: Pointer to buffer
+ */
+int ttm_bo_wait_unreserved(struct ttm_buffer_object *bo)
+{
+ int ret;
+
+ /*
+ * In the absense of a wait_unlocked API,
+ * Use the bo::wu_mutex to avoid triggering livelocks due to
+ * concurrent use of this function. Note that this use of
+ * bo::wu_mutex can go away if we change locking order to
+ * mmap_sem -> bo::reserve.
+ */
+ ret = mutex_lock_interruptible(&bo->wu_mutex);
+ if (unlikely(ret != 0))
+ return -ERESTARTSYS;
+ if (!ww_mutex_is_locked(&bo->resv->lock))
+ goto out_unlock;
+ ret = ttm_bo_reserve_nolru(bo, true, false, false, NULL);
+ if (unlikely(ret != 0))
+ goto out_unlock;
+ ww_mutex_unlock(&bo->resv->lock);
+
+out_unlock:
+ mutex_unlock(&bo->wu_mutex);
+ return ret;
+}
goto out2;
/*
- * Move nonexistent data. NOP.
+ * Don't move nonexistent data. Clear destination instead.
*/
- if (old_iomap == NULL && ttm == NULL)
+ if (old_iomap == NULL &&
+ (ttm == NULL || ttm->state == tt_unpopulated)) {
+ memset_io(new_iomap, 0, new_mem->num_pages*PAGE_SIZE);
goto out2;
+ }
/*
* TTM might be null for moves within the same region.
/*
* Work around locking order reversal in fault / nopfn
* between mmap_sem and bo_reserve: Perform a trylock operation
- * for reserve, and if it fails, retry the fault after scheduling.
+ * for reserve, and if it fails, retry the fault after waiting
+ * for the buffer to become unreserved.
*/
-
- ret = ttm_bo_reserve(bo, true, true, false, 0);
+ ret = ttm_bo_reserve(bo, true, true, false, NULL);
if (unlikely(ret != 0)) {
- if (ret == -EBUSY)
- set_need_resched();
+ if (ret != -EBUSY)
+ return VM_FAULT_NOPAGE;
+
+ if (vmf->flags & FAULT_FLAG_ALLOW_RETRY) {
+ if (!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
+ up_read(&vma->vm_mm->mmap_sem);
+ (void) ttm_bo_wait_unreserved(bo);
+ }
+
+ return VM_FAULT_RETRY;
+ }
+
+ /*
+ * If we'd want to change locking order to
+ * mmap_sem -> bo::reserve, we'd use a blocking reserve here
+ * instead of retrying the fault...
+ */
return VM_FAULT_NOPAGE;
}
case 0:
break;
case -EBUSY:
- set_need_resched();
case -ERESTARTSYS:
retval = VM_FAULT_NOPAGE;
goto out_unlock;
#include <linux/sched.h>
#include <linux/module.h>
-static void ttm_eu_backoff_reservation_locked(struct list_head *list,
- struct ww_acquire_ctx *ticket)
+static void ttm_eu_backoff_reservation_locked(struct list_head *list)
{
struct ttm_validate_buffer *entry;
entry = list_first_entry(list, struct ttm_validate_buffer, head);
glob = entry->bo->glob;
spin_lock(&glob->lru_lock);
- ttm_eu_backoff_reservation_locked(list, ticket);
- ww_acquire_fini(ticket);
+ ttm_eu_backoff_reservation_locked(list);
+ if (ticket)
+ ww_acquire_fini(ticket);
spin_unlock(&glob->lru_lock);
}
EXPORT_SYMBOL(ttm_eu_backoff_reservation);
entry = list_first_entry(list, struct ttm_validate_buffer, head);
glob = entry->bo->glob;
- ww_acquire_init(ticket, &reservation_ww_class);
+ if (ticket)
+ ww_acquire_init(ticket, &reservation_ww_class);
retry:
list_for_each_entry(entry, list, head) {
struct ttm_buffer_object *bo = entry->bo;
if (entry->reserved)
continue;
-
- ret = ttm_bo_reserve_nolru(bo, true, false, true, ticket);
+ ret = ttm_bo_reserve_nolru(bo, true, (ticket == NULL), true,
+ ticket);
if (ret == -EDEADLK) {
/* uh oh, we lost out, drop every reservation and try
* to only reserve this buffer, then start over if
* this succeeds.
*/
+ BUG_ON(ticket == NULL);
spin_lock(&glob->lru_lock);
- ttm_eu_backoff_reservation_locked(list, ticket);
+ ttm_eu_backoff_reservation_locked(list);
spin_unlock(&glob->lru_lock);
ttm_eu_list_ref_sub(list);
ret = ww_mutex_lock_slow_interruptible(&bo->resv->lock,
}
}
- ww_acquire_done(ticket);
+ if (ticket)
+ ww_acquire_done(ticket);
spin_lock(&glob->lru_lock);
ttm_eu_del_from_lru_locked(list);
spin_unlock(&glob->lru_lock);
err:
spin_lock(&glob->lru_lock);
- ttm_eu_backoff_reservation_locked(list, ticket);
+ ttm_eu_backoff_reservation_locked(list);
spin_unlock(&glob->lru_lock);
ttm_eu_list_ref_sub(list);
err_fini:
- ww_acquire_done(ticket);
- ww_acquire_fini(ticket);
+ if (ticket) {
+ ww_acquire_done(ticket);
+ ww_acquire_fini(ticket);
+ }
return ret;
}
EXPORT_SYMBOL(ttm_eu_reserve_buffers);
}
spin_unlock(&bdev->fence_lock);
spin_unlock(&glob->lru_lock);
- ww_acquire_fini(ticket);
+ if (ticket)
+ ww_acquire_fini(ticket);
list_for_each_entry(entry, list, head) {
if (entry->old_sync_obj)
/**************************************************************************
*
- * Copyright (c) 2009 VMware, Inc., Palo Alto, CA., USA
+ * Copyright (c) 2009-2013 VMware, Inc., Palo Alto, CA., USA
* All Rights Reserved.
*
* Permission is hereby granted, free of charge, to any person obtaining a
**************************************************************************/
/*
* Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com>
+ *
+ * While no substantial code is shared, the prime code is inspired by
+ * drm_prime.c, with
+ * Authors:
+ * Dave Airlie <airlied@redhat.com>
+ * Rob Clark <rob.clark@linaro.org>
*/
/** @file ttm_ref_object.c
*
* and release on file close.
*/
+
/**
* struct ttm_object_file
*
struct drm_open_hash object_hash;
atomic_t object_count;
struct ttm_mem_global *mem_glob;
+ struct dma_buf_ops ops;
+ void (*dmabuf_release)(struct dma_buf *dma_buf);
+ size_t dma_buf_size;
};
/**
struct ttm_object_file *tfile;
};
+static void ttm_prime_dmabuf_release(struct dma_buf *dma_buf);
+
static inline struct ttm_object_file *
ttm_object_file_ref(struct ttm_object_file *tfile)
{
}
EXPORT_SYMBOL(ttm_object_file_init);
-struct ttm_object_device *ttm_object_device_init(struct ttm_mem_global
- *mem_glob,
- unsigned int hash_order)
+struct ttm_object_device *
+ttm_object_device_init(struct ttm_mem_global *mem_glob,
+ unsigned int hash_order,
+ const struct dma_buf_ops *ops)
{
struct ttm_object_device *tdev = kmalloc(sizeof(*tdev), GFP_KERNEL);
int ret;
spin_lock_init(&tdev->object_lock);
atomic_set(&tdev->object_count, 0);
ret = drm_ht_create(&tdev->object_hash, hash_order);
+ if (ret != 0)
+ goto out_no_object_hash;
- if (likely(ret == 0))
- return tdev;
+ tdev->ops = *ops;
+ tdev->dmabuf_release = tdev->ops.release;
+ tdev->ops.release = ttm_prime_dmabuf_release;
+ tdev->dma_buf_size = ttm_round_pot(sizeof(struct dma_buf)) +
+ ttm_round_pot(sizeof(struct file));
+ return tdev;
+out_no_object_hash:
kfree(tdev);
return NULL;
}
kfree(tdev);
}
EXPORT_SYMBOL(ttm_object_device_release);
+
+/**
+ * get_dma_buf_unless_doomed - get a dma_buf reference if possible.
+ *
+ * @dma_buf: Non-refcounted pointer to a struct dma-buf.
+ *
+ * Obtain a file reference from a lookup structure that doesn't refcount
+ * the file, but synchronizes with its release method to make sure it has
+ * not been freed yet. See for example kref_get_unless_zero documentation.
+ * Returns true if refcounting succeeds, false otherwise.
+ *
+ * Nobody really wants this as a public API yet, so let it mature here
+ * for some time...
+ */
+static bool __must_check get_dma_buf_unless_doomed(struct dma_buf *dmabuf)
+{
+ return atomic_long_inc_not_zero(&dmabuf->file->f_count) != 0L;
+}
+
+/**
+ * ttm_prime_refcount_release - refcount release method for a prime object.
+ *
+ * @p_base: Pointer to ttm_base_object pointer.
+ *
+ * This is a wrapper that calls the refcount_release founction of the
+ * underlying object. At the same time it cleans up the prime object.
+ * This function is called when all references to the base object we
+ * derive from are gone.
+ */
+static void ttm_prime_refcount_release(struct ttm_base_object **p_base)
+{
+ struct ttm_base_object *base = *p_base;
+ struct ttm_prime_object *prime;
+
+ *p_base = NULL;
+ prime = container_of(base, struct ttm_prime_object, base);
+ BUG_ON(prime->dma_buf != NULL);
+ mutex_destroy(&prime->mutex);
+ if (prime->refcount_release)
+ prime->refcount_release(&base);
+}
+
+/**
+ * ttm_prime_dmabuf_release - Release method for the dma-bufs we export
+ *
+ * @dma_buf:
+ *
+ * This function first calls the dma_buf release method the driver
+ * provides. Then it cleans up our dma_buf pointer used for lookup,
+ * and finally releases the reference the dma_buf has on our base
+ * object.
+ */
+static void ttm_prime_dmabuf_release(struct dma_buf *dma_buf)
+{
+ struct ttm_prime_object *prime =
+ (struct ttm_prime_object *) dma_buf->priv;
+ struct ttm_base_object *base = &prime->base;
+ struct ttm_object_device *tdev = base->tfile->tdev;
+
+ if (tdev->dmabuf_release)
+ tdev->dmabuf_release(dma_buf);
+ mutex_lock(&prime->mutex);
+ if (prime->dma_buf == dma_buf)
+ prime->dma_buf = NULL;
+ mutex_unlock(&prime->mutex);
+ ttm_mem_global_free(tdev->mem_glob, tdev->dma_buf_size);
+ ttm_base_object_unref(&base);
+}
+
+/**
+ * ttm_prime_fd_to_handle - Get a base object handle from a prime fd
+ *
+ * @tfile: A struct ttm_object_file identifying the caller.
+ * @fd: The prime / dmabuf fd.
+ * @handle: The returned handle.
+ *
+ * This function returns a handle to an object that previously exported
+ * a dma-buf. Note that we don't handle imports yet, because we simply
+ * have no consumers of that implementation.
+ */
+int ttm_prime_fd_to_handle(struct ttm_object_file *tfile,
+ int fd, u32 *handle)
+{
+ struct ttm_object_device *tdev = tfile->tdev;
+ struct dma_buf *dma_buf;
+ struct ttm_prime_object *prime;
+ struct ttm_base_object *base;
+ int ret;
+
+ dma_buf = dma_buf_get(fd);
+ if (IS_ERR(dma_buf))
+ return PTR_ERR(dma_buf);
+
+ if (dma_buf->ops != &tdev->ops)
+ return -ENOSYS;
+
+ prime = (struct ttm_prime_object *) dma_buf->priv;
+ base = &prime->base;
+ *handle = base->hash.key;
+ ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL);
+
+ dma_buf_put(dma_buf);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(ttm_prime_fd_to_handle);
+
+/**
+ * ttm_prime_handle_to_fd - Return a dma_buf fd from a ttm prime object
+ *
+ * @tfile: Struct ttm_object_file identifying the caller.
+ * @handle: Handle to the object we're exporting from.
+ * @flags: flags for dma-buf creation. We just pass them on.
+ * @prime_fd: The returned file descriptor.
+ *
+ */
+int ttm_prime_handle_to_fd(struct ttm_object_file *tfile,
+ uint32_t handle, uint32_t flags,
+ int *prime_fd)
+{
+ struct ttm_object_device *tdev = tfile->tdev;
+ struct ttm_base_object *base;
+ struct dma_buf *dma_buf;
+ struct ttm_prime_object *prime;
+ int ret;
+
+ base = ttm_base_object_lookup(tfile, handle);
+ if (unlikely(base == NULL ||
+ base->object_type != ttm_prime_type)) {
+ ret = -ENOENT;
+ goto out_unref;
+ }
+
+ prime = container_of(base, struct ttm_prime_object, base);
+ if (unlikely(!base->shareable)) {
+ ret = -EPERM;
+ goto out_unref;
+ }
+
+ ret = mutex_lock_interruptible(&prime->mutex);
+ if (unlikely(ret != 0)) {
+ ret = -ERESTARTSYS;
+ goto out_unref;
+ }
+
+ dma_buf = prime->dma_buf;
+ if (!dma_buf || !get_dma_buf_unless_doomed(dma_buf)) {
+
+ /*
+ * Need to create a new dma_buf, with memory accounting.
+ */
+ ret = ttm_mem_global_alloc(tdev->mem_glob, tdev->dma_buf_size,
+ false, true);
+ if (unlikely(ret != 0)) {
+ mutex_unlock(&prime->mutex);
+ goto out_unref;
+ }
+
+ dma_buf = dma_buf_export(prime, &tdev->ops,
+ prime->size, flags);
+ if (IS_ERR(dma_buf)) {
+ ret = PTR_ERR(dma_buf);
+ ttm_mem_global_free(tdev->mem_glob,
+ tdev->dma_buf_size);
+ mutex_unlock(&prime->mutex);
+ goto out_unref;
+ }
+
+ /*
+ * dma_buf has taken the base object reference
+ */
+ base = NULL;
+ prime->dma_buf = dma_buf;
+ }
+ mutex_unlock(&prime->mutex);
+
+ ret = dma_buf_fd(dma_buf, flags);
+ if (ret >= 0) {
+ *prime_fd = ret;
+ ret = 0;
+ } else
+ dma_buf_put(dma_buf);
+
+out_unref:
+ if (base)
+ ttm_base_object_unref(&base);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(ttm_prime_handle_to_fd);
+
+/**
+ * ttm_prime_object_init - Initialize a ttm_prime_object
+ *
+ * @tfile: struct ttm_object_file identifying the caller
+ * @size: The size of the dma_bufs we export.
+ * @prime: The object to be initialized.
+ * @shareable: See ttm_base_object_init
+ * @type: See ttm_base_object_init
+ * @refcount_release: See ttm_base_object_init
+ * @ref_obj_release: See ttm_base_object_init
+ *
+ * Initializes an object which is compatible with the drm_prime model
+ * for data sharing between processes and devices.
+ */
+int ttm_prime_object_init(struct ttm_object_file *tfile, size_t size,
+ struct ttm_prime_object *prime, bool shareable,
+ enum ttm_object_type type,
+ void (*refcount_release) (struct ttm_base_object **),
+ void (*ref_obj_release) (struct ttm_base_object *,
+ enum ttm_ref_type ref_type))
+{
+ mutex_init(&prime->mutex);
+ prime->size = PAGE_ALIGN(size);
+ prime->real_type = type;
+ prime->dma_buf = NULL;
+ prime->refcount_release = refcount_release;
+ return ttm_base_object_init(tfile, &prime->base, shareable,
+ ttm_prime_type,
+ ttm_prime_refcount_release,
+ ref_obj_release);
+}
+EXPORT_SYMBOL(ttm_prime_object_init);
vmwgfx_fifo.o vmwgfx_irq.o vmwgfx_ldu.o vmwgfx_ttm_glue.o \
vmwgfx_overlay.o vmwgfx_marker.o vmwgfx_gmrid_manager.o \
vmwgfx_fence.o vmwgfx_dmabuf.o vmwgfx_scrn.o vmwgfx_context.o \
- vmwgfx_surface.o
+ vmwgfx_surface.o vmwgfx_prime.o
obj-$(CONFIG_DRM_VMWGFX) := vmwgfx.o
}
dev_priv->tdev = ttm_object_device_init
- (dev_priv->mem_global_ref.object, 12);
+ (dev_priv->mem_global_ref.object, 12, &vmw_prime_dmabuf_ops);
if (unlikely(dev_priv->tdev == NULL)) {
DRM_ERROR("Unable to initialize TTM object management.\n");
static struct drm_driver driver = {
.driver_features = DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED |
- DRIVER_MODESET,
+ DRIVER_MODESET | DRIVER_PRIME,
.load = vmw_driver_load,
.unload = vmw_driver_unload,
.lastclose = vmw_lastclose,
.dumb_map_offset = vmw_dumb_map_offset,
.dumb_destroy = vmw_dumb_destroy,
+ .prime_fd_to_handle = vmw_prime_fd_to_handle,
+ .prime_handle_to_fd = vmw_prime_handle_to_fd,
+
.fops = &vmwgfx_driver_fops,
.name = VMWGFX_DRIVER_NAME,
.desc = VMWGFX_DRIVER_DESC,
extern const struct ttm_mem_type_manager_func vmw_gmrid_manager_func;
+/**
+ * Prime - vmwgfx_prime.c
+ */
+
+extern const struct dma_buf_ops vmw_prime_dmabuf_ops;
+extern int vmw_prime_fd_to_handle(struct drm_device *dev,
+ struct drm_file *file_priv,
+ int fd, u32 *handle);
+extern int vmw_prime_handle_to_fd(struct drm_device *dev,
+ struct drm_file *file_priv,
+ uint32_t handle, uint32_t flags,
+ int *prime_fd);
+
+
/**
* Inline helper functions
*/
--- /dev/null
+/**************************************************************************
+ *
+ * Copyright © 2013 VMware, Inc., Palo Alto, CA., USA
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ **************************************************************************/
+/*
+ * Authors:
+ * Thomas Hellstrom <thellstrom@vmware.com>
+ *
+ */
+
+#include "vmwgfx_drv.h"
+#include <linux/dma-buf.h>
+#include <drm/ttm/ttm_object.h>
+
+/*
+ * DMA-BUF attach- and mapping methods. No need to implement
+ * these until we have other virtual devices use them.
+ */
+
+static int vmw_prime_map_attach(struct dma_buf *dma_buf,
+ struct device *target_dev,
+ struct dma_buf_attachment *attach)
+{
+ return -ENOSYS;
+}
+
+static void vmw_prime_map_detach(struct dma_buf *dma_buf,
+ struct dma_buf_attachment *attach)
+{
+}
+
+static struct sg_table *vmw_prime_map_dma_buf(struct dma_buf_attachment *attach,
+ enum dma_data_direction dir)
+{
+ return ERR_PTR(-ENOSYS);
+}
+
+static void vmw_prime_unmap_dma_buf(struct dma_buf_attachment *attach,
+ struct sg_table *sgb,
+ enum dma_data_direction dir)
+{
+}
+
+static void *vmw_prime_dmabuf_vmap(struct dma_buf *dma_buf)
+{
+ return NULL;
+}
+
+static void vmw_prime_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
+{
+}
+
+static void *vmw_prime_dmabuf_kmap_atomic(struct dma_buf *dma_buf,
+ unsigned long page_num)
+{
+ return NULL;
+}
+
+static void vmw_prime_dmabuf_kunmap_atomic(struct dma_buf *dma_buf,
+ unsigned long page_num, void *addr)
+{
+
+}
+static void *vmw_prime_dmabuf_kmap(struct dma_buf *dma_buf,
+ unsigned long page_num)
+{
+ return NULL;
+}
+
+static void vmw_prime_dmabuf_kunmap(struct dma_buf *dma_buf,
+ unsigned long page_num, void *addr)
+{
+
+}
+
+static int vmw_prime_dmabuf_mmap(struct dma_buf *dma_buf,
+ struct vm_area_struct *vma)
+{
+ WARN_ONCE(true, "Attempted use of dmabuf mmap. Bad.\n");
+ return -ENOSYS;
+}
+
+const struct dma_buf_ops vmw_prime_dmabuf_ops = {
+ .attach = vmw_prime_map_attach,
+ .detach = vmw_prime_map_detach,
+ .map_dma_buf = vmw_prime_map_dma_buf,
+ .unmap_dma_buf = vmw_prime_unmap_dma_buf,
+ .release = NULL,
+ .kmap = vmw_prime_dmabuf_kmap,
+ .kmap_atomic = vmw_prime_dmabuf_kmap_atomic,
+ .kunmap = vmw_prime_dmabuf_kunmap,
+ .kunmap_atomic = vmw_prime_dmabuf_kunmap_atomic,
+ .mmap = vmw_prime_dmabuf_mmap,
+ .vmap = vmw_prime_dmabuf_vmap,
+ .vunmap = vmw_prime_dmabuf_vunmap,
+};
+
+int vmw_prime_fd_to_handle(struct drm_device *dev,
+ struct drm_file *file_priv,
+ int fd, u32 *handle)
+{
+ struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+
+ return ttm_prime_fd_to_handle(tfile, fd, handle);
+}
+
+int vmw_prime_handle_to_fd(struct drm_device *dev,
+ struct drm_file *file_priv,
+ uint32_t handle, uint32_t flags,
+ int *prime_fd)
+{
+ struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+
+ return ttm_prime_handle_to_fd(tfile, handle, flags, prime_fd);
+}
#define VMW_RES_EVICT_ERR_COUNT 10
struct vmw_user_dma_buffer {
- struct ttm_base_object base;
+ struct ttm_prime_object prime;
struct vmw_dma_buffer dma;
};
if (unlikely(base == NULL))
return -EINVAL;
- if (unlikely(base->object_type != converter->object_type))
+ if (unlikely(ttm_base_object_type(base) != converter->object_type))
goto out_bad_resource;
res = converter->base_obj_to_res(base);
{
struct vmw_user_dma_buffer *vmw_user_bo = vmw_user_dma_buffer(bo);
- ttm_base_object_kfree(vmw_user_bo, base);
+ ttm_prime_object_kfree(vmw_user_bo, prime);
}
static void vmw_user_dmabuf_release(struct ttm_base_object **p_base)
if (unlikely(base == NULL))
return;
- vmw_user_bo = container_of(base, struct vmw_user_dma_buffer, base);
+ vmw_user_bo = container_of(base, struct vmw_user_dma_buffer,
+ prime.base);
bo = &vmw_user_bo->dma.base;
ttm_bo_unref(&bo);
}
return ret;
tmp = ttm_bo_reference(&user_bo->dma.base);
- ret = ttm_base_object_init(tfile,
- &user_bo->base,
- shareable,
- ttm_buffer_type,
- &vmw_user_dmabuf_release, NULL);
+ ret = ttm_prime_object_init(tfile,
+ size,
+ &user_bo->prime,
+ shareable,
+ ttm_buffer_type,
+ &vmw_user_dmabuf_release, NULL);
if (unlikely(ret != 0)) {
ttm_bo_unref(&tmp);
goto out_no_base_object;
}
*p_dma_buf = &user_bo->dma;
- *handle = user_bo->base.hash.key;
+ *handle = user_bo->prime.base.hash.key;
out_no_base_object:
return ret;
return -EPERM;
vmw_user_bo = vmw_user_dma_buffer(bo);
- return (vmw_user_bo->base.tfile == tfile ||
- vmw_user_bo->base.shareable) ? 0 : -EPERM;
+ return (vmw_user_bo->prime.base.tfile == tfile ||
+ vmw_user_bo->prime.base.shareable) ? 0 : -EPERM;
}
int vmw_dmabuf_alloc_ioctl(struct drm_device *dev, void *data,
return -ESRCH;
}
- if (unlikely(base->object_type != ttm_buffer_type)) {
+ if (unlikely(ttm_base_object_type(base) != ttm_buffer_type)) {
ttm_base_object_unref(&base);
printk(KERN_ERR "Invalid buffer object handle 0x%08lx.\n",
(unsigned long)handle);
return -EINVAL;
}
- vmw_user_bo = container_of(base, struct vmw_user_dma_buffer, base);
+ vmw_user_bo = container_of(base, struct vmw_user_dma_buffer,
+ prime.base);
(void)ttm_bo_reference(&vmw_user_bo->dma.base);
ttm_base_object_unref(&base);
*out = &vmw_user_bo->dma;
return -EINVAL;
user_bo = container_of(dma_buf, struct vmw_user_dma_buffer, dma);
- return ttm_ref_object_add(tfile, &user_bo->base, TTM_REF_USAGE, NULL);
+ return ttm_ref_object_add(tfile, &user_bo->prime.base,
+ TTM_REF_USAGE, NULL);
}
/*
goto out_no_dmabuf;
tmp = ttm_bo_reference(&vmw_user_bo->dma.base);
- ret = ttm_base_object_init(vmw_fpriv(file_priv)->tfile,
- &vmw_user_bo->base,
- false,
- ttm_buffer_type,
- &vmw_user_dmabuf_release, NULL);
+ ret = ttm_prime_object_init(vmw_fpriv(file_priv)->tfile,
+ args->size,
+ &vmw_user_bo->prime,
+ false,
+ ttm_buffer_type,
+ &vmw_user_dmabuf_release, NULL);
if (unlikely(ret != 0))
goto out_no_base_object;
- args->handle = vmw_user_bo->base.hash.key;
+ args->handle = vmw_user_bo->prime.base.hash.key;
out_no_base_object:
ttm_bo_unref(&tmp);
*/
static int
vmw_resource_check_buffer(struct vmw_resource *res,
- struct ww_acquire_ctx *ticket,
bool interruptible,
struct ttm_validate_buffer *val_buf)
{
INIT_LIST_HEAD(&val_list);
val_buf->bo = ttm_bo_reference(&res->backup->base);
list_add_tail(&val_buf->head, &val_list);
- ret = ttm_eu_reserve_buffers(ticket, &val_list);
+ ret = ttm_eu_reserve_buffers(NULL, &val_list);
if (unlikely(ret != 0))
goto out_no_reserve;
return 0;
out_no_validate:
- ttm_eu_backoff_reservation(ticket, &val_list);
+ ttm_eu_backoff_reservation(NULL, &val_list);
out_no_reserve:
ttm_bo_unref(&val_buf->bo);
if (backup_dirty)
* @val_buf: Backup buffer information.
*/
static void
-vmw_resource_backoff_reservation(struct ww_acquire_ctx *ticket,
- struct ttm_validate_buffer *val_buf)
+vmw_resource_backoff_reservation(struct ttm_validate_buffer *val_buf)
{
struct list_head val_list;
INIT_LIST_HEAD(&val_list);
list_add_tail(&val_buf->head, &val_list);
- ttm_eu_backoff_reservation(ticket, &val_list);
+ ttm_eu_backoff_reservation(NULL, &val_list);
ttm_bo_unref(&val_buf->bo);
}
{
struct ttm_validate_buffer val_buf;
const struct vmw_res_func *func = res->func;
- struct ww_acquire_ctx ticket;
int ret;
BUG_ON(!func->may_evict);
val_buf.bo = NULL;
- ret = vmw_resource_check_buffer(res, &ticket, interruptible,
- &val_buf);
+ ret = vmw_resource_check_buffer(res, interruptible, &val_buf);
if (unlikely(ret != 0))
return ret;
res->backup_dirty = true;
res->res_dirty = false;
out_no_unbind:
- vmw_resource_backoff_reservation(&ticket, &val_buf);
+ vmw_resource_backoff_reservation(&val_buf);
return ret;
}
* @size: TTM accounting size for the surface.
*/
struct vmw_user_surface {
- struct ttm_base_object base;
+ struct ttm_prime_object prime;
struct vmw_surface srf;
uint32_t size;
uint32_t backup_handle;
static struct vmw_resource *
vmw_user_surface_base_to_res(struct ttm_base_object *base)
{
- return &(container_of(base, struct vmw_user_surface, base)->srf.res);
+ return &(container_of(base, struct vmw_user_surface,
+ prime.base)->srf.res);
}
/**
kfree(srf->offsets);
kfree(srf->sizes);
kfree(srf->snooper.image);
- ttm_base_object_kfree(user_srf, base);
+ ttm_prime_object_kfree(user_srf, prime);
ttm_mem_global_free(vmw_mem_glob(dev_priv), size);
}
{
struct ttm_base_object *base = *p_base;
struct vmw_user_surface *user_srf =
- container_of(base, struct vmw_user_surface, base);
+ container_of(base, struct vmw_user_surface, prime.base);
struct vmw_resource *res = &user_srf->srf.res;
*p_base = NULL;
}
srf->snooper.crtc = NULL;
- user_srf->base.shareable = false;
- user_srf->base.tfile = NULL;
+ user_srf->prime.base.shareable = false;
+ user_srf->prime.base.tfile = NULL;
/**
* From this point, the generic resource management functions
goto out_unlock;
tmp = vmw_resource_reference(&srf->res);
- ret = ttm_base_object_init(tfile, &user_srf->base,
- req->shareable, VMW_RES_SURFACE,
- &vmw_user_surface_base_release, NULL);
+ ret = ttm_prime_object_init(tfile, res->backup_size, &user_srf->prime,
+ req->shareable, VMW_RES_SURFACE,
+ &vmw_user_surface_base_release, NULL);
if (unlikely(ret != 0)) {
vmw_resource_unreference(&tmp);
goto out_unlock;
}
- rep->sid = user_srf->base.hash.key;
+ rep->sid = user_srf->prime.base.hash.key;
vmw_resource_unreference(&res);
ttm_read_unlock(&vmaster->lock);
out_no_offsets:
kfree(srf->sizes);
out_no_sizes:
- ttm_base_object_kfree(user_srf, base);
+ ttm_prime_object_kfree(user_srf, prime);
out_no_user_srf:
ttm_mem_global_free(vmw_mem_glob(dev_priv), size);
out_unlock:
return -EINVAL;
}
- if (unlikely(base->object_type != VMW_RES_SURFACE))
+ if (unlikely(ttm_base_object_type(base) != VMW_RES_SURFACE))
goto out_bad_resource;
- user_srf = container_of(base, struct vmw_user_surface, base);
+ user_srf = container_of(base, struct vmw_user_surface, prime.base);
srf = &user_srf->srf;
- ret = ttm_ref_object_add(tfile, &user_srf->base, TTM_REF_USAGE, NULL);
+ ret = ttm_ref_object_add(tfile, &user_srf->prime.base,
+ TTM_REF_USAGE, NULL);
if (unlikely(ret != 0)) {
DRM_ERROR("Could not add a reference to a surface.\n");
goto out_no_reference;
- Analog Devices ADT75
- Dallas Semiconductor DS75, DS1775 and DS7505
+ - Global Mixed-mode Technology (GMT) G751
- Maxim MAX6625 and MAX6626
- Microchip MCP980x
- National Semiconductor LM75, LM75A
/* Create a symlink to domain objects */
resource->domain_devices[i] = NULL;
- status = acpi_bus_get_device(element->reference.handle,
- &resource->domain_devices[i]);
- if (ACPI_FAILURE(status))
+ if (acpi_bus_get_device(element->reference.handle,
+ &resource->domain_devices[i]))
continue;
obj = resource->domain_devices[i];
ds1775,
ds75,
ds7505,
+ g751,
lm75,
lm75a,
max6625,
data->resolution = 12;
data->sample_time = HZ / 4;
break;
+ case g751:
case lm75:
case lm75a:
data->resolution = 9;
{ "ds1775", ds1775, },
{ "ds75", ds75, },
{ "ds7505", ds7505, },
+ { "g751", g751, },
{ "lm75", lm75, },
{ "lm75a", lm75a, },
{ "max6625", max6625, },
static const u16 NCT6775_REG_TEMP[] = {
0x27, 0x150, 0x250, 0x62b, 0x62c, 0x62d };
+static const u16 NCT6775_REG_TEMP_MON[] = { 0x73, 0x75, 0x77 };
+
static const u16 NCT6775_REG_TEMP_CONFIG[ARRAY_SIZE(NCT6775_REG_TEMP)] = {
0, 0x152, 0x252, 0x628, 0x629, 0x62A };
static const u16 NCT6775_REG_TEMP_HYST[ARRAY_SIZE(NCT6775_REG_TEMP)] = {
0x137, 0x237, 0x337, 0x837, 0x937, 0xa37 };
static const u16 NCT6779_REG_TEMP[] = { 0x27, 0x150 };
+static const u16 NCT6779_REG_TEMP_MON[] = { 0x73, 0x75, 0x77, 0x79, 0x7b };
static const u16 NCT6779_REG_TEMP_CONFIG[ARRAY_SIZE(NCT6779_REG_TEMP)] = {
0x18, 0x152 };
static const u16 NCT6779_REG_TEMP_HYST[ARRAY_SIZE(NCT6779_REG_TEMP)] = {
#define NCT6791_REG_HM_IO_SPACE_LOCK_ENABLE 0x28
+static const u16 NCT6791_REG_WEIGHT_TEMP_SEL[6] = { 0, 0x239 };
+static const u16 NCT6791_REG_WEIGHT_TEMP_STEP[6] = { 0, 0x23a };
+static const u16 NCT6791_REG_WEIGHT_TEMP_STEP_TOL[6] = { 0, 0x23b };
+static const u16 NCT6791_REG_WEIGHT_DUTY_STEP[6] = { 0, 0x23c };
+static const u16 NCT6791_REG_WEIGHT_TEMP_BASE[6] = { 0, 0x23d };
+static const u16 NCT6791_REG_WEIGHT_DUTY_BASE[6] = { 0, 0x23e };
+
static const u16 NCT6791_REG_ALARM[NUM_REG_ALARM] = {
0x459, 0x45A, 0x45B, 0x568, 0x45D };
0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x07, 0x08, 0x09 };
static const u16 NCT6106_REG_TEMP[] = { 0x10, 0x11, 0x12, 0x13, 0x14, 0x15 };
+static const u16 NCT6106_REG_TEMP_MON[] = { 0x18, 0x19, 0x1a };
static const u16 NCT6106_REG_TEMP_HYST[] = {
0xc3, 0xc7, 0xcb, 0xcf, 0xd3, 0xd7 };
static const u16 NCT6106_REG_TEMP_OVER[] = {
if (reg & 0x80)
data->pwm[2][i] = 0;
+ if (!data->REG_WEIGHT_TEMP_SEL[i])
+ continue;
+
reg = nct6775_read_value(data, data->REG_WEIGHT_TEMP_SEL[i]);
data->pwm_weight_temp_sel[i] = reg & 0x1f;
/* If weight is disabled, report weight source as 0 */
if (!(data->has_pwm & (1 << pwm)))
return 0;
+ if ((nr >= 14 && nr <= 18) || nr == 21) /* weight */
+ if (!data->REG_WEIGHT_TEMP_SEL[pwm])
+ return 0;
if (nr == 19 && data->REG_PWM[3] == NULL) /* pwm_max */
return 0;
if (nr == 20 && data->REG_PWM[4] == NULL) /* pwm_step */
&sensor_dev_template_pwm_step_down_time,
&sensor_dev_template_pwm_start,
&sensor_dev_template_pwm_floor,
- &sensor_dev_template_pwm_weight_temp_sel,
+ &sensor_dev_template_pwm_weight_temp_sel, /* 14 */
&sensor_dev_template_pwm_weight_temp_step,
&sensor_dev_template_pwm_weight_temp_step_tol,
&sensor_dev_template_pwm_weight_temp_step_base,
- &sensor_dev_template_pwm_weight_duty_step,
+ &sensor_dev_template_pwm_weight_duty_step, /* 18 */
&sensor_dev_template_pwm_max, /* 19 */
&sensor_dev_template_pwm_step, /* 20 */
&sensor_dev_template_pwm_weight_duty_base, /* 21 */
int i, s, err = 0;
int src, mask, available;
const u16 *reg_temp, *reg_temp_over, *reg_temp_hyst, *reg_temp_config;
- const u16 *reg_temp_alternate, *reg_temp_crit;
+ const u16 *reg_temp_mon, *reg_temp_alternate, *reg_temp_crit;
const u16 *reg_temp_crit_l = NULL, *reg_temp_crit_h = NULL;
- int num_reg_temp;
+ int num_reg_temp, num_reg_temp_mon;
u8 cr2a;
struct attribute_group *group;
struct device *hwmon_dev;
data->BEEP_BITS = NCT6106_BEEP_BITS;
reg_temp = NCT6106_REG_TEMP;
+ reg_temp_mon = NCT6106_REG_TEMP_MON;
num_reg_temp = ARRAY_SIZE(NCT6106_REG_TEMP);
+ num_reg_temp_mon = ARRAY_SIZE(NCT6106_REG_TEMP_MON);
reg_temp_over = NCT6106_REG_TEMP_OVER;
reg_temp_hyst = NCT6106_REG_TEMP_HYST;
reg_temp_config = NCT6106_REG_TEMP_CONFIG;
data->REG_BEEP = NCT6775_REG_BEEP;
reg_temp = NCT6775_REG_TEMP;
+ reg_temp_mon = NCT6775_REG_TEMP_MON;
num_reg_temp = ARRAY_SIZE(NCT6775_REG_TEMP);
+ num_reg_temp_mon = ARRAY_SIZE(NCT6775_REG_TEMP_MON);
reg_temp_over = NCT6775_REG_TEMP_OVER;
reg_temp_hyst = NCT6775_REG_TEMP_HYST;
reg_temp_config = NCT6775_REG_TEMP_CONFIG;
data->REG_BEEP = NCT6776_REG_BEEP;
reg_temp = NCT6775_REG_TEMP;
+ reg_temp_mon = NCT6775_REG_TEMP_MON;
num_reg_temp = ARRAY_SIZE(NCT6775_REG_TEMP);
+ num_reg_temp_mon = ARRAY_SIZE(NCT6775_REG_TEMP_MON);
reg_temp_over = NCT6775_REG_TEMP_OVER;
reg_temp_hyst = NCT6775_REG_TEMP_HYST;
reg_temp_config = NCT6776_REG_TEMP_CONFIG;
data->REG_BEEP = NCT6776_REG_BEEP;
reg_temp = NCT6779_REG_TEMP;
+ reg_temp_mon = NCT6779_REG_TEMP_MON;
num_reg_temp = ARRAY_SIZE(NCT6779_REG_TEMP);
+ num_reg_temp_mon = ARRAY_SIZE(NCT6779_REG_TEMP_MON);
reg_temp_over = NCT6779_REG_TEMP_OVER;
reg_temp_hyst = NCT6779_REG_TEMP_HYST;
reg_temp_config = NCT6779_REG_TEMP_CONFIG;
data->REG_PWM[0] = NCT6775_REG_PWM;
data->REG_PWM[1] = NCT6775_REG_FAN_START_OUTPUT;
data->REG_PWM[2] = NCT6775_REG_FAN_STOP_OUTPUT;
- data->REG_PWM[5] = NCT6775_REG_WEIGHT_DUTY_STEP;
- data->REG_PWM[6] = NCT6776_REG_WEIGHT_DUTY_BASE;
+ data->REG_PWM[5] = NCT6791_REG_WEIGHT_DUTY_STEP;
+ data->REG_PWM[6] = NCT6791_REG_WEIGHT_DUTY_BASE;
data->REG_PWM_READ = NCT6775_REG_PWM_READ;
data->REG_PWM_MODE = NCT6776_REG_PWM_MODE;
data->PWM_MODE_MASK = NCT6776_PWM_MODE_MASK;
data->REG_TEMP_OFFSET = NCT6779_REG_TEMP_OFFSET;
data->REG_TEMP_SOURCE = NCT6775_REG_TEMP_SOURCE;
data->REG_TEMP_SEL = NCT6775_REG_TEMP_SEL;
- data->REG_WEIGHT_TEMP_SEL = NCT6775_REG_WEIGHT_TEMP_SEL;
- data->REG_WEIGHT_TEMP[0] = NCT6775_REG_WEIGHT_TEMP_STEP;
- data->REG_WEIGHT_TEMP[1] = NCT6775_REG_WEIGHT_TEMP_STEP_TOL;
- data->REG_WEIGHT_TEMP[2] = NCT6775_REG_WEIGHT_TEMP_BASE;
+ data->REG_WEIGHT_TEMP_SEL = NCT6791_REG_WEIGHT_TEMP_SEL;
+ data->REG_WEIGHT_TEMP[0] = NCT6791_REG_WEIGHT_TEMP_STEP;
+ data->REG_WEIGHT_TEMP[1] = NCT6791_REG_WEIGHT_TEMP_STEP_TOL;
+ data->REG_WEIGHT_TEMP[2] = NCT6791_REG_WEIGHT_TEMP_BASE;
data->REG_ALARM = NCT6791_REG_ALARM;
data->REG_BEEP = NCT6776_REG_BEEP;
reg_temp = NCT6779_REG_TEMP;
+ reg_temp_mon = NCT6779_REG_TEMP_MON;
num_reg_temp = ARRAY_SIZE(NCT6779_REG_TEMP);
+ num_reg_temp_mon = ARRAY_SIZE(NCT6779_REG_TEMP_MON);
reg_temp_over = NCT6779_REG_TEMP_OVER;
reg_temp_hyst = NCT6779_REG_TEMP_HYST;
reg_temp_config = NCT6779_REG_TEMP_CONFIG;
s++;
}
+ /*
+ * Repeat with temperatures used for fan control.
+ * This set of registers does not support limits.
+ */
+ for (i = 0; i < num_reg_temp_mon; i++) {
+ if (reg_temp_mon[i] == 0)
+ continue;
+
+ src = nct6775_read_value(data, data->REG_TEMP_SEL[i]) & 0x1f;
+ if (!src || (mask & (1 << src)))
+ continue;
+
+ if (src >= data->temp_label_num ||
+ !strlen(data->temp_label[src])) {
+ dev_info(dev,
+ "Invalid temperature source %d at index %d, source register 0x%x, temp register 0x%x\n",
+ src, i, data->REG_TEMP_SEL[i],
+ reg_temp_mon[i]);
+ continue;
+ }
+
+ mask |= 1 << src;
+
+ /* Use fixed index for SYSTIN(1), CPUTIN(2), AUXTIN(3) */
+ if (src <= data->temp_fixed_num) {
+ if (data->have_temp & (1 << (src - 1)))
+ continue;
+ data->have_temp |= 1 << (src - 1);
+ data->have_temp_fixed |= 1 << (src - 1);
+ data->reg_temp[0][src - 1] = reg_temp_mon[i];
+ data->temp_src[src - 1] = src;
+ continue;
+ }
+
+ if (s >= NUM_TEMP)
+ continue;
+
+ /* Use dynamic index for other sources */
+ data->have_temp |= 1 << s;
+ data->reg_temp[0][s] = reg_temp_mon[i];
+ data->temp_src[s] = src;
+ s++;
+ }
+
#ifdef USE_ALTERNATE
/*
* Go through the list of alternate temp registers and enable
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/in6.h>
+#include <linux/llist.h>
#include <rdma/ib_verbs.h>
#include <rdma/rdma_cm.h>
#include <target/target_core_base.h>
kref_init(&isert_conn->conn_kref);
kref_get(&isert_conn->conn_kref);
mutex_init(&isert_conn->conn_mutex);
+ mutex_init(&isert_conn->conn_comp_mutex);
spin_lock_init(&isert_conn->conn_lock);
cma_id->context = isert_conn;
}
static void
-isert_init_send_wr(struct isert_cmd *isert_cmd, struct ib_send_wr *send_wr)
+isert_init_send_wr(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd,
+ struct ib_send_wr *send_wr, bool coalesce)
{
+ struct iser_tx_desc *tx_desc = &isert_cmd->tx_desc;
+
isert_cmd->rdma_wr.iser_ib_op = ISER_IB_SEND;
send_wr->wr_id = (unsigned long)&isert_cmd->tx_desc;
send_wr->opcode = IB_WR_SEND;
- send_wr->send_flags = IB_SEND_SIGNALED;
- send_wr->sg_list = &isert_cmd->tx_desc.tx_sg[0];
+ send_wr->sg_list = &tx_desc->tx_sg[0];
send_wr->num_sge = isert_cmd->tx_desc.num_sge;
+ /*
+ * Coalesce send completion interrupts by only setting IB_SEND_SIGNALED
+ * bit for every ISERT_COMP_BATCH_COUNT number of ib_post_send() calls.
+ */
+ mutex_lock(&isert_conn->conn_comp_mutex);
+ if (coalesce &&
+ ++isert_conn->conn_comp_batch < ISERT_COMP_BATCH_COUNT) {
+ llist_add(&tx_desc->comp_llnode, &isert_conn->conn_comp_llist);
+ mutex_unlock(&isert_conn->conn_comp_mutex);
+ return;
+ }
+ isert_conn->conn_comp_batch = 0;
+ tx_desc->comp_llnode_batch = llist_del_all(&isert_conn->conn_comp_llist);
+ mutex_unlock(&isert_conn->conn_comp_mutex);
+
+ send_wr->send_flags = IB_SEND_SIGNALED;
}
static int
}
static void
-isert_send_completion(struct iser_tx_desc *tx_desc,
- struct isert_conn *isert_conn)
+__isert_send_completion(struct iser_tx_desc *tx_desc,
+ struct isert_conn *isert_conn)
{
struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
struct isert_cmd *isert_cmd = tx_desc->isert_cmd;
}
}
+static void
+isert_send_completion(struct iser_tx_desc *tx_desc,
+ struct isert_conn *isert_conn)
+{
+ struct llist_node *llnode = tx_desc->comp_llnode_batch;
+ struct iser_tx_desc *t;
+ /*
+ * Drain coalesced completion llist starting from comp_llnode_batch
+ * setup in isert_init_send_wr(), and then complete trailing tx_desc.
+ */
+ while (llnode) {
+ t = llist_entry(llnode, struct iser_tx_desc, comp_llnode);
+ llnode = llist_next(llnode);
+ __isert_send_completion(t, isert_conn);
+ }
+ __isert_send_completion(tx_desc, isert_conn);
+}
+
static void
isert_cq_comp_err(struct iser_tx_desc *tx_desc, struct isert_conn *isert_conn)
{
isert_cmd->tx_desc.num_sge = 2;
}
- isert_init_send_wr(isert_cmd, send_wr);
+ isert_init_send_wr(isert_conn, isert_cmd, send_wr, true);
pr_debug("Posting SCSI Response IB_WR_SEND >>>>>>>>>>>>>>>>>>>>>>\n");
&isert_cmd->tx_desc.iscsi_header,
nopout_response);
isert_init_tx_hdrs(isert_conn, &isert_cmd->tx_desc);
- isert_init_send_wr(isert_cmd, send_wr);
+ isert_init_send_wr(isert_conn, isert_cmd, send_wr, false);
pr_debug("Posting NOPIN Response IB_WR_SEND >>>>>>>>>>>>>>>>>>>>>>\n");
iscsit_build_logout_rsp(cmd, conn, (struct iscsi_logout_rsp *)
&isert_cmd->tx_desc.iscsi_header);
isert_init_tx_hdrs(isert_conn, &isert_cmd->tx_desc);
- isert_init_send_wr(isert_cmd, send_wr);
+ isert_init_send_wr(isert_conn, isert_cmd, send_wr, false);
pr_debug("Posting Logout Response IB_WR_SEND >>>>>>>>>>>>>>>>>>>>>>\n");
iscsit_build_task_mgt_rsp(cmd, conn, (struct iscsi_tm_rsp *)
&isert_cmd->tx_desc.iscsi_header);
isert_init_tx_hdrs(isert_conn, &isert_cmd->tx_desc);
- isert_init_send_wr(isert_cmd, send_wr);
+ isert_init_send_wr(isert_conn, isert_cmd, send_wr, false);
pr_debug("Posting Task Management Response IB_WR_SEND >>>>>>>>>>>>>>>>>>>>>>\n");
tx_dsg->lkey = isert_conn->conn_mr->lkey;
isert_cmd->tx_desc.num_sge = 2;
- isert_init_send_wr(isert_cmd, send_wr);
+ isert_init_send_wr(isert_conn, isert_cmd, send_wr, false);
pr_debug("Posting Reject IB_WR_SEND >>>>>>>>>>>>>>>>>>>>>>\n");
tx_dsg->lkey = isert_conn->conn_mr->lkey;
isert_cmd->tx_desc.num_sge = 2;
}
- isert_init_send_wr(isert_cmd, send_wr);
+ isert_init_send_wr(isert_conn, isert_cmd, send_wr, false);
pr_debug("Posting Text Response IB_WR_SEND >>>>>>>>>>>>>>>>>>>>>>\n");
if (wr->iser_ib_op == ISER_IB_RDMA_WRITE) {
data_left = se_cmd->data_length;
- iscsit_increment_maxcmdsn(cmd, conn->sess);
- cmd->stat_sn = conn->stat_sn++;
} else {
sg_off = cmd->write_data_done / PAGE_SIZE;
data_left = se_cmd->data_length - cmd->write_data_done;
if (wr->iser_ib_op == ISER_IB_RDMA_WRITE) {
data_left = se_cmd->data_length;
- iscsit_increment_maxcmdsn(cmd, conn->sess);
- cmd->stat_sn = conn->stat_sn++;
} else {
sg_off = cmd->write_data_done / PAGE_SIZE;
data_left = se_cmd->data_length - cmd->write_data_done;
data_len = min(data_left, rdma_write_max);
wr->cur_rdma_length = data_len;
- spin_lock_irqsave(&isert_conn->conn_lock, flags);
- fr_desc = list_first_entry(&isert_conn->conn_frwr_pool,
- struct fast_reg_descriptor, list);
- list_del(&fr_desc->list);
- spin_unlock_irqrestore(&isert_conn->conn_lock, flags);
- wr->fr_desc = fr_desc;
+ /* if there is a single dma entry, dma mr is sufficient */
+ if (count == 1) {
+ ib_sge->addr = ib_sg_dma_address(ib_dev, &sg_start[0]);
+ ib_sge->length = ib_sg_dma_len(ib_dev, &sg_start[0]);
+ ib_sge->lkey = isert_conn->conn_mr->lkey;
+ wr->fr_desc = NULL;
+ } else {
+ spin_lock_irqsave(&isert_conn->conn_lock, flags);
+ fr_desc = list_first_entry(&isert_conn->conn_frwr_pool,
+ struct fast_reg_descriptor, list);
+ list_del(&fr_desc->list);
+ spin_unlock_irqrestore(&isert_conn->conn_lock, flags);
+ wr->fr_desc = fr_desc;
- ret = isert_fast_reg_mr(fr_desc, isert_cmd, isert_conn,
- ib_sge, offset, data_len);
- if (ret) {
- list_add_tail(&fr_desc->list, &isert_conn->conn_frwr_pool);
- goto unmap_sg;
+ ret = isert_fast_reg_mr(fr_desc, isert_cmd, isert_conn,
+ ib_sge, offset, data_len);
+ if (ret) {
+ list_add_tail(&fr_desc->list, &isert_conn->conn_frwr_pool);
+ goto unmap_sg;
+ }
}
return 0;
* Build isert_conn->tx_desc for iSCSI response PDU and attach
*/
isert_create_send_desc(isert_conn, isert_cmd, &isert_cmd->tx_desc);
- iscsit_build_rsp_pdu(cmd, conn, false, (struct iscsi_scsi_rsp *)
+ iscsit_build_rsp_pdu(cmd, conn, true, (struct iscsi_scsi_rsp *)
&isert_cmd->tx_desc.iscsi_header);
isert_init_tx_hdrs(isert_conn, &isert_cmd->tx_desc);
- isert_init_send_wr(isert_cmd, &isert_cmd->tx_desc.send_wr);
+ isert_init_send_wr(isert_conn, isert_cmd,
+ &isert_cmd->tx_desc.send_wr, true);
atomic_inc(&isert_conn->post_send_buf_count);
struct ib_sge tx_sg[2];
int num_sge;
struct isert_cmd *isert_cmd;
+ struct llist_node *comp_llnode_batch;
+ struct llist_node comp_llnode;
struct ib_send_wr send_wr;
} __packed;
int conn_frwr_pool_size;
/* lock to protect frwr_pool */
spinlock_t conn_lock;
+#define ISERT_COMP_BATCH_COUNT 8
+ int conn_comp_batch;
+ struct llist_head conn_comp_llist;
+ struct mutex conn_comp_mutex;
};
#define ISERT_MAX_CQ 64
/* XXX(hch): this is a horrible layering violation.. */
spin_lock_irqsave(&ioctx->cmd.t_state_lock, flags);
- ioctx->cmd.transport_state |= CMD_T_LUN_STOP;
ioctx->cmd.transport_state &= ~CMD_T_ACTIVE;
spin_unlock_irqrestore(&ioctx->cmd.t_state_lock, flags);
-
- complete(&ioctx->cmd.transport_lun_stop_comp);
break;
case SRPT_STATE_CMD_RSP_SENT:
/*
* not been received in time.
*/
srpt_unmap_sg_to_ib_sge(ioctx->ch, ioctx);
- spin_lock_irqsave(&ioctx->cmd.t_state_lock, flags);
- ioctx->cmd.transport_state |= CMD_T_LUN_STOP;
- spin_unlock_irqrestore(&ioctx->cmd.t_state_lock, flags);
target_put_sess_cmd(ioctx->ch->sess, &ioctx->cmd);
break;
case SRPT_STATE_MGMT_RSP_SENT:
{
struct se_cmd *cmd;
enum srpt_command_state state;
- unsigned long flags;
cmd = &ioctx->cmd;
state = srpt_get_cmd_state(ioctx);
__func__, __LINE__, state);
break;
case SRPT_RDMA_WRITE_LAST:
- spin_lock_irqsave(&ioctx->cmd.t_state_lock, flags);
- ioctx->cmd.transport_state |= CMD_T_LUN_STOP;
- spin_unlock_irqrestore(&ioctx->cmd.t_state_lock, flags);
break;
default:
printk(KERN_ERR "%s[%d]: opcode = %u\n", __func__,
{
struct sk_buff *skb;
struct sock *sk = sock->sk;
- struct sockaddr_mISDN *maddr;
int copied, err;
if (!skb)
return err;
- if (msg->msg_namelen >= sizeof(struct sockaddr_mISDN)) {
- msg->msg_namelen = sizeof(struct sockaddr_mISDN);
- maddr = (struct sockaddr_mISDN *)msg->msg_name;
+ if (msg->msg_name) {
+ struct sockaddr_mISDN *maddr = msg->msg_name;
+
maddr->family = AF_ISDN;
maddr->dev = _pms(sk)->dev->id;
if ((sk->sk_protocol == ISDN_P_LAPD_TE) ||
maddr->sapi = _pms(sk)->ch.addr & 0xFF;
maddr->tei = (_pms(sk)->ch.addr >> 8) & 0xFF;
}
- } else {
- if (msg->msg_namelen)
- printk(KERN_WARNING "%s: too small namelen %d\n",
- __func__, msg->msg_namelen);
- msg->msg_namelen = 0;
+ msg->msg_namelen = sizeof(*maddr);
}
copied = skb->len + MISDN_HEADER_LEN;
* to the values in phydev. Assumes that the values are valid.
* Please see phy_sanitize_settings().
*/
-static int genphy_setup_forced(struct phy_device *phydev)
+int genphy_setup_forced(struct phy_device *phydev)
{
int err;
int ctl = 0;
return err;
}
-
+EXPORT_SYMBOL(genphy_setup_forced);
/**
* genphy_restart_aneg - Enable and Restart Autonegotiation
*
* Author: Kriston Carson
*
- * Copyright (c) 2005, 2009 Freescale Semiconductor, Inc.
+ * Copyright (c) 2005, 2009, 2011 Freescale Semiconductor, Inc.
*
* 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
#include <linux/ethtool.h>
#include <linux/phy.h>
+/* Vitesse Extended Page Magic Register(s) */
+#define MII_VSC82X4_EXT_PAGE_16E 0x10
+#define MII_VSC82X4_EXT_PAGE_17E 0x11
+#define MII_VSC82X4_EXT_PAGE_18E 0x12
+
/* Vitesse Extended Control Register 1 */
#define MII_VSC8244_EXT_CON1 0x17
#define MII_VSC8244_EXTCON1_INIT 0x0000
#define MII_VSC8221_AUXCONSTAT_INIT 0x0004 /* need to set this bit? */
#define MII_VSC8221_AUXCONSTAT_RESERVED 0x0004
+/* Vitesse Extended Page Access Register */
+#define MII_VSC82X4_EXT_PAGE_ACCESS 0x1f
+
+#define PHY_ID_VSC8234 0x000fc620
#define PHY_ID_VSC8244 0x000fc6c0
+#define PHY_ID_VSC8574 0x000704a0
+#define PHY_ID_VSC8662 0x00070660
#define PHY_ID_VSC8221 0x000fc550
#define PHY_ID_VSC8211 0x000fc4b0
if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
err = phy_write(phydev, MII_VSC8244_IMASK,
- phydev->drv->phy_id == PHY_ID_VSC8244 ?
+ (phydev->drv->phy_id == PHY_ID_VSC8234 ||
+ phydev->drv->phy_id == PHY_ID_VSC8244 ||
+ phydev->drv->phy_id == PHY_ID_VSC8574) ?
MII_VSC8244_IMASK_MASK :
MII_VSC8221_IMASK_MASK);
else {
*/
}
-/* Vitesse 824x */
+/* vsc82x4_config_autocross_enable - Enable auto MDI/MDI-X for forced links
+ * @phydev: target phy_device struct
+ *
+ * Enable auto MDI/MDI-X when in 10/100 forced link speeds by writing
+ * special values in the VSC8234/VSC8244 extended reserved registers
+ */
+static int vsc82x4_config_autocross_enable(struct phy_device *phydev)
+{
+ int ret;
+
+ if (phydev->autoneg == AUTONEG_ENABLE || phydev->speed > SPEED_100)
+ return 0;
+
+ /* map extended registers set 0x10 - 0x1e */
+ ret = phy_write(phydev, MII_VSC82X4_EXT_PAGE_ACCESS, 0x52b5);
+ if (ret >= 0)
+ ret = phy_write(phydev, MII_VSC82X4_EXT_PAGE_18E, 0x0012);
+ if (ret >= 0)
+ ret = phy_write(phydev, MII_VSC82X4_EXT_PAGE_17E, 0x2803);
+ if (ret >= 0)
+ ret = phy_write(phydev, MII_VSC82X4_EXT_PAGE_16E, 0x87fa);
+ /* map standard registers set 0x10 - 0x1e */
+ if (ret >= 0)
+ ret = phy_write(phydev, MII_VSC82X4_EXT_PAGE_ACCESS, 0x0000);
+ else
+ phy_write(phydev, MII_VSC82X4_EXT_PAGE_ACCESS, 0x0000);
+
+ return ret;
+}
+
+/* vsc82x4_config_aneg - restart auto-negotiation or write BMCR
+ * @phydev: target phy_device struct
+ *
+ * Description: If auto-negotiation is enabled, we configure the
+ * advertising, and then restart auto-negotiation. If it is not
+ * enabled, then we write the BMCR and also start the auto
+ * MDI/MDI-X feature
+ */
+static int vsc82x4_config_aneg(struct phy_device *phydev)
+{
+ int ret;
+
+ /* Enable auto MDI/MDI-X when in 10/100 forced link speeds by
+ * writing special values in the VSC8234 extended reserved registers
+ */
+ if (phydev->autoneg != AUTONEG_ENABLE && phydev->speed <= SPEED_100) {
+ ret = genphy_setup_forced(phydev);
+
+ if (ret < 0) /* error */
+ return ret;
+
+ return vsc82x4_config_autocross_enable(phydev);
+ }
+
+ return genphy_config_aneg(phydev);
+}
+
+/* Vitesse 82xx */
static struct phy_driver vsc82xx_driver[] = {
{
+ .phy_id = PHY_ID_VSC8234,
+ .name = "Vitesse VSC8234",
+ .phy_id_mask = 0x000ffff0,
+ .features = PHY_GBIT_FEATURES,
+ .flags = PHY_HAS_INTERRUPT,
+ .config_init = &vsc824x_config_init,
+ .config_aneg = &vsc82x4_config_aneg,
+ .read_status = &genphy_read_status,
+ .ack_interrupt = &vsc824x_ack_interrupt,
+ .config_intr = &vsc82xx_config_intr,
+ .driver = { .owner = THIS_MODULE,},
+}, {
.phy_id = PHY_ID_VSC8244,
.name = "Vitesse VSC8244",
.phy_id_mask = 0x000fffc0,
.features = PHY_GBIT_FEATURES,
.flags = PHY_HAS_INTERRUPT,
.config_init = &vsc824x_config_init,
- .config_aneg = &genphy_config_aneg,
+ .config_aneg = &vsc82x4_config_aneg,
.read_status = &genphy_read_status,
.ack_interrupt = &vsc824x_ack_interrupt,
.config_intr = &vsc82xx_config_intr,
.driver = { .owner = THIS_MODULE,},
+}, {
+ .phy_id = PHY_ID_VSC8574,
+ .name = "Vitesse VSC8574",
+ .phy_id_mask = 0x000ffff0,
+ .features = PHY_GBIT_FEATURES,
+ .flags = PHY_HAS_INTERRUPT,
+ .config_init = &vsc824x_config_init,
+ .config_aneg = &vsc82x4_config_aneg,
+ .read_status = &genphy_read_status,
+ .ack_interrupt = &vsc824x_ack_interrupt,
+ .config_intr = &vsc82xx_config_intr,
+ .driver = { .owner = THIS_MODULE,},
+}, {
+ .phy_id = PHY_ID_VSC8662,
+ .name = "Vitesse VSC8662",
+ .phy_id_mask = 0x000ffff0,
+ .features = PHY_GBIT_FEATURES,
+ .flags = PHY_HAS_INTERRUPT,
+ .config_init = &vsc824x_config_init,
+ .config_aneg = &vsc82x4_config_aneg,
+ .read_status = &genphy_read_status,
+ .ack_interrupt = &vsc824x_ack_interrupt,
+ .config_intr = &vsc82xx_config_intr,
+ .driver = { .owner = THIS_MODULE,},
}, {
/* Vitesse 8221 */
.phy_id = PHY_ID_VSC8221,
module_exit(vsc82xx_exit);
static struct mdio_device_id __maybe_unused vitesse_tbl[] = {
+ { PHY_ID_VSC8234, 0x000ffff0 },
{ PHY_ID_VSC8244, 0x000fffc0 },
+ { PHY_ID_VSC8574, 0x000ffff0 },
+ { PHY_ID_VSC8662, 0x000ffff0 },
{ PHY_ID_VSC8221, 0x000ffff0 },
{ PHY_ID_VSC8211, 0x000ffff0 },
{ }
if (error < 0)
goto end;
- m->msg_namelen = 0;
-
if (skb) {
total_len = min_t(size_t, total_len, skb->len);
error = skb_copy_datagram_iovec(skb, 0, m->msg_iov, total_len);
#include <linux/ipv6.h>
/* Version Information */
-#define DRIVER_VERSION "v1.01.0 (2013/08/12)"
+#define DRIVER_VERSION "v1.02.0 (2013/10/28)"
#define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
#define DRIVER_DESC "Realtek RTL8152 Based USB 2.0 Ethernet Adapters"
#define MODULENAME "r8152"
#define MCU_TYPE_USB 0x0000
struct rx_desc {
- u32 opts1;
+ __le32 opts1;
#define RX_LEN_MASK 0x7fff
- u32 opts2;
- u32 opts3;
- u32 opts4;
- u32 opts5;
- u32 opts6;
+ __le32 opts2;
+ __le32 opts3;
+ __le32 opts4;
+ __le32 opts5;
+ __le32 opts6;
};
struct tx_desc {
- u32 opts1;
+ __le32 opts1;
#define TX_FS (1 << 31) /* First segment of a packet */
#define TX_LS (1 << 30) /* Final segment of a packet */
#define TX_LEN_MASK 0x3ffff
- u32 opts2;
+ __le32 opts2;
#define UDP_CS (1 << 31) /* Calculate UDP/IP checksum */
#define TCP_CS (1 << 30) /* Calculate TCP/IP checksum */
#define IPV4_CS (1 << 29) /* Calculate IPv4 checksum */
struct mii_if_info mii;
int intr_interval;
u32 msg_enable;
+ u32 tx_qlen;
u16 ocp_base;
u8 *intr_buff;
u8 version;
static void intr_callback(struct urb *urb)
{
struct r8152 *tp;
- __u16 *d;
+ __le16 *d;
int status = urb->status;
int res;
static int r8152_tx_agg_fill(struct r8152 *tp, struct tx_agg *agg)
{
- u32 remain;
+ int remain;
u8 *tx_data;
tx_data = agg->head;
agg->skb_num = agg->skb_len = 0;
- remain = rx_buf_sz - sizeof(struct tx_desc);
+ remain = rx_buf_sz;
- while (remain >= ETH_ZLEN) {
+ while (remain >= ETH_ZLEN + sizeof(struct tx_desc)) {
struct tx_desc *tx_desc;
struct sk_buff *skb;
unsigned int len;
if (!skb)
break;
+ remain -= sizeof(*tx_desc);
len = skb->len;
if (remain < len) {
skb_queue_head(&tp->tx_queue, skb);
break;
}
+ tx_data = tx_agg_align(tx_data);
tx_desc = (struct tx_desc *)tx_data;
tx_data += sizeof(*tx_desc);
agg->skb_len += len;
dev_kfree_skb_any(skb);
- tx_data = tx_agg_align(tx_data + len);
- remain = rx_buf_sz - sizeof(*tx_desc) -
- (u32)((void *)tx_data - agg->head);
+ tx_data += len;
+ remain = rx_buf_sz - (int)(tx_agg_align(tx_data) - agg->head);
}
+ netif_tx_lock(tp->netdev);
+
+ if (netif_queue_stopped(tp->netdev) &&
+ skb_queue_len(&tp->tx_queue) < tp->tx_qlen)
+ netif_wake_queue(tp->netdev);
+
+ netif_tx_unlock(tp->netdev);
+
usb_fill_bulk_urb(agg->urb, tp->udev, usb_sndbulkpipe(tp->udev, 2),
agg->head, (int)(tx_data - (u8 *)agg->head),
(usb_complete_t)write_bulk_callback, agg);
list_for_each_safe(cursor, next, &tp->rx_done) {
struct rx_desc *rx_desc;
struct rx_agg *agg;
- unsigned pkt_len;
int len_used = 0;
struct urb *urb;
u8 *rx_data;
rx_desc = agg->head;
rx_data = agg->head;
- pkt_len = le32_to_cpu(rx_desc->opts1) & RX_LEN_MASK;
- len_used += sizeof(struct rx_desc) + pkt_len;
+ len_used += sizeof(struct rx_desc);
- while (urb->actual_length >= len_used) {
+ while (urb->actual_length > len_used) {
struct net_device *netdev = tp->netdev;
struct net_device_stats *stats;
+ unsigned int pkt_len;
struct sk_buff *skb;
+ pkt_len = le32_to_cpu(rx_desc->opts1) & RX_LEN_MASK;
if (pkt_len < ETH_ZLEN)
break;
+ len_used += pkt_len;
+ if (urb->actual_length < len_used)
+ break;
+
stats = rtl8152_get_stats(netdev);
pkt_len -= 4; /* CRC */
rx_data = rx_agg_align(rx_data + pkt_len + 4);
rx_desc = (struct rx_desc *)rx_data;
- pkt_len = le32_to_cpu(rx_desc->opts1) & RX_LEN_MASK;
len_used = (int)(rx_data - (u8 *)agg->head);
- len_used += sizeof(struct rx_desc) + pkt_len;
+ len_used += sizeof(struct rx_desc);
}
submit:
struct net_device *netdev)
{
struct r8152 *tp = netdev_priv(netdev);
- struct net_device_stats *stats = rtl8152_get_stats(netdev);
- unsigned long flags;
- struct tx_agg *agg = NULL;
- struct tx_desc *tx_desc;
- unsigned int len;
- u8 *tx_data;
- int res;
skb_tx_timestamp(skb);
- /* If tx_queue is not empty, it means at least one previous packt */
- /* is waiting for sending. Don't send current one before it. */
- if (skb_queue_empty(&tp->tx_queue))
- agg = r8152_get_tx_agg(tp);
-
- if (!agg) {
- skb_queue_tail(&tp->tx_queue, skb);
- return NETDEV_TX_OK;
- }
+ skb_queue_tail(&tp->tx_queue, skb);
- tx_desc = (struct tx_desc *)agg->head;
- tx_data = agg->head + sizeof(*tx_desc);
- agg->skb_num = agg->skb_len = 0;
+ if (list_empty(&tp->tx_free) &&
+ skb_queue_len(&tp->tx_queue) > tp->tx_qlen)
+ netif_stop_queue(netdev);
- len = skb->len;
- r8152_tx_csum(tp, tx_desc, skb);
- memcpy(tx_data, skb->data, len);
- dev_kfree_skb_any(skb);
- agg->skb_num++;
- agg->skb_len += len;
- usb_fill_bulk_urb(agg->urb, tp->udev, usb_sndbulkpipe(tp->udev, 2),
- agg->head, len + sizeof(*tx_desc),
- (usb_complete_t)write_bulk_callback, agg);
- res = usb_submit_urb(agg->urb, GFP_ATOMIC);
- if (res) {
- /* Can we get/handle EPIPE here? */
- if (res == -ENODEV) {
- netif_device_detach(tp->netdev);
- } else {
- netif_warn(tp, tx_err, netdev,
- "failed tx_urb %d\n", res);
- stats->tx_dropped++;
- spin_lock_irqsave(&tp->tx_lock, flags);
- list_add_tail(&agg->list, &tp->tx_free);
- spin_unlock_irqrestore(&tp->tx_lock, flags);
- }
- }
+ if (!list_empty(&tp->tx_free))
+ tasklet_schedule(&tp->tl);
return NETDEV_TX_OK;
}
}
}
+static void set_tx_qlen(struct r8152 *tp)
+{
+ struct net_device *netdev = tp->netdev;
+
+ tp->tx_qlen = rx_buf_sz / (netdev->mtu + VLAN_ETH_HLEN + VLAN_HLEN +
+ sizeof(struct tx_desc));
+}
+
static inline u8 rtl8152_get_speed(struct r8152 *tp)
{
return ocp_read_byte(tp, MCU_TYPE_PLA, PLA_PHYSTATUS);
int i, ret;
u8 speed;
+ set_tx_qlen(tp);
speed = rtl8152_get_speed(tp);
if (speed & _10bps) {
ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_EEEP_CR);
return ret;
}
+static void ar9003_doubler_fix(struct ath_hw *ah)
+{
+ if (AR_SREV_9300(ah) || AR_SREV_9580(ah) || AR_SREV_9550(ah)) {
+ REG_RMW(ah, AR_PHY_65NM_CH0_RXTX2,
+ 1 << AR_PHY_65NM_CH0_RXTX2_SYNTHON_MASK_S |
+ 1 << AR_PHY_65NM_CH0_RXTX2_SYNTHOVR_MASK_S, 0);
+ REG_RMW(ah, AR_PHY_65NM_CH1_RXTX2,
+ 1 << AR_PHY_65NM_CH0_RXTX2_SYNTHON_MASK_S |
+ 1 << AR_PHY_65NM_CH0_RXTX2_SYNTHOVR_MASK_S, 0);
+ REG_RMW(ah, AR_PHY_65NM_CH2_RXTX2,
+ 1 << AR_PHY_65NM_CH0_RXTX2_SYNTHON_MASK_S |
+ 1 << AR_PHY_65NM_CH0_RXTX2_SYNTHOVR_MASK_S, 0);
+
+ udelay(200);
+
+ REG_CLR_BIT(ah, AR_PHY_65NM_CH0_RXTX2,
+ AR_PHY_65NM_CH0_RXTX2_SYNTHON_MASK);
+ REG_CLR_BIT(ah, AR_PHY_65NM_CH1_RXTX2,
+ AR_PHY_65NM_CH0_RXTX2_SYNTHON_MASK);
+ REG_CLR_BIT(ah, AR_PHY_65NM_CH2_RXTX2,
+ AR_PHY_65NM_CH0_RXTX2_SYNTHON_MASK);
+
+ udelay(1);
+
+ REG_RMW_FIELD(ah, AR_PHY_65NM_CH0_RXTX2,
+ AR_PHY_65NM_CH0_RXTX2_SYNTHON_MASK, 1);
+ REG_RMW_FIELD(ah, AR_PHY_65NM_CH1_RXTX2,
+ AR_PHY_65NM_CH0_RXTX2_SYNTHON_MASK, 1);
+ REG_RMW_FIELD(ah, AR_PHY_65NM_CH2_RXTX2,
+ AR_PHY_65NM_CH0_RXTX2_SYNTHON_MASK, 1);
+
+ udelay(200);
+
+ REG_RMW_FIELD(ah, AR_PHY_65NM_CH0_SYNTH12,
+ AR_PHY_65NM_CH0_SYNTH12_VREFMUL3, 0xf);
+
+ REG_RMW(ah, AR_PHY_65NM_CH0_RXTX2, 0,
+ 1 << AR_PHY_65NM_CH0_RXTX2_SYNTHON_MASK_S |
+ 1 << AR_PHY_65NM_CH0_RXTX2_SYNTHOVR_MASK_S);
+ REG_RMW(ah, AR_PHY_65NM_CH1_RXTX2, 0,
+ 1 << AR_PHY_65NM_CH0_RXTX2_SYNTHON_MASK_S |
+ 1 << AR_PHY_65NM_CH0_RXTX2_SYNTHOVR_MASK_S);
+ REG_RMW(ah, AR_PHY_65NM_CH2_RXTX2, 0,
+ 1 << AR_PHY_65NM_CH0_RXTX2_SYNTHON_MASK_S |
+ 1 << AR_PHY_65NM_CH0_RXTX2_SYNTHOVR_MASK_S);
+ }
+}
+
static int ar9003_hw_process_ini(struct ath_hw *ah,
struct ath9k_channel *chan)
{
modesIndex);
}
+ ar9003_doubler_fix(ah);
+
/*
* RXGAIN initvals.
*/
#define AR_PHY_SYNTH4_LONG_SHIFT_SELECT ((AR_SREV_9462(ah) || AR_SREV_9565(ah)) ? 0x00000001 : 0x00000002)
#define AR_PHY_SYNTH4_LONG_SHIFT_SELECT_S ((AR_SREV_9462(ah) || AR_SREV_9565(ah)) ? 0 : 1)
#define AR_PHY_65NM_CH0_SYNTH7 0x16098
+#define AR_PHY_65NM_CH0_SYNTH12 0x160ac
#define AR_PHY_65NM_CH0_BIAS1 0x160c0
#define AR_PHY_65NM_CH0_BIAS2 0x160c4
#define AR_PHY_65NM_CH0_BIAS4 0x160cc
+#define AR_PHY_65NM_CH0_RXTX2 0x16104
+#define AR_PHY_65NM_CH1_RXTX2 0x16504
+#define AR_PHY_65NM_CH2_RXTX2 0x16904
#define AR_PHY_65NM_CH0_RXTX4 0x1610c
#define AR_PHY_65NM_CH1_RXTX4 0x1650c
#define AR_PHY_65NM_CH2_RXTX4 0x1690c
+#define AR_PHY_65NM_CH0_SYNTH12_VREFMUL3 0x00780000
+#define AR_PHY_65NM_CH0_SYNTH12_VREFMUL3_S 19
+#define AR_PHY_65NM_CH0_RXTX2_SYNTHON_MASK 0x00000004
+#define AR_PHY_65NM_CH0_RXTX2_SYNTHON_MASK_S 2
+#define AR_PHY_65NM_CH0_RXTX2_SYNTHOVR_MASK 0x00000008
+#define AR_PHY_65NM_CH0_RXTX2_SYNTHOVR_MASK_S 3
+
#define AR_CH0_TOP (AR_SREV_9300(ah) ? 0x16288 : \
(((AR_SREV_9462(ah) || AR_SREV_9565(ah)) ? 0x1628c : 0x16280)))
#define AR_CH0_TOP_XPABIASLVL (AR_SREV_9550(ah) ? 0x3c0 : 0x300)
{0x00009e14, 0x37b95d5e, 0x37b9605e, 0x3236605e, 0x32365a5e},
{0x00009e18, 0x00000000, 0x00000000, 0x00000000, 0x00000000},
{0x00009e1c, 0x0001cf9c, 0x0001cf9c, 0x00021f9c, 0x00021f9c},
- {0x00009e20, 0x000003b5, 0x000003b5, 0x000003ce, 0x000003ce},
+ {0x00009e20, 0x000003a5, 0x000003a5, 0x000003a5, 0x000003a5},
{0x00009e2c, 0x0000001c, 0x0000001c, 0x00000021, 0x00000021},
{0x00009e3c, 0xcf946220, 0xcf946220, 0xcfd5c782, 0xcfd5c282},
{0x00009e44, 0x62321e27, 0x62321e27, 0xfe291e27, 0xfe291e27},
{0x0000ae04, 0x001c0000, 0x001c0000, 0x001c0000, 0x00100000},
{0x0000ae18, 0x00000000, 0x00000000, 0x00000000, 0x00000000},
{0x0000ae1c, 0x0000019c, 0x0000019c, 0x0000019c, 0x0000019c},
- {0x0000ae20, 0x000001b5, 0x000001b5, 0x000001ce, 0x000001ce},
+ {0x0000ae20, 0x000001a6, 0x000001a6, 0x000001aa, 0x000001aa},
{0x0000b284, 0x00000000, 0x00000000, 0x00000550, 0x00000550},
};
static const u32 ar9462_2p1_soc_preamble[][2] = {
/* Addr allmodes */
- {0x000040a4, 0x00a0c1c9},
+ {0x000040a4, 0x00a0c9c9},
{0x00007020, 0x00000000},
{0x00007034, 0x00000002},
{0x00007038, 0x000004c2},
{
u16 country_code;
- if (!ath_is_world_regd(reg))
+ if (request->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE &&
+ !ath_is_world_regd(reg))
return -EINVAL;
country_code = ath_regd_find_country_by_name(request->alpha2);
}
err = brcmf_p2p_escan(p2p, num_nodfs, chanspecs, search_state,
action, P2PAPI_BSSCFG_DEVICE);
+ kfree(chanspecs);
}
exit:
if (err)
priv->bss_started = 0;
priv->bss_num = 0;
- if (mwifiex_cfg80211_init_p2p_client(priv))
- return ERR_PTR(-EFAULT);
+ if (mwifiex_cfg80211_init_p2p_client(priv)) {
+ wdev = ERR_PTR(-EFAULT);
+ goto done;
+ }
break;
default:
if (!dev) {
wiphy_err(wiphy, "no memory available for netdevice\n");
priv->bss_mode = NL80211_IFTYPE_UNSPECIFIED;
- return ERR_PTR(-ENOMEM);
+ wdev = ERR_PTR(-ENOMEM);
+ goto done;
}
mwifiex_init_priv_params(priv, dev);
wiphy_err(wiphy, "cannot register virtual network device\n");
free_netdev(dev);
priv->bss_mode = NL80211_IFTYPE_UNSPECIFIED;
- return ERR_PTR(-EFAULT);
+ priv->netdev = NULL;
+ wdev = ERR_PTR(-EFAULT);
+ goto done;
}
sema_init(&priv->async_sem, 1);
#ifdef CONFIG_DEBUG_FS
mwifiex_dev_debugfs_init(priv);
#endif
+
+done:
+ if (IS_ERR(wdev)) {
+ kfree(priv->wdev);
+ priv->wdev = NULL;
+ }
+
return wdev;
}
EXPORT_SYMBOL_GPL(mwifiex_add_virtual_intf);
unregister_netdevice(wdev->netdev);
/* Clear the priv in adapter */
+ priv->netdev->ieee80211_ptr = NULL;
priv->netdev = NULL;
+ kfree(wdev);
+ priv->wdev = NULL;
priv->media_connected = false;
*/
static void mwifiex_fw_dpc(const struct firmware *firmware, void *context)
{
- int ret, i;
+ int ret;
char fmt[64];
struct mwifiex_private *priv;
struct mwifiex_adapter *adapter = context;
struct mwifiex_fw_image fw;
struct semaphore *sem = adapter->card_sem;
bool init_failed = false;
+ struct wireless_dev *wdev;
if (!firmware) {
dev_err(adapter->dev,
priv = adapter->priv[MWIFIEX_BSS_ROLE_STA];
if (mwifiex_register_cfg80211(adapter)) {
dev_err(adapter->dev, "cannot register with cfg80211\n");
- goto err_register_cfg80211;
+ goto err_init_fw;
}
rtnl_lock();
/* Create station interface by default */
- if (!mwifiex_add_virtual_intf(adapter->wiphy, "mlan%d",
- NL80211_IFTYPE_STATION, NULL, NULL)) {
+ wdev = mwifiex_add_virtual_intf(adapter->wiphy, "mlan%d",
+ NL80211_IFTYPE_STATION, NULL, NULL);
+ if (IS_ERR(wdev)) {
dev_err(adapter->dev, "cannot create default STA interface\n");
+ rtnl_unlock();
goto err_add_intf;
}
rtnl_unlock();
goto done;
err_add_intf:
- for (i = 0; i < adapter->priv_num; i++) {
- priv = adapter->priv[i];
-
- if (!priv)
- continue;
-
- if (priv->wdev && priv->netdev)
- mwifiex_del_virtual_intf(adapter->wiphy, priv->wdev);
- }
- rtnl_unlock();
-err_register_cfg80211:
wiphy_unregister(adapter->wiphy);
wiphy_free(adapter->wiphy);
err_init_fw:
wiphy_unregister(priv->wdev->wiphy);
wiphy_free(priv->wdev->wiphy);
- for (i = 0; i < adapter->priv_num; i++) {
- priv = adapter->priv[i];
- if (priv)
- kfree(priv->wdev);
- }
-
mwifiex_terminate_workqueue(adapter);
/* Unregister device */
}
mwifiex_remove_card(card->adapter, &add_remove_card_sem);
- kfree(card);
}
static void mwifiex_pcie_shutdown(struct pci_dev *pdev)
pci_release_region(pdev, 0);
pci_set_drvdata(pdev, NULL);
}
+ kfree(card);
}
/*
}
mwifiex_remove_card(card->adapter, &add_remove_card_sem);
- kfree(card);
}
/*
sdio_claim_host(card->func);
sdio_disable_func(card->func);
sdio_release_host(card->func);
- sdio_set_drvdata(card->func, NULL);
}
}
return ret;
}
- sdio_set_drvdata(func, card);
adapter->dev = &func->dev;
int ret;
u8 sdio_ireg;
+ sdio_set_drvdata(card->func, card);
+
/*
* Read the HOST_INT_STATUS_REG for ACK the first interrupt got
* from the bootloader. If we don't do this we get a interrupt
kfree(card->mpa_rx.len_arr);
kfree(card->mpa_tx.buf);
kfree(card->mpa_rx.buf);
+ sdio_set_drvdata(card->func, NULL);
+ kfree(card);
}
/*
card->udev = udev;
card->intf = intf;
- usb_card = card;
pr_debug("info: bcdUSB=%#x Device Class=%#x SubClass=%#x Protocol=%#x\n",
udev->descriptor.bcdUSB, udev->descriptor.bDeviceClass,
static void mwifiex_usb_disconnect(struct usb_interface *intf)
{
struct usb_card_rec *card = usb_get_intfdata(intf);
- struct mwifiex_adapter *adapter;
- if (!card || !card->adapter) {
- pr_err("%s: card or card->adapter is NULL\n", __func__);
+ if (!card) {
+ pr_err("%s: card is NULL\n", __func__);
return;
}
- adapter = card->adapter;
- if (!adapter->priv_num)
- return;
-
mwifiex_usb_free(card);
- dev_dbg(adapter->dev, "%s: removing card\n", __func__);
- mwifiex_remove_card(adapter, &add_remove_card_sem);
+ if (card->adapter) {
+ struct mwifiex_adapter *adapter = card->adapter;
+
+ if (!adapter->priv_num)
+ return;
+
+ dev_dbg(adapter->dev, "%s: removing card\n", __func__);
+ mwifiex_remove_card(adapter, &add_remove_card_sem);
+ }
usb_set_intfdata(intf, NULL);
usb_put_dev(interface_to_usbdev(intf));
kfree(card);
+ usb_card = NULL;
return;
}
card->adapter = adapter;
adapter->dev = &card->udev->dev;
strcpy(adapter->fw_name, USB8797_DEFAULT_FW_NAME);
+ usb_card = card;
return 0;
}
{
struct usb_card_rec *card = (struct usb_card_rec *)adapter->card;
- usb_set_intfdata(card->intf, NULL);
+ card->adapter = NULL;
}
static int mwifiex_prog_fw_w_helper(struct mwifiex_adapter *adapter,
if (!down_interruptible(&add_remove_card_sem))
up(&add_remove_card_sem);
- if (usb_card) {
+ if (usb_card && usb_card->adapter) {
struct mwifiex_adapter *adapter = usb_card->adapter;
int i;
static void rt2x00lib_bc_buffer_iter(void *data, u8 *mac,
struct ieee80211_vif *vif)
{
+ struct ieee80211_tx_control control = {};
struct rt2x00_dev *rt2x00dev = data;
struct sk_buff *skb;
*/
skb = ieee80211_get_buffered_bc(rt2x00dev->hw, vif);
while (skb) {
- rt2x00mac_tx(rt2x00dev->hw, NULL, skb);
+ rt2x00mac_tx(rt2x00dev->hw, &control, skb);
skb = ieee80211_get_buffered_bc(rt2x00dev->hw, vif);
}
}
static void _rtl92c_query_rxphystatus(struct ieee80211_hw *hw,
struct rtl_stats *pstats,
- struct rx_desc_92c *pdesc,
+ struct rx_desc_92c *p_desc,
struct rx_fwinfo_92c *p_drvinfo,
bool packet_match_bssid,
bool packet_toself,
u32 rssi, total_rssi = 0;
bool in_powersavemode = false;
bool is_cck_rate;
+ u8 *pdesc = (u8 *)p_desc;
- is_cck_rate = RX_HAL_IS_CCK_RATE(pdesc);
+ is_cck_rate = RX_HAL_IS_CCK_RATE(p_desc);
pstats->packet_matchbssid = packet_match_bssid;
pstats->packet_toself = packet_toself;
- pstats->is_cck = is_cck_rate;
pstats->packet_beacon = packet_beacon;
pstats->is_cck = is_cck_rate;
pstats->RX_SIGQ[0] = -1;
bool rtl92cu_rx_query_desc(struct ieee80211_hw *hw,
struct rtl_stats *stats,
struct ieee80211_rx_status *rx_status,
- u8 *p_desc, struct sk_buff *skb)
+ u8 *pdesc, struct sk_buff *skb)
{
struct rx_fwinfo_92c *p_drvinfo;
- struct rx_desc_92c *pdesc = (struct rx_desc_92c *)p_desc;
+ struct rx_desc_92c *p_desc = (struct rx_desc_92c *)pdesc;
u32 phystatus = GET_RX_DESC_PHY_STATUS(pdesc);
stats->length = (u16) GET_RX_DESC_PKT_LEN(pdesc);
if (phystatus) {
p_drvinfo = (struct rx_fwinfo_92c *)(skb->data +
stats->rx_bufshift);
- rtl92c_translate_rx_signal_stuff(hw, skb, stats, pdesc,
+ rtl92c_translate_rx_signal_stuff(hw, skb, stats, p_desc,
p_drvinfo);
}
/*rx_status->qual = stats->signal; */
if (netif_carrier_ok(vif->dev))
xenvif_carrier_off(vif);
+ if (vif->task)
+ kthread_stop(vif->task);
+
if (vif->tx_irq) {
if (vif->tx_irq == vif->rx_irq)
unbind_from_irqhandler(vif->tx_irq, vif);
vif->tx_irq = 0;
}
- if (vif->task)
- kthread_stop(vif->task);
-
xenvif_unmap_frontend_rings(vif);
}
* Otherwise is returns a bitmask with supported features. Current
* features reported are:
* PCI_PASID_CAP_EXEC - Execute permission supported
- * PCI_PASID_CAP_PRIV - Priviledged mode supported
+ * PCI_PASID_CAP_PRIV - Privileged mode supported
*/
int pci_pasid_features(struct pci_dev *pdev)
{
void __iomem *afi;
int irq;
- struct list_head busses;
+ struct list_head buses;
struct resource *cs;
struct resource io;
/*
* Look up a virtual address mapping for the specified bus number. If no such
- * mapping existis, try to create one.
+ * mapping exists, try to create one.
*/
static void __iomem *tegra_pcie_bus_map(struct tegra_pcie *pcie,
unsigned int busnr)
{
struct tegra_pcie_bus *bus;
- list_for_each_entry(bus, &pcie->busses, list)
+ list_for_each_entry(bus, &pcie->buses, list)
if (bus->nr == busnr)
return (void __iomem *)bus->area->addr;
if (IS_ERR(bus))
return NULL;
- list_add_tail(&bus->list, &pcie->busses);
+ list_add_tail(&bus->list, &pcie->buses);
return (void __iomem *)bus->area->addr;
}
value &= ~AFI_FUSE_PCIE_T0_GEN2_DIS;
afi_writel(pcie, value, AFI_FUSE);
- /* initialze internal PHY, enable up to 16 PCIE lanes */
+ /* initialize internal PHY, enable up to 16 PCIE lanes */
pads_writel(pcie, 0x0, PADS_CTL_SEL);
/* override IDDQ to 1 on all 4 lanes */
if (!pcie)
return -ENOMEM;
- INIT_LIST_HEAD(&pcie->busses);
+ INIT_LIST_HEAD(&pcie->buses);
INIT_LIST_HEAD(&pcie->ports);
pcie->soc_data = match->data;
pcie->dev = &pdev->dev;
return -ENOSPC;
/*
* Check if this position is at correct offset.nvec is always a
- * power of two. pos0 must be nvec bit alligned.
+ * power of two. pos0 must be nvec bit aligned.
*/
if (pos % msgvec)
pos += msgvec - (pos % msgvec);
To compile this driver as a module, choose M here: the
module will be called rpadlpar_io.
-
- When in doubt, say N.
+
+ When in doubt, say N.
config HOTPLUG_PCI_SGI
tristate "SGI PCI Hotplug Support"
cpci_hotplug_pci.o
endif
ifdef CONFIG_ACPI
-pci_hotplug-objs += acpi_pcihp.o
+pci_hotplug-objs += acpi_pcihp.o
endif
cpqphp-objs := cpqphp_core.o \
* @info: must match the pointer used to register
*
* Description: This is used to un-register a hardware specific acpi
- * driver that manipulates the attention LED. The pointer to the
+ * driver that manipulates the attention LED. The pointer to the
* info struct must be the same as the one used to set it.
*/
int acpiphp_unregister_attention(struct acpiphp_attention_info *info)
* was registered with us. This allows hardware specific
* ACPI implementations to blink the light for us.
*/
- static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status)
- {
+static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status)
+{
int retval = -ENODEV;
pr_debug("%s - physical_slot = %s\n", __func__,
} else
attention_info = NULL;
return retval;
- }
-
+}
+
/**
* get_power_status - get power status of a slot
if (retval) {
pr_err("pci_hp_register failed with error %d\n", retval);
goto error_hpslot;
- }
+ }
pr_info("Slot [%s] registered\n", slot_name(slot));
list_add_tail(&slot->node, &bridge->slots);
- /* Register slots for ejectable funtions only. */
+ /* Register slots for ejectable functions only. */
if (acpi_pci_check_ejectable(pbus, handle) || is_dock_device(handle)) {
unsigned long long sun;
int retval;
.read = ibm_read_apci_table,
.write = NULL,
};
-static struct acpiphp_attention_info ibm_attention_info =
+static struct acpiphp_attention_info ibm_attention_info =
{
.set_attn = ibm_set_attention_status,
.get_attn = ibm_get_attention_status,
*/
static int ibm_set_attention_status(struct hotplug_slot *slot, u8 status)
{
- union acpi_object args[2];
+ union acpi_object args[2];
struct acpi_object_list params = { .pointer = args, .count = 2 };
- acpi_status stat;
+ acpi_status stat;
unsigned long long rc;
union apci_descriptor *ibm_slot;
*
* Description: This method is registered with the acpiphp module as a
* callback to do the device specific task of getting the LED status.
- *
+ *
* Because there is no direct method of getting the LED status directly
* from an ACPI call, we read the aPCI table and parse out our
* slot descriptor to read the status from that.
pr_debug("%s: Received notification %02x\n", __func__, event);
if (subevent == 0x80) {
- pr_debug("%s: generationg bus event\n", __func__);
+ pr_debug("%s: generating bus event\n", __func__);
acpi_bus_generate_netlink_event(note->device->pnp.device_class,
dev_name(¬e->device->dev),
note->event, detail);
u32 lvl, void *context, void **rv)
{
acpi_handle *phandle = (acpi_handle *)context;
- acpi_status status;
+ acpi_status status;
struct acpi_device_info *info;
int retval = 0;
info->hardware_id.string, handle);
*phandle = handle;
/* returning non-zero causes the search to stop
- * and returns this value to the caller of
+ * and returns this value to the caller of
* acpi_walk_namespace, but it also causes some warnings
* in the acpi debug code to print...
*/
do { \
if (cpci_debug) \
printk (KERN_DEBUG "%s: " format "\n", \
- MY_NAME , ## arg); \
+ MY_NAME , ## arg); \
} while (0)
#define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME , ## arg)
#define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME , ## arg)
do { \
if (cpci_debug) \
printk (KERN_DEBUG "%s: " format "\n", \
- MY_NAME , ## arg); \
+ MY_NAME , ## arg); \
} while (0)
#define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME , ## arg)
#define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME , ## arg)
* option) any later version.
*
* THIS SOFTWARE IS PROVIDED "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
- * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
- * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL
- * THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
- * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
- * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
- * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
+ * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL
+ * THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+ * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+ * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
* You should have received a copy of the GNU General Public License along
#define dbg(format, arg...) \
do { \
- if(debug) \
+ if (debug) \
printk (KERN_DEBUG "%s: " format "\n", \
- MY_NAME , ## arg); \
+ MY_NAME , ## arg); \
} while(0)
#define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME , ## arg)
#define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME , ## arg)
* option) any later version.
*
* THIS SOFTWARE IS PROVIDED "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
- * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
- * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL
- * THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
- * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
- * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
- * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
+ * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL
+ * THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+ * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+ * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
* You should have received a copy of the GNU General Public License along
#define dbg(format, arg...) \
do { \
- if(debug) \
+ if (debug) \
printk (KERN_DEBUG "%s: " format "\n", \
- MY_NAME , ## arg); \
+ MY_NAME , ## arg); \
} while(0)
#define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME , ## arg)
#define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME , ## arg)
{ 0, }
};
MODULE_DEVICE_TABLE(pci, zt5550_hc_pci_tbl);
-
+
static struct pci_driver zt5550_hc_driver = {
.name = "zt5550_hc",
.id_table = zt5550_hc_pci_tbl,
* option) any later version.
*
* THIS SOFTWARE IS PROVIDED "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
- * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
- * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL
- * THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
- * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
- * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
- * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
+ * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL
+ * THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+ * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+ * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
* You should have received a copy of the GNU General Public License along
#define HC_CMD_REG 0x0C
#define ARB_CONFIG_GNT_REG 0x10
#define ARB_CONFIG_CFG_REG 0x12
-#define ARB_CONFIG_REG 0x10
+#define ARB_CONFIG_REG 0x10
#define ISOL_CONFIG_REG 0x18
#define FAULT_STATUS_REG 0x20
#define FAULT_CONFIG_REG 0x24
goto err_disable_device;
}
- /* Check for the proper subsystem ID's
+ /* Check for the proper subsystem IDs
* Intel uses a different SSID programming model than Compaq.
* For Intel, each SSID bit identifies a PHP capability.
- * Also Intel HPC's may have RID=0.
+ * Also Intel HPCs may have RID=0.
*/
if ((pdev->revision <= 2) && (vendor_id != PCI_VENDOR_ID_INTEL)) {
err(msg_HPC_not_supported);
/* Only if mode change...*/
if (((bus->cur_bus_speed == PCI_SPEED_66MHz) && (adapter_speed == PCI_SPEED_66MHz_PCIX)) ||
- ((bus->cur_bus_speed == PCI_SPEED_66MHz_PCIX) && (adapter_speed == PCI_SPEED_66MHz)))
+ ((bus->cur_bus_speed == PCI_SPEED_66MHz_PCIX) && (adapter_speed == PCI_SPEED_66MHz)))
set_SOGO(ctrl);
wait_for_ctrl_irq(ctrl);
if (ctrl->event_queue[loop].event_type == INT_BUTTON_PRESS) {
dbg("button pressed\n");
- } else if (ctrl->event_queue[loop].event_type ==
+ } else if (ctrl->event_queue[loop].event_type ==
INT_BUTTON_CANCEL) {
dbg("button cancel\n");
del_timer(&p_slot->task_event);
if (rc)
return rc;
- /* find range of busses to use */
+ /* find range of buses to use */
dbg("find ranges of buses to use\n");
bus_node = get_max_resource(&(resources->bus_head), 1);
- /* If we don't have any busses to allocate, we can't continue */
+ /* If we don't have any buses to allocate, we can't continue */
if (!bus_node)
return -ENOMEM;
/* If this function needs an interrupt and we are behind
* a bridge and the pin is tied to something that's
- * alread mapped, set this one the same */
+ * already mapped, set this one the same */
if (temp_byte && resources->irqs &&
(resources->irqs->valid_INT &
(0x01 << ((temp_byte + resources->irqs->barber_pole - 1) & 0x03)))) {
*
* Reads configuration for all slots in a PCI bus and saves info.
*
- * Note: For non-hot plug busses, the slot # saved is the device #
+ * Note: For non-hot plug buses, the slot # saved is the device #
*
* returns 0 if success
*/
* cpqhp_save_slot_config
*
* Saves configuration info for all PCI devices in a given slot
- * including subordinate busses.
+ * including subordinate buses.
*
* returns 0 if success
*/
kfree(tres);
}
}
-
/************************************************************
-* RESOURE TYPE *
+* RESOURCE TYPE *
************************************************************/
#define EBDA_RSRC_TYPE_MASK 0x03
//--------------------------------------------------------------
struct rio_table_hdr {
- u8 ver_num;
+ u8 ver_num;
u8 scal_count;
u8 riodev_count;
u16 offset;
};
//--------------------------------------------------------------
-// RIO DETAIL
+// RIO DETAIL
//--------------------------------------------------------------
struct rio_detail {
u8 first_slot_num;
u8 middle_num;
struct list_head opt_rio_list;
-};
+};
struct opt_rio_lo {
u8 rio_type;
u8 middle_num;
u8 pack_count;
struct list_head opt_rio_lo_list;
-};
+};
/****************************************************************
* HPC DESCRIPTOR NODE *
#define HPC_CTLR_IRQ_PENDG 0x80
//----------------------------------------------------------------------------
-// HPC_CTLR_WROKING status return codes
+// HPC_CTLR_WORKING status return codes
//----------------------------------------------------------------------------
#define HPC_CTLR_WORKING_NO 0x00
#define HPC_CTLR_WORKING_YES 0x01
struct pci_bus *ibmphp_pci_bus;
static int max_slots;
-static int irqs[16]; /* PIC mode IRQ's we're using so far (in case MPS
+static int irqs[16]; /* PIC mode IRQs we're using so far (in case MPS
* tables don't provide default info for empty slots */
static int init_flag;
return get_max_adapter_speed_1 (hs, value, 1);
}
*/
-static inline int get_cur_bus_info(struct slot **sl)
+static inline int get_cur_bus_info(struct slot **sl)
{
int rc = 1;
struct slot * slot_cur = *sl;
debug("options = %x\n", slot_cur->ctrl->options);
- debug("revision = %x\n", slot_cur->ctrl->revision);
+ debug("revision = %x\n", slot_cur->ctrl->revision);
- if (READ_BUS_STATUS(slot_cur->ctrl))
+ if (READ_BUS_STATUS(slot_cur->ctrl))
rc = ibmphp_hpc_readslot(slot_cur, READ_BUSSTATUS, NULL);
-
- if (rc)
+
+ if (rc)
return rc;
-
+
slot_cur->bus_on->current_speed = CURRENT_BUS_SPEED(slot_cur->busstatus);
if (READ_BUS_MODE(slot_cur->ctrl))
slot_cur->bus_on->current_bus_mode =
slot_cur->busstatus,
slot_cur->bus_on->current_speed,
slot_cur->bus_on->current_bus_mode);
-
+
*sl = slot_cur;
return 0;
}
static inline int slot_update(struct slot **sl)
{
int rc;
- rc = ibmphp_hpc_readslot(*sl, READ_ALLSTAT, NULL);
- if (rc)
+ rc = ibmphp_hpc_readslot(*sl, READ_ALLSTAT, NULL);
+ if (rc)
return rc;
if (!init_flag)
rc = get_cur_bus_info(sl);
debug("(*cur_slot)->irq[3] = %x\n",
(*cur_slot)->irq[3]);
- debug("rtable->exlusive_irqs = %x\n",
+ debug("rtable->exclusive_irqs = %x\n",
rtable->exclusive_irqs);
debug("rtable->slots[loop].irq[0].bitmap = %x\n",
rtable->slots[loop].irq[0].bitmap);
else
rc = -ENODEV;
}
- } else
+ } else
rc = -ENODEV;
ibmphp_unlock_operations();
debug("get_attention_status - Entry hotplug_slot[%lx] pvalue[%lx]\n",
(ulong) hotplug_slot, (ulong) value);
-
+
ibmphp_lock_operations();
if (hotplug_slot) {
pslot = hotplug_slot->private;
ibmphp_lock_operations();
mode = slot->supported_bus_mode;
- speed = slot->supported_speed;
+ speed = slot->supported_speed;
ibmphp_unlock_operations();
switch (speed) {
case BUS_SPEED_33:
break;
case BUS_SPEED_66:
- if (mode == BUS_MODE_PCIX)
+ if (mode == BUS_MODE_PCIX)
speed += 0x01;
break;
case BUS_SPEED_100:
debug("BEFORE GETTING SLOT STATUS, slot # %x\n",
slot_cur->number);
- if (slot_cur->ctrl->revision == 0xFF)
+ if (slot_cur->ctrl->revision == 0xFF)
if (get_ctrl_revision(slot_cur,
&slot_cur->ctrl->revision))
return -1;
- if (slot_cur->bus_on->current_speed == 0xFF)
- if (get_cur_bus_info(&slot_cur))
+ if (slot_cur->bus_on->current_speed == 0xFF)
+ if (get_cur_bus_info(&slot_cur))
return -1;
get_max_bus_speed(slot_cur);
debug("SLOT_PRESENT = %x\n", SLOT_PRESENT(slot_cur->status));
debug("SLOT_LATCH = %x\n", SLOT_LATCH(slot_cur->status));
- if ((SLOT_PWRGD(slot_cur->status)) &&
- !(SLOT_PRESENT(slot_cur->status)) &&
+ if ((SLOT_PWRGD(slot_cur->status)) &&
+ !(SLOT_PRESENT(slot_cur->status)) &&
!(SLOT_LATCH(slot_cur->status))) {
debug("BEFORE POWER OFF COMMAND\n");
rc = power_off(slot_cur);
switch (opn) {
case ENABLE:
- if (!(SLOT_PWRGD(slot_cur->status)) &&
- (SLOT_PRESENT(slot_cur->status)) &&
+ if (!(SLOT_PWRGD(slot_cur->status)) &&
+ (SLOT_PRESENT(slot_cur->status)) &&
!(SLOT_LATCH(slot_cur->status)))
return 0;
break;
case DISABLE:
- if ((SLOT_PWRGD(slot_cur->status)) &&
+ if ((SLOT_PWRGD(slot_cur->status)) &&
(SLOT_PRESENT(slot_cur->status)) &&
!(SLOT_LATCH(slot_cur->status)))
return 0;
err("out of system memory\n");
return -ENOMEM;
}
-
+
info->power_status = SLOT_PWRGD(slot_cur->status);
info->attention_status = SLOT_ATTN(slot_cur->status,
slot_cur->ext_status);
case BUS_SPEED_33:
break;
case BUS_SPEED_66:
- if (mode == BUS_MODE_PCIX)
+ if (mode == BUS_MODE_PCIX)
bus_speed += 0x01;
else if (mode == BUS_MODE_PCI)
;
}
bus->cur_bus_speed = bus_speed;
- // To do: bus_names
-
+ // To do: bus_names
+
rc = pci_hp_change_slot_info(slot_cur->hotplug_slot, info);
kfree(info);
return rc;
}
/*
- * The following function is to fix kernel bug regarding
- * getting bus entries, here we manually add those primary
+ * The following function is to fix kernel bug regarding
+ * getting bus entries, here we manually add those primary
* bus entries to kernel bus structure whenever apply
*/
static u8 bus_structure_fixup(u8 busno)
}
/*******************************************************
- * Returns whether the bus is empty or not
+ * Returns whether the bus is empty or not
*******************************************************/
static int is_bus_empty(struct slot * slot_cur)
{
}
/***********************************************************
- * If the HPC permits and the bus currently empty, tries to set the
+ * If the HPC permits and the bus currently empty, tries to set the
* bus speed and mode at the maximum card and bus capability
* Parameters: slot
* Returns: bus is set (0) or error code
static struct pci_device_id ciobx[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_SERVERWORKS, 0x0101) },
{ },
- };
+ };
debug("%s - entry slot # %d\n", __func__, slot_cur->number);
if (SET_BUS_STATUS(slot_cur->ctrl) && is_bus_empty(slot_cur)) {
else if (!SLOT_BUS_MODE(slot_cur->ext_status))
/* if max slot/bus capability is 66 pci
and there's no bus mode mismatch, then
- the adapter supports 66 pci */
+ the adapter supports 66 pci */
cmd = HPC_BUS_66CONVMODE;
else
cmd = HPC_BUS_33CONVMODE;
return -EIO;
}
}
- /* This is for x440, once Brandon fixes the firmware,
+ /* This is for x440, once Brandon fixes the firmware,
will not need this delay */
msleep(1000);
debug("%s -Exit\n", __func__);
}
/* This routine checks the bus limitations that the slot is on from the BIOS.
- * This is used in deciding whether or not to power up the slot.
+ * This is used in deciding whether or not to power up the slot.
* (electrical/spec limitations. For example, >1 133 MHz or >2 66 PCI cards on
- * same bus)
+ * same bus)
* Parameters: slot
* Returns: 0 = no limitations, -EINVAL = exceeded limitations on the bus
*/
static inline void print_card_capability(struct slot *slot_cur)
{
info("capability of the card is ");
- if ((slot_cur->ext_status & CARD_INFO) == PCIX133)
+ if ((slot_cur->ext_status & CARD_INFO) == PCIX133)
info(" 133 MHz PCI-X\n");
else if ((slot_cur->ext_status & CARD_INFO) == PCIX66)
info(" 66 MHz PCI-X\n");
}
attn_LED_blink(slot_cur);
-
+
rc = set_bus(slot_cur);
if (rc) {
err("was not able to set the bus\n");
rc = slot_update(&slot_cur);
if (rc)
goto error_power;
-
+
rc = -EINVAL;
if (SLOT_POWER(slot_cur->status) && !(SLOT_PWRGD(slot_cur->status))) {
err("power fault occurred trying to power up...\n");
"speed and card capability\n");
print_card_capability(slot_cur);
goto error_power;
- }
+ }
/* Don't think this case will happen after above checks...
* but just in case, for paranoia sake */
if (!(SLOT_POWER(slot_cur->status))) {
ibmphp_print_test();
rc = ibmphp_update_slot_info(slot_cur);
exit:
- ibmphp_unlock_operations();
+ ibmphp_unlock_operations();
return rc;
error_nopower:
{
struct slot *slot = hotplug_slot->private;
int rc;
-
+
ibmphp_lock_operations();
rc = ibmphp_do_disable_slot(slot);
ibmphp_unlock_operations();
int rc;
u8 flag;
- debug("DISABLING SLOT...\n");
-
+ debug("DISABLING SLOT...\n");
+
if ((slot_cur == NULL) || (slot_cur->ctrl == NULL)) {
return -ENODEV;
}
-
+
flag = slot_cur->flag;
slot_cur->flag = 1;
attn_LED_blink(slot_cur);
if (slot_cur->func == NULL) {
- /* We need this for fncs's that were there on bootup */
+ /* We need this for functions that were there on bootup */
slot_cur->func = kzalloc(sizeof(struct pci_func), GFP_KERNEL);
if (!slot_cur->func) {
err("out of system memory\n");
}
ibm_unconfigure_device(slot_cur->func);
-
- /* If we got here from latch suddenly opening on operating card or
- a power fault, there's no power to the card, so cannot
- read from it to determine what resources it occupied. This operation
- is forbidden anyhow. The best we can do is remove it from kernel
- lists at least */
+
+ /*
+ * If we got here from latch suddenly opening on operating card or
+ * a power fault, there's no power to the card, so cannot
+ * read from it to determine what resources it occupied. This operation
+ * is forbidden anyhow. The best we can do is remove it from kernel
+ * lists at least */
if (!flag) {
attn_off(slot_cur);
rc = -EFAULT;
goto exit;
}
- if (flag)
+ if (flag)
ibmphp_update_slot_info(slot_cur);
goto exit;
}
debug("AFTER Resource & EBDA INITIALIZATIONS\n");
max_slots = get_max_slots();
-
+
if ((rc = ibmphp_register_pci()))
goto error;
static void __init print_bus_info (void)
{
struct bus_info *ptr;
-
+
list_for_each_entry(ptr, &bus_info_head, bus_info_list) {
debug ("%s - slot_min = %x\n", __func__, ptr->slot_min);
debug ("%s - slot_max = %x\n", __func__, ptr->slot_max);
debug ("%s - bus# = %x\n", __func__, ptr->busno);
debug ("%s - current_speed = %x\n", __func__, ptr->current_speed);
debug ("%s - controller_id = %x\n", __func__, ptr->controller_id);
-
+
debug ("%s - slots_at_33_conv = %x\n", __func__, ptr->slots_at_33_conv);
debug ("%s - slots_at_66_conv = %x\n", __func__, ptr->slots_at_66_conv);
debug ("%s - slots_at_66_pcix = %x\n", __func__, ptr->slots_at_66_pcix);
static void print_lo_info (void)
{
struct rio_detail *ptr;
- debug ("print_lo_info ----\n");
+ debug ("print_lo_info ----\n");
list_for_each_entry(ptr, &rio_lo_head, rio_detail_list) {
debug ("%s - rio_node_id = %x\n", __func__, ptr->rio_node_id);
debug ("%s - rio_type = %x\n", __func__, ptr->rio_type);
struct ebda_pci_rsrc *ptr;
list_for_each_entry(ptr, &ibmphp_ebda_pci_rsrc_head, ebda_pci_rsrc_list) {
- debug ("%s - rsrc type: %x bus#: %x dev_func: %x start addr: %x end addr: %x\n",
+ debug ("%s - rsrc type: %x bus#: %x dev_func: %x start addr: %x end addr: %x\n",
__func__, ptr->rsrc_type ,ptr->bus_num, ptr->dev_fun,ptr->start_addr, ptr->end_addr);
}
}
ebda_seg = readw (io_mem);
iounmap (io_mem);
debug ("returned ebda segment: %x\n", ebda_seg);
-
+
io_mem = ioremap(ebda_seg<<4, 1);
if (!io_mem)
return -ENOMEM;
re = readw (io_mem + sub_addr); /* next sub blk */
sub_addr += 2;
- rc_id = readw (io_mem + sub_addr); /* sub blk id */
+ rc_id = readw (io_mem + sub_addr); /* sub blk id */
sub_addr += 2;
if (rc_id != 0x5243)
debug ("info about hpc descriptor---\n");
debug ("hot blk format: %x\n", format);
debug ("num of controller: %x\n", num_ctlrs);
- debug ("offset of hpc data structure enteries: %x\n ", sub_addr);
+ debug ("offset of hpc data structure entries: %x\n ", sub_addr);
sub_addr = base + re; /* re sub blk */
/* FIXME: rc is never used/checked */
debug ("info about rsrc descriptor---\n");
debug ("format: %x\n", format);
debug ("num of rsrc: %x\n", num_entries);
- debug ("offset of rsrc data structure enteries: %x\n ", sub_addr);
+ debug ("offset of rsrc data structure entries: %x\n ", sub_addr);
hs_complete = 1;
} else {
rio_table_ptr->scal_count = readb (io_mem + offset + 1);
rio_table_ptr->riodev_count = readb (io_mem + offset + 2);
rio_table_ptr->offset = offset +3 ;
-
+
debug("info about rio table hdr ---\n");
debug("ver_num: %x\nscal_count: %x\nriodev_count: %x\noffset of rio table: %x\n ",
rio_table_ptr->ver_num, rio_table_ptr->scal_count,
rio_detail_ptr->chassis_num = readb (io_mem + offset + 14);
// debug ("rio_node_id: %x\nbbar: %x\nrio_type: %x\nowner_id: %x\nport0_node: %x\nport0_port: %x\nport1_node: %x\nport1_port: %x\nfirst_slot_num: %x\nstatus: %x\n", rio_detail_ptr->rio_node_id, rio_detail_ptr->bbar, rio_detail_ptr->rio_type, rio_detail_ptr->owner_id, rio_detail_ptr->port0_node_connect, rio_detail_ptr->port0_port_connect, rio_detail_ptr->port1_node_connect, rio_detail_ptr->port1_port_connect, rio_detail_ptr->first_slot_num, rio_detail_ptr->status);
//create linked list of chassis
- if (rio_detail_ptr->rio_type == 4 || rio_detail_ptr->rio_type == 5)
+ if (rio_detail_ptr->rio_type == 4 || rio_detail_ptr->rio_type == 5)
list_add (&rio_detail_ptr->rio_detail_list, &rio_vg_head);
- //create linked list of expansion box
- else if (rio_detail_ptr->rio_type == 6 || rio_detail_ptr->rio_type == 7)
+ //create linked list of expansion box
+ else if (rio_detail_ptr->rio_type == 6 || rio_detail_ptr->rio_type == 7)
list_add (&rio_detail_ptr->rio_detail_list, &rio_lo_head);
- else
+ else
// not in my concern
kfree (rio_detail_ptr);
offset += 15;
}
/*
- * reorganizing linked list of chassis
+ * reorganizing linked list of chassis
*/
static struct opt_rio *search_opt_vg (u8 chassis_num)
{
list_for_each_entry(ptr, &opt_vg_head, opt_rio_list) {
if (ptr->chassis_num == chassis_num)
return ptr;
- }
+ }
return NULL;
}
{
struct opt_rio *opt_rio_ptr = NULL;
struct rio_detail *rio_detail_ptr = NULL;
-
+
list_for_each_entry(rio_detail_ptr, &rio_vg_head, rio_detail_list) {
opt_rio_ptr = search_opt_vg (rio_detail_ptr->chassis_num);
if (!opt_rio_ptr) {
opt_rio_ptr->first_slot_num = rio_detail_ptr->first_slot_num;
opt_rio_ptr->middle_num = rio_detail_ptr->first_slot_num;
list_add (&opt_rio_ptr->opt_rio_list, &opt_vg_head);
- } else {
+ } else {
opt_rio_ptr->first_slot_num = min (opt_rio_ptr->first_slot_num, rio_detail_ptr->first_slot_num);
opt_rio_ptr->middle_num = max (opt_rio_ptr->middle_num, rio_detail_ptr->first_slot_num);
- }
+ }
}
print_opt_vg ();
- return 0;
-}
+ return 0;
+}
/*
* reorganizing linked list of expansion box
list_for_each_entry(ptr, &opt_lo_head, opt_rio_lo_list) {
if (ptr->chassis_num == chassis_num)
return ptr;
- }
+ }
return NULL;
}
{
struct opt_rio_lo *opt_rio_lo_ptr = NULL;
struct rio_detail *rio_detail_ptr = NULL;
-
+
list_for_each_entry(rio_detail_ptr, &rio_lo_head, rio_detail_list) {
opt_rio_lo_ptr = search_opt_lo (rio_detail_ptr->chassis_num);
if (!opt_rio_lo_ptr) {
opt_rio_lo_ptr->first_slot_num = rio_detail_ptr->first_slot_num;
opt_rio_lo_ptr->middle_num = rio_detail_ptr->first_slot_num;
opt_rio_lo_ptr->pack_count = 1;
-
+
list_add (&opt_rio_lo_ptr->opt_rio_lo_list, &opt_lo_head);
- } else {
+ } else {
opt_rio_lo_ptr->first_slot_num = min (opt_rio_lo_ptr->first_slot_num, rio_detail_ptr->first_slot_num);
opt_rio_lo_ptr->middle_num = max (opt_rio_lo_ptr->middle_num, rio_detail_ptr->first_slot_num);
opt_rio_lo_ptr->pack_count = 2;
- }
+ }
}
- return 0;
+ return 0;
}
-
+
/* Since we don't know the max slot number per each chassis, hence go
* through the list of all chassis to find out the range
- * Arguments: slot_num, 1st slot number of the chassis we think we are on,
- * var (0 = chassis, 1 = expansion box)
+ * Arguments: slot_num, 1st slot number of the chassis we think we are on,
+ * var (0 = chassis, 1 = expansion box)
*/
static int first_slot_num (u8 slot_num, u8 first_slot, u8 var)
{
if (!var) {
list_for_each_entry(opt_vg_ptr, &opt_vg_head, opt_rio_list) {
- if ((first_slot < opt_vg_ptr->first_slot_num) && (slot_num >= opt_vg_ptr->first_slot_num)) {
+ if ((first_slot < opt_vg_ptr->first_slot_num) && (slot_num >= opt_vg_ptr->first_slot_num)) {
rc = -ENODEV;
break;
}
list_for_each_entry(opt_lo_ptr, &opt_lo_head, opt_rio_lo_list) {
//check to see if this slot_num belongs to expansion box
- if ((slot_num >= opt_lo_ptr->first_slot_num) && (!first_slot_num (slot_num, opt_lo_ptr->first_slot_num, 1)))
+ if ((slot_num >= opt_lo_ptr->first_slot_num) && (!first_slot_num (slot_num, opt_lo_ptr->first_slot_num, 1)))
return opt_lo_ptr;
}
return NULL;
struct opt_rio *opt_vg_ptr;
list_for_each_entry(opt_vg_ptr, &opt_vg_head, opt_rio_list) {
- //check to see if this slot_num belongs to chassis
- if ((slot_num >= opt_vg_ptr->first_slot_num) && (!first_slot_num (slot_num, opt_vg_ptr->first_slot_num, 0)))
+ //check to see if this slot_num belongs to chassis
+ if ((slot_num >= opt_vg_ptr->first_slot_num) && (!first_slot_num (slot_num, opt_vg_ptr->first_slot_num, 0)))
return opt_vg_ptr;
}
return NULL;
{
u8 first_slot = 1;
struct slot * slot_cur;
-
+
list_for_each_entry(slot_cur, &ibmphp_slot_head, ibm_slot_list) {
if (slot_cur->ctrl) {
- if ((slot_cur->ctrl->ctlr_type != 4) && (slot_cur->ctrl->ending_slot_num > first_slot) && (slot_num > slot_cur->ctrl->ending_slot_num))
+ if ((slot_cur->ctrl->ctlr_type != 4) && (slot_cur->ctrl->ending_slot_num > first_slot) && (slot_num > slot_cur->ctrl->ending_slot_num))
first_slot = slot_cur->ctrl->ending_slot_num;
}
- }
+ }
return first_slot + 1;
}
err ("Structure passed is empty\n");
return NULL;
}
-
+
slot_num = slot_cur->number;
memset (str, 0, sizeof(str));
-
+
if (rio_table_ptr) {
if (rio_table_ptr->ver_num == 3) {
opt_vg_ptr = find_chassis_num (slot_num);
/* if both NULL and we DO have correct RIO table in BIOS */
return NULL;
}
- }
+ }
if (!flag) {
if (slot_cur->ctrl->ctlr_type == 4) {
first_slot = calculate_first_slot (slot_num);
slot_ptr->ctl_index = readb (io_mem + addr_slot + 2*slot_num);
slot_ptr->slot_cap = readb (io_mem + addr_slot + 3*slot_num);
- // create bus_info lined list --- if only one slot per bus: slot_min = slot_max
+ // create bus_info lined list --- if only one slot per bus: slot_min = slot_max
bus_info_ptr2 = ibmphp_find_same_bus_num (slot_ptr->slot_bus_num);
if (!bus_info_ptr2) {
bus_info_ptr1->index = bus_index++;
bus_info_ptr1->current_speed = 0xff;
bus_info_ptr1->current_bus_mode = 0xff;
-
+
bus_info_ptr1->controller_id = hpc_ptr->ctlr_id;
-
+
list_add_tail (&bus_info_ptr1->bus_info_list, &bus_info_head);
} else {
bus_info_ptr2->slots_at_66_conv = bus_ptr->slots_at_66_conv;
bus_info_ptr2->slots_at_66_pcix = bus_ptr->slots_at_66_pcix;
bus_info_ptr2->slots_at_100_pcix = bus_ptr->slots_at_100_pcix;
- bus_info_ptr2->slots_at_133_pcix = bus_ptr->slots_at_133_pcix;
+ bus_info_ptr2->slots_at_133_pcix = bus_ptr->slots_at_133_pcix;
}
bus_ptr++;
}
hpc_ptr->u.pci_ctlr.dev_fun = readb (io_mem + addr + 1);
hpc_ptr->irq = readb (io_mem + addr + 2);
addr += 3;
- debug ("ctrl bus = %x, ctlr devfun = %x, irq = %x\n",
+ debug ("ctrl bus = %x, ctlr devfun = %x, irq = %x\n",
hpc_ptr->u.pci_ctlr.bus,
hpc_ptr->u.pci_ctlr.dev_fun, hpc_ptr->irq);
break;
tmp_slot->supported_speed = 2;
else if ((hpc_ptr->slots[index].slot_cap & EBDA_SLOT_66_MAX) == EBDA_SLOT_66_MAX)
tmp_slot->supported_speed = 1;
-
+
if ((hpc_ptr->slots[index].slot_cap & EBDA_SLOT_PCIX_CAP) == EBDA_SLOT_PCIX_CAP)
tmp_slot->supported_bus_mode = 1;
else
return rc;
}
-/*
+/*
* map info (bus, devfun, start addr, end addr..) of i/o, memory,
* pfm from the physical addr to a list of resource.
*/
addr += 10;
debug ("rsrc from mem or pfm ---\n");
- debug ("rsrc type: %x bus#: %x dev_func: %x start addr: %x end addr: %x\n",
+ debug ("rsrc type: %x bus#: %x dev_func: %x start addr: %x end addr: %x\n",
rsrc_ptr->rsrc_type, rsrc_ptr->bus_num, rsrc_ptr->dev_fun, rsrc_ptr->start_addr, rsrc_ptr->end_addr);
list_add (&rsrc_ptr->ebda_pci_rsrc_list, &ibmphp_ebda_pci_rsrc_head);
struct bus_info *ptr;
list_for_each_entry(ptr, &bus_info_head, bus_info_list) {
- if (ptr->busno == num)
+ if (ptr->busno == num)
return ptr;
}
return NULL;
struct bus_info *ptr;
list_for_each_entry(ptr, &bus_info_head, bus_info_list) {
- if (ptr->busno == num)
+ if (ptr->busno == num)
return ptr->index;
}
return -ENODEV;
.subdevice = HPC_SUBSYSTEM_ID,
.class = ((PCI_CLASS_SYSTEM_PCI_HOTPLUG << 8) | 0x00),
}, {}
-};
+};
MODULE_DEVICE_TABLE(pci, id_table);
struct controller *ctrl;
debug ("inside ibmphp_probe\n");
-
+
list_for_each_entry(ctrl, &ebda_hpc_head, ebda_hpc_list) {
if (ctrl->ctlr_type == 1) {
if ((dev->devfn == ctrl->u.pci_ctlr.dev_fun) && (dev->bus->number == ctrl->u.pci_ctlr.bus)) {
}
return -ENODEV;
}
-
{
u8 rc;
void __iomem *wpg_addr; // base addr + offset
- unsigned long wpg_data; // data to/from WPG LOHI format
+ unsigned long wpg_data; // data to/from WPG LOHI format
unsigned long ultemp;
unsigned long data; // actual data HILO format
int i;
}
//------------------------------------------------------------
-// Read from ISA type HPC
+// Read from ISA type HPC
//------------------------------------------------------------
static u8 isa_ctrl_read (struct controller *ctlr_ptr, u8 offset)
{
{
u16 start_address;
u16 port_address;
-
+
start_address = ctlr_ptr->u.isa_ctlr.io_start;
port_address = start_address + (u16) offset;
outb (data, port_address);
//--------------------------------------------------------------------
// cleanup
//--------------------------------------------------------------------
-
+
// remove physical to logical address mapping
if ((ctlr_ptr->ctlr_type == 2) || (ctlr_ptr->ctlr_type == 4))
iounmap (wpg_bbar);
-
+
free_hpc_access ();
debug_polling ("%s - Exit rc[%d]\n", __func__, rc);
down (&semOperations);
switch (poll_state) {
- case POLL_LATCH_REGISTER:
+ case POLL_LATCH_REGISTER:
oldlatchlow = curlatchlow;
ctrl_count = 0x00;
list_for_each (pslotlist, &ibmphp_slot_head) {
if (kthread_should_stop())
goto out_sleep;
-
+
down (&semOperations);
-
+
if (poll_count >= POLL_LATCH_CNT) {
poll_count = 0;
poll_state = POLL_SLOTS;
} else
poll_state = POLL_LATCH_REGISTER;
break;
- }
+ }
/* give up the hardware semaphore */
up (&semOperations);
/* sleep for a short time just for good measure */
// bit 5 - HPC_SLOT_PWRGD
if ((pslot->status & 0x20) != (poldslot->status & 0x20))
// OFF -> ON: ignore, ON -> OFF: disable slot
- if ((poldslot->status & 0x20) && (SLOT_CONNECT (poldslot->status) == HPC_SLOT_CONNECTED) && (SLOT_PRESENT (poldslot->status)))
+ if ((poldslot->status & 0x20) && (SLOT_CONNECT (poldslot->status) == HPC_SLOT_CONNECTED) && (SLOT_PRESENT (poldslot->status)))
disable = 1;
// bit 6 - HPC_SLOT_BUS_SPEED
pslot->status &= ~HPC_SLOT_POWER;
}
}
- // CLOSE -> OPEN
+ // CLOSE -> OPEN
else if ((SLOT_PWRGD (poldslot->status) == HPC_SLOT_PWRGD_GOOD)
&& (SLOT_CONNECT (poldslot->status) == HPC_SLOT_CONNECTED) && (SLOT_PRESENT (poldslot->status))) {
disable = 1;
debug ("before locking operations \n");
ibmphp_lock_operations ();
debug ("after locking operations \n");
-
+
// wait for poll thread to exit
debug ("before sem_exit down \n");
down (&sem_exit);
/*
* IBM Hot Plug Controller Driver
- *
+ *
* Written By: Irene Zubarev, IBM Corporation
- *
+ *
* Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
* Copyright (C) 2001,2002 IBM Corp.
*
/*
* NOTE..... If BIOS doesn't provide default routing, we assign:
- * 9 for SCSI, 10 for LAN adapters, and 11 for everything else.
+ * 9 for SCSI, 10 for LAN adapters, and 11 for everything else.
* If adapter is bridged, then we assign 11 to it and devices behind it.
* We also assign the same irq numbers for multi function devices.
* These are PIC mode, so shouldn't matter n.e.ways (hopefully)
* Configures the device to be added (will allocate needed resources if it
* can), the device can be a bridge or a regular pci device, can also be
* multi-functional
- *
+ *
* Input: function to be added
- *
+ *
* TO DO: The error case with Multifunction device or multi function bridge,
- * if there is an error, will need to go through all previous functions and
+ * if there is an error, will need to go through all previous functions and
* unconfigure....or can add some code into unconfigure_card....
*/
int ibmphp_configure_card (struct pci_func *func, u8 slotno)
cur_func = func;
/* We only get bus and device from IRQ routing table. So at this point,
- * func->busno is correct, and func->device contains only device (at the 5
+ * func->busno is correct, and func->device contains only device (at the 5
* highest bits)
*/
cur_func->device, cur_func->busno);
cleanup_count = 6;
goto error;
- }
+ }
cur_func->next = NULL;
function = 0x8;
break;
}
/*
- * This function configures the pci BARs of a single device.
+ * This function configures the pci BARs of a single device.
* Input: pointer to the pci_func
* Output: configured PCI, 0, or error
*/
for (count = 0; address[count]; count++) { /* for 6 BARs */
- /* not sure if i need this. per scott, said maybe need smth like this
+ /* not sure if i need this. per scott, said maybe need * something like this
if devices don't adhere 100% to the spec, so don't want to write
to the reserved bits
- pcibios_read_config_byte(cur_func->busno, cur_func->device,
+ pcibios_read_config_byte(cur_func->busno, cur_func->device,
PCI_BASE_ADDRESS_0 + 4 * count, &tmp);
if (tmp & 0x01) // IO
- pcibios_write_config_dword(cur_func->busno, cur_func->device,
+ pcibios_write_config_dword(cur_func->busno, cur_func->device,
PCI_BASE_ADDRESS_0 + 4 * count, 0xFFFFFFFD);
else // Memory
- pcibios_write_config_dword(cur_func->busno, cur_func->device,
+ pcibios_write_config_dword(cur_func->busno, cur_func->device,
PCI_BASE_ADDRESS_0 + 4 * count, 0xFFFFFFFF);
*/
pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], 0xFFFFFFFF);
return -EIO;
}
pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], func->io[count]->start);
-
- /* _______________This is for debugging purposes only_____________________ */
+
+ /* _______________This is for debugging purposes only_____________________ */
debug ("b4 writing, the IO address is %x\n", func->io[count]->start);
pci_bus_read_config_dword (ibmphp_pci_bus, devfn, address[count], &bar[count]);
debug ("after writing.... the start address is %x\n", bar[count]);
pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], func->pfmem[count]->start);
- /*_______________This is for debugging purposes only______________________________*/
+ /*_______________This is for debugging purposes only______________________________*/
debug ("b4 writing, start address is %x\n", func->pfmem[count]->start);
pci_bus_read_config_dword (ibmphp_pci_bus, devfn, address[count], &bar[count]);
debug ("after writing, start address is %x\n", bar[count]);
/******************************************************************************
* This routine configures a PCI-2-PCI bridge and the functions behind it
* Parameters: pci_func
- * Returns:
+ * Returns:
******************************************************************************/
static int configure_bridge (struct pci_func **func_passed, u8 slotno)
{
debug ("AFTER FIND_SEC_NUMBER, func->busno IS %x\n", func->busno);
pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_SECONDARY_BUS, sec_number);
-
+
/* __________________For debugging purposes only __________________________________
pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_SECONDARY_BUS, &sec_number);
debug ("sec_number after write/read is %x\n", sec_number);
/* !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
- !!!!!!!!!!!!!!!NEED TO ADD!!! FAST BACK-TO-BACK ENABLE!!!!!!!!!!!!!!!!!!!!
+ !!!!!!!!!!!!!!!NEED TO ADD!!! FAST BACK-TO-BACK ENABLE!!!!!!!!!!!!!!!!!!!!
!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!*/
debug ("len[count] in IO = %x\n", len[count]);
bus_io[count] = kzalloc(sizeof(struct resource_node), GFP_KERNEL);
-
+
if (!bus_io[count]) {
err ("out of system memory\n");
retval = -ENOMEM;
ibmphp_add_pfmem_from_mem (bus_pfmem[count]);
func->pfmem[count] = bus_pfmem[count];
} else {
- err ("cannot allocate requested pfmem for bus %x, device %x, len %x\n",
+ err ("cannot allocate requested pfmem for bus %x, device %x, len %x\n",
func->busno, func->device, len[count]);
kfree (mem_tmp);
kfree (bus_pfmem[count]);
debug ("amount_needed->mem = %x\n", amount_needed->mem);
debug ("amount_needed->pfmem = %x\n", amount_needed->pfmem);
- if (amount_needed->not_correct) {
+ if (amount_needed->not_correct) {
debug ("amount_needed is not correct\n");
for (count = 0; address[count]; count++) {
/* for 2 BARs */
} else {
debug ("it wants %x IO behind the bridge\n", amount_needed->io);
io = kzalloc(sizeof(*io), GFP_KERNEL);
-
+
if (!io) {
err ("out of system memory\n");
retval = -ENOMEM;
if (bus->noIORanges) {
pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_IO_BASE, 0x00 | bus->rangeIO->start >> 8);
- pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_IO_LIMIT, 0x00 | bus->rangeIO->end >> 8);
+ pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_IO_LIMIT, 0x00 | bus->rangeIO->end >> 8);
/* _______________This is for debugging purposes only ____________________
pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_IO_BASE, &temp);
if (bus->noMemRanges) {
pci_bus_write_config_word (ibmphp_pci_bus, devfn, PCI_MEMORY_BASE, 0x0000 | bus->rangeMem->start >> 16);
pci_bus_write_config_word (ibmphp_pci_bus, devfn, PCI_MEMORY_LIMIT, 0x0000 | bus->rangeMem->end >> 16);
-
+
/* ____________________This is for debugging purposes only ________________________
pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_MEMORY_BASE, &temp);
debug ("mem_base = %x\n", (temp & PCI_MEMORY_RANGE_TYPE_MASK) << 16);
pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_INTERRUPT_PIN, &irq);
if ((irq > 0x00) && (irq < 0x05))
pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_INTERRUPT_LINE, func->irq[irq - 1]);
- /*
+ /*
pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_BRIDGE_CONTROL, ctrl);
pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_BRIDGE_CONTROL, PCI_BRIDGE_CTL_PARITY);
pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_BRIDGE_CONTROL, PCI_BRIDGE_CTL_SERR);
* This function adds up the amount of resources needed behind the PPB bridge
* and passes it to the configure_bridge function
* Input: bridge function
- * Ouput: amount of resources needed
+ * Output: amount of resources needed
*****************************************************************************/
static struct res_needed *scan_behind_bridge (struct pci_func * func, u8 busno)
{
return amount;
}
-/* The following 3 unconfigure_boot_ routines deal with the case when we had the card
- * upon bootup in the system, since we don't allocate func to such case, we need to read
- * the start addresses from pci config space and then find the corresponding entries in
+/* The following 3 unconfigure_boot_ routines deal with the case when we had the card
+ * upon bootup in the system, since we don't allocate func to such case, we need to read
+ * the start addresses from pci config space and then find the corresponding entries in
* our resource lists. The functions return either 0, -ENODEV, or -1 (general failure)
* Change: we also call these functions even if we configured the card ourselves (i.e., not
* the bootup case), since it should work same way
* unconfiguring the device
* TO DO: will probably need to add some code in case there was some resource,
* to remove it... this is from when we have errors in the configure_card...
- * !!!!!!!!!!!!!!!!!!!!!!!!!FOR BUSES!!!!!!!!!!!!
- * Returns: 0, -1, -ENODEV
+ * !!!!!!!!!!!!!!!!!!!!!!!!!FOR BUSES!!!!!!!!!!!!
+ * Returns: 0, -1, -ENODEV
*/
int ibmphp_unconfigure_card (struct slot **slot_cur, int the_end)
{
* Input: bus and the amount of resources needed (we know we can assign those,
* since they've been checked already
* Output: bus added to the correct spot
- * 0, -1, error
+ * 0, -1, error
*/
static int add_new_bus (struct bus_node *bus, struct resource_node *io, struct resource_node *mem, struct resource_node *pfmem, u8 parent_busno)
{
err ("strange, cannot find bus which is supposed to be at the system... something is terribly wrong...\n");
return -ENODEV;
}
-
+
list_add (&bus->bus_list, &cur_bus->bus_list);
}
if (io) {
}
if (pfmem) {
pfmem_range = kzalloc(sizeof(*pfmem_range), GFP_KERNEL);
- if (!pfmem_range) {
+ if (!pfmem_range) {
err ("out of system memory\n");
return -ENOMEM;
}
return busno;
return 0xff;
}
-
static struct resource_node * __init alloc_resources (struct ebda_pci_rsrc * curr)
{
struct resource_node *rs;
-
+
if (!curr) {
err ("NULL passed to allocate\n");
return NULL;
}
newrange->start = curr->start_addr;
newrange->end = curr->end_addr;
-
+
if (first_bus || (!num_ranges))
newrange->rangeno = 1;
else {
newbus->rangePFMem = newrange;
if (first_bus)
newbus->noPFMemRanges = 1;
- else {
+ else {
debug ("1st PFMemory Primary on Bus %x [%x - %x]\n", newbus->busno, newrange->start, newrange->end);
++newbus->noPFMemRanges;
fix_resources (newbus);
* This is the Resource Management initialization function. It will go through
* the Resource list taken from EBDA and fill in this module's data structures
*
- * THIS IS NOT TAKING INTO CONSIDERATION IO RESTRICTIONS OF PRIMARY BUSES,
+ * THIS IS NOT TAKING INTO CONSIDERATION IO RESTRICTIONS OF PRIMARY BUSES,
* SINCE WE'RE GOING TO ASSUME FOR NOW WE DON'T HAVE THOSE ON OUR BUSES FOR NOW
*
* Input: ptr to the head of the resource list from EBDA
* pci devices' resources for the appropriate resource
*
* Input: type of the resource, range to add, current bus
- * Output: 0 or -1, bus and range ptrs
+ * Output: 0 or -1, bus and range ptrs
********************************************************************************/
static int add_bus_range (int type, struct range_node *range, struct bus_node *bus_cur)
{
switch (type) {
case MEM:
- if (bus_cur->firstMem)
+ if (bus_cur->firstMem)
res = bus_cur->firstMem;
break;
case PFMEM:
}
/*******************************************************************************
- * This routine adds a resource to the list of resources to the appropriate bus
+ * This routine adds a resource to the list of resources to the appropriate bus
* based on their resource type and sorted by their starting addresses. It assigns
* the ptrs to next and nextRange if needed.
*
err ("NULL passed to add\n");
return -ENODEV;
}
-
+
bus_cur = find_bus_wprev (res->busno, NULL, 0);
-
+
if (!bus_cur) {
- /* didn't find a bus, smth's wrong!!! */
+ /* didn't find a bus, something's wrong!!! */
debug ("no bus in the system, either pci_dev's wrong or allocation failed\n");
return -ENODEV;
}
if (!range_cur) {
switch (res->type) {
case IO:
- ++bus_cur->needIOUpdate;
+ ++bus_cur->needIOUpdate;
break;
case MEM:
++bus_cur->needMemUpdate;
}
res->rangeno = -1;
}
-
+
debug ("The range is %d\n", res->rangeno);
if (!res_start) {
/* no first{IO,Mem,Pfmem} on the bus, 1st IO/Mem/Pfmem resource ever */
switch (res->type) {
case IO:
- bus_cur->firstIO = res;
+ bus_cur->firstIO = res;
break;
case MEM:
bus_cur->firstMem = res;
case PFMEM:
bus_cur->firstPFMem = res;
break;
- }
+ }
res->next = NULL;
res->nextRange = NULL;
} else {
* This routine will remove the resource from the list of resources
*
* Input: io, mem, and/or pfmem resource to be deleted
- * Ouput: modified resource list
+ * Output: modified resource list
* 0 or error code
****************************************************************************/
int ibmphp_remove_resource (struct resource_node *res)
if (!res_cur) {
if (res->type == PFMEM) {
- /*
+ /*
* case where pfmem might be in the PFMemFromMem list
* so will also need to remove the corresponding mem
* entry
}
/*****************************************************************************
- * This routine will check to make sure the io/mem/pfmem->len that the device asked for
+ * This routine will check to make sure the io/mem/pfmem->len that the device asked for
* can fit w/i our list of available IO/MEM/PFMEM resources. If cannot, returns -EINVAL,
* otherwise, returns 0
*
* Input: resource
- * Ouput: the correct start and end address are inputted into the resource node,
+ * Output: the correct start and end address are inputted into the resource node,
* 0 or -EINVAL
*****************************************************************************/
int ibmphp_check_resource (struct resource_node *res, u8 bridge)
bus_cur = find_bus_wprev (res->busno, NULL, 0);
if (!bus_cur) {
- /* didn't find a bus, smth's wrong!!! */
+ /* didn't find a bus, something's wrong!!! */
debug ("no bus in the system, either pci_dev's wrong or allocation failed\n");
return -EINVAL;
}
break;
}
}
-
+
if (flag && len_cur == res->len) {
debug ("but we are not here, right?\n");
res->start = start_cur;
if (res_prev) {
if (res_prev->rangeno != res_cur->rangeno) {
/* 1st device on this range */
- if ((res_cur->start != range->start) &&
+ if ((res_cur->start != range->start) &&
((len_tmp = res_cur->start - 1 - range->start) >= res->len)) {
if ((len_tmp < len_cur) || (len_cur == 0)) {
- if ((range->start % tmp_divide) == 0) {
+ if ((range->start % tmp_divide) == 0) {
/* just perfect, starting address is divisible by length */
flag = 1;
len_cur = len_tmp;
* This routine is called from remove_card if the card contained PPB.
* It will remove all the resources on the bus as well as the bus itself
* Input: Bus
- * Ouput: 0, -ENODEV
+ * Output: 0, -ENODEV
********************************************************************************/
int ibmphp_remove_bus (struct bus_node *bus, u8 parent_busno)
{
struct bus_node *prev_bus;
int rc;
- prev_bus = find_bus_wprev (parent_busno, NULL, 0);
+ prev_bus = find_bus_wprev (parent_busno, NULL, 0);
if (!prev_bus) {
debug ("something terribly wrong. Cannot find parent bus to the one to remove\n");
}
/******************************************************************************
- * This routine deletes the ranges from a given bus, and the entries from the
+ * This routine deletes the ranges from a given bus, and the entries from the
* parent's bus in the resources
* Input: current bus, previous bus
* Output: 0, -EINVAL
if (bus_cur->noMemRanges) {
range_cur = bus_cur->rangeMem;
for (i = 0; i < bus_cur->noMemRanges; i++) {
- if (ibmphp_find_resource (bus_prev, range_cur->start, &res, MEM) < 0)
+ if (ibmphp_find_resource (bus_prev, range_cur->start, &res, MEM) < 0)
return -EINVAL;
ibmphp_remove_resource (res);
if (bus_cur->noPFMemRanges) {
range_cur = bus_cur->rangePFMem;
for (i = 0; i < bus_cur->noPFMemRanges; i++) {
- if (ibmphp_find_resource (bus_prev, range_cur->start, &res, PFMEM) < 0)
+ if (ibmphp_find_resource (bus_prev, range_cur->start, &res, PFMEM) < 0)
return -EINVAL;
ibmphp_remove_resource (res);
}
/*
- * find the resource node in the bus
+ * find the resource node in the bus
* Input: Resource needed, start address of the resource, type of resource
*/
int ibmphp_find_resource (struct bus_node *bus, u32 start_address, struct resource_node **res, int flag)
err ("wrong type of flag\n");
return -EINVAL;
}
-
+
while (res_cur) {
if (res_cur->start == start_address) {
*res = res_cur;
} /* end for pfmem */
} /* end if */
} /* end list_for_each bus */
- return 0;
+ return 0;
}
int ibmphp_add_pfmem_from_mem (struct resource_node *pfmem)
list_for_each (tmp, &gbuses) {
tmp_prev = tmp->prev;
bus_cur = list_entry (tmp, struct bus_node, bus_list);
- if (flag)
+ if (flag)
*prev = list_entry (tmp_prev, struct bus_node, bus_list);
- if (bus_cur->busno == bus_number)
+ if (bus_cur->busno == bus_number)
return bus_cur;
}
struct range_node *range;
struct resource_node *res;
struct list_head *tmp;
-
+
debug_pci ("*****************START**********************\n");
if ((!list_empty(&gbuses)) && flags) {
return 1;
range_cur = range_cur->next;
}
-
+
return 0;
}
* Returns: none
* Note: this function doesn't take into account IO restrictions etc,
* so will only work for bridges with no video/ISA devices behind them It
- * also will not work for onboard PPB's that can have more than 1 *bus
+ * also will not work for onboard PPBs that can have more than 1 *bus
* behind them All these are TO DO.
* Also need to add more error checkings... (from fnc returns etc)
*/
case PCI_HEADER_TYPE_BRIDGE:
function = 0x8;
case PCI_HEADER_TYPE_MULTIBRIDGE:
- /* We assume here that only 1 bus behind the bridge
+ /* We assume here that only 1 bus behind the bridge
TO DO: add functionality for several:
temp = secondary;
while (temp < subordinate) {
}
*/
pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_SECONDARY_BUS, &sec_busno);
- bus_sec = find_bus_wprev (sec_busno, NULL, 0);
+ bus_sec = find_bus_wprev (sec_busno, NULL, 0);
/* this bus structure doesn't exist yet, PPB was configured during previous loading of ibmphp */
if (!bus_sec) {
bus_sec = alloc_error_bus (NULL, sec_busno, 1);
io->len = io->end - io->start + 1;
ibmphp_add_resource (io);
}
- }
+ }
pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_MEMORY_BASE, &start_mem_address);
pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_MEMORY_LIMIT, &end_mem_address);
}
module_put(slot->ops->owner);
-exit:
+exit:
if (retval)
return retval;
return count;
retval = ops->set_attention_status(slot->hotplug, attention);
module_put(ops->owner);
-exit:
+exit:
if (retval)
return retval;
return count;
retval = slot->ops->hardware_test(slot, test);
module_put(slot->ops->owner);
-exit:
+exit:
if (retval)
return retval;
return count;
* @hotplug: pointer to the slot whose info has changed
* @info: pointer to the info copy into the slot's info structure
*
- * @slot must have been registered with the pci
+ * @slot must have been registered with the pci
* hotplug subsystem previously with a call to pci_hp_register().
*
* Returns 0 if successful, anything else for an error.
{
return 0;
}
-#endif /* CONFIG_ACPI */
+#endif /* CONFIG_ACPI */
#endif /* _PCIEHP_H */
static int __initdata acpi_slot_detected;
static struct list_head __initdata dummy_slots = LIST_HEAD_INIT(dummy_slots);
-/* Dummy driver for dumplicate name detection */
+/* Dummy driver for duplicate name detection */
static int __init dummy_probe(struct pcie_device *dev)
{
u32 slot_cap;
pciehp_firmware_init();
retval = pcie_port_service_register(&hpdriver_portdrv);
- dbg("pcie_port_service_register = %d\n", retval);
- info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
+ dbg("pcie_port_service_register = %d\n", retval);
+ info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
if (retval)
dbg("Failure to register service\n");
{
/* Clamp to sane value */
if ((sec <= 0) || (sec > 60))
- sec = 2;
+ sec = 2;
ctrl->poll_timer.function = &int_poll_timeout;
ctrl->poll_timer.data = (unsigned long)ctrl;
ctrl_dbg(ctrl, "CMD_COMPLETED not clear after 1 sec\n");
} else if (!NO_CMD_CMPL(ctrl)) {
/*
- * This controller semms to notify of command completed
+ * This controller seems to notify of command completed
* event even though it supports none of power
* controller, attention led, power led and EMI.
*/
if (pciehp_writew(ctrl, PCI_EXP_SLTSTA, 0x1f))
goto abort_ctrl;
- /* Disable sotfware notification */
+ /* Disable software notification */
pcie_disable_notification(ctrl);
ctrl_info(ctrl, "HPC vendor_id %x device_id %x ss_vid %x ss_did %x\n",
do { \
if (debug) \
printk (KERN_DEBUG "%s: " format "\n", \
- MY_NAME , ## arg); \
+ MY_NAME , ## arg); \
} while (0)
#define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME , ## arg)
#define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME , ## arg)
hotplug_slot->release = &release_slot;
make_slot_name(slot);
hotplug_slot->ops = &skel_hotplug_slot_ops;
-
+
/*
* Initialize the slot info structure with some known
* good values.
get_attention_status(hotplug_slot, &info->attention_status);
get_latch_status(hotplug_slot, &info->latch_status);
get_adapter_status(hotplug_slot, &info->adapter_status);
-
+
dbg("registering slot %d\n", i);
retval = pci_hp_register(slot->hotplug_slot);
if (retval) {
pci_hp_deregister(slot->hotplug_slot);
}
}
-
+
static int __init pcihp_skel_init(void)
{
int retval;
if (!pcibios_find_pci_bus(dn))
return -EINVAL;
- /* If pci slot is hotplugable, use hotplug to remove it */
+ /* If pci slot is hotpluggable, use hotplug to remove it */
slot = find_php_slot(dn);
if (slot && rpaphp_deregister_slot(slot)) {
printk(KERN_ERR "%s: unable to remove hotplug slot %s\n",
extern bool rpaphp_debug;
#define dbg(format, arg...) \
do { \
- if (rpaphp_debug) \
+ if (rpaphp_debug) \
printk(KERN_DEBUG "%s: " format, \
- MY_NAME , ## arg); \
+ MY_NAME , ## arg); \
} while (0)
#define err(format, arg...) printk(KERN_ERR "%s: " format, MY_NAME , ## arg)
#define info(format, arg...) printk(KERN_INFO "%s: " format, MY_NAME , ## arg)
struct slot *alloc_slot_struct(struct device_node *dn, int drc_index, char *drc_name, int power_domain);
int rpaphp_register_slot(struct slot *slot);
int rpaphp_deregister_slot(struct slot *slot);
-
+
#endif /* _PPC64PHP_H */
for (i = 0; i < indexes[0]; i++) {
if ((unsigned int) indexes[i + 1] == *my_index) {
if (drc_name)
- *drc_name = name_tmp;
+ *drc_name = name_tmp;
if (drc_type)
*drc_type = type_tmp;
if (drc_index)
* rpaphp_add_slot -- declare a hotplug slot to the hotplug subsystem.
* @dn: device node of slot
*
- * This subroutine will register a hotplugable slot with the
+ * This subroutine will register a hotpluggable slot with the
* PCI hotplug infrastructure. This routine is typically called
* during boot time, if the hotplug slots are present at boot time,
* or is called later, by the dlpar add code, if the slot is
return -ENOMEM;
slot->type = simple_strtoul(type, NULL, 10);
-
+
dbg("Found drc-index:0x%x drc-name:%s drc-type:%s\n",
indexes[i + 1], name, type);
/*
* Unregister all of our slots with the pci_hotplug subsystem,
* and free up all memory that we had allocated.
- * memory will be freed in release_slot callback.
+ * memory will be freed in release_slot callback.
*/
list_for_each_safe(tmp, n, &rpaphp_slot_head) {
dbg("%s: slot must be power up to get sensor-state\n",
__func__);
- /* some slots have to be powered up
+ /* some slots have to be powered up
* before get-sensor will succeed.
*/
rc = rtas_set_power_level(slot->power_domain, POWER_ON,
return 0;
}
-
/*
- * RPA Virtual I/O device functions
+ * RPA Virtual I/O device functions
* Copyright (C) 2004 Linda Xie <lxie@us.ibm.com>
*
* All rights reserved.
int drc_index, char *drc_name, int power_domain)
{
struct slot *slot;
-
+
slot = kzalloc(sizeof(struct slot), GFP_KERNEL);
if (!slot)
goto error_nomem;
slot->hotplug_slot = kzalloc(sizeof(struct hotplug_slot), GFP_KERNEL);
if (!slot->hotplug_slot)
- goto error_slot;
+ goto error_slot;
slot->hotplug_slot->info = kzalloc(sizeof(struct hotplug_slot_info),
GFP_KERNEL);
if (!slot->hotplug_slot->info)
goto error_hpslot;
slot->name = kstrdup(drc_name, GFP_KERNEL);
if (!slot->name)
- goto error_info;
+ goto error_info;
slot->dn = dn;
slot->index = drc_index;
slot->power_domain = power_domain;
slot->hotplug_slot->private = slot;
slot->hotplug_slot->ops = &rpaphp_hotplug_slot_ops;
slot->hotplug_slot->release = &rpaphp_release_slot;
-
+
return (slot);
error_info:
list_for_each_entry(tmp_slot, &rpaphp_slot_head, rpaphp_slot_list) {
if (!strcmp(tmp_slot->name, slot->name))
return 1;
- }
+ }
return 0;
}
__func__, slot->name);
list_del(&slot->rpaphp_slot_list);
-
+
retval = pci_hp_deregister(php_slot);
if (retval)
err("Problem unregistering a slot %s\n", slot->name);
int retval;
int slotno;
- dbg("%s registering slot:path[%s] index[%x], name[%s] pdomain[%x] type[%d]\n",
+ dbg("%s registering slot:path[%s] index[%x], name[%s] pdomain[%x] type[%d]\n",
__func__, slot->dn->full_name, slot->index, slot->name,
slot->power_domain, slot->type);
if (is_registered(slot)) {
err("rpaphp_register_slot: slot[%s] is already registered\n", slot->name);
return -EAGAIN;
- }
+ }
if (slot->dn->child)
slotno = PCI_SLOT(PCI_DN(slot->dn->child)->devfn);
info("Slot [%s] registered\n", slot->name);
return 0;
}
-
/* offsets to the controller registers based on the above structure layout */
enum ctrl_offsets {
- BASE_OFFSET = offsetof(struct ctrl_reg, base_offset),
- SLOT_AVAIL1 = offsetof(struct ctrl_reg, slot_avail1),
+ BASE_OFFSET = offsetof(struct ctrl_reg, base_offset),
+ SLOT_AVAIL1 = offsetof(struct ctrl_reg, slot_avail1),
SLOT_AVAIL2 = offsetof(struct ctrl_reg, slot_avail2),
- SLOT_CONFIG = offsetof(struct ctrl_reg, slot_config),
+ SLOT_CONFIG = offsetof(struct ctrl_reg, slot_config),
SEC_BUS_CONFIG = offsetof(struct ctrl_reg, sec_bus_config),
MSI_CTRL = offsetof(struct ctrl_reg, msi_ctrl),
- PROG_INTERFACE = offsetof(struct ctrl_reg, prog_interface),
+ PROG_INTERFACE = offsetof(struct ctrl_reg, prog_interface),
CMD = offsetof(struct ctrl_reg, cmd),
CMD_STATUS = offsetof(struct ctrl_reg, cmd_status),
INTR_LOC = offsetof(struct ctrl_reg, intr_loc),
snprintf(name, SLOT_NAME_SIZE, "%d", slot->number);
hotplug_slot->ops = &shpchp_hotplug_slot_ops;
- ctrl_dbg(ctrl, "Registering domain:bus:dev=%04x:%02x:%02x "
- "hp_slot=%x sun=%x slot_device_offset=%x\n",
- pci_domain_nr(ctrl->pci_dev->subordinate),
- slot->bus, slot->device, slot->hp_slot, slot->number,
- ctrl->slot_device_offset);
+ ctrl_dbg(ctrl, "Registering domain:bus:dev=%04x:%02x:%02x "
+ "hp_slot=%x sun=%x slot_device_offset=%x\n",
+ pci_domain_nr(ctrl->pci_dev->subordinate),
+ slot->bus, slot->device, slot->hp_slot, slot->number,
+ ctrl->slot_device_offset);
retval = pci_hp_register(slot->hotplug_slot,
ctrl->pci_dev->subordinate, slot->device, name);
if (retval) {
#define SLOT_REG_RSVDZ_MASK ((1 << 15) | (7 << 21))
/*
- * SHPC Command Code definitnions
+ * SHPC Command Code definitions
*
* Slot Operation 00h - 3Fh
* Set Bus Segment Speed/Mode A 40h - 47h
struct resource tmp;
enum pci_bar_type type;
int reg = pci_iov_resource_bar(dev, resno, &type);
-
+
if (!reg)
return 0;
/**
* pci_lost_interrupt - reports a lost PCI interrupt
* @pdev: device whose interrupt is lost
- *
+ *
* The primary function of this routine is to report a lost interrupt
* in a standard way which users can recognise (instead of blaming the
* driver).
* @nvec: how many MSIs have been requested ?
* @type: are we checking for MSI or MSI-X ?
*
- * Look at global flags, the device itself, and its parent busses
+ * Look at global flags, the device itself, and its parent buses
* to determine if MSI/-X are supported for the device. If MSI/-X is
* supported return 0, else return an error code.
**/
* if (_PRW at S-state x)
* choose from highest power _SxD to lowest power _SxW
* else // no _PRW at S-state x
- * choose highest power _SxD or any lower power
+ * choose highest power _SxD or any lower power
*/
static pci_power_t acpi_pci_choose_state(struct pci_dev *pdev)
* __pci_device_probe - check if a driver wants to claim a specific PCI device
* @drv: driver to call to check if it wants the PCI device
* @pci_dev: PCI device being probed
- *
+ *
* returns 0 on success, else error.
* side-effect: pci_dev->driver is set to drv when drv claims pci_dev.
*/
* We would love to complain here if pci_dev->is_enabled is set, that
* the driver should have called pci_disable_device(), but the
* unfortunate fact is there are too many odd BIOS and bridge setups
- * that don't like drivers doing that all of the time.
+ * that don't like drivers doing that all of the time.
* Oh well, we can dream of sane hardware when we sleep, no matter how
* horrible the crap we have to deal with is when we are awake...
*/
* @drv: the driver structure to register
* @owner: owner module of drv
* @mod_name: module name string
- *
+ *
* Adds the driver structure to the list of registered drivers.
- * Returns a negative value on error, otherwise 0.
- * If no error occurred, the driver remains registered even if
+ * Returns a negative value on error, otherwise 0.
+ * If no error occurred, the driver remains registered even if
* no device was claimed during registration.
*/
int __pci_register_driver(struct pci_driver *drv, struct module *owner,
/**
* pci_unregister_driver - unregister a pci driver
* @drv: the driver structure to unregister
- *
+ *
* Deletes the driver structure from the list of registered PCI drivers,
* gives it a chance to clean up by calling its remove() function for
* each device it was responsible for, and marks those devices as
* pci_dev_driver - get the pci_driver of a device
* @dev: the device to query
*
- * Returns the appropriate pci_driver structure or %NULL if there is no
+ * Returns the appropriate pci_driver structure or %NULL if there is no
* registered driver for the device.
*/
struct pci_driver *
* pci_bus_match - Tell if a PCI device structure has a matching PCI device id structure
* @dev: the PCI device structure to match against
* @drv: the device driver to search for matching PCI device id structures
- *
+ *
* Used by a driver to check whether a PCI device present in the
* system is in its list of supported devices. Returns the matching
* pci_device_id structure or %NULL if there is no match.
*
* Copyright (C) 2008 Red Hat, Inc.
* Author:
- * Chris Wright
+ * Chris Wright
*
* This work is licensed under the terms of the GNU GPL, version 2.
*
* Usage is simple, allocate a new id to the stub driver and bind the
* device to it. For example:
- *
+ *
* # echo "8086 10f5" > /sys/bus/pci/drivers/pci-stub/new_id
* # echo -n 0000:00:19.0 > /sys/bus/pci/drivers/e1000e/unbind
* # echo -n 0000:00:19.0 > /sys/bus/pci/drivers/pci-stub/bind
*
* File attributes for PCI devices
*
- * Modeled after usb's driverfs.c
+ * Modeled after usb's driverfs.c
*
*/
if (kstrtoul(buf, 0, &val) < 0)
return -EINVAL;
- /* bad things may happen if the no_msi flag is changed
- * while some drivers are loaded */
+ /*
+ * Bad things may happen if the no_msi flag is changed
+ * while drivers are loaded.
+ */
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- /* Maybe pci devices without subordinate busses shouldn't even have this
- * attribute in the first place? */
+ /*
+ * Maybe devices without subordinate buses shouldn't have this
+ * attribute in the first place?
+ */
if (!pdev->subordinate)
return count;
size = dev->cfg_size - off;
count = size;
}
-
+
pci_config_pm_runtime_get(dev);
if ((off & 1) && size) {
off++;
size--;
}
-
+
if ((off & 3) && size > 2) {
u16 val = data[off - init_off];
val |= (u16) data[off - init_off + 1] << 8;
off += 4;
size -= 4;
}
-
+
if (size >= 2) {
u16 val = data[off - init_off];
val |= (u16) data[off - init_off + 1] << 8;
if (!pdev->rom_attr_enabled)
return -EINVAL;
-
+
rom = pci_map_rom(pdev, &size); /* size starts out as PCI window size */
if (!rom || !size)
return -EIO;
-
+
if (off >= size)
count = 0;
else {
if (off + count > size)
count = size - off;
-
+
memcpy_fromio(buf, rom + off, count);
}
pci_unmap_rom(pdev, rom);
-
+
return count;
}
}
/**
- * pci_find_capability - query for devices' capabilities
+ * pci_find_capability - query for devices' capabilities
* @dev: PCI device to query
* @cap: capability code
*
* device's PCI configuration space or 0 in case the device does not
* support it. Possible values for @cap:
*
- * %PCI_CAP_ID_PM Power Management
- * %PCI_CAP_ID_AGP Accelerated Graphics Port
- * %PCI_CAP_ID_VPD Vital Product Data
- * %PCI_CAP_ID_SLOTID Slot Identification
+ * %PCI_CAP_ID_PM Power Management
+ * %PCI_CAP_ID_AGP Accelerated Graphics Port
+ * %PCI_CAP_ID_VPD Vital Product Data
+ * %PCI_CAP_ID_SLOTID Slot Identification
* %PCI_CAP_ID_MSI Message Signalled Interrupts
- * %PCI_CAP_ID_CHSWP CompactPCI HotSwap
+ * %PCI_CAP_ID_CHSWP CompactPCI HotSwap
* %PCI_CAP_ID_PCIX PCI-X
* %PCI_CAP_ID_EXP PCI Express
*/
}
/**
- * pci_bus_find_capability - query for devices' capabilities
+ * pci_bus_find_capability - query for devices' capabilities
* @bus: the PCI bus to query
* @devfn: PCI device to query
* @cap: capability code
*
* Like pci_find_capability() but works for pci devices that do not have a
- * pci_dev structure set up yet.
+ * pci_dev structure set up yet.
*
* Returns the address of the requested capability structure within the
* device's PCI configuration space or 0 in case the device does not
return -EINVAL;
/* Validate current state:
- * Can enter D0 from any state, but if we can only go deeper
+ * Can enter D0 from any state, but if we can only go deeper
* to sleep if we're already in a low power state
*/
if (state != PCI_D0 && dev->current_state <= PCI_D3cold
}
}
-/**
+/**
* pci_restore_state - Restore the saved state of a PCI device
* @dev: - PCI device that we're dealing with
*/
* the device saved state.
* @dev: PCI device that we're dealing with
*
- * Rerturn NULL if no state or error.
+ * Return NULL if no state or error.
*/
struct pci_saved_state *pci_store_saved_state(struct pci_dev *dev)
{
* pci_dev_run_wake - Check if device can generate run-time wake-up events.
* @dev: Device to check.
*
- * Return true if the device itself is cabable of generating wake-up events
+ * Return true if the device itself is capable of generating wake-up events
* (through the platform or using the native PCIe PME) or if the device supports
* PME and one of its upstream bridges can generate wake-up events.
*/
switch (pci_pcie_type(pdev)) {
/*
* PCI/X-to-PCIe bridges are not specifically mentioned by the spec,
- * but since their primary inteface is PCI/X, we conservatively
+ * but since their primary interface is PCI/X, we conservatively
* handle them as we would a non-PCIe device.
*/
case PCI_EXP_TYPE_PCIE_BRIDGE:
/*
* PCIe 3.0, 6.12.1.2 specifies ACS capabilities that should be
* implemented by the remaining PCIe types to indicate peer-to-peer
- * capabilities, but only when they are part of a multifunciton
+ * capabilities, but only when they are part of a multifunction
* device. The footnote for section 6.12 indicates the specific
* PCIe types included here.
*/
}
/*
- * PCIe 3.0, 6.12.1.3 specifies no ACS capabilties are applicable
+ * PCIe 3.0, 6.12.1.3 specifies no ACS capabilities are applicable
* to single function devices with the exception of downstream ports.
*/
return true;
*
* If @exclusive is set, then the region is marked so that userspace
* is explicitly not allowed to map the resource via /dev/mem or
- * sysfs MMIO access.
+ * sysfs MMIO access.
*
* Returns 0 on success, or %EBUSY on error. A warning
* message is also printed on failure.
if (pci_resource_len(pdev, bar) == 0)
return 0;
-
+
if (pci_resource_flags(pdev, bar) & IORESOURCE_IO) {
if (!request_region(pci_resource_start(pdev, bar),
pci_resource_len(pdev, bar), res_name))
*
* The key difference that _exclusive makes it that userspace is
* explicitly not allowed to map the resource via /dev/mem or
- * sysfs.
+ * sysfs.
*/
int pci_request_region_exclusive(struct pci_dev *pdev, int bar, const char *res_name)
{
* successfully.
*
* pci_request_regions_exclusive() will mark the region so that
- * /dev/mem and the sysfs MMIO access will not be allowed.
+ * /dev/mem and the sysfs MMIO access will not be allowed.
*
* Returns 0 on success, or %EBUSY on error. A warning
* message is also printed on failure.
cmd |= PCI_COMMAND_INVALIDATE;
pci_write_config_word(dev, PCI_COMMAND, cmd);
}
-
+
return 0;
}
*
* NOTE: This causes the caller to sleep for twice the device power transition
* cooldown period, which for the D0->D3hot and D3hot->D0 transitions is 10 ms
- * by devault (i.e. unless the @dev's d3_delay field has a different value).
+ * by default (i.e. unless the @dev's d3_delay field has a different value).
* Moreover, only devices in D0 can be reset by this function.
*/
static int pci_pm_reset(struct pci_dev *dev, int probe)
pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl);
/*
* PCI spec v3.0 7.6.4.2 requires minimum Trst of 1ms. Double
- * this to 2ms to ensure that we meet the minium requirement.
+ * this to 2ms to ensure that we meet the minimum requirement.
*/
msleep(2);
return -EINVAL;
v = ffs(mps) - 8;
- if (v > dev->pcie_mpss)
+ if (v > dev->pcie_mpss)
return -EINVAL;
v <<= 5;
if (info->severity == AER_CORRECTABLE) {
/*
- * Correctable error does not need software intevention.
+ * Correctable error does not need software intervention.
* No need to go through error recovery process.
*/
pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
/*
* pcie_aspm_init_link_state: Initiate PCI express link state.
- * It is called after the pcie and its children devices are scaned.
+ * It is called after the pcie and its children devices are scanned.
* @pdev: the root port or switch downstream port
*/
void pcie_aspm_init_link_state(struct pci_dev *pdev)
static struct pcie_port_service_driver pcie_pme_driver = {
.name = "pcie_pme",
- .port_type = PCI_EXP_TYPE_ROOT_PORT,
- .service = PCIE_PORT_SERVICE_PME,
+ .port_type = PCI_EXP_TYPE_ROOT_PORT,
+ .service = PCIE_PORT_SERVICE_PME,
.probe = pcie_pme_probe,
.suspend = pcie_pme_suspend,
#define PCIE_PORT_DEVICE_MAXSERVICES 4
/*
* According to the PCI Express Base Specification 2.0, the indices of
- * the MSI-X table entires used by port services must not exceed 31
+ * the MSI-X table entries used by port services must not exceed 31
*/
#define PCIE_PORT_MAX_MSIX_ENTRIES 32
static int pcie_port_bus_match(struct device *dev, struct device_driver *drv);
struct bus_type pcie_port_bus_type = {
- .name = "pci_express",
- .match = pcie_port_bus_match,
+ .name = "pci_express",
+ .match = pcie_port_bus_match,
};
EXPORT_SYMBOL_GPL(pcie_port_bus_type);
* pcie_port_msix_add_entry - add entry to given array of MSI-X entries
* @entries: Array of MSI-X entries
* @new_entry: Index of the entry to add to the array
- * @nr_entries: Number of entries aleady in the array
+ * @nr_entries: Number of entries already in the array
*
* Return value: Position of the added entry in the array
*/
static void pcie_portdrv_remove(struct pci_dev *dev)
{
pcie_port_device_remove(dev);
- pci_disable_device(dev);
}
static int error_detected_iter(struct device *device, void *data)
.probe = pcie_portdrv_probe,
.remove = pcie_portdrv_remove,
- .err_handler = &pcie_portdrv_err_handler,
+ .err_handler = &pcie_portdrv_err_handler,
- .driver.pm = PCIE_PORTDRV_PM_OPS,
+ .driver.pm = PCIE_PORTDRV_PM_OPS,
};
static int __init dmi_pcie_pme_disable_msi(const struct dmi_system_id *d)
.ident = "MSI Wind U-100",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR,
- "MICRO-STAR INTERNATIONAL CO., LTD"),
+ "MICRO-STAR INTERNATIONAL CO., LTD"),
DMI_MATCH(DMI_PRODUCT_NAME, "U-100"),
},
},
index = 1;
else
goto out;
-
+
if (agp3) {
index += 2;
if (index == 5)
}
/* Disable MasterAbortMode during probing to avoid reporting
- of bus errors (in some architectures) */
+ of bus errors (in some architectures) */
pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &bctl);
pci_write_config_word(dev, PCI_BRIDGE_CONTROL,
bctl & ~PCI_BRIDGE_CTL_MASTER_ABORT);
* pci_setup_device - fill in class and map information of a device
* @dev: the device structure to fill
*
- * Initialize the device structure with information about the device's
+ * Initialize the device structure with information about the device's
* vendor,class,memory and IO-space addresses,IRQ lines etc.
* Called at initialisation of the PCI subsystem and by CardBus services.
* Returns 0 on success and negative if unknown type of device (not normal,
goto bad;
/* The PCI-to-PCI bridge spec requires that subtractive
decoding (i.e. transparent) bridge must have programming
- interface code of 0x01. */
+ interface code of 0x01. */
pci_read_irq(dev);
dev->transparent = ((dev->class & 0xff) == 1);
pci_read_bases(dev, 2, PCI_ROM_ADDRESS1);
* subsequent read will verify if the value is acceptable or not.
* If the MRRS value provided is not acceptable (e.g., too large),
* shrink the value until it is acceptable to the HW.
- */
+ */
while (mrrs != pcie_get_readrq(dev) && mrrs >= 128) {
rc = pcie_set_readrq(dev, mrrs);
if (!rc)
default:
ret = -EINVAL;
break;
- };
+ }
return ret;
}
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MELLANOX,PCI_DEVICE_ID_MELLANOX_TAVOR,quirk_mellanox_tavor);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MELLANOX,PCI_DEVICE_ID_MELLANOX_TAVOR_BRIDGE,quirk_mellanox_tavor);
-/* Deal with broken BIOS'es that neglect to enable passive release,
+/* Deal with broken BIOSes that neglect to enable passive release,
which can cause problems in combination with the 82441FX/PPro MTRRs */
static void quirk_passive_release(struct pci_dev *dev)
{
/* The VIA VP2/VP3/MVP3 seem to have some 'features'. There may be a workaround
but VIA don't answer queries. If you happen to have good contacts at VIA
- ask them for me please -- Alan
-
- This appears to be BIOS not version dependent. So presumably there is a
+ ask them for me please -- Alan
+
+ This appears to be BIOS not version dependent. So presumably there is a
chipset level fix */
-
+
static void quirk_isa_dma_hangs(struct pci_dev *dev)
{
if (!isa_dma_bridge_buggy) {
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_82C586_0, quirk_isa_dma_hangs);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_82C596, quirk_isa_dma_hangs);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82371SB_0, quirk_isa_dma_hangs);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, quirk_isa_dma_hangs);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, quirk_isa_dma_hangs);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NEC, PCI_DEVICE_ID_NEC_CBUS_1, quirk_isa_dma_hangs);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NEC, PCI_DEVICE_ID_NEC_CBUS_2, quirk_isa_dma_hangs);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NEC, PCI_DEVICE_ID_NEC_CBUS_3, quirk_isa_dma_hangs);
pci_pci_problems |= PCIPCI_TRITON;
}
}
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82437, quirk_triton);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82437VX, quirk_triton);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82439, quirk_triton);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82439TX, quirk_triton);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82437, quirk_triton);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82437VX, quirk_triton);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82439, quirk_triton);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82439TX, quirk_triton);
/*
* VIA Apollo KT133 needs PCI latency patch
* the info on which Mr Breese based his work.
*
* Updated based on further information from the site and also on
- * information provided by VIA
+ * information provided by VIA
*/
static void quirk_vialatency(struct pci_dev *dev)
{
u8 busarb;
/* Ok we have a potential problem chipset here. Now see if we have
a buggy southbridge */
-
+
p = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_82C686, NULL);
if (p!=NULL) {
/* 0x40 - 0x4f == 686B, 0x10 - 0x2f == 686A; thanks Dan Hollis */
if (p->revision < 0x10 || p->revision > 0x12)
goto exit;
}
-
+
/*
- * Ok we have the problem. Now set the PCI master grant to
+ * Ok we have the problem. Now set the PCI master grant to
* occur every master grant. The apparent bug is that under high
* PCI load (quite common in Linux of course) you can get data
* loss when the CPU is held off the bus for 3 bus master requests
*/
pci_read_config_byte(dev, 0x76, &busarb);
- /* Set bit 4 and bi 5 of byte 76 to 0x01
+ /* Set bit 4 and bi 5 of byte 76 to 0x01
"Master priority rotation on every PCI master grant */
busarb &= ~(1<<5);
busarb |= (1<<4);
* that DMA to AGP space. Latency must be set to 0xA and triton
* workaround applied too
* [Info kindly provided by ALi]
- */
+ */
static void quirk_alimagik(struct pci_dev *dev)
{
if ((pci_pci_problems&PCIPCI_ALIMAGIK)==0) {
pci_pci_problems |= PCIPCI_ALIMAGIK|PCIPCI_TRITON;
}
}
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1647, quirk_alimagik);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1651, quirk_alimagik);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1647, quirk_alimagik);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1651, quirk_alimagik);
/*
* Natoma has some interesting boundary conditions with Zoran stuff
pci_pci_problems |= PCIPCI_NATOMA;
}
}
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82441, quirk_natoma);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443LX_0, quirk_natoma);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443LX_1, quirk_natoma);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443BX_0, quirk_natoma);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443BX_1, quirk_natoma);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443BX_2, quirk_natoma);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82441, quirk_natoma);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443LX_0, quirk_natoma);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443LX_1, quirk_natoma);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443BX_0, quirk_natoma);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443BX_1, quirk_natoma);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443BX_2, quirk_natoma);
/*
* This chip can cause PCI parity errors if config register 0xA0 is read
/*
* For now we only print it out. Eventually we'll want to
* reserve it (at least if it's in the 0x1000+ range), but
- * let's get enough confirmation reports first.
+ * let's get enough confirmation reports first.
*/
base &= -size;
dev_info(&dev->dev, "%s PIO at %04x-%04x\n", name, base, base + size - 1);
}
/*
* For now we only print it out. Eventually we'll want to
- * reserve it, but let's get enough confirmation reports first.
+ * reserve it, but let's get enough confirmation reports first.
*/
base &= -size;
dev_info(&dev->dev, "%s MMIO at %04x-%04x\n", name, base, base + size - 1);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_TI, PCI_DEVICE_ID_TI_XIO2000A,
quirk_xio2000a);
-#ifdef CONFIG_X86_IO_APIC
+#ifdef CONFIG_X86_IO_APIC
#include <asm/io_apic.h>
static void quirk_via_ioapic(struct pci_dev *dev)
{
u8 tmp;
-
+
if (nr_ioapics < 1)
tmp = 0; /* nothing routed to external APIC */
else
tmp = 0x1f; /* all known bits (4-0) routed to external APIC */
-
+
dev_info(&dev->dev, "%sbling VIA external APIC routing\n",
tmp == 0 ? "Disa" : "Ena");
DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_82C686, quirk_via_ioapic);
/*
- * VIA 8237: Some BIOSs don't set the 'Bypass APIC De-Assert Message' Bit.
+ * VIA 8237: Some BIOSes don't set the 'Bypass APIC De-Assert Message' Bit.
* This leads to doubled level interrupt rates.
* Set this bit to get rid of cycle wastage.
* Otherwise uncritical.
static void quirk_disable_pxb(struct pci_dev *pdev)
{
u16 config;
-
+
if (pdev->revision != 0x04) /* Only C0 requires this */
return;
pci_read_config_word(pdev, 0x40, &config);
* On ASUS P4B boards, the SMBus PCI Device within the ICH2/4 southbridge
* is not activated. The myth is that Asus said that they do not want the
* users to be irritated by just another PCI Device in the Win98 device
- * manager. (see the file prog/hotplug/README.p4b in the lm_sensors
+ * manager. (see the file prog/hotplug/README.p4b in the lm_sensors
* package 2.7.0 for details)
*
- * The SMBus PCI Device can be activated by setting a bit in the ICH LPC
- * bridge. Unfortunately, this device has no subvendor/subdevice ID. So it
+ * The SMBus PCI Device can be activated by setting a bit in the ICH LPC
+ * bridge. Unfortunately, this device has no subvendor/subdevice ID. So it
* becomes necessary to do this tweak in two steps -- the chosen trigger
* is either the Host bridge (preferred) or on-board VGA controller.
*
static void asus_hides_smbus_lpc(struct pci_dev *dev)
{
u16 val;
-
+
if (likely(!asus_hides_smbus))
return;
dev_info(&dev->dev, "disabled boot interrupts on device [%04x:%04x]\n",
dev->vendor, dev->device);
}
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_10, quirk_disable_intel_boot_interrupt);
-DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_10, quirk_disable_intel_boot_interrupt);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_10, quirk_disable_intel_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_10, quirk_disable_intel_boot_interrupt);
/*
* disable boot interrupts on HT-1000
dev_info(&dev->dev, "disabled boot interrupts on device [%04x:%04x]\n",
dev->vendor, dev->device);
}
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_HT1000SB, quirk_disable_broadcom_boot_interrupt);
-DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_HT1000SB, quirk_disable_broadcom_boot_interrupt);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_HT1000SB, quirk_disable_broadcom_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_HT1000SB, quirk_disable_broadcom_boot_interrupt);
/*
* disable boot interrupts on AMD and ATI chipsets
dev_info(&dev->dev, "disabled boot interrupts on device [%04x:%04x]\n",
dev->vendor, dev->device);
}
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8111_SMBUS, quirk_disable_amd_8111_boot_interrupt);
-DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8111_SMBUS, quirk_disable_amd_8111_boot_interrupt);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8111_SMBUS, quirk_disable_amd_8111_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8111_SMBUS, quirk_disable_amd_8111_boot_interrupt);
#endif /* CONFIG_X86_IO_APIC */
/*
#ifdef CONFIG_PCI_MSI
/* Some chipsets do not support MSI. We cannot easily rely on setting
* PCI_BUS_FLAGS_NO_MSI in its bus flags because there are actually
- * some other busses controlled by the chipset even if Linux is not
- * aware of it. Instead of setting the flag on all busses in the
+ * some other buses controlled by the chipset even if Linux is not
+ * aware of it. Instead of setting the flag on all buses in the
* machine, simply disable MSI globally.
*/
static void quirk_disable_all_msi(struct pci_dev *dev)
nvenet_msi_disable);
/*
- * Some versions of the MCP55 bridge from nvidia have a legacy irq routing
- * config register. This register controls the routing of legacy interrupts
- * from devices that route through the MCP55. If this register is misprogramed
- * interrupts are only sent to the bsp, unlike conventional systems where the
- * irq is broadxast to all online cpus. Not having this register set
- * properly prevents kdump from booting up properly, so lets make sure that
- * we have it set correctly.
- * Note this is an undocumented register.
+ * Some versions of the MCP55 bridge from Nvidia have a legacy IRQ routing
+ * config register. This register controls the routing of legacy
+ * interrupts from devices that route through the MCP55. If this register
+ * is misprogrammed, interrupts are only sent to the BSP, unlike
+ * conventional systems where the IRQ is broadcast to all online CPUs. Not
+ * having this register set properly prevents kdump from booting up
+ * properly, so let's make sure that we have it set correctly.
+ * Note that this is an undocumented register.
*/
static void nvbridge_check_legacy_irq_routing(struct pci_dev *dev)
{
/* Allow manual resource allocation for PCI hotplug bridges
* via pci=hpmemsize=nnM and pci=hpiosize=nnM parameters. For
* some PCI-PCI hotplug bridges, like PLX 6254 (former HINT HB6),
- * kernel fails to allocate resources when hotplug device is
+ * kernel fails to allocate resources when hotplug device is
* inserted and PCI bus is rescanned.
*/
static void quirk_hotplug_bridge(struct pci_dev *dev)
{
int i;
- msi_remove_pci_irq_vectors(dev);
+ msi_remove_pci_irq_vectors(dev);
pci_cleanup_rom(dev);
for (i = 0; i < PCI_NUM_RESOURCES; i++) {
/*
- * PCI searching functions.
+ * PCI searching functions.
*
* Copyright (C) 1993 -- 1997 Drew Eckhardt, Frederic Potter,
* David Mosberger-Tang
* pci_find_next_bus - begin or continue searching for a PCI bus
* @from: Previous PCI bus found, or %NULL for new search.
*
- * Iterates through the list of known PCI busses. A new search is
+ * Iterates through the list of known PCI buses. A new search is
* initiated by passing %NULL as the @from argument. Otherwise if
* @from is not %NULL, searches continue from next device on the
* global list.
*/
-struct pci_bus *
+struct pci_bus *
pci_find_next_bus(const struct pci_bus *from)
{
struct list_head *n;
/**
* pci_get_slot - locate PCI device for a given PCI slot
* @bus: PCI bus on which desired PCI device resides
- * @devfn: encodes number of PCI slot in which the desired PCI
- * device resides and the logical device number within that slot
+ * @devfn: encodes number of PCI slot in which the desired PCI
+ * device resides and the logical device number within that slot
* in case of multi-function devices.
*
- * Given a PCI bus and slot/function number, the desired PCI device
+ * Given a PCI bus and slot/function number, the desired PCI device
* is located in the list of PCI devices.
* If the device is found, its reference count is increased and this
* function returns a pointer to its data structure. The caller must
(!(res->flags & IORESOURCE_ROM_ENABLE))))
add_to_list(fail_head,
dev_res->dev, res,
- 0 /* dont care */,
- 0 /* dont care */);
+ 0 /* don't care */,
+ 0 /* don't care */);
}
reset_resource(res);
}
if (!io) {
pci_write_config_word(bridge, PCI_IO_BASE, 0xf0f0);
pci_read_config_word(bridge, PCI_IO_BASE, &io);
- pci_write_config_word(bridge, PCI_IO_BASE, 0x0);
- }
- if (io)
+ pci_write_config_word(bridge, PCI_IO_BASE, 0x0);
+ }
+ if (io)
b_res[0].flags |= IORESOURCE_IO;
/* DECchip 21050 pass 2 errata: the bridge may miss an address
disconnect boundary by one PCI data phase.
resource_size_t min_align, align;
if (!b_res)
- return;
+ return;
min_align = window_alignment(bus, IORESOURCE_IO);
list_for_each_entry(dev, &bus->devices, bus_list) {
if (realloc_head && i >= PCI_IOV_RESOURCES &&
i <= PCI_IOV_RESOURCE_END) {
r->end = r->start - 1;
- add_to_list(realloc_head, dev, r, r_size, 0/* dont' care */);
+ add_to_list(realloc_head, dev, r, r_size, 0/* don't care */);
children_add_size += r_size;
continue;
}
/*
* first try will not touch pci bridge res
- * second and later try will clear small leaf bridge res
- * will stop till to the max deepth if can not find good one
+ * second and later try will clear small leaf bridge res
+ * will stop till to the max depth if can not find good one
*/
void pci_assign_unassigned_root_bus_resources(struct pci_bus *bus)
{
return 0;
}
-static int pci_revert_fw_address(struct resource *res, struct pci_dev *dev,
+static int pci_revert_fw_address(struct resource *res, struct pci_dev *dev,
int resno, resource_size_t size)
{
struct resource *root, *conflict;
static const char *pci_bus_speed_strings[] = {
"33 MHz PCI", /* 0x00 */
"66 MHz PCI", /* 0x01 */
- "66 MHz PCI-X", /* 0x02 */
+ "66 MHz PCI-X", /* 0x02 */
"100 MHz PCI-X", /* 0x03 */
"133 MHz PCI-X", /* 0x04 */
NULL, /* 0x05 */
default:
err = -EINVAL;
goto error;
- };
+ }
err = -EIO;
if (cfg_ret != PCIBIOS_SUCCESSFUL)
return 0;
}
+static void at91_rtc_shutdown(struct platform_device *pdev)
+{
+ /* Disable all interrupts */
+ at91_rtc_write(AT91_RTC_IDR, AT91_RTC_ACKUPD | AT91_RTC_ALARM |
+ AT91_RTC_SECEV | AT91_RTC_TIMEV |
+ AT91_RTC_CALEV);
+}
+
#ifdef CONFIG_PM_SLEEP
/* AT91RM9200 RTC Power management control */
static struct platform_driver at91_rtc_driver = {
.remove = __exit_p(at91_rtc_remove),
+ .shutdown = at91_rtc_shutdown,
.driver = {
.name = "at91_rtc",
.owner = THIS_MODULE,
struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
struct tcm_qla2xxx_tpg, se_tpg);
- return QLA_TPG_ATTRIB(tpg)->generate_node_acls;
+ return tpg->tpg_attrib.generate_node_acls;
}
static int tcm_qla2xxx_check_demo_mode_cache(struct se_portal_group *se_tpg)
struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
struct tcm_qla2xxx_tpg, se_tpg);
- return QLA_TPG_ATTRIB(tpg)->cache_dynamic_acls;
+ return tpg->tpg_attrib.cache_dynamic_acls;
}
static int tcm_qla2xxx_check_demo_write_protect(struct se_portal_group *se_tpg)
struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
struct tcm_qla2xxx_tpg, se_tpg);
- return QLA_TPG_ATTRIB(tpg)->demo_mode_write_protect;
+ return tpg->tpg_attrib.demo_mode_write_protect;
}
static int tcm_qla2xxx_check_prod_write_protect(struct se_portal_group *se_tpg)
struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
struct tcm_qla2xxx_tpg, se_tpg);
- return QLA_TPG_ATTRIB(tpg)->prod_mode_write_protect;
+ return tpg->tpg_attrib.prod_mode_write_protect;
}
static int tcm_qla2xxx_check_demo_mode_login_only(struct se_portal_group *se_tpg)
struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
struct tcm_qla2xxx_tpg, se_tpg);
- return QLA_TPG_ATTRIB(tpg)->demo_mode_login_only;
+ return tpg->tpg_attrib.demo_mode_login_only;
}
static struct se_node_acl *tcm_qla2xxx_alloc_fabric_acl(
struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg, \
struct tcm_qla2xxx_tpg, se_tpg); \
\
- return sprintf(page, "%u\n", QLA_TPG_ATTRIB(tpg)->name); \
+ return sprintf(page, "%u\n", tpg->tpg_attrib.name); \
} \
\
static ssize_t tcm_qla2xxx_tpg_attrib_store_##name( \
* By default allow READ-ONLY TPG demo-mode access w/ cached dynamic
* NodeACLs
*/
- QLA_TPG_ATTRIB(tpg)->generate_node_acls = 1;
- QLA_TPG_ATTRIB(tpg)->demo_mode_write_protect = 1;
- QLA_TPG_ATTRIB(tpg)->cache_dynamic_acls = 1;
- QLA_TPG_ATTRIB(tpg)->demo_mode_login_only = 1;
+ tpg->tpg_attrib.generate_node_acls = 1;
+ tpg->tpg_attrib.demo_mode_write_protect = 1;
+ tpg->tpg_attrib.cache_dynamic_acls = 1;
+ tpg->tpg_attrib.demo_mode_login_only = 1;
ret = core_tpg_register(&tcm_qla2xxx_fabric_configfs->tf_ops, wwn,
&tpg->se_tpg, tpg, TRANSPORT_TPG_TYPE_NORMAL);
/*
* Setup default attribute lists for various fabric->tf_cit_tmpl
*/
- TF_CIT_TMPL(fabric)->tfc_wwn_cit.ct_attrs = tcm_qla2xxx_wwn_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_base_cit.ct_attrs = tcm_qla2xxx_tpg_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_attrib_cit.ct_attrs =
+ fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = tcm_qla2xxx_wwn_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = tcm_qla2xxx_tpg_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs =
tcm_qla2xxx_tpg_attrib_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_param_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_np_base_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_base_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_param_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL;
/*
* Register the fabric for use within TCM
*/
/*
* Setup default attribute lists for various npiv_fabric->tf_cit_tmpl
*/
- TF_CIT_TMPL(npiv_fabric)->tfc_wwn_cit.ct_attrs = tcm_qla2xxx_wwn_attrs;
- TF_CIT_TMPL(npiv_fabric)->tfc_tpg_base_cit.ct_attrs = NULL;
- TF_CIT_TMPL(npiv_fabric)->tfc_tpg_attrib_cit.ct_attrs = NULL;
- TF_CIT_TMPL(npiv_fabric)->tfc_tpg_param_cit.ct_attrs = NULL;
- TF_CIT_TMPL(npiv_fabric)->tfc_tpg_np_base_cit.ct_attrs = NULL;
- TF_CIT_TMPL(npiv_fabric)->tfc_tpg_nacl_base_cit.ct_attrs = NULL;
- TF_CIT_TMPL(npiv_fabric)->tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
- TF_CIT_TMPL(npiv_fabric)->tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
- TF_CIT_TMPL(npiv_fabric)->tfc_tpg_nacl_param_cit.ct_attrs = NULL;
+ npiv_fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = tcm_qla2xxx_wwn_attrs;
+ npiv_fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = NULL;
+ npiv_fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL;
+ npiv_fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;
+ npiv_fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;
+ npiv_fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL;
+ npiv_fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
+ npiv_fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
+ npiv_fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL;
/*
* Register the npiv_fabric for use within TCM
*/
struct se_portal_group se_tpg;
};
-#define QLA_TPG_ATTRIB(tpg) (&(tpg)->tpg_attrib)
-
struct tcm_qla2xxx_fc_loopid {
struct se_node_acl *se_nacl;
};
int iscsi_task_attr;
int sam_task_attr;
- spin_lock_bh(&conn->sess->session_stats_lock);
- conn->sess->cmd_pdus++;
- if (conn->sess->se_sess->se_node_acl) {
- spin_lock(&conn->sess->se_sess->se_node_acl->stats_lock);
- conn->sess->se_sess->se_node_acl->num_cmds++;
- spin_unlock(&conn->sess->se_sess->se_node_acl->stats_lock);
- }
- spin_unlock_bh(&conn->sess->session_stats_lock);
+ atomic_long_inc(&conn->sess->cmd_pdus);
hdr = (struct iscsi_scsi_req *) buf;
payload_length = ntoh24(hdr->dlength);
int rc;
if (!payload_length) {
- pr_err("DataOUT payload is ZERO, protocol error.\n");
- return iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR,
- buf);
+ pr_warn("DataOUT payload is ZERO, ignoring.\n");
+ return 0;
}
/* iSCSI write */
- spin_lock_bh(&conn->sess->session_stats_lock);
- conn->sess->rx_data_octets += payload_length;
- if (conn->sess->se_sess->se_node_acl) {
- spin_lock(&conn->sess->se_sess->se_node_acl->stats_lock);
- conn->sess->se_sess->se_node_acl->write_bytes += payload_length;
- spin_unlock(&conn->sess->se_sess->se_node_acl->stats_lock);
- }
- spin_unlock_bh(&conn->sess->session_stats_lock);
+ atomic_long_add(payload_length, &conn->sess->rx_data_octets);
if (payload_length > conn->conn_ops->MaxXmitDataSegmentLength) {
pr_err("DataSegmentLength: %u is greater than"
static int iscsit_handle_data_out(struct iscsi_conn *conn, unsigned char *buf)
{
- struct iscsi_cmd *cmd;
+ struct iscsi_cmd *cmd = NULL;
struct iscsi_data *hdr = (struct iscsi_data *)buf;
int rc;
bool data_crc_failed = false;
(unsigned char *)hdr);
}
+ if (!(hdr->flags & ISCSI_FLAG_CMD_FINAL) ||
+ (hdr->flags & ISCSI_FLAG_TEXT_CONTINUE)) {
+ pr_err("Multi sequence text commands currently not supported\n");
+ return iscsit_reject_cmd(cmd, ISCSI_REASON_CMD_NOT_SUPPORTED,
+ (unsigned char *)hdr);
+ }
+
pr_debug("Got Text Request: ITT: 0x%08x, CmdSN: 0x%08x,"
" ExpStatSN: 0x%08x, Length: %u\n", hdr->itt, hdr->cmdsn,
hdr->exp_statsn, payload_length);
return -1;
}
- spin_lock_bh(&conn->sess->session_stats_lock);
- conn->sess->tx_data_octets += datain.length;
- if (conn->sess->se_sess->se_node_acl) {
- spin_lock(&conn->sess->se_sess->se_node_acl->stats_lock);
- conn->sess->se_sess->se_node_acl->read_bytes += datain.length;
- spin_unlock(&conn->sess->se_sess->se_node_acl->stats_lock);
- }
- spin_unlock_bh(&conn->sess->session_stats_lock);
+ atomic_long_add(datain.length, &conn->sess->tx_data_octets);
/*
* Special case for successfully execution w/ both DATAIN
* and Sense Data.
if (inc_stat_sn)
cmd->stat_sn = conn->stat_sn++;
- spin_lock_bh(&conn->sess->session_stats_lock);
- conn->sess->rsp_pdus++;
- spin_unlock_bh(&conn->sess->session_stats_lock);
+ atomic_long_inc(&conn->sess->rsp_pdus);
memset(hdr, 0, ISCSI_HDR_LEN);
hdr->opcode = ISCSI_OP_SCSI_CMD_RSP;
struct iscsi_tiqn *tiqn;
struct iscsi_tpg_np *tpg_np;
int buffer_len, end_of_buf = 0, len = 0, payload_len = 0;
+ int target_name_printed;
unsigned char buf[ISCSI_IQN_LEN+12]; /* iqn + "TargetName=" + \0 */
unsigned char *text_in = cmd->text_in_ptr, *text_ptr = NULL;
continue;
}
- len = sprintf(buf, "TargetName=%s", tiqn->tiqn);
- len += 1;
-
- if ((len + payload_len) > buffer_len) {
- end_of_buf = 1;
- goto eob;
- }
- memcpy(payload + payload_len, buf, len);
- payload_len += len;
+ target_name_printed = 0;
spin_lock(&tiqn->tiqn_tpg_lock);
list_for_each_entry(tpg, &tiqn->tiqn_tpg_list, tpg_list) {
+ /* If demo_mode_discovery=0 and generate_node_acls=0
+ * (demo mode dislabed) do not return
+ * TargetName+TargetAddress unless a NodeACL exists.
+ */
+
+ if ((tpg->tpg_attrib.generate_node_acls == 0) &&
+ (tpg->tpg_attrib.demo_mode_discovery == 0) &&
+ (!core_tpg_get_initiator_node_acl(&tpg->tpg_se_tpg,
+ cmd->conn->sess->sess_ops->InitiatorName))) {
+ continue;
+ }
+
spin_lock(&tpg->tpg_state_lock);
if ((tpg->tpg_state == TPG_STATE_FREE) ||
(tpg->tpg_state == TPG_STATE_INACTIVE)) {
struct iscsi_np *np = tpg_np->tpg_np;
bool inaddr_any = iscsit_check_inaddr_any(np);
+ if (!target_name_printed) {
+ len = sprintf(buf, "TargetName=%s",
+ tiqn->tiqn);
+ len += 1;
+
+ if ((len + payload_len) > buffer_len) {
+ spin_unlock(&tpg->tpg_np_lock);
+ spin_unlock(&tiqn->tiqn_tpg_lock);
+ end_of_buf = 1;
+ goto eob;
+ }
+ memcpy(payload + payload_len, buf, len);
+ payload_len += len;
+ target_name_printed = 1;
+ }
+
len = sprintf(buf, "TargetAddress="
"%s:%hu,%hu",
(inaddr_any == false) ?
* hit default in the switch below.
*/
memset(buffer, 0xff, ISCSI_HDR_LEN);
- spin_lock_bh(&conn->sess->session_stats_lock);
- conn->sess->conn_digest_errors++;
- spin_unlock_bh(&conn->sess->session_stats_lock);
+ atomic_long_inc(&conn->sess->conn_digest_errors);
} else {
pr_debug("Got HeaderDigest CRC32C"
" 0x%08x\n", checksum);
int iscsit_close_session(struct iscsi_session *sess)
{
- struct iscsi_portal_group *tpg = ISCSI_TPG_S(sess);
+ struct iscsi_portal_group *tpg = sess->tpg;
struct se_portal_group *se_tpg = &tpg->tpg_se_tpg;
if (atomic_read(&sess->nconn)) {
/*
* Set Identifier.
*/
- chap->id = ISCSI_TPG_C(conn)->tpg_chap_id++;
+ chap->id = conn->tpg->tpg_chap_id++;
*aic_len += sprintf(aic_str + *aic_len, "CHAP_I=%d", chap->id);
*aic_len += 1;
pr_debug("[server] Sending CHAP_I=%d\n", chap->id);
unsigned char client_digest[MD5_SIGNATURE_SIZE];
unsigned char server_digest[MD5_SIGNATURE_SIZE];
unsigned char chap_n[MAX_CHAP_N_SIZE], chap_r[MAX_RESPONSE_LENGTH];
+ size_t compare_len;
struct iscsi_chap *chap = conn->auth_protocol;
struct crypto_hash *tfm;
struct hash_desc desc;
goto out;
}
- if (memcmp(chap_n, auth->userid, strlen(auth->userid)) != 0) {
+ /* Include the terminating NULL in the compare */
+ compare_len = strlen(auth->userid) + 1;
+ if (strncmp(chap_n, auth->userid, compare_len) != 0) {
pr_err("CHAP_N values do not match!\n");
goto out;
}
struct iscsi_node_acl *nacl = container_of(se_nacl, struct iscsi_node_acl, \
se_node_acl); \
\
- return sprintf(page, "%u\n", ISCSI_NODE_ATTRIB(nacl)->name); \
+ return sprintf(page, "%u\n", nacl->node_attrib.name); \
} \
\
static ssize_t iscsi_nacl_attrib_store_##name( \
if (!se_nacl_new)
return ERR_PTR(-ENOMEM);
- cmdsn_depth = ISCSI_TPG_ATTRIB(tpg)->default_cmdsn_depth;
+ cmdsn_depth = tpg->tpg_attrib.default_cmdsn_depth;
/*
* se_nacl_new may be released by core_tpg_add_initiator_node_acl()
* when converting a NdoeACL from demo mode -> explict
return ERR_PTR(-ENOMEM);
}
- stats_cg->default_groups[0] = &NODE_STAT_GRPS(acl)->iscsi_sess_stats_group;
+ stats_cg->default_groups[0] = &acl->node_stat_grps.iscsi_sess_stats_group;
stats_cg->default_groups[1] = NULL;
- config_group_init_type_name(&NODE_STAT_GRPS(acl)->iscsi_sess_stats_group,
+ config_group_init_type_name(&acl->node_stat_grps.iscsi_sess_stats_group,
"iscsi_sess_stats", &iscsi_stat_sess_cit);
return se_nacl;
if (iscsit_get_tpg(tpg) < 0) \
return -EINVAL; \
\
- rb = sprintf(page, "%u\n", ISCSI_TPG_ATTRIB(tpg)->name); \
+ rb = sprintf(page, "%u\n", tpg->tpg_attrib.name); \
iscsit_put_tpg(tpg); \
return rb; \
} \
*/
DEF_TPG_ATTRIB(prod_mode_write_protect);
TPG_ATTR(prod_mode_write_protect, S_IRUGO | S_IWUSR);
+/*
+ * Define iscsi_tpg_attrib_s_demo_mode_discovery,
+ */
+DEF_TPG_ATTRIB(demo_mode_discovery);
+TPG_ATTR(demo_mode_discovery, S_IRUGO | S_IWUSR);
+/*
+ * Define iscsi_tpg_attrib_s_default_erl
+ */
+DEF_TPG_ATTRIB(default_erl);
+TPG_ATTR(default_erl, S_IRUGO | S_IWUSR);
static struct configfs_attribute *lio_target_tpg_attrib_attrs[] = {
&iscsi_tpg_attrib_authentication.attr,
&iscsi_tpg_attrib_cache_dynamic_acls.attr,
&iscsi_tpg_attrib_demo_mode_write_protect.attr,
&iscsi_tpg_attrib_prod_mode_write_protect.attr,
+ &iscsi_tpg_attrib_demo_mode_discovery.attr,
+ &iscsi_tpg_attrib_default_erl.attr,
NULL,
};
return ERR_PTR(-ENOMEM);
}
- stats_cg->default_groups[0] = &WWN_STAT_GRPS(tiqn)->iscsi_instance_group;
- stats_cg->default_groups[1] = &WWN_STAT_GRPS(tiqn)->iscsi_sess_err_group;
- stats_cg->default_groups[2] = &WWN_STAT_GRPS(tiqn)->iscsi_tgt_attr_group;
- stats_cg->default_groups[3] = &WWN_STAT_GRPS(tiqn)->iscsi_login_stats_group;
- stats_cg->default_groups[4] = &WWN_STAT_GRPS(tiqn)->iscsi_logout_stats_group;
+ stats_cg->default_groups[0] = &tiqn->tiqn_stat_grps.iscsi_instance_group;
+ stats_cg->default_groups[1] = &tiqn->tiqn_stat_grps.iscsi_sess_err_group;
+ stats_cg->default_groups[2] = &tiqn->tiqn_stat_grps.iscsi_tgt_attr_group;
+ stats_cg->default_groups[3] = &tiqn->tiqn_stat_grps.iscsi_login_stats_group;
+ stats_cg->default_groups[4] = &tiqn->tiqn_stat_grps.iscsi_logout_stats_group;
stats_cg->default_groups[5] = NULL;
- config_group_init_type_name(&WWN_STAT_GRPS(tiqn)->iscsi_instance_group,
+ config_group_init_type_name(&tiqn->tiqn_stat_grps.iscsi_instance_group,
"iscsi_instance", &iscsi_stat_instance_cit);
- config_group_init_type_name(&WWN_STAT_GRPS(tiqn)->iscsi_sess_err_group,
+ config_group_init_type_name(&tiqn->tiqn_stat_grps.iscsi_sess_err_group,
"iscsi_sess_err", &iscsi_stat_sess_err_cit);
- config_group_init_type_name(&WWN_STAT_GRPS(tiqn)->iscsi_tgt_attr_group,
+ config_group_init_type_name(&tiqn->tiqn_stat_grps.iscsi_tgt_attr_group,
"iscsi_tgt_attr", &iscsi_stat_tgt_attr_cit);
- config_group_init_type_name(&WWN_STAT_GRPS(tiqn)->iscsi_login_stats_group,
+ config_group_init_type_name(&tiqn->tiqn_stat_grps.iscsi_login_stats_group,
"iscsi_login_stats", &iscsi_stat_login_cit);
- config_group_init_type_name(&WWN_STAT_GRPS(tiqn)->iscsi_logout_stats_group,
+ config_group_init_type_name(&tiqn->tiqn_stat_grps.iscsi_logout_stats_group,
"iscsi_logout_stats", &iscsi_stat_logout_cit);
pr_debug("LIO_Target_ConfigFS: REGISTER -> %s\n", tiqn->tiqn);
struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd);
cmd->i_state = ISTATE_SEND_STATUS;
+
+ if (cmd->se_cmd.scsi_status || cmd->sense_reason) {
+ iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state);
+ return 0;
+ }
cmd->conn->conn_transport->iscsit_queue_status(cmd->conn, cmd);
return 0;
{
struct iscsi_portal_group *tpg = se_tpg->se_tpg_fabric_ptr;
- return ISCSI_TPG_ATTRIB(tpg)->default_cmdsn_depth;
+ return tpg->tpg_attrib.default_cmdsn_depth;
}
static int lio_tpg_check_demo_mode(struct se_portal_group *se_tpg)
{
struct iscsi_portal_group *tpg = se_tpg->se_tpg_fabric_ptr;
- return ISCSI_TPG_ATTRIB(tpg)->generate_node_acls;
+ return tpg->tpg_attrib.generate_node_acls;
}
static int lio_tpg_check_demo_mode_cache(struct se_portal_group *se_tpg)
{
struct iscsi_portal_group *tpg = se_tpg->se_tpg_fabric_ptr;
- return ISCSI_TPG_ATTRIB(tpg)->cache_dynamic_acls;
+ return tpg->tpg_attrib.cache_dynamic_acls;
}
static int lio_tpg_check_demo_mode_write_protect(
{
struct iscsi_portal_group *tpg = se_tpg->se_tpg_fabric_ptr;
- return ISCSI_TPG_ATTRIB(tpg)->demo_mode_write_protect;
+ return tpg->tpg_attrib.demo_mode_write_protect;
}
static int lio_tpg_check_prod_mode_write_protect(
{
struct iscsi_portal_group *tpg = se_tpg->se_tpg_fabric_ptr;
- return ISCSI_TPG_ATTRIB(tpg)->prod_mode_write_protect;
+ return tpg->tpg_attrib.prod_mode_write_protect;
}
static void lio_tpg_release_fabric_acl(
{
struct iscsi_node_acl *acl = container_of(se_acl, struct iscsi_node_acl,
se_node_acl);
+ struct se_portal_group *se_tpg = se_acl->se_tpg;
+ struct iscsi_portal_group *tpg = container_of(se_tpg,
+ struct iscsi_portal_group, tpg_se_tpg);
- ISCSI_NODE_ATTRIB(acl)->nacl = acl;
- iscsit_set_default_node_attribues(acl);
+ acl->node_attrib.nacl = acl;
+ iscsit_set_default_node_attribues(acl, tpg);
}
static int lio_check_stop_free(struct se_cmd *se_cmd)
* Setup default attribute lists for various fabric->tf_cit_tmpl
* sturct config_item_type's
*/
- TF_CIT_TMPL(fabric)->tfc_discovery_cit.ct_attrs = lio_target_discovery_auth_attrs;
- TF_CIT_TMPL(fabric)->tfc_wwn_cit.ct_attrs = lio_target_wwn_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_base_cit.ct_attrs = lio_target_tpg_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_attrib_cit.ct_attrs = lio_target_tpg_attrib_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_auth_cit.ct_attrs = lio_target_tpg_auth_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_param_cit.ct_attrs = lio_target_tpg_param_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_np_base_cit.ct_attrs = lio_target_portal_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_base_cit.ct_attrs = lio_target_initiator_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_attrib_cit.ct_attrs = lio_target_nacl_attrib_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_auth_cit.ct_attrs = lio_target_nacl_auth_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_param_cit.ct_attrs = lio_target_nacl_param_attrs;
+ fabric->tf_cit_tmpl.tfc_discovery_cit.ct_attrs = lio_target_discovery_auth_attrs;
+ fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = lio_target_wwn_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = lio_target_tpg_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = lio_target_tpg_attrib_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_auth_cit.ct_attrs = lio_target_tpg_auth_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = lio_target_tpg_param_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = lio_target_portal_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = lio_target_initiator_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = lio_target_nacl_attrib_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = lio_target_nacl_auth_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = lio_target_nacl_param_attrs;
ret = target_fabric_configfs_register(fabric);
if (ret < 0) {
#define NA_RANDOM_DATAIN_PDU_OFFSETS 0
#define NA_RANDOM_DATAIN_SEQ_OFFSETS 0
#define NA_RANDOM_R2T_OFFSETS 0
-#define NA_DEFAULT_ERL 0
-#define NA_DEFAULT_ERL_MAX 2
-#define NA_DEFAULT_ERL_MIN 0
/* struct iscsi_tpg_attrib sanity values */
#define TA_AUTHENTICATION 1
#define TA_DEMO_MODE_WRITE_PROTECT 1
/* Disabled by default in production mode w/ explict ACLs */
#define TA_PROD_MODE_WRITE_PROTECT 0
+#define TA_DEMO_MODE_DISCOVERY 1
+#define TA_DEFAULT_ERL 0
#define TA_CACHE_CORE_NPS 0
CMDSN_NORMAL_OPERATION = 0,
CMDSN_LOWER_THAN_EXP = 1,
CMDSN_HIGHER_THAN_EXP = 2,
+ CMDSN_MAXCMDSN_OVERRUN = 3,
};
/* Used for iscsi_handle_immediate_data() return values */
/* Used for session reference counting */
int session_usage_count;
int session_waiting_on_uc;
- u32 cmd_pdus;
- u32 rsp_pdus;
- u64 tx_data_octets;
- u64 rx_data_octets;
- u32 conn_digest_errors;
- u32 conn_timeout_errors;
+ atomic_long_t cmd_pdus;
+ atomic_long_t rsp_pdus;
+ atomic_long_t tx_data_octets;
+ atomic_long_t rx_data_octets;
+ atomic_long_t conn_digest_errors;
+ atomic_long_t conn_timeout_errors;
u64 creation_time;
- spinlock_t session_stats_lock;
/* Number of active connections */
atomic_t nconn;
atomic_t session_continuation;
struct se_node_acl se_node_acl;
};
-#define NODE_STAT_GRPS(nacl) (&(nacl)->node_stat_grps)
-
-#define ISCSI_NODE_ATTRIB(t) (&(t)->node_attrib)
-#define ISCSI_NODE_AUTH(t) (&(t)->node_auth)
-
struct iscsi_tpg_attrib {
u32 authentication;
u32 login_timeout;
u32 default_cmdsn_depth;
u32 demo_mode_write_protect;
u32 prod_mode_write_protect;
+ u32 demo_mode_discovery;
+ u32 default_erl;
struct iscsi_portal_group *tpg;
};
struct list_head tpg_list;
} ____cacheline_aligned;
-#define ISCSI_TPG_C(c) ((struct iscsi_portal_group *)(c)->tpg)
-#define ISCSI_TPG_LUN(c, l) ((iscsi_tpg_list_t *)(c)->tpg->tpg_lun_list_t[l])
-#define ISCSI_TPG_S(s) ((struct iscsi_portal_group *)(s)->tpg)
-#define ISCSI_TPG_ATTRIB(t) (&(t)->tpg_attrib)
-#define SE_TPG(tpg) (&(tpg)->tpg_se_tpg)
-
struct iscsi_wwn_stat_grps {
struct config_group iscsi_stat_group;
struct config_group iscsi_instance_group;
struct iscsi_logout_stats logout_stats;
} ____cacheline_aligned;
-#define WWN_STAT_GRPS(tiqn) (&(tiqn)->tiqn_stat_grps)
-
struct iscsit_global {
/* In core shutdown */
u32 in_shutdown;
cmd->maxcmdsn_inc = 1;
- if (!mutex_trylock(&sess->cmdsn_mutex)) {
- sess->max_cmd_sn += 1;
- pr_debug("Updated MaxCmdSN to 0x%08x\n", sess->max_cmd_sn);
- return;
- }
+ mutex_lock(&sess->cmdsn_mutex);
sess->max_cmd_sn += 1;
pr_debug("Updated MaxCmdSN to 0x%08x\n", sess->max_cmd_sn);
mutex_unlock(&sess->cmdsn_mutex);
static void iscsit_handle_time2retain_timeout(unsigned long data)
{
struct iscsi_session *sess = (struct iscsi_session *) data;
- struct iscsi_portal_group *tpg = ISCSI_TPG_S(sess);
+ struct iscsi_portal_group *tpg = sess->tpg;
struct se_portal_group *se_tpg = &tpg->tpg_se_tpg;
spin_lock_bh(&se_tpg->session_lock);
tiqn->sess_err_stats.last_sess_failure_type =
ISCSI_SESS_ERR_CXN_TIMEOUT;
tiqn->sess_err_stats.cxn_timeout_errors++;
- sess->conn_timeout_errors++;
+ atomic_long_inc(&sess->conn_timeout_errors);
spin_unlock(&tiqn->sess_err_stats.lock);
}
}
* Only start Time2Retain timer when the associated TPG is still in
* an ACTIVE (eg: not disabled or shutdown) state.
*/
- spin_lock(&ISCSI_TPG_S(sess)->tpg_state_lock);
- tpg_active = (ISCSI_TPG_S(sess)->tpg_state == TPG_STATE_ACTIVE);
- spin_unlock(&ISCSI_TPG_S(sess)->tpg_state_lock);
+ spin_lock(&sess->tpg->tpg_state_lock);
+ tpg_active = (sess->tpg->tpg_state == TPG_STATE_ACTIVE);
+ spin_unlock(&sess->tpg->tpg_state_lock);
if (!tpg_active)
return;
*/
int iscsit_stop_time2retain_timer(struct iscsi_session *sess)
{
- struct iscsi_portal_group *tpg = ISCSI_TPG_S(sess);
+ struct iscsi_portal_group *tpg = sess->tpg;
struct se_portal_group *se_tpg = &tpg->tpg_se_tpg;
if (sess->time2retain_timer_flags & ISCSI_TF_EXPIRED)
}
sess->creation_time = get_jiffies_64();
- spin_lock_init(&sess->session_stats_lock);
/*
* The FFP CmdSN window values will be allocated from the TPG's
* Initiator Node's ACL once the login has been successfully completed.
* Assign a new TPG Session Handle. Note this is protected with
* struct iscsi_portal_group->np_login_sem from iscsit_access_np().
*/
- sess->tsih = ++ISCSI_TPG_S(sess)->ntsih;
+ sess->tsih = ++sess->tpg->ntsih;
if (!sess->tsih)
- sess->tsih = ++ISCSI_TPG_S(sess)->ntsih;
+ sess->tsih = ++sess->tpg->ntsih;
/*
* Create the default params from user defined values..
*/
if (iscsi_copy_param_list(&conn->param_list,
- ISCSI_TPG_C(conn)->param_list, 1) < 0) {
+ conn->tpg->param_list, 1) < 0) {
iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
ISCSI_LOGIN_STATUS_NO_RESOURCES);
return -1;
* In our case, we have already located the struct iscsi_tiqn at this point.
*/
memset(buf, 0, 32);
- sprintf(buf, "TargetPortalGroupTag=%hu", ISCSI_TPG_S(sess)->tpgt);
+ sprintf(buf, "TargetPortalGroupTag=%hu", sess->tpg->tpgt);
if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
ISCSI_LOGIN_STATUS_NO_RESOURCES);
iscsi_login_set_conn_values(sess, conn, pdu->cid);
if (iscsi_copy_param_list(&conn->param_list,
- ISCSI_TPG_C(conn)->param_list, 0) < 0) {
+ conn->tpg->param_list, 0) < 0) {
iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
ISCSI_LOGIN_STATUS_NO_RESOURCES);
return -1;
* In our case, we have already located the struct iscsi_tiqn at this point.
*/
memset(buf, 0, 32);
- sprintf(buf, "TargetPortalGroupTag=%hu", ISCSI_TPG_S(sess)->tpgt);
+ sprintf(buf, "TargetPortalGroupTag=%hu", sess->tpg->tpgt);
if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
ISCSI_LOGIN_STATUS_NO_RESOURCES);
int stop_timer = 0;
struct iscsi_session *sess = conn->sess;
struct se_session *se_sess = sess->se_sess;
- struct iscsi_portal_group *tpg = ISCSI_TPG_S(sess);
+ struct iscsi_portal_group *tpg = sess->tpg;
struct se_portal_group *se_tpg = &tpg->tpg_se_tpg;
struct iscsi_thread_set *ts;
spin_lock_bh(&conn->sess->conn_lock);
if (conn->sess->session_state == TARG_SESS_STATE_FAILED) {
struct se_portal_group *se_tpg =
- &ISCSI_TPG_C(conn)->tpg_se_tpg;
+ &conn->tpg->tpg_se_tpg;
atomic_set(&conn->sess->session_continuation, 0);
spin_unlock_bh(&conn->sess->conn_lock);
if (len < 0)
return -1;
- if (len > max_length) {
+ if (len >= max_length) {
pr_err("Length of input: %d exceeds max_length:"
" %d\n", len, max_length);
return -1;
iscsi_nacl = container_of(se_nacl, struct iscsi_node_acl,
se_node_acl);
- auth = ISCSI_NODE_AUTH(iscsi_nacl);
+ auth = &iscsi_nacl->node_auth;
}
} else {
/*
return -1;
if (!iscsi_check_negotiated_keys(conn->param_list)) {
- if (ISCSI_TPG_ATTRIB(ISCSI_TPG_C(conn))->authentication &&
+ if (conn->tpg->tpg_attrib.authentication &&
!strncmp(param->value, NONE, 4)) {
pr_err("Initiator sent AuthMethod=None but"
" Target is enforcing iSCSI Authentication,"
return -1;
}
- if (ISCSI_TPG_ATTRIB(ISCSI_TPG_C(conn))->authentication &&
+ if (conn->tpg->tpg_attrib.authentication &&
!login->auth_complete)
return 0;
}
if (!login->auth_complete &&
- ISCSI_TPG_ATTRIB(ISCSI_TPG_C(conn))->authentication) {
+ conn->tpg->tpg_attrib.authentication) {
pr_err("Initiator is requesting CSG: 1, has not been"
" successfully authenticated, and the Target is"
" enforcing iSCSI Authentication, login failed.\n");
}
void iscsit_set_default_node_attribues(
- struct iscsi_node_acl *acl)
+ struct iscsi_node_acl *acl,
+ struct iscsi_portal_group *tpg)
{
struct iscsi_node_attrib *a = &acl->node_attrib;
a->random_datain_pdu_offsets = NA_RANDOM_DATAIN_PDU_OFFSETS;
a->random_datain_seq_offsets = NA_RANDOM_DATAIN_SEQ_OFFSETS;
a->random_r2t_offsets = NA_RANDOM_R2T_OFFSETS;
- a->default_erl = NA_DEFAULT_ERL;
+ a->default_erl = tpg->tpg_attrib.default_erl;
}
int iscsit_na_dataout_timeout(
#ifndef ISCSI_TARGET_NODEATTRIB_H
#define ISCSI_TARGET_NODEATTRIB_H
-extern void iscsit_set_default_node_attribues(struct iscsi_node_acl *);
+extern void iscsit_set_default_node_attribues(struct iscsi_node_acl *,
+ struct iscsi_portal_group *);
extern int iscsit_na_dataout_timeout(struct iscsi_node_acl *, u32);
extern int iscsit_na_dataout_timeout_retries(struct iscsi_node_acl *, u32);
extern int iscsit_na_nopin_timeout(struct iscsi_node_acl *, u32);
if (se_sess) {
sess = se_sess->fabric_sess_ptr;
if (sess)
- ret = snprintf(page, PAGE_SIZE, "%u\n", sess->cmd_pdus);
+ ret = snprintf(page, PAGE_SIZE, "%lu\n",
+ atomic_long_read(&sess->cmd_pdus));
}
spin_unlock_bh(&se_nacl->nacl_sess_lock);
if (se_sess) {
sess = se_sess->fabric_sess_ptr;
if (sess)
- ret = snprintf(page, PAGE_SIZE, "%u\n", sess->rsp_pdus);
+ ret = snprintf(page, PAGE_SIZE, "%lu\n",
+ atomic_long_read(&sess->rsp_pdus));
}
spin_unlock_bh(&se_nacl->nacl_sess_lock);
if (se_sess) {
sess = se_sess->fabric_sess_ptr;
if (sess)
- ret = snprintf(page, PAGE_SIZE, "%llu\n",
- (unsigned long long)sess->tx_data_octets);
+ ret = snprintf(page, PAGE_SIZE, "%lu\n",
+ atomic_long_read(&sess->tx_data_octets));
}
spin_unlock_bh(&se_nacl->nacl_sess_lock);
if (se_sess) {
sess = se_sess->fabric_sess_ptr;
if (sess)
- ret = snprintf(page, PAGE_SIZE, "%llu\n",
- (unsigned long long)sess->rx_data_octets);
+ ret = snprintf(page, PAGE_SIZE, "%lu\n",
+ atomic_long_read(&sess->rx_data_octets));
}
spin_unlock_bh(&se_nacl->nacl_sess_lock);
if (se_sess) {
sess = se_sess->fabric_sess_ptr;
if (sess)
- ret = snprintf(page, PAGE_SIZE, "%u\n",
- sess->conn_digest_errors);
+ ret = snprintf(page, PAGE_SIZE, "%lu\n",
+ atomic_long_read(&sess->conn_digest_errors));
}
spin_unlock_bh(&se_nacl->nacl_sess_lock);
if (se_sess) {
sess = se_sess->fabric_sess_ptr;
if (sess)
- ret = snprintf(page, PAGE_SIZE, "%u\n",
- sess->conn_timeout_errors);
+ ret = snprintf(page, PAGE_SIZE, "%lu\n",
+ atomic_long_read(&sess->conn_timeout_errors));
}
spin_unlock_bh(&se_nacl->nacl_sess_lock);
a->cache_dynamic_acls = TA_CACHE_DYNAMIC_ACLS;
a->demo_mode_write_protect = TA_DEMO_MODE_WRITE_PROTECT;
a->prod_mode_write_protect = TA_PROD_MODE_WRITE_PROTECT;
+ a->demo_mode_discovery = TA_DEMO_MODE_DISCOVERY;
+ a->default_erl = TA_DEFAULT_ERL;
}
int iscsit_tpg_add_portal_group(struct iscsi_tiqn *tiqn, struct iscsi_portal_group *tpg)
if (iscsi_create_default_params(&tpg->param_list) < 0)
goto err_out;
- ISCSI_TPG_ATTRIB(tpg)->tpg = tpg;
+ tpg->tpg_attrib.tpg = tpg;
spin_lock(&tpg->tpg_state_lock);
tpg->tpg_state = TPG_STATE_INACTIVE;
return -EINVAL;
}
- if (ISCSI_TPG_ATTRIB(tpg)->authentication) {
+ if (tpg->tpg_attrib.authentication) {
if (!strcmp(param->value, NONE)) {
ret = iscsi_update_param_value(param, CHAP);
if (ret)
return 0;
}
+
+int iscsit_ta_demo_mode_discovery(
+ struct iscsi_portal_group *tpg,
+ u32 flag)
+{
+ struct iscsi_tpg_attrib *a = &tpg->tpg_attrib;
+
+ if ((flag != 0) && (flag != 1)) {
+ pr_err("Illegal value %d\n", flag);
+ return -EINVAL;
+ }
+
+ a->demo_mode_discovery = flag;
+ pr_debug("iSCSI_TPG[%hu] - Demo Mode Discovery bit:"
+ " %s\n", tpg->tpgt, (a->demo_mode_discovery) ?
+ "ON" : "OFF");
+
+ return 0;
+}
+
+int iscsit_ta_default_erl(
+ struct iscsi_portal_group *tpg,
+ u32 default_erl)
+{
+ struct iscsi_tpg_attrib *a = &tpg->tpg_attrib;
+
+ if ((default_erl != 0) && (default_erl != 1) && (default_erl != 2)) {
+ pr_err("Illegal value for default_erl: %u\n", default_erl);
+ return -EINVAL;
+ }
+
+ a->default_erl = default_erl;
+ pr_debug("iSCSI_TPG[%hu] - DefaultERL: %u\n", tpg->tpgt, a->default_erl);
+
+ return 0;
+}
extern int iscsit_ta_cache_dynamic_acls(struct iscsi_portal_group *, u32);
extern int iscsit_ta_demo_mode_write_protect(struct iscsi_portal_group *, u32);
extern int iscsit_ta_prod_mode_write_protect(struct iscsi_portal_group *, u32);
+extern int iscsit_ta_demo_mode_discovery(struct iscsi_portal_group *, u32);
+extern int iscsit_ta_default_erl(struct iscsi_portal_group *, u32);
#endif /* ISCSI_TARGET_TPG_H */
*/
if (iscsi_sna_gt(cmdsn, sess->max_cmd_sn)) {
pr_err("Received CmdSN: 0x%08x is greater than"
- " MaxCmdSN: 0x%08x, protocol error.\n", cmdsn,
+ " MaxCmdSN: 0x%08x, ignoring.\n", cmdsn,
sess->max_cmd_sn);
- ret = CMDSN_ERROR_CANNOT_RECOVER;
+ ret = CMDSN_MAXCMDSN_OVERRUN;
} else if (cmdsn == sess->exp_cmd_sn) {
sess->exp_cmd_sn++;
ret = CMDSN_HIGHER_THAN_EXP;
break;
case CMDSN_LOWER_THAN_EXP:
+ case CMDSN_MAXCMDSN_OVERRUN:
+ default:
cmd->i_state = ISTATE_REMOVE;
iscsit_add_cmd_to_immediate_queue(cmd, conn, cmd->i_state);
- ret = cmdsn_ret;
- break;
- default:
- reason = ISCSI_REASON_PROTOCOL_ERROR;
- reject = true;
- ret = cmdsn_ret;
+ /*
+ * Existing callers for iscsit_sequence_cmd() will silently
+ * ignore commands with CMDSN_LOWER_THAN_EXP, so force this
+ * return for CMDSN_MAXCMDSN_OVERRUN as well..
+ */
+ ret = CMDSN_LOWER_THAN_EXP;
break;
}
mutex_unlock(&conn->sess->cmdsn_mutex);
tiqn->sess_err_stats.last_sess_failure_type =
ISCSI_SESS_ERR_CXN_TIMEOUT;
tiqn->sess_err_stats.cxn_timeout_errors++;
- conn->sess->conn_timeout_errors++;
+ atomic_long_inc(&conn->sess->conn_timeout_errors);
spin_unlock_bh(&tiqn->sess_err_stats.lock);
}
}
return sdev->queue_depth;
}
+static int tcm_loop_change_queue_type(struct scsi_device *sdev, int tag)
+{
+ if (sdev->tagged_supported) {
+ scsi_set_tag_type(sdev, tag);
+
+ if (tag)
+ scsi_activate_tcq(sdev, sdev->queue_depth);
+ else
+ scsi_deactivate_tcq(sdev, sdev->queue_depth);
+ } else
+ tag = 0;
+
+ return tag;
+}
+
/*
* Locate the SAM Task Attr from struct scsi_cmnd *
*/
set_host_byte(sc, DID_NO_CONNECT);
goto out_done;
}
-
+ if (tl_tpg->tl_transport_status == TCM_TRANSPORT_OFFLINE) {
+ set_host_byte(sc, DID_TRANSPORT_DISRUPTED);
+ goto out_done;
+ }
tl_nexus = tl_hba->tl_nexus;
if (!tl_nexus) {
scmd_printk(KERN_ERR, sc, "TCM_Loop I_T Nexus"
}
tl_cmd->sc = sc;
+ tl_cmd->sc_cmd_tag = sc->tag;
INIT_WORK(&tl_cmd->work, tcm_loop_submission_work);
queue_work(tcm_loop_workqueue, &tl_cmd->work);
return 0;
* Called from SCSI EH process context to issue a LUN_RESET TMR
* to struct scsi_device
*/
-static int tcm_loop_device_reset(struct scsi_cmnd *sc)
+static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg,
+ struct tcm_loop_nexus *tl_nexus,
+ int lun, int task, enum tcm_tmreq_table tmr)
{
struct se_cmd *se_cmd = NULL;
- struct se_portal_group *se_tpg;
struct se_session *se_sess;
+ struct se_portal_group *se_tpg;
struct tcm_loop_cmd *tl_cmd = NULL;
- struct tcm_loop_hba *tl_hba;
- struct tcm_loop_nexus *tl_nexus;
struct tcm_loop_tmr *tl_tmr = NULL;
- struct tcm_loop_tpg *tl_tpg;
- int ret = FAILED, rc;
- /*
- * Locate the tcm_loop_hba_t pointer
- */
- tl_hba = *(struct tcm_loop_hba **)shost_priv(sc->device->host);
- /*
- * Locate the tl_nexus and se_sess pointers
- */
- tl_nexus = tl_hba->tl_nexus;
- if (!tl_nexus) {
- pr_err("Unable to perform device reset without"
- " active I_T Nexus\n");
- return FAILED;
- }
- se_sess = tl_nexus->se_sess;
- /*
- * Locate the tl_tpg and se_tpg pointers from TargetID in sc->device->id
- */
- tl_tpg = &tl_hba->tl_hba_tpgs[sc->device->id];
- se_tpg = &tl_tpg->tl_se_tpg;
+ int ret = TMR_FUNCTION_FAILED, rc;
tl_cmd = kmem_cache_zalloc(tcm_loop_cmd_cache, GFP_KERNEL);
if (!tl_cmd) {
pr_err("Unable to allocate memory for tl_cmd\n");
- return FAILED;
+ return ret;
}
tl_tmr = kzalloc(sizeof(struct tcm_loop_tmr), GFP_KERNEL);
init_waitqueue_head(&tl_tmr->tl_tmr_wait);
se_cmd = &tl_cmd->tl_se_cmd;
+ se_tpg = &tl_tpg->tl_se_tpg;
+ se_sess = tl_nexus->se_sess;
/*
* Initialize struct se_cmd descriptor from target_core_mod infrastructure
*/
DMA_NONE, MSG_SIMPLE_TAG,
&tl_cmd->tl_sense_buf[0]);
- rc = core_tmr_alloc_req(se_cmd, tl_tmr, TMR_LUN_RESET, GFP_KERNEL);
+ rc = core_tmr_alloc_req(se_cmd, tl_tmr, tmr, GFP_KERNEL);
if (rc < 0)
goto release;
+
+ if (tmr == TMR_ABORT_TASK)
+ se_cmd->se_tmr_req->ref_task_tag = task;
+
/*
- * Locate the underlying TCM struct se_lun from sc->device->lun
+ * Locate the underlying TCM struct se_lun
*/
- if (transport_lookup_tmr_lun(se_cmd, sc->device->lun) < 0)
+ if (transport_lookup_tmr_lun(se_cmd, lun) < 0) {
+ ret = TMR_LUN_DOES_NOT_EXIST;
goto release;
+ }
/*
- * Queue the TMR to TCM Core and sleep waiting for tcm_loop_queue_tm_rsp()
- * to wake us up.
+ * Queue the TMR to TCM Core and sleep waiting for
+ * tcm_loop_queue_tm_rsp() to wake us up.
*/
transport_generic_handle_tmr(se_cmd);
wait_event(tl_tmr->tl_tmr_wait, atomic_read(&tl_tmr->tmr_complete));
* The TMR LUN_RESET has completed, check the response status and
* then release allocations.
*/
- ret = (se_cmd->se_tmr_req->response == TMR_FUNCTION_COMPLETE) ?
- SUCCESS : FAILED;
+ ret = se_cmd->se_tmr_req->response;
release:
if (se_cmd)
transport_generic_free_cmd(se_cmd, 1);
return ret;
}
+static int tcm_loop_abort_task(struct scsi_cmnd *sc)
+{
+ struct tcm_loop_hba *tl_hba;
+ struct tcm_loop_nexus *tl_nexus;
+ struct tcm_loop_tpg *tl_tpg;
+ int ret = FAILED;
+
+ /*
+ * Locate the tcm_loop_hba_t pointer
+ */
+ tl_hba = *(struct tcm_loop_hba **)shost_priv(sc->device->host);
+ /*
+ * Locate the tl_nexus and se_sess pointers
+ */
+ tl_nexus = tl_hba->tl_nexus;
+ if (!tl_nexus) {
+ pr_err("Unable to perform device reset without"
+ " active I_T Nexus\n");
+ return FAILED;
+ }
+
+ /*
+ * Locate the tl_tpg pointer from TargetID in sc->device->id
+ */
+ tl_tpg = &tl_hba->tl_hba_tpgs[sc->device->id];
+ ret = tcm_loop_issue_tmr(tl_tpg, tl_nexus, sc->device->lun,
+ sc->tag, TMR_ABORT_TASK);
+ return (ret == TMR_FUNCTION_COMPLETE) ? SUCCESS : FAILED;
+}
+
+/*
+ * Called from SCSI EH process context to issue a LUN_RESET TMR
+ * to struct scsi_device
+ */
+static int tcm_loop_device_reset(struct scsi_cmnd *sc)
+{
+ struct tcm_loop_hba *tl_hba;
+ struct tcm_loop_nexus *tl_nexus;
+ struct tcm_loop_tpg *tl_tpg;
+ int ret = FAILED;
+
+ /*
+ * Locate the tcm_loop_hba_t pointer
+ */
+ tl_hba = *(struct tcm_loop_hba **)shost_priv(sc->device->host);
+ /*
+ * Locate the tl_nexus and se_sess pointers
+ */
+ tl_nexus = tl_hba->tl_nexus;
+ if (!tl_nexus) {
+ pr_err("Unable to perform device reset without"
+ " active I_T Nexus\n");
+ return FAILED;
+ }
+ /*
+ * Locate the tl_tpg pointer from TargetID in sc->device->id
+ */
+ tl_tpg = &tl_hba->tl_hba_tpgs[sc->device->id];
+ ret = tcm_loop_issue_tmr(tl_tpg, tl_nexus, sc->device->lun,
+ 0, TMR_LUN_RESET);
+ return (ret == TMR_FUNCTION_COMPLETE) ? SUCCESS : FAILED;
+}
+
+static int tcm_loop_target_reset(struct scsi_cmnd *sc)
+{
+ struct tcm_loop_hba *tl_hba;
+ struct tcm_loop_tpg *tl_tpg;
+
+ /*
+ * Locate the tcm_loop_hba_t pointer
+ */
+ tl_hba = *(struct tcm_loop_hba **)shost_priv(sc->device->host);
+ if (!tl_hba) {
+ pr_err("Unable to perform device reset without"
+ " active I_T Nexus\n");
+ return FAILED;
+ }
+ /*
+ * Locate the tl_tpg pointer from TargetID in sc->device->id
+ */
+ tl_tpg = &tl_hba->tl_hba_tpgs[sc->device->id];
+ if (tl_tpg) {
+ tl_tpg->tl_transport_status = TCM_TRANSPORT_ONLINE;
+ return SUCCESS;
+ }
+ return FAILED;
+}
+
static int tcm_loop_slave_alloc(struct scsi_device *sd)
{
set_bit(QUEUE_FLAG_BIDI, &sd->request_queue->queue_flags);
static int tcm_loop_slave_configure(struct scsi_device *sd)
{
+ if (sd->tagged_supported) {
+ scsi_activate_tcq(sd, sd->queue_depth);
+ scsi_adjust_queue_depth(sd, MSG_SIMPLE_TAG,
+ sd->host->cmd_per_lun);
+ } else {
+ scsi_adjust_queue_depth(sd, 0,
+ sd->host->cmd_per_lun);
+ }
+
return 0;
}
.name = "TCM_Loopback",
.queuecommand = tcm_loop_queuecommand,
.change_queue_depth = tcm_loop_change_queue_depth,
+ .change_queue_type = tcm_loop_change_queue_type,
+ .eh_abort_handler = tcm_loop_abort_task,
.eh_device_reset_handler = tcm_loop_device_reset,
+ .eh_target_reset_handler = tcm_loop_target_reset,
.can_queue = 1024,
.this_id = -1,
.sg_tablesize = 256,
static u32 tcm_loop_get_task_tag(struct se_cmd *se_cmd)
{
- return 1;
+ struct tcm_loop_cmd *tl_cmd = container_of(se_cmd,
+ struct tcm_loop_cmd, tl_se_cmd);
+
+ return tl_cmd->sc_cmd_tag;
}
static int tcm_loop_get_cmd_state(struct se_cmd *se_cmd)
struct tcm_loop_nexus *tl_nexus;
struct tcm_loop_hba *tl_hba = tpg->tl_hba;
- tl_nexus = tpg->tl_hba->tl_nexus;
+ if (!tl_hba)
+ return -ENODEV;
+
+ tl_nexus = tl_hba->tl_nexus;
if (!tl_nexus)
return -ENODEV;
TF_TPG_BASE_ATTR(tcm_loop, nexus, S_IRUGO | S_IWUSR);
+static ssize_t tcm_loop_tpg_show_transport_status(
+ struct se_portal_group *se_tpg,
+ char *page)
+{
+ struct tcm_loop_tpg *tl_tpg = container_of(se_tpg,
+ struct tcm_loop_tpg, tl_se_tpg);
+ const char *status = NULL;
+ ssize_t ret = -EINVAL;
+
+ switch (tl_tpg->tl_transport_status) {
+ case TCM_TRANSPORT_ONLINE:
+ status = "online";
+ break;
+ case TCM_TRANSPORT_OFFLINE:
+ status = "offline";
+ break;
+ default:
+ break;
+ }
+
+ if (status)
+ ret = snprintf(page, PAGE_SIZE, "%s\n", status);
+
+ return ret;
+}
+
+static ssize_t tcm_loop_tpg_store_transport_status(
+ struct se_portal_group *se_tpg,
+ const char *page,
+ size_t count)
+{
+ struct tcm_loop_tpg *tl_tpg = container_of(se_tpg,
+ struct tcm_loop_tpg, tl_se_tpg);
+
+ if (!strncmp(page, "online", 6)) {
+ tl_tpg->tl_transport_status = TCM_TRANSPORT_ONLINE;
+ return count;
+ }
+ if (!strncmp(page, "offline", 7)) {
+ tl_tpg->tl_transport_status = TCM_TRANSPORT_OFFLINE;
+ return count;
+ }
+ return -EINVAL;
+}
+
+TF_TPG_BASE_ATTR(tcm_loop, transport_status, S_IRUGO | S_IWUSR);
+
static struct configfs_attribute *tcm_loop_tpg_attrs[] = {
&tcm_loop_tpg_nexus.attr,
+ &tcm_loop_tpg_transport_status.attr,
NULL,
};
/*
* Setup default attribute lists for various fabric->tf_cit_tmpl
*/
- TF_CIT_TMPL(fabric)->tfc_wwn_cit.ct_attrs = tcm_loop_wwn_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_base_cit.ct_attrs = tcm_loop_tpg_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_attrib_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_param_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_np_base_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = tcm_loop_wwn_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = tcm_loop_tpg_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;
/*
* Once fabric->tf_ops has been setup, now register the fabric for
* use within TCM
struct tcm_loop_cmd {
/* State of Linux/SCSI CDB+Data descriptor */
u32 sc_cmd_state;
+ /* Tagged command queueing */
+ u32 sc_cmd_tag;
/* Pointer to the CDB+Data descriptor from Linux/SCSI subsystem */
struct scsi_cmnd *sc;
/* The TCM I/O descriptor that is accessed via container_of() */
struct se_node_acl se_node_acl;
};
+#define TCM_TRANSPORT_ONLINE 0
+#define TCM_TRANSPORT_OFFLINE 1
+
struct tcm_loop_tpg {
unsigned short tl_tpgt;
+ unsigned short tl_transport_status;
atomic_t tl_tpg_port_count;
struct se_portal_group tl_se_tpg;
struct tcm_loop_hba *tl_hba;
/*
* Setup default attribute lists for various fabric->tf_cit_tmpl
*/
- TF_CIT_TMPL(fabric)->tfc_wwn_cit.ct_attrs = sbp_wwn_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_base_cit.ct_attrs = sbp_tpg_base_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_attrib_cit.ct_attrs = sbp_tpg_attrib_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_param_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_np_base_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_base_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_param_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = sbp_wwn_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = sbp_tpg_base_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = sbp_tpg_attrib_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL;
ret = target_fabric_configfs_register(fabric);
if (ret < 0) {
static sense_reason_t core_alua_check_transition(int state, int *primary);
static int core_alua_set_tg_pt_secondary_state(
struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem,
- struct se_port *port, int explict, int offline);
+ struct se_port *port, int explicit, int offline);
static u16 alua_lu_gps_counter;
static u32 alua_lu_gps_count;
/*
* Set supported ASYMMETRIC ACCESS State bits
*/
- buf[off] = 0x80; /* T_SUP */
- buf[off] |= 0x40; /* O_SUP */
- buf[off] |= 0x8; /* U_SUP */
- buf[off] |= 0x4; /* S_SUP */
- buf[off] |= 0x2; /* AN_SUP */
- buf[off++] |= 0x1; /* AO_SUP */
+ buf[off++] |= tg_pt_gp->tg_pt_gp_alua_supported_states;
/*
* TARGET PORT GROUP
*/
if (ext_hdr != 0) {
buf[4] = 0x10;
/*
- * Set the implict transition time (in seconds) for the application
+ * Set the implicit transition time (in seconds) for the application
* client to use as a base for it's transition timeout value.
*
* Use the current tg_pt_gp_mem -> tg_pt_gp membership from the LUN
spin_lock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
tg_pt_gp = tg_pt_gp_mem->tg_pt_gp;
if (tg_pt_gp)
- buf[5] = tg_pt_gp->tg_pt_gp_implict_trans_secs;
+ buf[5] = tg_pt_gp->tg_pt_gp_implicit_trans_secs;
spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
}
}
}
/*
- * SET_TARGET_PORT_GROUPS for explict ALUA operation.
+ * SET_TARGET_PORT_GROUPS for explicit ALUA operation.
*
* See spc4r17 section 6.35
*/
return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
/*
- * Determine if explict ALUA via SET_TARGET_PORT_GROUPS is allowed
+ * Determine if explicit ALUA via SET_TARGET_PORT_GROUPS is allowed
* for the local tg_pt_gp.
*/
l_tg_pt_gp_mem = l_port->sep_alua_tg_pt_gp_mem;
}
spin_unlock(&l_tg_pt_gp_mem->tg_pt_gp_mem_lock);
- if (!(l_tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICT_ALUA)) {
+ if (!(l_tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICIT_ALUA)) {
pr_debug("Unable to process SET_TARGET_PORT_GROUPS"
- " while TPGS_EXPLICT_ALUA is disabled\n");
+ " while TPGS_EXPLICIT_ALUA is disabled\n");
rc = TCM_UNSUPPORTED_SCSI_OPCODE;
goto out;
}
spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
} else {
/*
- * Extact the RELATIVE TARGET PORT IDENTIFIER to identify
+ * Extract the RELATIVE TARGET PORT IDENTIFIER to identify
* the Target Port in question for the the incoming
* SET_TARGET_PORT_GROUPS op.
*/
u8 *alua_ascq)
{
/*
- * Allowed CDBs for ALUA_ACCESS_STATE_TRANSITIO as defined by
+ * Allowed CDBs for ALUA_ACCESS_STATE_TRANSITION as defined by
* spc4r17 section 5.9.2.5
*/
switch (cdb[0]) {
}
/*
- * return 1: Is used to signal LUN not accecsable, and check condition/not ready
+ * return 1: Is used to signal LUN not accessible, and check condition/not ready
* return 0: Used to signal success
- * reutrn -1: Used to signal failure, and invalid cdb field
+ * return -1: Used to signal failure, and invalid cdb field
*/
sense_reason_t
target_alua_state_check(struct se_cmd *cmd)
nonop_delay_msecs = tg_pt_gp->tg_pt_gp_nonop_delay_msecs;
spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
/*
- * Process ALUA_ACCESS_STATE_ACTIVE_OPTMIZED in a separate conditional
+ * Process ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED in a separate conditional
* statement so the compiler knows explicitly to check this case first.
* For the Optimized ALUA access state case, we want to process the
* incoming fabric cmd ASAP..
*/
- if (out_alua_state == ALUA_ACCESS_STATE_ACTIVE_OPTMIZED)
+ if (out_alua_state == ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED)
return 0;
switch (out_alua_state) {
}
/*
- * Check implict and explict ALUA state change request.
+ * Check implicit and explicit ALUA state change request.
*/
static sense_reason_t
core_alua_check_transition(int state, int *primary)
{
switch (state) {
- case ALUA_ACCESS_STATE_ACTIVE_OPTMIZED:
+ case ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED:
case ALUA_ACCESS_STATE_ACTIVE_NON_OPTIMIZED:
case ALUA_ACCESS_STATE_STANDBY:
case ALUA_ACCESS_STATE_UNAVAILABLE:
static char *core_alua_dump_state(int state)
{
switch (state) {
- case ALUA_ACCESS_STATE_ACTIVE_OPTMIZED:
+ case ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED:
return "Active/Optimized";
case ALUA_ACCESS_STATE_ACTIVE_NON_OPTIMIZED:
return "Active/NonOptimized";
switch (status) {
case ALUA_STATUS_NONE:
return "None";
- case ALUA_STATUS_ALTERED_BY_EXPLICT_STPG:
- return "Altered by Explict STPG";
- case ALUA_STATUS_ALTERED_BY_IMPLICT_ALUA:
- return "Altered by Implict ALUA";
+ case ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG:
+ return "Altered by Explicit STPG";
+ case ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA:
+ return "Altered by Implicit ALUA";
default:
return "Unknown";
}
struct se_node_acl *nacl,
unsigned char *md_buf,
int new_state,
- int explict)
+ int explicit)
{
struct se_dev_entry *se_deve;
struct se_lun_acl *lacl;
old_state = atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state);
atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
ALUA_ACCESS_STATE_TRANSITION);
- tg_pt_gp->tg_pt_gp_alua_access_status = (explict) ?
- ALUA_STATUS_ALTERED_BY_EXPLICT_STPG :
- ALUA_STATUS_ALTERED_BY_IMPLICT_ALUA;
+ tg_pt_gp->tg_pt_gp_alua_access_status = (explicit) ?
+ ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG :
+ ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA;
/*
* Check for the optional ALUA primary state transition delay
*/
* change, a device server shall establish a unit attention
* condition for the initiator port associated with every I_T
* nexus with the additional sense code set to ASYMMETRIC
- * ACCESS STATE CHAGED.
+ * ACCESS STATE CHANGED.
*
* After an explicit target port asymmetric access state
* change, a device server shall establish a unit attention
lacl = se_deve->se_lun_acl;
/*
* se_deve->se_lun_acl pointer may be NULL for a
- * entry created without explict Node+MappedLUN ACLs
+ * entry created without explicit Node+MappedLUN ACLs
*/
if (!lacl)
continue;
- if (explict &&
+ if (explicit &&
(nacl != NULL) && (nacl == lacl->se_lun_nacl) &&
(l_port != NULL) && (l_port == port))
continue;
atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state, new_state);
pr_debug("Successful %s ALUA transition TG PT Group: %s ID: %hu"
- " from primary access state %s to %s\n", (explict) ? "explict" :
- "implict", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item),
+ " from primary access state %s to %s\n", (explicit) ? "explicit" :
+ "implicit", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item),
tg_pt_gp->tg_pt_gp_id, core_alua_dump_state(old_state),
core_alua_dump_state(new_state));
struct se_port *l_port,
struct se_node_acl *l_nacl,
int new_state,
- int explict)
+ int explicit)
{
struct se_device *dev;
struct se_port *port;
* success.
*/
core_alua_do_transition_tg_pt(l_tg_pt_gp, l_port, l_nacl,
- md_buf, new_state, explict);
+ md_buf, new_state, explicit);
atomic_dec(&lu_gp->lu_gp_ref_cnt);
smp_mb__after_atomic_dec();
kfree(md_buf);
continue;
/*
* If the target behavior port asymmetric access state
- * is changed for any target port group accessiable via
+ * is changed for any target port group accessible via
* a logical unit within a LU group, the target port
* behavior group asymmetric access states for the same
* target port group accessible via other logical units
* success.
*/
core_alua_do_transition_tg_pt(tg_pt_gp, port,
- nacl, md_buf, new_state, explict);
+ nacl, md_buf, new_state, explicit);
spin_lock(&dev->t10_alua.tg_pt_gps_lock);
atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt);
pr_debug("Successfully processed LU Group: %s all ALUA TG PT"
" Group IDs: %hu %s transition to primary state: %s\n",
config_item_name(&lu_gp->lu_gp_group.cg_item),
- l_tg_pt_gp->tg_pt_gp_id, (explict) ? "explict" : "implict",
+ l_tg_pt_gp->tg_pt_gp_id, (explicit) ? "explicit" : "implicit",
core_alua_dump_state(new_state));
atomic_dec(&lu_gp->lu_gp_ref_cnt);
static int core_alua_set_tg_pt_secondary_state(
struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem,
struct se_port *port,
- int explict,
+ int explicit,
int offline)
{
struct t10_alua_tg_pt_gp *tg_pt_gp;
atomic_set(&port->sep_tg_pt_secondary_offline, 0);
md_buf_len = tg_pt_gp->tg_pt_gp_md_buf_len;
- port->sep_tg_pt_secondary_stat = (explict) ?
- ALUA_STATUS_ALTERED_BY_EXPLICT_STPG :
- ALUA_STATUS_ALTERED_BY_IMPLICT_ALUA;
+ port->sep_tg_pt_secondary_stat = (explicit) ?
+ ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG :
+ ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA;
pr_debug("Successful %s ALUA transition TG PT Group: %s ID: %hu"
- " to secondary access state: %s\n", (explict) ? "explict" :
- "implict", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item),
+ " to secondary access state: %s\n", (explicit) ? "explicit" :
+ "implicit", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item),
tg_pt_gp->tg_pt_gp_id, (offline) ? "OFFLINE" : "ONLINE");
spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
* struct se_device is released via core_alua_free_lu_gp_mem().
*
* If the passed lu_gp does NOT match the default_lu_gp, assume
- * we want to re-assocate a given lu_gp_mem with default_lu_gp.
+ * we want to re-associate a given lu_gp_mem with default_lu_gp.
*/
spin_lock(&lu_gp_mem->lu_gp_mem_lock);
if (lu_gp != default_lu_gp)
tg_pt_gp->tg_pt_gp_dev = dev;
tg_pt_gp->tg_pt_gp_md_buf_len = ALUA_MD_BUF_LEN;
atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
- ALUA_ACCESS_STATE_ACTIVE_OPTMIZED);
+ ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED);
/*
- * Enable both explict and implict ALUA support by default
+ * Enable both explicit and implicit ALUA support by default
*/
tg_pt_gp->tg_pt_gp_alua_access_type =
- TPGS_EXPLICT_ALUA | TPGS_IMPLICT_ALUA;
+ TPGS_EXPLICIT_ALUA | TPGS_IMPLICIT_ALUA;
/*
* Set the default Active/NonOptimized Delay in milliseconds
*/
tg_pt_gp->tg_pt_gp_nonop_delay_msecs = ALUA_DEFAULT_NONOP_DELAY_MSECS;
tg_pt_gp->tg_pt_gp_trans_delay_msecs = ALUA_DEFAULT_TRANS_DELAY_MSECS;
- tg_pt_gp->tg_pt_gp_implict_trans_secs = ALUA_DEFAULT_IMPLICT_TRANS_SECS;
+ tg_pt_gp->tg_pt_gp_implicit_trans_secs = ALUA_DEFAULT_IMPLICIT_TRANS_SECS;
+
+ /*
+ * Enable all supported states
+ */
+ tg_pt_gp->tg_pt_gp_alua_supported_states =
+ ALUA_T_SUP | ALUA_O_SUP |
+ ALUA_U_SUP | ALUA_S_SUP | ALUA_AN_SUP | ALUA_AO_SUP;
if (def_group) {
spin_lock(&dev->t10_alua.tg_pt_gps_lock);
* been called from target_core_alua_drop_tg_pt_gp().
*
* Here we remove *tg_pt_gp from the global list so that
- * no assications *OR* explict ALUA via SET_TARGET_PORT_GROUPS
+ * no associations *OR* explicit ALUA via SET_TARGET_PORT_GROUPS
* can be made while we are releasing struct t10_alua_tg_pt_gp.
*/
spin_lock(&dev->t10_alua.tg_pt_gps_lock);
* core_alua_free_tg_pt_gp_mem().
*
* If the passed tg_pt_gp does NOT match the default_tg_pt_gp,
- * assume we want to re-assocate a given tg_pt_gp_mem with
+ * assume we want to re-associate a given tg_pt_gp_mem with
* default_tg_pt_gp.
*/
spin_lock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
struct t10_alua_tg_pt_gp *tg_pt_gp,
char *page)
{
- if ((tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICT_ALUA) &&
- (tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_IMPLICT_ALUA))
- return sprintf(page, "Implict and Explict\n");
- else if (tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_IMPLICT_ALUA)
- return sprintf(page, "Implict\n");
- else if (tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICT_ALUA)
- return sprintf(page, "Explict\n");
+ if ((tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICIT_ALUA) &&
+ (tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_IMPLICIT_ALUA))
+ return sprintf(page, "Implicit and Explicit\n");
+ else if (tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_IMPLICIT_ALUA)
+ return sprintf(page, "Implicit\n");
+ else if (tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICIT_ALUA)
+ return sprintf(page, "Explicit\n");
else
return sprintf(page, "None\n");
}
}
if (tmp == 3)
tg_pt_gp->tg_pt_gp_alua_access_type =
- TPGS_IMPLICT_ALUA | TPGS_EXPLICT_ALUA;
+ TPGS_IMPLICIT_ALUA | TPGS_EXPLICIT_ALUA;
else if (tmp == 2)
- tg_pt_gp->tg_pt_gp_alua_access_type = TPGS_EXPLICT_ALUA;
+ tg_pt_gp->tg_pt_gp_alua_access_type = TPGS_EXPLICIT_ALUA;
else if (tmp == 1)
- tg_pt_gp->tg_pt_gp_alua_access_type = TPGS_IMPLICT_ALUA;
+ tg_pt_gp->tg_pt_gp_alua_access_type = TPGS_IMPLICIT_ALUA;
else
tg_pt_gp->tg_pt_gp_alua_access_type = 0;
return count;
}
-ssize_t core_alua_show_implict_trans_secs(
+ssize_t core_alua_show_implicit_trans_secs(
struct t10_alua_tg_pt_gp *tg_pt_gp,
char *page)
{
- return sprintf(page, "%d\n", tg_pt_gp->tg_pt_gp_implict_trans_secs);
+ return sprintf(page, "%d\n", tg_pt_gp->tg_pt_gp_implicit_trans_secs);
}
-ssize_t core_alua_store_implict_trans_secs(
+ssize_t core_alua_store_implicit_trans_secs(
struct t10_alua_tg_pt_gp *tg_pt_gp,
const char *page,
size_t count)
ret = kstrtoul(page, 0, &tmp);
if (ret < 0) {
- pr_err("Unable to extract implict_trans_secs\n");
+ pr_err("Unable to extract implicit_trans_secs\n");
return ret;
}
- if (tmp > ALUA_MAX_IMPLICT_TRANS_SECS) {
- pr_err("Passed implict_trans_secs: %lu, exceeds"
- " ALUA_MAX_IMPLICT_TRANS_SECS: %d\n", tmp,
- ALUA_MAX_IMPLICT_TRANS_SECS);
+ if (tmp > ALUA_MAX_IMPLICIT_TRANS_SECS) {
+ pr_err("Passed implicit_trans_secs: %lu, exceeds"
+ " ALUA_MAX_IMPLICIT_TRANS_SECS: %d\n", tmp,
+ ALUA_MAX_IMPLICIT_TRANS_SECS);
return -EINVAL;
}
- tg_pt_gp->tg_pt_gp_implict_trans_secs = (int)tmp;
+ tg_pt_gp->tg_pt_gp_implicit_trans_secs = (int)tmp;
return count;
}
return ret;
}
if ((tmp != ALUA_STATUS_NONE) &&
- (tmp != ALUA_STATUS_ALTERED_BY_EXPLICT_STPG) &&
- (tmp != ALUA_STATUS_ALTERED_BY_IMPLICT_ALUA)) {
+ (tmp != ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG) &&
+ (tmp != ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA)) {
pr_err("Illegal value for alua_tg_pt_status: %lu\n",
tmp);
return -EINVAL;
* from spc4r17 section 6.4.2 Table 135
*/
#define TPGS_NO_ALUA 0x00
-#define TPGS_IMPLICT_ALUA 0x10
-#define TPGS_EXPLICT_ALUA 0x20
+#define TPGS_IMPLICIT_ALUA 0x10
+#define TPGS_EXPLICIT_ALUA 0x20
/*
* ASYMMETRIC ACCESS STATE field
*
* from spc4r17 section 6.27 Table 245
*/
-#define ALUA_ACCESS_STATE_ACTIVE_OPTMIZED 0x0
+#define ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED 0x0
#define ALUA_ACCESS_STATE_ACTIVE_NON_OPTIMIZED 0x1
#define ALUA_ACCESS_STATE_STANDBY 0x2
#define ALUA_ACCESS_STATE_UNAVAILABLE 0x3
#define ALUA_ACCESS_STATE_OFFLINE 0xe
#define ALUA_ACCESS_STATE_TRANSITION 0xf
+/*
+ * from spc4r36j section 6.37 Table 306
+ */
+#define ALUA_T_SUP 0x80
+#define ALUA_O_SUP 0x40
+#define ALUA_LBD_SUP 0x10
+#define ALUA_U_SUP 0x08
+#define ALUA_S_SUP 0x04
+#define ALUA_AN_SUP 0x02
+#define ALUA_AO_SUP 0x01
+
/*
* REPORT_TARGET_PORT_GROUP STATUS CODE
*
* from spc4r17 section 6.27 Table 246
*/
#define ALUA_STATUS_NONE 0x00
-#define ALUA_STATUS_ALTERED_BY_EXPLICT_STPG 0x01
-#define ALUA_STATUS_ALTERED_BY_IMPLICT_ALUA 0x02
+#define ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG 0x01
+#define ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA 0x02
/*
* From spc4r17, Table D.1: ASC and ASCQ Assignement
#define ALUA_DEFAULT_NONOP_DELAY_MSECS 100
#define ALUA_MAX_NONOP_DELAY_MSECS 10000 /* 10 seconds */
/*
- * Used for implict and explict ALUA transitional delay, that is disabled
+ * Used for implicit and explicit ALUA transitional delay, that is disabled
* by default, and is intended to be used for debugging client side ALUA code.
*/
#define ALUA_DEFAULT_TRANS_DELAY_MSECS 0
#define ALUA_MAX_TRANS_DELAY_MSECS 30000 /* 30 seconds */
/*
- * Used for the recommended application client implict transition timeout
+ * Used for the recommended application client implicit transition timeout
* in seconds, returned by the REPORT_TARGET_PORT_GROUPS w/ extended header.
*/
-#define ALUA_DEFAULT_IMPLICT_TRANS_SECS 0
-#define ALUA_MAX_IMPLICT_TRANS_SECS 255
+#define ALUA_DEFAULT_IMPLICIT_TRANS_SECS 0
+#define ALUA_MAX_IMPLICIT_TRANS_SECS 255
/*
* Used by core_alua_update_tpg_primary_metadata() and
* core_alua_update_tpg_secondary_metadata()
char *);
extern ssize_t core_alua_store_trans_delay_msecs(struct t10_alua_tg_pt_gp *,
const char *, size_t);
-extern ssize_t core_alua_show_implict_trans_secs(struct t10_alua_tg_pt_gp *,
+extern ssize_t core_alua_show_implicit_trans_secs(struct t10_alua_tg_pt_gp *,
char *);
-extern ssize_t core_alua_store_implict_trans_secs(struct t10_alua_tg_pt_gp *,
+extern ssize_t core_alua_store_implicit_trans_secs(struct t10_alua_tg_pt_gp *,
const char *, size_t);
extern ssize_t core_alua_show_preferred_bit(struct t10_alua_tg_pt_gp *,
char *);
* struct target_fabric_configfs *tf will contain a usage reference.
*/
pr_debug("Target_Core_ConfigFS: REGISTER tfc_wwn_cit -> %p\n",
- &TF_CIT_TMPL(tf)->tfc_wwn_cit);
+ &tf->tf_cit_tmpl.tfc_wwn_cit);
tf->tf_group.default_groups = tf->tf_default_groups;
tf->tf_group.default_groups[0] = &tf->tf_disc_group;
tf->tf_group.default_groups[1] = NULL;
config_group_init_type_name(&tf->tf_group, name,
- &TF_CIT_TMPL(tf)->tfc_wwn_cit);
+ &tf->tf_cit_tmpl.tfc_wwn_cit);
config_group_init_type_name(&tf->tf_disc_group, "discovery_auth",
- &TF_CIT_TMPL(tf)->tfc_discovery_cit);
+ &tf->tf_cit_tmpl.tfc_discovery_cit);
pr_debug("Target_Core_ConfigFS: REGISTER -> Allocated Fabric:"
" %s\n", tf->tf_group.cg_item.ci_name);
int new_state, ret;
if (!tg_pt_gp->tg_pt_gp_valid_id) {
- pr_err("Unable to do implict ALUA on non valid"
+ pr_err("Unable to do implicit ALUA on non valid"
" tg_pt_gp ID: %hu\n", tg_pt_gp->tg_pt_gp_valid_id);
return -EINVAL;
}
}
new_state = (int)tmp;
- if (!(tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_IMPLICT_ALUA)) {
- pr_err("Unable to process implict configfs ALUA"
- " transition while TPGS_IMPLICT_ALUA is disabled\n");
+ if (!(tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_IMPLICIT_ALUA)) {
+ pr_err("Unable to process implicit configfs ALUA"
+ " transition while TPGS_IMPLICIT_ALUA is disabled\n");
return -EINVAL;
}
new_status = (int)tmp;
if ((new_status != ALUA_STATUS_NONE) &&
- (new_status != ALUA_STATUS_ALTERED_BY_EXPLICT_STPG) &&
- (new_status != ALUA_STATUS_ALTERED_BY_IMPLICT_ALUA)) {
+ (new_status != ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG) &&
+ (new_status != ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA)) {
pr_err("Illegal ALUA access status: 0x%02x\n",
new_status);
return -EINVAL;
SE_DEV_ALUA_TG_PT_ATTR(alua_access_type, S_IRUGO | S_IWUSR);
+/*
+ * alua_supported_states
+ */
+
+#define SE_DEV_ALUA_SUPPORT_STATE_SHOW(_name, _var, _bit) \
+static ssize_t target_core_alua_tg_pt_gp_show_attr_alua_support_##_name( \
+ struct t10_alua_tg_pt_gp *t, char *p) \
+{ \
+ return sprintf(p, "%d\n", !!(t->_var & _bit)); \
+}
+
+#define SE_DEV_ALUA_SUPPORT_STATE_STORE(_name, _var, _bit) \
+static ssize_t target_core_alua_tg_pt_gp_store_attr_alua_support_##_name(\
+ struct t10_alua_tg_pt_gp *t, const char *p, size_t c) \
+{ \
+ unsigned long tmp; \
+ int ret; \
+ \
+ if (!t->tg_pt_gp_valid_id) { \
+ pr_err("Unable to do set ##_name ALUA state on non" \
+ " valid tg_pt_gp ID: %hu\n", \
+ t->tg_pt_gp_valid_id); \
+ return -EINVAL; \
+ } \
+ \
+ ret = kstrtoul(p, 0, &tmp); \
+ if (ret < 0) { \
+ pr_err("Invalid value '%s', must be '0' or '1'\n", p); \
+ return -EINVAL; \
+ } \
+ if (tmp > 1) { \
+ pr_err("Invalid value '%ld', must be '0' or '1'\n", tmp); \
+ return -EINVAL; \
+ } \
+ if (!tmp) \
+ t->_var |= _bit; \
+ else \
+ t->_var &= ~_bit; \
+ \
+ return c; \
+}
+
+SE_DEV_ALUA_SUPPORT_STATE_SHOW(transitioning,
+ tg_pt_gp_alua_supported_states, ALUA_T_SUP);
+SE_DEV_ALUA_SUPPORT_STATE_STORE(transitioning,
+ tg_pt_gp_alua_supported_states, ALUA_T_SUP);
+SE_DEV_ALUA_TG_PT_ATTR(alua_support_transitioning, S_IRUGO | S_IWUSR);
+
+SE_DEV_ALUA_SUPPORT_STATE_SHOW(offline,
+ tg_pt_gp_alua_supported_states, ALUA_O_SUP);
+SE_DEV_ALUA_SUPPORT_STATE_STORE(offline,
+ tg_pt_gp_alua_supported_states, ALUA_O_SUP);
+SE_DEV_ALUA_TG_PT_ATTR(alua_support_offline, S_IRUGO | S_IWUSR);
+
+SE_DEV_ALUA_SUPPORT_STATE_SHOW(lba_dependent,
+ tg_pt_gp_alua_supported_states, ALUA_LBD_SUP);
+SE_DEV_ALUA_SUPPORT_STATE_STORE(lba_dependent,
+ tg_pt_gp_alua_supported_states, ALUA_LBD_SUP);
+SE_DEV_ALUA_TG_PT_ATTR(alua_support_lba_dependent, S_IRUGO | S_IWUSR);
+
+SE_DEV_ALUA_SUPPORT_STATE_SHOW(unavailable,
+ tg_pt_gp_alua_supported_states, ALUA_U_SUP);
+SE_DEV_ALUA_SUPPORT_STATE_STORE(unavailable,
+ tg_pt_gp_alua_supported_states, ALUA_U_SUP);
+SE_DEV_ALUA_TG_PT_ATTR(alua_support_unavailable, S_IRUGO | S_IWUSR);
+
+SE_DEV_ALUA_SUPPORT_STATE_SHOW(standby,
+ tg_pt_gp_alua_supported_states, ALUA_S_SUP);
+SE_DEV_ALUA_SUPPORT_STATE_STORE(standby,
+ tg_pt_gp_alua_supported_states, ALUA_S_SUP);
+SE_DEV_ALUA_TG_PT_ATTR(alua_support_standby, S_IRUGO | S_IWUSR);
+
+SE_DEV_ALUA_SUPPORT_STATE_SHOW(active_optimized,
+ tg_pt_gp_alua_supported_states, ALUA_AO_SUP);
+SE_DEV_ALUA_SUPPORT_STATE_STORE(active_optimized,
+ tg_pt_gp_alua_supported_states, ALUA_AO_SUP);
+SE_DEV_ALUA_TG_PT_ATTR(alua_support_active_optimized, S_IRUGO | S_IWUSR);
+
+SE_DEV_ALUA_SUPPORT_STATE_SHOW(active_nonoptimized,
+ tg_pt_gp_alua_supported_states, ALUA_AN_SUP);
+SE_DEV_ALUA_SUPPORT_STATE_STORE(active_nonoptimized,
+ tg_pt_gp_alua_supported_states, ALUA_AN_SUP);
+SE_DEV_ALUA_TG_PT_ATTR(alua_support_active_nonoptimized, S_IRUGO | S_IWUSR);
+
/*
* alua_write_metadata
*/
SE_DEV_ALUA_TG_PT_ATTR(trans_delay_msecs, S_IRUGO | S_IWUSR);
/*
- * implict_trans_secs
+ * implicit_trans_secs
*/
-static ssize_t target_core_alua_tg_pt_gp_show_attr_implict_trans_secs(
+static ssize_t target_core_alua_tg_pt_gp_show_attr_implicit_trans_secs(
struct t10_alua_tg_pt_gp *tg_pt_gp,
char *page)
{
- return core_alua_show_implict_trans_secs(tg_pt_gp, page);
+ return core_alua_show_implicit_trans_secs(tg_pt_gp, page);
}
-static ssize_t target_core_alua_tg_pt_gp_store_attr_implict_trans_secs(
+static ssize_t target_core_alua_tg_pt_gp_store_attr_implicit_trans_secs(
struct t10_alua_tg_pt_gp *tg_pt_gp,
const char *page,
size_t count)
{
- return core_alua_store_implict_trans_secs(tg_pt_gp, page, count);
+ return core_alua_store_implicit_trans_secs(tg_pt_gp, page, count);
}
-SE_DEV_ALUA_TG_PT_ATTR(implict_trans_secs, S_IRUGO | S_IWUSR);
+SE_DEV_ALUA_TG_PT_ATTR(implicit_trans_secs, S_IRUGO | S_IWUSR);
/*
* preferred
&target_core_alua_tg_pt_gp_alua_access_state.attr,
&target_core_alua_tg_pt_gp_alua_access_status.attr,
&target_core_alua_tg_pt_gp_alua_access_type.attr,
+ &target_core_alua_tg_pt_gp_alua_support_transitioning.attr,
+ &target_core_alua_tg_pt_gp_alua_support_offline.attr,
+ &target_core_alua_tg_pt_gp_alua_support_lba_dependent.attr,
+ &target_core_alua_tg_pt_gp_alua_support_unavailable.attr,
+ &target_core_alua_tg_pt_gp_alua_support_standby.attr,
+ &target_core_alua_tg_pt_gp_alua_support_active_nonoptimized.attr,
+ &target_core_alua_tg_pt_gp_alua_support_active_optimized.attr,
&target_core_alua_tg_pt_gp_alua_write_metadata.attr,
&target_core_alua_tg_pt_gp_nonop_delay_msecs.attr,
&target_core_alua_tg_pt_gp_trans_delay_msecs.attr,
- &target_core_alua_tg_pt_gp_implict_trans_secs.attr,
+ &target_core_alua_tg_pt_gp_implicit_trans_secs.attr,
&target_core_alua_tg_pt_gp_preferred.attr,
&target_core_alua_tg_pt_gp_tg_pt_gp_id.attr,
&target_core_alua_tg_pt_gp_members.attr,
se_cmd->pr_res_key = deve->pr_res_key;
se_cmd->orig_fe_lun = unpacked_lun;
se_cmd->se_cmd_flags |= SCF_SE_LUN_CMD;
+
+ percpu_ref_get(&se_lun->lun_ref);
+ se_cmd->lun_ref_active = true;
}
spin_unlock_irqrestore(&se_sess->se_node_acl->device_list_lock, flags);
se_cmd->se_lun = &se_sess->se_tpg->tpg_virt_lun0;
se_cmd->orig_fe_lun = 0;
se_cmd->se_cmd_flags |= SCF_SE_LUN_CMD;
+
+ percpu_ref_get(&se_lun->lun_ref);
+ se_cmd->lun_ref_active = true;
}
/* Directly associate cmd with se_dev */
se_cmd->se_dev = se_lun->lun_se_dev;
- /* TODO: get rid of this and use atomics for stats */
dev = se_lun->lun_se_dev;
- spin_lock_irqsave(&dev->stats_lock, flags);
- dev->num_cmds++;
+ atomic_long_inc(&dev->num_cmds);
if (se_cmd->data_direction == DMA_TO_DEVICE)
- dev->write_bytes += se_cmd->data_length;
+ atomic_long_add(se_cmd->data_length, &dev->write_bytes);
else if (se_cmd->data_direction == DMA_FROM_DEVICE)
- dev->read_bytes += se_cmd->data_length;
- spin_unlock_irqrestore(&dev->stats_lock, flags);
-
- spin_lock_irqsave(&se_lun->lun_cmd_lock, flags);
- list_add_tail(&se_cmd->se_lun_node, &se_lun->lun_cmd_list);
- spin_unlock_irqrestore(&se_lun->lun_cmd_lock, flags);
+ atomic_long_add(se_cmd->data_length, &dev->read_bytes);
return 0;
}
deve = nacl->device_list[mapped_lun];
/*
- * Check if the call is handling demo mode -> explict LUN ACL
+ * Check if the call is handling demo mode -> explicit LUN ACL
* transition. This transition must be for the same struct se_lun
* + mapped_lun that was setup in demo mode..
*/
if (deve->lun_flags & TRANSPORT_LUNFLAGS_INITIATOR_ACCESS) {
if (deve->se_lun_acl != NULL) {
pr_err("struct se_dev_entry->se_lun_acl"
- " already set for demo mode -> explict"
+ " already set for demo mode -> explicit"
" LUN ACL transition\n");
spin_unlock_irq(&nacl->device_list_lock);
return -EINVAL;
if (deve->se_lun != lun) {
pr_err("struct se_dev_entry->se_lun does"
" match passed struct se_lun for demo mode"
- " -> explict LUN ACL transition\n");
+ " -> explicit LUN ACL transition\n");
spin_unlock_irq(&nacl->device_list_lock);
return -EINVAL;
}
struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
{
struct se_device *dev;
+ struct se_lun *xcopy_lun;
dev = hba->transport->alloc_device(hba, name);
if (!dev)
INIT_LIST_HEAD(&dev->state_list);
INIT_LIST_HEAD(&dev->qf_cmd_list);
INIT_LIST_HEAD(&dev->g_dev_node);
- spin_lock_init(&dev->stats_lock);
spin_lock_init(&dev->execute_task_lock);
spin_lock_init(&dev->delayed_cmd_lock);
spin_lock_init(&dev->dev_reservation_lock);
dev->dev_attrib.fabric_max_sectors = DA_FABRIC_MAX_SECTORS;
dev->dev_attrib.optimal_sectors = DA_FABRIC_MAX_SECTORS;
+ xcopy_lun = &dev->xcopy_lun;
+ xcopy_lun->lun_se_dev = dev;
+ init_completion(&xcopy_lun->lun_shutdown_comp);
+ INIT_LIST_HEAD(&xcopy_lun->lun_acl_list);
+ spin_lock_init(&xcopy_lun->lun_acl_lock);
+ spin_lock_init(&xcopy_lun->lun_sep_lock);
+ init_completion(&xcopy_lun->lun_ref_comp);
+
return dev;
}
}
config_group_init_type_name(&lacl->se_lun_group, name,
- &TF_CIT_TMPL(tf)->tfc_tpg_mappedlun_cit);
+ &tf->tf_cit_tmpl.tfc_tpg_mappedlun_cit);
config_group_init_type_name(&lacl->ml_stat_grps.stat_group,
- "statistics", &TF_CIT_TMPL(tf)->tfc_tpg_mappedlun_stat_cit);
+ "statistics", &tf->tf_cit_tmpl.tfc_tpg_mappedlun_stat_cit);
lacl_cg->default_groups[0] = &lacl->ml_stat_grps.stat_group;
lacl_cg->default_groups[1] = NULL;
nacl_cg->default_groups[4] = NULL;
config_group_init_type_name(&se_nacl->acl_group, name,
- &TF_CIT_TMPL(tf)->tfc_tpg_nacl_base_cit);
+ &tf->tf_cit_tmpl.tfc_tpg_nacl_base_cit);
config_group_init_type_name(&se_nacl->acl_attrib_group, "attrib",
- &TF_CIT_TMPL(tf)->tfc_tpg_nacl_attrib_cit);
+ &tf->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit);
config_group_init_type_name(&se_nacl->acl_auth_group, "auth",
- &TF_CIT_TMPL(tf)->tfc_tpg_nacl_auth_cit);
+ &tf->tf_cit_tmpl.tfc_tpg_nacl_auth_cit);
config_group_init_type_name(&se_nacl->acl_param_group, "param",
- &TF_CIT_TMPL(tf)->tfc_tpg_nacl_param_cit);
+ &tf->tf_cit_tmpl.tfc_tpg_nacl_param_cit);
config_group_init_type_name(&se_nacl->acl_fabric_stat_group,
"fabric_statistics",
- &TF_CIT_TMPL(tf)->tfc_tpg_nacl_stat_cit);
+ &tf->tf_cit_tmpl.tfc_tpg_nacl_stat_cit);
return &se_nacl->acl_group;
}
se_tpg_np->tpg_np_parent = se_tpg;
config_group_init_type_name(&se_tpg_np->tpg_np_group, name,
- &TF_CIT_TMPL(tf)->tfc_tpg_np_base_cit);
+ &tf->tf_cit_tmpl.tfc_tpg_np_base_cit);
return &se_tpg_np->tpg_np_group;
}
}
config_group_init_type_name(&lun->lun_group, name,
- &TF_CIT_TMPL(tf)->tfc_tpg_port_cit);
+ &tf->tf_cit_tmpl.tfc_tpg_port_cit);
config_group_init_type_name(&lun->port_stat_grps.stat_group,
- "statistics", &TF_CIT_TMPL(tf)->tfc_tpg_port_stat_cit);
+ "statistics", &tf->tf_cit_tmpl.tfc_tpg_port_stat_cit);
lun_cg->default_groups[0] = &lun->port_stat_grps.stat_group;
lun_cg->default_groups[1] = NULL;
se_tpg->tpg_group.default_groups[6] = NULL;
config_group_init_type_name(&se_tpg->tpg_group, name,
- &TF_CIT_TMPL(tf)->tfc_tpg_base_cit);
+ &tf->tf_cit_tmpl.tfc_tpg_base_cit);
config_group_init_type_name(&se_tpg->tpg_lun_group, "lun",
- &TF_CIT_TMPL(tf)->tfc_tpg_lun_cit);
+ &tf->tf_cit_tmpl.tfc_tpg_lun_cit);
config_group_init_type_name(&se_tpg->tpg_np_group, "np",
- &TF_CIT_TMPL(tf)->tfc_tpg_np_cit);
+ &tf->tf_cit_tmpl.tfc_tpg_np_cit);
config_group_init_type_name(&se_tpg->tpg_acl_group, "acls",
- &TF_CIT_TMPL(tf)->tfc_tpg_nacl_cit);
+ &tf->tf_cit_tmpl.tfc_tpg_nacl_cit);
config_group_init_type_name(&se_tpg->tpg_attrib_group, "attrib",
- &TF_CIT_TMPL(tf)->tfc_tpg_attrib_cit);
+ &tf->tf_cit_tmpl.tfc_tpg_attrib_cit);
config_group_init_type_name(&se_tpg->tpg_auth_group, "auth",
- &TF_CIT_TMPL(tf)->tfc_tpg_auth_cit);
+ &tf->tf_cit_tmpl.tfc_tpg_auth_cit);
config_group_init_type_name(&se_tpg->tpg_param_group, "param",
- &TF_CIT_TMPL(tf)->tfc_tpg_param_cit);
+ &tf->tf_cit_tmpl.tfc_tpg_param_cit);
return &se_tpg->tpg_group;
}
wwn->wwn_group.default_groups[1] = NULL;
config_group_init_type_name(&wwn->wwn_group, name,
- &TF_CIT_TMPL(tf)->tfc_tpg_cit);
+ &tf->tf_cit_tmpl.tfc_tpg_cit);
config_group_init_type_name(&wwn->fabric_stat_group, "fabric_statistics",
- &TF_CIT_TMPL(tf)->tfc_wwn_fabric_stats_cit);
+ &tf->tf_cit_tmpl.tfc_wwn_fabric_stats_cit);
return &wwn->wwn_group;
}
} else {
ret = fd_do_rw(cmd, sgl, sgl_nents, 1);
/*
- * Perform implict vfs_fsync_range() for fd_do_writev() ops
+ * Perform implicit vfs_fsync_range() for fd_do_writev() ops
* for SCSI WRITEs with Forced Unit Access (FUA) set.
* Allow this to happen independent of WCE=0 setting.
*/
return iblock_emulate_read_cap_with_block_size(dev, bd, q);
}
+static sector_t iblock_get_alignment_offset_lbas(struct se_device *dev)
+{
+ struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
+ struct block_device *bd = ib_dev->ibd_bd;
+ int ret;
+
+ ret = bdev_alignment_offset(bd);
+ if (ret == -1)
+ return 0;
+
+ /* convert offset-bytes to offset-lbas */
+ return ret / bdev_logical_block_size(bd);
+}
+
+static unsigned int iblock_get_lbppbe(struct se_device *dev)
+{
+ struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
+ struct block_device *bd = ib_dev->ibd_bd;
+ int logs_per_phys = bdev_physical_block_size(bd) / bdev_logical_block_size(bd);
+
+ return ilog2(logs_per_phys);
+}
+
+static unsigned int iblock_get_io_min(struct se_device *dev)
+{
+ struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
+ struct block_device *bd = ib_dev->ibd_bd;
+
+ return bdev_io_min(bd);
+}
+
+static unsigned int iblock_get_io_opt(struct se_device *dev)
+{
+ struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
+ struct block_device *bd = ib_dev->ibd_bd;
+
+ return bdev_io_opt(bd);
+}
+
static struct sbc_ops iblock_sbc_ops = {
.execute_rw = iblock_execute_rw,
.execute_sync_cache = iblock_execute_sync_cache,
.show_configfs_dev_params = iblock_show_configfs_dev_params,
.get_device_type = sbc_get_device_type,
.get_blocks = iblock_get_blocks,
+ .get_alignment_offset_lbas = iblock_get_alignment_offset_lbas,
+ .get_lbppbe = iblock_get_lbppbe,
+ .get_io_min = iblock_get_io_min,
+ .get_io_opt = iblock_get_io_opt,
.get_write_cache = iblock_get_write_cache,
};
struct se_node_acl *__core_tpg_get_initiator_node_acl(struct se_portal_group *tpg,
const char *);
-struct se_node_acl *core_tpg_get_initiator_node_acl(struct se_portal_group *tpg,
- unsigned char *);
void core_tpg_add_node_to_devs(struct se_node_acl *, struct se_portal_group *);
void core_tpg_wait_for_nacl_pr_ref(struct se_node_acl *);
struct se_lun *core_tpg_pre_addlun(struct se_portal_group *, u32);
int transport_dump_vpd_ident_type(struct t10_vpd *, unsigned char *, int);
int transport_dump_vpd_ident(struct t10_vpd *, unsigned char *, int);
bool target_stop_cmd(struct se_cmd *cmd, unsigned long *flags);
-int transport_clear_lun_from_sessions(struct se_lun *);
+int transport_clear_lun_ref(struct se_lun *);
void transport_send_task_abort(struct se_cmd *);
sense_reason_t target_cmd_size_check(struct se_cmd *cmd, unsigned int size);
void target_qf_do_work(struct work_struct *work);
* statement.
*/
if (!ret && !other_cdb) {
- pr_debug("Allowing explict CDB: 0x%02x for %s"
+ pr_debug("Allowing explicit CDB: 0x%02x for %s"
" reservation holder\n", cdb[0],
core_scsi3_pr_dump_type(pr_reg_type));
*/
if (!registered_nexus) {
- pr_debug("Allowing implict CDB: 0x%02x"
+ pr_debug("Allowing implicit CDB: 0x%02x"
" for %s reservation on unregistered"
" nexus\n", cdb[0],
core_scsi3_pr_dump_type(pr_reg_type));
* allow commands from registered nexuses.
*/
- pr_debug("Allowing implict CDB: 0x%02x for %s"
+ pr_debug("Allowing implicit CDB: 0x%02x for %s"
" reservation\n", cdb[0],
core_scsi3_pr_dump_type(pr_reg_type));
alua_port_list) {
/*
* This pointer will be NULL for demo mode MappedLUNs
- * that have not been make explict via a ConfigFS
+ * that have not been make explicit via a ConfigFS
* MappedLUN group for the SCSI Initiator Node ACL.
*/
if (!deve_tmp->se_lun_acl)
smp_mb__after_atomic_dec();
}
-static int core_scsi3_check_implict_release(
+static int core_scsi3_check_implicit_release(
struct se_device *dev,
struct t10_pr_registration *pr_reg)
{
}
if (pr_res_holder == pr_reg) {
/*
- * Perform an implict RELEASE if the registration that
+ * Perform an implicit RELEASE if the registration that
* is being released is holding the reservation.
*
* From spc4r17, section 5.7.11.1:
* For 'All Registrants' reservation types, all existing
* registrations are still processed as reservation holders
* in core_scsi3_pr_seq_non_holder() after the initial
- * reservation holder is implictly released here.
+ * reservation holder is implicitly released here.
*/
} else if (pr_reg->pr_reg_all_tg_pt &&
(!strcmp(pr_res_holder->pr_reg_nacl->initiatorname,
/*
* sa_res_key=0 Unregister Reservation Key for registered I_T Nexus.
*/
- pr_holder = core_scsi3_check_implict_release(
+ pr_holder = core_scsi3_check_implicit_release(
cmd->se_dev, pr_reg);
if (pr_holder < 0) {
ret = TCM_RESERVATION_CONFLICT;
struct se_device *dev,
struct se_node_acl *se_nacl,
struct t10_pr_registration *pr_reg,
- int explict)
+ int explicit)
{
struct target_core_fabric_ops *tfo = se_nacl->se_tpg->se_tpg_tfo;
char i_buf[PR_REG_ISID_ID_LEN];
pr_debug("SPC-3 PR [%s] Service Action: %s RELEASE cleared"
" reservation holder TYPE: %s ALL_TG_PT: %d\n",
- tfo->get_fabric_name(), (explict) ? "explict" : "implict",
+ tfo->get_fabric_name(), (explicit) ? "explicit" : "implicit",
core_scsi3_pr_dump_type(pr_reg->pr_res_type),
(pr_reg->pr_reg_all_tg_pt) ? 1 : 0);
pr_debug("SPC-3 PR [%s] RELEASE Node: %s%s\n",
memset(i_buf, 0, PR_REG_ISID_ID_LEN);
core_pr_dump_initiator_port(pr_reg, i_buf, PR_REG_ISID_ID_LEN);
/*
- * Do an implict RELEASE of the existing reservation.
+ * Do an implicit RELEASE of the existing reservation.
*/
if (dev->dev_pr_res_holder)
__core_scsi3_complete_pro_release(dev, nacl,
* 5.7.11.4 Preempting, Table 52 and Figure 7.
*
* For a ZERO SA Reservation key, release
- * all other registrations and do an implict
+ * all other registrations and do an implicit
* release of active persistent reservation.
*
* For a non-ZERO SA Reservation key, only
#include <linux/string.h>
#include <linux/parser.h>
#include <linux/timer.h>
-#include <linux/blkdev.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <scsi/scsi.h>
buf[9] = (dev->dev_attrib.block_size >> 16) & 0xff;
buf[10] = (dev->dev_attrib.block_size >> 8) & 0xff;
buf[11] = dev->dev_attrib.block_size & 0xff;
+
+ if (dev->transport->get_lbppbe)
+ buf[13] = dev->transport->get_lbppbe(dev) & 0x0f;
+
+ if (dev->transport->get_alignment_offset_lbas) {
+ u16 lalba = dev->transport->get_alignment_offset_lbas(dev);
+ buf[14] = (lalba >> 8) & 0x3f;
+ buf[15] = lalba & 0xff;
+ }
+
/*
* Set Thin Provisioning Enable bit following sbc3r22 in section
* READ CAPACITY (16) byte 14 if emulate_tpu or emulate_tpws is enabled.
*/
if (dev->dev_attrib.emulate_tpu || dev->dev_attrib.emulate_tpws)
- buf[14] = 0x80;
+ buf[14] |= 0x80;
rbuf = transport_kmap_data_sg(cmd);
if (rbuf) {
buf[5] = 0x80;
/*
- * Set TPGS field for explict and/or implict ALUA access type
+ * Set TPGS field for explicit and/or implicit ALUA access type
* and opteration.
*
* See spc4r17 section 6.4.2 Table 135
struct se_device *dev = cmd->se_dev;
u32 max_sectors;
int have_tp = 0;
+ int opt, min;
/*
* Following spc3r22 section 6.5.3 Block Limits VPD page, when
/*
* Set OPTIMAL TRANSFER LENGTH GRANULARITY
*/
- put_unaligned_be16(1, &buf[6]);
+ if (dev->transport->get_io_min && (min = dev->transport->get_io_min(dev)))
+ put_unaligned_be16(min / dev->dev_attrib.block_size, &buf[6]);
+ else
+ put_unaligned_be16(1, &buf[6]);
/*
* Set MAXIMUM TRANSFER LENGTH
/*
* Set OPTIMAL TRANSFER LENGTH
*/
- put_unaligned_be32(dev->dev_attrib.optimal_sectors, &buf[12]);
+ if (dev->transport->get_io_opt && (opt = dev->transport->get_io_opt(dev)))
+ put_unaligned_be32(opt / dev->dev_attrib.block_size, &buf[12]);
+ else
+ put_unaligned_be32(dev->dev_attrib.optimal_sectors, &buf[12]);
/*
* Exit now if we don't support TP.
*size = (cdb[3] << 8) + cdb[4];
/*
- * Do implict HEAD_OF_QUEUE processing for INQUIRY.
+ * Do implicit HEAD_OF_QUEUE processing for INQUIRY.
* See spc4r17 section 5.3
*/
cmd->sam_task_attr = MSG_HEAD_TAG;
cmd->execute_cmd = spc_emulate_report_luns;
*size = (cdb[6] << 24) | (cdb[7] << 16) | (cdb[8] << 8) | cdb[9];
/*
- * Do implict HEAD_OF_QUEUE processing for REPORT_LUNS
+ * Do implicit HEAD_OF_QUEUE processing for REPORT_LUNS
* See spc4r17 section 5.3
*/
cmd->sam_task_attr = MSG_HEAD_TAG;
#include <linux/utsname.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
-#include <linux/blkdev.h>
#include <linux/configfs.h>
#include <scsi/scsi.h>
#include <scsi/scsi_device.h>
struct se_device *dev =
container_of(sgrps, struct se_device, dev_stat_grps);
- return snprintf(page, PAGE_SIZE, "%u\n", dev->num_resets);
+ return snprintf(page, PAGE_SIZE, "%lu\n",
+ atomic_long_read(&dev->num_resets));
}
DEV_STAT_SCSI_TGT_DEV_ATTR_RO(resets);
container_of(sgrps, struct se_device, dev_stat_grps);
/* scsiLuNumCommands */
- return snprintf(page, PAGE_SIZE, "%llu\n",
- (unsigned long long)dev->num_cmds);
+ return snprintf(page, PAGE_SIZE, "%lu\n",
+ atomic_long_read(&dev->num_cmds));
}
DEV_STAT_SCSI_LU_ATTR_RO(num_cmds);
container_of(sgrps, struct se_device, dev_stat_grps);
/* scsiLuReadMegaBytes */
- return snprintf(page, PAGE_SIZE, "%u\n", (u32)(dev->read_bytes >> 20));
+ return snprintf(page, PAGE_SIZE, "%lu\n",
+ atomic_long_read(&dev->read_bytes) >> 20);
}
DEV_STAT_SCSI_LU_ATTR_RO(read_mbytes);
container_of(sgrps, struct se_device, dev_stat_grps);
/* scsiLuWrittenMegaBytes */
- return snprintf(page, PAGE_SIZE, "%u\n", (u32)(dev->write_bytes >> 20));
+ return snprintf(page, PAGE_SIZE, "%lu\n",
+ atomic_long_read(&dev->write_bytes) >> 20);
}
DEV_STAT_SCSI_LU_ATTR_RO(write_mbytes);
container_of(sgrps, struct se_device, dev_stat_grps);
/* scsiLuInResets */
- return snprintf(page, PAGE_SIZE, "%u\n", dev->num_resets);
+ return snprintf(page, PAGE_SIZE, "%lu\n", atomic_long_read(&dev->num_resets));
}
DEV_STAT_SCSI_LU_ATTR_RO(resets);
pr_debug("LUN_RESET: SCSI-2 Released reservation\n");
}
- spin_lock_irq(&dev->stats_lock);
- dev->num_resets++;
- spin_unlock_irq(&dev->stats_lock);
+ atomic_long_inc(&dev->num_resets);
pr_debug("LUN_RESET: %s for [%s] Complete\n",
(preempt_and_abort_list) ? "Preempt" : "TMR",
return acl;
}
+EXPORT_SYMBOL(core_tpg_get_initiator_node_acl);
/* core_tpg_add_node_to_devs():
*
}
EXPORT_SYMBOL(core_tpg_set_initiator_node_tag);
+static void core_tpg_lun_ref_release(struct percpu_ref *ref)
+{
+ struct se_lun *lun = container_of(ref, struct se_lun, lun_ref);
+
+ complete(&lun->lun_ref_comp);
+}
+
static int core_tpg_setup_virtual_lun0(struct se_portal_group *se_tpg)
{
/* Set in core_dev_setup_virtual_lun0() */
atomic_set(&lun->lun_acl_count, 0);
init_completion(&lun->lun_shutdown_comp);
INIT_LIST_HEAD(&lun->lun_acl_list);
- INIT_LIST_HEAD(&lun->lun_cmd_list);
spin_lock_init(&lun->lun_acl_lock);
- spin_lock_init(&lun->lun_cmd_lock);
spin_lock_init(&lun->lun_sep_lock);
+ init_completion(&lun->lun_ref_comp);
- ret = core_tpg_post_addlun(se_tpg, lun, lun_access, dev);
+ ret = percpu_ref_init(&lun->lun_ref, core_tpg_lun_ref_release);
if (ret < 0)
return ret;
+ ret = core_tpg_post_addlun(se_tpg, lun, lun_access, dev);
+ if (ret < 0) {
+ percpu_ref_cancel_init(&lun->lun_ref);
+ return ret;
+ }
+
return 0;
}
atomic_set(&lun->lun_acl_count, 0);
init_completion(&lun->lun_shutdown_comp);
INIT_LIST_HEAD(&lun->lun_acl_list);
- INIT_LIST_HEAD(&lun->lun_cmd_list);
spin_lock_init(&lun->lun_acl_lock);
- spin_lock_init(&lun->lun_cmd_lock);
spin_lock_init(&lun->lun_sep_lock);
+ init_completion(&lun->lun_ref_comp);
}
se_tpg->se_tpg_type = se_tpg_type;
{
int ret;
- ret = core_dev_export(lun_ptr, tpg, lun);
+ ret = percpu_ref_init(&lun->lun_ref, core_tpg_lun_ref_release);
if (ret < 0)
return ret;
+ ret = core_dev_export(lun_ptr, tpg, lun);
+ if (ret < 0) {
+ percpu_ref_cancel_init(&lun->lun_ref);
+ return ret;
+ }
+
spin_lock(&tpg->tpg_lun_lock);
lun->lun_access = lun_access;
lun->lun_status = TRANSPORT_LUN_STATUS_ACTIVE;
return 0;
}
-static void core_tpg_shutdown_lun(
- struct se_portal_group *tpg,
- struct se_lun *lun)
-{
- core_clear_lun_from_tpg(lun, tpg);
- transport_clear_lun_from_sessions(lun);
-}
-
struct se_lun *core_tpg_pre_dellun(
struct se_portal_group *tpg,
u32 unpacked_lun)
struct se_portal_group *tpg,
struct se_lun *lun)
{
- core_tpg_shutdown_lun(tpg, lun);
+ core_clear_lun_from_tpg(lun, tpg);
+ transport_clear_lun_ref(lun);
core_dev_unexport(lun->lun_se_dev, tpg, lun);
#include <linux/string.h>
#include <linux/timer.h>
#include <linux/slab.h>
-#include <linux/blkdev.h>
#include <linux/spinlock.h>
#include <linux/kthread.h>
#include <linux/in.h>
pr_debug("TARGET_CORE[%s]: Deregistered fabric_sess\n",
se_tpg->se_tpg_tfo->get_fabric_name());
/*
- * If last kref is dropping now for an explict NodeACL, awake sleeping
+ * If last kref is dropping now for an explicit NodeACL, awake sleeping
* ->acl_free_comp caller to wakeup configfs se_node_acl->acl_group
* removal context.
*/
if (write_pending)
cmd->t_state = TRANSPORT_WRITE_PENDING;
- /*
- * Determine if IOCTL context caller in requesting the stopping of this
- * command for LUN shutdown purposes.
- */
- if (cmd->transport_state & CMD_T_LUN_STOP) {
- pr_debug("%s:%d CMD_T_LUN_STOP for ITT: 0x%08x\n",
- __func__, __LINE__, cmd->se_tfo->get_task_tag(cmd));
-
- cmd->transport_state &= ~CMD_T_ACTIVE;
- if (remove_from_lists)
- target_remove_from_state_list(cmd);
- spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-
- complete(&cmd->transport_lun_stop_comp);
- return 1;
- }
-
if (remove_from_lists) {
target_remove_from_state_list(cmd);
static void transport_lun_remove_cmd(struct se_cmd *cmd)
{
struct se_lun *lun = cmd->se_lun;
- unsigned long flags;
- if (!lun)
+ if (!lun || !cmd->lun_ref_active)
return;
- spin_lock_irqsave(&lun->lun_cmd_lock, flags);
- if (!list_empty(&cmd->se_lun_node))
- list_del_init(&cmd->se_lun_node);
- spin_unlock_irqrestore(&lun->lun_cmd_lock, flags);
+ percpu_ref_put(&lun->lun_ref);
}
void transport_cmd_finish_abort(struct se_cmd *cmd, int remove)
cmd->transport_state |= CMD_T_FAILED;
/*
- * Check for case where an explict ABORT_TASK has been received
+ * Check for case where an explicit ABORT_TASK has been received
* and transport_wait_for_tasks() will be waiting for completion..
*/
if (cmd->transport_state & CMD_T_ABORTED &&
int task_attr,
unsigned char *sense_buffer)
{
- INIT_LIST_HEAD(&cmd->se_lun_node);
INIT_LIST_HEAD(&cmd->se_delayed_node);
INIT_LIST_HEAD(&cmd->se_qf_node);
INIT_LIST_HEAD(&cmd->se_cmd_list);
INIT_LIST_HEAD(&cmd->state_list);
- init_completion(&cmd->transport_lun_fe_stop_comp);
- init_completion(&cmd->transport_lun_stop_comp);
init_completion(&cmd->t_transport_stop_comp);
init_completion(&cmd->cmd_wait_comp);
init_completion(&cmd->task_stop_comp);
/*
* If the received CDB has aleady been aborted stop processing it here.
*/
- if (transport_check_aborted_status(cmd, 1)) {
- complete(&cmd->transport_lun_stop_comp);
+ if (transport_check_aborted_status(cmd, 1))
return;
- }
- /*
- * Determine if IOCTL context caller in requesting the stopping of this
- * command for LUN shutdown purposes.
- */
- spin_lock_irq(&cmd->t_state_lock);
- if (cmd->transport_state & CMD_T_LUN_STOP) {
- pr_debug("%s:%d CMD_T_LUN_STOP for ITT: 0x%08x\n",
- __func__, __LINE__, cmd->se_tfo->get_task_tag(cmd));
-
- cmd->transport_state &= ~CMD_T_ACTIVE;
- spin_unlock_irq(&cmd->t_state_lock);
- complete(&cmd->transport_lun_stop_comp);
- return;
- }
/*
* Determine if frontend context caller is requesting the stopping of
* this command for frontend exceptions.
*/
+ spin_lock_irq(&cmd->t_state_lock);
if (cmd->transport_state & CMD_T_STOP) {
pr_debug("%s:%d CMD_T_STOP for ITT: 0x%08x\n",
__func__, __LINE__,
}
EXPORT_SYMBOL(target_wait_for_sess_cmds);
-/* transport_lun_wait_for_tasks():
- *
- * Called from ConfigFS context to stop the passed struct se_cmd to allow
- * an struct se_lun to be successfully shutdown.
- */
-static int transport_lun_wait_for_tasks(struct se_cmd *cmd, struct se_lun *lun)
-{
- unsigned long flags;
- int ret = 0;
-
- /*
- * If the frontend has already requested this struct se_cmd to
- * be stopped, we can safely ignore this struct se_cmd.
- */
- spin_lock_irqsave(&cmd->t_state_lock, flags);
- if (cmd->transport_state & CMD_T_STOP) {
- cmd->transport_state &= ~CMD_T_LUN_STOP;
-
- pr_debug("ConfigFS ITT[0x%08x] - CMD_T_STOP, skipping\n",
- cmd->se_tfo->get_task_tag(cmd));
- spin_unlock_irqrestore(&cmd->t_state_lock, flags);
- transport_cmd_check_stop(cmd, false, false);
- return -EPERM;
- }
- cmd->transport_state |= CMD_T_LUN_FE_STOP;
- spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-
- // XXX: audit task_flags checks.
- spin_lock_irqsave(&cmd->t_state_lock, flags);
- if ((cmd->transport_state & CMD_T_BUSY) &&
- (cmd->transport_state & CMD_T_SENT)) {
- if (!target_stop_cmd(cmd, &flags))
- ret++;
- }
- spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-
- pr_debug("ConfigFS: cmd: %p stop tasks ret:"
- " %d\n", cmd, ret);
- if (!ret) {
- pr_debug("ConfigFS: ITT[0x%08x] - stopping cmd....\n",
- cmd->se_tfo->get_task_tag(cmd));
- wait_for_completion(&cmd->transport_lun_stop_comp);
- pr_debug("ConfigFS: ITT[0x%08x] - stopped cmd....\n",
- cmd->se_tfo->get_task_tag(cmd));
- }
-
- return 0;
-}
-
-static void __transport_clear_lun_from_sessions(struct se_lun *lun)
-{
- struct se_cmd *cmd = NULL;
- unsigned long lun_flags, cmd_flags;
- /*
- * Do exception processing and return CHECK_CONDITION status to the
- * Initiator Port.
- */
- spin_lock_irqsave(&lun->lun_cmd_lock, lun_flags);
- while (!list_empty(&lun->lun_cmd_list)) {
- cmd = list_first_entry(&lun->lun_cmd_list,
- struct se_cmd, se_lun_node);
- list_del_init(&cmd->se_lun_node);
-
- spin_lock(&cmd->t_state_lock);
- pr_debug("SE_LUN[%d] - Setting cmd->transport"
- "_lun_stop for ITT: 0x%08x\n",
- cmd->se_lun->unpacked_lun,
- cmd->se_tfo->get_task_tag(cmd));
- cmd->transport_state |= CMD_T_LUN_STOP;
- spin_unlock(&cmd->t_state_lock);
-
- spin_unlock_irqrestore(&lun->lun_cmd_lock, lun_flags);
-
- if (!cmd->se_lun) {
- pr_err("ITT: 0x%08x, [i,t]_state: %u/%u\n",
- cmd->se_tfo->get_task_tag(cmd),
- cmd->se_tfo->get_cmd_state(cmd), cmd->t_state);
- BUG();
- }
- /*
- * If the Storage engine still owns the iscsi_cmd_t, determine
- * and/or stop its context.
- */
- pr_debug("SE_LUN[%d] - ITT: 0x%08x before transport"
- "_lun_wait_for_tasks()\n", cmd->se_lun->unpacked_lun,
- cmd->se_tfo->get_task_tag(cmd));
-
- if (transport_lun_wait_for_tasks(cmd, cmd->se_lun) < 0) {
- spin_lock_irqsave(&lun->lun_cmd_lock, lun_flags);
- continue;
- }
-
- pr_debug("SE_LUN[%d] - ITT: 0x%08x after transport_lun"
- "_wait_for_tasks(): SUCCESS\n",
- cmd->se_lun->unpacked_lun,
- cmd->se_tfo->get_task_tag(cmd));
-
- spin_lock_irqsave(&cmd->t_state_lock, cmd_flags);
- if (!(cmd->transport_state & CMD_T_DEV_ACTIVE)) {
- spin_unlock_irqrestore(&cmd->t_state_lock, cmd_flags);
- goto check_cond;
- }
- cmd->transport_state &= ~CMD_T_DEV_ACTIVE;
- target_remove_from_state_list(cmd);
- spin_unlock_irqrestore(&cmd->t_state_lock, cmd_flags);
-
- /*
- * The Storage engine stopped this struct se_cmd before it was
- * send to the fabric frontend for delivery back to the
- * Initiator Node. Return this SCSI CDB back with an
- * CHECK_CONDITION status.
- */
-check_cond:
- transport_send_check_condition_and_sense(cmd,
- TCM_NON_EXISTENT_LUN, 0);
- /*
- * If the fabric frontend is waiting for this iscsi_cmd_t to
- * be released, notify the waiting thread now that LU has
- * finished accessing it.
- */
- spin_lock_irqsave(&cmd->t_state_lock, cmd_flags);
- if (cmd->transport_state & CMD_T_LUN_FE_STOP) {
- pr_debug("SE_LUN[%d] - Detected FE stop for"
- " struct se_cmd: %p ITT: 0x%08x\n",
- lun->unpacked_lun,
- cmd, cmd->se_tfo->get_task_tag(cmd));
-
- spin_unlock_irqrestore(&cmd->t_state_lock,
- cmd_flags);
- transport_cmd_check_stop(cmd, false, false);
- complete(&cmd->transport_lun_fe_stop_comp);
- spin_lock_irqsave(&lun->lun_cmd_lock, lun_flags);
- continue;
- }
- pr_debug("SE_LUN[%d] - ITT: 0x%08x finished processing\n",
- lun->unpacked_lun, cmd->se_tfo->get_task_tag(cmd));
-
- spin_unlock_irqrestore(&cmd->t_state_lock, cmd_flags);
- spin_lock_irqsave(&lun->lun_cmd_lock, lun_flags);
- }
- spin_unlock_irqrestore(&lun->lun_cmd_lock, lun_flags);
-}
-
-static int transport_clear_lun_thread(void *p)
+static int transport_clear_lun_ref_thread(void *p)
{
struct se_lun *lun = p;
- __transport_clear_lun_from_sessions(lun);
+ percpu_ref_kill(&lun->lun_ref);
+
+ wait_for_completion(&lun->lun_ref_comp);
complete(&lun->lun_shutdown_comp);
return 0;
}
-int transport_clear_lun_from_sessions(struct se_lun *lun)
+int transport_clear_lun_ref(struct se_lun *lun)
{
struct task_struct *kt;
- kt = kthread_run(transport_clear_lun_thread, lun,
+ kt = kthread_run(transport_clear_lun_ref_thread, lun,
"tcm_cl_%u", lun->unpacked_lun);
if (IS_ERR(kt)) {
pr_err("Unable to start clear_lun thread\n");
spin_unlock_irqrestore(&cmd->t_state_lock, flags);
return false;
}
- /*
- * If we are already stopped due to an external event (ie: LUN shutdown)
- * sleep until the connection can have the passed struct se_cmd back.
- * The cmd->transport_lun_stopped_sem will be upped by
- * transport_clear_lun_from_sessions() once the ConfigFS context caller
- * has completed its operation on the struct se_cmd.
- */
- if (cmd->transport_state & CMD_T_LUN_STOP) {
- pr_debug("wait_for_tasks: Stopping"
- " wait_for_completion(&cmd->t_tasktransport_lun_fe"
- "_stop_comp); for ITT: 0x%08x\n",
- cmd->se_tfo->get_task_tag(cmd));
- /*
- * There is a special case for WRITES where a FE exception +
- * LUN shutdown means ConfigFS context is still sleeping on
- * transport_lun_stop_comp in transport_lun_wait_for_tasks().
- * We go ahead and up transport_lun_stop_comp just to be sure
- * here.
- */
- spin_unlock_irqrestore(&cmd->t_state_lock, flags);
- complete(&cmd->transport_lun_stop_comp);
- wait_for_completion(&cmd->transport_lun_fe_stop_comp);
- spin_lock_irqsave(&cmd->t_state_lock, flags);
-
- target_remove_from_state_list(cmd);
- /*
- * At this point, the frontend who was the originator of this
- * struct se_cmd, now owns the structure and can be released through
- * normal means below.
- */
- pr_debug("wait_for_tasks: Stopped"
- " wait_for_completion(&cmd->t_tasktransport_lun_fe_"
- "stop_comp); for ITT: 0x%08x\n",
- cmd->se_tfo->get_task_tag(cmd));
-
- cmd->transport_state &= ~CMD_T_LUN_STOP;
- }
if (!(cmd->transport_state & CMD_T_ACTIVE)) {
spin_unlock_irqrestore(&cmd->t_state_lock, flags);
cmd->t_task_cdb[0], cmd->se_tfo->get_task_tag(cmd));
cmd->se_cmd_flags |= SCF_SENT_DELAYED_TAS;
+ cmd->scsi_status = SAM_STAT_TASK_ABORTED;
trace_target_cmd_complete(cmd);
cmd->se_tfo->queue_status(cmd);
if (cmd->se_tfo->write_pending_status(cmd) != 0) {
cmd->transport_state |= CMD_T_ABORTED;
smp_mb__after_atomic_inc();
+ return;
}
}
cmd->scsi_status = SAM_STAT_TASK_ABORTED;
#define ASCQ_2AH_RESERVATIONS_RELEASED 0x04
#define ASCQ_2AH_REGISTRATIONS_PREEMPTED 0x05
#define ASCQ_2AH_ASYMMETRIC_ACCESS_STATE_CHANGED 0x06
-#define ASCQ_2AH_IMPLICT_ASYMMETRIC_ACCESS_STATE_TRANSITION_FAILED 0x07
+#define ASCQ_2AH_IMPLICIT_ASYMMETRIC_ACCESS_STATE_TRANSITION_FAILED 0x07
#define ASCQ_2AH_PRIORITY_CHANGED 0x08
#define ASCQ_2CH_PREVIOUS_RESERVATION_CONFLICT_STATUS 0x09
struct xcopy_pt_cmd *xpt_cmd = container_of(se_cmd,
struct xcopy_pt_cmd, se_cmd);
- if (xpt_cmd->remote_port)
- kfree(se_cmd->se_lun);
-
kfree(xpt_cmd);
}
return 0;
}
- pt_cmd->se_lun = kzalloc(sizeof(struct se_lun), GFP_KERNEL);
- if (!pt_cmd->se_lun) {
- pr_err("Unable to allocate pt_cmd->se_lun\n");
- return -ENOMEM;
- }
- init_completion(&pt_cmd->se_lun->lun_shutdown_comp);
- INIT_LIST_HEAD(&pt_cmd->se_lun->lun_cmd_list);
- INIT_LIST_HEAD(&pt_cmd->se_lun->lun_acl_list);
- spin_lock_init(&pt_cmd->se_lun->lun_acl_lock);
- spin_lock_init(&pt_cmd->se_lun->lun_cmd_lock);
- spin_lock_init(&pt_cmd->se_lun->lun_sep_lock);
-
+ pt_cmd->se_lun = &se_dev->xcopy_lun;
pt_cmd->se_dev = se_dev;
pr_debug("Setup emulated se_dev: %p from se_dev\n", pt_cmd->se_dev);
- pt_cmd->se_lun->lun_se_dev = se_dev;
pt_cmd->se_cmd_flags |= SCF_SE_LUN_CMD | SCF_CMD_XCOPY_PASSTHROUGH;
pr_debug("Setup emulated se_dev: %p to pt_cmd->se_lun->lun_se_dev\n",
return 0;
out:
- if (remote_port == true)
- kfree(cmd->se_lun);
return ret;
}
#define FT_NAMELEN 32 /* length of ASCII WWPNs including pad */
#define FT_TPG_NAMELEN 32 /* max length of TPG name */
#define FT_LUN_NAMELEN 32 /* max length of LUN name */
+#define TCM_FC_DEFAULT_TAGS 512 /* tags used for per-session preallocation */
struct ft_transport_id {
__u8 format;
#include <linux/configfs.h>
#include <linux/ctype.h>
#include <linux/hash.h>
+#include <linux/percpu_ida.h>
#include <asm/unaligned.h>
#include <scsi/scsi.h>
#include <scsi/scsi_host.h>
{
struct fc_frame *fp;
struct fc_lport *lport;
+ struct se_session *se_sess;
if (!cmd)
return;
+ se_sess = cmd->sess->se_sess;
fp = cmd->req_frame;
lport = fr_dev(fp);
if (fr_seq(fp))
lport->tt.seq_release(fr_seq(fp));
fc_frame_free(fp);
+ percpu_ida_free(&se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
ft_sess_put(cmd->sess); /* undo get from lookup at recv */
- kfree(cmd);
}
void ft_release_cmd(struct se_cmd *se_cmd)
{
struct ft_cmd *cmd;
struct fc_lport *lport = sess->tport->lport;
+ struct se_session *se_sess = sess->se_sess;
+ int tag;
- cmd = kzalloc(sizeof(*cmd), GFP_ATOMIC);
- if (!cmd)
+ tag = percpu_ida_alloc(&se_sess->sess_tag_pool, GFP_ATOMIC);
+ if (tag < 0)
goto busy;
+
+ cmd = &((struct ft_cmd *)se_sess->sess_cmd_map)[tag];
+ memset(cmd, 0, sizeof(struct ft_cmd));
+
+ cmd->se_cmd.map_tag = tag;
cmd->sess = sess;
cmd->seq = lport->tt.seq_assign(lport, fp);
if (!cmd->seq) {
- kfree(cmd);
+ percpu_ida_free(&se_sess->sess_tag_pool, tag);
goto busy;
}
cmd->req_frame = fp; /* hold frame during cmd */
/*
* Setup default attribute lists for various fabric->tf_cit_tmpl
*/
- TF_CIT_TMPL(fabric)->tfc_wwn_cit.ct_attrs = ft_wwn_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_base_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_attrib_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_param_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_np_base_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_base_cit.ct_attrs =
+ fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = ft_wwn_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs =
ft_nacl_base_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_param_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL;
/*
* register the fabric for use within TCM
*/
if (!sess)
return NULL;
- sess->se_sess = transport_init_session();
+ sess->se_sess = transport_init_session_tags(TCM_FC_DEFAULT_TAGS,
+ sizeof(struct ft_cmd));
if (IS_ERR(sess->se_sess)) {
kfree(sess);
return NULL;
}
fabric->tf_ops = usbg_ops;
- TF_CIT_TMPL(fabric)->tfc_wwn_cit.ct_attrs = usbg_wwn_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_base_cit.ct_attrs = usbg_base_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_attrib_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_param_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_np_base_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_base_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_param_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = usbg_wwn_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = usbg_base_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL;
ret = target_fabric_configfs_register(fabric);
if (ret < 0) {
printk(KERN_ERR "target_fabric_configfs_register() failed"
/*
* Setup default attribute lists for various fabric->tf_cit_tmpl
*/
- TF_CIT_TMPL(fabric)->tfc_wwn_cit.ct_attrs = tcm_vhost_wwn_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_base_cit.ct_attrs = tcm_vhost_tpg_attrs;
- TF_CIT_TMPL(fabric)->tfc_tpg_attrib_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_param_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_np_base_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_base_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
- TF_CIT_TMPL(fabric)->tfc_tpg_nacl_param_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = tcm_vhost_wwn_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = tcm_vhost_tpg_attrs;
+ fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
+ fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL;
/*
* Register the fabric for use within TCM
*/
struct percpu_ref users;
atomic_t dead;
+ struct percpu_ref reqs;
+
unsigned long user_id;
struct __percpu kioctx_cpu *cpu;
struct page **ring_pages;
long nr_pages;
- struct rcu_head rcu_head;
struct work_struct free_work;
struct {
put_aio_ring_file(ctx);
- if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages)
+ if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages) {
kfree(ctx->ring_pages);
+ ctx->ring_pages = NULL;
+ }
}
static int aio_ring_mmap(struct file *file, struct vm_area_struct *vma)
return cancel(kiocb);
}
-static void free_ioctx_rcu(struct rcu_head *head)
+static void free_ioctx(struct work_struct *work)
{
- struct kioctx *ctx = container_of(head, struct kioctx, rcu_head);
+ struct kioctx *ctx = container_of(work, struct kioctx, free_work);
+ pr_debug("freeing %p\n", ctx);
+
+ aio_free_ring(ctx);
free_percpu(ctx->cpu);
kmem_cache_free(kioctx_cachep, ctx);
}
+static void free_ioctx_reqs(struct percpu_ref *ref)
+{
+ struct kioctx *ctx = container_of(ref, struct kioctx, reqs);
+
+ INIT_WORK(&ctx->free_work, free_ioctx);
+ schedule_work(&ctx->free_work);
+}
+
/*
* When this function runs, the kioctx has been removed from the "hash table"
* and ctx->users has dropped to 0, so we know no more kiocbs can be submitted -
* now it's safe to cancel any that need to be.
*/
-static void free_ioctx(struct work_struct *work)
+static void free_ioctx_users(struct percpu_ref *ref)
{
- struct kioctx *ctx = container_of(work, struct kioctx, free_work);
- struct aio_ring *ring;
+ struct kioctx *ctx = container_of(ref, struct kioctx, users);
struct kiocb *req;
- unsigned cpu, avail;
- DEFINE_WAIT(wait);
spin_lock_irq(&ctx->ctx_lock);
spin_unlock_irq(&ctx->ctx_lock);
- for_each_possible_cpu(cpu) {
- struct kioctx_cpu *kcpu = per_cpu_ptr(ctx->cpu, cpu);
-
- atomic_add(kcpu->reqs_available, &ctx->reqs_available);
- kcpu->reqs_available = 0;
- }
-
- while (1) {
- prepare_to_wait(&ctx->wait, &wait, TASK_UNINTERRUPTIBLE);
-
- ring = kmap_atomic(ctx->ring_pages[0]);
- avail = (ring->head <= ring->tail)
- ? ring->tail - ring->head
- : ctx->nr_events - ring->head + ring->tail;
-
- atomic_add(avail, &ctx->reqs_available);
- ring->head = ring->tail;
- kunmap_atomic(ring);
-
- if (atomic_read(&ctx->reqs_available) >= ctx->nr_events - 1)
- break;
-
- schedule();
- }
- finish_wait(&ctx->wait, &wait);
-
- WARN_ON(atomic_read(&ctx->reqs_available) > ctx->nr_events - 1);
-
- aio_free_ring(ctx);
-
- pr_debug("freeing %p\n", ctx);
-
- /*
- * Here the call_rcu() is between the wait_event() for reqs_active to
- * hit 0, and freeing the ioctx.
- *
- * aio_complete() decrements reqs_active, but it has to touch the ioctx
- * after to issue a wakeup so we use rcu.
- */
- call_rcu(&ctx->rcu_head, free_ioctx_rcu);
-}
-
-static void free_ioctx_ref(struct percpu_ref *ref)
-{
- struct kioctx *ctx = container_of(ref, struct kioctx, users);
-
- INIT_WORK(&ctx->free_work, free_ioctx);
- schedule_work(&ctx->free_work);
+ percpu_ref_kill(&ctx->reqs);
+ percpu_ref_put(&ctx->reqs);
}
static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm)
}
}
+static void aio_nr_sub(unsigned nr)
+{
+ spin_lock(&aio_nr_lock);
+ if (WARN_ON(aio_nr - nr > aio_nr))
+ aio_nr = 0;
+ else
+ aio_nr -= nr;
+ spin_unlock(&aio_nr_lock);
+}
+
/* ioctx_alloc
* Allocates and initializes an ioctx. Returns an ERR_PTR if it failed.
*/
ctx->max_reqs = nr_events;
- if (percpu_ref_init(&ctx->users, free_ioctx_ref))
- goto out_freectx;
+ if (percpu_ref_init(&ctx->users, free_ioctx_users))
+ goto err;
+
+ if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs))
+ goto err;
spin_lock_init(&ctx->ctx_lock);
spin_lock_init(&ctx->completion_lock);
ctx->cpu = alloc_percpu(struct kioctx_cpu);
if (!ctx->cpu)
- goto out_freeref;
+ goto err;
if (aio_setup_ring(ctx) < 0)
- goto out_freepcpu;
+ goto err;
atomic_set(&ctx->reqs_available, ctx->nr_events - 1);
ctx->req_batch = (ctx->nr_events - 1) / (num_possible_cpus() * 4);
if (aio_nr + nr_events > (aio_max_nr * 2UL) ||
aio_nr + nr_events < aio_nr) {
spin_unlock(&aio_nr_lock);
- goto out_cleanup;
+ err = -EAGAIN;
+ goto err;
}
aio_nr += ctx->max_reqs;
spin_unlock(&aio_nr_lock);
err = ioctx_add_table(ctx, mm);
if (err)
- goto out_cleanup_put;
+ goto err_cleanup;
pr_debug("allocated ioctx %p[%ld]: mm=%p mask=0x%x\n",
ctx, ctx->user_id, mm, ctx->nr_events);
return ctx;
-out_cleanup_put:
- percpu_ref_put(&ctx->users);
-out_cleanup:
- err = -EAGAIN;
- aio_free_ring(ctx);
-out_freepcpu:
+err_cleanup:
+ aio_nr_sub(ctx->max_reqs);
+err:
free_percpu(ctx->cpu);
-out_freeref:
+ free_percpu(ctx->reqs.pcpu_count);
free_percpu(ctx->users.pcpu_count);
-out_freectx:
- put_aio_ring_file(ctx);
kmem_cache_free(kioctx_cachep, ctx);
pr_debug("error allocating ioctx %d\n", err);
return ERR_PTR(err);
* -EAGAIN with no ioctxs actually in use (as far as userspace
* could tell).
*/
- spin_lock(&aio_nr_lock);
- BUG_ON(aio_nr - ctx->max_reqs > aio_nr);
- aio_nr -= ctx->max_reqs;
- spin_unlock(&aio_nr_lock);
+ aio_nr_sub(ctx->max_reqs);
if (ctx->mmap_size)
vm_munmap(ctx->mmap_base, ctx->mmap_size);
if (unlikely(!req))
goto out_put;
+ percpu_ref_get(&ctx->reqs);
+
req->ki_ctx = ctx;
return req;
out_put:
return;
}
- /*
- * Take rcu_read_lock() in case the kioctx is being destroyed, as we
- * need to issue a wakeup after incrementing reqs_available.
- */
- rcu_read_lock();
-
if (iocb->ki_list.next) {
unsigned long flags;
if (waitqueue_active(&ctx->wait))
wake_up(&ctx->wait);
- rcu_read_unlock();
+ percpu_ref_put(&ctx->reqs);
}
EXPORT_SYMBOL(aio_complete);
return 0;
out_put_req:
put_reqs_available(ctx, 1);
+ percpu_ref_put(&ctx->reqs);
kiocb_free(req);
return ret;
}
select XOR_BLOCKS
help
- Btrfs is a new filesystem with extents, writable snapshotting,
- support for multiple devices and many more features.
+ Btrfs is a general purpose copy-on-write filesystem with extents,
+ writable snapshotting, support for multiple devices and many more
+ features focused on fault tolerance, repair and easy administration.
- Btrfs is highly experimental, and THE DISK FORMAT IS NOT YET
- FINALIZED. You should say N here unless you are interested in
- testing Btrfs with non-critical data.
+ The filesystem disk format is no longer unstable, and it's not
+ expected to change unless there are strong reasons to do so. If there
+ is a format change, file systems with a unchanged format will
+ continue to be mountable and usable by newer kernels.
+
+ For more information, please see the web pages at
+ http://btrfs.wiki.kernel.org.
To compile this file system support as a module, choose M here. The
module will be called btrfs.
spin_lock_irq(&workers->lock);
if (workers->stopping) {
spin_unlock_irq(&workers->lock);
+ ret = -EINVAL;
goto fail_kthread;
}
list_add_tail(&worker->worker_list, &workers->idle_list);
* the integrity of (super)-block write requests, do not
* enable the config option BTRFS_FS_CHECK_INTEGRITY to
* include and compile the integrity check tool.
+ *
+ * Expect millions of lines of information in the kernel log with an
+ * enabled check_int_print_mask. Therefore set LOG_BUF_SHIFT in the
+ * kernel config to at least 26 (which is 64MB). Usually the value is
+ * limited to 21 (which is 2MB) in init/Kconfig. The file needs to be
+ * changed like this before LOG_BUF_SHIFT can be set to a high value:
+ * config LOG_BUF_SHIFT
+ * int "Kernel log buffer size (16 => 64KB, 17 => 128KB)"
+ * range 12 30
*/
#include <linux/sched.h>
#define BTRFSIC_PRINT_MASK_INITIAL_DATABASE 0x00000400
#define BTRFSIC_PRINT_MASK_NUM_COPIES 0x00000800
#define BTRFSIC_PRINT_MASK_TREE_WITH_ALL_MIRRORS 0x00001000
+#define BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH_VERBOSE 0x00002000
struct btrfsic_dev_state;
struct btrfsic_state;
(rw & WRITE) && NULL != bio->bi_io_vec) {
unsigned int i;
u64 dev_bytenr;
+ u64 cur_bytenr;
int bio_is_patched;
char **mapped_datav;
GFP_NOFS);
if (!mapped_datav)
goto leave;
+ cur_bytenr = dev_bytenr;
for (i = 0; i < bio->bi_vcnt; i++) {
BUG_ON(bio->bi_io_vec[i].bv_len != PAGE_CACHE_SIZE);
mapped_datav[i] = kmap(bio->bi_io_vec[i].bv_page);
kfree(mapped_datav);
goto leave;
}
- if ((BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH |
- BTRFSIC_PRINT_MASK_VERBOSE) ==
- (dev_state->state->print_mask &
- (BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH |
- BTRFSIC_PRINT_MASK_VERBOSE)))
+ if (dev_state->state->print_mask &
+ BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH_VERBOSE)
printk(KERN_INFO
- "#%u: page=%p, len=%u, offset=%u\n",
- i, bio->bi_io_vec[i].bv_page,
- bio->bi_io_vec[i].bv_len,
+ "#%u: bytenr=%llu, len=%u, offset=%u\n",
+ i, cur_bytenr, bio->bi_io_vec[i].bv_len,
bio->bi_io_vec[i].bv_offset);
+ cur_bytenr += bio->bi_io_vec[i].bv_len;
}
btrfsic_process_written_block(dev_state, dev_bytenr,
mapped_datav, bio->bi_vcnt,
struct btrfs_ordered_sum *sums);
int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
struct bio *bio, u64 file_start, int contig);
-int btrfs_csum_truncate(struct btrfs_trans_handle *trans,
- struct btrfs_root *root, struct btrfs_path *path,
- u64 isize);
int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
struct list_head *list, int search_commit);
/* inode.c */
int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
int skip_pinned);
-int btrfs_replace_extent_cache(struct inode *inode, struct extent_map *replace,
- u64 start, u64 end, int skip_pinned,
- int modified);
extern const struct file_operations btrfs_file_operations;
int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct inode *inode,
dev_replace->tgtdev = tgt_device;
printk_in_rcu(KERN_INFO
- "btrfs: dev_replace from %s (devid %llu) to %s) started\n",
+ "btrfs: dev_replace from %s (devid %llu) to %s started\n",
src_device->missing ? "<missing disk>" :
rcu_str_deref(src_device->name),
src_device->devid,
int btrfs_commit_super(struct btrfs_root *root)
{
struct btrfs_trans_handle *trans;
- int ret;
mutex_lock(&root->fs_info->cleaner_mutex);
btrfs_run_delayed_iputs(root);
trans = btrfs_join_transaction(root);
if (IS_ERR(trans))
return PTR_ERR(trans);
- ret = btrfs_commit_transaction(trans, root);
- if (ret)
- return ret;
- /* run commit again to drop the original snapshot */
- trans = btrfs_join_transaction(root);
- if (IS_ERR(trans))
- return PTR_ERR(trans);
- ret = btrfs_commit_transaction(trans, root);
- if (ret)
- return ret;
- ret = btrfs_write_and_wait_transaction(NULL, root);
- if (ret) {
- btrfs_error(root->fs_info, ret,
- "Failed to sync btree inode to disk.");
- return ret;
- }
-
- ret = write_ctree_super(NULL, root, 0);
- return ret;
+ return btrfs_commit_transaction(trans, root);
}
int close_ctree(struct btrfs_root *root)
struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
int ret;
+ ASSERT(!(fs_info->sb->s_flags & MS_RDONLY));
BUG_ON(!mirror_num);
/* we can't repair anything in raid56 yet */
unsigned long i, num_pages = num_extent_pages(eb->start, eb->len);
int ret = 0;
+ if (root->fs_info->sb->s_flags & MS_RDONLY)
+ return -EROFS;
+
for (i = 0; i < num_pages; i++) {
struct page *p = extent_buffer_page(eb, i);
ret = repair_io_failure(root->fs_info, start, PAGE_CACHE_SIZE,
u64 private;
u64 private_failure;
struct io_failure_record *failrec;
- struct btrfs_fs_info *fs_info;
+ struct inode *inode = page->mapping->host;
+ struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
struct extent_state *state;
int num_copies;
int did_repair = 0;
int ret;
- struct inode *inode = page->mapping->host;
private = 0;
ret = count_range_bits(&BTRFS_I(inode)->io_failure_tree, &private,
did_repair = 1;
goto out;
}
+ if (fs_info->sb->s_flags & MS_RDONLY)
+ goto out;
spin_lock(&BTRFS_I(inode)->io_tree.lock);
state = find_first_extent_bit_state(&BTRFS_I(inode)->io_tree,
if (state && state->start <= failrec->start &&
state->end >= failrec->start + failrec->len - 1) {
- fs_info = BTRFS_I(inode)->root->fs_info;
num_copies = btrfs_num_copies(fs_info, failrec->logical,
failrec->len);
if (num_copies > 1) {
old->extent_offset, fs_info,
path, record_one_backref,
old);
- BUG_ON(ret < 0 && ret != -ENOENT);
+ if (ret < 0 && ret != -ENOENT)
+ return false;
/* no backref to be processed for this extent */
if (!old->count) {
write_unlock(&em_tree->lock);
out:
- if (em)
- trace_btrfs_get_extent(root, em);
+ trace_btrfs_get_extent(root, em);
if (path)
btrfs_free_path(path);
WARN_ON(nr < 0);
}
}
+ list_splice_tail(&splice, &fs_info->ordered_roots);
spin_unlock(&fs_info->ordered_root_lock);
}
btrfs_put_ordered_extent(ordered);
break;
}
- if (ordered->file_offset + ordered->len < start) {
+ if (ordered->file_offset + ordered->len <= start) {
btrfs_put_ordered_extent(ordered);
break;
}
BTRFS_DEV_STAT_CORRUPTION_ERRS);
}
- if (sctx->readonly && !sctx->is_dev_replace)
- goto did_not_correct_error;
+ if (sctx->readonly) {
+ ASSERT(!sctx->is_dev_replace);
+ goto out;
+ }
if (!is_metadata && !have_csum) {
struct scrub_fixup_nodatasum *fixup_nodatasum;
* We've got freeze protection passed with the transaction.
* Tell lockdep about it.
*/
- if (ac->newtrans->type < TRANS_JOIN_NOLOCK)
+ if (ac->newtrans->type & __TRANS_FREEZABLE)
rwsem_acquire_read(
&ac->root->fs_info->sb->s_writers.lock_map[SB_FREEZE_FS-1],
0, 1, _THIS_IP_);
* Tell lockdep we've released the freeze rwsem, since the
* async commit thread will be the one to unlock it.
*/
- if (trans->type < TRANS_JOIN_NOLOCK)
+ if (ac->newtrans->type & __TRANS_FREEZABLE)
rwsem_release(
&root->fs_info->sb->s_writers.lock_map[SB_FREEZE_FS-1],
1, _THIS_IP_);
ret = btrfs_truncate_inode_items(trans, log,
inode, 0, 0);
} else if (test_and_clear_bit(BTRFS_INODE_COPY_EVERYTHING,
- &BTRFS_I(inode)->runtime_flags)) {
+ &BTRFS_I(inode)->runtime_flags) ||
+ inode_only == LOG_INODE_EXISTS) {
if (inode_only == LOG_INODE_ALL)
fast_search = true;
max_key.type = BTRFS_XATTR_ITEM_KEY;
err = ret;
goto out_unlock;
}
- } else {
+ } else if (inode_only == LOG_INODE_ALL) {
struct extent_map_tree *tree = &BTRFS_I(inode)->extent_tree;
struct extent_map *em, *n;
{
struct bio_vec *prev;
struct request_queue *q = bdev_get_queue(bdev);
- unsigned short max_sectors = queue_max_sectors(q);
+ unsigned int max_sectors = queue_max_sectors(q);
struct bvec_merge_data bvm = {
.bi_bdev = bdev,
.bi_sector = sector,
struct configfs_dirent *sd = dentry->d_fsdata;
if (sd) {
- BUG_ON(sd->s_dentry != dentry);
/* Coordinate with configfs_readdir */
spin_lock(&configfs_dirent_lock);
- sd->s_dentry = NULL;
+ /* Coordinate with configfs_attach_attr where will increase
+ * sd->s_count and update sd->s_dentry to new allocated one.
+ * Only set sd->dentry to null when this dentry is the only
+ * sd owner.
+ * If not do so, configfs_d_iput may run just after
+ * configfs_attach_attr and set sd->s_dentry to null
+ * even it's still in use.
+ */
+ if (atomic_read(&sd->s_count) <= 2)
+ sd->s_dentry = NULL;
+
spin_unlock(&configfs_dirent_lock);
configfs_put(sd);
}
struct configfs_attribute * attr = sd->s_element;
int error;
+ spin_lock(&configfs_dirent_lock);
dentry->d_fsdata = configfs_get(sd);
sd->s_dentry = dentry;
+ spin_unlock(&configfs_dirent_lock);
+
error = configfs_create(dentry, (attr->ca_mode & S_IALLUGO) | S_IFREG,
configfs_init_file);
if (error) {
static long
ecryptfs_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
- struct file *lower_file = NULL;
+ struct file *lower_file = ecryptfs_file_to_lower(file);
long rc = -ENOTTY;
- if (ecryptfs_file_to_private(file))
- lower_file = ecryptfs_file_to_lower(file);
if (lower_file->f_op->unlocked_ioctl)
rc = lower_file->f_op->unlocked_ioctl(lower_file, cmd, arg);
return rc;
static long
ecryptfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
- struct file *lower_file = NULL;
+ struct file *lower_file = ecryptfs_file_to_lower(file);
long rc = -ENOIOCTLCMD;
- if (ecryptfs_file_to_private(file))
- lower_file = ecryptfs_file_to_lower(file);
if (lower_file->f_op && lower_file->f_op->compat_ioctl)
rc = lower_file->f_op->compat_ioctl(lower_file, cmd, arg);
return rc;
if (retval)
return retval;
- retval = audit_bprm(bprm);
- if (retval)
- return retval;
-
retval = -ENOENT;
retry:
read_lock(&binfmt_lock);
ret = search_binary_handler(bprm);
if (ret >= 0) {
+ audit_bprm(bprm);
trace_sched_process_exec(current, old_pid, bprm);
ptrace_event(PTRACE_EVENT_EXEC, old_vpid);
current->did_exec = 1;
gi->nhash = 0;
}
/* Skip entries for other sb and dead entries */
- } while (gi->sdp != gi->gl->gl_sbd || __lockref_is_dead(&gl->gl_lockref));
+ } while (gi->sdp != gi->gl->gl_sbd ||
+ __lockref_is_dead(&gi->gl->gl_lockref));
return 0;
}
if (d != NULL)
dentry = d;
if (dentry->d_inode) {
- if (!(*opened & FILE_OPENED))
+ if (!(*opened & FILE_OPENED)) {
+ if (d == NULL)
+ dget(dentry);
return finish_no_open(file, dentry);
+ }
dput(d);
return 0;
}
*/
static inline int may_create(struct inode *dir, struct dentry *child)
{
+ audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE);
if (child->d_inode)
return -EEXIST;
if (IS_DEADDIR(dir))
static void next_decode_page(struct nfsd4_compoundargs *argp)
{
- argp->pagelist++;
argp->p = page_address(argp->pagelist[0]);
+ argp->pagelist++;
if (argp->pagelen < PAGE_SIZE) {
argp->end = argp->p + (argp->pagelen>>2);
argp->pagelen = 0;
len -= pages * PAGE_SIZE;
argp->p = (__be32 *)page_address(argp->pagelist[0]);
+ argp->pagelist++;
argp->end = argp->p + XDR_QUADLEN(PAGE_SIZE);
}
argp->p += XDR_QUADLEN(len);
}
/*
- * Set various file attributes.
- * N.B. After this call fhp needs an fh_put
+ * Go over the attributes and take care of the small differences between
+ * NFS semantics and what Linux expects.
*/
-__be32
-nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
- int check_guard, time_t guardtime)
+static void
+nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap)
{
- struct dentry *dentry;
- struct inode *inode;
- int accmode = NFSD_MAY_SATTR;
- umode_t ftype = 0;
- __be32 err;
- int host_err;
- int size_change = 0;
-
- if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
- accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
- if (iap->ia_valid & ATTR_SIZE)
- ftype = S_IFREG;
-
- /* Get inode */
- err = fh_verify(rqstp, fhp, ftype, accmode);
- if (err)
- goto out;
-
- dentry = fhp->fh_dentry;
- inode = dentry->d_inode;
-
- /* Ignore any mode updates on symlinks */
- if (S_ISLNK(inode->i_mode))
- iap->ia_valid &= ~ATTR_MODE;
-
- if (!iap->ia_valid)
- goto out;
-
/*
* NFSv2 does not differentiate between "set-[ac]time-to-now"
* which only requires access, and "set-[ac]time-to-X" which
* convert to "set to now" instead of "set to explicit time"
*
* We only call inode_change_ok as the last test as technically
- * it is not an interface that we should be using. It is only
- * valid if the filesystem does not define it's own i_op->setattr.
+ * it is not an interface that we should be using.
*/
#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET)
#define MAX_TOUCH_TIME_ERROR (30*60)
iap->ia_valid &= ~BOTH_TIME_SET;
}
}
-
- /*
- * The size case is special.
- * It changes the file as well as the attributes.
- */
- if (iap->ia_valid & ATTR_SIZE) {
- if (iap->ia_size < inode->i_size) {
- err = nfsd_permission(rqstp, fhp->fh_export, dentry,
- NFSD_MAY_TRUNC|NFSD_MAY_OWNER_OVERRIDE);
- if (err)
- goto out;
- }
-
- host_err = get_write_access(inode);
- if (host_err)
- goto out_nfserr;
-
- size_change = 1;
- host_err = locks_verify_truncate(inode, NULL, iap->ia_size);
- if (host_err) {
- put_write_access(inode);
- goto out_nfserr;
- }
- }
/* sanitize the mode change */
if (iap->ia_valid & ATTR_MODE) {
iap->ia_valid |= (ATTR_KILL_SUID | ATTR_KILL_SGID);
}
}
+}
- /* Change the attributes. */
+static __be32
+nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ struct iattr *iap)
+{
+ struct inode *inode = fhp->fh_dentry->d_inode;
+ int host_err;
- iap->ia_valid |= ATTR_CTIME;
+ if (iap->ia_size < inode->i_size) {
+ __be32 err;
- err = nfserr_notsync;
- if (!check_guard || guardtime == inode->i_ctime.tv_sec) {
- host_err = nfsd_break_lease(inode);
- if (host_err)
- goto out_nfserr;
- fh_lock(fhp);
+ err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
+ NFSD_MAY_TRUNC | NFSD_MAY_OWNER_OVERRIDE);
+ if (err)
+ return err;
+ }
- host_err = notify_change(dentry, iap, NULL);
- err = nfserrno(host_err);
- fh_unlock(fhp);
+ host_err = get_write_access(inode);
+ if (host_err)
+ goto out_nfserrno;
+
+ host_err = locks_verify_truncate(inode, NULL, iap->ia_size);
+ if (host_err)
+ goto out_put_write_access;
+ return 0;
+
+out_put_write_access:
+ put_write_access(inode);
+out_nfserrno:
+ return nfserrno(host_err);
+}
+
+/*
+ * Set various file attributes. After this call fhp needs an fh_put.
+ */
+__be32
+nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
+ int check_guard, time_t guardtime)
+{
+ struct dentry *dentry;
+ struct inode *inode;
+ int accmode = NFSD_MAY_SATTR;
+ umode_t ftype = 0;
+ __be32 err;
+ int host_err;
+ int size_change = 0;
+
+ if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
+ accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
+ if (iap->ia_valid & ATTR_SIZE)
+ ftype = S_IFREG;
+
+ /* Get inode */
+ err = fh_verify(rqstp, fhp, ftype, accmode);
+ if (err)
+ goto out;
+
+ dentry = fhp->fh_dentry;
+ inode = dentry->d_inode;
+
+ /* Ignore any mode updates on symlinks */
+ if (S_ISLNK(inode->i_mode))
+ iap->ia_valid &= ~ATTR_MODE;
+
+ if (!iap->ia_valid)
+ goto out;
+
+ nfsd_sanitize_attrs(inode, iap);
+
+ /*
+ * The size case is special, it changes the file in addition to the
+ * attributes.
+ */
+ if (iap->ia_valid & ATTR_SIZE) {
+ err = nfsd_get_write_access(rqstp, fhp, iap);
+ if (err)
+ goto out;
+ size_change = 1;
}
+
+ iap->ia_valid |= ATTR_CTIME;
+
+ if (check_guard && guardtime != inode->i_ctime.tv_sec) {
+ err = nfserr_notsync;
+ goto out_put_write_access;
+ }
+
+ host_err = nfsd_break_lease(inode);
+ if (host_err)
+ goto out_put_write_access_nfserror;
+
+ fh_lock(fhp);
+ host_err = notify_change(dentry, iap, NULL);
+ fh_unlock(fhp);
+
+out_put_write_access_nfserror:
+ err = nfserrno(host_err);
+out_put_write_access:
if (size_change)
put_write_access(inode);
if (!err)
commit_metadata(fhp);
out:
return err;
-
-out_nfserr:
- err = nfserrno(host_err);
- goto out;
}
#if defined(CONFIG_NFSD_V2_ACL) || \
goto out_free_page;
}
- kloginuid = make_kuid(file->f_cred->user_ns, loginuid);
- if (!uid_valid(kloginuid)) {
- length = -EINVAL;
- goto out_free_page;
+
+ /* is userspace tring to explicitly UNSET the loginuid? */
+ if (loginuid == AUDIT_UID_UNSET) {
+ kloginuid = INVALID_UID;
+ } else {
+ kloginuid = make_kuid(file->f_cred->user_ns, loginuid);
+ if (!uid_valid(kloginuid)) {
+ length = -EINVAL;
+ goto out_free_page;
+ }
}
length = audit_set_loginuid(kloginuid);
int committed; /* xaction was committed */
int logflags; /* logging flags */
int error; /* error return value */
+ int cancel_flags = 0;
ASSERT(XFS_IFORK_Q(ip) == 0);
if (rsvd)
tp->t_flags |= XFS_TRANS_RESERVE;
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_addafork, blks, 0);
- if (error)
- goto error0;
+ if (error) {
+ xfs_trans_cancel(tp, 0);
+ return error;
+ }
+ cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
xfs_ilock(ip, XFS_ILOCK_EXCL);
error = xfs_trans_reserve_quota_nblks(tp, ip, blks, 0, rsvd ?
XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES :
XFS_QMOPT_RES_REGBLKS);
- if (error) {
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES);
- return error;
- }
+ if (error)
+ goto trans_cancel;
+ cancel_flags |= XFS_TRANS_ABORT;
if (XFS_IFORK_Q(ip))
- goto error1;
+ goto trans_cancel;
if (ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS) {
/*
* For inodes coming from pre-6.2 filesystems.
}
ASSERT(ip->i_d.di_anextents == 0);
- xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(tp, ip, 0);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
switch (ip->i_d.di_format) {
default:
ASSERT(0);
error = XFS_ERROR(EINVAL);
- goto error1;
+ goto trans_cancel;
}
ASSERT(ip->i_afp == NULL);
if (logflags)
xfs_trans_log_inode(tp, ip, logflags);
if (error)
- goto error2;
+ goto bmap_cancel;
if (!xfs_sb_version_hasattr(&mp->m_sb) ||
(!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2)) {
__int64_t sbfields = 0;
error = xfs_bmap_finish(&tp, &flist, &committed);
if (error)
- goto error2;
- return xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
-error2:
+ goto bmap_cancel;
+ error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ return error;
+
+bmap_cancel:
xfs_bmap_cancel(&flist);
-error1:
+trans_cancel:
+ xfs_trans_cancel(tp, cancel_flags);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
-error0:
- xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
return error;
}
#include "xfs_fsops.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
+#include "xfs_dinode.h"
#ifdef HAVE_PERCPU_SB
* Set the inode cluster size.
* This may still be overridden by the file system
* block size if it is larger than the chosen cluster size.
+ *
+ * For v5 filesystems, scale the cluster size with the inode size to
+ * keep a constant ratio of inode per cluster buffer, but only if mkfs
+ * has set the inode alignment value appropriately for larger cluster
+ * sizes.
*/
mp->m_inode_cluster_size = XFS_INODE_BIG_CLUSTER_SIZE;
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ int new_size = mp->m_inode_cluster_size;
+
+ new_size *= mp->m_sb.sb_inodesize / XFS_DINODE_MIN_SIZE;
+ if (mp->m_sb.sb_inoalignmt >= XFS_B_TO_FSBT(mp, new_size))
+ mp->m_inode_cluster_size = new_size;
+ xfs_info(mp, "Using inode cluster size of %d bytes",
+ mp->m_inode_cluster_size);
+ }
/*
* Set inode alignment fields
__uint8_t m_blkbb_log; /* blocklog - BBSHIFT */
__uint8_t m_agno_log; /* log #ag's */
__uint8_t m_agino_log; /* #bits for agino in inum */
- __uint16_t m_inode_cluster_size;/* min inode buf size */
+ uint m_inode_cluster_size;/* min inode buf size */
uint m_blockmask; /* sb_blocksize-1 */
uint m_blockwsize; /* sb_blocksize in words */
uint m_blockwmask; /* blockwsize-1 */
/*
* First time we log the inode in a transaction, bump the inode change
- * counter if it is configured for this to occur.
+ * counter if it is configured for this to occur. We don't use
+ * inode_inc_version() because there is no need for extra locking around
+ * i_version as we already hold the inode locked exclusively for
+ * metadata modification.
*/
if (!(ip->i_itemp->ili_item.li_desc->lid_flags & XFS_LID_DIRTY) &&
IS_I_VERSION(VFS_I(ip))) {
- inode_inc_iversion(VFS_I(ip));
- ip->i_d.di_changecount = VFS_I(ip)->i_version;
+ ip->i_d.di_changecount = ++VFS_I(ip)->i_version;
flags |= XFS_ILOG_CORE;
}
xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(1, XFS_FSB_TO_B(mp, 1)) +
- MAX((__uint16_t)XFS_FSB_TO_B(mp, 1),
- XFS_INODE_CLUSTER_SIZE(mp)) +
+ max_t(uint, XFS_FSB_TO_B(mp, 1), XFS_INODE_CLUSTER_SIZE(mp)) +
xfs_calc_buf_res(1, 0) +
xfs_calc_buf_res(2 + XFS_IALLOC_BLOCKS(mp) +
mp->m_in_maxlevels, 0) +
--- /dev/null
+/*
+ * Hash Info: Hash algorithms information
+ *
+ * Copyright (c) 2013 Dmitry Kasatkin <d.kasatkin@samsung.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.
+ *
+ */
+
+#ifndef _CRYPTO_HASH_INFO_H
+#define _CRYPTO_HASH_INFO_H
+
+#include <crypto/sha.h>
+#include <crypto/md5.h>
+
+#include <uapi/linux/hash_info.h>
+
+/* not defined in include/crypto/ */
+#define RMD128_DIGEST_SIZE 16
+#define RMD160_DIGEST_SIZE 20
+#define RMD256_DIGEST_SIZE 32
+#define RMD320_DIGEST_SIZE 40
+
+/* not defined in include/crypto/ */
+#define WP512_DIGEST_SIZE 64
+#define WP384_DIGEST_SIZE 48
+#define WP256_DIGEST_SIZE 32
+
+/* not defined in include/crypto/ */
+#define TGR128_DIGEST_SIZE 16
+#define TGR160_DIGEST_SIZE 20
+#define TGR192_DIGEST_SIZE 24
+
+extern const char *const hash_algo_name[HASH_ALGO__LAST];
+extern const int hash_digest_size[HASH_ALGO__LAST];
+
+#endif /* _CRYPTO_HASH_INFO_H */
#define _LINUX_PUBLIC_KEY_H
#include <linux/mpi.h>
+#include <crypto/hash_info.h>
enum pkey_algo {
PKEY_ALGO_DSA,
PKEY_ALGO__LAST
};
-extern const char *const pkey_algo[PKEY_ALGO__LAST];
+extern const char *const pkey_algo_name[PKEY_ALGO__LAST];
+extern const struct public_key_algorithm *pkey_algo[PKEY_ALGO__LAST];
-enum pkey_hash_algo {
- PKEY_HASH_MD4,
- PKEY_HASH_MD5,
- PKEY_HASH_SHA1,
- PKEY_HASH_RIPE_MD_160,
- PKEY_HASH_SHA256,
- PKEY_HASH_SHA384,
- PKEY_HASH_SHA512,
- PKEY_HASH_SHA224,
- PKEY_HASH__LAST
-};
-
-extern const char *const pkey_hash_algo[PKEY_HASH__LAST];
+/* asymmetric key implementation supports only up to SHA224 */
+#define PKEY_HASH__LAST (HASH_ALGO_SHA224 + 1)
enum pkey_id_type {
PKEY_ID_PGP, /* OpenPGP generated key ID */
PKEY_ID_TYPE__LAST
};
-extern const char *const pkey_id_type[PKEY_ID_TYPE__LAST];
+extern const char *const pkey_id_type_name[PKEY_ID_TYPE__LAST];
/*
* Cryptographic data for the public-key subtype of the asymmetric key type.
#define PKEY_CAN_DECRYPT 0x02
#define PKEY_CAN_SIGN 0x04
#define PKEY_CAN_VERIFY 0x08
+ enum pkey_algo pkey_algo : 8;
enum pkey_id_type id_type : 8;
union {
MPI mpi[5];
u8 *digest;
u8 digest_size; /* Number of bytes in digest */
u8 nr_mpi; /* Occupancy of mpi[] */
- enum pkey_hash_algo pkey_hash_algo : 8;
+ enum pkey_algo pkey_algo : 8;
+ enum hash_algo pkey_hash_algo : 8;
union {
MPI mpi[2];
struct {
* @offset: The current GPU offset, which can have different meanings
* depending on the memory type. For SYSTEM type memory, it should be 0.
* @cur_placement: Hint of current placement.
+ * @wu_mutex: Wait unreserved mutex.
*
* Base class for TTM buffer object, that deals with data placement and CPU
* mappings. GPU mappings are really up to the driver, but for simpler GPUs
struct reservation_object *resv;
struct reservation_object ttm_resv;
+ struct mutex wu_mutex;
};
/**
size_t count, loff_t *f_pos, bool write);
extern void ttm_bo_swapout_all(struct ttm_bo_device *bdev);
-
+extern int ttm_bo_wait_unreserved(struct ttm_buffer_object *bo);
#endif
/**
* function ttm_eu_reserve_buffers
*
- * @ticket: [out] ww_acquire_ctx returned by call.
+ * @ticket: [out] ww_acquire_ctx filled in by call, or NULL if only
+ * non-blocking reserves should be tried.
* @list: thread private list of ttm_validate_buffer structs.
*
* Tries to reserve bos pointed to by the list entries for validation.
#include <drm/drm_hashtab.h>
#include <linux/kref.h>
#include <linux/rcupdate.h>
+#include <linux/dma-buf.h>
#include <ttm/ttm_memory.h>
/**
ttm_fence_type,
ttm_buffer_type,
ttm_lock_type,
+ ttm_prime_type,
ttm_driver_type0 = 256,
ttm_driver_type1,
ttm_driver_type2,
enum ttm_ref_type ref_type);
};
+
+/**
+ * struct ttm_prime_object - Modified base object that is prime-aware
+ *
+ * @base: struct ttm_base_object that we derive from
+ * @mutex: Mutex protecting the @dma_buf member.
+ * @size: Size of the dma_buf associated with this object
+ * @real_type: Type of the underlying object. Needed since we're setting
+ * the value of @base::object_type to ttm_prime_type
+ * @dma_buf: Non ref-coutned pointer to a struct dma_buf created from this
+ * object.
+ * @refcount_release: The underlying object's release method. Needed since
+ * we set @base::refcount_release to our own release method.
+ */
+
+struct ttm_prime_object {
+ struct ttm_base_object base;
+ struct mutex mutex;
+ size_t size;
+ enum ttm_object_type real_type;
+ struct dma_buf *dma_buf;
+ void (*refcount_release) (struct ttm_base_object **);
+};
+
/**
* ttm_base_object_init
*
/**
* ttm_object device init - initialize a struct ttm_object_device
*
+ * @mem_glob: struct ttm_mem_global for memory accounting.
* @hash_order: Order of hash table used to hash the base objects.
+ * @ops: DMA buf ops for prime objects of this device.
*
* This function is typically called on device initialization to prepare
* data structures needed for ttm base and ref objects.
*/
-extern struct ttm_object_device *ttm_object_device_init
- (struct ttm_mem_global *mem_glob, unsigned int hash_order);
+extern struct ttm_object_device *
+ttm_object_device_init(struct ttm_mem_global *mem_glob,
+ unsigned int hash_order,
+ const struct dma_buf_ops *ops);
/**
* ttm_object_device_release - release data held by a ttm_object_device
#define ttm_base_object_kfree(__object, __base)\
kfree_rcu(__object, __base.rhead)
+
+extern int ttm_prime_object_init(struct ttm_object_file *tfile,
+ size_t size,
+ struct ttm_prime_object *prime,
+ bool shareable,
+ enum ttm_object_type type,
+ void (*refcount_release)
+ (struct ttm_base_object **),
+ void (*ref_obj_release)
+ (struct ttm_base_object *,
+ enum ttm_ref_type ref_type));
+
+static inline enum ttm_object_type
+ttm_base_object_type(struct ttm_base_object *base)
+{
+ return (base->object_type == ttm_prime_type) ?
+ container_of(base, struct ttm_prime_object, base)->real_type :
+ base->object_type;
+}
+extern int ttm_prime_fd_to_handle(struct ttm_object_file *tfile,
+ int fd, u32 *handle);
+extern int ttm_prime_handle_to_fd(struct ttm_object_file *tfile,
+ uint32_t handle, uint32_t flags,
+ int *prime_fd);
+
+#define ttm_prime_object_kfree(__obj, __prime) \
+ kfree_rcu(__obj, __prime.base.rhead)
#endif
--- /dev/null
+/* Big capacity key type.
+ *
+ * Copyright (C) 2013 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.
+ */
+
+#ifndef _KEYS_BIG_KEY_TYPE_H
+#define _KEYS_BIG_KEY_TYPE_H
+
+#include <linux/key-type.h>
+
+extern struct key_type key_type_big_key;
+
+extern int big_key_instantiate(struct key *key, struct key_preparsed_payload *prep);
+extern void big_key_revoke(struct key *key);
+extern void big_key_destroy(struct key *key);
+extern void big_key_describe(const struct key *big_key, struct seq_file *m);
+extern long big_key_read(const struct key *key, char __user *buffer, size_t buflen);
+
+#endif /* _KEYS_BIG_KEY_TYPE_H */
/* Keyring key type
*
- * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2008, 2013 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
#define _KEYS_KEYRING_TYPE_H
#include <linux/key.h>
-#include <linux/rcupdate.h>
-
-/*
- * the keyring payload contains a list of the keys to which the keyring is
- * subscribed
- */
-struct keyring_list {
- struct rcu_head rcu; /* RCU deletion hook */
- unsigned short maxkeys; /* max keys this list can hold */
- unsigned short nkeys; /* number of keys currently held */
- unsigned short delkey; /* key to be unlinked by RCU */
- struct key __rcu *keys[0];
-};
-
+#include <linux/assoc_array.h>
#endif /* _KEYS_KEYRING_TYPE_H */
--- /dev/null
+/* System keyring containing trusted public keys.
+ *
+ * Copyright (C) 2013 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _KEYS_SYSTEM_KEYRING_H
+#define _KEYS_SYSTEM_KEYRING_H
+
+#ifdef CONFIG_SYSTEM_TRUSTED_KEYRING
+
+#include <linux/key.h>
+
+extern struct key *system_trusted_keyring;
+
+#endif
+
+#endif /* _KEYS_SYSTEM_KEYRING_H */
--- /dev/null
+/* Generic associative array implementation.
+ *
+ * See Documentation/assoc_array.txt for information.
+ *
+ * Copyright (C) 2013 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_ASSOC_ARRAY_H
+#define _LINUX_ASSOC_ARRAY_H
+
+#ifdef CONFIG_ASSOCIATIVE_ARRAY
+
+#include <linux/types.h>
+
+#define ASSOC_ARRAY_KEY_CHUNK_SIZE BITS_PER_LONG /* Key data retrieved in chunks of this size */
+
+/*
+ * Generic associative array.
+ */
+struct assoc_array {
+ struct assoc_array_ptr *root; /* The node at the root of the tree */
+ unsigned long nr_leaves_on_tree;
+};
+
+/*
+ * Operations on objects and index keys for use by array manipulation routines.
+ */
+struct assoc_array_ops {
+ /* Method to get a chunk of an index key from caller-supplied data */
+ unsigned long (*get_key_chunk)(const void *index_key, int level);
+
+ /* Method to get a piece of an object's index key */
+ unsigned long (*get_object_key_chunk)(const void *object, int level);
+
+ /* Is this the object we're looking for? */
+ bool (*compare_object)(const void *object, const void *index_key);
+
+ /* How different are two objects, to a bit position in their keys? (or
+ * -1 if they're the same)
+ */
+ int (*diff_objects)(const void *a, const void *b);
+
+ /* Method to free an object. */
+ void (*free_object)(void *object);
+};
+
+/*
+ * Access and manipulation functions.
+ */
+struct assoc_array_edit;
+
+static inline void assoc_array_init(struct assoc_array *array)
+{
+ array->root = NULL;
+ array->nr_leaves_on_tree = 0;
+}
+
+extern int assoc_array_iterate(const struct assoc_array *array,
+ int (*iterator)(const void *object,
+ void *iterator_data),
+ void *iterator_data);
+extern void *assoc_array_find(const struct assoc_array *array,
+ const struct assoc_array_ops *ops,
+ const void *index_key);
+extern void assoc_array_destroy(struct assoc_array *array,
+ const struct assoc_array_ops *ops);
+extern struct assoc_array_edit *assoc_array_insert(struct assoc_array *array,
+ const struct assoc_array_ops *ops,
+ const void *index_key,
+ void *object);
+extern void assoc_array_insert_set_object(struct assoc_array_edit *edit,
+ void *object);
+extern struct assoc_array_edit *assoc_array_delete(struct assoc_array *array,
+ const struct assoc_array_ops *ops,
+ const void *index_key);
+extern struct assoc_array_edit *assoc_array_clear(struct assoc_array *array,
+ const struct assoc_array_ops *ops);
+extern void assoc_array_apply_edit(struct assoc_array_edit *edit);
+extern void assoc_array_cancel_edit(struct assoc_array_edit *edit);
+extern int assoc_array_gc(struct assoc_array *array,
+ const struct assoc_array_ops *ops,
+ bool (*iterator)(void *object, void *iterator_data),
+ void *iterator_data);
+
+#endif /* CONFIG_ASSOCIATIVE_ARRAY */
+#endif /* _LINUX_ASSOC_ARRAY_H */
--- /dev/null
+/* Private definitions for the generic associative array implementation.
+ *
+ * See Documentation/assoc_array.txt for information.
+ *
+ * Copyright (C) 2013 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_ASSOC_ARRAY_PRIV_H
+#define _LINUX_ASSOC_ARRAY_PRIV_H
+
+#ifdef CONFIG_ASSOCIATIVE_ARRAY
+
+#include <linux/assoc_array.h>
+
+#define ASSOC_ARRAY_FAN_OUT 16 /* Number of slots per node */
+#define ASSOC_ARRAY_FAN_MASK (ASSOC_ARRAY_FAN_OUT - 1)
+#define ASSOC_ARRAY_LEVEL_STEP (ilog2(ASSOC_ARRAY_FAN_OUT))
+#define ASSOC_ARRAY_LEVEL_STEP_MASK (ASSOC_ARRAY_LEVEL_STEP - 1)
+#define ASSOC_ARRAY_KEY_CHUNK_MASK (ASSOC_ARRAY_KEY_CHUNK_SIZE - 1)
+#define ASSOC_ARRAY_KEY_CHUNK_SHIFT (ilog2(BITS_PER_LONG))
+
+/*
+ * Undefined type representing a pointer with type information in the bottom
+ * two bits.
+ */
+struct assoc_array_ptr;
+
+/*
+ * An N-way node in the tree.
+ *
+ * Each slot contains one of four things:
+ *
+ * (1) Nothing (NULL).
+ *
+ * (2) A leaf object (pointer types 0).
+ *
+ * (3) A next-level node (pointer type 1, subtype 0).
+ *
+ * (4) A shortcut (pointer type 1, subtype 1).
+ *
+ * The tree is optimised for search-by-ID, but permits reasonable iteration
+ * also.
+ *
+ * The tree is navigated by constructing an index key consisting of an array of
+ * segments, where each segment is ilog2(ASSOC_ARRAY_FAN_OUT) bits in size.
+ *
+ * The segments correspond to levels of the tree (the first segment is used at
+ * level 0, the second at level 1, etc.).
+ */
+struct assoc_array_node {
+ struct assoc_array_ptr *back_pointer;
+ u8 parent_slot;
+ struct assoc_array_ptr *slots[ASSOC_ARRAY_FAN_OUT];
+ unsigned long nr_leaves_on_branch;
+};
+
+/*
+ * A shortcut through the index space out to where a collection of nodes/leaves
+ * with the same IDs live.
+ */
+struct assoc_array_shortcut {
+ struct assoc_array_ptr *back_pointer;
+ int parent_slot;
+ int skip_to_level;
+ struct assoc_array_ptr *next_node;
+ unsigned long index_key[];
+};
+
+/*
+ * Preallocation cache.
+ */
+struct assoc_array_edit {
+ struct rcu_head rcu;
+ struct assoc_array *array;
+ const struct assoc_array_ops *ops;
+ const struct assoc_array_ops *ops_for_excised_subtree;
+ struct assoc_array_ptr *leaf;
+ struct assoc_array_ptr **leaf_p;
+ struct assoc_array_ptr *dead_leaf;
+ struct assoc_array_ptr *new_meta[3];
+ struct assoc_array_ptr *excised_meta[1];
+ struct assoc_array_ptr *excised_subtree;
+ struct assoc_array_ptr **set_backpointers[ASSOC_ARRAY_FAN_OUT];
+ struct assoc_array_ptr *set_backpointers_to;
+ struct assoc_array_node *adjust_count_on;
+ long adjust_count_by;
+ struct {
+ struct assoc_array_ptr **ptr;
+ struct assoc_array_ptr *to;
+ } set[2];
+ struct {
+ u8 *p;
+ u8 to;
+ } set_parent_slot[1];
+ u8 segment_cache[ASSOC_ARRAY_FAN_OUT + 1];
+};
+
+/*
+ * Internal tree member pointers are marked in the bottom one or two bits to
+ * indicate what type they are so that we don't have to look behind every
+ * pointer to see what it points to.
+ *
+ * We provide functions to test type annotations and to create and translate
+ * the annotated pointers.
+ */
+#define ASSOC_ARRAY_PTR_TYPE_MASK 0x1UL
+#define ASSOC_ARRAY_PTR_LEAF_TYPE 0x0UL /* Points to leaf (or nowhere) */
+#define ASSOC_ARRAY_PTR_META_TYPE 0x1UL /* Points to node or shortcut */
+#define ASSOC_ARRAY_PTR_SUBTYPE_MASK 0x2UL
+#define ASSOC_ARRAY_PTR_NODE_SUBTYPE 0x0UL
+#define ASSOC_ARRAY_PTR_SHORTCUT_SUBTYPE 0x2UL
+
+static inline bool assoc_array_ptr_is_meta(const struct assoc_array_ptr *x)
+{
+ return (unsigned long)x & ASSOC_ARRAY_PTR_TYPE_MASK;
+}
+static inline bool assoc_array_ptr_is_leaf(const struct assoc_array_ptr *x)
+{
+ return !assoc_array_ptr_is_meta(x);
+}
+static inline bool assoc_array_ptr_is_shortcut(const struct assoc_array_ptr *x)
+{
+ return (unsigned long)x & ASSOC_ARRAY_PTR_SUBTYPE_MASK;
+}
+static inline bool assoc_array_ptr_is_node(const struct assoc_array_ptr *x)
+{
+ return !assoc_array_ptr_is_shortcut(x);
+}
+
+static inline void *assoc_array_ptr_to_leaf(const struct assoc_array_ptr *x)
+{
+ return (void *)((unsigned long)x & ~ASSOC_ARRAY_PTR_TYPE_MASK);
+}
+
+static inline
+unsigned long __assoc_array_ptr_to_meta(const struct assoc_array_ptr *x)
+{
+ return (unsigned long)x &
+ ~(ASSOC_ARRAY_PTR_SUBTYPE_MASK | ASSOC_ARRAY_PTR_TYPE_MASK);
+}
+static inline
+struct assoc_array_node *assoc_array_ptr_to_node(const struct assoc_array_ptr *x)
+{
+ return (struct assoc_array_node *)__assoc_array_ptr_to_meta(x);
+}
+static inline
+struct assoc_array_shortcut *assoc_array_ptr_to_shortcut(const struct assoc_array_ptr *x)
+{
+ return (struct assoc_array_shortcut *)__assoc_array_ptr_to_meta(x);
+}
+
+static inline
+struct assoc_array_ptr *__assoc_array_x_to_ptr(const void *p, unsigned long t)
+{
+ return (struct assoc_array_ptr *)((unsigned long)p | t);
+}
+static inline
+struct assoc_array_ptr *assoc_array_leaf_to_ptr(const void *p)
+{
+ return __assoc_array_x_to_ptr(p, ASSOC_ARRAY_PTR_LEAF_TYPE);
+}
+static inline
+struct assoc_array_ptr *assoc_array_node_to_ptr(const struct assoc_array_node *p)
+{
+ return __assoc_array_x_to_ptr(
+ p, ASSOC_ARRAY_PTR_META_TYPE | ASSOC_ARRAY_PTR_NODE_SUBTYPE);
+}
+static inline
+struct assoc_array_ptr *assoc_array_shortcut_to_ptr(const struct assoc_array_shortcut *p)
+{
+ return __assoc_array_x_to_ptr(
+ p, ASSOC_ARRAY_PTR_META_TYPE | ASSOC_ARRAY_PTR_SHORTCUT_SUBTYPE);
+}
+
+#endif /* CONFIG_ASSOCIATIVE_ARRAY */
+#endif /* _LINUX_ASSOC_ARRAY_PRIV_H */
void *lsm_rule;
};
+extern int is_audit_feature_set(int which);
+
extern int __init audit_register_class(int class, unsigned *list);
extern int audit_classify_syscall(int abi, unsigned syscall);
extern int audit_classify_arch(int arch);
extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp);
extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode);
-extern int __audit_bprm(struct linux_binprm *bprm);
+extern void __audit_bprm(struct linux_binprm *bprm);
extern int __audit_socketcall(int nargs, unsigned long *args);
extern int __audit_sockaddr(int len, void *addr);
extern void __audit_fd_pair(int fd1, int fd2);
if (unlikely(!audit_dummy_context()))
__audit_ipc_set_perm(qbytes, uid, gid, mode);
}
-static inline int audit_bprm(struct linux_binprm *bprm)
+static inline void audit_bprm(struct linux_binprm *bprm)
{
if (unlikely(!audit_dummy_context()))
- return __audit_bprm(bprm);
- return 0;
+ __audit_bprm(bprm);
}
static inline int audit_socketcall(int nargs, unsigned long *args)
{
static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid,
gid_t gid, umode_t mode)
{ }
-static inline int audit_bprm(struct linux_binprm *bprm)
-{
- return 0;
-}
+static inline void audit_bprm(struct linux_binprm *bprm)
+{ }
static inline int audit_socketcall(int nargs, unsigned long *args)
{
return 0;
void hugepage_put_subpool(struct hugepage_subpool *spool);
int PageHuge(struct page *page);
+int PageHeadHuge(struct page *page_head);
void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
bool isolate_huge_page(struct page *page, struct list_head *list);
void putback_active_hugepage(struct page *page);
bool is_hugepage_active(struct page *page);
-void copy_huge_page(struct page *dst, struct page *src);
#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
return 0;
}
+static inline int PageHeadHuge(struct page *page_head)
+{
+ return 0;
+}
+
static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
{
}
#define isolate_huge_page(p, l) false
#define putback_active_hugepage(p) do {} while (0)
#define is_hugepage_active(x) false
-static inline void copy_huge_page(struct page *dst, struct page *src)
-{
-}
static inline unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
unsigned long address, unsigned long end, pgprot_t newprot)
const void *data; /* Raw data */
size_t datalen; /* Raw datalen */
size_t quotalen; /* Quota length for proposed payload */
+ bool trusted; /* True if key is trusted */
};
typedef int (*request_key_actor_t)(struct key_construction *key,
*/
size_t def_datalen;
+ /* Default key search algorithm. */
+ unsigned def_lookup_type;
+#define KEYRING_SEARCH_LOOKUP_DIRECT 0x0000 /* Direct lookup by description. */
+#define KEYRING_SEARCH_LOOKUP_ITERATE 0x0001 /* Iterative search. */
+
/* vet a description */
int (*vet_description)(const char *description);
#include <linux/sysctl.h>
#include <linux/rwsem.h>
#include <linux/atomic.h>
+#include <linux/assoc_array.h>
#ifdef __KERNEL__
#include <linux/uidgid.h>
struct keyring_list;
struct keyring_name;
+struct keyring_index_key {
+ struct key_type *type;
+ const char *description;
+ size_t desc_len;
+};
+
/*****************************************************************************/
/*
* key reference with possession attribute handling
typedef struct __key_reference_with_attributes *key_ref_t;
static inline key_ref_t make_key_ref(const struct key *key,
- unsigned long possession)
+ bool possession)
{
return (key_ref_t) ((unsigned long) key | possession);
}
return (struct key *) ((unsigned long) key_ref & ~1UL);
}
-static inline unsigned long is_key_possessed(const key_ref_t key_ref)
+static inline bool is_key_possessed(const key_ref_t key_ref)
{
return (unsigned long) key_ref & 1UL;
}
struct list_head graveyard_link;
struct rb_node serial_node;
};
- struct key_type *type; /* type of key */
struct rw_semaphore sem; /* change vs change sem */
struct key_user *user; /* owner of this key */
void *security; /* security data for this key */
#define KEY_FLAG_NEGATIVE 5 /* set if key is negative */
#define KEY_FLAG_ROOT_CAN_CLEAR 6 /* set if key can be cleared by root without permission */
#define KEY_FLAG_INVALIDATED 7 /* set if key has been invalidated */
+#define KEY_FLAG_TRUSTED 8 /* set if key is trusted */
+#define KEY_FLAG_TRUSTED_ONLY 9 /* set if keyring only accepts links to trusted keys */
- /* the description string
- * - this is used to match a key against search criteria
- * - this should be a printable string
+ /* the key type and key description string
+ * - the desc is used to match a key against search criteria
+ * - it should be a printable string
* - eg: for krb5 AFS, this might be "afs@REDHAT.COM"
*/
- char *description;
+ union {
+ struct keyring_index_key index_key;
+ struct {
+ struct key_type *type; /* type of key */
+ char *description;
+ };
+ };
/* type specific data
* - this is used by the keyring type to index the name
* whatever
*/
union {
- unsigned long value;
- void __rcu *rcudata;
- void *data;
- struct keyring_list __rcu *subscriptions;
- } payload;
+ union {
+ unsigned long value;
+ void __rcu *rcudata;
+ void *data;
+ void *data2[2];
+ } payload;
+ struct assoc_array keys;
+ };
};
extern struct key *key_alloc(struct key_type *type,
#define KEY_ALLOC_IN_QUOTA 0x0000 /* add to quota, reject if would overrun */
#define KEY_ALLOC_QUOTA_OVERRUN 0x0001 /* add to quota, permit even if overrun */
#define KEY_ALLOC_NOT_IN_QUOTA 0x0002 /* not in quota */
+#define KEY_ALLOC_TRUSTED 0x0004 /* Key should be flagged as trusted */
extern void key_revoke(struct key *key);
extern void key_invalidate(struct key *key);
extern void key_put(struct key *key);
-static inline struct key *key_get(struct key *key)
+static inline struct key *__key_get(struct key *key)
{
- if (key)
- atomic_inc(&key->usage);
+ atomic_inc(&key->usage);
return key;
}
+static inline struct key *key_get(struct key *key)
+{
+ return key ? __key_get(key) : key;
+}
+
static inline void key_ref_put(key_ref_t key_ref)
{
key_put(key_ref_to_ptr(key_ref));
/* First double word block */
unsigned long flags; /* Atomic flags, some possibly
* updated asynchronously */
- struct address_space *mapping; /* If low bit clear, points to
- * inode address_space, or NULL.
- * If page mapped as anonymous
- * memory, low bit is set, and
- * it points to anon_vma object:
- * see PAGE_MAPPING_ANON below.
- */
+ union {
+ struct address_space *mapping; /* If low bit clear, points to
+ * inode address_space, or NULL.
+ * If page mapped as anonymous
+ * memory, low bit is set, and
+ * it points to anon_vma object:
+ * see PAGE_MAPPING_ANON below.
+ */
+ void *s_mem; /* slab first object */
+ };
+
/* Second double word */
struct {
union {
pgoff_t index; /* Our offset within mapping. */
- void *freelist; /* slub/slob first free object */
+ void *freelist; /* sl[aou]b first free object */
bool pfmemalloc; /* If set by the page allocator,
* ALLOC_NO_WATERMARKS was set
* and the low watermark was not
* this page is only used to
* free other pages.
*/
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
- pgtable_t pmd_huge_pte; /* protected by page->ptl */
-#endif
};
union {
};
atomic_t _count; /* Usage count, see below. */
};
+ unsigned int active; /* SLAB */
};
};
struct list_head list; /* slobs list of pages */
struct slab *slab_page; /* slab fields */
+ struct rcu_head rcu_head; /* Used by SLAB
+ * when destroying via RCU
+ */
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
+ pgtable_t pmd_huge_pte; /* protected by page->ptl */
+#endif
};
/* Remainder is not double word aligned */
struct {
__u8 is_msix : 1;
__u8 multiple: 3; /* log2 number of messages */
- __u8 maskbit : 1; /* mask-pending bit supported ? */
- __u8 is_64 : 1; /* Address size: 0=32bit 1=64bit */
- __u8 pos; /* Location of the msi capability */
- __u16 entry_nr; /* specific enabled entry */
- unsigned default_irq; /* default pre-assigned irq */
+ __u8 maskbit : 1; /* mask-pending bit supported ? */
+ __u8 is_64 : 1; /* Address size: 0=32bit 1=64bit */
+ __u8 pos; /* Location of the msi capability */
+ __u16 entry_nr; /* specific enabled entry */
+ unsigned default_irq; /* default pre-assigned irq */
} msi_attrib;
u32 masked; /* mask bits */
#endif
int (*sendmsg) (struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t total_len);
+ /* Notes for implementing recvmsg:
+ * ===============================
+ * msg->msg_namelen should get updated by the recvmsg handlers
+ * iff msg_name != NULL. It is by default 0 to prevent
+ * returning uninitialized memory to user space. The recvfrom
+ * handlers can assume that msg.msg_name is either NULL or has
+ * a minimum size of sizeof(struct sockaddr_storage).
+ */
int (*recvmsg) (struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t total_len,
int flags);
#include <linux/irqreturn.h>
#include <uapi/linux/pci.h>
-/* Include the ID list */
#include <linux/pci_ids.h>
/*
*
* 7:3 = slot
* 2:0 = function
- * PCI_DEVFN(), PCI_SLOT(), and PCI_FUNC() are defined uapi/linux/pci.h
+ *
+ * PCI_DEVFN(), PCI_SLOT(), and PCI_FUNC() are defined in uapi/linux/pci.h.
* In the interest of not exposing interfaces to user-space unnecessarily,
- * the following kernel only defines are being added here.
+ * the following kernel-only defines are being added here.
*/
#define PCI_DEVID(bus, devfn) ((((u16)bus) << 8) | devfn)
/* return bus from PCI devid = ((u16)bus_number) << 8) | devfn */
/* Reset is NOT asserted (Use to deassert reset) */
pcie_deassert_reset = (__force pcie_reset_state_t) 1,
- /* Use #PERST to reset PCI-E device */
+ /* Use #PERST to reset PCIe device */
pcie_warm_reset = (__force pcie_reset_state_t) 2,
- /* Use PCI-E Hot Reset to reset device */
+ /* Use PCIe Hot Reset to reset device */
pcie_hot_reset = (__force pcie_reset_state_t) 3
};
unsigned int class; /* 3 bytes: (base,sub,prog-if) */
u8 revision; /* PCI revision, low byte of class word */
u8 hdr_type; /* PCI header type (`multi' flag masked out) */
- u8 pcie_cap; /* PCI-E capability offset */
+ u8 pcie_cap; /* PCIe capability offset */
u8 msi_cap; /* MSI capability offset */
u8 msix_cap; /* MSI-X capability offset */
- u8 pcie_mpss:3; /* PCI-E Max Payload Size Supported */
+ u8 pcie_mpss:3; /* PCIe Max Payload Size Supported */
u8 rom_base_reg; /* which config register controls the ROM */
- u8 pin; /* which interrupt pin this device uses */
- u16 pcie_flags_reg; /* cached PCI-E Capabilities Register */
+ u8 pin; /* which interrupt pin this device uses */
+ u16 pcie_flags_reg; /* cached PCIe Capabilities Register */
struct pci_driver *driver; /* which driver has allocated this device */
u64 dma_mask; /* Mask of the bits of bus address this
unsigned int d3cold_delay; /* D3cold->D0 transition time in ms */
#ifdef CONFIG_PCIEASPM
- struct pcie_link_state *link_state; /* ASPM link state. */
+ struct pcie_link_state *link_state; /* ASPM link state */
#endif
pci_channel_state_t error_state; /* current connectivity state */
bool match_driver; /* Skip attaching driver */
/* These fields are used by common fixups */
- unsigned int transparent:1; /* Transparent PCI bridge */
+ unsigned int transparent:1; /* Subtractive decode PCI bridge */
unsigned int multifunction:1;/* Part of multi-function device */
/* keep track of device state */
unsigned int is_added:1;
unsigned int block_cfg_access:1; /* config space access is blocked */
unsigned int broken_parity_status:1; /* Device generates false positive parity */
unsigned int irq_reroute_variant:2; /* device needs IRQ rerouting variant */
- unsigned int msi_enabled:1;
+ unsigned int msi_enabled:1;
unsigned int msix_enabled:1;
unsigned int ari_enabled:1; /* ARI forwarding */
unsigned int is_managed:1;
if (dev->is_virtfn)
dev = dev->physfn;
#endif
-
return dev;
}
char name[48];
unsigned short bridge_ctl; /* manage NO_ISA/FBB/et al behaviors */
- pci_bus_flags_t bus_flags; /* Inherited by child busses */
+ pci_bus_flags_t bus_flags; /* inherited by child buses */
struct device *bridge;
struct device dev;
struct bin_attribute *legacy_io; /* legacy I/O for this bus */
#define to_pci_bus(n) container_of(n, struct pci_bus, dev)
/*
- * Returns true if the pci bus is root (behind host-pci bridge),
+ * Returns true if the PCI bus is root (behind host-PCI bridge),
* false otherwise
*
* Some code assumes that "bus->self == NULL" means that bus is a root bus.
#define PCIBIOS_BUFFER_TOO_SMALL 0x89
/*
- * Translate above to generic errno for passing back through non-pci.
+ * Translate above to generic errno for passing back through non-PCI code.
*/
static inline int pcibios_err_to_errno(int err)
{
struct list_head list; /* for IDs added at runtime */
};
-/* ---------------------------------------------------------------- */
-/** PCI Error Recovery System (PCI-ERS). If a PCI device driver provides
- * a set of callbacks in struct pci_error_handlers, then that device driver
- * will be notified of PCI bus errors, and will be driven to recovery
- * when an error occurs.
+
+/*
+ * PCI Error Recovery System (PCI-ERS). If a PCI device driver provides
+ * a set of callbacks in struct pci_error_handlers, that device driver
+ * will be notified of PCI bus errors, and will be driven to recovery
+ * when an error occurs.
*/
typedef unsigned int __bitwise pci_ers_result_t;
void (*resume)(struct pci_dev *dev);
};
-/* ---------------------------------------------------------------- */
struct module;
struct pci_driver {
extern struct bus_type pci_bus_type;
-/* Do NOT directly access these two variables, unless you are arch specific pci
- * code, or pci core code. */
+/* Do NOT directly access these two variables, unless you are arch-specific PCI
+ * code, or PCI core code. */
extern struct list_head pci_root_buses; /* list of all known PCI buses */
-/* Some device drivers need know if pci is initiated */
+/* Some device drivers need know if PCI is initiated */
int no_pci_devices(void);
void pcibios_resource_survey_bus(struct pci_bus *bus);
void pcibios_remove_bus(struct pci_bus *bus);
void pcibios_fixup_bus(struct pci_bus *);
int __must_check pcibios_enable_device(struct pci_dev *, int mask);
-/* Architecture specific versions may override this (weak) */
+/* Architecture-specific versions may override this (weak) */
char *pcibios_setup(char *str);
/* Used only when drivers/pci/setup.c is used */
/*
* PCI domain support. Sometimes called PCI segment (eg by ACPI),
- * a PCI domain is defined to be a set of PCI busses which share
+ * a PCI domain is defined to be a set of PCI buses which share
* configuration space.
*/
#ifdef CONFIG_PCI_DOMAINS
extern unsigned long pci_hotplug_io_size;
extern unsigned long pci_hotplug_mem_size;
-/* Architecture specific versions may override these (weak) */
+/* Architecture-specific versions may override these (weak) */
int pcibios_add_platform_entries(struct pci_dev *dev);
void pcibios_disable_device(struct pci_dev *dev);
void pcibios_set_master(struct pci_dev *dev);
* @hardware_test: Called to run a specified hardware test on the specified
* slot.
* @get_power_status: Called to get the current power status of a slot.
- * If this field is NULL, the value passed in the struct hotplug_slot_info
- * will be used when this value is requested by a user.
+ * If this field is NULL, the value passed in the struct hotplug_slot_info
+ * will be used when this value is requested by a user.
* @get_attention_status: Called to get the current attention status of a slot.
* If this field is NULL, the value passed in the struct hotplug_slot_info
* will be used when this value is requested by a user.
void pci_configure_slot(struct pci_dev *dev);
#endif
-
#define PCIE_PORT_SERVICE_VC (1 << PCIE_PORT_SERVICE_VC_SHIFT)
struct pcie_device {
- int irq; /* Service IRQ/MSI/MSI-X Vector */
+ int irq; /* Service IRQ/MSI/MSI-X Vector */
struct pci_dev *port; /* Root/Upstream/Downstream Port */
u32 service; /* Port service this device represents */
void *priv_data; /* Service Private Data */
return phydev->drv->read_status(phydev);
}
+int genphy_setup_forced(struct phy_device *phydev);
int genphy_restart_aneg(struct phy_device *phydev);
int genphy_config_aneg(struct phy_device *phydev);
int genphy_update_link(struct phy_device *phydev);
* @xfrm_policy_delete_security:
* @ctx contains the xfrm_sec_ctx.
* Authorize deletion of xp->security.
- * @xfrm_state_alloc_security:
+ * @xfrm_state_alloc:
* @x contains the xfrm_state being added to the Security Association
* Database by the XFRM system.
* @sec_ctx contains the security context information being provided by
* the user-level SA generation program (e.g., setkey or racoon).
- * @secid contains the secid from which to take the mls portion of the context.
* Allocate a security structure to the x->security field; the security
* field is initialized to NULL when the xfrm_state is allocated. Set the
- * context to correspond to either sec_ctx or polsec, with the mls portion
- * taken from secid in the latter case.
- * Return 0 if operation was successful (memory to allocate, legal context).
+ * context to correspond to sec_ctx. Return 0 if operation was successful
+ * (memory to allocate, legal context).
+ * @xfrm_state_alloc_acquire:
+ * @x contains the xfrm_state being added to the Security Association
+ * Database by the XFRM system.
+ * @polsec contains the policy's security context.
+ * @secid contains the secid from which to take the mls portion of the
+ * context.
+ * Allocate a security structure to the x->security field; the security
+ * field is initialized to NULL when the xfrm_state is allocated. Set the
+ * context to correspond to secid. Return 0 if operation was successful
+ * (memory to allocate, legal context).
* @xfrm_state_free_security:
* @x contains the xfrm_state.
* Deallocate x->security.
int (*xfrm_policy_clone_security) (struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctx);
void (*xfrm_policy_free_security) (struct xfrm_sec_ctx *ctx);
int (*xfrm_policy_delete_security) (struct xfrm_sec_ctx *ctx);
- int (*xfrm_state_alloc_security) (struct xfrm_state *x,
- struct xfrm_user_sec_ctx *sec_ctx,
- u32 secid);
+ int (*xfrm_state_alloc) (struct xfrm_state *x,
+ struct xfrm_user_sec_ctx *sec_ctx);
+ int (*xfrm_state_alloc_acquire) (struct xfrm_state *x,
+ struct xfrm_sec_ctx *polsec,
+ u32 secid);
void (*xfrm_state_free_security) (struct xfrm_state *x);
int (*xfrm_state_delete_security) (struct xfrm_state *x);
int (*xfrm_policy_lookup) (struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir);
* }
* rcu_read_unlock();
*
- * See also the comment on struct slab_rcu in mm/slab.c.
+ * This is useful if we need to approach a kernel structure obliquely,
+ * from its address obtained without the usual locking. We can lock
+ * the structure to stabilize it and check it's still at the given address,
+ * only if we can be sure that the memory has not been meanwhile reused
+ * for some other kind of object (which our subsystem's lock might corrupt).
+ *
+ * rcu_read_lock before reading the address, then rcu_read_unlock after
+ * taking the spinlock within the structure expected at that address.
*/
#define SLAB_DESTROY_BY_RCU 0x00080000UL /* Defer freeing slabs to RCU */
#define SLAB_MEM_SPREAD 0x00100000UL /* Spread some memory over cpuset */
size_t colour; /* cache colouring range */
unsigned int colour_off; /* colour offset */
- struct kmem_cache *slabp_cache;
- unsigned int slab_size;
+ struct kmem_cache *freelist_cache;
+ unsigned int freelist_size;
/* constructor func */
void (*ctor)(void *obj);
enum stat_item {
ALLOC_FASTPATH, /* Allocation from cpu slab */
ALLOC_SLOWPATH, /* Allocation by getting a new cpu slab */
- FREE_FASTPATH, /* Free to cpu slub */
+ FREE_FASTPATH, /* Free to cpu slab */
FREE_SLOWPATH, /* Freeing not to cpu slab */
FREE_FROZEN, /* Freeing to frozen slab */
FREE_ADD_PARTIAL, /* Freeing moves slab to partial list */
kuid_t owner;
kgid_t group;
unsigned int proc_inum;
+
+ /* Register of per-UID persistent keyrings for this namespace */
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+ struct key *persistent_keyring_register;
+ struct rw_semaphore persistent_keyring_register_sem;
+#endif
};
extern struct user_namespace init_user_ns;
struct net *net, struct sk_buff *skb,
u32 portid, unsigned int group, gfp_t flags)
{
- if (group >= family->n_mcgrps)
+ if (WARN_ON_ONCE(group >= family->n_mcgrps))
return -EINVAL;
group = family->mcgrp_offset + group;
return nlmsg_multicast(net->genl_sock, skb, portid, group, flags);
struct sk_buff *skb, u32 portid,
unsigned int group, gfp_t flags)
{
- if (group >= family->n_mcgrps)
- return -EINVAL;
- group = family->mcgrp_offset + group;
return genlmsg_multicast_netns(family, &init_net, skb,
portid, group, flags);
}
static inline int genl_set_err(struct genl_family *family, struct net *net,
u32 portid, u32 group, int code)
{
+ if (WARN_ON_ONCE(group >= family->n_mcgrps))
+ return -EINVAL;
+ group = family->mcgrp_offset + group;
return netlink_set_err(net->genl_sock, portid, group, code);
}
sense_reason_t (*parse_cdb)(struct se_cmd *cmd);
u32 (*get_device_type)(struct se_device *);
sector_t (*get_blocks)(struct se_device *);
+ sector_t (*get_alignment_offset_lbas)(struct se_device *);
+ /* lbppbe = logical blocks per physical block exponent. see SBC-3 */
+ unsigned int (*get_lbppbe)(struct se_device *);
+ unsigned int (*get_io_min)(struct se_device *);
+ unsigned int (*get_io_opt)(struct se_device *);
unsigned char *(*get_sense_buffer)(struct se_cmd *);
bool (*get_write_cache)(struct se_device *);
};
/* fabric independent task management response values */
enum tcm_tmrsp_table {
+ TMR_FUNCTION_FAILED = 0,
TMR_FUNCTION_COMPLETE = 1,
TMR_TASK_DOES_NOT_EXIST = 2,
TMR_LUN_DOES_NOT_EXIST = 3,
struct t10_alua_tg_pt_gp {
u16 tg_pt_gp_id;
int tg_pt_gp_valid_id;
+ int tg_pt_gp_alua_supported_states;
int tg_pt_gp_alua_access_status;
int tg_pt_gp_alua_access_type;
int tg_pt_gp_nonop_delay_msecs;
int tg_pt_gp_trans_delay_msecs;
- int tg_pt_gp_implict_trans_secs;
+ int tg_pt_gp_implicit_trans_secs;
int tg_pt_gp_pref;
int tg_pt_gp_write_metadata;
/* Used by struct t10_alua_tg_pt_gp->tg_pt_gp_md_buf_len */
/* Used for sense data */
void *sense_buffer;
struct list_head se_delayed_node;
- struct list_head se_lun_node;
struct list_head se_qf_node;
struct se_device *se_dev;
struct se_dev_entry *se_deve;
#define CMD_T_SENT (1 << 4)
#define CMD_T_STOP (1 << 5)
#define CMD_T_FAILED (1 << 6)
-#define CMD_T_LUN_STOP (1 << 7)
-#define CMD_T_LUN_FE_STOP (1 << 8)
-#define CMD_T_DEV_ACTIVE (1 << 9)
-#define CMD_T_REQUEST_STOP (1 << 10)
-#define CMD_T_BUSY (1 << 11)
+#define CMD_T_DEV_ACTIVE (1 << 7)
+#define CMD_T_REQUEST_STOP (1 << 8)
+#define CMD_T_BUSY (1 << 9)
spinlock_t t_state_lock;
struct completion t_transport_stop_comp;
- struct completion transport_lun_fe_stop_comp;
- struct completion transport_lun_stop_comp;
struct work_struct work;
/* backend private data */
void *priv;
+
+ /* Used for lun->lun_ref counting */
+ bool lun_ref_active;
};
struct se_ua {
struct config_group da_group;
};
+struct se_port_stat_grps {
+ struct config_group stat_group;
+ struct config_group scsi_port_group;
+ struct config_group scsi_tgt_port_group;
+ struct config_group scsi_transport_group;
+};
+
+struct se_lun {
+#define SE_LUN_LINK_MAGIC 0xffff7771
+ u32 lun_link_magic;
+ /* See transport_lun_status_table */
+ enum transport_lun_status_table lun_status;
+ u32 lun_access;
+ u32 lun_flags;
+ u32 unpacked_lun;
+ atomic_t lun_acl_count;
+ spinlock_t lun_acl_lock;
+ spinlock_t lun_sep_lock;
+ struct completion lun_shutdown_comp;
+ struct list_head lun_acl_list;
+ struct se_device *lun_se_dev;
+ struct se_port *lun_sep;
+ struct config_group lun_group;
+ struct se_port_stat_grps port_stat_grps;
+ struct completion lun_ref_comp;
+ struct percpu_ref lun_ref;
+};
+
struct se_dev_stat_grps {
struct config_group stat_group;
struct config_group scsi_dev_group;
/* Pointer to transport specific device structure */
u32 dev_index;
u64 creation_time;
- u32 num_resets;
- u64 num_cmds;
- u64 read_bytes;
- u64 write_bytes;
- spinlock_t stats_lock;
+ atomic_long_t num_resets;
+ atomic_long_t num_cmds;
+ atomic_long_t read_bytes;
+ atomic_long_t write_bytes;
/* Active commands on this virtual SE device */
atomic_t simple_cmds;
atomic_t dev_ordered_id;
struct se_subsystem_api *transport;
/* Linked list for struct se_hba struct se_device list */
struct list_head dev_list;
+ struct se_lun xcopy_lun;
};
struct se_hba {
struct se_subsystem_api *transport;
};
-struct se_port_stat_grps {
- struct config_group stat_group;
- struct config_group scsi_port_group;
- struct config_group scsi_tgt_port_group;
- struct config_group scsi_transport_group;
-};
-
-struct se_lun {
-#define SE_LUN_LINK_MAGIC 0xffff7771
- u32 lun_link_magic;
- /* See transport_lun_status_table */
- enum transport_lun_status_table lun_status;
- u32 lun_access;
- u32 lun_flags;
- u32 unpacked_lun;
- atomic_t lun_acl_count;
- spinlock_t lun_acl_lock;
- spinlock_t lun_cmd_lock;
- spinlock_t lun_sep_lock;
- struct completion lun_shutdown_comp;
- struct list_head lun_cmd_list;
- struct list_head lun_acl_list;
- struct se_device *lun_se_dev;
- struct se_port *lun_sep;
- struct config_group lun_group;
- struct se_port_stat_grps port_stat_grps;
-};
-
struct scsi_port_stats {
u64 cmd_pdus;
u64 tx_data_octets;
struct target_fabric_configfs_template tf_cit_tmpl;
};
-#define TF_CIT_TMPL(tf) (&(tf)->tf_cit_tmpl)
void __target_execute_cmd(struct se_cmd *);
int transport_lookup_tmr_lun(struct se_cmd *, u32);
+struct se_node_acl *core_tpg_get_initiator_node_acl(struct se_portal_group *tpg,
+ unsigned char *);
struct se_node_acl *core_tpg_check_initiator_node_acl(struct se_portal_group *,
unsigned char *);
void core_tpg_clear_object_luns(struct se_portal_group *);
{ EXTENT_FLAG_LOGGING, "LOGGING" }, \
{ EXTENT_FLAG_FILLING, "FILLING" })
-TRACE_EVENT(btrfs_get_extent,
+TRACE_EVENT_CONDITION(btrfs_get_extent,
TP_PROTO(struct btrfs_root *root, struct extent_map *map),
TP_ARGS(root, map),
+ TP_CONDITION(map),
+
TP_STRUCT__entry(
__field( u64, root_objectid )
__field( u64, start )
#define RADEON_INFO_SI_TILE_MODE_ARRAY 0x16
/* query if CP DMA is supported on the compute ring */
#define RADEON_INFO_SI_CP_DMA_COMPUTE 0x17
+/* CIK macrotile mode array */
+#define RADEON_INFO_CIK_MACROTILE_MODE_ARRAY 0x18
struct drm_radeon_info {
#define AUDIT_MAKE_EQUIV 1015 /* Append to watched tree */
#define AUDIT_TTY_GET 1016 /* Get TTY auditing status */
#define AUDIT_TTY_SET 1017 /* Set TTY auditing status */
+#define AUDIT_SET_FEATURE 1018 /* Turn an audit feature on or off */
+#define AUDIT_GET_FEATURE 1019 /* Get which features are enabled */
+#define AUDIT_FEATURE_CHANGE 1020 /* audit log listing feature changes */
#define AUDIT_FIRST_USER_MSG 1100 /* Userspace messages mostly uninteresting to kernel */
#define AUDIT_USER_AVC 1107 /* We filter this differently */
#define AUDIT_PERM_READ 4
#define AUDIT_PERM_ATTR 8
+/* MAX_AUDIT_MESSAGE_LENGTH is set in audit:lib/libaudit.h as:
+ * 8970 // PATH_MAX*2+CONTEXT_SIZE*2+11+256+1
+ * max header+body+tailer: 44 + 29 + 32 + 262 + 7 + pad
+ */
+#define AUDIT_MESSAGE_TEXT_MAX 8560
+
struct audit_status {
__u32 mask; /* Bit mask for valid entries */
__u32 enabled; /* 1 = enabled, 0 = disabled */
__u32 backlog; /* messages waiting in queue */
};
+struct audit_features {
+#define AUDIT_FEATURE_VERSION 1
+ __u32 vers;
+ __u32 mask; /* which bits we are dealing with */
+ __u32 features; /* which feature to enable/disable */
+ __u32 lock; /* which features to lock */
+};
+
+#define AUDIT_FEATURE_ONLY_UNSET_LOGINUID 0
+#define AUDIT_FEATURE_LOGINUID_IMMUTABLE 1
+#define AUDIT_LAST_FEATURE AUDIT_FEATURE_LOGINUID_IMMUTABLE
+
+#define audit_feature_valid(x) ((x) >= 0 && (x) <= AUDIT_LAST_FEATURE)
+#define AUDIT_FEATURE_TO_MASK(x) (1 << ((x) & 31)) /* mask for __u32 */
+
struct audit_tty_status {
__u32 enabled; /* 1 = enabled, 0 = disabled */
__u32 log_passwd; /* 1 = enabled, 0 = disabled */
};
+#define AUDIT_UID_UNSET (unsigned int)-1
+
/* audit_rule_data supports filter rules with both integer and string
* fields. It corresponds with AUDIT_ADD_RULE, AUDIT_DEL_RULE and
* AUDIT_LIST_RULES requests.
--- /dev/null
+/*
+ * Hash Info: Hash algorithms information
+ *
+ * Copyright (c) 2013 Dmitry Kasatkin <d.kasatkin@samsung.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.
+ *
+ */
+
+#ifndef _UAPI_LINUX_HASH_INFO_H
+#define _UAPI_LINUX_HASH_INFO_H
+
+enum hash_algo {
+ HASH_ALGO_MD4,
+ HASH_ALGO_MD5,
+ HASH_ALGO_SHA1,
+ HASH_ALGO_RIPE_MD_160,
+ HASH_ALGO_SHA256,
+ HASH_ALGO_SHA384,
+ HASH_ALGO_SHA512,
+ HASH_ALGO_SHA224,
+ HASH_ALGO_RIPE_MD_128,
+ HASH_ALGO_RIPE_MD_256,
+ HASH_ALGO_RIPE_MD_320,
+ HASH_ALGO_WP_256,
+ HASH_ALGO_WP_384,
+ HASH_ALGO_WP_512,
+ HASH_ALGO_TGR_128,
+ HASH_ALGO_TGR_160,
+ HASH_ALGO_TGR_192,
+ HASH_ALGO__LAST
+};
+
+#endif /* _UAPI_LINUX_HASH_INFO_H */
#define KEYCTL_REJECT 19 /* reject a partially constructed key */
#define KEYCTL_INSTANTIATE_IOV 20 /* instantiate a partially constructed key */
#define KEYCTL_INVALIDATE 21 /* invalidate a key */
+#define KEYCTL_GET_PERSISTENT 22 /* get a user's persistent keyring */
#endif /* _LINUX_KEYCTL_H */
* PCI to PCI Bridge Specification
* PCI System Design Guide
*
- * For hypertransport information, please consult the following manuals
- * from http://www.hypertransport.org
+ * For HyperTransport information, please consult the following manuals
+ * from http://www.hypertransport.org
*
- * The Hypertransport I/O Link Specification
+ * The HyperTransport I/O Link Specification
*/
#ifndef LINUX_PCI_REGS_H
#define PCI_COMMAND_INVALIDATE 0x10 /* Use memory write and invalidate */
#define PCI_COMMAND_VGA_PALETTE 0x20 /* Enable palette snooping */
#define PCI_COMMAND_PARITY 0x40 /* Enable parity checking */
-#define PCI_COMMAND_WAIT 0x80 /* Enable address/data stepping */
+#define PCI_COMMAND_WAIT 0x80 /* Enable address/data stepping */
#define PCI_COMMAND_SERR 0x100 /* Enable SERR */
#define PCI_COMMAND_FAST_BACK 0x200 /* Enable back-to-back writes */
#define PCI_COMMAND_INTX_DISABLE 0x400 /* INTx Emulation Disable */
#define PCI_STATUS 0x06 /* 16 bits */
#define PCI_STATUS_INTERRUPT 0x08 /* Interrupt status */
#define PCI_STATUS_CAP_LIST 0x10 /* Support Capability List */
-#define PCI_STATUS_66MHZ 0x20 /* Support 66 Mhz PCI 2.1 bus */
+#define PCI_STATUS_66MHZ 0x20 /* Support 66 MHz PCI 2.1 bus */
#define PCI_STATUS_UDF 0x40 /* Support User Definable Features [obsolete] */
#define PCI_STATUS_FAST_BACK 0x80 /* Accept fast-back to back */
#define PCI_STATUS_PARITY 0x100 /* Detected parity error */
#define PCI_CAP_ID_CHSWP 0x06 /* CompactPCI HotSwap */
#define PCI_CAP_ID_PCIX 0x07 /* PCI-X */
#define PCI_CAP_ID_HT 0x08 /* HyperTransport */
-#define PCI_CAP_ID_VNDR 0x09 /* Vendor specific */
+#define PCI_CAP_ID_VNDR 0x09 /* Vendor-Specific */
#define PCI_CAP_ID_DBG 0x0A /* Debug port */
#define PCI_CAP_ID_CCRC 0x0B /* CompactPCI Central Resource Control */
-#define PCI_CAP_ID_SHPC 0x0C /* PCI Standard Hot-Plug Controller */
+#define PCI_CAP_ID_SHPC 0x0C /* PCI Standard Hot-Plug Controller */
#define PCI_CAP_ID_SSVID 0x0D /* Bridge subsystem vendor/device ID */
#define PCI_CAP_ID_AGP3 0x0E /* AGP Target PCI-PCI bridge */
#define PCI_CAP_ID_SECDEV 0x0F /* Secure Device */
-#define PCI_CAP_ID_EXP 0x10 /* PCI Express */
+#define PCI_CAP_ID_EXP 0x10 /* PCI Express */
#define PCI_CAP_ID_MSIX 0x11 /* MSI-X */
#define PCI_CAP_ID_SATA 0x12 /* SATA Data/Index Conf. */
#define PCI_CAP_ID_AF 0x13 /* PCI Advanced Features */
#define PCI_AGP_COMMAND_RQ_MASK 0xff000000 /* Master: Maximum number of requests */
#define PCI_AGP_COMMAND_SBA 0x0200 /* Sideband addressing enabled */
#define PCI_AGP_COMMAND_AGP 0x0100 /* Allow processing of AGP transactions */
-#define PCI_AGP_COMMAND_64BIT 0x0020 /* Allow processing of 64-bit addresses */
-#define PCI_AGP_COMMAND_FW 0x0010 /* Force FW transfers */
+#define PCI_AGP_COMMAND_64BIT 0x0020 /* Allow processing of 64-bit addresses */
+#define PCI_AGP_COMMAND_FW 0x0010 /* Force FW transfers */
#define PCI_AGP_COMMAND_RATE4 0x0004 /* Use 4x rate */
#define PCI_AGP_COMMAND_RATE2 0x0002 /* Use 2x rate */
#define PCI_AGP_COMMAND_RATE1 0x0001 /* Use 1x rate */
#define PCI_MSIX_PBA_OFFSET 0xfffffff8 /* Offset into specified BAR */
#define PCI_CAP_MSIX_SIZEOF 12 /* size of MSIX registers */
-/* MSI-X entry's format */
+/* MSI-X Table entry format */
#define PCI_MSIX_ENTRY_SIZE 16
#define PCI_MSIX_ENTRY_LOWER_ADDR 0
#define PCI_MSIX_ENTRY_UPPER_ADDR 4
#define PCI_X_CMD_SPLIT_16 0x0060 /* Max 16 */
#define PCI_X_CMD_SPLIT_32 0x0070 /* Max 32 */
#define PCI_X_CMD_MAX_SPLIT 0x0070 /* Max Outstanding Split Transactions */
-#define PCI_X_CMD_VERSION(x) (((x) >> 12) & 3) /* Version */
+#define PCI_X_CMD_VERSION(x) (((x) >> 12) & 3) /* Version */
#define PCI_X_STATUS 4 /* PCI-X capabilities */
#define PCI_X_STATUS_DEVFN 0x000000ff /* A copy of devfn */
#define PCI_X_STATUS_BUS 0x0000ff00 /* A copy of bus nr */
/* PCI Bridge Subsystem ID registers */
-#define PCI_SSVID_VENDOR_ID 4 /* PCI-Bridge subsystem vendor id register */
-#define PCI_SSVID_DEVICE_ID 6 /* PCI-Bridge subsystem device id register */
+#define PCI_SSVID_VENDOR_ID 4 /* PCI Bridge subsystem vendor ID */
+#define PCI_SSVID_DEVICE_ID 6 /* PCI Bridge subsystem device ID */
/* PCI Express capability registers */
#define PCI_EXP_LNKCTL_CLKREQ_EN 0x0100 /* Enable clkreq */
#define PCI_EXP_LNKCTL_HAWD 0x0200 /* Hardware Autonomous Width Disable */
#define PCI_EXP_LNKCTL_LBMIE 0x0400 /* Link Bandwidth Management Interrupt Enable */
-#define PCI_EXP_LNKCTL_LABIE 0x0800 /* Lnk Autonomous Bandwidth Interrupt Enable */
+#define PCI_EXP_LNKCTL_LABIE 0x0800 /* Link Autonomous Bandwidth Interrupt Enable */
#define PCI_EXP_LNKSTA 18 /* Link Status */
#define PCI_EXP_LNKSTA_CLS 0x000f /* Current Link Speed */
#define PCI_EXP_LNKSTA_CLS_2_5GB 0x0001 /* Current Link Speed 2.5GT/s */
#define PCI_EXP_LNKSTA_CLS_5_0GB 0x0002 /* Current Link Speed 5.0GT/s */
-#define PCI_EXP_LNKSTA_NLW 0x03f0 /* Nogotiated Link Width */
+#define PCI_EXP_LNKSTA_NLW 0x03f0 /* Negotiated Link Width */
#define PCI_EXP_LNKSTA_NLW_SHIFT 4 /* start of NLW mask in link status */
#define PCI_EXP_LNKSTA_LT 0x0800 /* Link Training */
#define PCI_EXP_LNKSTA_SLC 0x1000 /* Slot Clock Configuration */
#define PCI_EXT_CAP_ID_MFVC 0x08 /* Multi-Function VC Capability */
#define PCI_EXT_CAP_ID_VC9 0x09 /* same as _VC */
#define PCI_EXT_CAP_ID_RCRB 0x0A /* Root Complex RB? */
-#define PCI_EXT_CAP_ID_VNDR 0x0B /* Vendor Specific */
+#define PCI_EXT_CAP_ID_VNDR 0x0B /* Vendor-Specific */
#define PCI_EXT_CAP_ID_CAC 0x0C /* Config Access - obsolete */
#define PCI_EXT_CAP_ID_ACS 0x0D /* Access Control Services */
#define PCI_EXT_CAP_ID_ARI 0x0E /* Alternate Routing ID */
#define PCI_EXT_CAP_ID_MRIOV 0x11 /* Multi Root I/O Virtualization */
#define PCI_EXT_CAP_ID_MCAST 0x12 /* Multicast */
#define PCI_EXT_CAP_ID_PRI 0x13 /* Page Request Interface */
-#define PCI_EXT_CAP_ID_AMD_XXX 0x14 /* reserved for AMD */
-#define PCI_EXT_CAP_ID_REBAR 0x15 /* resizable BAR */
-#define PCI_EXT_CAP_ID_DPA 0x16 /* dynamic power alloc */
-#define PCI_EXT_CAP_ID_TPH 0x17 /* TPH request */
-#define PCI_EXT_CAP_ID_LTR 0x18 /* latency tolerance reporting */
-#define PCI_EXT_CAP_ID_SECPCI 0x19 /* Secondary PCIe */
+#define PCI_EXT_CAP_ID_AMD_XXX 0x14 /* Reserved for AMD */
+#define PCI_EXT_CAP_ID_REBAR 0x15 /* Resizable BAR */
+#define PCI_EXT_CAP_ID_DPA 0x16 /* Dynamic Power Allocation */
+#define PCI_EXT_CAP_ID_TPH 0x17 /* TPH Requester */
+#define PCI_EXT_CAP_ID_LTR 0x18 /* Latency Tolerance Reporting */
+#define PCI_EXT_CAP_ID_SECPCI 0x19 /* Secondary PCIe Capability */
#define PCI_EXT_CAP_ID_PMUX 0x1A /* Protocol Multiplexing */
#define PCI_EXT_CAP_ID_PASID 0x1B /* Process Address Space ID */
#define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_PASID
#define PCI_ERR_ROOT_COR_RCV 0x00000001 /* ERR_COR Received */
/* Multi ERR_COR Received */
#define PCI_ERR_ROOT_MULTI_COR_RCV 0x00000002
-/* ERR_FATAL/NONFATAL Recevied */
+/* ERR_FATAL/NONFATAL Received */
#define PCI_ERR_ROOT_UNCOR_RCV 0x00000004
-/* Multi ERR_FATAL/NONFATAL Recevied */
+/* Multi ERR_FATAL/NONFATAL Received */
#define PCI_ERR_ROOT_MULTI_UNCOR_RCV 0x00000008
#define PCI_ERR_ROOT_FIRST_FATAL 0x00000010 /* First Fatal */
#define PCI_ERR_ROOT_NONFATAL_RCV 0x00000020 /* Non-Fatal Received */
/* Virtual Channel */
#define PCI_VC_PORT_REG1 4
-#define PCI_VC_REG1_EVCC 0x7 /* extended vc count */
+#define PCI_VC_REG1_EVCC 0x7 /* extended VC count */
#define PCI_VC_PORT_REG2 8
#define PCI_VC_REG2_32_PHASE 0x2
#define PCI_VC_REG2_64_PHASE 0x4
#define PCI_VNDR_HEADER_LEN(x) (((x) >> 20) & 0xfff)
/*
- * Hypertransport sub capability types
+ * HyperTransport sub capability types
*
* Unfortunately there are both 3 bit and 5 bit capability types defined
* in the HT spec, catering for that is a little messy. You probably don't
#define HT_CAPTYPE_DIRECT_ROUTE 0xB0 /* Direct routing configuration */
#define HT_CAPTYPE_VCSET 0xB8 /* Virtual Channel configuration */
#define HT_CAPTYPE_ERROR_RETRY 0xC0 /* Retry on error configuration */
-#define HT_CAPTYPE_GEN3 0xD0 /* Generation 3 hypertransport configuration */
-#define HT_CAPTYPE_PM 0xE0 /* Hypertransport powermanagement configuration */
+#define HT_CAPTYPE_GEN3 0xD0 /* Generation 3 HyperTransport configuration */
+#define HT_CAPTYPE_PM 0xE0 /* HyperTransport power management configuration */
#define HT_CAP_SIZEOF_LONG 28 /* slave & primary */
#define HT_CAP_SIZEOF_SHORT 24 /* host & secondary */
#define PCI_PRI_ALLOC_REQ 0x0c /* PRI max reqs allowed */
#define PCI_EXT_CAP_PRI_SIZEOF 16
-/* PASID capability */
+/* Process Address Space ID */
#define PCI_PASID_CAP 0x04 /* PASID feature register */
#define PCI_PASID_CAP_EXEC 0x02 /* Exec permissions Supported */
-#define PCI_PASID_CAP_PRIV 0x04 /* Priviledge Mode Supported */
+#define PCI_PASID_CAP_PRIV 0x04 /* Privilege Mode Supported */
#define PCI_PASID_CTRL 0x06 /* PASID control register */
#define PCI_PASID_CTRL_ENABLE 0x01 /* Enable bit */
#define PCI_PASID_CTRL_EXEC 0x02 /* Exec permissions Enable */
-#define PCI_PASID_CTRL_PRIV 0x04 /* Priviledge Mode Enable */
+#define PCI_PASID_CTRL_PRIV 0x04 /* Privilege Mode Enable */
#define PCI_EXT_CAP_PASID_SIZEOF 8
/* Single Root I/O Virtualization */
#define PCI_ACS_CTRL 0x06 /* ACS Control Register */
#define PCI_ACS_EGRESS_CTL_V 0x08 /* ACS Egress Control Vector */
-#define PCI_VSEC_HDR 4 /* extended cap - vendor specific */
+#define PCI_VSEC_HDR 4 /* extended cap - vendor-specific */
#define PCI_VSEC_HDR_LEN_SHIFT 20 /* shift for length field */
-/* sata capability */
+/* SATA capability */
#define PCI_SATA_REGS 4 /* SATA REGs specifier */
#define PCI_SATA_REGS_MASK 0xF /* location - BAR#/inline */
#define PCI_SATA_REGS_INLINE 0xF /* REGS in config space */
#define PCI_SATA_SIZEOF_SHORT 8
#define PCI_SATA_SIZEOF_LONG 16
-/* resizable BARs */
+/* Resizable BARs */
#define PCI_REBAR_CTRL 8 /* control register */
#define PCI_REBAR_CTRL_NBAR_MASK (7 << 5) /* mask for # bars */
#define PCI_REBAR_CTRL_NBAR_SHIFT 5 /* shift for # bars */
-/* dynamic power allocation */
+/* Dynamic Power Allocation */
#define PCI_DPA_CAP 4 /* capability register */
#define PCI_DPA_CAP_SUBSTATE_MASK 0x1F /* # substates - 1 */
#define PCI_DPA_BASE_SIZEOF 16 /* size with 0 substates */
depends on AUDITSYSCALL
select FSNOTIFY
-config AUDIT_LOGINUID_IMMUTABLE
- bool "Make audit loginuid immutable"
- depends on AUDIT
- help
- The config option toggles if a task setting its loginuid requires
- CAP_SYS_AUDITCONTROL or if that task should require no special permissions
- but should instead only allow setting its loginuid if it was never
- previously set. On systems which use systemd or a similar central
- process to restart login services this should be set to true. On older
- systems in which an admin would typically have to directly stop and
- start processes this should be set to false. Setting this to true allows
- one to drop potentially dangerous capabilites from the login tasks,
- but may not be backwards compatible with older init systems.
-
source "kernel/irq/Kconfig"
source "kernel/time/Kconfig"
default 0 if BASE_FULL
default 1 if !BASE_FULL
+config SYSTEM_TRUSTED_KEYRING
+ bool "Provide system-wide ring of trusted keys"
+ depends on KEYS
+ help
+ Provide a system keyring to which trusted keys can be added. Keys in
+ the keyring are considered to be trusted. Keys may be added at will
+ by the kernel from compiled-in data and from hardware key stores, but
+ userspace may only add extra keys if those keys can be verified by
+ keys already in the keyring.
+
+ Keys in this keyring are used by module signature checking.
+
menuconfig MODULES
bool "Enable loadable module support"
option modules
config MODULE_SIG
bool "Module signature verification"
depends on MODULES
+ select SYSTEM_TRUSTED_KEYRING
select KEYS
select CRYPTO
select ASYMMETRIC_KEY_TYPE
*/
static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
{
+ struct file *shm_file;
+
+ shm_file = shp->shm_file;
+ shp->shm_file = NULL;
ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT;
shm_rmid(ns, shp);
shm_unlock(shp);
- if (!is_file_hugepages(shp->shm_file))
- shmem_lock(shp->shm_file, 0, shp->mlock_user);
+ if (!is_file_hugepages(shm_file))
+ shmem_lock(shm_file, 0, shp->mlock_user);
else if (shp->mlock_user)
- user_shm_unlock(file_inode(shp->shm_file)->i_size,
- shp->mlock_user);
- fput (shp->shm_file);
+ user_shm_unlock(file_inode(shm_file)->i_size, shp->mlock_user);
+ fput(shm_file);
ipc_rcu_putref(shp, shm_rcu_free);
}
ipc_lock_object(&shp->shm_perm);
if (!ns_capable(ns->user_ns, CAP_IPC_LOCK)) {
kuid_t euid = current_euid();
- err = -EPERM;
if (!uid_eq(euid, shp->shm_perm.uid) &&
- !uid_eq(euid, shp->shm_perm.cuid))
+ !uid_eq(euid, shp->shm_perm.cuid)) {
+ err = -EPERM;
goto out_unlock0;
- if (cmd == SHM_LOCK && !rlimit(RLIMIT_MEMLOCK))
+ }
+ if (cmd == SHM_LOCK && !rlimit(RLIMIT_MEMLOCK)) {
+ err = -EPERM;
goto out_unlock0;
+ }
}
shm_file = shp->shm_file;
+
+ /* check if shm_destroy() is tearing down shp */
+ if (shm_file == NULL) {
+ err = -EIDRM;
+ goto out_unlock0;
+ }
+
if (is_file_hugepages(shm_file))
goto out_unlock0;
goto out_unlock;
ipc_lock_object(&shp->shm_perm);
+
+ /* check if shm_destroy() is tearing down shp */
+ if (shp->shm_file == NULL) {
+ ipc_unlock_object(&shp->shm_perm);
+ err = -EIDRM;
+ goto out_unlock;
+ }
+
path = shp->shm_file->f_path;
path_get(&path);
shp->shm_nattch++;
obj-y += up.o
endif
obj-$(CONFIG_UID16) += uid16.o
+obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o
obj-$(CONFIG_MODULES) += module.o
-obj-$(CONFIG_MODULE_SIG) += module_signing.o modsign_pubkey.o modsign_certificate.o
+obj-$(CONFIG_MODULE_SIG) += module_signing.o
obj-$(CONFIG_KALLSYMS) += kallsyms.o
obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o
obj-$(CONFIG_KEXEC) += kexec.o
$(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE
$(call if_changed,bc)
-ifeq ($(CONFIG_MODULE_SIG),y)
+###############################################################################
+#
+# Roll all the X.509 certificates that we can find together and pull them into
+# the kernel so that they get loaded into the system trusted keyring during
+# boot.
#
-# Pull the signing certificate and any extra certificates into the kernel
+# We look in the source root and the build root for all files whose name ends
+# in ".x509". Unfortunately, this will generate duplicate filenames, so we
+# have make canonicalise the pathnames and then sort them to discard the
+# duplicates.
#
+###############################################################################
+ifeq ($(CONFIG_SYSTEM_TRUSTED_KEYRING),y)
+X509_CERTIFICATES-y := $(wildcard *.x509) $(wildcard $(srctree)/*.x509)
+X509_CERTIFICATES-$(CONFIG_MODULE_SIG) += signing_key.x509
+X509_CERTIFICATES := $(sort $(foreach CERT,$(X509_CERTIFICATES-y), \
+ $(or $(realpath $(CERT)),$(CERT))))
+
+ifeq ($(X509_CERTIFICATES),)
+$(warning *** No X.509 certificates found ***)
+endif
+
+ifneq ($(wildcard $(obj)/.x509.list),)
+ifneq ($(shell cat $(obj)/.x509.list),$(X509_CERTIFICATES))
+$(info X.509 certificate list changed)
+$(shell rm $(obj)/.x509.list)
+endif
+endif
+
+kernel/system_certificates.o: $(obj)/x509_certificate_list
-quiet_cmd_touch = TOUCH $@
- cmd_touch = touch $@
+quiet_cmd_x509certs = CERTS $@
+ cmd_x509certs = cat $(X509_CERTIFICATES) /dev/null >$@ $(foreach X509,$(X509_CERTIFICATES),; echo " - Including cert $(X509)")
-extra_certificates:
- $(call cmd,touch)
+targets += $(obj)/x509_certificate_list
+$(obj)/x509_certificate_list: $(X509_CERTIFICATES) $(obj)/.x509.list
+ $(call if_changed,x509certs)
-kernel/modsign_certificate.o: signing_key.x509 extra_certificates
+targets += $(obj)/.x509.list
+$(obj)/.x509.list:
+ @echo $(X509_CERTIFICATES) >$@
+clean-files := x509_certificate_list .x509.list
+endif
+
+ifeq ($(CONFIG_MODULE_SIG),y)
###############################################################################
#
# If module signing is requested, say by allyesconfig, but a key has not been
#ifdef CONFIG_SECURITY
#include <linux/security.h>
#endif
-#include <net/netlink.h>
#include <linux/freezer.h>
#include <linux/tty.h>
#include <linux/pid_namespace.h>
static DECLARE_WAIT_QUEUE_HEAD(kauditd_wait);
static DECLARE_WAIT_QUEUE_HEAD(audit_backlog_wait);
+static struct audit_features af = {.vers = AUDIT_FEATURE_VERSION,
+ .mask = -1,
+ .features = 0,
+ .lock = 0,};
+
+static char *audit_feature_names[2] = {
+ "only_unset_loginuid",
+ "loginuid_immutable",
+};
+
+
/* Serialize requests from userspace. */
DEFINE_MUTEX(audit_cmd_mutex);
return -EOPNOTSUPP;
case AUDIT_GET:
case AUDIT_SET:
+ case AUDIT_GET_FEATURE:
+ case AUDIT_SET_FEATURE:
case AUDIT_LIST_RULES:
case AUDIT_ADD_RULE:
case AUDIT_DEL_RULE:
int rc = 0;
uid_t uid = from_kuid(&init_user_ns, current_uid());
- if (!audit_enabled) {
+ if (!audit_enabled && msg_type != AUDIT_USER_AVC) {
*ab = NULL;
return rc;
}
return rc;
}
+int is_audit_feature_set(int i)
+{
+ return af.features & AUDIT_FEATURE_TO_MASK(i);
+}
+
+
+static int audit_get_feature(struct sk_buff *skb)
+{
+ u32 seq;
+
+ seq = nlmsg_hdr(skb)->nlmsg_seq;
+
+ audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0,
+ &af, sizeof(af));
+
+ return 0;
+}
+
+static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature,
+ u32 old_lock, u32 new_lock, int res)
+{
+ struct audit_buffer *ab;
+
+ ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_FEATURE_CHANGE);
+ audit_log_format(ab, "feature=%s new=%d old=%d old_lock=%d new_lock=%d res=%d",
+ audit_feature_names[which], !!old_feature, !!new_feature,
+ !!old_lock, !!new_lock, res);
+ audit_log_end(ab);
+}
+
+static int audit_set_feature(struct sk_buff *skb)
+{
+ struct audit_features *uaf;
+ int i;
+
+ BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > sizeof(audit_feature_names)/sizeof(audit_feature_names[0]));
+ uaf = nlmsg_data(nlmsg_hdr(skb));
+
+ /* if there is ever a version 2 we should handle that here */
+
+ for (i = 0; i <= AUDIT_LAST_FEATURE; i++) {
+ u32 feature = AUDIT_FEATURE_TO_MASK(i);
+ u32 old_feature, new_feature, old_lock, new_lock;
+
+ /* if we are not changing this feature, move along */
+ if (!(feature & uaf->mask))
+ continue;
+
+ old_feature = af.features & feature;
+ new_feature = uaf->features & feature;
+ new_lock = (uaf->lock | af.lock) & feature;
+ old_lock = af.lock & feature;
+
+ /* are we changing a locked feature? */
+ if ((af.lock & feature) && (new_feature != old_feature)) {
+ audit_log_feature_change(i, old_feature, new_feature,
+ old_lock, new_lock, 0);
+ return -EPERM;
+ }
+ }
+ /* nothing invalid, do the changes */
+ for (i = 0; i <= AUDIT_LAST_FEATURE; i++) {
+ u32 feature = AUDIT_FEATURE_TO_MASK(i);
+ u32 old_feature, new_feature, old_lock, new_lock;
+
+ /* if we are not changing this feature, move along */
+ if (!(feature & uaf->mask))
+ continue;
+
+ old_feature = af.features & feature;
+ new_feature = uaf->features & feature;
+ old_lock = af.lock & feature;
+ new_lock = (uaf->lock | af.lock) & feature;
+
+ if (new_feature != old_feature)
+ audit_log_feature_change(i, old_feature, new_feature,
+ old_lock, new_lock, 1);
+
+ if (new_feature)
+ af.features |= feature;
+ else
+ af.features &= ~feature;
+ af.lock |= new_lock;
+ }
+
+ return 0;
+}
+
static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
{
u32 seq;
switch (msg_type) {
case AUDIT_GET:
+ memset(&status_set, 0, sizeof(status_set));
status_set.enabled = audit_enabled;
status_set.failure = audit_failure;
status_set.pid = audit_pid;
&status_set, sizeof(status_set));
break;
case AUDIT_SET:
- if (nlh->nlmsg_len < sizeof(struct audit_status))
+ if (nlmsg_len(nlh) < sizeof(struct audit_status))
return -EINVAL;
status_get = (struct audit_status *)data;
if (status_get->mask & AUDIT_STATUS_ENABLED) {
if (status_get->mask & AUDIT_STATUS_BACKLOG_LIMIT)
err = audit_set_backlog_limit(status_get->backlog_limit);
break;
+ case AUDIT_GET_FEATURE:
+ err = audit_get_feature(skb);
+ if (err)
+ return err;
+ break;
+ case AUDIT_SET_FEATURE:
+ err = audit_set_feature(skb);
+ if (err)
+ return err;
+ break;
case AUDIT_USER:
case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG:
case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2:
}
audit_log_common_recv_msg(&ab, msg_type);
if (msg_type != AUDIT_USER_TTY)
- audit_log_format(ab, " msg='%.1024s'",
+ audit_log_format(ab, " msg='%.*s'",
+ AUDIT_MESSAGE_TEXT_MAX,
(char *)data);
else {
int size;
struct task_struct *tsk = current;
spin_lock(&tsk->sighand->siglock);
- s.enabled = tsk->signal->audit_tty != 0;
+ s.enabled = tsk->signal->audit_tty;
s.log_passwd = tsk->signal->audit_tty_log_passwd;
spin_unlock(&tsk->sighand->siglock);
memset(&s, 0, sizeof(s));
/* guard against past and future API changes */
- memcpy(&s, data, min(sizeof(s), (size_t)nlh->nlmsg_len));
+ memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh)));
if ((s.enabled != 0 && s.enabled != 1) ||
(s.log_passwd != 0 && s.log_passwd != 1))
return -EINVAL;
remove_wait_queue(&audit_backlog_wait, &wait);
}
-/* Obtain an audit buffer. This routine does locking to obtain the
- * audit buffer, but then no locking is required for calls to
- * audit_log_*format. If the tsk is a task that is currently in a
- * syscall, then the syscall is marked as auditable and an audit record
- * will be written at syscall exit. If there is no associated task, tsk
- * should be NULL. */
-
/**
* audit_log_start - obtain an audit buffer
* @ctx: audit_context (may be NULL)
u32 sessionid = audit_get_sessionid(current);
uid_t auid = from_kuid(&init_user_ns, audit_get_loginuid(current));
- audit_log_format(ab, " auid=%u ses=%u\n", auid, sessionid);
+ audit_log_format(ab, " auid=%u ses=%u", auid, sessionid);
}
void audit_log_key(struct audit_buffer *ab, char *key)
}
}
+ /* log the audit_names record type */
+ audit_log_format(ab, " nametype=");
+ switch(n->type) {
+ case AUDIT_TYPE_NORMAL:
+ audit_log_format(ab, "NORMAL");
+ break;
+ case AUDIT_TYPE_PARENT:
+ audit_log_format(ab, "PARENT");
+ break;
+ case AUDIT_TYPE_CHILD_DELETE:
+ audit_log_format(ab, "DELETE");
+ break;
+ case AUDIT_TYPE_CHILD_CREATE:
+ audit_log_format(ab, "CREATE");
+ break;
+ default:
+ audit_log_format(ab, "UNKNOWN");
+ break;
+ }
+
audit_log_fcaps(ab, n);
audit_log_end(ab);
}
int fd;
int flags;
} mmap;
+ struct {
+ int argc;
+ } execve;
};
int fds[2];
case AUDIT_DEVMINOR:
case AUDIT_EXIT:
case AUDIT_SUCCESS:
+ case AUDIT_INODE:
/* bit ops are only useful on syscall args */
if (f->op == Audit_bitmask || f->op == Audit_bittest)
return -EINVAL;
f->lsm_rule = NULL;
/* Support legacy tests for a valid loginuid */
- if ((f->type == AUDIT_LOGINUID) && (f->val == ~0U)) {
+ if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) {
f->type = AUDIT_LOGINUID_SET;
f->val = 0;
}
/* Number of target pids per aux struct. */
#define AUDIT_AUX_PIDS 16
-struct audit_aux_data_execve {
- struct audit_aux_data d;
- int argc;
- int envc;
- struct mm_struct *mm;
-};
-
struct audit_aux_data_pids {
struct audit_aux_data d;
pid_t target_pid[AUDIT_AUX_PIDS];
struct audit_cap_data new_pcap;
};
-struct audit_aux_data_capset {
- struct audit_aux_data d;
- pid_t pid;
- struct audit_cap_data cap;
-};
-
struct audit_tree_refs {
struct audit_tree_refs *next;
struct audit_chunk *c[31];
break;
case AUDIT_INODE:
if (name)
- result = (name->ino == f->val);
+ result = audit_comparator(name->ino, f->op, f->val);
else if (ctx) {
list_for_each_entry(n, &ctx->names_list, list) {
if (audit_comparator(n->ino, f->op, f->val)) {
return 0; /* Return if not auditing. */
state = audit_filter_task(tsk, &key);
- if (state == AUDIT_DISABLED)
+ if (state == AUDIT_DISABLED) {
+ clear_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT);
return 0;
+ }
if (!(context = audit_alloc_context(state))) {
kfree(key);
}
static void audit_log_execve_info(struct audit_context *context,
- struct audit_buffer **ab,
- struct audit_aux_data_execve *axi)
+ struct audit_buffer **ab)
{
int i, len;
size_t len_sent = 0;
const char __user *p;
char *buf;
- if (axi->mm != current->mm)
- return; /* execve failed, no additional info */
-
- p = (const char __user *)axi->mm->arg_start;
+ p = (const char __user *)current->mm->arg_start;
- audit_log_format(*ab, "argc=%d", axi->argc);
+ audit_log_format(*ab, "argc=%d", context->execve.argc);
/*
* we need some kernel buffer to hold the userspace args. Just
return;
}
- for (i = 0; i < axi->argc; i++) {
+ for (i = 0; i < context->execve.argc; i++) {
len = audit_log_single_execve_arg(context, ab, i,
&len_sent, p, buf);
if (len <= 0)
audit_log_format(ab, "fd=%d flags=0x%x", context->mmap.fd,
context->mmap.flags);
break; }
+ case AUDIT_EXECVE: {
+ audit_log_execve_info(context, &ab);
+ break; }
}
audit_log_end(ab);
}
switch (aux->type) {
- case AUDIT_EXECVE: {
- struct audit_aux_data_execve *axi = (void *)aux;
- audit_log_execve_info(context, &ab, axi);
- break; }
-
case AUDIT_BPRM_FCAPS: {
struct audit_aux_data_bprm_fcaps *axs = (void *)aux;
audit_log_format(ab, "fver=%x", axs->fcap_ver);
/* global counter which is incremented every time something logs in */
static atomic_t session_id = ATOMIC_INIT(0);
+static int audit_set_loginuid_perm(kuid_t loginuid)
+{
+ /* if we are unset, we don't need privs */
+ if (!audit_loginuid_set(current))
+ return 0;
+ /* if AUDIT_FEATURE_LOGINUID_IMMUTABLE means never ever allow a change*/
+ if (is_audit_feature_set(AUDIT_FEATURE_LOGINUID_IMMUTABLE))
+ return -EPERM;
+ /* it is set, you need permission */
+ if (!capable(CAP_AUDIT_CONTROL))
+ return -EPERM;
+ /* reject if this is not an unset and we don't allow that */
+ if (is_audit_feature_set(AUDIT_FEATURE_ONLY_UNSET_LOGINUID) && uid_valid(loginuid))
+ return -EPERM;
+ return 0;
+}
+
+static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid,
+ unsigned int oldsessionid, unsigned int sessionid,
+ int rc)
+{
+ struct audit_buffer *ab;
+ uid_t uid, ologinuid, nloginuid;
+
+ uid = from_kuid(&init_user_ns, task_uid(current));
+ ologinuid = from_kuid(&init_user_ns, koldloginuid);
+ nloginuid = from_kuid(&init_user_ns, kloginuid),
+
+ ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
+ if (!ab)
+ return;
+ audit_log_format(ab, "pid=%d uid=%u old auid=%u new auid=%u old "
+ "ses=%u new ses=%u res=%d", current->pid, uid, ologinuid,
+ nloginuid, oldsessionid, sessionid, !rc);
+ audit_log_end(ab);
+}
+
/**
* audit_set_loginuid - set current task's audit_context loginuid
* @loginuid: loginuid value
int audit_set_loginuid(kuid_t loginuid)
{
struct task_struct *task = current;
- struct audit_context *context = task->audit_context;
- unsigned int sessionid;
+ unsigned int oldsessionid, sessionid = (unsigned int)-1;
+ kuid_t oldloginuid;
+ int rc;
-#ifdef CONFIG_AUDIT_LOGINUID_IMMUTABLE
- if (audit_loginuid_set(task))
- return -EPERM;
-#else /* CONFIG_AUDIT_LOGINUID_IMMUTABLE */
- if (!capable(CAP_AUDIT_CONTROL))
- return -EPERM;
-#endif /* CONFIG_AUDIT_LOGINUID_IMMUTABLE */
+ oldloginuid = audit_get_loginuid(current);
+ oldsessionid = audit_get_sessionid(current);
- sessionid = atomic_inc_return(&session_id);
- if (context && context->in_syscall) {
- struct audit_buffer *ab;
+ rc = audit_set_loginuid_perm(loginuid);
+ if (rc)
+ goto out;
+
+ /* are we setting or clearing? */
+ if (uid_valid(loginuid))
+ sessionid = atomic_inc_return(&session_id);
- ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
- if (ab) {
- audit_log_format(ab, "login pid=%d uid=%u "
- "old auid=%u new auid=%u"
- " old ses=%u new ses=%u",
- task->pid,
- from_kuid(&init_user_ns, task_uid(task)),
- from_kuid(&init_user_ns, task->loginuid),
- from_kuid(&init_user_ns, loginuid),
- task->sessionid, sessionid);
- audit_log_end(ab);
- }
- }
task->sessionid = sessionid;
task->loginuid = loginuid;
- return 0;
+out:
+ audit_log_set_loginuid(oldloginuid, loginuid, oldsessionid, sessionid, rc);
+ return rc;
}
/**
context->ipc.has_perm = 1;
}
-int __audit_bprm(struct linux_binprm *bprm)
+void __audit_bprm(struct linux_binprm *bprm)
{
- struct audit_aux_data_execve *ax;
struct audit_context *context = current->audit_context;
- ax = kmalloc(sizeof(*ax), GFP_KERNEL);
- if (!ax)
- return -ENOMEM;
-
- ax->argc = bprm->argc;
- ax->envc = bprm->envc;
- ax->mm = bprm->mm;
- ax->d.type = AUDIT_EXECVE;
- ax->d.next = context->aux;
- context->aux = (void *)ax;
- return 0;
+ context->type = AUDIT_EXECVE;
+ context->execve.argc = bprm->argc;
}
+++ /dev/null
-#include <linux/export.h>
-
-#define GLOBAL(name) \
- .globl VMLINUX_SYMBOL(name); \
- VMLINUX_SYMBOL(name):
-
- .section ".init.data","aw"
-
-GLOBAL(modsign_certificate_list)
- .incbin "signing_key.x509"
- .incbin "extra_certificates"
-GLOBAL(modsign_certificate_list_end)
+++ /dev/null
-/* Public keys for module signature verification
- *
- * Copyright (C) 2012 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 Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/cred.h>
-#include <linux/err.h>
-#include <keys/asymmetric-type.h>
-#include "module-internal.h"
-
-struct key *modsign_keyring;
-
-extern __initconst const u8 modsign_certificate_list[];
-extern __initconst const u8 modsign_certificate_list_end[];
-
-/*
- * We need to make sure ccache doesn't cache the .o file as it doesn't notice
- * if modsign.pub changes.
- */
-static __initconst const char annoy_ccache[] = __TIME__ "foo";
-
-/*
- * Load the compiled-in keys
- */
-static __init int module_verify_init(void)
-{
- pr_notice("Initialise module verification\n");
-
- modsign_keyring = keyring_alloc(".module_sign",
- KUIDT_INIT(0), KGIDT_INIT(0),
- current_cred(),
- ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
- KEY_USR_VIEW | KEY_USR_READ),
- KEY_ALLOC_NOT_IN_QUOTA, NULL);
- if (IS_ERR(modsign_keyring))
- panic("Can't allocate module signing keyring\n");
-
- return 0;
-}
-
-/*
- * Must be initialised before we try and load the keys into the keyring.
- */
-device_initcall(module_verify_init);
-
-/*
- * Load the compiled-in keys
- */
-static __init int load_module_signing_keys(void)
-{
- key_ref_t key;
- const u8 *p, *end;
- size_t plen;
-
- pr_notice("Loading module verification certificates\n");
-
- end = modsign_certificate_list_end;
- p = modsign_certificate_list;
- while (p < end) {
- /* Each cert begins with an ASN.1 SEQUENCE tag and must be more
- * than 256 bytes in size.
- */
- if (end - p < 4)
- goto dodgy_cert;
- if (p[0] != 0x30 &&
- p[1] != 0x82)
- goto dodgy_cert;
- plen = (p[2] << 8) | p[3];
- plen += 4;
- if (plen > end - p)
- goto dodgy_cert;
-
- key = key_create_or_update(make_key_ref(modsign_keyring, 1),
- "asymmetric",
- NULL,
- p,
- plen,
- (KEY_POS_ALL & ~KEY_POS_SETATTR) |
- KEY_USR_VIEW,
- KEY_ALLOC_NOT_IN_QUOTA);
- if (IS_ERR(key))
- pr_err("MODSIGN: Problem loading in-kernel X.509 certificate (%ld)\n",
- PTR_ERR(key));
- else
- pr_notice("MODSIGN: Loaded cert '%s'\n",
- key_ref_to_ptr(key)->description);
- p += plen;
- }
-
- return 0;
-
-dodgy_cert:
- pr_err("MODSIGN: Problem parsing in-kernel X.509 certificate list\n");
- return 0;
-}
-late_initcall(load_module_signing_keys);
* 2 of the Licence, or (at your option) any later version.
*/
-extern struct key *modsign_keyring;
-
extern int mod_verify_sig(const void *mod, unsigned long *_modlen);
#include <crypto/public_key.h>
#include <crypto/hash.h>
#include <keys/asymmetric-type.h>
+#include <keys/system_keyring.h>
#include "module-internal.h"
/*
*/
struct module_signature {
u8 algo; /* Public-key crypto algorithm [enum pkey_algo] */
- u8 hash; /* Digest algorithm [enum pkey_hash_algo] */
+ u8 hash; /* Digest algorithm [enum hash_algo] */
u8 id_type; /* Key identifier type [enum pkey_id_type] */
u8 signer_len; /* Length of signer's name */
u8 key_id_len; /* Length of key identifier */
/*
* Digest the module contents.
*/
-static struct public_key_signature *mod_make_digest(enum pkey_hash_algo hash,
+static struct public_key_signature *mod_make_digest(enum hash_algo hash,
const void *mod,
unsigned long modlen)
{
/* Allocate the hashing algorithm we're going to need and find out how
* big the hash operational data will be.
*/
- tfm = crypto_alloc_shash(pkey_hash_algo[hash], 0, 0);
+ tfm = crypto_alloc_shash(hash_algo_name[hash], 0, 0);
if (IS_ERR(tfm))
return (PTR_ERR(tfm) == -ENOENT) ? ERR_PTR(-ENOPKG) : ERR_CAST(tfm);
pr_debug("Look up: \"%s\"\n", id);
- key = keyring_search(make_key_ref(modsign_keyring, 1),
+ key = keyring_search(make_key_ref(system_trusted_keyring, 1),
&key_type_asymmetric, id);
if (IS_ERR(key))
pr_warn("Request for unknown module key '%s' err %ld\n",
return -ENOPKG;
if (ms.hash >= PKEY_HASH__LAST ||
- !pkey_hash_algo[ms.hash])
+ !hash_algo_name[ms.hash])
return -ENOPKG;
key = request_asymmetric_key(sig, ms.signer_len,
--- /dev/null
+#include <linux/export.h>
+#include <linux/init.h>
+
+ __INITRODATA
+
+ .globl VMLINUX_SYMBOL(system_certificate_list)
+VMLINUX_SYMBOL(system_certificate_list):
+ .incbin "kernel/x509_certificate_list"
+ .globl VMLINUX_SYMBOL(system_certificate_list_end)
+VMLINUX_SYMBOL(system_certificate_list_end):
--- /dev/null
+/* System trusted keyring for trusted public keys
+ *
+ * Copyright (C) 2012 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/cred.h>
+#include <linux/err.h>
+#include <keys/asymmetric-type.h>
+#include <keys/system_keyring.h>
+#include "module-internal.h"
+
+struct key *system_trusted_keyring;
+EXPORT_SYMBOL_GPL(system_trusted_keyring);
+
+extern __initconst const u8 system_certificate_list[];
+extern __initconst const u8 system_certificate_list_end[];
+
+/*
+ * Load the compiled-in keys
+ */
+static __init int system_trusted_keyring_init(void)
+{
+ pr_notice("Initialise system trusted keyring\n");
+
+ system_trusted_keyring =
+ keyring_alloc(".system_keyring",
+ KUIDT_INIT(0), KGIDT_INIT(0), current_cred(),
+ ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+ KEY_USR_VIEW | KEY_USR_READ | KEY_USR_SEARCH),
+ KEY_ALLOC_NOT_IN_QUOTA, NULL);
+ if (IS_ERR(system_trusted_keyring))
+ panic("Can't allocate system trusted keyring\n");
+
+ set_bit(KEY_FLAG_TRUSTED_ONLY, &system_trusted_keyring->flags);
+ return 0;
+}
+
+/*
+ * Must be initialised before we try and load the keys into the keyring.
+ */
+device_initcall(system_trusted_keyring_init);
+
+/*
+ * Load the compiled-in list of X.509 certificates.
+ */
+static __init int load_system_certificate_list(void)
+{
+ key_ref_t key;
+ const u8 *p, *end;
+ size_t plen;
+
+ pr_notice("Loading compiled-in X.509 certificates\n");
+
+ end = system_certificate_list_end;
+ p = system_certificate_list;
+ while (p < end) {
+ /* Each cert begins with an ASN.1 SEQUENCE tag and must be more
+ * than 256 bytes in size.
+ */
+ if (end - p < 4)
+ goto dodgy_cert;
+ if (p[0] != 0x30 &&
+ p[1] != 0x82)
+ goto dodgy_cert;
+ plen = (p[2] << 8) | p[3];
+ plen += 4;
+ if (plen > end - p)
+ goto dodgy_cert;
+
+ key = key_create_or_update(make_key_ref(system_trusted_keyring, 1),
+ "asymmetric",
+ NULL,
+ p,
+ plen,
+ ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+ KEY_USR_VIEW | KEY_USR_READ),
+ KEY_ALLOC_NOT_IN_QUOTA |
+ KEY_ALLOC_TRUSTED);
+ if (IS_ERR(key)) {
+ pr_err("Problem loading in-kernel X.509 certificate (%ld)\n",
+ PTR_ERR(key));
+ } else {
+ pr_notice("Loaded X.509 cert '%s'\n",
+ key_ref_to_ptr(key)->description);
+ key_ref_put(key);
+ }
+ p += plen;
+ }
+
+ return 0;
+
+dodgy_cert:
+ pr_err("Problem parsing in-kernel X.509 certificate list\n");
+ return 0;
+}
+late_initcall(load_system_certificate_list);
.owner = GLOBAL_ROOT_UID,
.group = GLOBAL_ROOT_GID,
.proc_inum = PROC_USER_INIT_INO,
+#ifdef CONFIG_KEYS_KERBEROS_CACHE
+ .krb_cache_register_sem =
+ __RWSEM_INITIALIZER(init_user_ns.krb_cache_register_sem),
+#endif
};
EXPORT_SYMBOL_GPL(init_user_ns);
set_cred_user_ns(new, ns);
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+ init_rwsem(&ns->persistent_keyring_register_sem);
+#endif
return 0;
}
do {
parent = ns->parent;
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+ key_put(ns->persistent_keyring_register);
+#endif
proc_free_inum(ns->proc_inum);
kmem_cache_free(user_ns_cachep, ns);
ns = parent;
config BTREE
boolean
+config ASSOCIATIVE_ARRAY
+ bool
+ help
+ Generic associative array. Can be searched and iterated over whilst
+ it is being modified. It is also reasonably quick to search and
+ modify. The algorithms are non-recursive, and the trees are highly
+ capacious.
+
+ See:
+
+ Documentation/assoc_array.txt
+
+ for more information.
+
config HAS_IOMEM
boolean
depends on !NO_IOMEM
sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
proportions.o flex_proportions.o prio_heap.o ratelimit.o show_mem.o \
is_single_threaded.o plist.o decompress.o kobject_uevent.o \
- earlycpio.o percpu-refcount.o percpu_ida.o
+ earlycpio.o
obj-$(CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS) += usercopy.o
lib-$(CONFIG_MMU) += ioremap.o
bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
gcd.o lcm.o list_sort.o uuid.o flex_array.o iovec.o clz_ctz.o \
bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o \
- percpu_ida.o
+ percpu-refcount.o percpu_ida.o
obj-y += string_helpers.o
obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o
obj-y += kstrtox.o
obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
obj-$(CONFIG_BTREE) += btree.o
+obj-$(CONFIG_ASSOCIATIVE_ARRAY) += assoc_array.o
obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o
obj-$(CONFIG_DEBUG_LIST) += list_debug.o
obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o
--- /dev/null
+/* Generic associative array implementation.
+ *
+ * See Documentation/assoc_array.txt for information.
+ *
+ * Copyright (C) 2013 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+//#define DEBUG
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/assoc_array_priv.h>
+
+/*
+ * Iterate over an associative array. The caller must hold the RCU read lock
+ * or better.
+ */
+static int assoc_array_subtree_iterate(const struct assoc_array_ptr *root,
+ const struct assoc_array_ptr *stop,
+ int (*iterator)(const void *leaf,
+ void *iterator_data),
+ void *iterator_data)
+{
+ const struct assoc_array_shortcut *shortcut;
+ const struct assoc_array_node *node;
+ const struct assoc_array_ptr *cursor, *ptr, *parent;
+ unsigned long has_meta;
+ int slot, ret;
+
+ cursor = root;
+
+begin_node:
+ if (assoc_array_ptr_is_shortcut(cursor)) {
+ /* Descend through a shortcut */
+ shortcut = assoc_array_ptr_to_shortcut(cursor);
+ smp_read_barrier_depends();
+ cursor = ACCESS_ONCE(shortcut->next_node);
+ }
+
+ node = assoc_array_ptr_to_node(cursor);
+ smp_read_barrier_depends();
+ slot = 0;
+
+ /* We perform two passes of each node.
+ *
+ * The first pass does all the leaves in this node. This means we
+ * don't miss any leaves if the node is split up by insertion whilst
+ * we're iterating over the branches rooted here (we may, however, see
+ * some leaves twice).
+ */
+ has_meta = 0;
+ for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+ ptr = ACCESS_ONCE(node->slots[slot]);
+ has_meta |= (unsigned long)ptr;
+ if (ptr && assoc_array_ptr_is_leaf(ptr)) {
+ /* We need a barrier between the read of the pointer
+ * and dereferencing the pointer - but only if we are
+ * actually going to dereference it.
+ */
+ smp_read_barrier_depends();
+
+ /* Invoke the callback */
+ ret = iterator(assoc_array_ptr_to_leaf(ptr),
+ iterator_data);
+ if (ret)
+ return ret;
+ }
+ }
+
+ /* The second pass attends to all the metadata pointers. If we follow
+ * one of these we may find that we don't come back here, but rather go
+ * back to a replacement node with the leaves in a different layout.
+ *
+ * We are guaranteed to make progress, however, as the slot number for
+ * a particular portion of the key space cannot change - and we
+ * continue at the back pointer + 1.
+ */
+ if (!(has_meta & ASSOC_ARRAY_PTR_META_TYPE))
+ goto finished_node;
+ slot = 0;
+
+continue_node:
+ node = assoc_array_ptr_to_node(cursor);
+ smp_read_barrier_depends();
+
+ for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+ ptr = ACCESS_ONCE(node->slots[slot]);
+ if (assoc_array_ptr_is_meta(ptr)) {
+ cursor = ptr;
+ goto begin_node;
+ }
+ }
+
+finished_node:
+ /* Move up to the parent (may need to skip back over a shortcut) */
+ parent = ACCESS_ONCE(node->back_pointer);
+ slot = node->parent_slot;
+ if (parent == stop)
+ return 0;
+
+ if (assoc_array_ptr_is_shortcut(parent)) {
+ shortcut = assoc_array_ptr_to_shortcut(parent);
+ smp_read_barrier_depends();
+ cursor = parent;
+ parent = ACCESS_ONCE(shortcut->back_pointer);
+ slot = shortcut->parent_slot;
+ if (parent == stop)
+ return 0;
+ }
+
+ /* Ascend to next slot in parent node */
+ cursor = parent;
+ slot++;
+ goto continue_node;
+}
+
+/**
+ * assoc_array_iterate - Pass all objects in the array to a callback
+ * @array: The array to iterate over.
+ * @iterator: The callback function.
+ * @iterator_data: Private data for the callback function.
+ *
+ * Iterate over all the objects in an associative array. Each one will be
+ * presented to the iterator function.
+ *
+ * If the array is being modified concurrently with the iteration then it is
+ * possible that some objects in the array will be passed to the iterator
+ * callback more than once - though every object should be passed at least
+ * once. If this is undesirable then the caller must lock against modification
+ * for the duration of this function.
+ *
+ * The function will return 0 if no objects were in the array or else it will
+ * return the result of the last iterator function called. Iteration stops
+ * immediately if any call to the iteration function results in a non-zero
+ * return.
+ *
+ * The caller should hold the RCU read lock or better if concurrent
+ * modification is possible.
+ */
+int assoc_array_iterate(const struct assoc_array *array,
+ int (*iterator)(const void *object,
+ void *iterator_data),
+ void *iterator_data)
+{
+ struct assoc_array_ptr *root = ACCESS_ONCE(array->root);
+
+ if (!root)
+ return 0;
+ return assoc_array_subtree_iterate(root, NULL, iterator, iterator_data);
+}
+
+enum assoc_array_walk_status {
+ assoc_array_walk_tree_empty,
+ assoc_array_walk_found_terminal_node,
+ assoc_array_walk_found_wrong_shortcut,
+} status;
+
+struct assoc_array_walk_result {
+ struct {
+ struct assoc_array_node *node; /* Node in which leaf might be found */
+ int level;
+ int slot;
+ } terminal_node;
+ struct {
+ struct assoc_array_shortcut *shortcut;
+ int level;
+ int sc_level;
+ unsigned long sc_segments;
+ unsigned long dissimilarity;
+ } wrong_shortcut;
+};
+
+/*
+ * Navigate through the internal tree looking for the closest node to the key.
+ */
+static enum assoc_array_walk_status
+assoc_array_walk(const struct assoc_array *array,
+ const struct assoc_array_ops *ops,
+ const void *index_key,
+ struct assoc_array_walk_result *result)
+{
+ struct assoc_array_shortcut *shortcut;
+ struct assoc_array_node *node;
+ struct assoc_array_ptr *cursor, *ptr;
+ unsigned long sc_segments, dissimilarity;
+ unsigned long segments;
+ int level, sc_level, next_sc_level;
+ int slot;
+
+ pr_devel("-->%s()\n", __func__);
+
+ cursor = ACCESS_ONCE(array->root);
+ if (!cursor)
+ return assoc_array_walk_tree_empty;
+
+ level = 0;
+
+ /* Use segments from the key for the new leaf to navigate through the
+ * internal tree, skipping through nodes and shortcuts that are on
+ * route to the destination. Eventually we'll come to a slot that is
+ * either empty or contains a leaf at which point we've found a node in
+ * which the leaf we're looking for might be found or into which it
+ * should be inserted.
+ */
+jumped:
+ segments = ops->get_key_chunk(index_key, level);
+ pr_devel("segments[%d]: %lx\n", level, segments);
+
+ if (assoc_array_ptr_is_shortcut(cursor))
+ goto follow_shortcut;
+
+consider_node:
+ node = assoc_array_ptr_to_node(cursor);
+ smp_read_barrier_depends();
+
+ slot = segments >> (level & ASSOC_ARRAY_KEY_CHUNK_MASK);
+ slot &= ASSOC_ARRAY_FAN_MASK;
+ ptr = ACCESS_ONCE(node->slots[slot]);
+
+ pr_devel("consider slot %x [ix=%d type=%lu]\n",
+ slot, level, (unsigned long)ptr & 3);
+
+ if (!assoc_array_ptr_is_meta(ptr)) {
+ /* The node doesn't have a node/shortcut pointer in the slot
+ * corresponding to the index key that we have to follow.
+ */
+ result->terminal_node.node = node;
+ result->terminal_node.level = level;
+ result->terminal_node.slot = slot;
+ pr_devel("<--%s() = terminal_node\n", __func__);
+ return assoc_array_walk_found_terminal_node;
+ }
+
+ if (assoc_array_ptr_is_node(ptr)) {
+ /* There is a pointer to a node in the slot corresponding to
+ * this index key segment, so we need to follow it.
+ */
+ cursor = ptr;
+ level += ASSOC_ARRAY_LEVEL_STEP;
+ if ((level & ASSOC_ARRAY_KEY_CHUNK_MASK) != 0)
+ goto consider_node;
+ goto jumped;
+ }
+
+ /* There is a shortcut in the slot corresponding to the index key
+ * segment. We follow the shortcut if its partial index key matches
+ * this leaf's. Otherwise we need to split the shortcut.
+ */
+ cursor = ptr;
+follow_shortcut:
+ shortcut = assoc_array_ptr_to_shortcut(cursor);
+ smp_read_barrier_depends();
+ pr_devel("shortcut to %d\n", shortcut->skip_to_level);
+ sc_level = level + ASSOC_ARRAY_LEVEL_STEP;
+ BUG_ON(sc_level > shortcut->skip_to_level);
+
+ do {
+ /* Check the leaf against the shortcut's index key a word at a
+ * time, trimming the final word (the shortcut stores the index
+ * key completely from the root to the shortcut's target).
+ */
+ if ((sc_level & ASSOC_ARRAY_KEY_CHUNK_MASK) == 0)
+ segments = ops->get_key_chunk(index_key, sc_level);
+
+ sc_segments = shortcut->index_key[sc_level >> ASSOC_ARRAY_KEY_CHUNK_SHIFT];
+ dissimilarity = segments ^ sc_segments;
+
+ if (round_up(sc_level, ASSOC_ARRAY_KEY_CHUNK_SIZE) > shortcut->skip_to_level) {
+ /* Trim segments that are beyond the shortcut */
+ int shift = shortcut->skip_to_level & ASSOC_ARRAY_KEY_CHUNK_MASK;
+ dissimilarity &= ~(ULONG_MAX << shift);
+ next_sc_level = shortcut->skip_to_level;
+ } else {
+ next_sc_level = sc_level + ASSOC_ARRAY_KEY_CHUNK_SIZE;
+ next_sc_level = round_down(next_sc_level, ASSOC_ARRAY_KEY_CHUNK_SIZE);
+ }
+
+ if (dissimilarity != 0) {
+ /* This shortcut points elsewhere */
+ result->wrong_shortcut.shortcut = shortcut;
+ result->wrong_shortcut.level = level;
+ result->wrong_shortcut.sc_level = sc_level;
+ result->wrong_shortcut.sc_segments = sc_segments;
+ result->wrong_shortcut.dissimilarity = dissimilarity;
+ return assoc_array_walk_found_wrong_shortcut;
+ }
+
+ sc_level = next_sc_level;
+ } while (sc_level < shortcut->skip_to_level);
+
+ /* The shortcut matches the leaf's index to this point. */
+ cursor = ACCESS_ONCE(shortcut->next_node);
+ if (((level ^ sc_level) & ~ASSOC_ARRAY_KEY_CHUNK_MASK) != 0) {
+ level = sc_level;
+ goto jumped;
+ } else {
+ level = sc_level;
+ goto consider_node;
+ }
+}
+
+/**
+ * assoc_array_find - Find an object by index key
+ * @array: The associative array to search.
+ * @ops: The operations to use.
+ * @index_key: The key to the object.
+ *
+ * Find an object in an associative array by walking through the internal tree
+ * to the node that should contain the object and then searching the leaves
+ * there. NULL is returned if the requested object was not found in the array.
+ *
+ * The caller must hold the RCU read lock or better.
+ */
+void *assoc_array_find(const struct assoc_array *array,
+ const struct assoc_array_ops *ops,
+ const void *index_key)
+{
+ struct assoc_array_walk_result result;
+ const struct assoc_array_node *node;
+ const struct assoc_array_ptr *ptr;
+ const void *leaf;
+ int slot;
+
+ if (assoc_array_walk(array, ops, index_key, &result) !=
+ assoc_array_walk_found_terminal_node)
+ return NULL;
+
+ node = result.terminal_node.node;
+ smp_read_barrier_depends();
+
+ /* If the target key is available to us, it's has to be pointed to by
+ * the terminal node.
+ */
+ for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+ ptr = ACCESS_ONCE(node->slots[slot]);
+ if (ptr && assoc_array_ptr_is_leaf(ptr)) {
+ /* We need a barrier between the read of the pointer
+ * and dereferencing the pointer - but only if we are
+ * actually going to dereference it.
+ */
+ leaf = assoc_array_ptr_to_leaf(ptr);
+ smp_read_barrier_depends();
+ if (ops->compare_object(leaf, index_key))
+ return (void *)leaf;
+ }
+ }
+
+ return NULL;
+}
+
+/*
+ * Destructively iterate over an associative array. The caller must prevent
+ * other simultaneous accesses.
+ */
+static void assoc_array_destroy_subtree(struct assoc_array_ptr *root,
+ const struct assoc_array_ops *ops)
+{
+ struct assoc_array_shortcut *shortcut;
+ struct assoc_array_node *node;
+ struct assoc_array_ptr *cursor, *parent = NULL;
+ int slot = -1;
+
+ pr_devel("-->%s()\n", __func__);
+
+ cursor = root;
+ if (!cursor) {
+ pr_devel("empty\n");
+ return;
+ }
+
+move_to_meta:
+ if (assoc_array_ptr_is_shortcut(cursor)) {
+ /* Descend through a shortcut */
+ pr_devel("[%d] shortcut\n", slot);
+ BUG_ON(!assoc_array_ptr_is_shortcut(cursor));
+ shortcut = assoc_array_ptr_to_shortcut(cursor);
+ BUG_ON(shortcut->back_pointer != parent);
+ BUG_ON(slot != -1 && shortcut->parent_slot != slot);
+ parent = cursor;
+ cursor = shortcut->next_node;
+ slot = -1;
+ BUG_ON(!assoc_array_ptr_is_node(cursor));
+ }
+
+ pr_devel("[%d] node\n", slot);
+ node = assoc_array_ptr_to_node(cursor);
+ BUG_ON(node->back_pointer != parent);
+ BUG_ON(slot != -1 && node->parent_slot != slot);
+ slot = 0;
+
+continue_node:
+ pr_devel("Node %p [back=%p]\n", node, node->back_pointer);
+ for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+ struct assoc_array_ptr *ptr = node->slots[slot];
+ if (!ptr)
+ continue;
+ if (assoc_array_ptr_is_meta(ptr)) {
+ parent = cursor;
+ cursor = ptr;
+ goto move_to_meta;
+ }
+
+ if (ops) {
+ pr_devel("[%d] free leaf\n", slot);
+ ops->free_object(assoc_array_ptr_to_leaf(ptr));
+ }
+ }
+
+ parent = node->back_pointer;
+ slot = node->parent_slot;
+ pr_devel("free node\n");
+ kfree(node);
+ if (!parent)
+ return; /* Done */
+
+ /* Move back up to the parent (may need to free a shortcut on
+ * the way up) */
+ if (assoc_array_ptr_is_shortcut(parent)) {
+ shortcut = assoc_array_ptr_to_shortcut(parent);
+ BUG_ON(shortcut->next_node != cursor);
+ cursor = parent;
+ parent = shortcut->back_pointer;
+ slot = shortcut->parent_slot;
+ pr_devel("free shortcut\n");
+ kfree(shortcut);
+ if (!parent)
+ return;
+
+ BUG_ON(!assoc_array_ptr_is_node(parent));
+ }
+
+ /* Ascend to next slot in parent node */
+ pr_devel("ascend to %p[%d]\n", parent, slot);
+ cursor = parent;
+ node = assoc_array_ptr_to_node(cursor);
+ slot++;
+ goto continue_node;
+}
+
+/**
+ * assoc_array_destroy - Destroy an associative array
+ * @array: The array to destroy.
+ * @ops: The operations to use.
+ *
+ * Discard all metadata and free all objects in an associative array. The
+ * array will be empty and ready to use again upon completion. This function
+ * cannot fail.
+ *
+ * The caller must prevent all other accesses whilst this takes place as no
+ * attempt is made to adjust pointers gracefully to permit RCU readlock-holding
+ * accesses to continue. On the other hand, no memory allocation is required.
+ */
+void assoc_array_destroy(struct assoc_array *array,
+ const struct assoc_array_ops *ops)
+{
+ assoc_array_destroy_subtree(array->root, ops);
+ array->root = NULL;
+}
+
+/*
+ * Handle insertion into an empty tree.
+ */
+static bool assoc_array_insert_in_empty_tree(struct assoc_array_edit *edit)
+{
+ struct assoc_array_node *new_n0;
+
+ pr_devel("-->%s()\n", __func__);
+
+ new_n0 = kzalloc(sizeof(struct assoc_array_node), GFP_KERNEL);
+ if (!new_n0)
+ return false;
+
+ edit->new_meta[0] = assoc_array_node_to_ptr(new_n0);
+ edit->leaf_p = &new_n0->slots[0];
+ edit->adjust_count_on = new_n0;
+ edit->set[0].ptr = &edit->array->root;
+ edit->set[0].to = assoc_array_node_to_ptr(new_n0);
+
+ pr_devel("<--%s() = ok [no root]\n", __func__);
+ return true;
+}
+
+/*
+ * Handle insertion into a terminal node.
+ */
+static bool assoc_array_insert_into_terminal_node(struct assoc_array_edit *edit,
+ const struct assoc_array_ops *ops,
+ const void *index_key,
+ struct assoc_array_walk_result *result)
+{
+ struct assoc_array_shortcut *shortcut, *new_s0;
+ struct assoc_array_node *node, *new_n0, *new_n1, *side;
+ struct assoc_array_ptr *ptr;
+ unsigned long dissimilarity, base_seg, blank;
+ size_t keylen;
+ bool have_meta;
+ int level, diff;
+ int slot, next_slot, free_slot, i, j;
+
+ node = result->terminal_node.node;
+ level = result->terminal_node.level;
+ edit->segment_cache[ASSOC_ARRAY_FAN_OUT] = result->terminal_node.slot;
+
+ pr_devel("-->%s()\n", __func__);
+
+ /* We arrived at a node which doesn't have an onward node or shortcut
+ * pointer that we have to follow. This means that (a) the leaf we
+ * want must go here (either by insertion or replacement) or (b) we
+ * need to split this node and insert in one of the fragments.
+ */
+ free_slot = -1;
+
+ /* Firstly, we have to check the leaves in this node to see if there's
+ * a matching one we should replace in place.
+ */
+ for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
+ ptr = node->slots[i];
+ if (!ptr) {
+ free_slot = i;
+ continue;
+ }
+ if (ops->compare_object(assoc_array_ptr_to_leaf(ptr), index_key)) {
+ pr_devel("replace in slot %d\n", i);
+ edit->leaf_p = &node->slots[i];
+ edit->dead_leaf = node->slots[i];
+ pr_devel("<--%s() = ok [replace]\n", __func__);
+ return true;
+ }
+ }
+
+ /* If there is a free slot in this node then we can just insert the
+ * leaf here.
+ */
+ if (free_slot >= 0) {
+ pr_devel("insert in free slot %d\n", free_slot);
+ edit->leaf_p = &node->slots[free_slot];
+ edit->adjust_count_on = node;
+ pr_devel("<--%s() = ok [insert]\n", __func__);
+ return true;
+ }
+
+ /* The node has no spare slots - so we're either going to have to split
+ * it or insert another node before it.
+ *
+ * Whatever, we're going to need at least two new nodes - so allocate
+ * those now. We may also need a new shortcut, but we deal with that
+ * when we need it.
+ */
+ new_n0 = kzalloc(sizeof(struct assoc_array_node), GFP_KERNEL);
+ if (!new_n0)
+ return false;
+ edit->new_meta[0] = assoc_array_node_to_ptr(new_n0);
+ new_n1 = kzalloc(sizeof(struct assoc_array_node), GFP_KERNEL);
+ if (!new_n1)
+ return false;
+ edit->new_meta[1] = assoc_array_node_to_ptr(new_n1);
+
+ /* We need to find out how similar the leaves are. */
+ pr_devel("no spare slots\n");
+ have_meta = false;
+ for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
+ ptr = node->slots[i];
+ if (assoc_array_ptr_is_meta(ptr)) {
+ edit->segment_cache[i] = 0xff;
+ have_meta = true;
+ continue;
+ }
+ base_seg = ops->get_object_key_chunk(
+ assoc_array_ptr_to_leaf(ptr), level);
+ base_seg >>= level & ASSOC_ARRAY_KEY_CHUNK_MASK;
+ edit->segment_cache[i] = base_seg & ASSOC_ARRAY_FAN_MASK;
+ }
+
+ if (have_meta) {
+ pr_devel("have meta\n");
+ goto split_node;
+ }
+
+ /* The node contains only leaves */
+ dissimilarity = 0;
+ base_seg = edit->segment_cache[0];
+ for (i = 1; i < ASSOC_ARRAY_FAN_OUT; i++)
+ dissimilarity |= edit->segment_cache[i] ^ base_seg;
+
+ pr_devel("only leaves; dissimilarity=%lx\n", dissimilarity);
+
+ if ((dissimilarity & ASSOC_ARRAY_FAN_MASK) == 0) {
+ /* The old leaves all cluster in the same slot. We will need
+ * to insert a shortcut if the new node wants to cluster with them.
+ */
+ if ((edit->segment_cache[ASSOC_ARRAY_FAN_OUT] ^ base_seg) == 0)
+ goto all_leaves_cluster_together;
+
+ /* Otherwise we can just insert a new node ahead of the old
+ * one.
+ */
+ goto present_leaves_cluster_but_not_new_leaf;
+ }
+
+split_node:
+ pr_devel("split node\n");
+
+ /* We need to split the current node; we know that the node doesn't
+ * simply contain a full set of leaves that cluster together (it
+ * contains meta pointers and/or non-clustering leaves).
+ *
+ * We need to expel at least two leaves out of a set consisting of the
+ * leaves in the node and the new leaf.
+ *
+ * We need a new node (n0) to replace the current one and a new node to
+ * take the expelled nodes (n1).
+ */
+ edit->set[0].to = assoc_array_node_to_ptr(new_n0);
+ new_n0->back_pointer = node->back_pointer;
+ new_n0->parent_slot = node->parent_slot;
+ new_n1->back_pointer = assoc_array_node_to_ptr(new_n0);
+ new_n1->parent_slot = -1; /* Need to calculate this */
+
+do_split_node:
+ pr_devel("do_split_node\n");
+
+ new_n0->nr_leaves_on_branch = node->nr_leaves_on_branch;
+ new_n1->nr_leaves_on_branch = 0;
+
+ /* Begin by finding two matching leaves. There have to be at least two
+ * that match - even if there are meta pointers - because any leaf that
+ * would match a slot with a meta pointer in it must be somewhere
+ * behind that meta pointer and cannot be here. Further, given N
+ * remaining leaf slots, we now have N+1 leaves to go in them.
+ */
+ for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
+ slot = edit->segment_cache[i];
+ if (slot != 0xff)
+ for (j = i + 1; j < ASSOC_ARRAY_FAN_OUT + 1; j++)
+ if (edit->segment_cache[j] == slot)
+ goto found_slot_for_multiple_occupancy;
+ }
+found_slot_for_multiple_occupancy:
+ pr_devel("same slot: %x %x [%02x]\n", i, j, slot);
+ BUG_ON(i >= ASSOC_ARRAY_FAN_OUT);
+ BUG_ON(j >= ASSOC_ARRAY_FAN_OUT + 1);
+ BUG_ON(slot >= ASSOC_ARRAY_FAN_OUT);
+
+ new_n1->parent_slot = slot;
+
+ /* Metadata pointers cannot change slot */
+ for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++)
+ if (assoc_array_ptr_is_meta(node->slots[i]))
+ new_n0->slots[i] = node->slots[i];
+ else
+ new_n0->slots[i] = NULL;
+ BUG_ON(new_n0->slots[slot] != NULL);
+ new_n0->slots[slot] = assoc_array_node_to_ptr(new_n1);
+
+ /* Filter the leaf pointers between the new nodes */
+ free_slot = -1;
+ next_slot = 0;
+ for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
+ if (assoc_array_ptr_is_meta(node->slots[i]))
+ continue;
+ if (edit->segment_cache[i] == slot) {
+ new_n1->slots[next_slot++] = node->slots[i];
+ new_n1->nr_leaves_on_branch++;
+ } else {
+ do {
+ free_slot++;
+ } while (new_n0->slots[free_slot] != NULL);
+ new_n0->slots[free_slot] = node->slots[i];
+ }
+ }
+
+ pr_devel("filtered: f=%x n=%x\n", free_slot, next_slot);
+
+ if (edit->segment_cache[ASSOC_ARRAY_FAN_OUT] != slot) {
+ do {
+ free_slot++;
+ } while (new_n0->slots[free_slot] != NULL);
+ edit->leaf_p = &new_n0->slots[free_slot];
+ edit->adjust_count_on = new_n0;
+ } else {
+ edit->leaf_p = &new_n1->slots[next_slot++];
+ edit->adjust_count_on = new_n1;
+ }
+
+ BUG_ON(next_slot <= 1);
+
+ edit->set_backpointers_to = assoc_array_node_to_ptr(new_n0);
+ for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
+ if (edit->segment_cache[i] == 0xff) {
+ ptr = node->slots[i];
+ BUG_ON(assoc_array_ptr_is_leaf(ptr));
+ if (assoc_array_ptr_is_node(ptr)) {
+ side = assoc_array_ptr_to_node(ptr);
+ edit->set_backpointers[i] = &side->back_pointer;
+ } else {
+ shortcut = assoc_array_ptr_to_shortcut(ptr);
+ edit->set_backpointers[i] = &shortcut->back_pointer;
+ }
+ }
+ }
+
+ ptr = node->back_pointer;
+ if (!ptr)
+ edit->set[0].ptr = &edit->array->root;
+ else if (assoc_array_ptr_is_node(ptr))
+ edit->set[0].ptr = &assoc_array_ptr_to_node(ptr)->slots[node->parent_slot];
+ else
+ edit->set[0].ptr = &assoc_array_ptr_to_shortcut(ptr)->next_node;
+ edit->excised_meta[0] = assoc_array_node_to_ptr(node);
+ pr_devel("<--%s() = ok [split node]\n", __func__);
+ return true;
+
+present_leaves_cluster_but_not_new_leaf:
+ /* All the old leaves cluster in the same slot, but the new leaf wants
+ * to go into a different slot, so we create a new node to hold the new
+ * leaf and a pointer to a new node holding all the old leaves.
+ */
+ pr_devel("present leaves cluster but not new leaf\n");
+
+ new_n0->back_pointer = node->back_pointer;
+ new_n0->parent_slot = node->parent_slot;
+ new_n0->nr_leaves_on_branch = node->nr_leaves_on_branch;
+ new_n1->back_pointer = assoc_array_node_to_ptr(new_n0);
+ new_n1->parent_slot = edit->segment_cache[0];
+ new_n1->nr_leaves_on_branch = node->nr_leaves_on_branch;
+ edit->adjust_count_on = new_n0;
+
+ for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++)
+ new_n1->slots[i] = node->slots[i];
+
+ new_n0->slots[edit->segment_cache[0]] = assoc_array_node_to_ptr(new_n0);
+ edit->leaf_p = &new_n0->slots[edit->segment_cache[ASSOC_ARRAY_FAN_OUT]];
+
+ edit->set[0].ptr = &assoc_array_ptr_to_node(node->back_pointer)->slots[node->parent_slot];
+ edit->set[0].to = assoc_array_node_to_ptr(new_n0);
+ edit->excised_meta[0] = assoc_array_node_to_ptr(node);
+ pr_devel("<--%s() = ok [insert node before]\n", __func__);
+ return true;
+
+all_leaves_cluster_together:
+ /* All the leaves, new and old, want to cluster together in this node
+ * in the same slot, so we have to replace this node with a shortcut to
+ * skip over the identical parts of the key and then place a pair of
+ * nodes, one inside the other, at the end of the shortcut and
+ * distribute the keys between them.
+ *
+ * Firstly we need to work out where the leaves start diverging as a
+ * bit position into their keys so that we know how big the shortcut
+ * needs to be.
+ *
+ * We only need to make a single pass of N of the N+1 leaves because if
+ * any keys differ between themselves at bit X then at least one of
+ * them must also differ with the base key at bit X or before.
+ */
+ pr_devel("all leaves cluster together\n");
+ diff = INT_MAX;
+ for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
+ int x = ops->diff_objects(assoc_array_ptr_to_leaf(edit->leaf),
+ assoc_array_ptr_to_leaf(node->slots[i]));
+ if (x < diff) {
+ BUG_ON(x < 0);
+ diff = x;
+ }
+ }
+ BUG_ON(diff == INT_MAX);
+ BUG_ON(diff < level + ASSOC_ARRAY_LEVEL_STEP);
+
+ keylen = round_up(diff, ASSOC_ARRAY_KEY_CHUNK_SIZE);
+ keylen >>= ASSOC_ARRAY_KEY_CHUNK_SHIFT;
+
+ new_s0 = kzalloc(sizeof(struct assoc_array_shortcut) +
+ keylen * sizeof(unsigned long), GFP_KERNEL);
+ if (!new_s0)
+ return false;
+ edit->new_meta[2] = assoc_array_shortcut_to_ptr(new_s0);
+
+ edit->set[0].to = assoc_array_shortcut_to_ptr(new_s0);
+ new_s0->back_pointer = node->back_pointer;
+ new_s0->parent_slot = node->parent_slot;
+ new_s0->next_node = assoc_array_node_to_ptr(new_n0);
+ new_n0->back_pointer = assoc_array_shortcut_to_ptr(new_s0);
+ new_n0->parent_slot = 0;
+ new_n1->back_pointer = assoc_array_node_to_ptr(new_n0);
+ new_n1->parent_slot = -1; /* Need to calculate this */
+
+ new_s0->skip_to_level = level = diff & ~ASSOC_ARRAY_LEVEL_STEP_MASK;
+ pr_devel("skip_to_level = %d [diff %d]\n", level, diff);
+ BUG_ON(level <= 0);
+
+ for (i = 0; i < keylen; i++)
+ new_s0->index_key[i] =
+ ops->get_key_chunk(index_key, i * ASSOC_ARRAY_KEY_CHUNK_SIZE);
+
+ blank = ULONG_MAX << (level & ASSOC_ARRAY_KEY_CHUNK_MASK);
+ pr_devel("blank off [%zu] %d: %lx\n", keylen - 1, level, blank);
+ new_s0->index_key[keylen - 1] &= ~blank;
+
+ /* This now reduces to a node splitting exercise for which we'll need
+ * to regenerate the disparity table.
+ */
+ for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
+ ptr = node->slots[i];
+ base_seg = ops->get_object_key_chunk(assoc_array_ptr_to_leaf(ptr),
+ level);
+ base_seg >>= level & ASSOC_ARRAY_KEY_CHUNK_MASK;
+ edit->segment_cache[i] = base_seg & ASSOC_ARRAY_FAN_MASK;
+ }
+
+ base_seg = ops->get_key_chunk(index_key, level);
+ base_seg >>= level & ASSOC_ARRAY_KEY_CHUNK_MASK;
+ edit->segment_cache[ASSOC_ARRAY_FAN_OUT] = base_seg & ASSOC_ARRAY_FAN_MASK;
+ goto do_split_node;
+}
+
+/*
+ * Handle insertion into the middle of a shortcut.
+ */
+static bool assoc_array_insert_mid_shortcut(struct assoc_array_edit *edit,
+ const struct assoc_array_ops *ops,
+ struct assoc_array_walk_result *result)
+{
+ struct assoc_array_shortcut *shortcut, *new_s0, *new_s1;
+ struct assoc_array_node *node, *new_n0, *side;
+ unsigned long sc_segments, dissimilarity, blank;
+ size_t keylen;
+ int level, sc_level, diff;
+ int sc_slot;
+
+ shortcut = result->wrong_shortcut.shortcut;
+ level = result->wrong_shortcut.level;
+ sc_level = result->wrong_shortcut.sc_level;
+ sc_segments = result->wrong_shortcut.sc_segments;
+ dissimilarity = result->wrong_shortcut.dissimilarity;
+
+ pr_devel("-->%s(ix=%d dis=%lx scix=%d)\n",
+ __func__, level, dissimilarity, sc_level);
+
+ /* We need to split a shortcut and insert a node between the two
+ * pieces. Zero-length pieces will be dispensed with entirely.
+ *
+ * First of all, we need to find out in which level the first
+ * difference was.
+ */
+ diff = __ffs(dissimilarity);
+ diff &= ~ASSOC_ARRAY_LEVEL_STEP_MASK;
+ diff += sc_level & ~ASSOC_ARRAY_KEY_CHUNK_MASK;
+ pr_devel("diff=%d\n", diff);
+
+ if (!shortcut->back_pointer) {
+ edit->set[0].ptr = &edit->array->root;
+ } else if (assoc_array_ptr_is_node(shortcut->back_pointer)) {
+ node = assoc_array_ptr_to_node(shortcut->back_pointer);
+ edit->set[0].ptr = &node->slots[shortcut->parent_slot];
+ } else {
+ BUG();
+ }
+
+ edit->excised_meta[0] = assoc_array_shortcut_to_ptr(shortcut);
+
+ /* Create a new node now since we're going to need it anyway */
+ new_n0 = kzalloc(sizeof(struct assoc_array_node), GFP_KERNEL);
+ if (!new_n0)
+ return false;
+ edit->new_meta[0] = assoc_array_node_to_ptr(new_n0);
+ edit->adjust_count_on = new_n0;
+
+ /* Insert a new shortcut before the new node if this segment isn't of
+ * zero length - otherwise we just connect the new node directly to the
+ * parent.
+ */
+ level += ASSOC_ARRAY_LEVEL_STEP;
+ if (diff > level) {
+ pr_devel("pre-shortcut %d...%d\n", level, diff);
+ keylen = round_up(diff, ASSOC_ARRAY_KEY_CHUNK_SIZE);
+ keylen >>= ASSOC_ARRAY_KEY_CHUNK_SHIFT;
+
+ new_s0 = kzalloc(sizeof(struct assoc_array_shortcut) +
+ keylen * sizeof(unsigned long), GFP_KERNEL);
+ if (!new_s0)
+ return false;
+ edit->new_meta[1] = assoc_array_shortcut_to_ptr(new_s0);
+ edit->set[0].to = assoc_array_shortcut_to_ptr(new_s0);
+ new_s0->back_pointer = shortcut->back_pointer;
+ new_s0->parent_slot = shortcut->parent_slot;
+ new_s0->next_node = assoc_array_node_to_ptr(new_n0);
+ new_s0->skip_to_level = diff;
+
+ new_n0->back_pointer = assoc_array_shortcut_to_ptr(new_s0);
+ new_n0->parent_slot = 0;
+
+ memcpy(new_s0->index_key, shortcut->index_key,
+ keylen * sizeof(unsigned long));
+
+ blank = ULONG_MAX << (diff & ASSOC_ARRAY_KEY_CHUNK_MASK);
+ pr_devel("blank off [%zu] %d: %lx\n", keylen - 1, diff, blank);
+ new_s0->index_key[keylen - 1] &= ~blank;
+ } else {
+ pr_devel("no pre-shortcut\n");
+ edit->set[0].to = assoc_array_node_to_ptr(new_n0);
+ new_n0->back_pointer = shortcut->back_pointer;
+ new_n0->parent_slot = shortcut->parent_slot;
+ }
+
+ side = assoc_array_ptr_to_node(shortcut->next_node);
+ new_n0->nr_leaves_on_branch = side->nr_leaves_on_branch;
+
+ /* We need to know which slot in the new node is going to take a
+ * metadata pointer.
+ */
+ sc_slot = sc_segments >> (diff & ASSOC_ARRAY_KEY_CHUNK_MASK);
+ sc_slot &= ASSOC_ARRAY_FAN_MASK;
+
+ pr_devel("new slot %lx >> %d -> %d\n",
+ sc_segments, diff & ASSOC_ARRAY_KEY_CHUNK_MASK, sc_slot);
+
+ /* Determine whether we need to follow the new node with a replacement
+ * for the current shortcut. We could in theory reuse the current
+ * shortcut if its parent slot number doesn't change - but that's a
+ * 1-in-16 chance so not worth expending the code upon.
+ */
+ level = diff + ASSOC_ARRAY_LEVEL_STEP;
+ if (level < shortcut->skip_to_level) {
+ pr_devel("post-shortcut %d...%d\n", level, shortcut->skip_to_level);
+ keylen = round_up(shortcut->skip_to_level, ASSOC_ARRAY_KEY_CHUNK_SIZE);
+ keylen >>= ASSOC_ARRAY_KEY_CHUNK_SHIFT;
+
+ new_s1 = kzalloc(sizeof(struct assoc_array_shortcut) +
+ keylen * sizeof(unsigned long), GFP_KERNEL);
+ if (!new_s1)
+ return false;
+ edit->new_meta[2] = assoc_array_shortcut_to_ptr(new_s1);
+
+ new_s1->back_pointer = assoc_array_node_to_ptr(new_n0);
+ new_s1->parent_slot = sc_slot;
+ new_s1->next_node = shortcut->next_node;
+ new_s1->skip_to_level = shortcut->skip_to_level;
+
+ new_n0->slots[sc_slot] = assoc_array_shortcut_to_ptr(new_s1);
+
+ memcpy(new_s1->index_key, shortcut->index_key,
+ keylen * sizeof(unsigned long));
+
+ edit->set[1].ptr = &side->back_pointer;
+ edit->set[1].to = assoc_array_shortcut_to_ptr(new_s1);
+ } else {
+ pr_devel("no post-shortcut\n");
+
+ /* We don't have to replace the pointed-to node as long as we
+ * use memory barriers to make sure the parent slot number is
+ * changed before the back pointer (the parent slot number is
+ * irrelevant to the old parent shortcut).
+ */
+ new_n0->slots[sc_slot] = shortcut->next_node;
+ edit->set_parent_slot[0].p = &side->parent_slot;
+ edit->set_parent_slot[0].to = sc_slot;
+ edit->set[1].ptr = &side->back_pointer;
+ edit->set[1].to = assoc_array_node_to_ptr(new_n0);
+ }
+
+ /* Install the new leaf in a spare slot in the new node. */
+ if (sc_slot == 0)
+ edit->leaf_p = &new_n0->slots[1];
+ else
+ edit->leaf_p = &new_n0->slots[0];
+
+ pr_devel("<--%s() = ok [split shortcut]\n", __func__);
+ return edit;
+}
+
+/**
+ * assoc_array_insert - Script insertion of an object into an associative array
+ * @array: The array to insert into.
+ * @ops: The operations to use.
+ * @index_key: The key to insert at.
+ * @object: The object to insert.
+ *
+ * Precalculate and preallocate a script for the insertion or replacement of an
+ * object in an associative array. This results in an edit script that can
+ * either be applied or cancelled.
+ *
+ * The function returns a pointer to an edit script or -ENOMEM.
+ *
+ * The caller should lock against other modifications and must continue to hold
+ * the lock until assoc_array_apply_edit() has been called.
+ *
+ * Accesses to the tree may take place concurrently with this function,
+ * provided they hold the RCU read lock.
+ */
+struct assoc_array_edit *assoc_array_insert(struct assoc_array *array,
+ const struct assoc_array_ops *ops,
+ const void *index_key,
+ void *object)
+{
+ struct assoc_array_walk_result result;
+ struct assoc_array_edit *edit;
+
+ pr_devel("-->%s()\n", __func__);
+
+ /* The leaf pointer we're given must not have the bottom bit set as we
+ * use those for type-marking the pointer. NULL pointers are also not
+ * allowed as they indicate an empty slot but we have to allow them
+ * here as they can be updated later.
+ */
+ BUG_ON(assoc_array_ptr_is_meta(object));
+
+ edit = kzalloc(sizeof(struct assoc_array_edit), GFP_KERNEL);
+ if (!edit)
+ return ERR_PTR(-ENOMEM);
+ edit->array = array;
+ edit->ops = ops;
+ edit->leaf = assoc_array_leaf_to_ptr(object);
+ edit->adjust_count_by = 1;
+
+ switch (assoc_array_walk(array, ops, index_key, &result)) {
+ case assoc_array_walk_tree_empty:
+ /* Allocate a root node if there isn't one yet */
+ if (!assoc_array_insert_in_empty_tree(edit))
+ goto enomem;
+ return edit;
+
+ case assoc_array_walk_found_terminal_node:
+ /* We found a node that doesn't have a node/shortcut pointer in
+ * the slot corresponding to the index key that we have to
+ * follow.
+ */
+ if (!assoc_array_insert_into_terminal_node(edit, ops, index_key,
+ &result))
+ goto enomem;
+ return edit;
+
+ case assoc_array_walk_found_wrong_shortcut:
+ /* We found a shortcut that didn't match our key in a slot we
+ * needed to follow.
+ */
+ if (!assoc_array_insert_mid_shortcut(edit, ops, &result))
+ goto enomem;
+ return edit;
+ }
+
+enomem:
+ /* Clean up after an out of memory error */
+ pr_devel("enomem\n");
+ assoc_array_cancel_edit(edit);
+ return ERR_PTR(-ENOMEM);
+}
+
+/**
+ * assoc_array_insert_set_object - Set the new object pointer in an edit script
+ * @edit: The edit script to modify.
+ * @object: The object pointer to set.
+ *
+ * Change the object to be inserted in an edit script. The object pointed to
+ * by the old object is not freed. This must be done prior to applying the
+ * script.
+ */
+void assoc_array_insert_set_object(struct assoc_array_edit *edit, void *object)
+{
+ BUG_ON(!object);
+ edit->leaf = assoc_array_leaf_to_ptr(object);
+}
+
+struct assoc_array_delete_collapse_context {
+ struct assoc_array_node *node;
+ const void *skip_leaf;
+ int slot;
+};
+
+/*
+ * Subtree collapse to node iterator.
+ */
+static int assoc_array_delete_collapse_iterator(const void *leaf,
+ void *iterator_data)
+{
+ struct assoc_array_delete_collapse_context *collapse = iterator_data;
+
+ if (leaf == collapse->skip_leaf)
+ return 0;
+
+ BUG_ON(collapse->slot >= ASSOC_ARRAY_FAN_OUT);
+
+ collapse->node->slots[collapse->slot++] = assoc_array_leaf_to_ptr(leaf);
+ return 0;
+}
+
+/**
+ * assoc_array_delete - Script deletion of an object from an associative array
+ * @array: The array to search.
+ * @ops: The operations to use.
+ * @index_key: The key to the object.
+ *
+ * Precalculate and preallocate a script for the deletion of an object from an
+ * associative array. This results in an edit script that can either be
+ * applied or cancelled.
+ *
+ * The function returns a pointer to an edit script if the object was found,
+ * NULL if the object was not found or -ENOMEM.
+ *
+ * The caller should lock against other modifications and must continue to hold
+ * the lock until assoc_array_apply_edit() has been called.
+ *
+ * Accesses to the tree may take place concurrently with this function,
+ * provided they hold the RCU read lock.
+ */
+struct assoc_array_edit *assoc_array_delete(struct assoc_array *array,
+ const struct assoc_array_ops *ops,
+ const void *index_key)
+{
+ struct assoc_array_delete_collapse_context collapse;
+ struct assoc_array_walk_result result;
+ struct assoc_array_node *node, *new_n0;
+ struct assoc_array_edit *edit;
+ struct assoc_array_ptr *ptr;
+ bool has_meta;
+ int slot, i;
+
+ pr_devel("-->%s()\n", __func__);
+
+ edit = kzalloc(sizeof(struct assoc_array_edit), GFP_KERNEL);
+ if (!edit)
+ return ERR_PTR(-ENOMEM);
+ edit->array = array;
+ edit->ops = ops;
+ edit->adjust_count_by = -1;
+
+ switch (assoc_array_walk(array, ops, index_key, &result)) {
+ case assoc_array_walk_found_terminal_node:
+ /* We found a node that should contain the leaf we've been
+ * asked to remove - *if* it's in the tree.
+ */
+ pr_devel("terminal_node\n");
+ node = result.terminal_node.node;
+
+ for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+ ptr = node->slots[slot];
+ if (ptr &&
+ assoc_array_ptr_is_leaf(ptr) &&
+ ops->compare_object(assoc_array_ptr_to_leaf(ptr),
+ index_key))
+ goto found_leaf;
+ }
+ case assoc_array_walk_tree_empty:
+ case assoc_array_walk_found_wrong_shortcut:
+ default:
+ assoc_array_cancel_edit(edit);
+ pr_devel("not found\n");
+ return NULL;
+ }
+
+found_leaf:
+ BUG_ON(array->nr_leaves_on_tree <= 0);
+
+ /* In the simplest form of deletion we just clear the slot and release
+ * the leaf after a suitable interval.
+ */
+ edit->dead_leaf = node->slots[slot];
+ edit->set[0].ptr = &node->slots[slot];
+ edit->set[0].to = NULL;
+ edit->adjust_count_on = node;
+
+ /* If that concludes erasure of the last leaf, then delete the entire
+ * internal array.
+ */
+ if (array->nr_leaves_on_tree == 1) {
+ edit->set[1].ptr = &array->root;
+ edit->set[1].to = NULL;
+ edit->adjust_count_on = NULL;
+ edit->excised_subtree = array->root;
+ pr_devel("all gone\n");
+ return edit;
+ }
+
+ /* However, we'd also like to clear up some metadata blocks if we
+ * possibly can.
+ *
+ * We go for a simple algorithm of: if this node has FAN_OUT or fewer
+ * leaves in it, then attempt to collapse it - and attempt to
+ * recursively collapse up the tree.
+ *
+ * We could also try and collapse in partially filled subtrees to take
+ * up space in this node.
+ */
+ if (node->nr_leaves_on_branch <= ASSOC_ARRAY_FAN_OUT + 1) {
+ struct assoc_array_node *parent, *grandparent;
+ struct assoc_array_ptr *ptr;
+
+ /* First of all, we need to know if this node has metadata so
+ * that we don't try collapsing if all the leaves are already
+ * here.
+ */
+ has_meta = false;
+ for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
+ ptr = node->slots[i];
+ if (assoc_array_ptr_is_meta(ptr)) {
+ has_meta = true;
+ break;
+ }
+ }
+
+ pr_devel("leaves: %ld [m=%d]\n",
+ node->nr_leaves_on_branch - 1, has_meta);
+
+ /* Look further up the tree to see if we can collapse this node
+ * into a more proximal node too.
+ */
+ parent = node;
+ collapse_up:
+ pr_devel("collapse subtree: %ld\n", parent->nr_leaves_on_branch);
+
+ ptr = parent->back_pointer;
+ if (!ptr)
+ goto do_collapse;
+ if (assoc_array_ptr_is_shortcut(ptr)) {
+ struct assoc_array_shortcut *s = assoc_array_ptr_to_shortcut(ptr);
+ ptr = s->back_pointer;
+ if (!ptr)
+ goto do_collapse;
+ }
+
+ grandparent = assoc_array_ptr_to_node(ptr);
+ if (grandparent->nr_leaves_on_branch <= ASSOC_ARRAY_FAN_OUT + 1) {
+ parent = grandparent;
+ goto collapse_up;
+ }
+
+ do_collapse:
+ /* There's no point collapsing if the original node has no meta
+ * pointers to discard and if we didn't merge into one of that
+ * node's ancestry.
+ */
+ if (has_meta || parent != node) {
+ node = parent;
+
+ /* Create a new node to collapse into */
+ new_n0 = kzalloc(sizeof(struct assoc_array_node), GFP_KERNEL);
+ if (!new_n0)
+ goto enomem;
+ edit->new_meta[0] = assoc_array_node_to_ptr(new_n0);
+
+ new_n0->back_pointer = node->back_pointer;
+ new_n0->parent_slot = node->parent_slot;
+ new_n0->nr_leaves_on_branch = node->nr_leaves_on_branch;
+ edit->adjust_count_on = new_n0;
+
+ collapse.node = new_n0;
+ collapse.skip_leaf = assoc_array_ptr_to_leaf(edit->dead_leaf);
+ collapse.slot = 0;
+ assoc_array_subtree_iterate(assoc_array_node_to_ptr(node),
+ node->back_pointer,
+ assoc_array_delete_collapse_iterator,
+ &collapse);
+ pr_devel("collapsed %d,%lu\n", collapse.slot, new_n0->nr_leaves_on_branch);
+ BUG_ON(collapse.slot != new_n0->nr_leaves_on_branch - 1);
+
+ if (!node->back_pointer) {
+ edit->set[1].ptr = &array->root;
+ } else if (assoc_array_ptr_is_leaf(node->back_pointer)) {
+ BUG();
+ } else if (assoc_array_ptr_is_node(node->back_pointer)) {
+ struct assoc_array_node *p =
+ assoc_array_ptr_to_node(node->back_pointer);
+ edit->set[1].ptr = &p->slots[node->parent_slot];
+ } else if (assoc_array_ptr_is_shortcut(node->back_pointer)) {
+ struct assoc_array_shortcut *s =
+ assoc_array_ptr_to_shortcut(node->back_pointer);
+ edit->set[1].ptr = &s->next_node;
+ }
+ edit->set[1].to = assoc_array_node_to_ptr(new_n0);
+ edit->excised_subtree = assoc_array_node_to_ptr(node);
+ }
+ }
+
+ return edit;
+
+enomem:
+ /* Clean up after an out of memory error */
+ pr_devel("enomem\n");
+ assoc_array_cancel_edit(edit);
+ return ERR_PTR(-ENOMEM);
+}
+
+/**
+ * assoc_array_clear - Script deletion of all objects from an associative array
+ * @array: The array to clear.
+ * @ops: The operations to use.
+ *
+ * Precalculate and preallocate a script for the deletion of all the objects
+ * from an associative array. This results in an edit script that can either
+ * be applied or cancelled.
+ *
+ * The function returns a pointer to an edit script if there are objects to be
+ * deleted, NULL if there are no objects in the array or -ENOMEM.
+ *
+ * The caller should lock against other modifications and must continue to hold
+ * the lock until assoc_array_apply_edit() has been called.
+ *
+ * Accesses to the tree may take place concurrently with this function,
+ * provided they hold the RCU read lock.
+ */
+struct assoc_array_edit *assoc_array_clear(struct assoc_array *array,
+ const struct assoc_array_ops *ops)
+{
+ struct assoc_array_edit *edit;
+
+ pr_devel("-->%s()\n", __func__);
+
+ if (!array->root)
+ return NULL;
+
+ edit = kzalloc(sizeof(struct assoc_array_edit), GFP_KERNEL);
+ if (!edit)
+ return ERR_PTR(-ENOMEM);
+ edit->array = array;
+ edit->ops = ops;
+ edit->set[1].ptr = &array->root;
+ edit->set[1].to = NULL;
+ edit->excised_subtree = array->root;
+ edit->ops_for_excised_subtree = ops;
+ pr_devel("all gone\n");
+ return edit;
+}
+
+/*
+ * Handle the deferred destruction after an applied edit.
+ */
+static void assoc_array_rcu_cleanup(struct rcu_head *head)
+{
+ struct assoc_array_edit *edit =
+ container_of(head, struct assoc_array_edit, rcu);
+ int i;
+
+ pr_devel("-->%s()\n", __func__);
+
+ if (edit->dead_leaf)
+ edit->ops->free_object(assoc_array_ptr_to_leaf(edit->dead_leaf));
+ for (i = 0; i < ARRAY_SIZE(edit->excised_meta); i++)
+ if (edit->excised_meta[i])
+ kfree(assoc_array_ptr_to_node(edit->excised_meta[i]));
+
+ if (edit->excised_subtree) {
+ BUG_ON(assoc_array_ptr_is_leaf(edit->excised_subtree));
+ if (assoc_array_ptr_is_node(edit->excised_subtree)) {
+ struct assoc_array_node *n =
+ assoc_array_ptr_to_node(edit->excised_subtree);
+ n->back_pointer = NULL;
+ } else {
+ struct assoc_array_shortcut *s =
+ assoc_array_ptr_to_shortcut(edit->excised_subtree);
+ s->back_pointer = NULL;
+ }
+ assoc_array_destroy_subtree(edit->excised_subtree,
+ edit->ops_for_excised_subtree);
+ }
+
+ kfree(edit);
+}
+
+/**
+ * assoc_array_apply_edit - Apply an edit script to an associative array
+ * @edit: The script to apply.
+ *
+ * Apply an edit script to an associative array to effect an insertion,
+ * deletion or clearance. As the edit script includes preallocated memory,
+ * this is guaranteed not to fail.
+ *
+ * The edit script, dead objects and dead metadata will be scheduled for
+ * destruction after an RCU grace period to permit those doing read-only
+ * accesses on the array to continue to do so under the RCU read lock whilst
+ * the edit is taking place.
+ */
+void assoc_array_apply_edit(struct assoc_array_edit *edit)
+{
+ struct assoc_array_shortcut *shortcut;
+ struct assoc_array_node *node;
+ struct assoc_array_ptr *ptr;
+ int i;
+
+ pr_devel("-->%s()\n", __func__);
+
+ smp_wmb();
+ if (edit->leaf_p)
+ *edit->leaf_p = edit->leaf;
+
+ smp_wmb();
+ for (i = 0; i < ARRAY_SIZE(edit->set_parent_slot); i++)
+ if (edit->set_parent_slot[i].p)
+ *edit->set_parent_slot[i].p = edit->set_parent_slot[i].to;
+
+ smp_wmb();
+ for (i = 0; i < ARRAY_SIZE(edit->set_backpointers); i++)
+ if (edit->set_backpointers[i])
+ *edit->set_backpointers[i] = edit->set_backpointers_to;
+
+ smp_wmb();
+ for (i = 0; i < ARRAY_SIZE(edit->set); i++)
+ if (edit->set[i].ptr)
+ *edit->set[i].ptr = edit->set[i].to;
+
+ if (edit->array->root == NULL) {
+ edit->array->nr_leaves_on_tree = 0;
+ } else if (edit->adjust_count_on) {
+ node = edit->adjust_count_on;
+ for (;;) {
+ node->nr_leaves_on_branch += edit->adjust_count_by;
+
+ ptr = node->back_pointer;
+ if (!ptr)
+ break;
+ if (assoc_array_ptr_is_shortcut(ptr)) {
+ shortcut = assoc_array_ptr_to_shortcut(ptr);
+ ptr = shortcut->back_pointer;
+ if (!ptr)
+ break;
+ }
+ BUG_ON(!assoc_array_ptr_is_node(ptr));
+ node = assoc_array_ptr_to_node(ptr);
+ }
+
+ edit->array->nr_leaves_on_tree += edit->adjust_count_by;
+ }
+
+ call_rcu(&edit->rcu, assoc_array_rcu_cleanup);
+}
+
+/**
+ * assoc_array_cancel_edit - Discard an edit script.
+ * @edit: The script to discard.
+ *
+ * Free an edit script and all the preallocated data it holds without making
+ * any changes to the associative array it was intended for.
+ *
+ * NOTE! In the case of an insertion script, this does _not_ release the leaf
+ * that was to be inserted. That is left to the caller.
+ */
+void assoc_array_cancel_edit(struct assoc_array_edit *edit)
+{
+ struct assoc_array_ptr *ptr;
+ int i;
+
+ pr_devel("-->%s()\n", __func__);
+
+ /* Clean up after an out of memory error */
+ for (i = 0; i < ARRAY_SIZE(edit->new_meta); i++) {
+ ptr = edit->new_meta[i];
+ if (ptr) {
+ if (assoc_array_ptr_is_node(ptr))
+ kfree(assoc_array_ptr_to_node(ptr));
+ else
+ kfree(assoc_array_ptr_to_shortcut(ptr));
+ }
+ }
+ kfree(edit);
+}
+
+/**
+ * assoc_array_gc - Garbage collect an associative array.
+ * @array: The array to clean.
+ * @ops: The operations to use.
+ * @iterator: A callback function to pass judgement on each object.
+ * @iterator_data: Private data for the callback function.
+ *
+ * Collect garbage from an associative array and pack down the internal tree to
+ * save memory.
+ *
+ * The iterator function is asked to pass judgement upon each object in the
+ * array. If it returns false, the object is discard and if it returns true,
+ * the object is kept. If it returns true, it must increment the object's
+ * usage count (or whatever it needs to do to retain it) before returning.
+ *
+ * This function returns 0 if successful or -ENOMEM if out of memory. In the
+ * latter case, the array is not changed.
+ *
+ * The caller should lock against other modifications and must continue to hold
+ * the lock until assoc_array_apply_edit() has been called.
+ *
+ * Accesses to the tree may take place concurrently with this function,
+ * provided they hold the RCU read lock.
+ */
+int assoc_array_gc(struct assoc_array *array,
+ const struct assoc_array_ops *ops,
+ bool (*iterator)(void *object, void *iterator_data),
+ void *iterator_data)
+{
+ struct assoc_array_shortcut *shortcut, *new_s;
+ struct assoc_array_node *node, *new_n;
+ struct assoc_array_edit *edit;
+ struct assoc_array_ptr *cursor, *ptr;
+ struct assoc_array_ptr *new_root, *new_parent, **new_ptr_pp;
+ unsigned long nr_leaves_on_tree;
+ int keylen, slot, nr_free, next_slot, i;
+
+ pr_devel("-->%s()\n", __func__);
+
+ if (!array->root)
+ return 0;
+
+ edit = kzalloc(sizeof(struct assoc_array_edit), GFP_KERNEL);
+ if (!edit)
+ return -ENOMEM;
+ edit->array = array;
+ edit->ops = ops;
+ edit->ops_for_excised_subtree = ops;
+ edit->set[0].ptr = &array->root;
+ edit->excised_subtree = array->root;
+
+ new_root = new_parent = NULL;
+ new_ptr_pp = &new_root;
+ cursor = array->root;
+
+descend:
+ /* If this point is a shortcut, then we need to duplicate it and
+ * advance the target cursor.
+ */
+ if (assoc_array_ptr_is_shortcut(cursor)) {
+ shortcut = assoc_array_ptr_to_shortcut(cursor);
+ keylen = round_up(shortcut->skip_to_level, ASSOC_ARRAY_KEY_CHUNK_SIZE);
+ keylen >>= ASSOC_ARRAY_KEY_CHUNK_SHIFT;
+ new_s = kmalloc(sizeof(struct assoc_array_shortcut) +
+ keylen * sizeof(unsigned long), GFP_KERNEL);
+ if (!new_s)
+ goto enomem;
+ pr_devel("dup shortcut %p -> %p\n", shortcut, new_s);
+ memcpy(new_s, shortcut, (sizeof(struct assoc_array_shortcut) +
+ keylen * sizeof(unsigned long)));
+ new_s->back_pointer = new_parent;
+ new_s->parent_slot = shortcut->parent_slot;
+ *new_ptr_pp = new_parent = assoc_array_shortcut_to_ptr(new_s);
+ new_ptr_pp = &new_s->next_node;
+ cursor = shortcut->next_node;
+ }
+
+ /* Duplicate the node at this position */
+ node = assoc_array_ptr_to_node(cursor);
+ new_n = kzalloc(sizeof(struct assoc_array_node), GFP_KERNEL);
+ if (!new_n)
+ goto enomem;
+ pr_devel("dup node %p -> %p\n", node, new_n);
+ new_n->back_pointer = new_parent;
+ new_n->parent_slot = node->parent_slot;
+ *new_ptr_pp = new_parent = assoc_array_node_to_ptr(new_n);
+ new_ptr_pp = NULL;
+ slot = 0;
+
+continue_node:
+ /* Filter across any leaves and gc any subtrees */
+ for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+ ptr = node->slots[slot];
+ if (!ptr)
+ continue;
+
+ if (assoc_array_ptr_is_leaf(ptr)) {
+ if (iterator(assoc_array_ptr_to_leaf(ptr),
+ iterator_data))
+ /* The iterator will have done any reference
+ * counting on the object for us.
+ */
+ new_n->slots[slot] = ptr;
+ continue;
+ }
+
+ new_ptr_pp = &new_n->slots[slot];
+ cursor = ptr;
+ goto descend;
+ }
+
+ pr_devel("-- compress node %p --\n", new_n);
+
+ /* Count up the number of empty slots in this node and work out the
+ * subtree leaf count.
+ */
+ new_n->nr_leaves_on_branch = 0;
+ nr_free = 0;
+ for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+ ptr = new_n->slots[slot];
+ if (!ptr)
+ nr_free++;
+ else if (assoc_array_ptr_is_leaf(ptr))
+ new_n->nr_leaves_on_branch++;
+ }
+ pr_devel("free=%d, leaves=%lu\n", nr_free, new_n->nr_leaves_on_branch);
+
+ /* See what we can fold in */
+ next_slot = 0;
+ for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+ struct assoc_array_shortcut *s;
+ struct assoc_array_node *child;
+
+ ptr = new_n->slots[slot];
+ if (!ptr || assoc_array_ptr_is_leaf(ptr))
+ continue;
+
+ s = NULL;
+ if (assoc_array_ptr_is_shortcut(ptr)) {
+ s = assoc_array_ptr_to_shortcut(ptr);
+ ptr = s->next_node;
+ }
+
+ child = assoc_array_ptr_to_node(ptr);
+ new_n->nr_leaves_on_branch += child->nr_leaves_on_branch;
+
+ if (child->nr_leaves_on_branch <= nr_free + 1) {
+ /* Fold the child node into this one */
+ pr_devel("[%d] fold node %lu/%d [nx %d]\n",
+ slot, child->nr_leaves_on_branch, nr_free + 1,
+ next_slot);
+
+ /* We would already have reaped an intervening shortcut
+ * on the way back up the tree.
+ */
+ BUG_ON(s);
+
+ new_n->slots[slot] = NULL;
+ nr_free++;
+ if (slot < next_slot)
+ next_slot = slot;
+ for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
+ struct assoc_array_ptr *p = child->slots[i];
+ if (!p)
+ continue;
+ BUG_ON(assoc_array_ptr_is_meta(p));
+ while (new_n->slots[next_slot])
+ next_slot++;
+ BUG_ON(next_slot >= ASSOC_ARRAY_FAN_OUT);
+ new_n->slots[next_slot++] = p;
+ nr_free--;
+ }
+ kfree(child);
+ } else {
+ pr_devel("[%d] retain node %lu/%d [nx %d]\n",
+ slot, child->nr_leaves_on_branch, nr_free + 1,
+ next_slot);
+ }
+ }
+
+ pr_devel("after: %lu\n", new_n->nr_leaves_on_branch);
+
+ nr_leaves_on_tree = new_n->nr_leaves_on_branch;
+
+ /* Excise this node if it is singly occupied by a shortcut */
+ if (nr_free == ASSOC_ARRAY_FAN_OUT - 1) {
+ for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++)
+ if ((ptr = new_n->slots[slot]))
+ break;
+
+ if (assoc_array_ptr_is_meta(ptr) &&
+ assoc_array_ptr_is_shortcut(ptr)) {
+ pr_devel("excise node %p with 1 shortcut\n", new_n);
+ new_s = assoc_array_ptr_to_shortcut(ptr);
+ new_parent = new_n->back_pointer;
+ slot = new_n->parent_slot;
+ kfree(new_n);
+ if (!new_parent) {
+ new_s->back_pointer = NULL;
+ new_s->parent_slot = 0;
+ new_root = ptr;
+ goto gc_complete;
+ }
+
+ if (assoc_array_ptr_is_shortcut(new_parent)) {
+ /* We can discard any preceding shortcut also */
+ struct assoc_array_shortcut *s =
+ assoc_array_ptr_to_shortcut(new_parent);
+
+ pr_devel("excise preceding shortcut\n");
+
+ new_parent = new_s->back_pointer = s->back_pointer;
+ slot = new_s->parent_slot = s->parent_slot;
+ kfree(s);
+ if (!new_parent) {
+ new_s->back_pointer = NULL;
+ new_s->parent_slot = 0;
+ new_root = ptr;
+ goto gc_complete;
+ }
+ }
+
+ new_s->back_pointer = new_parent;
+ new_s->parent_slot = slot;
+ new_n = assoc_array_ptr_to_node(new_parent);
+ new_n->slots[slot] = ptr;
+ goto ascend_old_tree;
+ }
+ }
+
+ /* Excise any shortcuts we might encounter that point to nodes that
+ * only contain leaves.
+ */
+ ptr = new_n->back_pointer;
+ if (!ptr)
+ goto gc_complete;
+
+ if (assoc_array_ptr_is_shortcut(ptr)) {
+ new_s = assoc_array_ptr_to_shortcut(ptr);
+ new_parent = new_s->back_pointer;
+ slot = new_s->parent_slot;
+
+ if (new_n->nr_leaves_on_branch <= ASSOC_ARRAY_FAN_OUT) {
+ struct assoc_array_node *n;
+
+ pr_devel("excise shortcut\n");
+ new_n->back_pointer = new_parent;
+ new_n->parent_slot = slot;
+ kfree(new_s);
+ if (!new_parent) {
+ new_root = assoc_array_node_to_ptr(new_n);
+ goto gc_complete;
+ }
+
+ n = assoc_array_ptr_to_node(new_parent);
+ n->slots[slot] = assoc_array_node_to_ptr(new_n);
+ }
+ } else {
+ new_parent = ptr;
+ }
+ new_n = assoc_array_ptr_to_node(new_parent);
+
+ascend_old_tree:
+ ptr = node->back_pointer;
+ if (assoc_array_ptr_is_shortcut(ptr)) {
+ shortcut = assoc_array_ptr_to_shortcut(ptr);
+ slot = shortcut->parent_slot;
+ cursor = shortcut->back_pointer;
+ } else {
+ slot = node->parent_slot;
+ cursor = ptr;
+ }
+ BUG_ON(!ptr);
+ node = assoc_array_ptr_to_node(cursor);
+ slot++;
+ goto continue_node;
+
+gc_complete:
+ edit->set[0].to = new_root;
+ assoc_array_apply_edit(edit);
+ edit->array->nr_leaves_on_tree = nr_leaves_on_tree;
+ return 0;
+
+enomem:
+ pr_devel("enomem\n");
+ assoc_array_destroy_subtree(new_root, edit->ops);
+ kfree(edit);
+ return -ENOMEM;
+}
kfree(a);
}
EXPORT_SYMBOL_GPL(mpi_free);
+
+MODULE_DESCRIPTION("Multiprecision maths library");
+MODULE_LICENSE("GPL");
min(pool->nr_free, pool->percpu_batch_size));
}
-static inline unsigned alloc_local_tag(struct percpu_ida *pool,
- struct percpu_ida_cpu *tags)
+static inline unsigned alloc_local_tag(struct percpu_ida_cpu *tags)
{
int tag = -ENOSPC;
tags = this_cpu_ptr(pool->tag_cpu);
/* Fastpath */
- tag = alloc_local_tag(pool, tags);
+ tag = alloc_local_tag(tags);
if (likely(tag >= 0)) {
local_irq_restore(flags);
return tag;
return 0;
}
-static void copy_gigantic_page(struct page *dst, struct page *src)
-{
- int i;
- struct hstate *h = page_hstate(src);
- struct page *dst_base = dst;
- struct page *src_base = src;
-
- for (i = 0; i < pages_per_huge_page(h); ) {
- cond_resched();
- copy_highpage(dst, src);
-
- i++;
- dst = mem_map_next(dst, dst_base, i);
- src = mem_map_next(src, src_base, i);
- }
-}
-
-void copy_huge_page(struct page *dst, struct page *src)
-{
- int i;
- struct hstate *h = page_hstate(src);
-
- if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) {
- copy_gigantic_page(dst, src);
- return;
- }
-
- might_sleep();
- for (i = 0; i < pages_per_huge_page(h); i++) {
- cond_resched();
- copy_highpage(dst + i, src + i);
- }
-}
-
static void enqueue_huge_page(struct hstate *h, struct page *page)
{
int nid = page_to_nid(page);
}
EXPORT_SYMBOL_GPL(PageHuge);
+/*
+ * PageHeadHuge() only returns true for hugetlbfs head page, but not for
+ * normal or transparent huge pages.
+ */
+int PageHeadHuge(struct page *page_head)
+{
+ compound_page_dtor *dtor;
+
+ if (!PageHead(page_head))
+ return 0;
+
+ dtor = get_compound_page_dtor(page_head);
+
+ return dtor == free_huge_page;
+}
+EXPORT_SYMBOL_GPL(PageHeadHuge);
+
pgoff_t __basepage_index(struct page *page)
{
struct page *page_head = compound_head(page);
return;
}
- p += snprintf(p, maxlen, policy_modes[mode]);
+ p += snprintf(p, maxlen, "%s", policy_modes[mode]);
if (flags & MPOL_MODE_FLAGS) {
p += snprintf(p, buffer + maxlen - p, "=");
return MIGRATEPAGE_SUCCESS;
}
+/*
+ * Gigantic pages are so large that we do not guarantee that page++ pointer
+ * arithmetic will work across the entire page. We need something more
+ * specialized.
+ */
+static void __copy_gigantic_page(struct page *dst, struct page *src,
+ int nr_pages)
+{
+ int i;
+ struct page *dst_base = dst;
+ struct page *src_base = src;
+
+ for (i = 0; i < nr_pages; ) {
+ cond_resched();
+ copy_highpage(dst, src);
+
+ i++;
+ dst = mem_map_next(dst, dst_base, i);
+ src = mem_map_next(src, src_base, i);
+ }
+}
+
+static void copy_huge_page(struct page *dst, struct page *src)
+{
+ int i;
+ int nr_pages;
+
+ if (PageHuge(src)) {
+ /* hugetlbfs page */
+ struct hstate *h = page_hstate(src);
+ nr_pages = pages_per_huge_page(h);
+
+ if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) {
+ __copy_gigantic_page(dst, src, nr_pages);
+ return;
+ }
+ } else {
+ /* thp page */
+ BUG_ON(!PageTransHuge(src));
+ nr_pages = hpage_nr_pages(src);
+ }
+
+ for (i = 0; i < nr_pages; i++) {
+ cond_resched();
+ copy_highpage(dst + i, src + i);
+ }
+}
+
/*
* Copy the page to its new location
*/
*/
static bool pfmemalloc_active __read_mostly;
-/*
- * kmem_bufctl_t:
- *
- * Bufctl's are used for linking objs within a slab
- * linked offsets.
- *
- * This implementation relies on "struct page" for locating the cache &
- * slab an object belongs to.
- * This allows the bufctl structure to be small (one int), but limits
- * the number of objects a slab (not a cache) can contain when off-slab
- * bufctls are used. The limit is the size of the largest general cache
- * that does not use off-slab slabs.
- * For 32bit archs with 4 kB pages, is this 56.
- * This is not serious, as it is only for large objects, when it is unwise
- * to have too many per slab.
- * Note: This limit can be raised by introducing a general cache whose size
- * is less than 512 (PAGE_SIZE<<3), but greater than 256.
- */
-
-typedef unsigned int kmem_bufctl_t;
-#define BUFCTL_END (((kmem_bufctl_t)(~0U))-0)
-#define BUFCTL_FREE (((kmem_bufctl_t)(~0U))-1)
-#define BUFCTL_ACTIVE (((kmem_bufctl_t)(~0U))-2)
-#define SLAB_LIMIT (((kmem_bufctl_t)(~0U))-3)
-
-/*
- * struct slab_rcu
- *
- * slab_destroy on a SLAB_DESTROY_BY_RCU cache uses this structure to
- * arrange for kmem_freepages to be called via RCU. This is useful if
- * we need to approach a kernel structure obliquely, from its address
- * obtained without the usual locking. We can lock the structure to
- * stabilize it and check it's still at the given address, only if we
- * can be sure that the memory has not been meanwhile reused for some
- * other kind of object (which our subsystem's lock might corrupt).
- *
- * rcu_read_lock before reading the address, then rcu_read_unlock after
- * taking the spinlock within the structure expected at that address.
- */
-struct slab_rcu {
- struct rcu_head head;
- struct kmem_cache *cachep;
- void *addr;
-};
-
-/*
- * struct slab
- *
- * Manages the objs in a slab. Placed either at the beginning of mem allocated
- * for a slab, or allocated from an general cache.
- * Slabs are chained into three list: fully used, partial, fully free slabs.
- */
-struct slab {
- union {
- struct {
- struct list_head list;
- unsigned long colouroff;
- void *s_mem; /* including colour offset */
- unsigned int inuse; /* num of objs active in slab */
- kmem_bufctl_t free;
- unsigned short nodeid;
- };
- struct slab_rcu __slab_cover_slab_rcu;
- };
-};
-
/*
* struct array_cache
*
return page->slab_cache;
}
-static inline struct slab *virt_to_slab(const void *obj)
-{
- struct page *page = virt_to_head_page(obj);
-
- VM_BUG_ON(!PageSlab(page));
- return page->slab_page;
-}
-
-static inline void *index_to_obj(struct kmem_cache *cache, struct slab *slab,
+static inline void *index_to_obj(struct kmem_cache *cache, struct page *page,
unsigned int idx)
{
- return slab->s_mem + cache->size * idx;
+ return page->s_mem + cache->size * idx;
}
/*
* reciprocal_divide(offset, cache->reciprocal_buffer_size)
*/
static inline unsigned int obj_to_index(const struct kmem_cache *cache,
- const struct slab *slab, void *obj)
+ const struct page *page, void *obj)
{
- u32 offset = (obj - slab->s_mem);
+ u32 offset = (obj - page->s_mem);
return reciprocal_divide(offset, cache->reciprocal_buffer_size);
}
static size_t slab_mgmt_size(size_t nr_objs, size_t align)
{
- return ALIGN(sizeof(struct slab)+nr_objs*sizeof(kmem_bufctl_t), align);
+ return ALIGN(nr_objs * sizeof(unsigned int), align);
}
/*
* on it. For the latter case, the memory allocated for a
* slab is used for:
*
- * - The struct slab
- * - One kmem_bufctl_t for each object
+ * - One unsigned int for each object
* - Padding to respect alignment of @align
* - @buffer_size bytes for each object
*
mgmt_size = 0;
nr_objs = slab_size / buffer_size;
- if (nr_objs > SLAB_LIMIT)
- nr_objs = SLAB_LIMIT;
} else {
/*
* Ignore padding for the initial guess. The padding
* into the memory allocation when taking the padding
* into account.
*/
- nr_objs = (slab_size - sizeof(struct slab)) /
- (buffer_size + sizeof(kmem_bufctl_t));
+ nr_objs = (slab_size) / (buffer_size + sizeof(unsigned int));
/*
* This calculated number will be either the right
> slab_size)
nr_objs--;
- if (nr_objs > SLAB_LIMIT)
- nr_objs = SLAB_LIMIT;
-
mgmt_size = slab_mgmt_size(nr_objs, align);
}
*num = nr_objs;
return nc;
}
-static inline bool is_slab_pfmemalloc(struct slab *slabp)
+static inline bool is_slab_pfmemalloc(struct page *page)
{
- struct page *page = virt_to_page(slabp->s_mem);
-
return PageSlabPfmemalloc(page);
}
struct array_cache *ac)
{
struct kmem_cache_node *n = cachep->node[numa_mem_id()];
- struct slab *slabp;
+ struct page *page;
unsigned long flags;
if (!pfmemalloc_active)
return;
spin_lock_irqsave(&n->list_lock, flags);
- list_for_each_entry(slabp, &n->slabs_full, list)
- if (is_slab_pfmemalloc(slabp))
+ list_for_each_entry(page, &n->slabs_full, lru)
+ if (is_slab_pfmemalloc(page))
goto out;
- list_for_each_entry(slabp, &n->slabs_partial, list)
- if (is_slab_pfmemalloc(slabp))
+ list_for_each_entry(page, &n->slabs_partial, lru)
+ if (is_slab_pfmemalloc(page))
goto out;
- list_for_each_entry(slabp, &n->slabs_free, list)
- if (is_slab_pfmemalloc(slabp))
+ list_for_each_entry(page, &n->slabs_free, lru)
+ if (is_slab_pfmemalloc(page))
goto out;
pfmemalloc_active = false;
*/
n = cachep->node[numa_mem_id()];
if (!list_empty(&n->slabs_free) && force_refill) {
- struct slab *slabp = virt_to_slab(objp);
- ClearPageSlabPfmemalloc(virt_to_head_page(slabp->s_mem));
+ struct page *page = virt_to_head_page(objp);
+ ClearPageSlabPfmemalloc(page);
clear_obj_pfmemalloc(&objp);
recheck_pfmemalloc_active(cachep, ac);
return objp;
static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
{
- struct slab *slabp = virt_to_slab(objp);
- int nodeid = slabp->nodeid;
+ int nodeid = page_to_nid(virt_to_page(objp));
struct kmem_cache_node *n;
struct array_cache *alien = NULL;
int node;
* Make sure we are not freeing a object from another node to the array
* cache on this cpu.
*/
- if (likely(slabp->nodeid == node))
+ if (likely(nodeid == node))
return 0;
n = cachep->node[node];
{
int i;
+ BUILD_BUG_ON(sizeof(((struct page *)NULL)->lru) <
+ sizeof(struct rcu_head));
kmem_cache = &kmem_cache_boot;
setup_node_pointer(kmem_cache);
slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
{
struct kmem_cache_node *n;
- struct slab *slabp;
+ struct page *page;
unsigned long flags;
int node;
continue;
spin_lock_irqsave(&n->list_lock, flags);
- list_for_each_entry(slabp, &n->slabs_full, list) {
+ list_for_each_entry(page, &n->slabs_full, lru) {
active_objs += cachep->num;
active_slabs++;
}
- list_for_each_entry(slabp, &n->slabs_partial, list) {
- active_objs += slabp->inuse;
+ list_for_each_entry(page, &n->slabs_partial, lru) {
+ active_objs += page->active;
active_slabs++;
}
- list_for_each_entry(slabp, &n->slabs_free, list)
+ list_for_each_entry(page, &n->slabs_free, lru)
num_slabs++;
free_objects += n->free_objects;
* did not request dmaable memory, we might get it, but that
* would be relatively rare and ignorable.
*/
-static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
+static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
+ int nodeid)
{
struct page *page;
int nr_pages;
- int i;
-
-#ifndef CONFIG_MMU
- /*
- * Nommu uses slab's for process anonymous memory allocations, and thus
- * requires __GFP_COMP to properly refcount higher order allocations
- */
- flags |= __GFP_COMP;
-#endif
flags |= cachep->allocflags;
if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
else
add_zone_page_state(page_zone(page),
NR_SLAB_UNRECLAIMABLE, nr_pages);
- for (i = 0; i < nr_pages; i++) {
- __SetPageSlab(page + i);
-
- if (page->pfmemalloc)
- SetPageSlabPfmemalloc(page + i);
- }
+ __SetPageSlab(page);
+ if (page->pfmemalloc)
+ SetPageSlabPfmemalloc(page);
memcg_bind_pages(cachep, cachep->gfporder);
if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) {
kmemcheck_mark_unallocated_pages(page, nr_pages);
}
- return page_address(page);
+ return page;
}
/*
* Interface to system's page release.
*/
-static void kmem_freepages(struct kmem_cache *cachep, void *addr)
+static void kmem_freepages(struct kmem_cache *cachep, struct page *page)
{
- unsigned long i = (1 << cachep->gfporder);
- struct page *page = virt_to_page(addr);
- const unsigned long nr_freed = i;
+ const unsigned long nr_freed = (1 << cachep->gfporder);
kmemcheck_free_shadow(page, cachep->gfporder);
else
sub_zone_page_state(page_zone(page),
NR_SLAB_UNRECLAIMABLE, nr_freed);
- while (i--) {
- BUG_ON(!PageSlab(page));
- __ClearPageSlabPfmemalloc(page);
- __ClearPageSlab(page);
- page++;
- }
+
+ BUG_ON(!PageSlab(page));
+ __ClearPageSlabPfmemalloc(page);
+ __ClearPageSlab(page);
+ page_mapcount_reset(page);
+ page->mapping = NULL;
memcg_release_pages(cachep, cachep->gfporder);
if (current->reclaim_state)
current->reclaim_state->reclaimed_slab += nr_freed;
- free_memcg_kmem_pages((unsigned long)addr, cachep->gfporder);
+ __free_memcg_kmem_pages(page, cachep->gfporder);
}
static void kmem_rcu_free(struct rcu_head *head)
{
- struct slab_rcu *slab_rcu = (struct slab_rcu *)head;
- struct kmem_cache *cachep = slab_rcu->cachep;
+ struct kmem_cache *cachep;
+ struct page *page;
- kmem_freepages(cachep, slab_rcu->addr);
- if (OFF_SLAB(cachep))
- kmem_cache_free(cachep->slabp_cache, slab_rcu);
+ page = container_of(head, struct page, rcu_head);
+ cachep = page->slab_cache;
+
+ kmem_freepages(cachep, page);
}
#if DEBUG
/* Print some data about the neighboring objects, if they
* exist:
*/
- struct slab *slabp = virt_to_slab(objp);
+ struct page *page = virt_to_head_page(objp);
unsigned int objnr;
- objnr = obj_to_index(cachep, slabp, objp);
+ objnr = obj_to_index(cachep, page, objp);
if (objnr) {
- objp = index_to_obj(cachep, slabp, objnr - 1);
+ objp = index_to_obj(cachep, page, objnr - 1);
realobj = (char *)objp + obj_offset(cachep);
printk(KERN_ERR "Prev obj: start=%p, len=%d\n",
realobj, size);
print_objinfo(cachep, objp, 2);
}
if (objnr + 1 < cachep->num) {
- objp = index_to_obj(cachep, slabp, objnr + 1);
+ objp = index_to_obj(cachep, page, objnr + 1);
realobj = (char *)objp + obj_offset(cachep);
printk(KERN_ERR "Next obj: start=%p, len=%d\n",
realobj, size);
#endif
#if DEBUG
-static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slabp)
+static void slab_destroy_debugcheck(struct kmem_cache *cachep,
+ struct page *page)
{
int i;
for (i = 0; i < cachep->num; i++) {
- void *objp = index_to_obj(cachep, slabp, i);
+ void *objp = index_to_obj(cachep, page, i);
if (cachep->flags & SLAB_POISON) {
#ifdef CONFIG_DEBUG_PAGEALLOC
}
}
#else
-static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slabp)
+static void slab_destroy_debugcheck(struct kmem_cache *cachep,
+ struct page *page)
{
}
#endif
* Before calling the slab must have been unlinked from the cache. The
* cache-lock is not held/needed.
*/
-static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp)
+static void slab_destroy(struct kmem_cache *cachep, struct page *page)
{
- void *addr = slabp->s_mem - slabp->colouroff;
+ void *freelist;
- slab_destroy_debugcheck(cachep, slabp);
+ freelist = page->freelist;
+ slab_destroy_debugcheck(cachep, page);
if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) {
- struct slab_rcu *slab_rcu;
+ struct rcu_head *head;
+
+ /*
+ * RCU free overloads the RCU head over the LRU.
+ * slab_page has been overloeaded over the LRU,
+ * however it is not used from now on so that
+ * we can use it safely.
+ */
+ head = (void *)&page->rcu_head;
+ call_rcu(head, kmem_rcu_free);
- slab_rcu = (struct slab_rcu *)slabp;
- slab_rcu->cachep = cachep;
- slab_rcu->addr = addr;
- call_rcu(&slab_rcu->head, kmem_rcu_free);
} else {
- kmem_freepages(cachep, addr);
- if (OFF_SLAB(cachep))
- kmem_cache_free(cachep->slabp_cache, slabp);
+ kmem_freepages(cachep, page);
}
+
+ /*
+ * From now on, we don't use freelist
+ * although actual page can be freed in rcu context
+ */
+ if (OFF_SLAB(cachep))
+ kmem_cache_free(cachep->freelist_cache, freelist);
}
/**
* use off-slab slabs. Needed to avoid a possible
* looping condition in cache_grow().
*/
- offslab_limit = size - sizeof(struct slab);
- offslab_limit /= sizeof(kmem_bufctl_t);
+ offslab_limit = size;
+ offslab_limit /= sizeof(unsigned int);
if (num > offslab_limit)
break;
int
__kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
{
- size_t left_over, slab_size, ralign;
+ size_t left_over, freelist_size, ralign;
gfp_t gfp;
int err;
size_t size = cachep->size;
if (!cachep->num)
return -E2BIG;
- slab_size = ALIGN(cachep->num * sizeof(kmem_bufctl_t)
- + sizeof(struct slab), cachep->align);
+ freelist_size =
+ ALIGN(cachep->num * sizeof(unsigned int), cachep->align);
/*
* If the slab has been placed off-slab, and we have enough space then
* move it on-slab. This is at the expense of any extra colouring.
*/
- if (flags & CFLGS_OFF_SLAB && left_over >= slab_size) {
+ if (flags & CFLGS_OFF_SLAB && left_over >= freelist_size) {
flags &= ~CFLGS_OFF_SLAB;
- left_over -= slab_size;
+ left_over -= freelist_size;
}
if (flags & CFLGS_OFF_SLAB) {
/* really off slab. No need for manual alignment */
- slab_size =
- cachep->num * sizeof(kmem_bufctl_t) + sizeof(struct slab);
+ freelist_size = cachep->num * sizeof(unsigned int);
#ifdef CONFIG_PAGE_POISONING
/* If we're going to use the generic kernel_map_pages()
if (cachep->colour_off < cachep->align)
cachep->colour_off = cachep->align;
cachep->colour = left_over / cachep->colour_off;
- cachep->slab_size = slab_size;
+ cachep->freelist_size = freelist_size;
cachep->flags = flags;
- cachep->allocflags = 0;
+ cachep->allocflags = __GFP_COMP;
if (CONFIG_ZONE_DMA_FLAG && (flags & SLAB_CACHE_DMA))
cachep->allocflags |= GFP_DMA;
cachep->size = size;
cachep->reciprocal_buffer_size = reciprocal_value(size);
if (flags & CFLGS_OFF_SLAB) {
- cachep->slabp_cache = kmalloc_slab(slab_size, 0u);
+ cachep->freelist_cache = kmalloc_slab(freelist_size, 0u);
/*
* This is a possibility for one of the malloc_sizes caches.
* But since we go off slab only for object size greater than
* this should not happen at all.
* But leave a BUG_ON for some lucky dude.
*/
- BUG_ON(ZERO_OR_NULL_PTR(cachep->slabp_cache));
+ BUG_ON(ZERO_OR_NULL_PTR(cachep->freelist_cache));
}
err = setup_cpu_cache(cachep, gfp);
{
struct list_head *p;
int nr_freed;
- struct slab *slabp;
+ struct page *page;
nr_freed = 0;
while (nr_freed < tofree && !list_empty(&n->slabs_free)) {
goto out;
}
- slabp = list_entry(p, struct slab, list);
+ page = list_entry(p, struct page, lru);
#if DEBUG
- BUG_ON(slabp->inuse);
+ BUG_ON(page->active);
#endif
- list_del(&slabp->list);
+ list_del(&page->lru);
/*
* Safe to drop the lock. The slab is no longer linked
* to the cache.
*/
n->free_objects -= cache->num;
spin_unlock_irq(&n->list_lock);
- slab_destroy(cache, slabp);
+ slab_destroy(cache, page);
nr_freed++;
}
out:
* descriptors in kmem_cache_create, we search through the malloc_sizes array.
* If we are creating a malloc_sizes cache here it would not be visible to
* kmem_find_general_cachep till the initialization is complete.
- * Hence we cannot have slabp_cache same as the original cache.
+ * Hence we cannot have freelist_cache same as the original cache.
*/
-static struct slab *alloc_slabmgmt(struct kmem_cache *cachep, void *objp,
- int colour_off, gfp_t local_flags,
- int nodeid)
+static void *alloc_slabmgmt(struct kmem_cache *cachep,
+ struct page *page, int colour_off,
+ gfp_t local_flags, int nodeid)
{
- struct slab *slabp;
+ void *freelist;
+ void *addr = page_address(page);
if (OFF_SLAB(cachep)) {
/* Slab management obj is off-slab. */
- slabp = kmem_cache_alloc_node(cachep->slabp_cache,
+ freelist = kmem_cache_alloc_node(cachep->freelist_cache,
local_flags, nodeid);
- /*
- * If the first object in the slab is leaked (it's allocated
- * but no one has a reference to it), we want to make sure
- * kmemleak does not treat the ->s_mem pointer as a reference
- * to the object. Otherwise we will not report the leak.
- */
- kmemleak_scan_area(&slabp->list, sizeof(struct list_head),
- local_flags);
- if (!slabp)
+ if (!freelist)
return NULL;
} else {
- slabp = objp + colour_off;
- colour_off += cachep->slab_size;
+ freelist = addr + colour_off;
+ colour_off += cachep->freelist_size;
}
- slabp->inuse = 0;
- slabp->colouroff = colour_off;
- slabp->s_mem = objp + colour_off;
- slabp->nodeid = nodeid;
- slabp->free = 0;
- return slabp;
+ page->active = 0;
+ page->s_mem = addr + colour_off;
+ return freelist;
}
-static inline kmem_bufctl_t *slab_bufctl(struct slab *slabp)
+static inline unsigned int *slab_freelist(struct page *page)
{
- return (kmem_bufctl_t *) (slabp + 1);
+ return (unsigned int *)(page->freelist);
}
static void cache_init_objs(struct kmem_cache *cachep,
- struct slab *slabp)
+ struct page *page)
{
int i;
for (i = 0; i < cachep->num; i++) {
- void *objp = index_to_obj(cachep, slabp, i);
+ void *objp = index_to_obj(cachep, page, i);
#if DEBUG
/* need to poison the objs? */
if (cachep->flags & SLAB_POISON)
if (cachep->ctor)
cachep->ctor(objp);
#endif
- slab_bufctl(slabp)[i] = i + 1;
+ slab_freelist(page)[i] = i;
}
- slab_bufctl(slabp)[i - 1] = BUFCTL_END;
}
static void kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags)
}
}
-static void *slab_get_obj(struct kmem_cache *cachep, struct slab *slabp,
+static void *slab_get_obj(struct kmem_cache *cachep, struct page *page,
int nodeid)
{
- void *objp = index_to_obj(cachep, slabp, slabp->free);
- kmem_bufctl_t next;
+ void *objp;
- slabp->inuse++;
- next = slab_bufctl(slabp)[slabp->free];
+ objp = index_to_obj(cachep, page, slab_freelist(page)[page->active]);
+ page->active++;
#if DEBUG
- slab_bufctl(slabp)[slabp->free] = BUFCTL_FREE;
- WARN_ON(slabp->nodeid != nodeid);
+ WARN_ON(page_to_nid(virt_to_page(objp)) != nodeid);
#endif
- slabp->free = next;
return objp;
}
-static void slab_put_obj(struct kmem_cache *cachep, struct slab *slabp,
+static void slab_put_obj(struct kmem_cache *cachep, struct page *page,
void *objp, int nodeid)
{
- unsigned int objnr = obj_to_index(cachep, slabp, objp);
-
+ unsigned int objnr = obj_to_index(cachep, page, objp);
#if DEBUG
+ unsigned int i;
+
/* Verify that the slab belongs to the intended node */
- WARN_ON(slabp->nodeid != nodeid);
+ WARN_ON(page_to_nid(virt_to_page(objp)) != nodeid);
- if (slab_bufctl(slabp)[objnr] + 1 <= SLAB_LIMIT + 1) {
- printk(KERN_ERR "slab: double free detected in cache "
- "'%s', objp %p\n", cachep->name, objp);
- BUG();
+ /* Verify double free bug */
+ for (i = page->active; i < cachep->num; i++) {
+ if (slab_freelist(page)[i] == objnr) {
+ printk(KERN_ERR "slab: double free detected in cache "
+ "'%s', objp %p\n", cachep->name, objp);
+ BUG();
+ }
}
#endif
- slab_bufctl(slabp)[objnr] = slabp->free;
- slabp->free = objnr;
- slabp->inuse--;
+ page->active--;
+ slab_freelist(page)[page->active] = objnr;
}
/*
* for the slab allocator to be able to lookup the cache and slab of a
* virtual address for kfree, ksize, and slab debugging.
*/
-static void slab_map_pages(struct kmem_cache *cache, struct slab *slab,
- void *addr)
+static void slab_map_pages(struct kmem_cache *cache, struct page *page,
+ void *freelist)
{
- int nr_pages;
- struct page *page;
-
- page = virt_to_page(addr);
-
- nr_pages = 1;
- if (likely(!PageCompound(page)))
- nr_pages <<= cache->gfporder;
-
- do {
- page->slab_cache = cache;
- page->slab_page = slab;
- page++;
- } while (--nr_pages);
+ page->slab_cache = cache;
+ page->freelist = freelist;
}
/*
* kmem_cache_alloc() when there are no active objs left in a cache.
*/
static int cache_grow(struct kmem_cache *cachep,
- gfp_t flags, int nodeid, void *objp)
+ gfp_t flags, int nodeid, struct page *page)
{
- struct slab *slabp;
+ void *freelist;
size_t offset;
gfp_t local_flags;
struct kmem_cache_node *n;
* Get mem for the objs. Attempt to allocate a physical page from
* 'nodeid'.
*/
- if (!objp)
- objp = kmem_getpages(cachep, local_flags, nodeid);
- if (!objp)
+ if (!page)
+ page = kmem_getpages(cachep, local_flags, nodeid);
+ if (!page)
goto failed;
/* Get slab management. */
- slabp = alloc_slabmgmt(cachep, objp, offset,
+ freelist = alloc_slabmgmt(cachep, page, offset,
local_flags & ~GFP_CONSTRAINT_MASK, nodeid);
- if (!slabp)
+ if (!freelist)
goto opps1;
- slab_map_pages(cachep, slabp, objp);
+ slab_map_pages(cachep, page, freelist);
- cache_init_objs(cachep, slabp);
+ cache_init_objs(cachep, page);
if (local_flags & __GFP_WAIT)
local_irq_disable();
spin_lock(&n->list_lock);
/* Make slab active. */
- list_add_tail(&slabp->list, &(n->slabs_free));
+ list_add_tail(&page->lru, &(n->slabs_free));
STATS_INC_GROWN(cachep);
n->free_objects += cachep->num;
spin_unlock(&n->list_lock);
return 1;
opps1:
- kmem_freepages(cachep, objp);
+ kmem_freepages(cachep, page);
failed:
if (local_flags & __GFP_WAIT)
local_irq_disable();
static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
unsigned long caller)
{
- struct page *page;
unsigned int objnr;
- struct slab *slabp;
+ struct page *page;
BUG_ON(virt_to_cache(objp) != cachep);
kfree_debugcheck(objp);
page = virt_to_head_page(objp);
- slabp = page->slab_page;
-
if (cachep->flags & SLAB_RED_ZONE) {
verify_redzone_free(cachep, objp);
*dbg_redzone1(cachep, objp) = RED_INACTIVE;
if (cachep->flags & SLAB_STORE_USER)
*dbg_userword(cachep, objp) = (void *)caller;
- objnr = obj_to_index(cachep, slabp, objp);
+ objnr = obj_to_index(cachep, page, objp);
BUG_ON(objnr >= cachep->num);
- BUG_ON(objp != index_to_obj(cachep, slabp, objnr));
+ BUG_ON(objp != index_to_obj(cachep, page, objnr));
-#ifdef CONFIG_DEBUG_SLAB_LEAK
- slab_bufctl(slabp)[objnr] = BUFCTL_FREE;
-#endif
if (cachep->flags & SLAB_POISON) {
#ifdef CONFIG_DEBUG_PAGEALLOC
if ((cachep->size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) {
return objp;
}
-static void check_slabp(struct kmem_cache *cachep, struct slab *slabp)
-{
- kmem_bufctl_t i;
- int entries = 0;
-
- /* Check slab's freelist to see if this obj is there. */
- for (i = slabp->free; i != BUFCTL_END; i = slab_bufctl(slabp)[i]) {
- entries++;
- if (entries > cachep->num || i >= cachep->num)
- goto bad;
- }
- if (entries != cachep->num - slabp->inuse) {
-bad:
- printk(KERN_ERR "slab: Internal list corruption detected in "
- "cache '%s'(%d), slabp %p(%d). Tainted(%s). Hexdump:\n",
- cachep->name, cachep->num, slabp, slabp->inuse,
- print_tainted());
- print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1, slabp,
- sizeof(*slabp) + cachep->num * sizeof(kmem_bufctl_t),
- 1);
- BUG();
- }
-}
#else
#define kfree_debugcheck(x) do { } while(0)
#define cache_free_debugcheck(x,objp,z) (objp)
-#define check_slabp(x,y) do { } while(0)
#endif
static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags,
while (batchcount > 0) {
struct list_head *entry;
- struct slab *slabp;
+ struct page *page;
/* Get slab alloc is to come from. */
entry = n->slabs_partial.next;
if (entry == &n->slabs_partial) {
goto must_grow;
}
- slabp = list_entry(entry, struct slab, list);
- check_slabp(cachep, slabp);
+ page = list_entry(entry, struct page, lru);
check_spinlock_acquired(cachep);
/*
* there must be at least one object available for
* allocation.
*/
- BUG_ON(slabp->inuse >= cachep->num);
+ BUG_ON(page->active >= cachep->num);
- while (slabp->inuse < cachep->num && batchcount--) {
+ while (page->active < cachep->num && batchcount--) {
STATS_INC_ALLOCED(cachep);
STATS_INC_ACTIVE(cachep);
STATS_SET_HIGH(cachep);
- ac_put_obj(cachep, ac, slab_get_obj(cachep, slabp,
+ ac_put_obj(cachep, ac, slab_get_obj(cachep, page,
node));
}
- check_slabp(cachep, slabp);
/* move slabp to correct slabp list: */
- list_del(&slabp->list);
- if (slabp->free == BUFCTL_END)
- list_add(&slabp->list, &n->slabs_full);
+ list_del(&page->lru);
+ if (page->active == cachep->num)
+ list_add(&page->list, &n->slabs_full);
else
- list_add(&slabp->list, &n->slabs_partial);
+ list_add(&page->list, &n->slabs_partial);
}
must_grow:
*dbg_redzone1(cachep, objp) = RED_ACTIVE;
*dbg_redzone2(cachep, objp) = RED_ACTIVE;
}
-#ifdef CONFIG_DEBUG_SLAB_LEAK
- {
- struct slab *slabp;
- unsigned objnr;
-
- slabp = virt_to_head_page(objp)->slab_page;
- objnr = (unsigned)(objp - slabp->s_mem) / cachep->size;
- slab_bufctl(slabp)[objnr] = BUFCTL_ACTIVE;
- }
-#endif
objp += obj_offset(cachep);
if (cachep->ctor && cachep->flags & SLAB_POISON)
cachep->ctor(objp);
* We may trigger various forms of reclaim on the allowed
* set and go into memory reserves if necessary.
*/
+ struct page *page;
+
if (local_flags & __GFP_WAIT)
local_irq_enable();
kmem_flagcheck(cache, flags);
- obj = kmem_getpages(cache, local_flags, numa_mem_id());
+ page = kmem_getpages(cache, local_flags, numa_mem_id());
if (local_flags & __GFP_WAIT)
local_irq_disable();
- if (obj) {
+ if (page) {
/*
* Insert into the appropriate per node queues
*/
- nid = page_to_nid(virt_to_page(obj));
- if (cache_grow(cache, flags, nid, obj)) {
+ nid = page_to_nid(page);
+ if (cache_grow(cache, flags, nid, page)) {
obj = ____cache_alloc_node(cache,
flags | GFP_THISNODE, nid);
if (!obj)
int nodeid)
{
struct list_head *entry;
- struct slab *slabp;
+ struct page *page;
struct kmem_cache_node *n;
void *obj;
int x;
goto must_grow;
}
- slabp = list_entry(entry, struct slab, list);
+ page = list_entry(entry, struct page, lru);
check_spinlock_acquired_node(cachep, nodeid);
- check_slabp(cachep, slabp);
STATS_INC_NODEALLOCS(cachep);
STATS_INC_ACTIVE(cachep);
STATS_SET_HIGH(cachep);
- BUG_ON(slabp->inuse == cachep->num);
+ BUG_ON(page->active == cachep->num);
- obj = slab_get_obj(cachep, slabp, nodeid);
- check_slabp(cachep, slabp);
+ obj = slab_get_obj(cachep, page, nodeid);
n->free_objects--;
/* move slabp to correct slabp list: */
- list_del(&slabp->list);
+ list_del(&page->lru);
- if (slabp->free == BUFCTL_END)
- list_add(&slabp->list, &n->slabs_full);
+ if (page->active == cachep->num)
+ list_add(&page->lru, &n->slabs_full);
else
- list_add(&slabp->list, &n->slabs_partial);
+ list_add(&page->lru, &n->slabs_partial);
spin_unlock(&n->list_lock);
goto done;
for (i = 0; i < nr_objects; i++) {
void *objp;
- struct slab *slabp;
+ struct page *page;
clear_obj_pfmemalloc(&objpp[i]);
objp = objpp[i];
- slabp = virt_to_slab(objp);
+ page = virt_to_head_page(objp);
n = cachep->node[node];
- list_del(&slabp->list);
+ list_del(&page->lru);
check_spinlock_acquired_node(cachep, node);
- check_slabp(cachep, slabp);
- slab_put_obj(cachep, slabp, objp, node);
+ slab_put_obj(cachep, page, objp, node);
STATS_DEC_ACTIVE(cachep);
n->free_objects++;
- check_slabp(cachep, slabp);
/* fixup slab chains */
- if (slabp->inuse == 0) {
+ if (page->active == 0) {
if (n->free_objects > n->free_limit) {
n->free_objects -= cachep->num;
/* No need to drop any previously held
* a different cache, refer to comments before
* alloc_slabmgmt.
*/
- slab_destroy(cachep, slabp);
+ slab_destroy(cachep, page);
} else {
- list_add(&slabp->list, &n->slabs_free);
+ list_add(&page->lru, &n->slabs_free);
}
} else {
/* Unconditionally move a slab to the end of the
* partial list on free - maximum time for the
* other objects to be freed, too.
*/
- list_add_tail(&slabp->list, &n->slabs_partial);
+ list_add_tail(&page->lru, &n->slabs_partial);
}
}
}
p = n->slabs_free.next;
while (p != &(n->slabs_free)) {
- struct slab *slabp;
+ struct page *page;
- slabp = list_entry(p, struct slab, list);
- BUG_ON(slabp->inuse);
+ page = list_entry(p, struct page, lru);
+ BUG_ON(page->active);
i++;
p = p->next;
#ifdef CONFIG_SLABINFO
void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
{
- struct slab *slabp;
+ struct page *page;
unsigned long active_objs;
unsigned long num_objs;
unsigned long active_slabs = 0;
check_irq_on();
spin_lock_irq(&n->list_lock);
- list_for_each_entry(slabp, &n->slabs_full, list) {
- if (slabp->inuse != cachep->num && !error)
+ list_for_each_entry(page, &n->slabs_full, lru) {
+ if (page->active != cachep->num && !error)
error = "slabs_full accounting error";
active_objs += cachep->num;
active_slabs++;
}
- list_for_each_entry(slabp, &n->slabs_partial, list) {
- if (slabp->inuse == cachep->num && !error)
- error = "slabs_partial inuse accounting error";
- if (!slabp->inuse && !error)
- error = "slabs_partial/inuse accounting error";
- active_objs += slabp->inuse;
+ list_for_each_entry(page, &n->slabs_partial, lru) {
+ if (page->active == cachep->num && !error)
+ error = "slabs_partial accounting error";
+ if (!page->active && !error)
+ error = "slabs_partial accounting error";
+ active_objs += page->active;
active_slabs++;
}
- list_for_each_entry(slabp, &n->slabs_free, list) {
- if (slabp->inuse && !error)
- error = "slabs_free/inuse accounting error";
+ list_for_each_entry(page, &n->slabs_free, lru) {
+ if (page->active && !error)
+ error = "slabs_free accounting error";
num_slabs++;
}
free_objects += n->free_objects;
return 1;
}
-static void handle_slab(unsigned long *n, struct kmem_cache *c, struct slab *s)
+static void handle_slab(unsigned long *n, struct kmem_cache *c,
+ struct page *page)
{
void *p;
- int i;
+ int i, j;
+
if (n[0] == n[1])
return;
- for (i = 0, p = s->s_mem; i < c->num; i++, p += c->size) {
- if (slab_bufctl(s)[i] != BUFCTL_ACTIVE)
+ for (i = 0, p = page->s_mem; i < c->num; i++, p += c->size) {
+ bool active = true;
+
+ for (j = page->active; j < c->num; j++) {
+ /* Skip freed item */
+ if (slab_freelist(page)[j] == i) {
+ active = false;
+ break;
+ }
+ }
+ if (!active)
continue;
+
if (!add_caller(n, (unsigned long)*dbg_userword(c, p)))
return;
}
static int leaks_show(struct seq_file *m, void *p)
{
struct kmem_cache *cachep = list_entry(p, struct kmem_cache, list);
- struct slab *slabp;
+ struct page *page;
struct kmem_cache_node *n;
const char *name;
unsigned long *x = m->private;
check_irq_on();
spin_lock_irq(&n->list_lock);
- list_for_each_entry(slabp, &n->slabs_full, list)
- handle_slab(x, cachep, slabp);
- list_for_each_entry(slabp, &n->slabs_partial, list)
- handle_slab(x, cachep, slabp);
+ list_for_each_entry(page, &n->slabs_full, lru)
+ handle_slab(x, cachep, page);
+ list_for_each_entry(page, &n->slabs_partial, lru)
+ handle_slab(x, cachep, page);
spin_unlock_irq(&n->list_lock);
}
name = cachep->name;
/*
* Maximum number of desirable partial slabs.
* The existence of more partial slabs makes kmem_cache_shrink
- * sort the partial list by the number of objects in the.
+ * sort the partial list by the number of objects in use.
*/
#define MAX_PARTIAL 10
* Hooks for other subsystems that check memory allocations. In a typical
* production configuration these hooks all should produce no code at all.
*/
+static inline void kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags)
+{
+ kmemleak_alloc(ptr, size, 1, flags);
+}
+
+static inline void kfree_hook(const void *x)
+{
+ kmemleak_free(x);
+}
+
static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags)
{
flags &= gfp_allowed_mask;
/*
* Enable debugging if selected on the kernel commandline.
*/
- if (slub_debug && (!slub_debug_slabs ||
- !strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs))))
+ if (slub_debug && (!slub_debug_slabs || (name &&
+ !strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs)))))
flags |= slub_debug;
return flags;
static inline void dec_slabs_node(struct kmem_cache *s, int node,
int objects) {}
+static inline void kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags)
+{
+ kmemleak_alloc(ptr, size, 1, flags);
+}
+
+static inline void kfree_hook(const void *x)
+{
+ kmemleak_free(x);
+}
+
static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags)
{ return 0; }
static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags,
- void *object) {}
+ void *object)
+{
+ kmemleak_alloc_recursive(object, s->object_size, 1, s->flags,
+ flags & gfp_allowed_mask);
+}
-static inline void slab_free_hook(struct kmem_cache *s, void *x) {}
+static inline void slab_free_hook(struct kmem_cache *s, void *x)
+{
+ kmemleak_free_recursive(x, s->flags);
+}
#endif /* CONFIG_SLUB_DEBUG */
* slab on the node for this slabcache. There are no concurrent accesses
* possible.
*
- * Note that this function only works on the kmalloc_node_cache
- * when allocating for the kmalloc_node_cache. This is used for bootstrapping
+ * Note that this function only works on the kmem_cache_node
+ * when allocating for the kmem_cache_node. This is used for bootstrapping
* memory on a fresh node that has no slab structures yet.
*/
static void early_kmem_cache_node_alloc(int node)
if (page)
ptr = page_address(page);
- kmemleak_alloc(ptr, size, 1, flags);
+ kmalloc_large_node_hook(ptr, size, flags);
return ptr;
}
page = virt_to_head_page(x);
if (unlikely(!PageSlab(page))) {
BUG_ON(!PageCompound(page));
- kmemleak_free(x);
+ kfree_hook(x);
__free_memcg_kmem_pages(page, compound_order(page));
return;
}
static void put_compound_page(struct page *page)
{
- /*
- * hugetlbfs pages cannot be split from under us. If this is a
- * hugetlbfs page, check refcount on head page and release the page if
- * the refcount becomes zero.
- */
- if (PageHuge(page)) {
- page = compound_head(page);
- if (put_page_testzero(page))
- __put_compound_page(page);
-
- return;
- }
-
if (unlikely(PageTail(page))) {
/* __split_huge_page_refcount can run under us */
struct page *page_head = compound_trans_head(page);
* still hot on arches that do not support
* this_cpu_cmpxchg_double().
*/
- if (PageSlab(page_head)) {
- if (PageTail(page)) {
+ if (PageSlab(page_head) || PageHeadHuge(page_head)) {
+ if (likely(PageTail(page))) {
+ /*
+ * __split_huge_page_refcount
+ * cannot race here.
+ */
+ VM_BUG_ON(!PageHead(page_head));
+ atomic_dec(&page->_mapcount);
if (put_page_testzero(page_head))
VM_BUG_ON(1);
-
- atomic_dec(&page->_mapcount);
- goto skip_lock_tail;
+ if (put_page_testzero(page_head))
+ __put_compound_page(page_head);
+ return;
} else
+ /*
+ * __split_huge_page_refcount
+ * run before us, "page" was a
+ * THP tail. The split
+ * page_head has been freed
+ * and reallocated as slab or
+ * hugetlbfs page of smaller
+ * order (only possible if
+ * reallocated as slab on
+ * x86).
+ */
goto skip_lock;
}
/*
/* __split_huge_page_refcount run before us */
compound_unlock_irqrestore(page_head, flags);
skip_lock:
- if (put_page_testzero(page_head))
- __put_single_page(page_head);
+ if (put_page_testzero(page_head)) {
+ /*
+ * The head page may have been
+ * freed and reallocated as a
+ * compound page of smaller
+ * order and then freed again.
+ * All we know is that it
+ * cannot have become: a THP
+ * page, a compound page of
+ * higher order, a tail page.
+ * That is because we still
+ * hold the refcount of the
+ * split THP tail and
+ * page_head was the THP head
+ * before the split.
+ */
+ if (PageHead(page_head))
+ __put_compound_page(page_head);
+ else
+ __put_single_page(page_head);
+ }
out_put_single:
if (put_page_testzero(page))
__put_single_page(page);
VM_BUG_ON(atomic_read(&page->_count) != 0);
compound_unlock_irqrestore(page_head, flags);
-skip_lock_tail:
if (put_page_testzero(page_head)) {
if (PageHead(page_head))
__put_compound_page(page_head);
* proper PT lock that already serializes against
* split_huge_page().
*/
+ unsigned long flags;
bool got = false;
- struct page *page_head;
-
- /*
- * If this is a hugetlbfs page it cannot be split under us. Simply
- * increment refcount for the head page.
- */
- if (PageHuge(page)) {
- page_head = compound_head(page);
- atomic_inc(&page_head->_count);
- got = true;
- } else {
- unsigned long flags;
+ struct page *page_head = compound_trans_head(page);
- page_head = compound_trans_head(page);
- if (likely(page != page_head &&
- get_page_unless_zero(page_head))) {
-
- /* Ref to put_compound_page() comment. */
- if (PageSlab(page_head)) {
- if (likely(PageTail(page))) {
- __get_page_tail_foll(page, false);
- return true;
- } else {
- put_page(page_head);
- return false;
- }
- }
-
- /*
- * page_head wasn't a dangling pointer but it
- * may not be a head page anymore by the time
- * we obtain the lock. That is ok as long as it
- * can't be freed from under us.
- */
- flags = compound_lock_irqsave(page_head);
- /* here __split_huge_page_refcount won't run anymore */
+ if (likely(page != page_head && get_page_unless_zero(page_head))) {
+ /* Ref to put_compound_page() comment. */
+ if (PageSlab(page_head) || PageHeadHuge(page_head)) {
if (likely(PageTail(page))) {
+ /*
+ * This is a hugetlbfs page or a slab
+ * page. __split_huge_page_refcount
+ * cannot race here.
+ */
+ VM_BUG_ON(!PageHead(page_head));
__get_page_tail_foll(page, false);
- got = true;
- }
- compound_unlock_irqrestore(page_head, flags);
- if (unlikely(!got))
+ return true;
+ } else {
+ /*
+ * __split_huge_page_refcount run
+ * before us, "page" was a THP
+ * tail. The split page_head has been
+ * freed and reallocated as slab or
+ * hugetlbfs page of smaller order
+ * (only possible if reallocated as
+ * slab on x86).
+ */
put_page(page_head);
+ return false;
+ }
+ }
+
+ /*
+ * page_head wasn't a dangling pointer but it
+ * may not be a head page anymore by the time
+ * we obtain the lock. That is ok as long as it
+ * can't be freed from under us.
+ */
+ flags = compound_lock_irqsave(page_head);
+ /* here __split_huge_page_refcount won't run anymore */
+ if (likely(PageTail(page))) {
+ __get_page_tail_foll(page, false);
+ got = true;
}
+ compound_unlock_irqrestore(page_head, flags);
+ if (unlikely(!got))
+ put_page(page_head);
}
return got;
}
config RPS
boolean
- depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS
+ depends on SMP && SYSFS
default y
config RFS_ACCEL
config XPS
boolean
- depends on SMP && USE_GENERIC_SMP_HELPERS
+ depends on SMP
default y
config NETPRIO_CGROUP
size_t size, int flags)
{
struct sock *sk = sock->sk;
- struct sockaddr_at *sat = (struct sockaddr_at *)msg->msg_name;
struct ddpehdr *ddp;
int copied = 0;
int offset = 0;
}
err = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copied);
- if (!err) {
- if (sat) {
- sat->sat_family = AF_APPLETALK;
- sat->sat_port = ddp->deh_sport;
- sat->sat_addr.s_node = ddp->deh_snode;
- sat->sat_addr.s_net = ddp->deh_snet;
- }
- msg->msg_namelen = sizeof(*sat);
+ if (!err && msg->msg_name) {
+ struct sockaddr_at *sat = msg->msg_name;
+ sat->sat_family = AF_APPLETALK;
+ sat->sat_port = ddp->deh_sport;
+ sat->sat_addr.s_node = ddp->deh_snode;
+ sat->sat_addr.s_net = ddp->deh_snet;
+ msg->msg_namelen = sizeof(*sat);
}
skb_free_datagram(sk, skb); /* Free the datagram. */
struct sk_buff *skb;
int copied, error = -EINVAL;
- msg->msg_namelen = 0;
-
if (sock->state != SS_CONNECTED)
return -ENOTCONN;
skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
- if (msg->msg_namelen != 0) {
- struct sockaddr_ax25 *sax = (struct sockaddr_ax25 *)msg->msg_name;
+ if (msg->msg_name) {
ax25_digi digi;
ax25_address src;
const unsigned char *mac = skb_mac_header(skb);
+ struct sockaddr_ax25 *sax = msg->msg_name;
memset(sax, 0, sizeof(struct full_sockaddr_ax25));
ax25_addr_parse(mac + 1, skb->data - mac - 1, &src, NULL,
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb) {
- if (sk->sk_shutdown & RCV_SHUTDOWN) {
- msg->msg_namelen = 0;
+ if (sk->sk_shutdown & RCV_SHUTDOWN)
return 0;
- }
+
return err;
}
if (bt_sk(sk)->skb_msg_name)
bt_sk(sk)->skb_msg_name(skb, msg->msg_name,
&msg->msg_namelen);
- else
- msg->msg_namelen = 0;
}
skb_free_datagram(sk, skb);
if (flags & MSG_OOB)
return -EOPNOTSUPP;
- msg->msg_namelen = 0;
-
BT_DBG("sk %p size %zu", sk, size);
lock_sock(sk);
if (!skb)
return err;
- msg->msg_namelen = 0;
-
copied = skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
int err;
struct sk_buff_head seg_queue;
+ if (!chan->conn)
+ return -ENOTCONN;
+
/* Connectionless channel */
if (chan->chan_type == L2CAP_CHAN_CONN_LESS) {
skb = l2cap_create_connless_pdu(chan, msg, len, priority);
addr.l2_family = AF_BLUETOOTH;
addr.l2_psm = 0;
addr.l2_cid = 0;
+ addr.l2_bdaddr_type = BDADDR_BREDR;
*err = kernel_bind(sock, (struct sockaddr *) &addr, sizeof(addr));
if (*err < 0)
goto failed;
addr.l2_family = AF_BLUETOOTH;
addr.l2_psm = __constant_cpu_to_le16(RFCOMM_PSM);
addr.l2_cid = 0;
+ addr.l2_bdaddr_type = BDADDR_BREDR;
*err = kernel_connect(sock, (struct sockaddr *) &addr, sizeof(addr), O_NONBLOCK);
if (*err == 0 || *err == -EINPROGRESS)
return s;
addr.l2_family = AF_BLUETOOTH;
addr.l2_psm = __constant_cpu_to_le16(RFCOMM_PSM);
addr.l2_cid = 0;
+ addr.l2_bdaddr_type = BDADDR_BREDR;
err = kernel_bind(sock, (struct sockaddr *) &addr, sizeof(addr));
if (err < 0) {
BT_ERR("Bind failed %d", err);
if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) {
rfcomm_dlc_accept(d);
- msg->msg_namelen = 0;
return 0;
}
static int rfcomm_sock_getsockopt_old(struct socket *sock, int optname, char __user *optval, int __user *optlen)
{
struct sock *sk = sock->sk;
+ struct sock *l2cap_sk;
+ struct l2cap_conn *conn;
struct rfcomm_conninfo cinfo;
- struct l2cap_conn *conn = l2cap_pi(sk)->chan->conn;
int len, err = 0;
u32 opt;
break;
}
+ l2cap_sk = rfcomm_pi(sk)->dlc->session->sock->sk;
+ conn = l2cap_pi(l2cap_sk)->chan->conn;
+
memset(&cinfo, 0, sizeof(cinfo));
cinfo.hci_handle = conn->hcon->handle;
memcpy(cinfo.dev_class, conn->hcon->dev_class, 3);
test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) {
sco_conn_defer_accept(pi->conn->hcon, pi->setting);
sk->sk_state = BT_CONFIG;
- msg->msg_namelen = 0;
release_sock(sk);
return 0;
BT_DBG("conn %p", conn);
+ if (!(conn->hcon->link_mode & HCI_LM_MASTER))
+ return SMP_CMD_NOTSUPP;
+
hcon->pending_sec_level = authreq_to_seclevel(rp->auth_req);
if (smp_ltk_encrypt(conn, hcon->pending_sec_level))
del_nbp(p);
}
+ br_fdb_delete_by_port(br, NULL, 1);
+
br_vlan_flush(br);
del_timer_sync(&br->gc_timer);
if (info->bitmask & EBT_IP6_TCLASS &&
FWINV(info->tclass != ipv6_get_dsfield(ih6), EBT_IP6_TCLASS))
return false;
- if (FWINV(ipv6_masked_addr_cmp(&ih6->saddr, &info->smsk,
- &info->saddr), EBT_IP6_SOURCE) ||
+ if ((info->bitmask & EBT_IP6_SOURCE &&
+ FWINV(ipv6_masked_addr_cmp(&ih6->saddr, &info->smsk,
+ &info->saddr), EBT_IP6_SOURCE)) ||
+ (info->bitmask & EBT_IP6_DEST &&
FWINV(ipv6_masked_addr_cmp(&ih6->daddr, &info->dmsk,
- &info->daddr), EBT_IP6_DEST))
+ &info->daddr), EBT_IP6_DEST)))
return false;
if (info->bitmask & EBT_IP6_PROTO) {
uint8_t nexthdr = ih6->nexthdr;
if (m->msg_flags&MSG_OOB)
goto read_error;
- m->msg_namelen = 0;
-
skb = skb_recv_datagram(sk, flags, 0 , &ret);
if (!skb)
goto read_error;
if (flags&MSG_OOB)
goto out;
- msg->msg_namelen = 0;
-
/*
* Lock the socket to prevent queue disordering
* while sleeps in memcpy_tomsg
if (err < 0)
return err;
}
- kern_msg->msg_name = kern_address;
+ if (kern_msg->msg_name)
+ kern_msg->msg_name = kern_address;
} else
kern_msg->msg_name = NULL;
{
const struct net_device_ops *ops = dev->netdev_ops;
- if ((dev->flags & IFF_UP) && ops->ndo_change_rx_flags)
+ if (ops->ndo_change_rx_flags)
ops->ndo_change_rx_flags(dev, flags);
}
if (err < 0)
return err;
}
- m->msg_name = address;
+ if (m->msg_name)
+ m->msg_name = address;
} else {
m->msg_name = NULL;
}
struct sk_buff *segs = NULL;
struct sk_buff *tail = NULL;
struct sk_buff *fskb = skb_shinfo(skb)->frag_list;
+ skb_frag_t *skb_frag = skb_shinfo(skb)->frags;
unsigned int mss = skb_shinfo(skb)->gso_size;
unsigned int doffset = skb->data - skb_mac_header(skb);
unsigned int offset = doffset;
if (hsize > len || !sg)
hsize = len;
- if (!hsize && i >= nfrags) {
- BUG_ON(fskb->len != len);
+ if (!hsize && i >= nfrags && skb_headlen(fskb) &&
+ (skb_headlen(fskb) == len || sg)) {
+ BUG_ON(skb_headlen(fskb) > len);
+
+ i = 0;
+ nfrags = skb_shinfo(fskb)->nr_frags;
+ skb_frag = skb_shinfo(fskb)->frags;
+ pos += skb_headlen(fskb);
+
+ while (pos < offset + len) {
+ BUG_ON(i >= nfrags);
+
+ size = skb_frag_size(skb_frag);
+ if (pos + size > offset + len)
+ break;
+
+ i++;
+ pos += size;
+ skb_frag++;
+ }
- pos += len;
nskb = skb_clone(fskb, GFP_ATOMIC);
fskb = fskb->next;
if (unlikely(!nskb))
goto err;
+ if (unlikely(pskb_trim(nskb, len))) {
+ kfree_skb(nskb);
+ goto err;
+ }
+
hsize = skb_end_offset(nskb);
if (skb_cow_head(nskb, doffset + headroom)) {
kfree_skb(nskb);
nskb->data - tnl_hlen,
doffset + tnl_hlen);
- if (fskb != skb_shinfo(skb)->frag_list)
+ if (nskb->len == len + doffset)
goto perform_csum_check;
if (!sg) {
skb_shinfo(nskb)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG;
- while (pos < offset + len && i < nfrags) {
- *frag = skb_shinfo(skb)->frags[i];
+ while (pos < offset + len) {
+ if (i >= nfrags) {
+ BUG_ON(skb_headlen(fskb));
+
+ i = 0;
+ nfrags = skb_shinfo(fskb)->nr_frags;
+ skb_frag = skb_shinfo(fskb)->frags;
+
+ BUG_ON(!nfrags);
+
+ fskb = fskb->next;
+ }
+
+ if (unlikely(skb_shinfo(nskb)->nr_frags >=
+ MAX_SKB_FRAGS)) {
+ net_warn_ratelimited(
+ "skb_segment: too many frags: %u %u\n",
+ pos, mss);
+ goto err;
+ }
+
+ *frag = *skb_frag;
__skb_frag_ref(frag);
size = skb_frag_size(frag);
if (pos + size <= offset + len) {
i++;
+ skb_frag++;
pos += size;
} else {
skb_frag_size_sub(frag, pos + size - (offset + len));
frag++;
}
- if (pos < offset + len) {
- struct sk_buff *fskb2 = fskb;
-
- BUG_ON(pos + fskb->len != offset + len);
-
- pos += fskb->len;
- fskb = fskb->next;
-
- if (fskb2->next) {
- fskb2 = skb_clone(fskb2, GFP_ATOMIC);
- if (!fskb2)
- goto err;
- } else
- skb_get(fskb2);
-
- SKB_FRAG_ASSERT(nskb);
- skb_shinfo(nskb)->frag_list = fskb2;
- }
-
skip_fraglist:
nskb->data_len = len - hsize;
nskb->len += nskb->data_len;
this_cpu_inc(snet->stats->cookie_valid);
opts->mss = mss;
+ opts->options |= XT_SYNPROXY_OPT_MSS;
if (opts->options & XT_SYNPROXY_OPT_TIMESTAMP)
synproxy_check_timestamp_cookie(opts);
rth->dst.error= -err;
rth->rt_flags &= ~RTCF_LOCAL;
}
- if (do_cache)
- rt_cache_route(&FIB_RES_NH(res), rth);
+ if (do_cache) {
+ if (unlikely(!rt_cache_route(&FIB_RES_NH(res), rth))) {
+ rth->dst.flags |= DST_NOCACHE;
+ rt_add_uncached_list(rth);
+ }
+ }
skb_dst_set(skb, &rth->dst);
err = 0;
goto out;
this_cpu_inc(snet->stats->cookie_valid);
opts->mss = mss;
+ opts->options |= XT_SYNPROXY_OPT_MSS;
if (opts->options & XT_SYNPROXY_OPT_TIMESTAMP)
synproxy_check_timestamp_cookie(opts);
if (skb->tstamp.tv64)
sk->sk_stamp = skb->tstamp;
- msg->msg_namelen = sizeof(*sipx);
-
if (sipx) {
sipx->sipx_family = AF_IPX;
sipx->sipx_port = ipx->ipx_source.sock;
sipx->sipx_network = IPX_SKB_CB(skb)->ipx_source_net;
sipx->sipx_type = ipx->ipx_type;
sipx->sipx_zero = 0;
+ msg->msg_namelen = sizeof(*sipx);
}
rc = copied;
IRDA_DEBUG(4, "%s()\n", __func__);
- msg->msg_namelen = 0;
-
skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
flags & MSG_DONTWAIT, &err);
if (!skb)
target = sock_rcvlowat(sk, flags & MSG_WAITALL, size);
timeo = sock_rcvtimeo(sk, noblock);
- msg->msg_namelen = 0;
-
do {
int chunk;
struct sk_buff *skb = skb_dequeue(&sk->sk_receive_queue);
int err = 0;
u32 offset;
- msg->msg_namelen = 0;
-
if ((sk->sk_state == IUCV_DISCONN) &&
skb_queue_empty(&iucv->backlog_skb_q) &&
skb_queue_empty(&sk->sk_receive_queue) &&
if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT))
goto out;
- msg->msg_namelen = 0;
skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &err);
if (skb == NULL)
goto out;
if (sk->sk_state & PPPOX_BOUND)
goto end;
- msg->msg_namelen = 0;
-
err = 0;
skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
flags & MSG_DONTWAIT, &err);
int target; /* Read at least this many bytes */
long timeo;
- msg->msg_namelen = 0;
-
lock_sock(sk);
copied = -ENOTCONN;
if (unlikely(sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN))
connection simultaneously.
config NETFILTER_XT_MATCH_CONNLIMIT
- tristate '"connlimit" match support"'
+ tristate '"connlimit" match support'
depends on NF_CONNTRACK
depends on NETFILTER_ADVANCED
---help---
struct net *net = nf_ct_net(ct);
nf_ct_ext_destroy(ct);
- atomic_dec(&net->ct.count);
nf_ct_ext_free(ct);
kmem_cache_free(net->ct.nf_conntrack_cachep, ct);
+ smp_mb__before_atomic_dec();
+ atomic_dec(&net->ct.count);
}
EXPORT_SYMBOL_GPL(nf_conntrack_free);
spin_lock_bh(&ct->lock);
this_way = &seqadj->seq[dir];
if (this_way->offset_before == this_way->offset_after ||
- before(this_way->correction_pos, seq)) {
- this_way->correction_pos = seq;
+ before(this_way->correction_pos, ntohl(seq))) {
+ this_way->correction_pos = ntohl(seq);
this_way->offset_before = this_way->offset_after;
this_way->offset_after += off;
}
opts->tsecr = opts->tsval;
opts->tsval = tcp_time_stamp & ~0x3f;
- if (opts->options & XT_SYNPROXY_OPT_WSCALE)
- opts->tsval |= info->wscale;
- else
+ if (opts->options & XT_SYNPROXY_OPT_WSCALE) {
+ opts->tsval |= opts->wscale;
+ opts->wscale = info->wscale;
+ } else
opts->tsval |= 0xf;
if (opts->options & XT_SYNPROXY_OPT_SACK_PERM)
[NFTA_RULE_COMPAT_FLAGS] = { .type = NLA_U32 },
};
-static u8 nft_parse_compat(const struct nlattr *attr, bool *inv)
+static int nft_parse_compat(const struct nlattr *attr, u8 *proto, bool *inv)
{
struct nlattr *tb[NFTA_RULE_COMPAT_MAX+1];
u32 flags;
if (flags & NFT_RULE_COMPAT_F_INV)
*inv = true;
- return ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO]));
+ *proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO]));
+ return 0;
}
static int
target_compat_from_user(target, nla_data(tb[NFTA_TARGET_INFO]), info);
- if (ctx->nla[NFTA_RULE_COMPAT])
- proto = nft_parse_compat(ctx->nla[NFTA_RULE_COMPAT], &inv);
+ if (ctx->nla[NFTA_RULE_COMPAT]) {
+ ret = nft_parse_compat(ctx->nla[NFTA_RULE_COMPAT], &proto, &inv);
+ if (ret < 0)
+ goto err;
+ }
nft_target_set_tgchk_param(&par, ctx, target, info, &e, proto, inv);
match_compat_from_user(match, nla_data(tb[NFTA_MATCH_INFO]), info);
- if (ctx->nla[NFTA_RULE_COMPAT])
- proto = nft_parse_compat(ctx->nla[NFTA_RULE_COMPAT], &inv);
+ if (ctx->nla[NFTA_RULE_COMPAT]) {
+ ret = nft_parse_compat(ctx->nla[NFTA_RULE_COMPAT], &proto, &inv);
+ if (ret < 0)
+ goto err;
+ }
nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv);
}
#endif
- msg->msg_namelen = 0;
-
copied = data_skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
int genlmsg_multicast_allns(struct genl_family *family, struct sk_buff *skb,
u32 portid, unsigned int group, gfp_t flags)
{
- if (group >= family->n_mcgrps)
+ if (WARN_ON_ONCE(group >= family->n_mcgrps))
return -EINVAL;
group = family->mcgrp_offset + group;
return genlmsg_mcast(skb, portid, group, flags);
if (nlh)
report = nlmsg_report(nlh);
- if (group >= family->n_mcgrps)
+ if (WARN_ON_ONCE(group >= family->n_mcgrps))
return;
group = family->mcgrp_offset + group;
nlmsg_notify(sk, skb, portid, group, report, flags);
sax->sax25_family = AF_NETROM;
skb_copy_from_linear_data_offset(skb, 7, sax->sax25_call.ax25_call,
AX25_ADDR_LEN);
+ msg->msg_namelen = sizeof(*sax);
}
- msg->msg_namelen = sizeof(*sax);
-
skb_free_datagram(sk, skb);
release_sock(sk);
pr_debug("%p %zu\n", sk, len);
- msg->msg_namelen = 0;
-
lock_sock(sk);
if (sk->sk_state == LLCP_CLOSED &&
if (!skb)
return rc;
- msg->msg_namelen = 0;
-
copied = skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
static void register_prot_hook(struct sock *sk)
{
struct packet_sock *po = pkt_sk(sk);
+
if (!po->running) {
- if (po->fanout)
+ if (po->fanout) {
__fanout_link(sk, po);
- else
+ } else {
dev_add_pack(&po->prot_hook);
+ rcu_assign_pointer(po->cached_dev, po->prot_hook.dev);
+ }
+
sock_hold(sk);
po->running = 1;
}
struct packet_sock *po = pkt_sk(sk);
po->running = 0;
- if (po->fanout)
+ if (po->fanout) {
__fanout_unlink(sk, po);
- else
+ } else {
__dev_remove_pack(&po->prot_hook);
+ RCU_INIT_POINTER(po->cached_dev, NULL);
+ }
+
__sock_put(sk);
if (sync) {
return tp_len;
}
+static struct net_device *packet_cached_dev_get(struct packet_sock *po)
+{
+ struct net_device *dev;
+
+ rcu_read_lock();
+ dev = rcu_dereference(po->cached_dev);
+ if (dev)
+ dev_hold(dev);
+ rcu_read_unlock();
+
+ return dev;
+}
+
static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
{
struct sk_buff *skb;
struct net_device *dev;
__be16 proto;
- bool need_rls_dev = false;
int err, reserve = 0;
void *ph;
struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name;
mutex_lock(&po->pg_vec_lock);
if (saddr == NULL) {
- dev = po->prot_hook.dev;
+ dev = packet_cached_dev_get(po);
proto = po->num;
addr = NULL;
} else {
proto = saddr->sll_protocol;
addr = saddr->sll_addr;
dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
- need_rls_dev = true;
}
err = -ENXIO;
if (unlikely(dev == NULL))
goto out;
-
- reserve = dev->hard_header_len;
-
err = -ENETDOWN;
if (unlikely(!(dev->flags & IFF_UP)))
goto out_put;
+ reserve = dev->hard_header_len;
+
size_max = po->tx_ring.frame_size
- (po->tp_hdrlen - sizeof(struct sockaddr_ll));
__packet_set_status(po, ph, status);
kfree_skb(skb);
out_put:
- if (need_rls_dev)
- dev_put(dev);
+ dev_put(dev);
out:
mutex_unlock(&po->pg_vec_lock);
return err;
struct sk_buff *skb;
struct net_device *dev;
__be16 proto;
- bool need_rls_dev = false;
unsigned char *addr;
int err, reserve = 0;
struct virtio_net_hdr vnet_hdr = { 0 };
*/
if (saddr == NULL) {
- dev = po->prot_hook.dev;
+ dev = packet_cached_dev_get(po);
proto = po->num;
addr = NULL;
} else {
proto = saddr->sll_protocol;
addr = saddr->sll_addr;
dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
- need_rls_dev = true;
}
err = -ENXIO;
- if (dev == NULL)
+ if (unlikely(dev == NULL))
goto out_unlock;
- if (sock->type == SOCK_RAW)
- reserve = dev->hard_header_len;
-
err = -ENETDOWN;
- if (!(dev->flags & IFF_UP))
+ if (unlikely(!(dev->flags & IFF_UP)))
goto out_unlock;
+ if (sock->type == SOCK_RAW)
+ reserve = dev->hard_header_len;
if (po->has_vnet_hdr) {
vnet_hdr_len = sizeof(vnet_hdr);
if (err > 0 && (err = net_xmit_errno(err)) != 0)
goto out_unlock;
- if (need_rls_dev)
- dev_put(dev);
+ dev_put(dev);
return len;
out_free:
kfree_skb(skb);
out_unlock:
- if (dev && need_rls_dev)
+ if (dev)
dev_put(dev);
out:
return err;
po = pkt_sk(sk);
sk->sk_family = PF_PACKET;
po->num = proto;
+ RCU_INIT_POINTER(po->cached_dev, NULL);
sk->sk_destruct = packet_sock_destruct;
sk_refcnt_debug_inc(sk);
struct sock *sk = sock->sk;
struct sk_buff *skb;
int copied, err;
- struct sockaddr_ll *sll;
int vnet_hdr_len = 0;
err = -EINVAL;
goto out_free;
}
- /*
- * If the address length field is there to be filled in, we fill
- * it in now.
+ /* You lose any data beyond the buffer you gave. If it worries
+ * a user program they can ask the device for its MTU
+ * anyway.
*/
-
- sll = &PACKET_SKB_CB(skb)->sa.ll;
- if (sock->type == SOCK_PACKET)
- msg->msg_namelen = sizeof(struct sockaddr_pkt);
- else
- msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr);
-
- /*
- * You lose any data beyond the buffer you gave. If it worries a
- * user program they can ask the device for its MTU anyway.
- */
-
copied = skb->len;
if (copied > len) {
copied = len;
sock_recv_ts_and_drops(msg, sk, skb);
- if (msg->msg_name)
+ if (msg->msg_name) {
+ /* If the address length field is there to be filled
+ * in, we fill it in now.
+ */
+ if (sock->type == SOCK_PACKET) {
+ msg->msg_namelen = sizeof(struct sockaddr_pkt);
+ } else {
+ struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
+ msg->msg_namelen = sll->sll_halen +
+ offsetof(struct sockaddr_ll, sll_addr);
+ }
memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa,
msg->msg_namelen);
+ }
if (pkt_sk(sk)->auxdata) {
struct tpacket_auxdata aux;
unsigned int tp_loss:1;
unsigned int tp_tx_has_off:1;
unsigned int tp_tstamp;
+ struct net_device __rcu *cached_dev;
struct packet_type prot_hook ____cacheline_aligned_in_smp;
};
rdsdebug("size %zu flags 0x%x timeo %ld\n", size, msg_flags, timeo);
- msg->msg_namelen = 0;
-
if (msg_flags & MSG_OOB)
goto out;
{
struct sock *sk = sock->sk;
struct rose_sock *rose = rose_sk(sk);
- struct sockaddr_rose *srose = (struct sockaddr_rose *)msg->msg_name;
size_t copied;
unsigned char *asmptr;
struct sk_buff *skb;
skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
- if (srose != NULL) {
- memset(srose, 0, msg->msg_namelen);
+ if (msg->msg_name) {
+ struct sockaddr_rose *srose;
+
+ memset(msg->msg_name, 0, sizeof(struct full_sockaddr_rose));
+ srose = msg->msg_name;
srose->srose_family = AF_ROSE;
srose->srose_addr = rose->dest_addr;
srose->srose_call = rose->dest_call;
/* copy the peer address and timestamp */
if (!continue_call) {
- if (msg->msg_name && msg->msg_namelen > 0)
+ if (msg->msg_name) {
+ size_t len =
+ sizeof(call->conn->trans->peer->srx);
memcpy(msg->msg_name,
- &call->conn->trans->peer->srx,
- sizeof(call->conn->trans->peer->srx));
+ &call->conn->trans->peer->srx, len);
+ msg->msg_namelen = len;
+ }
sock_recv_ts_and_drops(msg, &rx->sk, skb);
}
int err;
int len;
+ BUG_ON(klen > sizeof(struct sockaddr_storage));
err = get_user(len, ulen);
if (err)
return err;
if (len > klen)
len = klen;
- if (len < 0 || len > sizeof(struct sockaddr_storage))
+ if (len < 0)
return -EINVAL;
if (len) {
if (audit_sockaddr(klen, kaddr))
msg.msg_iov = &iov;
iov.iov_len = size;
iov.iov_base = ubuf;
- msg.msg_name = (struct sockaddr *)&address;
- msg.msg_namelen = sizeof(address);
+ /* Save some cycles and don't copy the address if not needed */
+ msg.msg_name = addr ? (struct sockaddr *)&address : NULL;
+ /* We assume all kernel code knows the size of sockaddr_storage */
+ msg.msg_namelen = 0;
if (sock->file->f_flags & O_NONBLOCK)
flags |= MSG_DONTWAIT;
err = sock_recvmsg(sock, &msg, size, flags);
goto out;
}
- /*
- * Save the user-mode address (verify_iovec will change the
- * kernel msghdr to use the kernel address space)
+ /* Save the user-mode address (verify_iovec will change the
+ * kernel msghdr to use the kernel address space)
*/
-
uaddr = (__force void __user *)msg_sys->msg_name;
uaddr_len = COMPAT_NAMELEN(msg);
- if (MSG_CMSG_COMPAT & flags) {
+ if (MSG_CMSG_COMPAT & flags)
err = verify_compat_iovec(msg_sys, iov, &addr, VERIFY_WRITE);
- } else
+ else
err = verify_iovec(msg_sys, iov, &addr, VERIFY_WRITE);
if (err < 0)
goto out_freeiov;
cmsg_ptr = (unsigned long)msg_sys->msg_control;
msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT);
+ /* We assume all kernel code knows the size of sockaddr_storage */
+ msg_sys->msg_namelen = 0;
+
if (sock->file->f_flags & O_NONBLOCK)
flags |= MSG_DONTWAIT;
err = (nosec ? sock_recvmsg_nosec : sock_recvmsg)(sock, msg_sys,
goto exit;
}
- /* will be updated in set_orig_addr() if needed */
- m->msg_namelen = 0;
-
timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
restart:
goto exit;
}
- /* will be updated in set_orig_addr() if needed */
- m->msg_namelen = 0;
-
target = sock_rcvlowat(sk, flags & MSG_WAITALL, buf_len);
timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
{
struct unix_sock *u = unix_sk(sk);
- msg->msg_namelen = 0;
if (u->addr) {
msg->msg_namelen = u->addr->len;
memcpy(msg->msg_name, u->addr->name, u->addr->len);
if (flags&MSG_OOB)
goto out;
- msg->msg_namelen = 0;
-
err = mutex_lock_interruptible(&u->readlock);
if (err) {
err = sock_intr_errno(sock_rcvtimeo(sk, noblock));
target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);
- msg->msg_namelen = 0;
-
/* Lock the socket to prevent queue disordering
* while sleeps in memcpy_tomsg
*/
vsk = vsock_sk(sk);
err = 0;
- msg->msg_namelen = 0;
-
lock_sock(sk);
if (sk->sk_state != SS_CONNECTED) {
if (flags & MSG_OOB || flags & MSG_ERRQUEUE)
return -EOPNOTSUPP;
- msg->msg_namelen = 0;
-
/* Retrieve the head sk_buff from the socket's receive queue. */
err = 0;
skb = skb_recv_datagram(&vsk->sk, flags, noblock, &err);
d_fnend(4, NULL, "() = 0\n");
return 0;
- genl_unregister_family(&wimax_gnl_family);
error_register_family:
d_fnend(4, NULL, "() = %d\n", result);
return result;
if (sx25) {
sx25->sx25_family = AF_X25;
sx25->sx25_addr = x25->dest_addr;
+ msg->msg_namelen = sizeof(*sx25);
}
- msg->msg_namelen = sizeof(struct sockaddr_x25);
-
x25_check_rbuf(sk);
rc = copied;
out_free_dgram:
render_opcode(out, "ASN1_OP_END_SET_OF%s,\n", act);
render_opcode(out, "_jump_target(%u),\n", entry);
break;
+ default:
+ break;
}
if (e->action)
render_opcode(out, "_action(ACT_%s),\n",
}
}
if (!defined $suppress_whiletrailers{$linenr} &&
+ defined($stat) && defined($cond) &&
$line =~ /\b(?:if|while|for)\s*\(/ && $line !~ /^.\s*#/) {
my ($s, $c) = ($stat, $cond);
# Object file lists
obj-$(CONFIG_SECURITY) += security.o capability.o
obj-$(CONFIG_SECURITYFS) += inode.o
-# Must precede capability.o in order to stack properly.
obj-$(CONFIG_SECURITY_SELINUX) += selinux/built-in.o
obj-$(CONFIG_SECURITY_SMACK) += smack/built-in.o
obj-$(CONFIG_AUDIT) += lsm_audit.o
static void audit_pre(struct audit_buffer *ab, void *ca)
{
struct common_audit_data *sa = ca;
- struct task_struct *tsk = sa->aad->tsk ? sa->aad->tsk : current;
if (aa_g_audit_header) {
audit_log_format(ab, "apparmor=");
if (sa->aad->profile) {
struct aa_profile *profile = sa->aad->profile;
- pid_t pid;
- rcu_read_lock();
- pid = rcu_dereference(tsk->real_parent)->pid;
- rcu_read_unlock();
- audit_log_format(ab, " parent=%d", pid);
if (profile->ns != root_ns) {
audit_log_format(ab, " namespace=");
audit_log_untrustedstring(ab, profile->ns->base.hname);
audit_log_format(ab, " name=");
audit_log_untrustedstring(ab, sa->aad->name);
}
-
- if (sa->aad->tsk) {
- audit_log_format(ab, " pid=%d comm=", tsk->pid);
- audit_log_untrustedstring(ab, tsk->comm);
- }
-
}
/**
if (sa->aad->type == AUDIT_APPARMOR_KILL)
(void)send_sig_info(SIGKILL, NULL,
- sa->aad->tsk ? sa->aad->tsk : current);
+ sa->u.tsk ? sa->u.tsk : current);
if (sa->aad->type == AUDIT_APPARMOR_ALLOWED)
return complain_error(sa->aad->error);
/**
* audit_caps - audit a capability
- * @profile: profile confining task (NOT NULL)
- * @task: task capability test was performed against (NOT NULL)
+ * @profile: profile being tested for confinement (NOT NULL)
* @cap: capability tested
* @error: error code returned by test
*
*
* Returns: 0 or sa->error on success, error code on failure
*/
-static int audit_caps(struct aa_profile *profile, struct task_struct *task,
- int cap, int error)
+static int audit_caps(struct aa_profile *profile, int cap, int error)
{
struct audit_cache *ent;
int type = AUDIT_APPARMOR_AUTO;
sa.type = LSM_AUDIT_DATA_CAP;
sa.aad = &aad;
sa.u.cap = cap;
- sa.aad->tsk = task;
sa.aad->op = OP_CAPABLE;
sa.aad->error = error;
/**
* aa_capable - test permission to use capability
- * @task: task doing capability test against (NOT NULL)
- * @profile: profile confining @task (NOT NULL)
+ * @profile: profile being tested against (NOT NULL)
* @cap: capability to be tested
* @audit: whether an audit record should be generated
*
*
* Returns: 0 on success, or else an error code.
*/
-int aa_capable(struct task_struct *task, struct aa_profile *profile, int cap,
- int audit)
+int aa_capable(struct aa_profile *profile, int cap, int audit)
{
int error = profile_capable(profile, cap);
return error;
}
- return audit_caps(profile, task, cap, error);
+ return audit_caps(profile, cap, error);
}
/**
* may_change_ptraced_domain - check if can change profile on ptraced task
- * @task: task we want to change profile of (NOT NULL)
* @to_profile: profile to change to (NOT NULL)
*
- * Check if the task is ptraced and if so if the tracing task is allowed
+ * Check if current is ptraced and if so if the tracing task is allowed
* to trace the new domain
*
* Returns: %0 or error if change not allowed
*/
-static int may_change_ptraced_domain(struct task_struct *task,
- struct aa_profile *to_profile)
+static int may_change_ptraced_domain(struct aa_profile *to_profile)
{
struct task_struct *tracer;
struct aa_profile *tracerp = NULL;
int error = 0;
rcu_read_lock();
- tracer = ptrace_parent(task);
+ tracer = ptrace_parent(current);
if (tracer)
/* released below */
tracerp = aa_get_task_profile(tracer);
if (!tracer || unconfined(tracerp))
goto out;
- error = aa_may_ptrace(tracer, tracerp, to_profile, PTRACE_MODE_ATTACH);
+ error = aa_may_ptrace(tracerp, to_profile, PTRACE_MODE_ATTACH);
out:
rcu_read_unlock();
}
if (bprm->unsafe & (LSM_UNSAFE_PTRACE | LSM_UNSAFE_PTRACE_CAP)) {
- error = may_change_ptraced_domain(current, new_profile);
+ error = may_change_ptraced_domain(new_profile);
if (error) {
aa_put_profile(new_profile);
goto audit;
}
}
- error = may_change_ptraced_domain(current, hat);
+ error = may_change_ptraced_domain(hat);
if (error) {
info = "ptraced";
error = -EPERM;
}
/* check if tracing task is allowed to trace target domain */
- error = may_change_ptraced_domain(current, target);
+ error = may_change_ptraced_domain(target);
if (error) {
info = "ptrace prevents transition";
goto audit;
void *profile;
const char *name;
const char *info;
- struct task_struct *tsk;
union {
void *target;
struct {
* This file contains AppArmor capability mediation definitions.
*
* Copyright (C) 1998-2008 Novell/SUSE
- * Copyright 2009-2010 Canonical Ltd.
+ * Copyright 2009-2013 Canonical Ltd.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
extern struct aa_fs_entry aa_fs_entry_caps[];
-int aa_capable(struct task_struct *task, struct aa_profile *profile, int cap,
- int audit);
+int aa_capable(struct aa_profile *profile, int cap, int audit);
static inline void aa_free_cap_rules(struct aa_caps *caps)
{
struct aa_profile;
-int aa_may_ptrace(struct task_struct *tracer_task, struct aa_profile *tracer,
- struct aa_profile *tracee, unsigned int mode);
+int aa_may_ptrace(struct aa_profile *tracer, struct aa_profile *tracee,
+ unsigned int mode);
int aa_ptrace(struct task_struct *tracer, struct task_struct *tracee,
unsigned int mode);
/**
* aa_may_ptrace - test if tracer task can trace the tracee
- * @tracer_task: task who will do the tracing (NOT NULL)
* @tracer: profile of the task doing the tracing (NOT NULL)
* @tracee: task to be traced
* @mode: whether PTRACE_MODE_READ || PTRACE_MODE_ATTACH
*
* Returns: %0 else error code if permission denied or error
*/
-int aa_may_ptrace(struct task_struct *tracer_task, struct aa_profile *tracer,
- struct aa_profile *tracee, unsigned int mode)
+int aa_may_ptrace(struct aa_profile *tracer, struct aa_profile *tracee,
+ unsigned int mode)
{
/* TODO: currently only based on capability, not extended ptrace
* rules,
if (unconfined(tracer) || tracer == tracee)
return 0;
/* log this capability request */
- return aa_capable(tracer_task, tracer, CAP_SYS_PTRACE, 1);
+ return aa_capable(tracer, CAP_SYS_PTRACE, 1);
}
/**
if (!unconfined(tracer_p)) {
struct aa_profile *tracee_p = aa_get_task_profile(tracee);
- error = aa_may_ptrace(tracer, tracer_p, tracee_p, mode);
+ error = aa_may_ptrace(tracer_p, tracee_p, mode);
error = aa_audit_ptrace(tracer_p, tracee_p, error);
aa_put_profile(tracee_p);
if (!error) {
profile = aa_cred_profile(cred);
if (!unconfined(profile))
- error = aa_capable(current, profile, cap, audit);
+ error = aa_capable(profile, cap, audit);
}
return error;
}
return 0;
}
-static int cap_xfrm_state_alloc_security(struct xfrm_state *x,
- struct xfrm_user_sec_ctx *sec_ctx,
- u32 secid)
+static int cap_xfrm_state_alloc(struct xfrm_state *x,
+ struct xfrm_user_sec_ctx *sec_ctx)
+{
+ return 0;
+}
+
+static int cap_xfrm_state_alloc_acquire(struct xfrm_state *x,
+ struct xfrm_sec_ctx *polsec,
+ u32 secid)
{
return 0;
}
set_to_cap_if_null(ops, xfrm_policy_clone_security);
set_to_cap_if_null(ops, xfrm_policy_free_security);
set_to_cap_if_null(ops, xfrm_policy_delete_security);
- set_to_cap_if_null(ops, xfrm_state_alloc_security);
+ set_to_cap_if_null(ops, xfrm_state_alloc);
+ set_to_cap_if_null(ops, xfrm_state_alloc_acquire);
set_to_cap_if_null(ops, xfrm_state_free_security);
set_to_cap_if_null(ops, xfrm_state_delete_security);
set_to_cap_if_null(ops, xfrm_policy_lookup);
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/err.h>
+#include <linux/sched.h>
#include <linux/rbtree.h>
+#include <linux/cred.h>
#include <linux/key-type.h>
#include <linux/digsig.h>
static struct key *keyring[INTEGRITY_KEYRING_MAX];
+#ifdef CONFIG_IMA_TRUSTED_KEYRING
+static const char *keyring_name[INTEGRITY_KEYRING_MAX] = {
+ ".evm",
+ ".module",
+ ".ima",
+};
+#else
static const char *keyring_name[INTEGRITY_KEYRING_MAX] = {
"_evm",
"_module",
"_ima",
};
+#endif
int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen,
- const char *digest, int digestlen)
+ const char *digest, int digestlen)
{
if (id >= INTEGRITY_KEYRING_MAX)
return -EINVAL;
if (!keyring[id]) {
keyring[id] =
- request_key(&key_type_keyring, keyring_name[id], NULL);
+ request_key(&key_type_keyring, keyring_name[id], NULL);
if (IS_ERR(keyring[id])) {
int err = PTR_ERR(keyring[id]);
pr_err("no %s keyring: %d\n", keyring_name[id], err);
}
}
- switch (sig[0]) {
+ switch (sig[1]) {
case 1:
- return digsig_verify(keyring[id], sig, siglen,
+ /* v1 API expect signature without xattr type */
+ return digsig_verify(keyring[id], sig + 1, siglen - 1,
digest, digestlen);
case 2:
return asymmetric_verify(keyring[id], sig, siglen,
return -EOPNOTSUPP;
}
+
+int integrity_init_keyring(const unsigned int id)
+{
+ const struct cred *cred = current_cred();
+ const struct user_struct *user = cred->user;
+
+ keyring[id] = keyring_alloc(keyring_name[id], KUIDT_INIT(0),
+ KGIDT_INIT(0), cred,
+ ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+ KEY_USR_VIEW | KEY_USR_READ),
+ KEY_ALLOC_NOT_IN_QUOTA, user->uid_keyring);
+ if (!IS_ERR(keyring[id]))
+ set_bit(KEY_FLAG_TRUSTED_ONLY, &keyring[id]->flags);
+ else
+ pr_info("Can't allocate %s keyring (%ld)\n",
+ keyring_name[id], PTR_ERR(keyring[id]));
+ return 0;
+}
#include "integrity.h"
-/*
- * signature format v2 - for using with asymmetric keys
- */
-struct signature_v2_hdr {
- uint8_t version; /* signature format version */
- uint8_t hash_algo; /* Digest algorithm [enum pkey_hash_algo] */
- uint32_t keyid; /* IMA key identifier - not X509/PGP specific*/
- uint16_t sig_size; /* signature size */
- uint8_t sig[0]; /* signature payload */
-} __packed;
-
/*
* Request an asymmetric key.
*/
goto out;
}
- xattr_len = rc - 1;
+ xattr_len = rc;
/* check value type */
switch (xattr_data->type) {
if (rc)
break;
rc = integrity_digsig_verify(INTEGRITY_KEYRING_EVM,
- xattr_data->digest, xattr_len,
+ (const char *)xattr_data, xattr_len,
calc.digest, sizeof(calc.digest));
if (!rc) {
/* we probably want to replace rsa with hmac here */
#include <linux/module.h>
#include <linux/xattr.h>
+#include <linux/evm.h>
-int posix_xattr_acl(char *xattr)
+int posix_xattr_acl(const char *xattr)
{
int xattr_len = strlen(xattr);
static void iint_free(struct integrity_iint_cache *iint)
{
+ kfree(iint->ima_hash);
+ iint->ima_hash = NULL;
iint->version = 0;
iint->flags = 0UL;
iint->ima_file_status = INTEGRITY_UNKNOWN;
select CRYPTO_HMAC
select CRYPTO_MD5
select CRYPTO_SHA1
+ select CRYPTO_HASH_INFO
select TCG_TPM if HAS_IOMEM && !UML
select TCG_TIS if TCG_TPM && X86
select TCG_IBMVTPM if TCG_TPM && PPC64
help
Disabling this option will disregard LSM based policy rules.
+choice
+ prompt "Default template"
+ default IMA_NG_TEMPLATE
+ depends on IMA
+ help
+ Select the default IMA measurement template.
+
+ The original 'ima' measurement list template contains a
+ hash, defined as 20 bytes, and a null terminated pathname,
+ limited to 255 characters. The 'ima-ng' measurement list
+ template permits both larger hash digests and longer
+ pathnames.
+
+ config IMA_TEMPLATE
+ bool "ima"
+ config IMA_NG_TEMPLATE
+ bool "ima-ng (default)"
+ config IMA_SIG_TEMPLATE
+ bool "ima-sig"
+endchoice
+
+config IMA_DEFAULT_TEMPLATE
+ string
+ depends on IMA
+ default "ima" if IMA_TEMPLATE
+ default "ima-ng" if IMA_NG_TEMPLATE
+ default "ima-sig" if IMA_SIG_TEMPLATE
+
+choice
+ prompt "Default integrity hash algorithm"
+ default IMA_DEFAULT_HASH_SHA1
+ depends on IMA
+ help
+ Select the default hash algorithm used for the measurement
+ list, integrity appraisal and audit log. The compiled default
+ hash algorithm can be overwritten using the kernel command
+ line 'ima_hash=' option.
+
+ config IMA_DEFAULT_HASH_SHA1
+ bool "SHA1 (default)"
+ depends on CRYPTO_SHA1
+
+ config IMA_DEFAULT_HASH_SHA256
+ bool "SHA256"
+ depends on CRYPTO_SHA256 && !IMA_TEMPLATE
+
+ config IMA_DEFAULT_HASH_SHA512
+ bool "SHA512"
+ depends on CRYPTO_SHA512 && !IMA_TEMPLATE
+
+ config IMA_DEFAULT_HASH_WP512
+ bool "WP512"
+ depends on CRYPTO_WP512 && !IMA_TEMPLATE
+endchoice
+
+config IMA_DEFAULT_HASH
+ string
+ depends on IMA
+ default "sha1" if IMA_DEFAULT_HASH_SHA1
+ default "sha256" if IMA_DEFAULT_HASH_SHA256
+ default "sha512" if IMA_DEFAULT_HASH_SHA512
+ default "wp512" if IMA_DEFAULT_HASH_WP512
+
config IMA_APPRAISE
bool "Appraise integrity measurements"
depends on IMA
For more information on integrity appraisal refer to:
<http://linux-ima.sourceforge.net>
If unsure, say N.
+
+config IMA_TRUSTED_KEYRING
+ bool "Require all keys on the _ima keyring be signed"
+ depends on IMA_APPRAISE && SYSTEM_TRUSTED_KEYRING
+ default y
+ help
+ This option requires that all keys added to the _ima
+ keyring be signed by a key on the system trusted keyring.
obj-$(CONFIG_IMA) += ima.o
ima-y := ima_fs.o ima_queue.o ima_init.o ima_main.o ima_crypto.o ima_api.o \
- ima_policy.o
+ ima_policy.o ima_template.o ima_template_lib.o
ima-$(CONFIG_IMA_APPRAISE) += ima_appraise.o
#define IMA_HASH_BITS 9
#define IMA_MEASURE_HTABLE_SIZE (1 << IMA_HASH_BITS)
+#define IMA_TEMPLATE_FIELD_ID_MAX_LEN 16
+#define IMA_TEMPLATE_NUM_FIELDS_MAX 15
+
+#define IMA_TEMPLATE_IMA_NAME "ima"
+#define IMA_TEMPLATE_IMA_FMT "d|n"
+
/* set during initialization */
extern int ima_initialized;
extern int ima_used_chip;
-extern char *ima_hash;
+extern int ima_hash_algo;
extern int ima_appraise;
-/* IMA inode template definition */
-struct ima_template_data {
- u8 digest[IMA_DIGEST_SIZE]; /* sha1/md5 measurement hash */
- char file_name[IMA_EVENT_NAME_LEN_MAX + 1]; /* name + \0 */
+/* IMA template field data definition */
+struct ima_field_data {
+ u8 *data;
+ u32 len;
+};
+
+/* IMA template field definition */
+struct ima_template_field {
+ const char field_id[IMA_TEMPLATE_FIELD_ID_MAX_LEN];
+ int (*field_init) (struct integrity_iint_cache *iint, struct file *file,
+ const unsigned char *filename,
+ struct evm_ima_xattr_data *xattr_value,
+ int xattr_len, struct ima_field_data *field_data);
+ void (*field_show) (struct seq_file *m, enum ima_show_type show,
+ struct ima_field_data *field_data);
+};
+
+/* IMA template descriptor definition */
+struct ima_template_desc {
+ char *name;
+ char *fmt;
+ int num_fields;
+ struct ima_template_field **fields;
};
struct ima_template_entry {
- u8 digest[IMA_DIGEST_SIZE]; /* sha1 or md5 measurement hash */
- const char *template_name;
- int template_len;
- struct ima_template_data template;
+ u8 digest[TPM_DIGEST_SIZE]; /* sha1 or md5 measurement hash */
+ struct ima_template_desc *template_desc; /* template descriptor */
+ u32 template_data_len;
+ struct ima_field_data template_data[0]; /* template related data */
};
struct ima_queue_entry {
void ima_fs_cleanup(void);
int ima_inode_alloc(struct inode *inode);
int ima_add_template_entry(struct ima_template_entry *entry, int violation,
- const char *op, struct inode *inode);
-int ima_calc_file_hash(struct file *file, char *digest);
-int ima_calc_buffer_hash(const void *data, int len, char *digest);
-int ima_calc_boot_aggregate(char *digest);
-void ima_add_violation(struct inode *inode, const unsigned char *filename,
+ const char *op, struct inode *inode,
+ const unsigned char *filename);
+int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash);
+int ima_calc_field_array_hash(struct ima_field_data *field_data, int num_fields,
+ struct ima_digest_data *hash);
+int __init ima_calc_boot_aggregate(struct ima_digest_data *hash);
+void ima_add_violation(struct file *file, const unsigned char *filename,
const char *op, const char *cause);
int ima_init_crypto(void);
+void ima_putc(struct seq_file *m, void *data, int datalen);
+void ima_print_digest(struct seq_file *m, u8 *digest, int size);
+struct ima_template_desc *ima_template_desc_current(void);
+int ima_init_template(void);
+
+int ima_init_template(void);
/*
* used to protect h_table and sha_table
int ima_get_action(struct inode *inode, int mask, int function);
int ima_must_measure(struct inode *inode, int mask, int function);
int ima_collect_measurement(struct integrity_iint_cache *iint,
- struct file *file);
+ struct file *file,
+ struct evm_ima_xattr_data **xattr_value,
+ int *xattr_len);
void ima_store_measurement(struct integrity_iint_cache *iint, struct file *file,
- const unsigned char *filename);
+ const unsigned char *filename,
+ struct evm_ima_xattr_data *xattr_value,
+ int xattr_len);
void ima_audit_measurement(struct integrity_iint_cache *iint,
const unsigned char *filename);
+int ima_alloc_init_template(struct integrity_iint_cache *iint,
+ struct file *file, const unsigned char *filename,
+ struct evm_ima_xattr_data *xattr_value,
+ int xattr_len, struct ima_template_entry **entry);
int ima_store_template(struct ima_template_entry *entry, int violation,
- struct inode *inode);
-void ima_template_show(struct seq_file *m, void *e, enum ima_show_type show);
+ struct inode *inode, const unsigned char *filename);
const char *ima_d_path(struct path *path, char **pathbuf);
/* rbtree tree calls to lookup, insert, delete
#ifdef CONFIG_IMA_APPRAISE
int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
- struct file *file, const unsigned char *filename);
+ struct file *file, const unsigned char *filename,
+ struct evm_ima_xattr_data *xattr_value,
+ int xattr_len);
int ima_must_appraise(struct inode *inode, int mask, enum ima_hooks func);
void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file);
enum integrity_status ima_get_cache_status(struct integrity_iint_cache *iint,
int func);
+void ima_get_hash_algo(struct evm_ima_xattr_data *xattr_value, int xattr_len,
+ struct ima_digest_data *hash);
+int ima_read_xattr(struct dentry *dentry,
+ struct evm_ima_xattr_data **xattr_value);
#else
static inline int ima_appraise_measurement(int func,
struct integrity_iint_cache *iint,
struct file *file,
- const unsigned char *filename)
+ const unsigned char *filename,
+ struct evm_ima_xattr_data *xattr_value,
+ int xattr_len)
{
return INTEGRITY_UNKNOWN;
}
{
return INTEGRITY_UNKNOWN;
}
+
+static inline void ima_get_hash_algo(struct evm_ima_xattr_data *xattr_value,
+ int xattr_len,
+ struct ima_digest_data *hash)
+{
+}
+
+static inline int ima_read_xattr(struct dentry *dentry,
+ struct evm_ima_xattr_data **xattr_value)
+{
+ return 0;
+}
+
#endif
/* LSM based policy rules require audit */
#include <linux/fs.h>
#include <linux/xattr.h>
#include <linux/evm.h>
+#include <crypto/hash_info.h>
#include "ima.h"
-static const char *IMA_TEMPLATE_NAME = "ima";
+/*
+ * ima_alloc_init_template - create and initialize a new template entry
+ */
+int ima_alloc_init_template(struct integrity_iint_cache *iint,
+ struct file *file, const unsigned char *filename,
+ struct evm_ima_xattr_data *xattr_value,
+ int xattr_len, struct ima_template_entry **entry)
+{
+ struct ima_template_desc *template_desc = ima_template_desc_current();
+ int i, result = 0;
+
+ *entry = kzalloc(sizeof(**entry) + template_desc->num_fields *
+ sizeof(struct ima_field_data), GFP_NOFS);
+ if (!*entry)
+ return -ENOMEM;
+
+ for (i = 0; i < template_desc->num_fields; i++) {
+ struct ima_template_field *field = template_desc->fields[i];
+ u32 len;
+
+ result = field->field_init(iint, file, filename,
+ xattr_value, xattr_len,
+ &((*entry)->template_data[i]));
+ if (result != 0)
+ goto out;
+
+ len = (*entry)->template_data[i].len;
+ (*entry)->template_data_len += sizeof(len);
+ (*entry)->template_data_len += len;
+ }
+ (*entry)->template_desc = template_desc;
+ return 0;
+out:
+ kfree(*entry);
+ *entry = NULL;
+ return result;
+}
/*
* ima_store_template - store ima template measurements
* Returns 0 on success, error code otherwise
*/
int ima_store_template(struct ima_template_entry *entry,
- int violation, struct inode *inode)
+ int violation, struct inode *inode,
+ const unsigned char *filename)
{
const char *op = "add_template_measure";
const char *audit_cause = "hashing_error";
+ char *template_name = entry->template_desc->name;
int result;
-
- memset(entry->digest, 0, sizeof(entry->digest));
- entry->template_name = IMA_TEMPLATE_NAME;
- entry->template_len = sizeof(entry->template);
+ struct {
+ struct ima_digest_data hdr;
+ char digest[TPM_DIGEST_SIZE];
+ } hash;
if (!violation) {
- result = ima_calc_buffer_hash(&entry->template,
- entry->template_len,
- entry->digest);
+ int num_fields = entry->template_desc->num_fields;
+
+ /* this function uses default algo */
+ hash.hdr.algo = HASH_ALGO_SHA1;
+ result = ima_calc_field_array_hash(&entry->template_data[0],
+ num_fields, &hash.hdr);
if (result < 0) {
integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode,
- entry->template_name, op,
+ template_name, op,
audit_cause, result, 0);
return result;
}
+ memcpy(entry->digest, hash.hdr.digest, hash.hdr.length);
}
- result = ima_add_template_entry(entry, violation, op, inode);
+ result = ima_add_template_entry(entry, violation, op, inode, filename);
return result;
}
* By extending the PCR with 0xFF's instead of with zeroes, the PCR
* value is invalidated.
*/
-void ima_add_violation(struct inode *inode, const unsigned char *filename,
+void ima_add_violation(struct file *file, const unsigned char *filename,
const char *op, const char *cause)
{
struct ima_template_entry *entry;
+ struct inode *inode = file->f_dentry->d_inode;
int violation = 1;
int result;
/* can overflow, only indicator */
atomic_long_inc(&ima_htable.violations);
- entry = kmalloc(sizeof(*entry), GFP_KERNEL);
- if (!entry) {
+ result = ima_alloc_init_template(NULL, file, filename,
+ NULL, 0, &entry);
+ if (result < 0) {
result = -ENOMEM;
goto err_out;
}
- memset(&entry->template, 0, sizeof(entry->template));
- strncpy(entry->template.file_name, filename, IMA_EVENT_NAME_LEN_MAX);
- result = ima_store_template(entry, violation, inode);
+ result = ima_store_template(entry, violation, inode, filename);
if (result < 0)
kfree(entry);
err_out:
* Return 0 on success, error code otherwise
*/
int ima_collect_measurement(struct integrity_iint_cache *iint,
- struct file *file)
+ struct file *file,
+ struct evm_ima_xattr_data **xattr_value,
+ int *xattr_len)
{
struct inode *inode = file_inode(file);
const char *filename = file->f_dentry->d_name.name;
int result = 0;
+ struct {
+ struct ima_digest_data hdr;
+ char digest[IMA_MAX_DIGEST_SIZE];
+ } hash;
+
+ if (xattr_value)
+ *xattr_len = ima_read_xattr(file->f_dentry, xattr_value);
if (!(iint->flags & IMA_COLLECTED)) {
u64 i_version = file_inode(file)->i_version;
- iint->ima_xattr.type = IMA_XATTR_DIGEST;
- result = ima_calc_file_hash(file, iint->ima_xattr.digest);
+ /* use default hash algorithm */
+ hash.hdr.algo = ima_hash_algo;
+
+ if (xattr_value)
+ ima_get_hash_algo(*xattr_value, *xattr_len, &hash.hdr);
+
+ result = ima_calc_file_hash(file, &hash.hdr);
if (!result) {
- iint->version = i_version;
- iint->flags |= IMA_COLLECTED;
+ int length = sizeof(hash.hdr) + hash.hdr.length;
+ void *tmpbuf = krealloc(iint->ima_hash, length,
+ GFP_NOFS);
+ if (tmpbuf) {
+ iint->ima_hash = tmpbuf;
+ memcpy(iint->ima_hash, &hash, length);
+ iint->version = i_version;
+ iint->flags |= IMA_COLLECTED;
+ } else
+ result = -ENOMEM;
}
}
if (result)
* Must be called with iint->mutex held.
*/
void ima_store_measurement(struct integrity_iint_cache *iint,
- struct file *file, const unsigned char *filename)
+ struct file *file, const unsigned char *filename,
+ struct evm_ima_xattr_data *xattr_value,
+ int xattr_len)
{
const char *op = "add_template_measure";
const char *audit_cause = "ENOMEM";
if (iint->flags & IMA_MEASURED)
return;
- entry = kmalloc(sizeof(*entry), GFP_KERNEL);
- if (!entry) {
+ result = ima_alloc_init_template(iint, file, filename,
+ xattr_value, xattr_len, &entry);
+ if (result < 0) {
integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, filename,
op, audit_cause, result, 0);
return;
}
- memset(&entry->template, 0, sizeof(entry->template));
- memcpy(entry->template.digest, iint->ima_xattr.digest, IMA_DIGEST_SIZE);
- strcpy(entry->template.file_name,
- (strlen(filename) > IMA_EVENT_NAME_LEN_MAX) ?
- file->f_dentry->d_name.name : filename);
- result = ima_store_template(entry, violation, inode);
+ result = ima_store_template(entry, violation, inode, filename);
if (!result || result == -EEXIST)
iint->flags |= IMA_MEASURED;
if (result < 0)
const unsigned char *filename)
{
struct audit_buffer *ab;
- char hash[(IMA_DIGEST_SIZE * 2) + 1];
+ char hash[(iint->ima_hash->length * 2) + 1];
+ const char *algo_name = hash_algo_name[iint->ima_hash->algo];
+ char algo_hash[sizeof(hash) + strlen(algo_name) + 2];
int i;
if (iint->flags & IMA_AUDITED)
return;
- for (i = 0; i < IMA_DIGEST_SIZE; i++)
- hex_byte_pack(hash + (i * 2), iint->ima_xattr.digest[i]);
+ for (i = 0; i < iint->ima_hash->length; i++)
+ hex_byte_pack(hash + (i * 2), iint->ima_hash->digest[i]);
hash[i * 2] = '\0';
ab = audit_log_start(current->audit_context, GFP_KERNEL,
audit_log_format(ab, "file=");
audit_log_untrustedstring(ab, filename);
audit_log_format(ab, " hash=");
- audit_log_untrustedstring(ab, hash);
+ snprintf(algo_hash, sizeof(algo_hash), "%s:%s", algo_name, hash);
+ audit_log_untrustedstring(ab, algo_hash);
audit_log_task_info(ab, current);
audit_log_end(ab);
#include <linux/magic.h>
#include <linux/ima.h>
#include <linux/evm.h>
+#include <crypto/hash_info.h>
#include "ima.h"
}
static int ima_fix_xattr(struct dentry *dentry,
- struct integrity_iint_cache *iint)
+ struct integrity_iint_cache *iint)
{
- iint->ima_xattr.type = IMA_XATTR_DIGEST;
- return __vfs_setxattr_noperm(dentry, XATTR_NAME_IMA,
- (u8 *)&iint->ima_xattr,
- sizeof(iint->ima_xattr), 0);
+ int rc, offset;
+ u8 algo = iint->ima_hash->algo;
+
+ if (algo <= HASH_ALGO_SHA1) {
+ offset = 1;
+ iint->ima_hash->xattr.sha1.type = IMA_XATTR_DIGEST;
+ } else {
+ offset = 0;
+ iint->ima_hash->xattr.ng.type = IMA_XATTR_DIGEST_NG;
+ iint->ima_hash->xattr.ng.algo = algo;
+ }
+ rc = __vfs_setxattr_noperm(dentry, XATTR_NAME_IMA,
+ &iint->ima_hash->xattr.data[offset],
+ (sizeof(iint->ima_hash->xattr) - offset) +
+ iint->ima_hash->length, 0);
+ return rc;
}
/* Return specific func appraised cached result */
enum integrity_status ima_get_cache_status(struct integrity_iint_cache *iint,
int func)
{
- switch(func) {
+ switch (func) {
case MMAP_CHECK:
return iint->ima_mmap_status;
case BPRM_CHECK:
static void ima_set_cache_status(struct integrity_iint_cache *iint,
int func, enum integrity_status status)
{
- switch(func) {
+ switch (func) {
case MMAP_CHECK:
iint->ima_mmap_status = status;
break;
static void ima_cache_flags(struct integrity_iint_cache *iint, int func)
{
- switch(func) {
+ switch (func) {
case MMAP_CHECK:
iint->flags |= (IMA_MMAP_APPRAISED | IMA_APPRAISED);
break;
}
}
+void ima_get_hash_algo(struct evm_ima_xattr_data *xattr_value, int xattr_len,
+ struct ima_digest_data *hash)
+{
+ struct signature_v2_hdr *sig;
+
+ if (!xattr_value || xattr_len < 2)
+ return;
+
+ switch (xattr_value->type) {
+ case EVM_IMA_XATTR_DIGSIG:
+ sig = (typeof(sig))xattr_value;
+ if (sig->version != 2 || xattr_len <= sizeof(*sig))
+ return;
+ hash->algo = sig->hash_algo;
+ break;
+ case IMA_XATTR_DIGEST_NG:
+ hash->algo = xattr_value->digest[0];
+ break;
+ case IMA_XATTR_DIGEST:
+ /* this is for backward compatibility */
+ if (xattr_len == 21) {
+ unsigned int zero = 0;
+ if (!memcmp(&xattr_value->digest[16], &zero, 4))
+ hash->algo = HASH_ALGO_MD5;
+ else
+ hash->algo = HASH_ALGO_SHA1;
+ } else if (xattr_len == 17)
+ hash->algo = HASH_ALGO_MD5;
+ break;
+ }
+}
+
+int ima_read_xattr(struct dentry *dentry,
+ struct evm_ima_xattr_data **xattr_value)
+{
+ struct inode *inode = dentry->d_inode;
+
+ if (!inode->i_op->getxattr)
+ return 0;
+
+ return vfs_getxattr_alloc(dentry, XATTR_NAME_IMA, (char **)xattr_value,
+ 0, GFP_NOFS);
+}
+
/*
* ima_appraise_measurement - appraise file measurement
*
* Return 0 on success, error code otherwise
*/
int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
- struct file *file, const unsigned char *filename)
+ struct file *file, const unsigned char *filename,
+ struct evm_ima_xattr_data *xattr_value,
+ int xattr_len)
{
struct dentry *dentry = file->f_dentry;
struct inode *inode = dentry->d_inode;
- struct evm_ima_xattr_data *xattr_value = NULL;
enum integrity_status status = INTEGRITY_UNKNOWN;
const char *op = "appraise_data";
char *cause = "unknown";
- int rc;
+ int rc = xattr_len, hash_start = 0;
if (!ima_appraise)
return 0;
if (!inode->i_op->getxattr)
return INTEGRITY_UNKNOWN;
- rc = vfs_getxattr_alloc(dentry, XATTR_NAME_IMA, (char **)&xattr_value,
- 0, GFP_NOFS);
if (rc <= 0) {
if (rc && rc != -ENODATA)
goto out;
goto out;
}
switch (xattr_value->type) {
+ case IMA_XATTR_DIGEST_NG:
+ /* first byte contains algorithm id */
+ hash_start = 1;
case IMA_XATTR_DIGEST:
if (iint->flags & IMA_DIGSIG_REQUIRED) {
cause = "IMA signature required";
status = INTEGRITY_FAIL;
break;
}
- rc = memcmp(xattr_value->digest, iint->ima_xattr.digest,
- IMA_DIGEST_SIZE);
+ if (xattr_len - sizeof(xattr_value->type) - hash_start >=
+ iint->ima_hash->length)
+ /* xattr length may be longer. md5 hash in previous
+ version occupied 20 bytes in xattr, instead of 16
+ */
+ rc = memcmp(&xattr_value->digest[hash_start],
+ iint->ima_hash->digest,
+ iint->ima_hash->length);
+ else
+ rc = -EINVAL;
if (rc) {
cause = "invalid-hash";
status = INTEGRITY_FAIL;
case EVM_IMA_XATTR_DIGSIG:
iint->flags |= IMA_DIGSIG;
rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA,
- xattr_value->digest, rc - 1,
- iint->ima_xattr.digest,
- IMA_DIGEST_SIZE);
+ (const char *)xattr_value, rc,
+ iint->ima_hash->digest,
+ iint->ima_hash->length);
if (rc == -EOPNOTSUPP) {
status = INTEGRITY_UNKNOWN;
} else if (rc) {
ima_cache_flags(iint, func);
}
ima_set_cache_status(iint, func, status);
- kfree(xattr_value);
return status;
}
if (iint->flags & IMA_DIGSIG)
return;
- rc = ima_collect_measurement(iint, file);
+ rc = ima_collect_measurement(iint, file, NULL, NULL);
if (rc < 0)
return;
}
return result;
}
+
+#ifdef CONFIG_IMA_TRUSTED_KEYRING
+static int __init init_ima_keyring(void)
+{
+ int ret;
+
+ ret = integrity_init_keyring(INTEGRITY_KEYRING_IMA);
+ return 0;
+}
+late_initcall(init_ima_keyring);
+#endif
#include <linux/err.h>
#include <linux/slab.h>
#include <crypto/hash.h>
+#include <crypto/hash_info.h>
#include "ima.h"
static struct crypto_shash *ima_shash_tfm;
{
long rc;
- ima_shash_tfm = crypto_alloc_shash(ima_hash, 0, 0);
+ ima_shash_tfm = crypto_alloc_shash(hash_algo_name[ima_hash_algo], 0, 0);
if (IS_ERR(ima_shash_tfm)) {
rc = PTR_ERR(ima_shash_tfm);
- pr_err("Can not allocate %s (reason: %ld)\n", ima_hash, rc);
+ pr_err("Can not allocate %s (reason: %ld)\n",
+ hash_algo_name[ima_hash_algo], rc);
return rc;
}
return 0;
}
+static struct crypto_shash *ima_alloc_tfm(enum hash_algo algo)
+{
+ struct crypto_shash *tfm = ima_shash_tfm;
+ int rc;
+
+ if (algo != ima_hash_algo && algo < HASH_ALGO__LAST) {
+ tfm = crypto_alloc_shash(hash_algo_name[algo], 0, 0);
+ if (IS_ERR(tfm)) {
+ rc = PTR_ERR(tfm);
+ pr_err("Can not allocate %s (reason: %d)\n",
+ hash_algo_name[algo], rc);
+ }
+ }
+ return tfm;
+}
+
+static void ima_free_tfm(struct crypto_shash *tfm)
+{
+ if (tfm != ima_shash_tfm)
+ crypto_free_shash(tfm);
+}
+
/*
* Calculate the MD5/SHA1 file digest
*/
-int ima_calc_file_hash(struct file *file, char *digest)
+static int ima_calc_file_hash_tfm(struct file *file,
+ struct ima_digest_data *hash,
+ struct crypto_shash *tfm)
{
loff_t i_size, offset = 0;
char *rbuf;
int rc, read = 0;
struct {
struct shash_desc shash;
- char ctx[crypto_shash_descsize(ima_shash_tfm)];
+ char ctx[crypto_shash_descsize(tfm)];
} desc;
- desc.shash.tfm = ima_shash_tfm;
+ desc.shash.tfm = tfm;
desc.shash.flags = 0;
+ hash->length = crypto_shash_digestsize(tfm);
+
rc = crypto_shash_init(&desc.shash);
if (rc != 0)
return rc;
}
kfree(rbuf);
if (!rc)
- rc = crypto_shash_final(&desc.shash, digest);
+ rc = crypto_shash_final(&desc.shash, hash->digest);
if (read)
file->f_mode &= ~FMODE_READ;
out:
return rc;
}
+int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash)
+{
+ struct crypto_shash *tfm;
+ int rc;
+
+ tfm = ima_alloc_tfm(hash->algo);
+ if (IS_ERR(tfm))
+ return PTR_ERR(tfm);
+
+ rc = ima_calc_file_hash_tfm(file, hash, tfm);
+
+ ima_free_tfm(tfm);
+
+ return rc;
+}
+
/*
- * Calculate the hash of a given buffer
+ * Calculate the hash of template data
*/
-int ima_calc_buffer_hash(const void *data, int len, char *digest)
+static int ima_calc_field_array_hash_tfm(struct ima_field_data *field_data,
+ int num_fields,
+ struct ima_digest_data *hash,
+ struct crypto_shash *tfm)
{
struct {
struct shash_desc shash;
- char ctx[crypto_shash_descsize(ima_shash_tfm)];
+ char ctx[crypto_shash_descsize(tfm)];
} desc;
+ int rc, i;
- desc.shash.tfm = ima_shash_tfm;
+ desc.shash.tfm = tfm;
desc.shash.flags = 0;
- return crypto_shash_digest(&desc.shash, data, len, digest);
+ hash->length = crypto_shash_digestsize(tfm);
+
+ rc = crypto_shash_init(&desc.shash);
+ if (rc != 0)
+ return rc;
+
+ for (i = 0; i < num_fields; i++) {
+ rc = crypto_shash_update(&desc.shash,
+ (const u8 *) &field_data[i].len,
+ sizeof(field_data[i].len));
+ rc = crypto_shash_update(&desc.shash, field_data[i].data,
+ field_data[i].len);
+ if (rc)
+ break;
+ }
+
+ if (!rc)
+ rc = crypto_shash_final(&desc.shash, hash->digest);
+
+ return rc;
+}
+
+int ima_calc_field_array_hash(struct ima_field_data *field_data, int num_fields,
+ struct ima_digest_data *hash)
+{
+ struct crypto_shash *tfm;
+ int rc;
+
+ tfm = ima_alloc_tfm(hash->algo);
+ if (IS_ERR(tfm))
+ return PTR_ERR(tfm);
+
+ rc = ima_calc_field_array_hash_tfm(field_data, num_fields, hash, tfm);
+
+ ima_free_tfm(tfm);
+
+ return rc;
}
static void __init ima_pcrread(int idx, u8 *pcr)
/*
* Calculate the boot aggregate hash
*/
-int __init ima_calc_boot_aggregate(char *digest)
+static int __init ima_calc_boot_aggregate_tfm(char *digest,
+ struct crypto_shash *tfm)
{
- u8 pcr_i[IMA_DIGEST_SIZE];
+ u8 pcr_i[TPM_DIGEST_SIZE];
int rc, i;
struct {
struct shash_desc shash;
- char ctx[crypto_shash_descsize(ima_shash_tfm)];
+ char ctx[crypto_shash_descsize(tfm)];
} desc;
- desc.shash.tfm = ima_shash_tfm;
+ desc.shash.tfm = tfm;
desc.shash.flags = 0;
rc = crypto_shash_init(&desc.shash);
for (i = TPM_PCR0; i < TPM_PCR8; i++) {
ima_pcrread(i, pcr_i);
/* now accumulate with current aggregate */
- rc = crypto_shash_update(&desc.shash, pcr_i, IMA_DIGEST_SIZE);
+ rc = crypto_shash_update(&desc.shash, pcr_i, TPM_DIGEST_SIZE);
}
if (!rc)
crypto_shash_final(&desc.shash, digest);
return rc;
}
+
+int __init ima_calc_boot_aggregate(struct ima_digest_data *hash)
+{
+ struct crypto_shash *tfm;
+ int rc;
+
+ tfm = ima_alloc_tfm(hash->algo);
+ if (IS_ERR(tfm))
+ return PTR_ERR(tfm);
+
+ hash->length = crypto_shash_digestsize(tfm);
+ rc = ima_calc_boot_aggregate_tfm(hash->digest, tfm);
+
+ ima_free_tfm(tfm);
+
+ return rc;
+}
* against concurrent list-extension
*/
rcu_read_lock();
- qe = list_entry_rcu(qe->later.next,
- struct ima_queue_entry, later);
+ qe = list_entry_rcu(qe->later.next, struct ima_queue_entry, later);
rcu_read_unlock();
(*pos)++;
{
}
-static void ima_putc(struct seq_file *m, void *data, int datalen)
+void ima_putc(struct seq_file *m, void *data, int datalen)
{
while (datalen--)
seq_putc(m, *(char *)data++);
* char[20]=template digest
* 32bit-le=template name size
* char[n]=template name
+ * [eventdata length]
* eventdata[n]=template specific data
*/
static int ima_measurements_show(struct seq_file *m, void *v)
struct ima_template_entry *e;
int namelen;
u32 pcr = CONFIG_IMA_MEASURE_PCR_IDX;
+ int i;
/* get entry */
e = qe->entry;
ima_putc(m, &pcr, sizeof pcr);
/* 2nd: template digest */
- ima_putc(m, e->digest, IMA_DIGEST_SIZE);
+ ima_putc(m, e->digest, TPM_DIGEST_SIZE);
/* 3rd: template name size */
- namelen = strlen(e->template_name);
+ namelen = strlen(e->template_desc->name);
ima_putc(m, &namelen, sizeof namelen);
/* 4th: template name */
- ima_putc(m, (void *)e->template_name, namelen);
+ ima_putc(m, e->template_desc->name, namelen);
+
+ /* 5th: template length (except for 'ima' template) */
+ if (strcmp(e->template_desc->name, IMA_TEMPLATE_IMA_NAME) != 0)
+ ima_putc(m, &e->template_data_len,
+ sizeof(e->template_data_len));
- /* 5th: template specific data */
- ima_template_show(m, (struct ima_template_data *)&e->template,
- IMA_SHOW_BINARY);
+ /* 6th: template specific data */
+ for (i = 0; i < e->template_desc->num_fields; i++) {
+ e->template_desc->fields[i]->field_show(m, IMA_SHOW_BINARY,
+ &e->template_data[i]);
+ }
return 0;
}
.release = seq_release,
};
-static void ima_print_digest(struct seq_file *m, u8 *digest)
+void ima_print_digest(struct seq_file *m, u8 *digest, int size)
{
int i;
- for (i = 0; i < IMA_DIGEST_SIZE; i++)
+ for (i = 0; i < size; i++)
seq_printf(m, "%02x", *(digest + i));
}
-void ima_template_show(struct seq_file *m, void *e, enum ima_show_type show)
-{
- struct ima_template_data *entry = e;
- int namelen;
-
- switch (show) {
- case IMA_SHOW_ASCII:
- ima_print_digest(m, entry->digest);
- seq_printf(m, " %s\n", entry->file_name);
- break;
- case IMA_SHOW_BINARY:
- ima_putc(m, entry->digest, IMA_DIGEST_SIZE);
-
- namelen = strlen(entry->file_name);
- ima_putc(m, &namelen, sizeof namelen);
- ima_putc(m, entry->file_name, namelen);
- default:
- break;
- }
-}
-
/* print in ascii */
static int ima_ascii_measurements_show(struct seq_file *m, void *v)
{
/* the list never shrinks, so we don't need a lock here */
struct ima_queue_entry *qe = v;
struct ima_template_entry *e;
+ int i;
/* get entry */
e = qe->entry;
seq_printf(m, "%2d ", CONFIG_IMA_MEASURE_PCR_IDX);
/* 2nd: SHA1 template hash */
- ima_print_digest(m, e->digest);
+ ima_print_digest(m, e->digest, TPM_DIGEST_SIZE);
/* 3th: template name */
- seq_printf(m, " %s ", e->template_name);
+ seq_printf(m, " %s", e->template_desc->name);
/* 4th: template specific data */
- ima_template_show(m, (struct ima_template_data *)&e->template,
- IMA_SHOW_ASCII);
+ for (i = 0; i < e->template_desc->num_fields; i++) {
+ seq_puts(m, " ");
+ if (e->template_data[i].len == 0)
+ continue;
+
+ e->template_desc->fields[i]->field_show(m, IMA_SHOW_ASCII,
+ &e->template_data[i]);
+ }
+ seq_puts(m, "\n");
return 0;
}
#include <linux/scatterlist.h>
#include <linux/slab.h>
#include <linux/err.h>
+#include <crypto/hash_info.h>
#include "ima.h"
/* name for boot aggregate entry */
static void __init ima_add_boot_aggregate(void)
{
struct ima_template_entry *entry;
+ struct integrity_iint_cache tmp_iint, *iint = &tmp_iint;
const char *op = "add_boot_aggregate";
const char *audit_cause = "ENOMEM";
int result = -ENOMEM;
- int violation = 1;
+ int violation = 0;
+ struct {
+ struct ima_digest_data hdr;
+ char digest[TPM_DIGEST_SIZE];
+ } hash;
- entry = kmalloc(sizeof(*entry), GFP_KERNEL);
- if (!entry)
- goto err_out;
+ memset(iint, 0, sizeof(*iint));
+ memset(&hash, 0, sizeof(hash));
+ iint->ima_hash = &hash.hdr;
+ iint->ima_hash->algo = HASH_ALGO_SHA1;
+ iint->ima_hash->length = SHA1_DIGEST_SIZE;
- memset(&entry->template, 0, sizeof(entry->template));
- strncpy(entry->template.file_name, boot_aggregate_name,
- IMA_EVENT_NAME_LEN_MAX);
if (ima_used_chip) {
- violation = 0;
- result = ima_calc_boot_aggregate(entry->template.digest);
+ result = ima_calc_boot_aggregate(&hash.hdr);
if (result < 0) {
audit_cause = "hashing_error";
kfree(entry);
goto err_out;
}
}
- result = ima_store_template(entry, violation, NULL);
+
+ result = ima_alloc_init_template(iint, NULL, boot_aggregate_name,
+ NULL, 0, &entry);
+ if (result < 0)
+ return;
+
+ result = ima_store_template(entry, violation, NULL,
+ boot_aggregate_name);
if (result < 0)
kfree(entry);
return;
int __init ima_init(void)
{
- u8 pcr_i[IMA_DIGEST_SIZE];
+ u8 pcr_i[TPM_DIGEST_SIZE];
int rc;
ima_used_chip = 0;
rc = ima_init_crypto();
if (rc)
return rc;
+ rc = ima_init_template();
+ if (rc != 0)
+ return rc;
+
ima_add_boot_aggregate(); /* boot aggregate must be first entry */
ima_init_policy();
#include <linux/slab.h>
#include <linux/xattr.h>
#include <linux/ima.h>
+#include <crypto/hash_info.h>
#include "ima.h"
int ima_appraise;
#endif
-char *ima_hash = "sha1";
+int ima_hash_algo = HASH_ALGO_SHA1;
+static int hash_setup_done;
+
static int __init hash_setup(char *str)
{
- if (strncmp(str, "md5", 3) == 0)
- ima_hash = "md5";
+ struct ima_template_desc *template_desc = ima_template_desc_current();
+ int i;
+
+ if (hash_setup_done)
+ return 1;
+
+ if (strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) == 0) {
+ if (strncmp(str, "sha1", 4) == 0)
+ ima_hash_algo = HASH_ALGO_SHA1;
+ else if (strncmp(str, "md5", 3) == 0)
+ ima_hash_algo = HASH_ALGO_MD5;
+ goto out;
+ }
+
+ for (i = 0; i < HASH_ALGO__LAST; i++) {
+ if (strcmp(str, hash_algo_name[i]) == 0) {
+ ima_hash_algo = i;
+ break;
+ }
+ }
+out:
+ hash_setup_done = 1;
return 1;
}
__setup("ima_hash=", hash_setup);
pathname = dentry->d_name.name;
if (send_tomtou)
- ima_add_violation(inode, pathname,
- "invalid_pcr", "ToMToU");
+ ima_add_violation(file, pathname, "invalid_pcr", "ToMToU");
if (send_writers)
- ima_add_violation(inode, pathname,
+ ima_add_violation(file, pathname,
"invalid_pcr", "open_writers");
kfree(pathbuf);
}
{
struct inode *inode = file_inode(file);
struct integrity_iint_cache *iint;
+ struct ima_template_desc *template_desc = ima_template_desc_current();
char *pathbuf = NULL;
const char *pathname = NULL;
int rc = -ENOMEM, action, must_appraise, _func;
+ struct evm_ima_xattr_data *xattr_value = NULL, **xattr_ptr = NULL;
+ int xattr_len = 0;
if (!ima_initialized || !S_ISREG(inode->i_mode))
return 0;
goto out_digsig;
}
- rc = ima_collect_measurement(iint, file);
+ if (strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) == 0) {
+ if (action & IMA_APPRAISE_SUBMASK)
+ xattr_ptr = &xattr_value;
+ } else
+ xattr_ptr = &xattr_value;
+
+ rc = ima_collect_measurement(iint, file, xattr_ptr, &xattr_len);
if (rc != 0)
goto out_digsig;
pathname = (const char *)file->f_dentry->d_name.name;
if (action & IMA_MEASURE)
- ima_store_measurement(iint, file, pathname);
+ ima_store_measurement(iint, file, pathname,
+ xattr_value, xattr_len);
if (action & IMA_APPRAISE_SUBMASK)
- rc = ima_appraise_measurement(_func, iint, file, pathname);
+ rc = ima_appraise_measurement(_func, iint, file, pathname,
+ xattr_value, xattr_len);
if (action & IMA_AUDIT)
ima_audit_measurement(iint, pathname);
kfree(pathbuf);
rc = -EACCES;
out:
mutex_unlock(&inode->i_mutex);
+ kfree(xattr_value);
if ((rc && must_appraise) && (ima_appraise & IMA_APPRAISE_ENFORCE))
return -EACCES;
return 0;
int ima_bprm_check(struct linux_binprm *bprm)
{
return process_measurement(bprm->file,
- (strcmp(bprm->filename, bprm->interp) == 0) ?
- bprm->filename : bprm->interp,
- MAY_EXEC, BPRM_CHECK);
+ (strcmp(bprm->filename, bprm->interp) == 0) ?
+ bprm->filename : bprm->interp,
+ MAY_EXEC, BPRM_CHECK);
}
/**
{
ima_rdwr_violation_check(file);
return process_measurement(file, NULL,
- mask & (MAY_READ | MAY_WRITE | MAY_EXEC),
- FILE_CHECK);
+ mask & (MAY_READ | MAY_WRITE | MAY_EXEC),
+ FILE_CHECK);
}
EXPORT_SYMBOL_GPL(ima_file_check);
{
int error;
+ hash_setup(CONFIG_IMA_DEFAULT_HASH);
error = ima_init();
if (!error)
ima_initialized = 1;
{.action = DONT_MEASURE,.fsmagic = SYSFS_MAGIC,.flags = IMA_FSMAGIC},
{.action = DONT_MEASURE,.fsmagic = DEBUGFS_MAGIC,.flags = IMA_FSMAGIC},
{.action = DONT_MEASURE,.fsmagic = TMPFS_MAGIC,.flags = IMA_FSMAGIC},
- {.action = DONT_MEASURE,.fsmagic = RAMFS_MAGIC,.flags = IMA_FSMAGIC},
{.action = DONT_MEASURE,.fsmagic = DEVPTS_SUPER_MAGIC,.flags = IMA_FSMAGIC},
{.action = DONT_MEASURE,.fsmagic = BINFMTFS_MAGIC,.flags = IMA_FSMAGIC},
{.action = DONT_MEASURE,.fsmagic = SECURITYFS_MAGIC,.flags = IMA_FSMAGIC},
key = ima_hash_key(digest_value);
rcu_read_lock();
hlist_for_each_entry_rcu(qe, &ima_htable.queue[key], hnext) {
- rc = memcmp(qe->entry->digest, digest_value, IMA_DIGEST_SIZE);
+ rc = memcmp(qe->entry->digest, digest_value, TPM_DIGEST_SIZE);
if (rc == 0) {
ret = qe;
break;
* and extend the pcr.
*/
int ima_add_template_entry(struct ima_template_entry *entry, int violation,
- const char *op, struct inode *inode)
+ const char *op, struct inode *inode,
+ const unsigned char *filename)
{
- u8 digest[IMA_DIGEST_SIZE];
+ u8 digest[TPM_DIGEST_SIZE];
const char *audit_cause = "hash_added";
char tpm_audit_cause[AUDIT_CAUSE_LEN_MAX];
int audit_info = 1;
}
out:
mutex_unlock(&ima_extend_list_mutex);
- integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode,
- entry->template.file_name,
+ integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, filename,
op, audit_cause, result, audit_info);
return result;
}
--- /dev/null
+/*
+ * Copyright (C) 2013 Politecnico di Torino, Italy
+ * TORSEC group -- http://security.polito.it
+ *
+ * Author: Roberto Sassu <roberto.sassu@polito.it>
+ *
+ * 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, version 2 of the
+ * License.
+ *
+ * File: ima_template.c
+ * Helpers to manage template descriptors.
+ */
+#include <crypto/hash_info.h>
+
+#include "ima.h"
+#include "ima_template_lib.h"
+
+static struct ima_template_desc defined_templates[] = {
+ {.name = IMA_TEMPLATE_IMA_NAME, .fmt = IMA_TEMPLATE_IMA_FMT},
+ {.name = "ima-ng",.fmt = "d-ng|n-ng"},
+ {.name = "ima-sig",.fmt = "d-ng|n-ng|sig"},
+};
+
+static struct ima_template_field supported_fields[] = {
+ {.field_id = "d",.field_init = ima_eventdigest_init,
+ .field_show = ima_show_template_digest},
+ {.field_id = "n",.field_init = ima_eventname_init,
+ .field_show = ima_show_template_string},
+ {.field_id = "d-ng",.field_init = ima_eventdigest_ng_init,
+ .field_show = ima_show_template_digest_ng},
+ {.field_id = "n-ng",.field_init = ima_eventname_ng_init,
+ .field_show = ima_show_template_string},
+ {.field_id = "sig",.field_init = ima_eventsig_init,
+ .field_show = ima_show_template_sig},
+};
+
+static struct ima_template_desc *ima_template;
+static struct ima_template_desc *lookup_template_desc(const char *name);
+
+static int __init ima_template_setup(char *str)
+{
+ struct ima_template_desc *template_desc;
+ int template_len = strlen(str);
+
+ /*
+ * Verify that a template with the supplied name exists.
+ * If not, use CONFIG_IMA_DEFAULT_TEMPLATE.
+ */
+ template_desc = lookup_template_desc(str);
+ if (!template_desc)
+ return 1;
+
+ /*
+ * Verify whether the current hash algorithm is supported
+ * by the 'ima' template.
+ */
+ if (template_len == 3 && strcmp(str, IMA_TEMPLATE_IMA_NAME) == 0 &&
+ ima_hash_algo != HASH_ALGO_SHA1 && ima_hash_algo != HASH_ALGO_MD5) {
+ pr_err("IMA: template does not support hash alg\n");
+ return 1;
+ }
+
+ ima_template = template_desc;
+ return 1;
+}
+__setup("ima_template=", ima_template_setup);
+
+static struct ima_template_desc *lookup_template_desc(const char *name)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(defined_templates); i++) {
+ if (strcmp(defined_templates[i].name, name) == 0)
+ return defined_templates + i;
+ }
+
+ return NULL;
+}
+
+static struct ima_template_field *lookup_template_field(const char *field_id)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(supported_fields); i++)
+ if (strncmp(supported_fields[i].field_id, field_id,
+ IMA_TEMPLATE_FIELD_ID_MAX_LEN) == 0)
+ return &supported_fields[i];
+ return NULL;
+}
+
+static int template_fmt_size(char *template_fmt)
+{
+ char c;
+ int template_fmt_len = strlen(template_fmt);
+ int i = 0, j = 0;
+
+ while (i < template_fmt_len) {
+ c = template_fmt[i];
+ if (c == '|')
+ j++;
+ i++;
+ }
+
+ return j + 1;
+}
+
+static int template_desc_init_fields(char *template_fmt,
+ struct ima_template_field ***fields,
+ int *num_fields)
+{
+ char *c, *template_fmt_ptr = template_fmt;
+ int template_num_fields = template_fmt_size(template_fmt);
+ int i, result = 0;
+
+ if (template_num_fields > IMA_TEMPLATE_NUM_FIELDS_MAX)
+ return -EINVAL;
+
+ *fields = kzalloc(template_num_fields * sizeof(*fields), GFP_KERNEL);
+ if (*fields == NULL) {
+ result = -ENOMEM;
+ goto out;
+ }
+ for (i = 0; (c = strsep(&template_fmt_ptr, "|")) != NULL &&
+ i < template_num_fields; i++) {
+ struct ima_template_field *f = lookup_template_field(c);
+
+ if (!f) {
+ result = -ENOENT;
+ goto out;
+ }
+ (*fields)[i] = f;
+ }
+ *num_fields = i;
+ return 0;
+out:
+ kfree(*fields);
+ *fields = NULL;
+ return result;
+}
+
+static int init_defined_templates(void)
+{
+ int i = 0;
+ int result = 0;
+
+ /* Init defined templates. */
+ for (i = 0; i < ARRAY_SIZE(defined_templates); i++) {
+ struct ima_template_desc *template = &defined_templates[i];
+
+ result = template_desc_init_fields(template->fmt,
+ &(template->fields),
+ &(template->num_fields));
+ if (result < 0)
+ return result;
+ }
+ return result;
+}
+
+struct ima_template_desc *ima_template_desc_current(void)
+{
+ if (!ima_template)
+ ima_template =
+ lookup_template_desc(CONFIG_IMA_DEFAULT_TEMPLATE);
+ return ima_template;
+}
+
+int ima_init_template(void)
+{
+ int result;
+
+ result = init_defined_templates();
+ if (result < 0)
+ return result;
+
+ return 0;
+}
--- /dev/null
+/*
+ * Copyright (C) 2013 Politecnico di Torino, Italy
+ * TORSEC group -- http://security.polito.it
+ *
+ * Author: Roberto Sassu <roberto.sassu@polito.it>
+ *
+ * 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, version 2 of the
+ * License.
+ *
+ * File: ima_template_lib.c
+ * Library of supported template fields.
+ */
+#include <crypto/hash_info.h>
+
+#include "ima_template_lib.h"
+
+static bool ima_template_hash_algo_allowed(u8 algo)
+{
+ if (algo == HASH_ALGO_SHA1 || algo == HASH_ALGO_MD5)
+ return true;
+
+ return false;
+}
+
+enum data_formats {
+ DATA_FMT_DIGEST = 0,
+ DATA_FMT_DIGEST_WITH_ALGO,
+ DATA_FMT_EVENT_NAME,
+ DATA_FMT_STRING,
+ DATA_FMT_HEX
+};
+
+static int ima_write_template_field_data(const void *data, const u32 datalen,
+ enum data_formats datafmt,
+ struct ima_field_data *field_data)
+{
+ u8 *buf, *buf_ptr;
+ u32 buflen;
+
+ switch (datafmt) {
+ case DATA_FMT_EVENT_NAME:
+ buflen = IMA_EVENT_NAME_LEN_MAX + 1;
+ break;
+ case DATA_FMT_STRING:
+ buflen = datalen + 1;
+ break;
+ default:
+ buflen = datalen;
+ }
+
+ buf = kzalloc(buflen, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ memcpy(buf, data, datalen);
+
+ /*
+ * Replace all space characters with underscore for event names and
+ * strings. This avoid that, during the parsing of a measurements list,
+ * filenames with spaces or that end with the suffix ' (deleted)' are
+ * split into multiple template fields (the space is the delimitator
+ * character for measurements lists in ASCII format).
+ */
+ if (datafmt == DATA_FMT_EVENT_NAME || datafmt == DATA_FMT_STRING) {
+ for (buf_ptr = buf; buf_ptr - buf < datalen; buf_ptr++)
+ if (*buf_ptr == ' ')
+ *buf_ptr = '_';
+ }
+
+ field_data->data = buf;
+ field_data->len = buflen;
+ return 0;
+}
+
+static void ima_show_template_data_ascii(struct seq_file *m,
+ enum ima_show_type show,
+ enum data_formats datafmt,
+ struct ima_field_data *field_data)
+{
+ u8 *buf_ptr = field_data->data, buflen = field_data->len;
+
+ switch (datafmt) {
+ case DATA_FMT_DIGEST_WITH_ALGO:
+ buf_ptr = strnchr(field_data->data, buflen, ':');
+ if (buf_ptr != field_data->data)
+ seq_printf(m, "%s", field_data->data);
+
+ /* skip ':' and '\0' */
+ buf_ptr += 2;
+ buflen -= buf_ptr - field_data->data;
+ case DATA_FMT_DIGEST:
+ case DATA_FMT_HEX:
+ if (!buflen)
+ break;
+ ima_print_digest(m, buf_ptr, buflen);
+ break;
+ case DATA_FMT_STRING:
+ seq_printf(m, "%s", buf_ptr);
+ break;
+ default:
+ break;
+ }
+}
+
+static void ima_show_template_data_binary(struct seq_file *m,
+ enum ima_show_type show,
+ enum data_formats datafmt,
+ struct ima_field_data *field_data)
+{
+ ima_putc(m, &field_data->len, sizeof(u32));
+ if (!field_data->len)
+ return;
+ ima_putc(m, field_data->data, field_data->len);
+}
+
+static void ima_show_template_field_data(struct seq_file *m,
+ enum ima_show_type show,
+ enum data_formats datafmt,
+ struct ima_field_data *field_data)
+{
+ switch (show) {
+ case IMA_SHOW_ASCII:
+ ima_show_template_data_ascii(m, show, datafmt, field_data);
+ break;
+ case IMA_SHOW_BINARY:
+ ima_show_template_data_binary(m, show, datafmt, field_data);
+ break;
+ default:
+ break;
+ }
+}
+
+void ima_show_template_digest(struct seq_file *m, enum ima_show_type show,
+ struct ima_field_data *field_data)
+{
+ ima_show_template_field_data(m, show, DATA_FMT_DIGEST, field_data);
+}
+
+void ima_show_template_digest_ng(struct seq_file *m, enum ima_show_type show,
+ struct ima_field_data *field_data)
+{
+ ima_show_template_field_data(m, show, DATA_FMT_DIGEST_WITH_ALGO,
+ field_data);
+}
+
+void ima_show_template_string(struct seq_file *m, enum ima_show_type show,
+ struct ima_field_data *field_data)
+{
+ ima_show_template_field_data(m, show, DATA_FMT_STRING, field_data);
+}
+
+void ima_show_template_sig(struct seq_file *m, enum ima_show_type show,
+ struct ima_field_data *field_data)
+{
+ ima_show_template_field_data(m, show, DATA_FMT_HEX, field_data);
+}
+
+static int ima_eventdigest_init_common(u8 *digest, u32 digestsize, u8 hash_algo,
+ struct ima_field_data *field_data,
+ bool size_limit)
+{
+ /*
+ * digest formats:
+ * - DATA_FMT_DIGEST: digest
+ * - DATA_FMT_DIGEST_WITH_ALGO: [<hash algo>] + ':' + '\0' + digest,
+ * where <hash algo> is provided if the hash algoritm is not
+ * SHA1 or MD5
+ */
+ u8 buffer[CRYPTO_MAX_ALG_NAME + 2 + IMA_MAX_DIGEST_SIZE] = { 0 };
+ enum data_formats fmt = DATA_FMT_DIGEST;
+ u32 offset = 0;
+
+ if (!size_limit) {
+ fmt = DATA_FMT_DIGEST_WITH_ALGO;
+ if (hash_algo < HASH_ALGO__LAST)
+ offset += snprintf(buffer, CRYPTO_MAX_ALG_NAME + 1,
+ "%s", hash_algo_name[hash_algo]);
+ buffer[offset] = ':';
+ offset += 2;
+ }
+
+ if (digest)
+ memcpy(buffer + offset, digest, digestsize);
+ else
+ /*
+ * If digest is NULL, the event being recorded is a violation.
+ * Make room for the digest by increasing the offset of
+ * IMA_DIGEST_SIZE.
+ */
+ offset += IMA_DIGEST_SIZE;
+
+ return ima_write_template_field_data(buffer, offset + digestsize,
+ fmt, field_data);
+}
+
+/*
+ * This function writes the digest of an event (with size limit).
+ */
+int ima_eventdigest_init(struct integrity_iint_cache *iint, struct file *file,
+ const unsigned char *filename,
+ struct evm_ima_xattr_data *xattr_value, int xattr_len,
+ struct ima_field_data *field_data)
+{
+ struct {
+ struct ima_digest_data hdr;
+ char digest[IMA_MAX_DIGEST_SIZE];
+ } hash;
+ u8 *cur_digest = NULL;
+ u32 cur_digestsize = 0;
+ struct inode *inode;
+ int result;
+
+ memset(&hash, 0, sizeof(hash));
+
+ if (!iint) /* recording a violation. */
+ goto out;
+
+ if (ima_template_hash_algo_allowed(iint->ima_hash->algo)) {
+ cur_digest = iint->ima_hash->digest;
+ cur_digestsize = iint->ima_hash->length;
+ goto out;
+ }
+
+ if (!file) /* missing info to re-calculate the digest */
+ return -EINVAL;
+
+ inode = file_inode(file);
+ hash.hdr.algo = ima_template_hash_algo_allowed(ima_hash_algo) ?
+ ima_hash_algo : HASH_ALGO_SHA1;
+ result = ima_calc_file_hash(file, &hash.hdr);
+ if (result) {
+ integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode,
+ filename, "collect_data",
+ "failed", result, 0);
+ return result;
+ }
+ cur_digest = hash.hdr.digest;
+ cur_digestsize = hash.hdr.length;
+out:
+ return ima_eventdigest_init_common(cur_digest, cur_digestsize, -1,
+ field_data, true);
+}
+
+/*
+ * This function writes the digest of an event (without size limit).
+ */
+int ima_eventdigest_ng_init(struct integrity_iint_cache *iint,
+ struct file *file, const unsigned char *filename,
+ struct evm_ima_xattr_data *xattr_value,
+ int xattr_len, struct ima_field_data *field_data)
+{
+ u8 *cur_digest = NULL, hash_algo = HASH_ALGO__LAST;
+ u32 cur_digestsize = 0;
+
+ /* If iint is NULL, we are recording a violation. */
+ if (!iint)
+ goto out;
+
+ cur_digest = iint->ima_hash->digest;
+ cur_digestsize = iint->ima_hash->length;
+
+ hash_algo = iint->ima_hash->algo;
+out:
+ return ima_eventdigest_init_common(cur_digest, cur_digestsize,
+ hash_algo, field_data, false);
+}
+
+static int ima_eventname_init_common(struct integrity_iint_cache *iint,
+ struct file *file,
+ const unsigned char *filename,
+ struct ima_field_data *field_data,
+ bool size_limit)
+{
+ const char *cur_filename = NULL;
+ u32 cur_filename_len = 0;
+ enum data_formats fmt = size_limit ?
+ DATA_FMT_EVENT_NAME : DATA_FMT_STRING;
+
+ BUG_ON(filename == NULL && file == NULL);
+
+ if (filename) {
+ cur_filename = filename;
+ cur_filename_len = strlen(filename);
+
+ if (!size_limit || cur_filename_len <= IMA_EVENT_NAME_LEN_MAX)
+ goto out;
+ }
+
+ if (file) {
+ cur_filename = file->f_dentry->d_name.name;
+ cur_filename_len = strlen(cur_filename);
+ } else
+ /*
+ * Truncate filename if the latter is too long and
+ * the file descriptor is not available.
+ */
+ cur_filename_len = IMA_EVENT_NAME_LEN_MAX;
+out:
+ return ima_write_template_field_data(cur_filename, cur_filename_len,
+ fmt, field_data);
+}
+
+/*
+ * This function writes the name of an event (with size limit).
+ */
+int ima_eventname_init(struct integrity_iint_cache *iint, struct file *file,
+ const unsigned char *filename,
+ struct evm_ima_xattr_data *xattr_value, int xattr_len,
+ struct ima_field_data *field_data)
+{
+ return ima_eventname_init_common(iint, file, filename,
+ field_data, true);
+}
+
+/*
+ * This function writes the name of an event (without size limit).
+ */
+int ima_eventname_ng_init(struct integrity_iint_cache *iint, struct file *file,
+ const unsigned char *filename,
+ struct evm_ima_xattr_data *xattr_value, int xattr_len,
+ struct ima_field_data *field_data)
+{
+ return ima_eventname_init_common(iint, file, filename,
+ field_data, false);
+}
+
+/*
+ * ima_eventsig_init - include the file signature as part of the template data
+ */
+int ima_eventsig_init(struct integrity_iint_cache *iint, struct file *file,
+ const unsigned char *filename,
+ struct evm_ima_xattr_data *xattr_value, int xattr_len,
+ struct ima_field_data *field_data)
+{
+ enum data_formats fmt = DATA_FMT_HEX;
+ int rc = 0;
+
+ if ((!xattr_value) || (xattr_value->type != EVM_IMA_XATTR_DIGSIG))
+ goto out;
+
+ rc = ima_write_template_field_data(xattr_value, xattr_len, fmt,
+ field_data);
+out:
+ return rc;
+}
--- /dev/null
+/*
+ * Copyright (C) 2013 Politecnico di Torino, Italy
+ * TORSEC group -- http://security.polito.it
+ *
+ * Author: Roberto Sassu <roberto.sassu@polito.it>
+ *
+ * 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, version 2 of the
+ * License.
+ *
+ * File: ima_template_lib.h
+ * Header for the library of supported template fields.
+ */
+#ifndef __LINUX_IMA_TEMPLATE_LIB_H
+#define __LINUX_IMA_TEMPLATE_LIB_H
+
+#include <linux/seq_file.h>
+#include "ima.h"
+
+void ima_show_template_digest(struct seq_file *m, enum ima_show_type show,
+ struct ima_field_data *field_data);
+void ima_show_template_digest_ng(struct seq_file *m, enum ima_show_type show,
+ struct ima_field_data *field_data);
+void ima_show_template_string(struct seq_file *m, enum ima_show_type show,
+ struct ima_field_data *field_data);
+void ima_show_template_sig(struct seq_file *m, enum ima_show_type show,
+ struct ima_field_data *field_data);
+int ima_eventdigest_init(struct integrity_iint_cache *iint, struct file *file,
+ const unsigned char *filename,
+ struct evm_ima_xattr_data *xattr_value, int xattr_len,
+ struct ima_field_data *field_data);
+int ima_eventname_init(struct integrity_iint_cache *iint, struct file *file,
+ const unsigned char *filename,
+ struct evm_ima_xattr_data *xattr_value, int xattr_len,
+ struct ima_field_data *field_data);
+int ima_eventdigest_ng_init(struct integrity_iint_cache *iint,
+ struct file *file, const unsigned char *filename,
+ struct evm_ima_xattr_data *xattr_value,
+ int xattr_len, struct ima_field_data *field_data);
+int ima_eventname_ng_init(struct integrity_iint_cache *iint, struct file *file,
+ const unsigned char *filename,
+ struct evm_ima_xattr_data *xattr_value, int xattr_len,
+ struct ima_field_data *field_data);
+int ima_eventsig_init(struct integrity_iint_cache *iint, struct file *file,
+ const unsigned char *filename,
+ struct evm_ima_xattr_data *xattr_value, int xattr_len,
+ struct ima_field_data *field_data);
+#endif /* __LINUX_IMA_TEMPLATE_LIB_H */
IMA_XATTR_DIGEST = 0x01,
EVM_XATTR_HMAC,
EVM_IMA_XATTR_DIGSIG,
+ IMA_XATTR_DIGEST_NG,
};
struct evm_ima_xattr_data {
u8 type;
u8 digest[SHA1_DIGEST_SIZE];
-} __attribute__((packed));
+} __packed;
+
+#define IMA_MAX_DIGEST_SIZE 64
+
+struct ima_digest_data {
+ u8 algo;
+ u8 length;
+ union {
+ struct {
+ u8 unused;
+ u8 type;
+ } sha1;
+ struct {
+ u8 type;
+ u8 algo;
+ } ng;
+ u8 data[2];
+ } xattr;
+ u8 digest[0];
+} __packed;
+
+/*
+ * signature format v2 - for using with asymmetric keys
+ */
+struct signature_v2_hdr {
+ uint8_t type; /* xattr type */
+ uint8_t version; /* signature format version */
+ uint8_t hash_algo; /* Digest algorithm [enum pkey_hash_algo] */
+ uint32_t keyid; /* IMA key identifier - not X509/PGP specific */
+ uint16_t sig_size; /* signature size */
+ uint8_t sig[0]; /* signature payload */
+} __packed;
/* integrity data associated with an inode */
struct integrity_iint_cache {
- struct rb_node rb_node; /* rooted in integrity_iint_tree */
+ struct rb_node rb_node; /* rooted in integrity_iint_tree */
struct inode *inode; /* back pointer to inode in question */
u64 version; /* track inode changes */
unsigned long flags;
- struct evm_ima_xattr_data ima_xattr;
enum integrity_status ima_file_status:4;
enum integrity_status ima_mmap_status:4;
enum integrity_status ima_bprm_status:4;
enum integrity_status ima_module_status:4;
enum integrity_status evm_status:4;
+ struct ima_digest_data *ima_hash;
};
/* rbtree tree calls to lookup, insert, delete
#ifdef CONFIG_INTEGRITY_SIGNATURE
int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen,
- const char *digest, int digestlen);
+ const char *digest, int digestlen);
#else
#ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS
int asymmetric_verify(struct key *keyring, const char *sig,
int siglen, const char *data, int datalen);
+
+int integrity_init_keyring(const unsigned int id);
#else
static inline int asymmetric_verify(struct key *keyring, const char *sig,
int siglen, const char *data, int datalen)
{
return -EOPNOTSUPP;
}
+
+static int integrity_init_keyring(const unsigned int id)
+{
+ return 0;
+}
#endif
#ifdef CONFIG_INTEGRITY_AUDIT
config KEYS
bool "Enable access key retention support"
+ select ASSOCIATIVE_ARRAY
help
This option provides support for retaining authentication tokens and
access keys in the kernel.
If you are unsure as to whether this is required, answer N.
+config PERSISTENT_KEYRINGS
+ bool "Enable register of persistent per-UID keyrings"
+ depends on KEYS
+ help
+ This option provides a register of persistent per-UID keyrings,
+ primarily aimed at Kerberos key storage. The keyrings are persistent
+ in the sense that they stay around after all processes of that UID
+ have exited, not that they survive the machine being rebooted.
+
+ A particular keyring may be accessed by either the user whose keyring
+ it is or by a process with administrative privileges. The active
+ LSMs gets to rule on which admin-level processes get to access the
+ cache.
+
+ Keyrings are created and added into the register upon demand and get
+ removed if they expire (a default timeout is set upon creation).
+
+config BIG_KEYS
+ bool "Large payload keys"
+ depends on KEYS
+ depends on TMPFS
+ help
+ This option provides support for holding large keys within the kernel
+ (for example Kerberos ticket caches). The data may be stored out to
+ swapspace by tmpfs.
+
+ If you are unsure as to whether this is required, answer N.
+
config TRUSTED_KEYS
tristate "TRUSTED KEYS"
depends on KEYS && TCG_TPM
obj-$(CONFIG_KEYS_COMPAT) += compat.o
obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_SYSCTL) += sysctl.o
+obj-$(CONFIG_PERSISTENT_KEYRINGS) += persistent.o
#
# Key types
#
+obj-$(CONFIG_BIG_KEYS) += big_key.o
obj-$(CONFIG_TRUSTED_KEYS) += trusted.o
obj-$(CONFIG_ENCRYPTED_KEYS) += encrypted-keys/
--- /dev/null
+/* Large capacity key type
+ *
+ * Copyright (C) 2013 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/seq_file.h>
+#include <linux/file.h>
+#include <linux/shmem_fs.h>
+#include <linux/err.h>
+#include <keys/user-type.h>
+#include <keys/big_key-type.h>
+
+MODULE_LICENSE("GPL");
+
+/*
+ * If the data is under this limit, there's no point creating a shm file to
+ * hold it as the permanently resident metadata for the shmem fs will be at
+ * least as large as the data.
+ */
+#define BIG_KEY_FILE_THRESHOLD (sizeof(struct inode) + sizeof(struct dentry))
+
+/*
+ * big_key defined keys take an arbitrary string as the description and an
+ * arbitrary blob of data as the payload
+ */
+struct key_type key_type_big_key = {
+ .name = "big_key",
+ .def_lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT,
+ .instantiate = big_key_instantiate,
+ .match = user_match,
+ .revoke = big_key_revoke,
+ .destroy = big_key_destroy,
+ .describe = big_key_describe,
+ .read = big_key_read,
+};
+
+/*
+ * Instantiate a big key
+ */
+int big_key_instantiate(struct key *key, struct key_preparsed_payload *prep)
+{
+ struct path *path = (struct path *)&key->payload.data2;
+ struct file *file;
+ ssize_t written;
+ size_t datalen = prep->datalen;
+ int ret;
+
+ ret = -EINVAL;
+ if (datalen <= 0 || datalen > 1024 * 1024 || !prep->data)
+ goto error;
+
+ /* Set an arbitrary quota */
+ ret = key_payload_reserve(key, 16);
+ if (ret < 0)
+ goto error;
+
+ key->type_data.x[1] = datalen;
+
+ if (datalen > BIG_KEY_FILE_THRESHOLD) {
+ /* Create a shmem file to store the data in. This will permit the data
+ * to be swapped out if needed.
+ *
+ * TODO: Encrypt the stored data with a temporary key.
+ */
+ file = shmem_file_setup("", datalen, 0);
+ if (IS_ERR(file)) {
+ ret = PTR_ERR(file);
+ goto err_quota;
+ }
+
+ written = kernel_write(file, prep->data, prep->datalen, 0);
+ if (written != datalen) {
+ ret = written;
+ if (written >= 0)
+ ret = -ENOMEM;
+ goto err_fput;
+ }
+
+ /* Pin the mount and dentry to the key so that we can open it again
+ * later
+ */
+ *path = file->f_path;
+ path_get(path);
+ fput(file);
+ } else {
+ /* Just store the data in a buffer */
+ void *data = kmalloc(datalen, GFP_KERNEL);
+ if (!data) {
+ ret = -ENOMEM;
+ goto err_quota;
+ }
+
+ key->payload.data = memcpy(data, prep->data, prep->datalen);
+ }
+ return 0;
+
+err_fput:
+ fput(file);
+err_quota:
+ key_payload_reserve(key, 0);
+error:
+ return ret;
+}
+
+/*
+ * dispose of the links from a revoked keyring
+ * - called with the key sem write-locked
+ */
+void big_key_revoke(struct key *key)
+{
+ struct path *path = (struct path *)&key->payload.data2;
+
+ /* clear the quota */
+ key_payload_reserve(key, 0);
+ if (key_is_instantiated(key) && key->type_data.x[1] > BIG_KEY_FILE_THRESHOLD)
+ vfs_truncate(path, 0);
+}
+
+/*
+ * dispose of the data dangling from the corpse of a big_key key
+ */
+void big_key_destroy(struct key *key)
+{
+ if (key->type_data.x[1] > BIG_KEY_FILE_THRESHOLD) {
+ struct path *path = (struct path *)&key->payload.data2;
+ path_put(path);
+ path->mnt = NULL;
+ path->dentry = NULL;
+ } else {
+ kfree(key->payload.data);
+ key->payload.data = NULL;
+ }
+}
+
+/*
+ * describe the big_key key
+ */
+void big_key_describe(const struct key *key, struct seq_file *m)
+{
+ unsigned long datalen = key->type_data.x[1];
+
+ seq_puts(m, key->description);
+
+ if (key_is_instantiated(key))
+ seq_printf(m, ": %lu [%s]",
+ datalen,
+ datalen > BIG_KEY_FILE_THRESHOLD ? "file" : "buff");
+}
+
+/*
+ * read the key data
+ * - the key's semaphore is read-locked
+ */
+long big_key_read(const struct key *key, char __user *buffer, size_t buflen)
+{
+ unsigned long datalen = key->type_data.x[1];
+ long ret;
+
+ if (!buffer || buflen < datalen)
+ return datalen;
+
+ if (datalen > BIG_KEY_FILE_THRESHOLD) {
+ struct path *path = (struct path *)&key->payload.data2;
+ struct file *file;
+ loff_t pos;
+
+ file = dentry_open(path, O_RDONLY, current_cred());
+ if (IS_ERR(file))
+ return PTR_ERR(file);
+
+ pos = 0;
+ ret = vfs_read(file, buffer, datalen, &pos);
+ fput(file);
+ if (ret >= 0 && ret != datalen)
+ ret = -EIO;
+ } else {
+ ret = datalen;
+ if (copy_to_user(buffer, key->payload.data, datalen) != 0)
+ ret = -EFAULT;
+ }
+
+ return ret;
+}
+
+/*
+ * Module stuff
+ */
+static int __init big_key_init(void)
+{
+ return register_key_type(&key_type_big_key);
+}
+
+static void __exit big_key_cleanup(void)
+{
+ unregister_key_type(&key_type_big_key);
+}
+
+module_init(big_key_init);
+module_exit(big_key_cleanup);
case KEYCTL_INVALIDATE:
return keyctl_invalidate_key(arg2);
+ case KEYCTL_GET_PERSISTENT:
+ return keyctl_get_persistent(arg2, arg3);
+
default:
return -EOPNOTSUPP;
}
kleave("");
}
-/*
- * Garbage collect pointers from a keyring.
- *
- * Not called with any locks held. The keyring's key struct will not be
- * deallocated under us as only our caller may deallocate it.
- */
-static void key_gc_keyring(struct key *keyring, time_t limit)
-{
- struct keyring_list *klist;
- int loop;
-
- kenter("%x", key_serial(keyring));
-
- if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) |
- (1 << KEY_FLAG_REVOKED)))
- goto dont_gc;
-
- /* scan the keyring looking for dead keys */
- rcu_read_lock();
- klist = rcu_dereference(keyring->payload.subscriptions);
- if (!klist)
- goto unlock_dont_gc;
-
- loop = klist->nkeys;
- smp_rmb();
- for (loop--; loop >= 0; loop--) {
- struct key *key = rcu_dereference(klist->keys[loop]);
- if (key_is_dead(key, limit))
- goto do_gc;
- }
-
-unlock_dont_gc:
- rcu_read_unlock();
-dont_gc:
- kleave(" [no gc]");
- return;
-
-do_gc:
- rcu_read_unlock();
-
- keyring_gc(keyring, limit);
- kleave(" [gc]");
-}
-
/*
* Garbage collect a list of unreferenced, detached keys
*/
*/
found_keyring:
spin_unlock(&key_serial_lock);
- kdebug("scan keyring %d", key->serial);
- key_gc_keyring(key, limit);
+ keyring_gc(key, limit);
goto maybe_resched;
/* We found a dead key that is still referenced. Reset its type and
extern void key_type_put(struct key_type *ktype);
extern int __key_link_begin(struct key *keyring,
- const struct key_type *type,
- const char *description,
- unsigned long *_prealloc);
+ const struct keyring_index_key *index_key,
+ struct assoc_array_edit **_edit);
extern int __key_link_check_live_key(struct key *keyring, struct key *key);
-extern void __key_link(struct key *keyring, struct key *key,
- unsigned long *_prealloc);
+extern void __key_link(struct key *key, struct assoc_array_edit **_edit);
extern void __key_link_end(struct key *keyring,
- struct key_type *type,
- unsigned long prealloc);
+ const struct keyring_index_key *index_key,
+ struct assoc_array_edit *edit);
-extern key_ref_t __keyring_search_one(key_ref_t keyring_ref,
- const struct key_type *type,
- const char *description,
- key_perm_t perm);
+extern key_ref_t find_key_to_update(key_ref_t keyring_ref,
+ const struct keyring_index_key *index_key);
extern struct key *keyring_search_instkey(struct key *keyring,
key_serial_t target_id);
+extern int iterate_over_keyring(const struct key *keyring,
+ int (*func)(const struct key *key, void *data),
+ void *data);
+
typedef int (*key_match_func_t)(const struct key *, const void *);
+struct keyring_search_context {
+ struct keyring_index_key index_key;
+ const struct cred *cred;
+ key_match_func_t match;
+ const void *match_data;
+ unsigned flags;
+#define KEYRING_SEARCH_LOOKUP_TYPE 0x0001 /* [as type->def_lookup_type] */
+#define KEYRING_SEARCH_NO_STATE_CHECK 0x0002 /* Skip state checks */
+#define KEYRING_SEARCH_DO_STATE_CHECK 0x0004 /* Override NO_STATE_CHECK */
+#define KEYRING_SEARCH_NO_UPDATE_TIME 0x0008 /* Don't update times */
+#define KEYRING_SEARCH_NO_CHECK_PERM 0x0010 /* Don't check permissions */
+#define KEYRING_SEARCH_DETECT_TOO_DEEP 0x0020 /* Give an error on excessive depth */
+
+ int (*iterator)(const void *object, void *iterator_data);
+
+ /* Internal stuff */
+ int skipped_ret;
+ bool possessed;
+ key_ref_t result;
+ struct timespec now;
+};
+
extern key_ref_t keyring_search_aux(key_ref_t keyring_ref,
- const struct cred *cred,
- struct key_type *type,
- const void *description,
- key_match_func_t match,
- bool no_state_check);
-
-extern key_ref_t search_my_process_keyrings(struct key_type *type,
- const void *description,
- key_match_func_t match,
- bool no_state_check,
- const struct cred *cred);
-extern key_ref_t search_process_keyrings(struct key_type *type,
- const void *description,
- key_match_func_t match,
- const struct cred *cred);
+ struct keyring_search_context *ctx);
+
+extern key_ref_t search_my_process_keyrings(struct keyring_search_context *ctx);
+extern key_ref_t search_process_keyrings(struct keyring_search_context *ctx);
extern struct key *find_keyring_by_name(const char *name, bool skip_perm_check);
/*
* Determine whether a key is dead.
*/
-static inline bool key_is_dead(struct key *key, time_t limit)
+static inline bool key_is_dead(const struct key *key, time_t limit)
{
return
key->flags & ((1 << KEY_FLAG_DEAD) |
extern long keyctl_instantiate_key_common(key_serial_t,
const struct iovec *,
unsigned, size_t, key_serial_t);
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+extern long keyctl_get_persistent(uid_t, key_serial_t);
+extern unsigned persistent_keyring_expiry;
+#else
+static inline long keyctl_get_persistent(uid_t uid, key_serial_t destring)
+{
+ return -EOPNOTSUPP;
+}
+#endif
/*
* Debugging key validation
}
}
- desclen = strlen(desc) + 1;
- quotalen = desclen + type->def_datalen;
+ desclen = strlen(desc);
+ quotalen = desclen + 1 + type->def_datalen;
/* get hold of the key tracking for this user */
user = key_user_lookup(uid);
goto no_memory_2;
if (desc) {
- key->description = kmemdup(desc, desclen, GFP_KERNEL);
+ key->index_key.desc_len = desclen;
+ key->index_key.description = kmemdup(desc, desclen + 1, GFP_KERNEL);
if (!key->description)
goto no_memory_3;
}
atomic_set(&key->usage, 1);
init_rwsem(&key->sem);
lockdep_set_class(&key->sem, &type->lock_class);
- key->type = type;
+ key->index_key.type = type;
key->user = user;
key->quotalen = quotalen;
key->datalen = type->def_datalen;
if (!(flags & KEY_ALLOC_NOT_IN_QUOTA))
key->flags |= 1 << KEY_FLAG_IN_QUOTA;
+ if (flags & KEY_ALLOC_TRUSTED)
+ key->flags |= 1 << KEY_FLAG_TRUSTED;
memset(&key->type_data, 0, sizeof(key->type_data));
struct key_preparsed_payload *prep,
struct key *keyring,
struct key *authkey,
- unsigned long *_prealloc)
+ struct assoc_array_edit **_edit)
{
int ret, awaken;
/* and link it into the destination keyring */
if (keyring)
- __key_link(keyring, key, _prealloc);
+ __key_link(key, _edit);
/* disable the authorisation key */
if (authkey)
struct key *authkey)
{
struct key_preparsed_payload prep;
- unsigned long prealloc;
+ struct assoc_array_edit *edit;
int ret;
memset(&prep, 0, sizeof(prep));
}
if (keyring) {
- ret = __key_link_begin(keyring, key->type, key->description,
- &prealloc);
+ ret = __key_link_begin(keyring, &key->index_key, &edit);
if (ret < 0)
goto error_free_preparse;
}
- ret = __key_instantiate_and_link(key, &prep, keyring, authkey,
- &prealloc);
+ ret = __key_instantiate_and_link(key, &prep, keyring, authkey, &edit);
if (keyring)
- __key_link_end(keyring, key->type, prealloc);
+ __key_link_end(keyring, &key->index_key, edit);
error_free_preparse:
if (key->type->preparse)
struct key *keyring,
struct key *authkey)
{
- unsigned long prealloc;
+ struct assoc_array_edit *edit;
struct timespec now;
int ret, awaken, link_ret = 0;
ret = -EBUSY;
if (keyring)
- link_ret = __key_link_begin(keyring, key->type,
- key->description, &prealloc);
+ link_ret = __key_link_begin(keyring, &key->index_key, &edit);
mutex_lock(&key_construction_mutex);
if (!test_bit(KEY_FLAG_INSTANTIATED, &key->flags)) {
/* mark the key as being negatively instantiated */
atomic_inc(&key->user->nikeys);
+ key->type_data.reject_error = -error;
+ smp_wmb();
set_bit(KEY_FLAG_NEGATIVE, &key->flags);
set_bit(KEY_FLAG_INSTANTIATED, &key->flags);
- key->type_data.reject_error = -error;
now = current_kernel_time();
key->expiry = now.tv_sec + timeout;
key_schedule_gc(key->expiry + key_gc_delay);
/* and link it into the destination keyring */
if (keyring && link_ret == 0)
- __key_link(keyring, key, &prealloc);
+ __key_link(key, &edit);
/* disable the authorisation key */
if (authkey)
mutex_unlock(&key_construction_mutex);
if (keyring)
- __key_link_end(keyring, key->type, prealloc);
+ __key_link_end(keyring, &key->index_key, edit);
/* wake up anyone waiting for a key to be constructed */
if (awaken)
/* this races with key_put(), but that doesn't matter since key_put()
* doesn't actually change the key
*/
- atomic_inc(&key->usage);
+ __key_get(key);
error:
spin_unlock(&key_serial_lock);
key_perm_t perm,
unsigned long flags)
{
- unsigned long prealloc;
+ struct keyring_index_key index_key = {
+ .description = description,
+ };
struct key_preparsed_payload prep;
+ struct assoc_array_edit *edit;
const struct cred *cred = current_cred();
- struct key_type *ktype;
struct key *keyring, *key = NULL;
key_ref_t key_ref;
int ret;
/* look up the key type to see if it's one of the registered kernel
* types */
- ktype = key_type_lookup(type);
- if (IS_ERR(ktype)) {
+ index_key.type = key_type_lookup(type);
+ if (IS_ERR(index_key.type)) {
key_ref = ERR_PTR(-ENODEV);
goto error;
}
key_ref = ERR_PTR(-EINVAL);
- if (!ktype->match || !ktype->instantiate ||
- (!description && !ktype->preparse))
+ if (!index_key.type->match || !index_key.type->instantiate ||
+ (!index_key.description && !index_key.type->preparse))
goto error_put_type;
keyring = key_ref_to_ptr(keyring_ref);
memset(&prep, 0, sizeof(prep));
prep.data = payload;
prep.datalen = plen;
- prep.quotalen = ktype->def_datalen;
- if (ktype->preparse) {
- ret = ktype->preparse(&prep);
+ prep.quotalen = index_key.type->def_datalen;
+ prep.trusted = flags & KEY_ALLOC_TRUSTED;
+ if (index_key.type->preparse) {
+ ret = index_key.type->preparse(&prep);
if (ret < 0) {
key_ref = ERR_PTR(ret);
goto error_put_type;
}
- if (!description)
- description = prep.description;
+ if (!index_key.description)
+ index_key.description = prep.description;
key_ref = ERR_PTR(-EINVAL);
- if (!description)
+ if (!index_key.description)
goto error_free_prep;
}
+ index_key.desc_len = strlen(index_key.description);
+
+ key_ref = ERR_PTR(-EPERM);
+ if (!prep.trusted && test_bit(KEY_FLAG_TRUSTED_ONLY, &keyring->flags))
+ goto error_free_prep;
+ flags |= prep.trusted ? KEY_ALLOC_TRUSTED : 0;
- ret = __key_link_begin(keyring, ktype, description, &prealloc);
+ ret = __key_link_begin(keyring, &index_key, &edit);
if (ret < 0) {
key_ref = ERR_PTR(ret);
goto error_free_prep;
* key of the same type and description in the destination keyring and
* update that instead if possible
*/
- if (ktype->update) {
- key_ref = __keyring_search_one(keyring_ref, ktype, description,
- 0);
- if (!IS_ERR(key_ref))
+ if (index_key.type->update) {
+ key_ref = find_key_to_update(keyring_ref, &index_key);
+ if (key_ref)
goto found_matching_key;
}
perm = KEY_POS_VIEW | KEY_POS_SEARCH | KEY_POS_LINK | KEY_POS_SETATTR;
perm |= KEY_USR_VIEW;
- if (ktype->read)
+ if (index_key.type->read)
perm |= KEY_POS_READ;
- if (ktype == &key_type_keyring || ktype->update)
+ if (index_key.type == &key_type_keyring ||
+ index_key.type->update)
perm |= KEY_POS_WRITE;
}
/* allocate a new key */
- key = key_alloc(ktype, description, cred->fsuid, cred->fsgid, cred,
- perm, flags);
+ key = key_alloc(index_key.type, index_key.description,
+ cred->fsuid, cred->fsgid, cred, perm, flags);
if (IS_ERR(key)) {
key_ref = ERR_CAST(key);
goto error_link_end;
}
/* instantiate it and link it into the target keyring */
- ret = __key_instantiate_and_link(key, &prep, keyring, NULL, &prealloc);
+ ret = __key_instantiate_and_link(key, &prep, keyring, NULL, &edit);
if (ret < 0) {
key_put(key);
key_ref = ERR_PTR(ret);
key_ref = make_key_ref(key, is_key_possessed(keyring_ref));
error_link_end:
- __key_link_end(keyring, ktype, prealloc);
+ __key_link_end(keyring, &index_key, edit);
error_free_prep:
- if (ktype->preparse)
- ktype->free_preparse(&prep);
+ if (index_key.type->preparse)
+ index_key.type->free_preparse(&prep);
error_put_type:
- key_type_put(ktype);
+ key_type_put(index_key.type);
error:
return key_ref;
/* we found a matching key, so we're going to try to update it
* - we can drop the locks first as we have the key pinned
*/
- __key_link_end(keyring, ktype, prealloc);
+ __key_link_end(keyring, &index_key, edit);
key_ref = __key_update(key_ref, &prep);
goto error_free_prep;
case KEYCTL_INVALIDATE:
return keyctl_invalidate_key((key_serial_t) arg2);
+ case KEYCTL_GET_PERSISTENT:
+ return keyctl_get_persistent((uid_t)arg2, (key_serial_t)arg3);
+
default:
return -EOPNOTSUPP;
}
/* Keyring handling
*
- * Copyright (C) 2004-2005, 2008 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2004-2005, 2008, 2013 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
#include <linux/seq_file.h>
#include <linux/err.h>
#include <keys/keyring-type.h>
+#include <keys/user-type.h>
+#include <linux/assoc_array_priv.h>
#include <linux/uaccess.h>
#include "internal.h"
-#define rcu_dereference_locked_keyring(keyring) \
- (rcu_dereference_protected( \
- (keyring)->payload.subscriptions, \
- rwsem_is_locked((struct rw_semaphore *)&(keyring)->sem)))
-
-#define rcu_deref_link_locked(klist, index, keyring) \
- (rcu_dereference_protected( \
- (klist)->keys[index], \
- rwsem_is_locked((struct rw_semaphore *)&(keyring)->sem)))
-
-#define MAX_KEYRING_LINKS \
- min_t(size_t, USHRT_MAX - 1, \
- ((PAGE_SIZE - sizeof(struct keyring_list)) / sizeof(struct key *)))
-
-#define KEY_LINK_FIXQUOTA 1UL
-
/*
* When plumbing the depths of the key tree, this sets a hard limit
* set on how deep we're willing to go.
*/
#define KEYRING_NAME_HASH_SIZE (1 << 5)
+/*
+ * We mark pointers we pass to the associative array with bit 1 set if
+ * they're keyrings and clear otherwise.
+ */
+#define KEYRING_PTR_SUBTYPE 0x2UL
+
+static inline bool keyring_ptr_is_keyring(const struct assoc_array_ptr *x)
+{
+ return (unsigned long)x & KEYRING_PTR_SUBTYPE;
+}
+static inline struct key *keyring_ptr_to_key(const struct assoc_array_ptr *x)
+{
+ void *object = assoc_array_ptr_to_leaf(x);
+ return (struct key *)((unsigned long)object & ~KEYRING_PTR_SUBTYPE);
+}
+static inline void *keyring_key_to_ptr(struct key *key)
+{
+ if (key->type == &key_type_keyring)
+ return (void *)((unsigned long)key | KEYRING_PTR_SUBTYPE);
+ return key;
+}
+
static struct list_head keyring_name_hash[KEYRING_NAME_HASH_SIZE];
static DEFINE_RWLOCK(keyring_name_lock);
*/
static int keyring_instantiate(struct key *keyring,
struct key_preparsed_payload *prep);
-static int keyring_match(const struct key *keyring, const void *criterion);
static void keyring_revoke(struct key *keyring);
static void keyring_destroy(struct key *keyring);
static void keyring_describe(const struct key *keyring, struct seq_file *m);
struct key_type key_type_keyring = {
.name = "keyring",
- .def_datalen = sizeof(struct keyring_list),
+ .def_datalen = 0,
.instantiate = keyring_instantiate,
- .match = keyring_match,
+ .match = user_match,
.revoke = keyring_revoke,
.destroy = keyring_destroy,
.describe = keyring_describe,
ret = -EINVAL;
if (prep->datalen == 0) {
+ assoc_array_init(&keyring->keys);
/* make the keyring available by name if it has one */
keyring_publish_name(keyring);
ret = 0;
}
/*
- * Match keyrings on their name
+ * Multiply 64-bits by 32-bits to 96-bits and fold back to 64-bit. Ideally we'd
+ * fold the carry back too, but that requires inline asm.
+ */
+static u64 mult_64x32_and_fold(u64 x, u32 y)
+{
+ u64 hi = (u64)(u32)(x >> 32) * y;
+ u64 lo = (u64)(u32)(x) * y;
+ return lo + ((u64)(u32)hi << 32) + (u32)(hi >> 32);
+}
+
+/*
+ * Hash a key type and description.
+ */
+static unsigned long hash_key_type_and_desc(const struct keyring_index_key *index_key)
+{
+ const unsigned level_shift = ASSOC_ARRAY_LEVEL_STEP;
+ const unsigned long level_mask = ASSOC_ARRAY_LEVEL_STEP_MASK;
+ const char *description = index_key->description;
+ unsigned long hash, type;
+ u32 piece;
+ u64 acc;
+ int n, desc_len = index_key->desc_len;
+
+ type = (unsigned long)index_key->type;
+
+ acc = mult_64x32_and_fold(type, desc_len + 13);
+ acc = mult_64x32_and_fold(acc, 9207);
+ for (;;) {
+ n = desc_len;
+ if (n <= 0)
+ break;
+ if (n > 4)
+ n = 4;
+ piece = 0;
+ memcpy(&piece, description, n);
+ description += n;
+ desc_len -= n;
+ acc = mult_64x32_and_fold(acc, piece);
+ acc = mult_64x32_and_fold(acc, 9207);
+ }
+
+ /* Fold the hash down to 32 bits if need be. */
+ hash = acc;
+ if (ASSOC_ARRAY_KEY_CHUNK_SIZE == 32)
+ hash ^= acc >> 32;
+
+ /* Squidge all the keyrings into a separate part of the tree to
+ * ordinary keys by making sure the lowest level segment in the hash is
+ * zero for keyrings and non-zero otherwise.
+ */
+ if (index_key->type != &key_type_keyring && (hash & level_mask) == 0)
+ return hash | (hash >> (ASSOC_ARRAY_KEY_CHUNK_SIZE - level_shift)) | 1;
+ if (index_key->type == &key_type_keyring && (hash & level_mask) != 0)
+ return (hash + (hash << level_shift)) & ~level_mask;
+ return hash;
+}
+
+/*
+ * Build the next index key chunk.
+ *
+ * On 32-bit systems the index key is laid out as:
+ *
+ * 0 4 5 9...
+ * hash desclen typeptr desc[]
+ *
+ * On 64-bit systems:
+ *
+ * 0 8 9 17...
+ * hash desclen typeptr desc[]
+ *
+ * We return it one word-sized chunk at a time.
*/
-static int keyring_match(const struct key *keyring, const void *description)
+static unsigned long keyring_get_key_chunk(const void *data, int level)
+{
+ const struct keyring_index_key *index_key = data;
+ unsigned long chunk = 0;
+ long offset = 0;
+ int desc_len = index_key->desc_len, n = sizeof(chunk);
+
+ level /= ASSOC_ARRAY_KEY_CHUNK_SIZE;
+ switch (level) {
+ case 0:
+ return hash_key_type_and_desc(index_key);
+ case 1:
+ return ((unsigned long)index_key->type << 8) | desc_len;
+ case 2:
+ if (desc_len == 0)
+ return (u8)((unsigned long)index_key->type >>
+ (ASSOC_ARRAY_KEY_CHUNK_SIZE - 8));
+ n--;
+ offset = 1;
+ default:
+ offset += sizeof(chunk) - 1;
+ offset += (level - 3) * sizeof(chunk);
+ if (offset >= desc_len)
+ return 0;
+ desc_len -= offset;
+ if (desc_len > n)
+ desc_len = n;
+ offset += desc_len;
+ do {
+ chunk <<= 8;
+ chunk |= ((u8*)index_key->description)[--offset];
+ } while (--desc_len > 0);
+
+ if (level == 2) {
+ chunk <<= 8;
+ chunk |= (u8)((unsigned long)index_key->type >>
+ (ASSOC_ARRAY_KEY_CHUNK_SIZE - 8));
+ }
+ return chunk;
+ }
+}
+
+static unsigned long keyring_get_object_key_chunk(const void *object, int level)
+{
+ const struct key *key = keyring_ptr_to_key(object);
+ return keyring_get_key_chunk(&key->index_key, level);
+}
+
+static bool keyring_compare_object(const void *object, const void *data)
{
- return keyring->description &&
- strcmp(keyring->description, description) == 0;
+ const struct keyring_index_key *index_key = data;
+ const struct key *key = keyring_ptr_to_key(object);
+
+ return key->index_key.type == index_key->type &&
+ key->index_key.desc_len == index_key->desc_len &&
+ memcmp(key->index_key.description, index_key->description,
+ index_key->desc_len) == 0;
}
+/*
+ * Compare the index keys of a pair of objects and determine the bit position
+ * at which they differ - if they differ.
+ */
+static int keyring_diff_objects(const void *_a, const void *_b)
+{
+ const struct key *key_a = keyring_ptr_to_key(_a);
+ const struct key *key_b = keyring_ptr_to_key(_b);
+ const struct keyring_index_key *a = &key_a->index_key;
+ const struct keyring_index_key *b = &key_b->index_key;
+ unsigned long seg_a, seg_b;
+ int level, i;
+
+ level = 0;
+ seg_a = hash_key_type_and_desc(a);
+ seg_b = hash_key_type_and_desc(b);
+ if ((seg_a ^ seg_b) != 0)
+ goto differ;
+
+ /* The number of bits contributed by the hash is controlled by a
+ * constant in the assoc_array headers. Everything else thereafter we
+ * can deal with as being machine word-size dependent.
+ */
+ level += ASSOC_ARRAY_KEY_CHUNK_SIZE / 8;
+ seg_a = a->desc_len;
+ seg_b = b->desc_len;
+ if ((seg_a ^ seg_b) != 0)
+ goto differ;
+
+ /* The next bit may not work on big endian */
+ level++;
+ seg_a = (unsigned long)a->type;
+ seg_b = (unsigned long)b->type;
+ if ((seg_a ^ seg_b) != 0)
+ goto differ;
+
+ level += sizeof(unsigned long);
+ if (a->desc_len == 0)
+ goto same;
+
+ i = 0;
+ if (((unsigned long)a->description | (unsigned long)b->description) &
+ (sizeof(unsigned long) - 1)) {
+ do {
+ seg_a = *(unsigned long *)(a->description + i);
+ seg_b = *(unsigned long *)(b->description + i);
+ if ((seg_a ^ seg_b) != 0)
+ goto differ_plus_i;
+ i += sizeof(unsigned long);
+ } while (i < (a->desc_len & (sizeof(unsigned long) - 1)));
+ }
+
+ for (; i < a->desc_len; i++) {
+ seg_a = *(unsigned char *)(a->description + i);
+ seg_b = *(unsigned char *)(b->description + i);
+ if ((seg_a ^ seg_b) != 0)
+ goto differ_plus_i;
+ }
+
+same:
+ return -1;
+
+differ_plus_i:
+ level += i;
+differ:
+ i = level * 8 + __ffs(seg_a ^ seg_b);
+ return i;
+}
+
+/*
+ * Free an object after stripping the keyring flag off of the pointer.
+ */
+static void keyring_free_object(void *object)
+{
+ key_put(keyring_ptr_to_key(object));
+}
+
+/*
+ * Operations for keyring management by the index-tree routines.
+ */
+static const struct assoc_array_ops keyring_assoc_array_ops = {
+ .get_key_chunk = keyring_get_key_chunk,
+ .get_object_key_chunk = keyring_get_object_key_chunk,
+ .compare_object = keyring_compare_object,
+ .diff_objects = keyring_diff_objects,
+ .free_object = keyring_free_object,
+};
+
/*
* Clean up a keyring when it is destroyed. Unpublish its name if it had one
* and dispose of its data.
*/
static void keyring_destroy(struct key *keyring)
{
- struct keyring_list *klist;
- int loop;
-
if (keyring->description) {
write_lock(&keyring_name_lock);
write_unlock(&keyring_name_lock);
}
- klist = rcu_access_pointer(keyring->payload.subscriptions);
- if (klist) {
- for (loop = klist->nkeys - 1; loop >= 0; loop--)
- key_put(rcu_access_pointer(klist->keys[loop]));
- kfree(klist);
- }
+ assoc_array_destroy(&keyring->keys, &keyring_assoc_array_ops);
}
/*
*/
static void keyring_describe(const struct key *keyring, struct seq_file *m)
{
- struct keyring_list *klist;
-
if (keyring->description)
seq_puts(m, keyring->description);
else
seq_puts(m, "[anon]");
if (key_is_instantiated(keyring)) {
- rcu_read_lock();
- klist = rcu_dereference(keyring->payload.subscriptions);
- if (klist)
- seq_printf(m, ": %u/%u", klist->nkeys, klist->maxkeys);
+ if (keyring->keys.nr_leaves_on_tree != 0)
+ seq_printf(m, ": %lu", keyring->keys.nr_leaves_on_tree);
else
seq_puts(m, ": empty");
- rcu_read_unlock();
}
}
+struct keyring_read_iterator_context {
+ size_t qty;
+ size_t count;
+ key_serial_t __user *buffer;
+};
+
+static int keyring_read_iterator(const void *object, void *data)
+{
+ struct keyring_read_iterator_context *ctx = data;
+ const struct key *key = keyring_ptr_to_key(object);
+ int ret;
+
+ kenter("{%s,%d},,{%zu/%zu}",
+ key->type->name, key->serial, ctx->count, ctx->qty);
+
+ if (ctx->count >= ctx->qty)
+ return 1;
+
+ ret = put_user(key->serial, ctx->buffer);
+ if (ret < 0)
+ return ret;
+ ctx->buffer++;
+ ctx->count += sizeof(key->serial);
+ return 0;
+}
+
/*
* Read a list of key IDs from the keyring's contents in binary form
*
- * The keyring's semaphore is read-locked by the caller.
+ * The keyring's semaphore is read-locked by the caller. This prevents someone
+ * from modifying it under us - which could cause us to read key IDs multiple
+ * times.
*/
static long keyring_read(const struct key *keyring,
char __user *buffer, size_t buflen)
{
- struct keyring_list *klist;
- struct key *key;
- size_t qty, tmp;
- int loop, ret;
+ struct keyring_read_iterator_context ctx;
+ unsigned long nr_keys;
+ int ret;
- ret = 0;
- klist = rcu_dereference_locked_keyring(keyring);
- if (klist) {
- /* calculate how much data we could return */
- qty = klist->nkeys * sizeof(key_serial_t);
-
- if (buffer && buflen > 0) {
- if (buflen > qty)
- buflen = qty;
-
- /* copy the IDs of the subscribed keys into the
- * buffer */
- ret = -EFAULT;
-
- for (loop = 0; loop < klist->nkeys; loop++) {
- key = rcu_deref_link_locked(klist, loop,
- keyring);
-
- tmp = sizeof(key_serial_t);
- if (tmp > buflen)
- tmp = buflen;
-
- if (copy_to_user(buffer,
- &key->serial,
- tmp) != 0)
- goto error;
-
- buflen -= tmp;
- if (buflen == 0)
- break;
- buffer += tmp;
- }
- }
+ kenter("{%d},,%zu", key_serial(keyring), buflen);
+
+ if (buflen & (sizeof(key_serial_t) - 1))
+ return -EINVAL;
+
+ nr_keys = keyring->keys.nr_leaves_on_tree;
+ if (nr_keys == 0)
+ return 0;
- ret = qty;
+ /* Calculate how much data we could return */
+ ctx.qty = nr_keys * sizeof(key_serial_t);
+
+ if (!buffer || !buflen)
+ return ctx.qty;
+
+ if (buflen > ctx.qty)
+ ctx.qty = buflen;
+
+ /* Copy the IDs of the subscribed keys into the buffer */
+ ctx.buffer = (key_serial_t __user *)buffer;
+ ctx.count = 0;
+ ret = assoc_array_iterate(&keyring->keys, keyring_read_iterator, &ctx);
+ if (ret < 0) {
+ kleave(" = %d [iterate]", ret);
+ return ret;
}
-error:
- return ret;
+ kleave(" = %zu [ok]", ctx.count);
+ return ctx.count;
}
/*
}
EXPORT_SYMBOL(keyring_alloc);
-/**
- * keyring_search_aux - Search a keyring tree for a key matching some criteria
- * @keyring_ref: A pointer to the keyring with possession indicator.
- * @cred: The credentials to use for permissions checks.
- * @type: The type of key to search for.
- * @description: Parameter for @match.
- * @match: Function to rule on whether or not a key is the one required.
- * @no_state_check: Don't check if a matching key is bad
- *
- * Search the supplied keyring tree for a key that matches the criteria given.
- * The root keyring and any linked keyrings must grant Search permission to the
- * caller to be searchable and keys can only be found if they too grant Search
- * to the caller. The possession flag on the root keyring pointer controls use
- * of the possessor bits in permissions checking of the entire tree. In
- * addition, the LSM gets to forbid keyring searches and key matches.
- *
- * The search is performed as a breadth-then-depth search up to the prescribed
- * limit (KEYRING_SEARCH_MAX_DEPTH).
- *
- * Keys are matched to the type provided and are then filtered by the match
- * function, which is given the description to use in any way it sees fit. The
- * match function may use any attributes of a key that it wishes to to
- * determine the match. Normally the match function from the key type would be
- * used.
- *
- * RCU is used to prevent the keyring key lists from disappearing without the
- * need to take lots of locks.
- *
- * Returns a pointer to the found key and increments the key usage count if
- * successful; -EAGAIN if no matching keys were found, or if expired or revoked
- * keys were found; -ENOKEY if only negative keys were found; -ENOTDIR if the
- * specified keyring wasn't a keyring.
- *
- * In the case of a successful return, the possession attribute from
- * @keyring_ref is propagated to the returned key reference.
+/*
+ * Iteration function to consider each key found.
*/
-key_ref_t keyring_search_aux(key_ref_t keyring_ref,
- const struct cred *cred,
- struct key_type *type,
- const void *description,
- key_match_func_t match,
- bool no_state_check)
+static int keyring_search_iterator(const void *object, void *iterator_data)
{
- struct {
- /* Need a separate keylist pointer for RCU purposes */
- struct key *keyring;
- struct keyring_list *keylist;
- int kix;
- } stack[KEYRING_SEARCH_MAX_DEPTH];
-
- struct keyring_list *keylist;
- struct timespec now;
- unsigned long possessed, kflags;
- struct key *keyring, *key;
- key_ref_t key_ref;
- long err;
- int sp, nkeys, kix;
+ struct keyring_search_context *ctx = iterator_data;
+ const struct key *key = keyring_ptr_to_key(object);
+ unsigned long kflags = key->flags;
- keyring = key_ref_to_ptr(keyring_ref);
- possessed = is_key_possessed(keyring_ref);
- key_check(keyring);
+ kenter("{%d}", key->serial);
- /* top keyring must have search permission to begin the search */
- err = key_task_permission(keyring_ref, cred, KEY_SEARCH);
- if (err < 0) {
- key_ref = ERR_PTR(err);
- goto error;
+ /* ignore keys not of this type */
+ if (key->type != ctx->index_key.type) {
+ kleave(" = 0 [!type]");
+ return 0;
}
- key_ref = ERR_PTR(-ENOTDIR);
- if (keyring->type != &key_type_keyring)
- goto error;
+ /* skip invalidated, revoked and expired keys */
+ if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) {
+ if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
+ (1 << KEY_FLAG_REVOKED))) {
+ ctx->result = ERR_PTR(-EKEYREVOKED);
+ kleave(" = %d [invrev]", ctx->skipped_ret);
+ goto skipped;
+ }
- rcu_read_lock();
+ if (key->expiry && ctx->now.tv_sec >= key->expiry) {
+ ctx->result = ERR_PTR(-EKEYEXPIRED);
+ kleave(" = %d [expire]", ctx->skipped_ret);
+ goto skipped;
+ }
+ }
- now = current_kernel_time();
- err = -EAGAIN;
- sp = 0;
-
- /* firstly we should check to see if this top-level keyring is what we
- * are looking for */
- key_ref = ERR_PTR(-EAGAIN);
- kflags = keyring->flags;
- if (keyring->type == type && match(keyring, description)) {
- key = keyring;
- if (no_state_check)
- goto found;
+ /* keys that don't match */
+ if (!ctx->match(key, ctx->match_data)) {
+ kleave(" = 0 [!match]");
+ return 0;
+ }
- /* check it isn't negative and hasn't expired or been
- * revoked */
- if (kflags & (1 << KEY_FLAG_REVOKED))
- goto error_2;
- if (key->expiry && now.tv_sec >= key->expiry)
- goto error_2;
- key_ref = ERR_PTR(key->type_data.reject_error);
- if (kflags & (1 << KEY_FLAG_NEGATIVE))
- goto error_2;
- goto found;
+ /* key must have search permissions */
+ if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) &&
+ key_task_permission(make_key_ref(key, ctx->possessed),
+ ctx->cred, KEY_SEARCH) < 0) {
+ ctx->result = ERR_PTR(-EACCES);
+ kleave(" = %d [!perm]", ctx->skipped_ret);
+ goto skipped;
}
- /* otherwise, the top keyring must not be revoked, expired, or
- * negatively instantiated if we are to search it */
- key_ref = ERR_PTR(-EAGAIN);
- if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
- (1 << KEY_FLAG_REVOKED) |
- (1 << KEY_FLAG_NEGATIVE)) ||
- (keyring->expiry && now.tv_sec >= keyring->expiry))
- goto error_2;
-
- /* start processing a new keyring */
-descend:
- kflags = keyring->flags;
- if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
- (1 << KEY_FLAG_REVOKED)))
- goto not_this_keyring;
+ if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) {
+ /* we set a different error code if we pass a negative key */
+ if (kflags & (1 << KEY_FLAG_NEGATIVE)) {
+ smp_rmb();
+ ctx->result = ERR_PTR(key->type_data.reject_error);
+ kleave(" = %d [neg]", ctx->skipped_ret);
+ goto skipped;
+ }
+ }
- keylist = rcu_dereference(keyring->payload.subscriptions);
- if (!keylist)
- goto not_this_keyring;
+ /* Found */
+ ctx->result = make_key_ref(key, ctx->possessed);
+ kleave(" = 1 [found]");
+ return 1;
- /* iterate through the keys in this keyring first */
- nkeys = keylist->nkeys;
- smp_rmb();
- for (kix = 0; kix < nkeys; kix++) {
- key = rcu_dereference(keylist->keys[kix]);
- kflags = key->flags;
+skipped:
+ return ctx->skipped_ret;
+}
- /* ignore keys not of this type */
- if (key->type != type)
- continue;
+/*
+ * Search inside a keyring for a key. We can search by walking to it
+ * directly based on its index-key or we can iterate over the entire
+ * tree looking for it, based on the match function.
+ */
+static int search_keyring(struct key *keyring, struct keyring_search_context *ctx)
+{
+ if ((ctx->flags & KEYRING_SEARCH_LOOKUP_TYPE) ==
+ KEYRING_SEARCH_LOOKUP_DIRECT) {
+ const void *object;
+
+ object = assoc_array_find(&keyring->keys,
+ &keyring_assoc_array_ops,
+ &ctx->index_key);
+ return object ? ctx->iterator(object, ctx) : 0;
+ }
+ return assoc_array_iterate(&keyring->keys, ctx->iterator, ctx);
+}
- /* skip invalidated, revoked and expired keys */
- if (!no_state_check) {
- if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
- (1 << KEY_FLAG_REVOKED)))
- continue;
+/*
+ * Search a tree of keyrings that point to other keyrings up to the maximum
+ * depth.
+ */
+static bool search_nested_keyrings(struct key *keyring,
+ struct keyring_search_context *ctx)
+{
+ struct {
+ struct key *keyring;
+ struct assoc_array_node *node;
+ int slot;
+ } stack[KEYRING_SEARCH_MAX_DEPTH];
- if (key->expiry && now.tv_sec >= key->expiry)
- continue;
- }
+ struct assoc_array_shortcut *shortcut;
+ struct assoc_array_node *node;
+ struct assoc_array_ptr *ptr;
+ struct key *key;
+ int sp = 0, slot;
- /* keys that don't match */
- if (!match(key, description))
- continue;
+ kenter("{%d},{%s,%s}",
+ keyring->serial,
+ ctx->index_key.type->name,
+ ctx->index_key.description);
- /* key must have search permissions */
- if (key_task_permission(make_key_ref(key, possessed),
- cred, KEY_SEARCH) < 0)
- continue;
+ if (ctx->index_key.description)
+ ctx->index_key.desc_len = strlen(ctx->index_key.description);
- if (no_state_check)
+ /* Check to see if this top-level keyring is what we are looking for
+ * and whether it is valid or not.
+ */
+ if (ctx->flags & KEYRING_SEARCH_LOOKUP_ITERATE ||
+ keyring_compare_object(keyring, &ctx->index_key)) {
+ ctx->skipped_ret = 2;
+ ctx->flags |= KEYRING_SEARCH_DO_STATE_CHECK;
+ switch (ctx->iterator(keyring_key_to_ptr(keyring), ctx)) {
+ case 1:
goto found;
-
- /* we set a different error code if we pass a negative key */
- if (kflags & (1 << KEY_FLAG_NEGATIVE)) {
- err = key->type_data.reject_error;
- continue;
+ case 2:
+ return false;
+ default:
+ break;
}
+ }
+
+ ctx->skipped_ret = 0;
+ if (ctx->flags & KEYRING_SEARCH_NO_STATE_CHECK)
+ ctx->flags &= ~KEYRING_SEARCH_DO_STATE_CHECK;
+ /* Start processing a new keyring */
+descend_to_keyring:
+ kdebug("descend to %d", keyring->serial);
+ if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) |
+ (1 << KEY_FLAG_REVOKED)))
+ goto not_this_keyring;
+
+ /* Search through the keys in this keyring before its searching its
+ * subtrees.
+ */
+ if (search_keyring(keyring, ctx))
goto found;
- }
- /* search through the keyrings nested in this one */
- kix = 0;
-ascend:
- nkeys = keylist->nkeys;
- smp_rmb();
- for (; kix < nkeys; kix++) {
- key = rcu_dereference(keylist->keys[kix]);
- if (key->type != &key_type_keyring)
- continue;
+ /* Then manually iterate through the keyrings nested in this one.
+ *
+ * Start from the root node of the index tree. Because of the way the
+ * hash function has been set up, keyrings cluster on the leftmost
+ * branch of the root node (root slot 0) or in the root node itself.
+ * Non-keyrings avoid the leftmost branch of the root entirely (root
+ * slots 1-15).
+ */
+ ptr = ACCESS_ONCE(keyring->keys.root);
+ if (!ptr)
+ goto not_this_keyring;
- /* recursively search nested keyrings
- * - only search keyrings for which we have search permission
+ if (assoc_array_ptr_is_shortcut(ptr)) {
+ /* If the root is a shortcut, either the keyring only contains
+ * keyring pointers (everything clusters behind root slot 0) or
+ * doesn't contain any keyring pointers.
*/
- if (sp >= KEYRING_SEARCH_MAX_DEPTH)
+ shortcut = assoc_array_ptr_to_shortcut(ptr);
+ smp_read_barrier_depends();
+ if ((shortcut->index_key[0] & ASSOC_ARRAY_FAN_MASK) != 0)
+ goto not_this_keyring;
+
+ ptr = ACCESS_ONCE(shortcut->next_node);
+ node = assoc_array_ptr_to_node(ptr);
+ goto begin_node;
+ }
+
+ node = assoc_array_ptr_to_node(ptr);
+ smp_read_barrier_depends();
+
+ ptr = node->slots[0];
+ if (!assoc_array_ptr_is_meta(ptr))
+ goto begin_node;
+
+descend_to_node:
+ /* Descend to a more distal node in this keyring's content tree and go
+ * through that.
+ */
+ kdebug("descend");
+ if (assoc_array_ptr_is_shortcut(ptr)) {
+ shortcut = assoc_array_ptr_to_shortcut(ptr);
+ smp_read_barrier_depends();
+ ptr = ACCESS_ONCE(shortcut->next_node);
+ BUG_ON(!assoc_array_ptr_is_node(ptr));
+ node = assoc_array_ptr_to_node(ptr);
+ }
+
+begin_node:
+ kdebug("begin_node");
+ smp_read_barrier_depends();
+ slot = 0;
+ascend_to_node:
+ /* Go through the slots in a node */
+ for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+ ptr = ACCESS_ONCE(node->slots[slot]);
+
+ if (assoc_array_ptr_is_meta(ptr) && node->back_pointer)
+ goto descend_to_node;
+
+ if (!keyring_ptr_is_keyring(ptr))
continue;
- if (key_task_permission(make_key_ref(key, possessed),
- cred, KEY_SEARCH) < 0)
+ key = keyring_ptr_to_key(ptr);
+
+ if (sp >= KEYRING_SEARCH_MAX_DEPTH) {
+ if (ctx->flags & KEYRING_SEARCH_DETECT_TOO_DEEP) {
+ ctx->result = ERR_PTR(-ELOOP);
+ return false;
+ }
+ goto not_this_keyring;
+ }
+
+ /* Search a nested keyring */
+ if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) &&
+ key_task_permission(make_key_ref(key, ctx->possessed),
+ ctx->cred, KEY_SEARCH) < 0)
continue;
/* stack the current position */
stack[sp].keyring = keyring;
- stack[sp].keylist = keylist;
- stack[sp].kix = kix;
+ stack[sp].node = node;
+ stack[sp].slot = slot;
sp++;
/* begin again with the new keyring */
keyring = key;
- goto descend;
+ goto descend_to_keyring;
}
- /* the keyring we're looking at was disqualified or didn't contain a
- * matching key */
+ /* We've dealt with all the slots in the current node, so now we need
+ * to ascend to the parent and continue processing there.
+ */
+ ptr = ACCESS_ONCE(node->back_pointer);
+ slot = node->parent_slot;
+
+ if (ptr && assoc_array_ptr_is_shortcut(ptr)) {
+ shortcut = assoc_array_ptr_to_shortcut(ptr);
+ smp_read_barrier_depends();
+ ptr = ACCESS_ONCE(shortcut->back_pointer);
+ slot = shortcut->parent_slot;
+ }
+ if (!ptr)
+ goto not_this_keyring;
+ node = assoc_array_ptr_to_node(ptr);
+ smp_read_barrier_depends();
+ slot++;
+
+ /* If we've ascended to the root (zero backpointer), we must have just
+ * finished processing the leftmost branch rather than the root slots -
+ * so there can't be any more keyrings for us to find.
+ */
+ if (node->back_pointer) {
+ kdebug("ascend %d", slot);
+ goto ascend_to_node;
+ }
+
+ /* The keyring we're looking at was disqualified or didn't contain a
+ * matching key.
+ */
not_this_keyring:
- if (sp > 0) {
- /* resume the processing of a keyring higher up in the tree */
- sp--;
- keyring = stack[sp].keyring;
- keylist = stack[sp].keylist;
- kix = stack[sp].kix + 1;
- goto ascend;
+ kdebug("not_this_keyring %d", sp);
+ if (sp <= 0) {
+ kleave(" = false");
+ return false;
}
- key_ref = ERR_PTR(err);
- goto error_2;
+ /* Resume the processing of a keyring higher up in the tree */
+ sp--;
+ keyring = stack[sp].keyring;
+ node = stack[sp].node;
+ slot = stack[sp].slot + 1;
+ kdebug("ascend to %d [%d]", keyring->serial, slot);
+ goto ascend_to_node;
- /* we found a viable match */
+ /* We found a viable match */
found:
- atomic_inc(&key->usage);
- key->last_used_at = now.tv_sec;
- keyring->last_used_at = now.tv_sec;
- while (sp > 0)
- stack[--sp].keyring->last_used_at = now.tv_sec;
+ key = key_ref_to_ptr(ctx->result);
key_check(key);
- key_ref = make_key_ref(key, possessed);
-error_2:
+ if (!(ctx->flags & KEYRING_SEARCH_NO_UPDATE_TIME)) {
+ key->last_used_at = ctx->now.tv_sec;
+ keyring->last_used_at = ctx->now.tv_sec;
+ while (sp > 0)
+ stack[--sp].keyring->last_used_at = ctx->now.tv_sec;
+ }
+ kleave(" = true");
+ return true;
+}
+
+/**
+ * keyring_search_aux - Search a keyring tree for a key matching some criteria
+ * @keyring_ref: A pointer to the keyring with possession indicator.
+ * @ctx: The keyring search context.
+ *
+ * Search the supplied keyring tree for a key that matches the criteria given.
+ * The root keyring and any linked keyrings must grant Search permission to the
+ * caller to be searchable and keys can only be found if they too grant Search
+ * to the caller. The possession flag on the root keyring pointer controls use
+ * of the possessor bits in permissions checking of the entire tree. In
+ * addition, the LSM gets to forbid keyring searches and key matches.
+ *
+ * The search is performed as a breadth-then-depth search up to the prescribed
+ * limit (KEYRING_SEARCH_MAX_DEPTH).
+ *
+ * Keys are matched to the type provided and are then filtered by the match
+ * function, which is given the description to use in any way it sees fit. The
+ * match function may use any attributes of a key that it wishes to to
+ * determine the match. Normally the match function from the key type would be
+ * used.
+ *
+ * RCU can be used to prevent the keyring key lists from disappearing without
+ * the need to take lots of locks.
+ *
+ * Returns a pointer to the found key and increments the key usage count if
+ * successful; -EAGAIN if no matching keys were found, or if expired or revoked
+ * keys were found; -ENOKEY if only negative keys were found; -ENOTDIR if the
+ * specified keyring wasn't a keyring.
+ *
+ * In the case of a successful return, the possession attribute from
+ * @keyring_ref is propagated to the returned key reference.
+ */
+key_ref_t keyring_search_aux(key_ref_t keyring_ref,
+ struct keyring_search_context *ctx)
+{
+ struct key *keyring;
+ long err;
+
+ ctx->iterator = keyring_search_iterator;
+ ctx->possessed = is_key_possessed(keyring_ref);
+ ctx->result = ERR_PTR(-EAGAIN);
+
+ keyring = key_ref_to_ptr(keyring_ref);
+ key_check(keyring);
+
+ if (keyring->type != &key_type_keyring)
+ return ERR_PTR(-ENOTDIR);
+
+ if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM)) {
+ err = key_task_permission(keyring_ref, ctx->cred, KEY_SEARCH);
+ if (err < 0)
+ return ERR_PTR(err);
+ }
+
+ rcu_read_lock();
+ ctx->now = current_kernel_time();
+ if (search_nested_keyrings(keyring, ctx))
+ __key_get(key_ref_to_ptr(ctx->result));
rcu_read_unlock();
-error:
- return key_ref;
+ return ctx->result;
}
/**
* @description: The name of the keyring we want to find.
*
* As keyring_search_aux() above, but using the current task's credentials and
- * type's default matching function.
+ * type's default matching function and preferred search method.
*/
key_ref_t keyring_search(key_ref_t keyring,
struct key_type *type,
const char *description)
{
- if (!type->match)
+ struct keyring_search_context ctx = {
+ .index_key.type = type,
+ .index_key.description = description,
+ .cred = current_cred(),
+ .match = type->match,
+ .match_data = description,
+ .flags = (type->def_lookup_type |
+ KEYRING_SEARCH_DO_STATE_CHECK),
+ };
+
+ if (!ctx.match)
return ERR_PTR(-ENOKEY);
- return keyring_search_aux(keyring, current->cred,
- type, description, type->match, false);
+ return keyring_search_aux(keyring, &ctx);
}
EXPORT_SYMBOL(keyring_search);
/*
- * Search the given keyring only (no recursion).
+ * Search the given keyring for a key that might be updated.
*
* The caller must guarantee that the keyring is a keyring and that the
- * permission is granted to search the keyring as no check is made here.
- *
- * RCU is used to make it unnecessary to lock the keyring key list here.
+ * permission is granted to modify the keyring as no check is made here. The
+ * caller must also hold a lock on the keyring semaphore.
*
* Returns a pointer to the found key with usage count incremented if
- * successful and returns -ENOKEY if not found. Revoked keys and keys not
- * providing the requested permission are skipped over.
+ * successful and returns NULL if not found. Revoked and invalidated keys are
+ * skipped over.
*
* If successful, the possession indicator is propagated from the keyring ref
* to the returned key reference.
*/
-key_ref_t __keyring_search_one(key_ref_t keyring_ref,
- const struct key_type *ktype,
- const char *description,
- key_perm_t perm)
+key_ref_t find_key_to_update(key_ref_t keyring_ref,
+ const struct keyring_index_key *index_key)
{
- struct keyring_list *klist;
- unsigned long possessed;
struct key *keyring, *key;
- int nkeys, loop;
+ const void *object;
keyring = key_ref_to_ptr(keyring_ref);
- possessed = is_key_possessed(keyring_ref);
- rcu_read_lock();
+ kenter("{%d},{%s,%s}",
+ keyring->serial, index_key->type->name, index_key->description);
- klist = rcu_dereference(keyring->payload.subscriptions);
- if (klist) {
- nkeys = klist->nkeys;
- smp_rmb();
- for (loop = 0; loop < nkeys ; loop++) {
- key = rcu_dereference(klist->keys[loop]);
- if (key->type == ktype &&
- (!key->type->match ||
- key->type->match(key, description)) &&
- key_permission(make_key_ref(key, possessed),
- perm) == 0 &&
- !(key->flags & ((1 << KEY_FLAG_INVALIDATED) |
- (1 << KEY_FLAG_REVOKED)))
- )
- goto found;
- }
- }
+ object = assoc_array_find(&keyring->keys, &keyring_assoc_array_ops,
+ index_key);
- rcu_read_unlock();
- return ERR_PTR(-ENOKEY);
+ if (object)
+ goto found;
+
+ kleave(" = NULL");
+ return NULL;
found:
- atomic_inc(&key->usage);
- keyring->last_used_at = key->last_used_at =
- current_kernel_time().tv_sec;
- rcu_read_unlock();
- return make_key_ref(key, possessed);
+ key = keyring_ptr_to_key(object);
+ if (key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+ (1 << KEY_FLAG_REVOKED))) {
+ kleave(" = NULL [x]");
+ return NULL;
+ }
+ __key_get(key);
+ kleave(" = {%d}", key->serial);
+ return make_key_ref(key, is_key_possessed(keyring_ref));
}
/*
return keyring;
}
+static int keyring_detect_cycle_iterator(const void *object,
+ void *iterator_data)
+{
+ struct keyring_search_context *ctx = iterator_data;
+ const struct key *key = keyring_ptr_to_key(object);
+
+ kenter("{%d}", key->serial);
+
+ BUG_ON(key != ctx->match_data);
+ ctx->result = ERR_PTR(-EDEADLK);
+ return 1;
+}
+
/*
* See if a cycle will will be created by inserting acyclic tree B in acyclic
* tree A at the topmost level (ie: as a direct child of A).
*/
static int keyring_detect_cycle(struct key *A, struct key *B)
{
- struct {
- struct keyring_list *keylist;
- int kix;
- } stack[KEYRING_SEARCH_MAX_DEPTH];
-
- struct keyring_list *keylist;
- struct key *subtree, *key;
- int sp, nkeys, kix, ret;
+ struct keyring_search_context ctx = {
+ .index_key = A->index_key,
+ .match_data = A,
+ .iterator = keyring_detect_cycle_iterator,
+ .flags = (KEYRING_SEARCH_LOOKUP_DIRECT |
+ KEYRING_SEARCH_NO_STATE_CHECK |
+ KEYRING_SEARCH_NO_UPDATE_TIME |
+ KEYRING_SEARCH_NO_CHECK_PERM |
+ KEYRING_SEARCH_DETECT_TOO_DEEP),
+ };
rcu_read_lock();
-
- ret = -EDEADLK;
- if (A == B)
- goto cycle_detected;
-
- subtree = B;
- sp = 0;
-
- /* start processing a new keyring */
-descend:
- if (test_bit(KEY_FLAG_REVOKED, &subtree->flags))
- goto not_this_keyring;
-
- keylist = rcu_dereference(subtree->payload.subscriptions);
- if (!keylist)
- goto not_this_keyring;
- kix = 0;
-
-ascend:
- /* iterate through the remaining keys in this keyring */
- nkeys = keylist->nkeys;
- smp_rmb();
- for (; kix < nkeys; kix++) {
- key = rcu_dereference(keylist->keys[kix]);
-
- if (key == A)
- goto cycle_detected;
-
- /* recursively check nested keyrings */
- if (key->type == &key_type_keyring) {
- if (sp >= KEYRING_SEARCH_MAX_DEPTH)
- goto too_deep;
-
- /* stack the current position */
- stack[sp].keylist = keylist;
- stack[sp].kix = kix;
- sp++;
-
- /* begin again with the new keyring */
- subtree = key;
- goto descend;
- }
- }
-
- /* the keyring we're looking at was disqualified or didn't contain a
- * matching key */
-not_this_keyring:
- if (sp > 0) {
- /* resume the checking of a keyring higher up in the tree */
- sp--;
- keylist = stack[sp].keylist;
- kix = stack[sp].kix + 1;
- goto ascend;
- }
-
- ret = 0; /* no cycles detected */
-
-error:
+ search_nested_keyrings(B, &ctx);
rcu_read_unlock();
- return ret;
-
-too_deep:
- ret = -ELOOP;
- goto error;
-
-cycle_detected:
- ret = -EDEADLK;
- goto error;
-}
-
-/*
- * Dispose of a keyring list after the RCU grace period, freeing the unlinked
- * key
- */
-static void keyring_unlink_rcu_disposal(struct rcu_head *rcu)
-{
- struct keyring_list *klist =
- container_of(rcu, struct keyring_list, rcu);
-
- if (klist->delkey != USHRT_MAX)
- key_put(rcu_access_pointer(klist->keys[klist->delkey]));
- kfree(klist);
+ return PTR_ERR(ctx.result) == -EAGAIN ? 0 : PTR_ERR(ctx.result);
}
/*
* Preallocate memory so that a key can be linked into to a keyring.
*/
-int __key_link_begin(struct key *keyring, const struct key_type *type,
- const char *description, unsigned long *_prealloc)
+int __key_link_begin(struct key *keyring,
+ const struct keyring_index_key *index_key,
+ struct assoc_array_edit **_edit)
__acquires(&keyring->sem)
__acquires(&keyring_serialise_link_sem)
{
- struct keyring_list *klist, *nklist;
- unsigned long prealloc;
- unsigned max;
- time_t lowest_lru;
- size_t size;
- int loop, lru, ret;
+ struct assoc_array_edit *edit;
+ int ret;
+
+ kenter("%d,%s,%s,",
+ keyring->serial, index_key->type->name, index_key->description);
- kenter("%d,%s,%s,", key_serial(keyring), type->name, description);
+ BUG_ON(index_key->desc_len == 0);
if (keyring->type != &key_type_keyring)
return -ENOTDIR;
/* serialise link/link calls to prevent parallel calls causing a cycle
* when linking two keyring in opposite orders */
- if (type == &key_type_keyring)
+ if (index_key->type == &key_type_keyring)
down_write(&keyring_serialise_link_sem);
- klist = rcu_dereference_locked_keyring(keyring);
-
- /* see if there's a matching key we can displace */
- lru = -1;
- if (klist && klist->nkeys > 0) {
- lowest_lru = TIME_T_MAX;
- for (loop = klist->nkeys - 1; loop >= 0; loop--) {
- struct key *key = rcu_deref_link_locked(klist, loop,
- keyring);
- if (key->type == type &&
- strcmp(key->description, description) == 0) {
- /* Found a match - we'll replace the link with
- * one to the new key. We record the slot
- * position.
- */
- klist->delkey = loop;
- prealloc = 0;
- goto done;
- }
- if (key->last_used_at < lowest_lru) {
- lowest_lru = key->last_used_at;
- lru = loop;
- }
- }
- }
-
- /* If the keyring is full then do an LRU discard */
- if (klist &&
- klist->nkeys == klist->maxkeys &&
- klist->maxkeys >= MAX_KEYRING_LINKS) {
- kdebug("LRU discard %d\n", lru);
- klist->delkey = lru;
- prealloc = 0;
- goto done;
- }
-
- /* check that we aren't going to overrun the user's quota */
- ret = key_payload_reserve(keyring,
- keyring->datalen + KEYQUOTA_LINK_BYTES);
- if (ret < 0)
+ /* Create an edit script that will insert/replace the key in the
+ * keyring tree.
+ */
+ edit = assoc_array_insert(&keyring->keys,
+ &keyring_assoc_array_ops,
+ index_key,
+ NULL);
+ if (IS_ERR(edit)) {
+ ret = PTR_ERR(edit);
goto error_sem;
+ }
- if (klist && klist->nkeys < klist->maxkeys) {
- /* there's sufficient slack space to append directly */
- klist->delkey = klist->nkeys;
- prealloc = KEY_LINK_FIXQUOTA;
- } else {
- /* grow the key list */
- max = 4;
- if (klist) {
- max += klist->maxkeys;
- if (max > MAX_KEYRING_LINKS)
- max = MAX_KEYRING_LINKS;
- BUG_ON(max <= klist->maxkeys);
- }
-
- size = sizeof(*klist) + sizeof(struct key *) * max;
-
- ret = -ENOMEM;
- nklist = kmalloc(size, GFP_KERNEL);
- if (!nklist)
- goto error_quota;
-
- nklist->maxkeys = max;
- if (klist) {
- memcpy(nklist->keys, klist->keys,
- sizeof(struct key *) * klist->nkeys);
- nklist->delkey = klist->nkeys;
- nklist->nkeys = klist->nkeys + 1;
- klist->delkey = USHRT_MAX;
- } else {
- nklist->nkeys = 1;
- nklist->delkey = 0;
- }
-
- /* add the key into the new space */
- RCU_INIT_POINTER(nklist->keys[nklist->delkey], NULL);
- prealloc = (unsigned long)nklist | KEY_LINK_FIXQUOTA;
+ /* If we're not replacing a link in-place then we're going to need some
+ * extra quota.
+ */
+ if (!edit->dead_leaf) {
+ ret = key_payload_reserve(keyring,
+ keyring->datalen + KEYQUOTA_LINK_BYTES);
+ if (ret < 0)
+ goto error_cancel;
}
-done:
- *_prealloc = prealloc;
+ *_edit = edit;
kleave(" = 0");
return 0;
-error_quota:
- /* undo the quota changes */
- key_payload_reserve(keyring,
- keyring->datalen - KEYQUOTA_LINK_BYTES);
+error_cancel:
+ assoc_array_cancel_edit(edit);
error_sem:
- if (type == &key_type_keyring)
+ if (index_key->type == &key_type_keyring)
up_write(&keyring_serialise_link_sem);
error_krsem:
up_write(&keyring->sem);
* holds at most one link to any given key of a particular type+description
* combination.
*/
-void __key_link(struct key *keyring, struct key *key,
- unsigned long *_prealloc)
+void __key_link(struct key *key, struct assoc_array_edit **_edit)
{
- struct keyring_list *klist, *nklist;
- struct key *discard;
-
- nklist = (struct keyring_list *)(*_prealloc & ~KEY_LINK_FIXQUOTA);
- *_prealloc = 0;
-
- kenter("%d,%d,%p", keyring->serial, key->serial, nklist);
-
- klist = rcu_dereference_locked_keyring(keyring);
-
- atomic_inc(&key->usage);
- keyring->last_used_at = key->last_used_at =
- current_kernel_time().tv_sec;
-
- /* there's a matching key we can displace or an empty slot in a newly
- * allocated list we can fill */
- if (nklist) {
- kdebug("reissue %hu/%hu/%hu",
- nklist->delkey, nklist->nkeys, nklist->maxkeys);
-
- RCU_INIT_POINTER(nklist->keys[nklist->delkey], key);
-
- rcu_assign_pointer(keyring->payload.subscriptions, nklist);
-
- /* dispose of the old keyring list and, if there was one, the
- * displaced key */
- if (klist) {
- kdebug("dispose %hu/%hu/%hu",
- klist->delkey, klist->nkeys, klist->maxkeys);
- call_rcu(&klist->rcu, keyring_unlink_rcu_disposal);
- }
- } else if (klist->delkey < klist->nkeys) {
- kdebug("replace %hu/%hu/%hu",
- klist->delkey, klist->nkeys, klist->maxkeys);
-
- discard = rcu_dereference_protected(
- klist->keys[klist->delkey],
- rwsem_is_locked(&keyring->sem));
- rcu_assign_pointer(klist->keys[klist->delkey], key);
- /* The garbage collector will take care of RCU
- * synchronisation */
- key_put(discard);
- } else {
- /* there's sufficient slack space to append directly */
- kdebug("append %hu/%hu/%hu",
- klist->delkey, klist->nkeys, klist->maxkeys);
-
- RCU_INIT_POINTER(klist->keys[klist->delkey], key);
- smp_wmb();
- klist->nkeys++;
- }
+ __key_get(key);
+ assoc_array_insert_set_object(*_edit, keyring_key_to_ptr(key));
+ assoc_array_apply_edit(*_edit);
+ *_edit = NULL;
}
/*
*
* Must be called with __key_link_begin() having being called.
*/
-void __key_link_end(struct key *keyring, struct key_type *type,
- unsigned long prealloc)
+void __key_link_end(struct key *keyring,
+ const struct keyring_index_key *index_key,
+ struct assoc_array_edit *edit)
__releases(&keyring->sem)
__releases(&keyring_serialise_link_sem)
{
- BUG_ON(type == NULL);
- BUG_ON(type->name == NULL);
- kenter("%d,%s,%lx", keyring->serial, type->name, prealloc);
+ BUG_ON(index_key->type == NULL);
+ kenter("%d,%s,", keyring->serial, index_key->type->name);
- if (type == &key_type_keyring)
+ if (index_key->type == &key_type_keyring)
up_write(&keyring_serialise_link_sem);
- if (prealloc) {
- if (prealloc & KEY_LINK_FIXQUOTA)
- key_payload_reserve(keyring,
- keyring->datalen -
- KEYQUOTA_LINK_BYTES);
- kfree((struct keyring_list *)(prealloc & ~KEY_LINK_FIXQUOTA));
+ if (edit && !edit->dead_leaf) {
+ key_payload_reserve(keyring,
+ keyring->datalen - KEYQUOTA_LINK_BYTES);
+ assoc_array_cancel_edit(edit);
}
up_write(&keyring->sem);
}
*/
int key_link(struct key *keyring, struct key *key)
{
- unsigned long prealloc;
+ struct assoc_array_edit *edit;
int ret;
+ kenter("{%d,%d}", keyring->serial, atomic_read(&keyring->usage));
+
key_check(keyring);
key_check(key);
- ret = __key_link_begin(keyring, key->type, key->description, &prealloc);
+ if (test_bit(KEY_FLAG_TRUSTED_ONLY, &keyring->flags) &&
+ !test_bit(KEY_FLAG_TRUSTED, &key->flags))
+ return -EPERM;
+
+ ret = __key_link_begin(keyring, &key->index_key, &edit);
if (ret == 0) {
+ kdebug("begun {%d,%d}", keyring->serial, atomic_read(&keyring->usage));
ret = __key_link_check_live_key(keyring, key);
if (ret == 0)
- __key_link(keyring, key, &prealloc);
- __key_link_end(keyring, key->type, prealloc);
+ __key_link(key, &edit);
+ __key_link_end(keyring, &key->index_key, edit);
}
+ kleave(" = %d {%d,%d}", ret, keyring->serial, atomic_read(&keyring->usage));
return ret;
}
EXPORT_SYMBOL(key_link);
*/
int key_unlink(struct key *keyring, struct key *key)
{
- struct keyring_list *klist, *nklist;
- int loop, ret;
+ struct assoc_array_edit *edit;
+ int ret;
key_check(keyring);
key_check(key);
- ret = -ENOTDIR;
if (keyring->type != &key_type_keyring)
- goto error;
+ return -ENOTDIR;
down_write(&keyring->sem);
- klist = rcu_dereference_locked_keyring(keyring);
- if (klist) {
- /* search the keyring for the key */
- for (loop = 0; loop < klist->nkeys; loop++)
- if (rcu_access_pointer(klist->keys[loop]) == key)
- goto key_is_present;
+ edit = assoc_array_delete(&keyring->keys, &keyring_assoc_array_ops,
+ &key->index_key);
+ if (IS_ERR(edit)) {
+ ret = PTR_ERR(edit);
+ goto error;
}
-
- up_write(&keyring->sem);
ret = -ENOENT;
- goto error;
-
-key_is_present:
- /* we need to copy the key list for RCU purposes */
- nklist = kmalloc(sizeof(*klist) +
- sizeof(struct key *) * klist->maxkeys,
- GFP_KERNEL);
- if (!nklist)
- goto nomem;
- nklist->maxkeys = klist->maxkeys;
- nklist->nkeys = klist->nkeys - 1;
-
- if (loop > 0)
- memcpy(&nklist->keys[0],
- &klist->keys[0],
- loop * sizeof(struct key *));
-
- if (loop < nklist->nkeys)
- memcpy(&nklist->keys[loop],
- &klist->keys[loop + 1],
- (nklist->nkeys - loop) * sizeof(struct key *));
-
- /* adjust the user's quota */
- key_payload_reserve(keyring,
- keyring->datalen - KEYQUOTA_LINK_BYTES);
-
- rcu_assign_pointer(keyring->payload.subscriptions, nklist);
-
- up_write(&keyring->sem);
-
- /* schedule for later cleanup */
- klist->delkey = loop;
- call_rcu(&klist->rcu, keyring_unlink_rcu_disposal);
+ if (edit == NULL)
+ goto error;
+ assoc_array_apply_edit(edit);
+ key_payload_reserve(keyring, keyring->datalen - KEYQUOTA_LINK_BYTES);
ret = 0;
error:
- return ret;
-nomem:
- ret = -ENOMEM;
up_write(&keyring->sem);
- goto error;
+ return ret;
}
EXPORT_SYMBOL(key_unlink);
-/*
- * Dispose of a keyring list after the RCU grace period, releasing the keys it
- * links to.
- */
-static void keyring_clear_rcu_disposal(struct rcu_head *rcu)
-{
- struct keyring_list *klist;
- int loop;
-
- klist = container_of(rcu, struct keyring_list, rcu);
-
- for (loop = klist->nkeys - 1; loop >= 0; loop--)
- key_put(rcu_access_pointer(klist->keys[loop]));
-
- kfree(klist);
-}
-
/**
* keyring_clear - Clear a keyring
* @keyring: The keyring to clear.
*/
int keyring_clear(struct key *keyring)
{
- struct keyring_list *klist;
+ struct assoc_array_edit *edit;
int ret;
- ret = -ENOTDIR;
- if (keyring->type == &key_type_keyring) {
- /* detach the pointer block with the locks held */
- down_write(&keyring->sem);
-
- klist = rcu_dereference_locked_keyring(keyring);
- if (klist) {
- /* adjust the quota */
- key_payload_reserve(keyring,
- sizeof(struct keyring_list));
-
- rcu_assign_pointer(keyring->payload.subscriptions,
- NULL);
- }
-
- up_write(&keyring->sem);
+ if (keyring->type != &key_type_keyring)
+ return -ENOTDIR;
- /* free the keys after the locks have been dropped */
- if (klist)
- call_rcu(&klist->rcu, keyring_clear_rcu_disposal);
+ down_write(&keyring->sem);
+ edit = assoc_array_clear(&keyring->keys, &keyring_assoc_array_ops);
+ if (IS_ERR(edit)) {
+ ret = PTR_ERR(edit);
+ } else {
+ if (edit)
+ assoc_array_apply_edit(edit);
+ key_payload_reserve(keyring, 0);
ret = 0;
}
+ up_write(&keyring->sem);
return ret;
}
EXPORT_SYMBOL(keyring_clear);
*/
static void keyring_revoke(struct key *keyring)
{
- struct keyring_list *klist;
+ struct assoc_array_edit *edit;
+
+ edit = assoc_array_clear(&keyring->keys, &keyring_assoc_array_ops);
+ if (!IS_ERR(edit)) {
+ if (edit)
+ assoc_array_apply_edit(edit);
+ key_payload_reserve(keyring, 0);
+ }
+}
+
+static bool keyring_gc_select_iterator(void *object, void *iterator_data)
+{
+ struct key *key = keyring_ptr_to_key(object);
+ time_t *limit = iterator_data;
- klist = rcu_dereference_locked_keyring(keyring);
+ if (key_is_dead(key, *limit))
+ return false;
+ key_get(key);
+ return true;
+}
- /* adjust the quota */
- key_payload_reserve(keyring, 0);
+static int keyring_gc_check_iterator(const void *object, void *iterator_data)
+{
+ const struct key *key = keyring_ptr_to_key(object);
+ time_t *limit = iterator_data;
- if (klist) {
- rcu_assign_pointer(keyring->payload.subscriptions, NULL);
- call_rcu(&klist->rcu, keyring_clear_rcu_disposal);
- }
+ key_check(key);
+ return key_is_dead(key, *limit);
}
/*
- * Collect garbage from the contents of a keyring, replacing the old list with
- * a new one with the pointers all shuffled down.
+ * Garbage collect pointers from a keyring.
*
- * Dead keys are classed as oned that are flagged as being dead or are revoked,
- * expired or negative keys that were revoked or expired before the specified
- * limit.
+ * Not called with any locks held. The keyring's key struct will not be
+ * deallocated under us as only our caller may deallocate it.
*/
void keyring_gc(struct key *keyring, time_t limit)
{
- struct keyring_list *klist, *new;
- struct key *key;
- int loop, keep, max;
-
- kenter("{%x,%s}", key_serial(keyring), keyring->description);
-
- down_write(&keyring->sem);
-
- klist = rcu_dereference_locked_keyring(keyring);
- if (!klist)
- goto no_klist;
-
- /* work out how many subscriptions we're keeping */
- keep = 0;
- for (loop = klist->nkeys - 1; loop >= 0; loop--)
- if (!key_is_dead(rcu_deref_link_locked(klist, loop, keyring),
- limit))
- keep++;
-
- if (keep == klist->nkeys)
- goto just_return;
-
- /* allocate a new keyring payload */
- max = roundup(keep, 4);
- new = kmalloc(sizeof(struct keyring_list) + max * sizeof(struct key *),
- GFP_KERNEL);
- if (!new)
- goto nomem;
- new->maxkeys = max;
- new->nkeys = 0;
- new->delkey = 0;
-
- /* install the live keys
- * - must take care as expired keys may be updated back to life
- */
- keep = 0;
- for (loop = klist->nkeys - 1; loop >= 0; loop--) {
- key = rcu_deref_link_locked(klist, loop, keyring);
- if (!key_is_dead(key, limit)) {
- if (keep >= max)
- goto discard_new;
- RCU_INIT_POINTER(new->keys[keep++], key_get(key));
- }
- }
- new->nkeys = keep;
-
- /* adjust the quota */
- key_payload_reserve(keyring,
- sizeof(struct keyring_list) +
- KEYQUOTA_LINK_BYTES * keep);
+ int result;
- if (keep == 0) {
- rcu_assign_pointer(keyring->payload.subscriptions, NULL);
- kfree(new);
- } else {
- rcu_assign_pointer(keyring->payload.subscriptions, new);
- }
+ kenter("%x{%s}", keyring->serial, keyring->description ?: "");
- up_write(&keyring->sem);
+ if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) |
+ (1 << KEY_FLAG_REVOKED)))
+ goto dont_gc;
- call_rcu(&klist->rcu, keyring_clear_rcu_disposal);
- kleave(" [yes]");
- return;
-
-discard_new:
- new->nkeys = keep;
- keyring_clear_rcu_disposal(&new->rcu);
- up_write(&keyring->sem);
- kleave(" [discard]");
- return;
-
-just_return:
- up_write(&keyring->sem);
- kleave(" [no dead]");
- return;
+ /* scan the keyring looking for dead keys */
+ rcu_read_lock();
+ result = assoc_array_iterate(&keyring->keys,
+ keyring_gc_check_iterator, &limit);
+ rcu_read_unlock();
+ if (result == true)
+ goto do_gc;
-no_klist:
- up_write(&keyring->sem);
- kleave(" [no_klist]");
+dont_gc:
+ kleave(" [no gc]");
return;
-nomem:
+do_gc:
+ down_write(&keyring->sem);
+ assoc_array_gc(&keyring->keys, &keyring_assoc_array_ops,
+ keyring_gc_select_iterator, &limit);
up_write(&keyring->sem);
- kleave(" [oom]");
+ kleave(" [gc]");
}
--- /dev/null
+/* General persistent per-UID keyrings register
+ *
+ * Copyright (C) 2013 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 Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/user_namespace.h>
+#include "internal.h"
+
+unsigned persistent_keyring_expiry = 3 * 24 * 3600; /* Expire after 3 days of non-use */
+
+/*
+ * Create the persistent keyring register for the current user namespace.
+ *
+ * Called with the namespace's sem locked for writing.
+ */
+static int key_create_persistent_register(struct user_namespace *ns)
+{
+ struct key *reg = keyring_alloc(".persistent_register",
+ KUIDT_INIT(0), KGIDT_INIT(0),
+ current_cred(),
+ ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+ KEY_USR_VIEW | KEY_USR_READ),
+ KEY_ALLOC_NOT_IN_QUOTA, NULL);
+ if (IS_ERR(reg))
+ return PTR_ERR(reg);
+
+ ns->persistent_keyring_register = reg;
+ return 0;
+}
+
+/*
+ * Create the persistent keyring for the specified user.
+ *
+ * Called with the namespace's sem locked for writing.
+ */
+static key_ref_t key_create_persistent(struct user_namespace *ns, kuid_t uid,
+ struct keyring_index_key *index_key)
+{
+ struct key *persistent;
+ key_ref_t reg_ref, persistent_ref;
+
+ if (!ns->persistent_keyring_register) {
+ long err = key_create_persistent_register(ns);
+ if (err < 0)
+ return ERR_PTR(err);
+ } else {
+ reg_ref = make_key_ref(ns->persistent_keyring_register, true);
+ persistent_ref = find_key_to_update(reg_ref, index_key);
+ if (persistent_ref)
+ return persistent_ref;
+ }
+
+ persistent = keyring_alloc(index_key->description,
+ uid, INVALID_GID, current_cred(),
+ ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+ KEY_USR_VIEW | KEY_USR_READ),
+ KEY_ALLOC_NOT_IN_QUOTA,
+ ns->persistent_keyring_register);
+ if (IS_ERR(persistent))
+ return ERR_CAST(persistent);
+
+ return make_key_ref(persistent, true);
+}
+
+/*
+ * Get the persistent keyring for a specific UID and link it to the nominated
+ * keyring.
+ */
+static long key_get_persistent(struct user_namespace *ns, kuid_t uid,
+ key_ref_t dest_ref)
+{
+ struct keyring_index_key index_key;
+ struct key *persistent;
+ key_ref_t reg_ref, persistent_ref;
+ char buf[32];
+ long ret;
+
+ /* Look in the register if it exists */
+ index_key.type = &key_type_keyring;
+ index_key.description = buf;
+ index_key.desc_len = sprintf(buf, "_persistent.%u", from_kuid(ns, uid));
+
+ if (ns->persistent_keyring_register) {
+ reg_ref = make_key_ref(ns->persistent_keyring_register, true);
+ down_read(&ns->persistent_keyring_register_sem);
+ persistent_ref = find_key_to_update(reg_ref, &index_key);
+ up_read(&ns->persistent_keyring_register_sem);
+
+ if (persistent_ref)
+ goto found;
+ }
+
+ /* It wasn't in the register, so we'll need to create it. We might
+ * also need to create the register.
+ */
+ down_write(&ns->persistent_keyring_register_sem);
+ persistent_ref = key_create_persistent(ns, uid, &index_key);
+ up_write(&ns->persistent_keyring_register_sem);
+ if (!IS_ERR(persistent_ref))
+ goto found;
+
+ return PTR_ERR(persistent_ref);
+
+found:
+ ret = key_task_permission(persistent_ref, current_cred(), KEY_LINK);
+ if (ret == 0) {
+ persistent = key_ref_to_ptr(persistent_ref);
+ ret = key_link(key_ref_to_ptr(dest_ref), persistent);
+ if (ret == 0) {
+ key_set_timeout(persistent, persistent_keyring_expiry);
+ ret = persistent->serial;
+ }
+ }
+
+ key_ref_put(persistent_ref);
+ return ret;
+}
+
+/*
+ * Get the persistent keyring for a specific UID and link it to the nominated
+ * keyring.
+ */
+long keyctl_get_persistent(uid_t _uid, key_serial_t destid)
+{
+ struct user_namespace *ns = current_user_ns();
+ key_ref_t dest_ref;
+ kuid_t uid;
+ long ret;
+
+ /* -1 indicates the current user */
+ if (_uid == (uid_t)-1) {
+ uid = current_uid();
+ } else {
+ uid = make_kuid(ns, _uid);
+ if (!uid_valid(uid))
+ return -EINVAL;
+
+ /* You can only see your own persistent cache if you're not
+ * sufficiently privileged.
+ */
+ if (!uid_eq(uid, current_uid()) &&
+ !uid_eq(uid, current_euid()) &&
+ !ns_capable(ns, CAP_SETUID))
+ return -EPERM;
+ }
+
+ /* There must be a destination keyring */
+ dest_ref = lookup_user_key(destid, KEY_LOOKUP_CREATE, KEY_WRITE);
+ if (IS_ERR(dest_ref))
+ return PTR_ERR(dest_ref);
+ if (key_ref_to_ptr(dest_ref)->type != &key_type_keyring) {
+ ret = -ENOTDIR;
+ goto out_put_dest;
+ }
+
+ ret = key_get_persistent(ns, uid, dest_ref);
+
+out_put_dest:
+ key_ref_put(dest_ref);
+ return ret;
+}
static int proc_keys_show(struct seq_file *m, void *v)
{
- const struct cred *cred = current_cred();
struct rb_node *_p = v;
struct key *key = rb_entry(_p, struct key, serial_node);
struct timespec now;
char xbuf[12];
int rc;
+ struct keyring_search_context ctx = {
+ .index_key.type = key->type,
+ .index_key.description = key->description,
+ .cred = current_cred(),
+ .match = lookup_user_key_possessed,
+ .match_data = key,
+ .flags = (KEYRING_SEARCH_NO_STATE_CHECK |
+ KEYRING_SEARCH_LOOKUP_DIRECT),
+ };
+
key_ref = make_key_ref(key, 0);
/* determine if the key is possessed by this process (a test we can
* skip if the key does not indicate the possessor can view it
*/
if (key->perm & KEY_POS_VIEW) {
- skey_ref = search_my_process_keyrings(key->type, key,
- lookup_user_key_possessed,
- true, cred);
+ skey_ref = search_my_process_keyrings(&ctx);
if (!IS_ERR(skey_ref)) {
key_ref_put(skey_ref);
key_ref = make_key_ref(key, 1);
* - the caller holds a spinlock, and thus the RCU read lock, making our
* access to __current_cred() safe
*/
- rc = key_task_permission(key_ref, cred, KEY_VIEW);
+ rc = key_task_permission(key_ref, ctx.cred, KEY_VIEW);
if (rc < 0)
return 0;
if (IS_ERR(keyring))
return PTR_ERR(keyring);
} else {
- atomic_inc(&keyring->usage);
+ __key_get(keyring);
}
/* install the keyring */
* In the case of a successful return, the possession attribute is set on the
* returned key reference.
*/
-key_ref_t search_my_process_keyrings(struct key_type *type,
- const void *description,
- key_match_func_t match,
- bool no_state_check,
- const struct cred *cred)
+key_ref_t search_my_process_keyrings(struct keyring_search_context *ctx)
{
key_ref_t key_ref, ret, err;
err = ERR_PTR(-EAGAIN);
/* search the thread keyring first */
- if (cred->thread_keyring) {
+ if (ctx->cred->thread_keyring) {
key_ref = keyring_search_aux(
- make_key_ref(cred->thread_keyring, 1),
- cred, type, description, match, no_state_check);
+ make_key_ref(ctx->cred->thread_keyring, 1), ctx);
if (!IS_ERR(key_ref))
goto found;
}
/* search the process keyring second */
- if (cred->process_keyring) {
+ if (ctx->cred->process_keyring) {
key_ref = keyring_search_aux(
- make_key_ref(cred->process_keyring, 1),
- cred, type, description, match, no_state_check);
+ make_key_ref(ctx->cred->process_keyring, 1), ctx);
if (!IS_ERR(key_ref))
goto found;
}
/* search the session keyring */
- if (cred->session_keyring) {
+ if (ctx->cred->session_keyring) {
rcu_read_lock();
key_ref = keyring_search_aux(
- make_key_ref(rcu_dereference(cred->session_keyring), 1),
- cred, type, description, match, no_state_check);
+ make_key_ref(rcu_dereference(ctx->cred->session_keyring), 1),
+ ctx);
rcu_read_unlock();
if (!IS_ERR(key_ref))
}
}
/* or search the user-session keyring */
- else if (cred->user->session_keyring) {
+ else if (ctx->cred->user->session_keyring) {
key_ref = keyring_search_aux(
- make_key_ref(cred->user->session_keyring, 1),
- cred, type, description, match, no_state_check);
+ make_key_ref(ctx->cred->user->session_keyring, 1),
+ ctx);
if (!IS_ERR(key_ref))
goto found;
*
* Return same as search_my_process_keyrings().
*/
-key_ref_t search_process_keyrings(struct key_type *type,
- const void *description,
- key_match_func_t match,
- const struct cred *cred)
+key_ref_t search_process_keyrings(struct keyring_search_context *ctx)
{
struct request_key_auth *rka;
key_ref_t key_ref, ret = ERR_PTR(-EACCES), err;
might_sleep();
- key_ref = search_my_process_keyrings(type, description, match,
- false, cred);
+ key_ref = search_my_process_keyrings(ctx);
if (!IS_ERR(key_ref))
goto found;
err = key_ref;
* search the keyrings of the process mentioned there
* - we don't permit access to request_key auth keys via this method
*/
- if (cred->request_key_auth &&
- cred == current_cred() &&
- type != &key_type_request_key_auth
+ if (ctx->cred->request_key_auth &&
+ ctx->cred == current_cred() &&
+ ctx->index_key.type != &key_type_request_key_auth
) {
+ const struct cred *cred = ctx->cred;
+
/* defend against the auth key being revoked */
down_read(&cred->request_key_auth->sem);
- if (key_validate(cred->request_key_auth) == 0) {
- rka = cred->request_key_auth->payload.data;
+ if (key_validate(ctx->cred->request_key_auth) == 0) {
+ rka = ctx->cred->request_key_auth->payload.data;
- key_ref = search_process_keyrings(type, description,
- match, rka->cred);
+ ctx->cred = rka->cred;
+ key_ref = search_process_keyrings(ctx);
+ ctx->cred = cred;
up_read(&cred->request_key_auth->sem);
key_ref_t lookup_user_key(key_serial_t id, unsigned long lflags,
key_perm_t perm)
{
+ struct keyring_search_context ctx = {
+ .match = lookup_user_key_possessed,
+ .flags = (KEYRING_SEARCH_NO_STATE_CHECK |
+ KEYRING_SEARCH_LOOKUP_DIRECT),
+ };
struct request_key_auth *rka;
- const struct cred *cred;
struct key *key;
key_ref_t key_ref, skey_ref;
int ret;
try_again:
- cred = get_current_cred();
+ ctx.cred = get_current_cred();
key_ref = ERR_PTR(-ENOKEY);
switch (id) {
case KEY_SPEC_THREAD_KEYRING:
- if (!cred->thread_keyring) {
+ if (!ctx.cred->thread_keyring) {
if (!(lflags & KEY_LOOKUP_CREATE))
goto error;
goto reget_creds;
}
- key = cred->thread_keyring;
- atomic_inc(&key->usage);
+ key = ctx.cred->thread_keyring;
+ __key_get(key);
key_ref = make_key_ref(key, 1);
break;
case KEY_SPEC_PROCESS_KEYRING:
- if (!cred->process_keyring) {
+ if (!ctx.cred->process_keyring) {
if (!(lflags & KEY_LOOKUP_CREATE))
goto error;
goto reget_creds;
}
- key = cred->process_keyring;
- atomic_inc(&key->usage);
+ key = ctx.cred->process_keyring;
+ __key_get(key);
key_ref = make_key_ref(key, 1);
break;
case KEY_SPEC_SESSION_KEYRING:
- if (!cred->session_keyring) {
+ if (!ctx.cred->session_keyring) {
/* always install a session keyring upon access if one
* doesn't exist yet */
ret = install_user_keyrings();
ret = join_session_keyring(NULL);
else
ret = install_session_keyring(
- cred->user->session_keyring);
+ ctx.cred->user->session_keyring);
if (ret < 0)
goto error;
goto reget_creds;
- } else if (cred->session_keyring ==
- cred->user->session_keyring &&
+ } else if (ctx.cred->session_keyring ==
+ ctx.cred->user->session_keyring &&
lflags & KEY_LOOKUP_CREATE) {
ret = join_session_keyring(NULL);
if (ret < 0)
}
rcu_read_lock();
- key = rcu_dereference(cred->session_keyring);
- atomic_inc(&key->usage);
+ key = rcu_dereference(ctx.cred->session_keyring);
+ __key_get(key);
rcu_read_unlock();
key_ref = make_key_ref(key, 1);
break;
case KEY_SPEC_USER_KEYRING:
- if (!cred->user->uid_keyring) {
+ if (!ctx.cred->user->uid_keyring) {
ret = install_user_keyrings();
if (ret < 0)
goto error;
}
- key = cred->user->uid_keyring;
- atomic_inc(&key->usage);
+ key = ctx.cred->user->uid_keyring;
+ __key_get(key);
key_ref = make_key_ref(key, 1);
break;
case KEY_SPEC_USER_SESSION_KEYRING:
- if (!cred->user->session_keyring) {
+ if (!ctx.cred->user->session_keyring) {
ret = install_user_keyrings();
if (ret < 0)
goto error;
}
- key = cred->user->session_keyring;
- atomic_inc(&key->usage);
+ key = ctx.cred->user->session_keyring;
+ __key_get(key);
key_ref = make_key_ref(key, 1);
break;
goto error;
case KEY_SPEC_REQKEY_AUTH_KEY:
- key = cred->request_key_auth;
+ key = ctx.cred->request_key_auth;
if (!key)
goto error;
- atomic_inc(&key->usage);
+ __key_get(key);
key_ref = make_key_ref(key, 1);
break;
case KEY_SPEC_REQUESTOR_KEYRING:
- if (!cred->request_key_auth)
+ if (!ctx.cred->request_key_auth)
goto error;
- down_read(&cred->request_key_auth->sem);
+ down_read(&ctx.cred->request_key_auth->sem);
if (test_bit(KEY_FLAG_REVOKED,
- &cred->request_key_auth->flags)) {
+ &ctx.cred->request_key_auth->flags)) {
key_ref = ERR_PTR(-EKEYREVOKED);
key = NULL;
} else {
- rka = cred->request_key_auth->payload.data;
+ rka = ctx.cred->request_key_auth->payload.data;
key = rka->dest_keyring;
- atomic_inc(&key->usage);
+ __key_get(key);
}
- up_read(&cred->request_key_auth->sem);
+ up_read(&ctx.cred->request_key_auth->sem);
if (!key)
goto error;
key_ref = make_key_ref(key, 1);
key_ref = make_key_ref(key, 0);
/* check to see if we possess the key */
- skey_ref = search_process_keyrings(key->type, key,
- lookup_user_key_possessed,
- cred);
+ ctx.index_key.type = key->type;
+ ctx.index_key.description = key->description;
+ ctx.index_key.desc_len = strlen(key->description);
+ ctx.match_data = key;
+ kdebug("check possessed");
+ skey_ref = search_process_keyrings(&ctx);
+ kdebug("possessed=%p", skey_ref);
if (!IS_ERR(skey_ref)) {
key_put(key);
goto invalid_key;
/* check the permissions */
- ret = key_task_permission(key_ref, cred, perm);
+ ret = key_task_permission(key_ref, ctx.cred, perm);
if (ret < 0)
goto invalid_key;
key->last_used_at = current_kernel_time().tv_sec;
error:
- put_cred(cred);
+ put_cred(ctx.cred);
return key_ref;
invalid_key:
/* if we attempted to install a keyring, then it may have caused new
* creds to be installed */
reget_creds:
- put_cred(cred);
+ put_cred(ctx.cred);
goto try_again;
}
commit_creds(new);
}
+
+/*
+ * Make sure that root's user and user-session keyrings exist.
+ */
+static int __init init_root_keyring(void)
+{
+ return install_user_keyrings();
+}
+
+late_initcall(init_root_keyring);
* May return a key that's already under construction instead if there was a
* race between two thread calling request_key().
*/
-static int construct_alloc_key(struct key_type *type,
- const char *description,
+static int construct_alloc_key(struct keyring_search_context *ctx,
struct key *dest_keyring,
unsigned long flags,
struct key_user *user,
struct key **_key)
{
- const struct cred *cred = current_cred();
- unsigned long prealloc;
+ struct assoc_array_edit *edit;
struct key *key;
key_perm_t perm;
key_ref_t key_ref;
int ret;
- kenter("%s,%s,,,", type->name, description);
+ kenter("%s,%s,,,",
+ ctx->index_key.type->name, ctx->index_key.description);
*_key = NULL;
mutex_lock(&user->cons_lock);
perm = KEY_POS_VIEW | KEY_POS_SEARCH | KEY_POS_LINK | KEY_POS_SETATTR;
perm |= KEY_USR_VIEW;
- if (type->read)
+ if (ctx->index_key.type->read)
perm |= KEY_POS_READ;
- if (type == &key_type_keyring || type->update)
+ if (ctx->index_key.type == &key_type_keyring ||
+ ctx->index_key.type->update)
perm |= KEY_POS_WRITE;
- key = key_alloc(type, description, cred->fsuid, cred->fsgid, cred,
+ key = key_alloc(ctx->index_key.type, ctx->index_key.description,
+ ctx->cred->fsuid, ctx->cred->fsgid, ctx->cred,
perm, flags);
if (IS_ERR(key))
goto alloc_failed;
set_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags);
if (dest_keyring) {
- ret = __key_link_begin(dest_keyring, type, description,
- &prealloc);
+ ret = __key_link_begin(dest_keyring, &ctx->index_key, &edit);
if (ret < 0)
goto link_prealloc_failed;
}
* waited for locks */
mutex_lock(&key_construction_mutex);
- key_ref = search_process_keyrings(type, description, type->match, cred);
+ key_ref = search_process_keyrings(ctx);
if (!IS_ERR(key_ref))
goto key_already_present;
if (dest_keyring)
- __key_link(dest_keyring, key, &prealloc);
+ __key_link(key, &edit);
mutex_unlock(&key_construction_mutex);
if (dest_keyring)
- __key_link_end(dest_keyring, type, prealloc);
+ __key_link_end(dest_keyring, &ctx->index_key, edit);
mutex_unlock(&user->cons_lock);
*_key = key;
kleave(" = 0 [%d]", key_serial(key));
if (dest_keyring) {
ret = __key_link_check_live_key(dest_keyring, key);
if (ret == 0)
- __key_link(dest_keyring, key, &prealloc);
- __key_link_end(dest_keyring, type, prealloc);
+ __key_link(key, &edit);
+ __key_link_end(dest_keyring, &ctx->index_key, edit);
if (ret < 0)
goto link_check_failed;
}
/*
* Commence key construction.
*/
-static struct key *construct_key_and_link(struct key_type *type,
- const char *description,
+static struct key *construct_key_and_link(struct keyring_search_context *ctx,
const char *callout_info,
size_t callout_len,
void *aux,
construct_get_dest_keyring(&dest_keyring);
- ret = construct_alloc_key(type, description, dest_keyring, flags, user,
- &key);
+ ret = construct_alloc_key(ctx, dest_keyring, flags, user, &key);
key_user_put(user);
if (ret == 0) {
struct key *dest_keyring,
unsigned long flags)
{
- const struct cred *cred = current_cred();
+ struct keyring_search_context ctx = {
+ .index_key.type = type,
+ .index_key.description = description,
+ .cred = current_cred(),
+ .match = type->match,
+ .match_data = description,
+ .flags = KEYRING_SEARCH_LOOKUP_DIRECT,
+ };
struct key *key;
key_ref_t key_ref;
int ret;
kenter("%s,%s,%p,%zu,%p,%p,%lx",
- type->name, description, callout_info, callout_len, aux,
- dest_keyring, flags);
+ ctx.index_key.type->name, ctx.index_key.description,
+ callout_info, callout_len, aux, dest_keyring, flags);
/* search all the process keyrings for a key */
- key_ref = search_process_keyrings(type, description, type->match, cred);
+ key_ref = search_process_keyrings(&ctx);
if (!IS_ERR(key_ref)) {
key = key_ref_to_ptr(key_ref);
if (!callout_info)
goto error;
- key = construct_key_and_link(type, description, callout_info,
- callout_len, aux, dest_keyring,
- flags);
+ key = construct_key_and_link(&ctx, callout_info, callout_len,
+ aux, dest_keyring, flags);
}
error:
intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
if (ret < 0)
return ret;
- if (test_bit(KEY_FLAG_NEGATIVE, &key->flags))
+ if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) {
+ smp_rmb();
return key->type_data.reject_error;
+ }
return key_validate(key);
}
EXPORT_SYMBOL(wait_for_key_construction);
#include <linux/slab.h>
#include <asm/uaccess.h>
#include "internal.h"
+#include <keys/user-type.h>
static int request_key_auth_instantiate(struct key *,
struct key_preparsed_payload *);
return ERR_PTR(ret);
}
-/*
- * See if an authorisation key is associated with a particular key.
- */
-static int key_get_instantiation_authkey_match(const struct key *key,
- const void *_id)
-{
- struct request_key_auth *rka = key->payload.data;
- key_serial_t id = (key_serial_t)(unsigned long) _id;
-
- return rka->target_key->serial == id;
-}
-
/*
* Search the current process's keyrings for the authorisation key for
* instantiation of a key.
*/
struct key *key_get_instantiation_authkey(key_serial_t target_id)
{
- const struct cred *cred = current_cred();
+ char description[16];
+ struct keyring_search_context ctx = {
+ .index_key.type = &key_type_request_key_auth,
+ .index_key.description = description,
+ .cred = current_cred(),
+ .match = user_match,
+ .match_data = description,
+ .flags = KEYRING_SEARCH_LOOKUP_DIRECT,
+ };
struct key *authkey;
key_ref_t authkey_ref;
- authkey_ref = search_process_keyrings(
- &key_type_request_key_auth,
- (void *) (unsigned long) target_id,
- key_get_instantiation_authkey_match,
- cred);
+ sprintf(description, "%x", target_id);
+
+ authkey_ref = search_process_keyrings(&ctx);
if (IS_ERR(authkey_ref)) {
authkey = ERR_CAST(authkey_ref);
.extra1 = (void *) &zero,
.extra2 = (void *) &max,
},
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+ {
+ .procname = "persistent_keyring_expiry",
+ .data = &persistent_keyring_expiry,
+ .maxlen = sizeof(unsigned),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = (void *) &zero,
+ .extra2 = (void *) &max,
+ },
+#endif
{ }
};
* arbitrary blob of data as the payload
*/
struct key_type key_type_user = {
- .name = "user",
- .instantiate = user_instantiate,
- .update = user_update,
- .match = user_match,
- .revoke = user_revoke,
- .destroy = user_destroy,
- .describe = user_describe,
- .read = user_read,
+ .name = "user",
+ .def_lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT,
+ .instantiate = user_instantiate,
+ .update = user_update,
+ .match = user_match,
+ .revoke = user_revoke,
+ .destroy = user_destroy,
+ .describe = user_describe,
+ .read = user_read,
};
EXPORT_SYMBOL_GPL(key_type_user);
*/
struct key_type key_type_logon = {
.name = "logon",
+ .def_lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT,
.instantiate = user_instantiate,
.update = user_update,
.match = user_match,
if (a == NULL)
return;
/* we use GFP_ATOMIC so we won't sleep */
- ab = audit_log_start(current->audit_context, GFP_ATOMIC, AUDIT_AVC);
+ ab = audit_log_start(current->audit_context, GFP_ATOMIC | __GFP_NOWARN,
+ AUDIT_AVC);
if (ab == NULL)
return;
return security_ops->xfrm_policy_delete_security(ctx);
}
-int security_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx)
+int security_xfrm_state_alloc(struct xfrm_state *x,
+ struct xfrm_user_sec_ctx *sec_ctx)
{
- return security_ops->xfrm_state_alloc_security(x, sec_ctx, 0);
+ return security_ops->xfrm_state_alloc(x, sec_ctx);
}
EXPORT_SYMBOL(security_xfrm_state_alloc);
int security_xfrm_state_alloc_acquire(struct xfrm_state *x,
struct xfrm_sec_ctx *polsec, u32 secid)
{
- if (!polsec)
- return 0;
- /*
- * We want the context to be taken from secid which is usually
- * from the sock.
- */
- return security_ops->xfrm_state_alloc_security(x, NULL, secid);
+ return security_ops->xfrm_state_alloc_acquire(x, polsec, secid);
}
int security_xfrm_state_delete(struct xfrm_state *x)
#include "audit.h"
#include "avc_ss.h"
-#define NUM_SEL_MNT_OPTS 5
+#define SB_TYPE_FMT "%s%s%s"
+#define SB_SUBTYPE(sb) (sb->s_subtype && sb->s_subtype[0])
+#define SB_TYPE_ARGS(sb) sb->s_type->name, SB_SUBTYPE(sb) ? "." : "", SB_SUBTYPE(sb) ? sb->s_subtype : ""
extern struct security_operations *security_ops;
* This function checks the SECMARK reference counter to see if any SECMARK
* targets are currently configured, if the reference counter is greater than
* zero SECMARK is considered to be enabled. Returns true (1) if SECMARK is
- * enabled, false (0) if SECMARK is disabled.
+ * enabled, false (0) if SECMARK is disabled. If the always_check_network
+ * policy capability is enabled, SECMARK is always considered enabled.
*
*/
static int selinux_secmark_enabled(void)
{
- return (atomic_read(&selinux_secmark_refcount) > 0);
+ return (selinux_policycap_alwaysnetwork || atomic_read(&selinux_secmark_refcount));
+}
+
+/**
+ * selinux_peerlbl_enabled - Check to see if peer labeling is currently enabled
+ *
+ * Description:
+ * This function checks if NetLabel or labeled IPSEC is enabled. Returns true
+ * (1) if any are enabled or false (0) if neither are enabled. If the
+ * always_check_network policy capability is enabled, peer labeling
+ * is always considered enabled.
+ *
+ */
+static int selinux_peerlbl_enabled(void)
+{
+ return (selinux_policycap_alwaysnetwork || netlbl_enabled() || selinux_xfrm_enabled());
}
/*
Opt_defcontext = 3,
Opt_rootcontext = 4,
Opt_labelsupport = 5,
+ Opt_nextmntopt = 6,
};
+#define NUM_SEL_MNT_OPTS (Opt_nextmntopt - 1)
+
static const match_table_t tokens = {
{Opt_context, CONTEXT_STR "%s"},
{Opt_fscontext, FSCONTEXT_STR "%s"},
return rc;
}
+static int selinux_is_sblabel_mnt(struct super_block *sb)
+{
+ struct superblock_security_struct *sbsec = sb->s_security;
+
+ if (sbsec->behavior == SECURITY_FS_USE_XATTR ||
+ sbsec->behavior == SECURITY_FS_USE_TRANS ||
+ sbsec->behavior == SECURITY_FS_USE_TASK)
+ return 1;
+
+ /* Special handling for sysfs. Is genfs but also has setxattr handler*/
+ if (strncmp(sb->s_type->name, "sysfs", sizeof("sysfs")) == 0)
+ return 1;
+
+ /*
+ * Special handling for rootfs. Is genfs but supports
+ * setting SELinux context on in-core inodes.
+ */
+ if (strncmp(sb->s_type->name, "rootfs", sizeof("rootfs")) == 0)
+ return 1;
+
+ return 0;
+}
+
static int sb_finish_set_opts(struct super_block *sb)
{
struct superblock_security_struct *sbsec = sb->s_security;
the first boot of the SELinux kernel before we have
assigned xattr values to the filesystem. */
if (!root_inode->i_op->getxattr) {
- printk(KERN_WARNING "SELinux: (dev %s, type %s) has no "
- "xattr support\n", sb->s_id, sb->s_type->name);
+ printk(KERN_WARNING "SELinux: (dev %s, type "SB_TYPE_FMT") has no "
+ "xattr support\n", sb->s_id, SB_TYPE_ARGS(sb));
rc = -EOPNOTSUPP;
goto out;
}
if (rc < 0 && rc != -ENODATA) {
if (rc == -EOPNOTSUPP)
printk(KERN_WARNING "SELinux: (dev %s, type "
- "%s) has no security xattr handler\n",
- sb->s_id, sb->s_type->name);
+ SB_TYPE_FMT") has no security xattr handler\n",
+ sb->s_id, SB_TYPE_ARGS(sb));
else
printk(KERN_WARNING "SELinux: (dev %s, type "
- "%s) getxattr errno %d\n", sb->s_id,
- sb->s_type->name, -rc);
+ SB_TYPE_FMT") getxattr errno %d\n", sb->s_id,
+ SB_TYPE_ARGS(sb), -rc);
goto out;
}
}
- sbsec->flags |= (SE_SBINITIALIZED | SE_SBLABELSUPP);
-
if (sbsec->behavior > ARRAY_SIZE(labeling_behaviors))
- printk(KERN_ERR "SELinux: initialized (dev %s, type %s), unknown behavior\n",
- sb->s_id, sb->s_type->name);
+ printk(KERN_ERR "SELinux: initialized (dev %s, type "SB_TYPE_FMT"), unknown behavior\n",
+ sb->s_id, SB_TYPE_ARGS(sb));
else
- printk(KERN_DEBUG "SELinux: initialized (dev %s, type %s), %s\n",
- sb->s_id, sb->s_type->name,
+ printk(KERN_DEBUG "SELinux: initialized (dev %s, type "SB_TYPE_FMT"), %s\n",
+ sb->s_id, SB_TYPE_ARGS(sb),
labeling_behaviors[sbsec->behavior-1]);
- if (sbsec->behavior == SECURITY_FS_USE_GENFS ||
- sbsec->behavior == SECURITY_FS_USE_MNTPOINT ||
- sbsec->behavior == SECURITY_FS_USE_NONE ||
- sbsec->behavior > ARRAY_SIZE(labeling_behaviors))
- sbsec->flags &= ~SE_SBLABELSUPP;
-
- /* Special handling for sysfs. Is genfs but also has setxattr handler*/
- if (strncmp(sb->s_type->name, "sysfs", sizeof("sysfs")) == 0)
- sbsec->flags |= SE_SBLABELSUPP;
+ sbsec->flags |= SE_SBINITIALIZED;
+ if (selinux_is_sblabel_mnt(sb))
+ sbsec->flags |= SBLABEL_MNT;
/* Initialize the root inode. */
rc = inode_doinit_with_dentry(root_inode, root);
if (!ss_initialized)
return -EINVAL;
+ /* make sure we always check enough bits to cover the mask */
+ BUILD_BUG_ON(SE_MNTMASK >= (1 << NUM_SEL_MNT_OPTS));
+
tmp = sbsec->flags & SE_MNTMASK;
/* count the number of mount options for this sb */
- for (i = 0; i < 8; i++) {
+ for (i = 0; i < NUM_SEL_MNT_OPTS; i++) {
if (tmp & 0x01)
opts->num_mnt_opts++;
tmp >>= 1;
}
/* Check if the Label support flag is set */
- if (sbsec->flags & SE_SBLABELSUPP)
+ if (sbsec->flags & SBLABEL_MNT)
opts->num_mnt_opts++;
opts->mnt_opts = kcalloc(opts->num_mnt_opts, sizeof(char *), GFP_ATOMIC);
opts->mnt_opts[i] = context;
opts->mnt_opts_flags[i++] = ROOTCONTEXT_MNT;
}
- if (sbsec->flags & SE_SBLABELSUPP) {
+ if (sbsec->flags & SBLABEL_MNT) {
opts->mnt_opts[i] = NULL;
- opts->mnt_opts_flags[i++] = SE_SBLABELSUPP;
+ opts->mnt_opts_flags[i++] = SBLABEL_MNT;
}
BUG_ON(i != opts->num_mnt_opts);
const struct cred *cred = current_cred();
int rc = 0, i;
struct superblock_security_struct *sbsec = sb->s_security;
- const char *name = sb->s_type->name;
struct inode *inode = sbsec->sb->s_root->d_inode;
struct inode_security_struct *root_isec = inode->i_security;
u32 fscontext_sid = 0, context_sid = 0, rootcontext_sid = 0;
for (i = 0; i < num_opts; i++) {
u32 sid;
- if (flags[i] == SE_SBLABELSUPP)
+ if (flags[i] == SBLABEL_MNT)
continue;
rc = security_context_to_sid(mount_options[i],
strlen(mount_options[i]), &sid);
if (rc) {
printk(KERN_WARNING "SELinux: security_context_to_sid"
- "(%s) failed for (dev %s, type %s) errno=%d\n",
- mount_options[i], sb->s_id, name, rc);
+ "(%s) failed for (dev %s, type "SB_TYPE_FMT") errno=%d\n",
+ mount_options[i], sb->s_id, SB_TYPE_ARGS(sb), rc);
goto out;
}
switch (flags[i]) {
* Determine the labeling behavior to use for this
* filesystem type.
*/
- rc = security_fs_use((sbsec->flags & SE_SBPROC) ?
- "proc" : sb->s_type->name,
- &sbsec->behavior, &sbsec->sid);
+ rc = security_fs_use(sb);
if (rc) {
printk(KERN_WARNING
"%s: security_fs_use(%s) returned %d\n",
out_double_mount:
rc = -EINVAL;
printk(KERN_WARNING "SELinux: mount invalid. Same superblock, different "
- "security settings for (dev %s, type %s)\n", sb->s_id, name);
+ "security settings for (dev %s, type "SB_TYPE_FMT")\n", sb->s_id,
+ SB_TYPE_ARGS(sb));
goto out;
}
case DEFCONTEXT_MNT:
prefix = DEFCONTEXT_STR;
break;
- case SE_SBLABELSUPP:
+ case SBLABEL_MNT:
seq_putc(m, ',');
seq_puts(m, LABELSUPP_STR);
continue;
if (rc)
return rc;
- if (!newsid || !(sbsec->flags & SE_SBLABELSUPP)) {
+ if (!newsid || !(sbsec->flags & SBLABEL_MNT)) {
rc = security_transition_sid(sid, dsec->sid, tclass,
&dentry->d_name, &newsid);
if (rc)
u32 sid;
size_t len;
- if (flags[i] == SE_SBLABELSUPP)
+ if (flags[i] == SBLABEL_MNT)
continue;
len = strlen(mount_options[i]);
rc = security_context_to_sid(mount_options[i], len, &sid);
if (rc) {
printk(KERN_WARNING "SELinux: security_context_to_sid"
- "(%s) failed for (dev %s, type %s) errno=%d\n",
- mount_options[i], sb->s_id, sb->s_type->name, rc);
+ "(%s) failed for (dev %s, type "SB_TYPE_FMT") errno=%d\n",
+ mount_options[i], sb->s_id, SB_TYPE_ARGS(sb), rc);
goto out_free_opts;
}
rc = -EINVAL;
return rc;
out_bad_option:
printk(KERN_WARNING "SELinux: unable to change security options "
- "during remount (dev %s, type=%s)\n", sb->s_id,
- sb->s_type->name);
+ "during remount (dev %s, type "SB_TYPE_FMT")\n", sb->s_id,
+ SB_TYPE_ARGS(sb));
goto out_free_opts;
}
if ((sbsec->flags & SE_SBINITIALIZED) &&
(sbsec->behavior == SECURITY_FS_USE_MNTPOINT))
newsid = sbsec->mntpoint_sid;
- else if (!newsid || !(sbsec->flags & SE_SBLABELSUPP)) {
+ else if (!newsid || !(sbsec->flags & SBLABEL_MNT)) {
rc = security_transition_sid(sid, dsec->sid,
inode_mode_to_security_class(inode->i_mode),
qstr, &newsid);
isec->initialized = 1;
}
- if (!ss_initialized || !(sbsec->flags & SE_SBLABELSUPP))
+ if (!ss_initialized || !(sbsec->flags & SBLABEL_MNT))
return -EOPNOTSUPP;
if (name)
return selinux_inode_setotherxattr(dentry, name);
sbsec = inode->i_sb->s_security;
- if (!(sbsec->flags & SE_SBLABELSUPP))
+ if (!(sbsec->flags & SBLABEL_MNT))
return -EOPNOTSUPP;
if (!inode_owner_or_capable(inode))
u32 nlbl_sid;
u32 nlbl_type;
- selinux_skb_xfrm_sid(skb, &xfrm_sid);
- selinux_netlbl_skbuff_getsid(skb, family, &nlbl_type, &nlbl_sid);
+ err = selinux_skb_xfrm_sid(skb, &xfrm_sid);
+ if (unlikely(err))
+ return -EACCES;
+ err = selinux_netlbl_skbuff_getsid(skb, family, &nlbl_type, &nlbl_sid);
+ if (unlikely(err))
+ return -EACCES;
err = security_net_peersid_resolve(nlbl_sid, nlbl_type, xfrm_sid, sid);
if (unlikely(err)) {
return selinux_sock_rcv_skb_compat(sk, skb, family);
secmark_active = selinux_secmark_enabled();
- peerlbl_active = netlbl_enabled() || selinux_xfrm_enabled();
+ peerlbl_active = selinux_peerlbl_enabled();
if (!secmark_active && !peerlbl_active)
return 0;
secmark_active = selinux_secmark_enabled();
netlbl_active = netlbl_enabled();
- peerlbl_active = netlbl_active || selinux_xfrm_enabled();
+ peerlbl_active = selinux_peerlbl_enabled();
if (!secmark_active && !peerlbl_active)
return NF_ACCEPT;
return NF_ACCEPT;
#endif
secmark_active = selinux_secmark_enabled();
- peerlbl_active = netlbl_enabled() || selinux_xfrm_enabled();
+ peerlbl_active = selinux_peerlbl_enabled();
if (!secmark_active && !peerlbl_active)
return NF_ACCEPT;
.xfrm_policy_clone_security = selinux_xfrm_policy_clone,
.xfrm_policy_free_security = selinux_xfrm_policy_free,
.xfrm_policy_delete_security = selinux_xfrm_policy_delete,
- .xfrm_state_alloc_security = selinux_xfrm_state_alloc,
+ .xfrm_state_alloc = selinux_xfrm_state_alloc,
+ .xfrm_state_alloc_acquire = selinux_xfrm_state_alloc_acquire,
.xfrm_state_free_security = selinux_xfrm_state_free,
.xfrm_state_delete_security = selinux_xfrm_state_delete,
.xfrm_policy_lookup = selinux_xfrm_policy_lookup,
u32 sid; /* SID of file system superblock */
u32 def_sid; /* default SID for labeling */
u32 mntpoint_sid; /* SECURITY_FS_USE_MNTPOINT context for files */
- unsigned int behavior; /* labeling behavior */
- unsigned char flags; /* which mount options were specified */
+ unsigned short behavior; /* labeling behavior */
+ unsigned short flags; /* which mount options were specified */
struct mutex lock;
struct list_head isec_head;
spinlock_t isec_lock;
/* Mask for just the mount related flags */
#define SE_MNTMASK 0x0f
/* Super block security struct flags for mount options */
+/* BE CAREFUL, these need to be the low order bits for selinux_get_mnt_opts */
#define CONTEXT_MNT 0x01
#define FSCONTEXT_MNT 0x02
#define ROOTCONTEXT_MNT 0x04
#define DEFCONTEXT_MNT 0x08
+#define SBLABEL_MNT 0x10
/* Non-mount related flags */
-#define SE_SBINITIALIZED 0x10
-#define SE_SBPROC 0x20
-#define SE_SBLABELSUPP 0x40
+#define SE_SBINITIALIZED 0x0100
+#define SE_SBPROC 0x0200
#define CONTEXT_STR "context="
#define FSCONTEXT_STR "fscontext="
enum {
POLICYDB_CAPABILITY_NETPEER,
POLICYDB_CAPABILITY_OPENPERM,
+ POLICYDB_CAPABILITY_REDHAT1,
+ POLICYDB_CAPABILITY_ALWAYSNETWORK,
__POLICYDB_CAPABILITY_MAX
};
#define POLICYDB_CAPABILITY_MAX (__POLICYDB_CAPABILITY_MAX - 1)
extern int selinux_policycap_netpeer;
extern int selinux_policycap_openperm;
+extern int selinux_policycap_alwaysnetwork;
/*
* type_datum properties
#define SECURITY_FS_USE_NATIVE 7 /* use native label support */
#define SECURITY_FS_USE_MAX 7 /* Highest SECURITY_FS_USE_XXX */
-int security_fs_use(const char *fstype, unsigned int *behavior,
- u32 *sid);
+int security_fs_use(struct super_block *sb);
int security_genfs_sid(const char *fstype, char *name, u16 sclass,
u32 *sid);
#include <net/flow.h>
int selinux_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
- struct xfrm_user_sec_ctx *sec_ctx);
+ struct xfrm_user_sec_ctx *uctx);
int selinux_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx,
struct xfrm_sec_ctx **new_ctxp);
void selinux_xfrm_policy_free(struct xfrm_sec_ctx *ctx);
int selinux_xfrm_policy_delete(struct xfrm_sec_ctx *ctx);
int selinux_xfrm_state_alloc(struct xfrm_state *x,
- struct xfrm_user_sec_ctx *sec_ctx, u32 secid);
+ struct xfrm_user_sec_ctx *uctx);
+int selinux_xfrm_state_alloc_acquire(struct xfrm_state *x,
+ struct xfrm_sec_ctx *polsec, u32 secid);
void selinux_xfrm_state_free(struct xfrm_state *x);
int selinux_xfrm_state_delete(struct xfrm_state *x);
int selinux_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir);
int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x,
- struct xfrm_policy *xp, const struct flowi *fl);
-
-/*
- * Extract the security blob from the sock (it's actually on the socket)
- */
-static inline struct inode_security_struct *get_sock_isec(struct sock *sk)
-{
- if (!sk->sk_socket)
- return NULL;
-
- return SOCK_INODE(sk->sk_socket)->i_security;
-}
+ struct xfrm_policy *xp,
+ const struct flowi *fl);
#ifdef CONFIG_SECURITY_NETWORK_XFRM
extern atomic_t selinux_xfrm_refcount;
return (atomic_read(&selinux_xfrm_refcount) > 0);
}
-int selinux_xfrm_sock_rcv_skb(u32 sid, struct sk_buff *skb,
- struct common_audit_data *ad);
-int selinux_xfrm_postroute_last(u32 isec_sid, struct sk_buff *skb,
- struct common_audit_data *ad, u8 proto);
+int selinux_xfrm_sock_rcv_skb(u32 sk_sid, struct sk_buff *skb,
+ struct common_audit_data *ad);
+int selinux_xfrm_postroute_last(u32 sk_sid, struct sk_buff *skb,
+ struct common_audit_data *ad, u8 proto);
int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall);
static inline void selinux_xfrm_notify_policyload(void)
return 0;
}
-static inline int selinux_xfrm_sock_rcv_skb(u32 isec_sid, struct sk_buff *skb,
- struct common_audit_data *ad)
+static inline int selinux_xfrm_sock_rcv_skb(u32 sk_sid, struct sk_buff *skb,
+ struct common_audit_data *ad)
{
return 0;
}
-static inline int selinux_xfrm_postroute_last(u32 isec_sid, struct sk_buff *skb,
- struct common_audit_data *ad, u8 proto)
+static inline int selinux_xfrm_postroute_last(u32 sk_sid, struct sk_buff *skb,
+ struct common_audit_data *ad,
+ u8 proto)
{
return 0;
}
-static inline int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall)
+static inline int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid,
+ int ckall)
{
*sid = SECSID_NULL;
return 0;
}
#endif
-static inline void selinux_skb_xfrm_sid(struct sk_buff *skb, u32 *sid)
+static inline int selinux_skb_xfrm_sid(struct sk_buff *skb, u32 *sid)
{
- int err = selinux_xfrm_decode_session(skb, sid, 0);
- BUG_ON(err);
+ return selinux_xfrm_decode_session(skb, sid, 0);
}
#endif /* _SELINUX_XFRM_H_ */
sksec->nlbl_state != NLBL_CONNLABELED)
return 0;
- local_bh_disable();
- bh_lock_sock_nested(sk);
+ lock_sock(sk);
/* connected sockets are allowed to disconnect when the address family
* is set to AF_UNSPEC, if that is what is happening we want to reset
sksec->nlbl_state = NLBL_CONNLABELED;
socket_connect_return:
- bh_unlock_sock(sk);
- local_bh_enable();
+ release_sock(sk);
return rc;
}
break;
default:
BUG();
+ return;
}
/* we need to impose a limit on the growth of the hash table so check
break;
default:
BUG();
+ ret = -EINVAL;
}
if (ret != 0)
goto out;
{ AUDIT_MAKE_EQUIV, NETLINK_AUDIT_SOCKET__NLMSG_WRITE },
{ AUDIT_TTY_GET, NETLINK_AUDIT_SOCKET__NLMSG_READ },
{ AUDIT_TTY_SET, NETLINK_AUDIT_SOCKET__NLMSG_TTY_AUDIT },
+ { AUDIT_GET_FEATURE, NETLINK_AUDIT_SOCKET__NLMSG_READ },
+ { AUDIT_SET_FEATURE, NETLINK_AUDIT_SOCKET__NLMSG_WRITE },
};
/* Policy capability filenames */
static char *policycap_names[] = {
"network_peer_controls",
- "open_perms"
+ "open_perms",
+ "redhat1",
+ "always_check_network"
};
unsigned int selinux_checkreqprot = CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE;
}
#endif /* CONFIG_NETLABEL */
-int ebitmap_contains(struct ebitmap *e1, struct ebitmap *e2)
+/*
+ * Check to see if all the bits set in e2 are also set in e1. Optionally,
+ * if last_e2bit is non-zero, the highest set bit in e2 cannot exceed
+ * last_e2bit.
+ */
+int ebitmap_contains(struct ebitmap *e1, struct ebitmap *e2, u32 last_e2bit)
{
struct ebitmap_node *n1, *n2;
int i;
n1 = e1->node;
n2 = e2->node;
+
while (n1 && n2 && (n1->startbit <= n2->startbit)) {
if (n1->startbit < n2->startbit) {
n1 = n1->next;
continue;
}
- for (i = 0; i < EBITMAP_UNIT_NUMS; i++) {
+ for (i = EBITMAP_UNIT_NUMS - 1; (i >= 0) && !n2->maps[i]; )
+ i--; /* Skip trailing NULL map entries */
+ if (last_e2bit && (i >= 0)) {
+ u32 lastsetbit = n2->startbit + i * EBITMAP_UNIT_SIZE +
+ __fls(n2->maps[i]);
+ if (lastsetbit > last_e2bit)
+ return 0;
+ }
+
+ while (i >= 0) {
if ((n1->maps[i] & n2->maps[i]) != n2->maps[i])
return 0;
+ i--;
}
n1 = n1->next;
#include <net/netlabel.h>
-#define EBITMAP_UNIT_NUMS ((32 - sizeof(void *) - sizeof(u32)) \
+#ifdef CONFIG_64BIT
+#define EBITMAP_NODE_SIZE 64
+#else
+#define EBITMAP_NODE_SIZE 32
+#endif
+
+#define EBITMAP_UNIT_NUMS ((EBITMAP_NODE_SIZE-sizeof(void *)-sizeof(u32))\
/ sizeof(unsigned long))
#define EBITMAP_UNIT_SIZE BITS_PER_LONG
#define EBITMAP_SIZE (EBITMAP_UNIT_NUMS * EBITMAP_UNIT_SIZE)
int ebitmap_cmp(struct ebitmap *e1, struct ebitmap *e2);
int ebitmap_cpy(struct ebitmap *dst, struct ebitmap *src);
-int ebitmap_contains(struct ebitmap *e1, struct ebitmap *e2);
+int ebitmap_contains(struct ebitmap *e1, struct ebitmap *e2, u32 last_e2bit);
int ebitmap_get_bit(struct ebitmap *e, unsigned long bit);
int ebitmap_set_bit(struct ebitmap *e, unsigned long bit, int value);
void ebitmap_destroy(struct ebitmap *e);
int mls_level_isvalid(struct policydb *p, struct mls_level *l)
{
struct level_datum *levdatum;
- struct ebitmap_node *node;
- int i;
if (!l->sens || l->sens > p->p_levels.nprim)
return 0;
if (!levdatum)
return 0;
- ebitmap_for_each_positive_bit(&l->cat, node, i) {
- if (i > p->p_cats.nprim)
- return 0;
- if (!ebitmap_get_bit(&levdatum->level->cat, i)) {
- /*
- * Category may not be associated with
- * sensitivity.
- */
- return 0;
- }
- }
-
- return 1;
+ /*
+ * Return 1 iff all the bits set in l->cat are also be set in
+ * levdatum->level->cat and no bit in l->cat is larger than
+ * p->p_cats.nprim.
+ */
+ return ebitmap_contains(&levdatum->level->cat, &l->cat,
+ p->p_cats.nprim);
}
int mls_range_isvalid(struct policydb *p, struct mls_range *r)
static inline int mls_level_dom(struct mls_level *l1, struct mls_level *l2)
{
return ((l1->sens >= l2->sens) &&
- ebitmap_contains(&l1->cat, &l2->cat));
+ ebitmap_contains(&l1->cat, &l2->cat, 0));
}
#define mls_level_incomp(l1, l2) \
static int range_write(struct policydb *p, void *fp)
{
- size_t nel;
__le32 buf[1];
- int rc;
+ int rc, nel;
struct policy_data pd;
pd.p = p;
int selinux_policycap_netpeer;
int selinux_policycap_openperm;
+int selinux_policycap_alwaysnetwork;
static DEFINE_RWLOCK(policy_rwlock);
POLICYDB_CAPABILITY_NETPEER);
selinux_policycap_openperm = ebitmap_get_bit(&policydb.policycaps,
POLICYDB_CAPABILITY_OPENPERM);
+ selinux_policycap_alwaysnetwork = ebitmap_get_bit(&policydb.policycaps,
+ POLICYDB_CAPABILITY_ALWAYSNETWORK);
}
static int security_preserve_bools(struct policydb *p);
/**
* security_fs_use - Determine how to handle labeling for a filesystem.
- * @fstype: filesystem type
- * @behavior: labeling behavior
- * @sid: SID for filesystem (superblock)
+ * @sb: superblock in question
*/
-int security_fs_use(
- const char *fstype,
- unsigned int *behavior,
- u32 *sid)
+int security_fs_use(struct super_block *sb)
{
int rc = 0;
struct ocontext *c;
+ struct superblock_security_struct *sbsec = sb->s_security;
+ const char *fstype = sb->s_type->name;
+ const char *subtype = (sb->s_subtype && sb->s_subtype[0]) ? sb->s_subtype : NULL;
+ struct ocontext *base = NULL;
read_lock(&policy_rwlock);
- c = policydb.ocontexts[OCON_FSUSE];
- while (c) {
- if (strcmp(fstype, c->u.name) == 0)
+ for (c = policydb.ocontexts[OCON_FSUSE]; c; c = c->next) {
+ char *sub;
+ int baselen;
+
+ baselen = strlen(fstype);
+
+ /* if base does not match, this is not the one */
+ if (strncmp(fstype, c->u.name, baselen))
+ continue;
+
+ /* if there is no subtype, this is the one! */
+ if (!subtype)
+ break;
+
+ /* skip past the base in this entry */
+ sub = c->u.name + baselen;
+
+ /* entry is only a base. save it. keep looking for subtype */
+ if (sub[0] == '\0') {
+ base = c;
+ continue;
+ }
+
+ /* entry is not followed by a subtype, so it is not a match */
+ if (sub[0] != '.')
+ continue;
+
+ /* whew, we found a subtype of this fstype */
+ sub++; /* move past '.' */
+
+ /* exact match of fstype AND subtype */
+ if (!strcmp(subtype, sub))
break;
- c = c->next;
}
+ /* in case we had found an fstype match but no subtype match */
+ if (!c)
+ c = base;
+
if (c) {
- *behavior = c->v.behavior;
+ sbsec->behavior = c->v.behavior;
if (!c->sid[0]) {
rc = sidtab_context_to_sid(&sidtab, &c->context[0],
&c->sid[0]);
if (rc)
goto out;
}
- *sid = c->sid[0];
+ sbsec->sid = c->sid[0];
} else {
- rc = security_genfs_sid(fstype, "/", SECCLASS_DIR, sid);
+ rc = security_genfs_sid(fstype, "/", SECCLASS_DIR, &sbsec->sid);
if (rc) {
- *behavior = SECURITY_FS_USE_NONE;
+ sbsec->behavior = SECURITY_FS_USE_NONE;
rc = 0;
} else {
- *behavior = SECURITY_FS_USE_GENFS;
+ sbsec->behavior = SECURITY_FS_USE_GENFS;
}
}
atomic_t selinux_xfrm_refcount = ATOMIC_INIT(0);
/*
- * Returns true if an LSM/SELinux context
+ * Returns true if the context is an LSM/SELinux context.
*/
static inline int selinux_authorizable_ctx(struct xfrm_sec_ctx *ctx)
{
}
/*
- * Returns true if the xfrm contains a security blob for SELinux
+ * Returns true if the xfrm contains a security blob for SELinux.
*/
static inline int selinux_authorizable_xfrm(struct xfrm_state *x)
{
}
/*
- * LSM hook implementation that authorizes that a flow can use
- * a xfrm policy rule.
+ * Allocates a xfrm_sec_state and populates it using the supplied security
+ * xfrm_user_sec_ctx context.
*/
-int selinux_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir)
+static int selinux_xfrm_alloc_user(struct xfrm_sec_ctx **ctxp,
+ struct xfrm_user_sec_ctx *uctx)
{
int rc;
- u32 sel_sid;
+ const struct task_security_struct *tsec = current_security();
+ struct xfrm_sec_ctx *ctx = NULL;
+ u32 str_len;
- /* Context sid is either set to label or ANY_ASSOC */
- if (ctx) {
- if (!selinux_authorizable_ctx(ctx))
- return -EINVAL;
-
- sel_sid = ctx->ctx_sid;
- } else
- /*
- * All flows should be treated as polmatch'ing an
- * otherwise applicable "non-labeled" policy. This
- * would prevent inadvertent "leaks".
- */
- return 0;
+ if (ctxp == NULL || uctx == NULL ||
+ uctx->ctx_doi != XFRM_SC_DOI_LSM ||
+ uctx->ctx_alg != XFRM_SC_ALG_SELINUX)
+ return -EINVAL;
- rc = avc_has_perm(fl_secid, sel_sid, SECCLASS_ASSOCIATION,
- ASSOCIATION__POLMATCH,
- NULL);
+ str_len = uctx->ctx_len;
+ if (str_len >= PAGE_SIZE)
+ return -ENOMEM;
- if (rc == -EACCES)
- return -ESRCH;
+ ctx = kmalloc(sizeof(*ctx) + str_len + 1, GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+ ctx->ctx_doi = XFRM_SC_DOI_LSM;
+ ctx->ctx_alg = XFRM_SC_ALG_SELINUX;
+ ctx->ctx_len = str_len;
+ memcpy(ctx->ctx_str, &uctx[1], str_len);
+ ctx->ctx_str[str_len] = '\0';
+ rc = security_context_to_sid(ctx->ctx_str, str_len, &ctx->ctx_sid);
+ if (rc)
+ goto err;
+
+ rc = avc_has_perm(tsec->sid, ctx->ctx_sid,
+ SECCLASS_ASSOCIATION, ASSOCIATION__SETCONTEXT, NULL);
+ if (rc)
+ goto err;
+
+ *ctxp = ctx;
+ atomic_inc(&selinux_xfrm_refcount);
+ return 0;
+
+err:
+ kfree(ctx);
return rc;
}
+/*
+ * Free the xfrm_sec_ctx structure.
+ */
+static void selinux_xfrm_free(struct xfrm_sec_ctx *ctx)
+{
+ if (!ctx)
+ return;
+
+ atomic_dec(&selinux_xfrm_refcount);
+ kfree(ctx);
+}
+
+/*
+ * Authorize the deletion of a labeled SA or policy rule.
+ */
+static int selinux_xfrm_delete(struct xfrm_sec_ctx *ctx)
+{
+ const struct task_security_struct *tsec = current_security();
+
+ if (!ctx)
+ return 0;
+
+ return avc_has_perm(tsec->sid, ctx->ctx_sid,
+ SECCLASS_ASSOCIATION, ASSOCIATION__SETCONTEXT,
+ NULL);
+}
+
+/*
+ * LSM hook implementation that authorizes that a flow can use a xfrm policy
+ * rule.
+ */
+int selinux_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir)
+{
+ int rc;
+
+ /* All flows should be treated as polmatch'ing an otherwise applicable
+ * "non-labeled" policy. This would prevent inadvertent "leaks". */
+ if (!ctx)
+ return 0;
+
+ /* Context sid is either set to label or ANY_ASSOC */
+ if (!selinux_authorizable_ctx(ctx))
+ return -EINVAL;
+
+ rc = avc_has_perm(fl_secid, ctx->ctx_sid,
+ SECCLASS_ASSOCIATION, ASSOCIATION__POLMATCH, NULL);
+ return (rc == -EACCES ? -ESRCH : rc);
+}
+
/*
* LSM hook implementation that authorizes that a state matches
* the given policy, flow combo.
*/
-
-int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *xp,
- const struct flowi *fl)
+int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x,
+ struct xfrm_policy *xp,
+ const struct flowi *fl)
{
u32 state_sid;
- int rc;
if (!xp->security)
if (x->security)
if (fl->flowi_secid != state_sid)
return 0;
- rc = avc_has_perm(fl->flowi_secid, state_sid, SECCLASS_ASSOCIATION,
- ASSOCIATION__SENDTO,
- NULL)? 0:1;
-
- /*
- * We don't need a separate SA Vs. policy polmatch check
- * since the SA is now of the same label as the flow and
- * a flow Vs. policy polmatch check had already happened
- * in selinux_xfrm_policy_lookup() above.
- */
-
- return rc;
+ /* We don't need a separate SA Vs. policy polmatch check since the SA
+ * is now of the same label as the flow and a flow Vs. policy polmatch
+ * check had already happened in selinux_xfrm_policy_lookup() above. */
+ return (avc_has_perm(fl->flowi_secid, state_sid,
+ SECCLASS_ASSOCIATION, ASSOCIATION__SENDTO,
+ NULL) ? 0 : 1);
}
/*
* LSM hook implementation that checks and/or returns the xfrm sid for the
* incoming packet.
*/
-
int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall)
{
+ u32 sid_session = SECSID_NULL;
struct sec_path *sp;
- *sid = SECSID_NULL;
-
if (skb == NULL)
- return 0;
+ goto out;
sp = skb->sp;
if (sp) {
- int i, sid_set = 0;
+ int i;
- for (i = sp->len-1; i >= 0; i--) {
+ for (i = sp->len - 1; i >= 0; i--) {
struct xfrm_state *x = sp->xvec[i];
if (selinux_authorizable_xfrm(x)) {
struct xfrm_sec_ctx *ctx = x->security;
- if (!sid_set) {
- *sid = ctx->ctx_sid;
- sid_set = 1;
-
+ if (sid_session == SECSID_NULL) {
+ sid_session = ctx->ctx_sid;
if (!ckall)
- break;
- } else if (*sid != ctx->ctx_sid)
+ goto out;
+ } else if (sid_session != ctx->ctx_sid) {
+ *sid = SECSID_NULL;
return -EINVAL;
+ }
}
}
}
- return 0;
-}
-
-/*
- * Security blob allocation for xfrm_policy and xfrm_state
- * CTX does not have a meaningful value on input
- */
-static int selinux_xfrm_sec_ctx_alloc(struct xfrm_sec_ctx **ctxp,
- struct xfrm_user_sec_ctx *uctx, u32 sid)
-{
- int rc = 0;
- const struct task_security_struct *tsec = current_security();
- struct xfrm_sec_ctx *ctx = NULL;
- char *ctx_str = NULL;
- u32 str_len;
-
- BUG_ON(uctx && sid);
-
- if (!uctx)
- goto not_from_user;
-
- if (uctx->ctx_alg != XFRM_SC_ALG_SELINUX)
- return -EINVAL;
-
- str_len = uctx->ctx_len;
- if (str_len >= PAGE_SIZE)
- return -ENOMEM;
-
- *ctxp = ctx = kmalloc(sizeof(*ctx) +
- str_len + 1,
- GFP_KERNEL);
-
- if (!ctx)
- return -ENOMEM;
-
- ctx->ctx_doi = uctx->ctx_doi;
- ctx->ctx_len = str_len;
- ctx->ctx_alg = uctx->ctx_alg;
-
- memcpy(ctx->ctx_str,
- uctx+1,
- str_len);
- ctx->ctx_str[str_len] = 0;
- rc = security_context_to_sid(ctx->ctx_str,
- str_len,
- &ctx->ctx_sid);
-
- if (rc)
- goto out;
-
- /*
- * Does the subject have permission to set security context?
- */
- rc = avc_has_perm(tsec->sid, ctx->ctx_sid,
- SECCLASS_ASSOCIATION,
- ASSOCIATION__SETCONTEXT, NULL);
- if (rc)
- goto out;
-
- return rc;
-
-not_from_user:
- rc = security_sid_to_context(sid, &ctx_str, &str_len);
- if (rc)
- goto out;
-
- *ctxp = ctx = kmalloc(sizeof(*ctx) +
- str_len,
- GFP_ATOMIC);
-
- if (!ctx) {
- rc = -ENOMEM;
- goto out;
- }
-
- ctx->ctx_doi = XFRM_SC_DOI_LSM;
- ctx->ctx_alg = XFRM_SC_ALG_SELINUX;
- ctx->ctx_sid = sid;
- ctx->ctx_len = str_len;
- memcpy(ctx->ctx_str,
- ctx_str,
- str_len);
-
- goto out2;
-
out:
- *ctxp = NULL;
- kfree(ctx);
-out2:
- kfree(ctx_str);
- return rc;
+ *sid = sid_session;
+ return 0;
}
/*
- * LSM hook implementation that allocs and transfers uctx spec to
- * xfrm_policy.
+ * LSM hook implementation that allocs and transfers uctx spec to xfrm_policy.
*/
int selinux_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
struct xfrm_user_sec_ctx *uctx)
{
- int err;
-
- BUG_ON(!uctx);
-
- err = selinux_xfrm_sec_ctx_alloc(ctxp, uctx, 0);
- if (err == 0)
- atomic_inc(&selinux_xfrm_refcount);
-
- return err;
+ return selinux_xfrm_alloc_user(ctxp, uctx);
}
-
/*
- * LSM hook implementation that copies security data structure from old to
- * new for policy cloning.
+ * LSM hook implementation that copies security data structure from old to new
+ * for policy cloning.
*/
int selinux_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx,
struct xfrm_sec_ctx **new_ctxp)
{
struct xfrm_sec_ctx *new_ctx;
- if (old_ctx) {
- new_ctx = kmalloc(sizeof(*old_ctx) + old_ctx->ctx_len,
- GFP_ATOMIC);
- if (!new_ctx)
- return -ENOMEM;
+ if (!old_ctx)
+ return 0;
+
+ new_ctx = kmemdup(old_ctx, sizeof(*old_ctx) + old_ctx->ctx_len,
+ GFP_ATOMIC);
+ if (!new_ctx)
+ return -ENOMEM;
+ atomic_inc(&selinux_xfrm_refcount);
+ *new_ctxp = new_ctx;
- memcpy(new_ctx, old_ctx, sizeof(*new_ctx));
- memcpy(new_ctx->ctx_str, old_ctx->ctx_str, new_ctx->ctx_len);
- atomic_inc(&selinux_xfrm_refcount);
- *new_ctxp = new_ctx;
- }
return 0;
}
*/
void selinux_xfrm_policy_free(struct xfrm_sec_ctx *ctx)
{
- atomic_dec(&selinux_xfrm_refcount);
- kfree(ctx);
+ selinux_xfrm_free(ctx);
}
/*
*/
int selinux_xfrm_policy_delete(struct xfrm_sec_ctx *ctx)
{
- const struct task_security_struct *tsec = current_security();
-
- if (!ctx)
- return 0;
+ return selinux_xfrm_delete(ctx);
+}
- return avc_has_perm(tsec->sid, ctx->ctx_sid,
- SECCLASS_ASSOCIATION, ASSOCIATION__SETCONTEXT,
- NULL);
+/*
+ * LSM hook implementation that allocates a xfrm_sec_state, populates it using
+ * the supplied security context, and assigns it to the xfrm_state.
+ */
+int selinux_xfrm_state_alloc(struct xfrm_state *x,
+ struct xfrm_user_sec_ctx *uctx)
+{
+ return selinux_xfrm_alloc_user(&x->security, uctx);
}
/*
- * LSM hook implementation that allocs and transfers sec_ctx spec to
- * xfrm_state.
+ * LSM hook implementation that allocates a xfrm_sec_state and populates based
+ * on a secid.
*/
-int selinux_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *uctx,
- u32 secid)
+int selinux_xfrm_state_alloc_acquire(struct xfrm_state *x,
+ struct xfrm_sec_ctx *polsec, u32 secid)
{
- int err;
+ int rc;
+ struct xfrm_sec_ctx *ctx;
+ char *ctx_str = NULL;
+ int str_len;
+
+ if (!polsec)
+ return 0;
- BUG_ON(!x);
+ if (secid == 0)
+ return -EINVAL;
- err = selinux_xfrm_sec_ctx_alloc(&x->security, uctx, secid);
- if (err == 0)
- atomic_inc(&selinux_xfrm_refcount);
- return err;
+ rc = security_sid_to_context(secid, &ctx_str, &str_len);
+ if (rc)
+ return rc;
+
+ ctx = kmalloc(sizeof(*ctx) + str_len, GFP_ATOMIC);
+ if (!ctx)
+ return -ENOMEM;
+
+ ctx->ctx_doi = XFRM_SC_DOI_LSM;
+ ctx->ctx_alg = XFRM_SC_ALG_SELINUX;
+ ctx->ctx_sid = secid;
+ ctx->ctx_len = str_len;
+ memcpy(ctx->ctx_str, ctx_str, str_len);
+ kfree(ctx_str);
+
+ x->security = ctx;
+ atomic_inc(&selinux_xfrm_refcount);
+ return 0;
}
/*
*/
void selinux_xfrm_state_free(struct xfrm_state *x)
{
- atomic_dec(&selinux_xfrm_refcount);
- kfree(x->security);
+ selinux_xfrm_free(x->security);
}
- /*
- * LSM hook implementation that authorizes deletion of labeled SAs.
- */
+/*
+ * LSM hook implementation that authorizes deletion of labeled SAs.
+ */
int selinux_xfrm_state_delete(struct xfrm_state *x)
{
- const struct task_security_struct *tsec = current_security();
- struct xfrm_sec_ctx *ctx = x->security;
-
- if (!ctx)
- return 0;
-
- return avc_has_perm(tsec->sid, ctx->ctx_sid,
- SECCLASS_ASSOCIATION, ASSOCIATION__SETCONTEXT,
- NULL);
+ return selinux_xfrm_delete(x->security);
}
/*
* we need to check for unlabelled access since this may not have
* gone thru the IPSec process.
*/
-int selinux_xfrm_sock_rcv_skb(u32 isec_sid, struct sk_buff *skb,
- struct common_audit_data *ad)
+int selinux_xfrm_sock_rcv_skb(u32 sk_sid, struct sk_buff *skb,
+ struct common_audit_data *ad)
{
- int i, rc = 0;
- struct sec_path *sp;
- u32 sel_sid = SECINITSID_UNLABELED;
-
- sp = skb->sp;
+ int i;
+ struct sec_path *sp = skb->sp;
+ u32 peer_sid = SECINITSID_UNLABELED;
if (sp) {
for (i = 0; i < sp->len; i++) {
if (x && selinux_authorizable_xfrm(x)) {
struct xfrm_sec_ctx *ctx = x->security;
- sel_sid = ctx->ctx_sid;
+ peer_sid = ctx->ctx_sid;
break;
}
}
}
- /*
- * This check even when there's no association involved is
- * intended, according to Trent Jaeger, to make sure a
- * process can't engage in non-ipsec communication unless
- * explicitly allowed by policy.
- */
-
- rc = avc_has_perm(isec_sid, sel_sid, SECCLASS_ASSOCIATION,
- ASSOCIATION__RECVFROM, ad);
-
- return rc;
+ /* This check even when there's no association involved is intended,
+ * according to Trent Jaeger, to make sure a process can't engage in
+ * non-IPsec communication unless explicitly allowed by policy. */
+ return avc_has_perm(sk_sid, peer_sid,
+ SECCLASS_ASSOCIATION, ASSOCIATION__RECVFROM, ad);
}
/*
* If we do have a authorizable security association, then it has already been
* checked in the selinux_xfrm_state_pol_flow_match hook above.
*/
-int selinux_xfrm_postroute_last(u32 isec_sid, struct sk_buff *skb,
- struct common_audit_data *ad, u8 proto)
+int selinux_xfrm_postroute_last(u32 sk_sid, struct sk_buff *skb,
+ struct common_audit_data *ad, u8 proto)
{
struct dst_entry *dst;
- int rc = 0;
-
- dst = skb_dst(skb);
-
- if (dst) {
- struct dst_entry *dst_test;
-
- for (dst_test = dst; dst_test != NULL;
- dst_test = dst_test->child) {
- struct xfrm_state *x = dst_test->xfrm;
-
- if (x && selinux_authorizable_xfrm(x))
- goto out;
- }
- }
switch (proto) {
case IPPROTO_AH:
case IPPROTO_ESP:
case IPPROTO_COMP:
- /*
- * We should have already seen this packet once before
- * it underwent xfrm(s). No need to subject it to the
- * unlabeled check.
- */
- goto out;
+ /* We should have already seen this packet once before it
+ * underwent xfrm(s). No need to subject it to the unlabeled
+ * check. */
+ return 0;
default:
break;
}
- /*
- * This check even when there's no association involved is
- * intended, according to Trent Jaeger, to make sure a
- * process can't engage in non-ipsec communication unless
- * explicitly allowed by policy.
- */
+ dst = skb_dst(skb);
+ if (dst) {
+ struct dst_entry *iter;
- rc = avc_has_perm(isec_sid, SECINITSID_UNLABELED, SECCLASS_ASSOCIATION,
- ASSOCIATION__SENDTO, ad);
-out:
- return rc;
+ for (iter = dst; iter != NULL; iter = iter->child) {
+ struct xfrm_state *x = iter->xfrm;
+
+ if (x && selinux_authorizable_xfrm(x))
+ return 0;
+ }
+ }
+
+ /* This check even when there's no association involved is intended,
+ * according to Trent Jaeger, to make sure a process can't engage in
+ * non-IPsec communication unless explicitly allowed by policy. */
+ return avc_has_perm(sk_sid, SECINITSID_UNLABELED,
+ SECCLASS_ASSOCIATION, ASSOCIATION__SENDTO, ad);
}
#define SMACK_CIPSO_MAXCATNUM 184 /* 23 * 8 */
/*
- * Flag for transmute access
+ * Flags for untraditional access modes.
+ * It shouldn't be necessary to avoid conflicts with definitions
+ * in fs.h, but do so anyway.
*/
-#define MAY_TRANSMUTE 64
+#define MAY_TRANSMUTE 0x00001000 /* Controls directory labeling */
+#define MAY_LOCK 0x00002000 /* Locks should be writes, but ... */
+
/*
* Just to make the common cases easier to deal with
*/
#define MAY_NOT 0
/*
- * Number of access types used by Smack (rwxat)
+ * Number of access types used by Smack (rwxatl)
*/
-#define SMK_NUM_ACCESS_TYPE 5
+#define SMK_NUM_ACCESS_TYPE 6
/* SMACK data */
struct smack_audit_data {
*
* Do the object check first because that is more
* likely to differ.
+ *
+ * Allowing write access implies allowing locking.
*/
int smk_access_entry(char *subject_label, char *object_label,
struct list_head *rule_list)
}
}
+ /*
+ * MAY_WRITE implies MAY_LOCK.
+ */
+ if ((may & MAY_WRITE) == MAY_WRITE)
+ may |= MAY_LOCK;
return may;
}
static inline void smack_str_from_perm(char *string, int access)
{
int i = 0;
+
if (access & MAY_READ)
string[i++] = 'r';
if (access & MAY_WRITE)
string[i++] = 'a';
if (access & MAY_TRANSMUTE)
string[i++] = 't';
+ if (access & MAY_LOCK)
+ string[i++] = 'l';
string[i] = '\0';
}
/**
smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
smk_ad_setfield_u_tsk(&ad, ctp);
- rc = smk_curacc(skp->smk_known, MAY_READWRITE, &ad);
+ rc = smk_curacc(skp->smk_known, mode, &ad);
return rc;
}
* @file: the object
* @cmd: unused
*
- * Returns 0 if current has write access, error code otherwise
+ * Returns 0 if current has lock access, error code otherwise
*/
static int smack_file_lock(struct file *file, unsigned int cmd)
{
smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
smk_ad_setfield_u_fs_path(&ad, file->f_path);
- return smk_curacc(file->f_security, MAY_WRITE, &ad);
+ return smk_curacc(file->f_security, MAY_LOCK, &ad);
}
/**
switch (cmd) {
case F_GETLK:
+ break;
case F_SETLK:
case F_SETLKW:
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
+ smk_ad_setfield_u_fs_path(&ad, file->f_path);
+ rc = smk_curacc(file->f_security, MAY_LOCK, &ad);
+ break;
case F_SETOWN:
case F_SETSIG:
smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
* SMK_LOADLEN: Smack rule length
*/
#define SMK_OACCESS "rwxa"
-#define SMK_ACCESS "rwxat"
+#define SMK_ACCESS "rwxatl"
#define SMK_OACCESSLEN (sizeof(SMK_OACCESS) - 1)
#define SMK_ACCESSLEN (sizeof(SMK_ACCESS) - 1)
#define SMK_OLOADLEN (SMK_LABELLEN + SMK_LABELLEN + SMK_OACCESSLEN)
case 'T':
perm |= MAY_TRANSMUTE;
break;
+ case 'l':
+ case 'L':
+ perm |= MAY_LOCK;
+ break;
default:
return perm;
}
/*
* Minor hack for backward compatibility
*/
- if (count != SMK_OLOADLEN && count != SMK_LOADLEN)
+ if (count < SMK_OLOADLEN || count > SMK_LOADLEN)
return -EINVAL;
} else {
if (count >= PAGE_SIZE) {
seq_putc(s, 'a');
if (srp->smk_access & MAY_TRANSMUTE)
seq_putc(s, 't');
+ if (srp->smk_access & MAY_LOCK)
+ seq_putc(s, 'l');
seq_putc(s, '\n');
}
#include <linux/err.h>
#include <linux/interrupt.h>
#include <linux/mutex.h>
+#include <sound/asound.h>
#include "packets-buffer.h"
/**
config SND_HDA_CODEC_CA0132_DSP
bool "Support new DSP code for CA0132 codec"
- depends on SND_HDA_CODEC_CA0132 && FW_LOADER
+ depends on SND_HDA_CODEC_CA0132
select SND_HDA_DSP_LOADER
+ select FW_LOADER
help
Say Y here to enable the DSP for Creative CA0132 for extended
features like equalizer or echo cancellation.
* in the resume / power-save sequence
*/
hda_keep_power_on(codec);
+ if (codec->pm_down_notified) {
+ codec->pm_down_notified = 0;
+ hda_call_pm_notify(codec->bus, true);
+ }
hda_set_power_state(codec, AC_PWRST_D0);
restore_shutup_pins(codec);
hda_exec_init_verbs(codec);
ALC260_FIXUP_KN1,
ALC260_FIXUP_FSC_S7020,
ALC260_FIXUP_FSC_S7020_JWSE,
+ ALC260_FIXUP_VAIO_PINS,
};
static void alc260_gpio1_automute(struct hda_codec *codec)
.chained = true,
.chain_id = ALC260_FIXUP_FSC_S7020,
},
+ [ALC260_FIXUP_VAIO_PINS] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ /* Pin configs are missing completely on some VAIOs */
+ { 0x0f, 0x01211020 },
+ { 0x10, 0x0001003f },
+ { 0x11, 0x411111f0 },
+ { 0x12, 0x01a15930 },
+ { 0x13, 0x411111f0 },
+ { 0x14, 0x411111f0 },
+ { 0x15, 0x411111f0 },
+ { 0x16, 0x411111f0 },
+ { 0x17, 0x411111f0 },
+ { 0x18, 0x411111f0 },
+ { 0x19, 0x411111f0 },
+ { }
+ }
+ },
};
static const struct snd_pci_quirk alc260_fixup_tbl[] = {
SND_PCI_QUIRK(0x1025, 0x008f, "Acer", ALC260_FIXUP_GPIO1),
SND_PCI_QUIRK(0x103c, 0x280a, "HP dc5750", ALC260_FIXUP_HP_DC5750),
SND_PCI_QUIRK(0x103c, 0x30ba, "HP Presario B1900", ALC260_FIXUP_HP_B1900),
+ SND_PCI_QUIRK(0x104d, 0x81bb, "Sony VAIO", ALC260_FIXUP_VAIO_PINS),
+ SND_PCI_QUIRK(0x104d, 0x81e2, "Sony VAIO TX", ALC260_FIXUP_HP_PIN_0F),
SND_PCI_QUIRK(0x10cf, 0x1326, "FSC LifeBook S7020", ALC260_FIXUP_FSC_S7020),
SND_PCI_QUIRK(0x1509, 0x4540, "Favorit 100XS", ALC260_FIXUP_GPIO1),
SND_PCI_QUIRK(0x152d, 0x0729, "Quanta KN1", ALC260_FIXUP_KN1),
static void alc_update_headset_jack_cb(struct hda_codec *codec, struct hda_jack_tbl *jack)
{
struct alc_spec *spec = codec->spec;
- spec->current_headset_type = ALC_HEADSET_MODE_UNKNOWN;
+ spec->current_headset_type = ALC_HEADSET_TYPE_UNKNOWN;
snd_hda_gen_hp_automute(codec, jack);
}
#if IS_ENABLED(CONFIG_THINKPAD_ACPI)
#include <linux/thinkpad_acpi.h>
+#include <acpi/acpi.h>
static int (*led_set_func)(int, bool);
+static acpi_status acpi_check_cb(acpi_handle handle, u32 lvl, void *context,
+ void **rv)
+{
+ bool *found = context;
+ *found = true;
+ return AE_OK;
+}
+
+static bool is_thinkpad(struct hda_codec *codec)
+{
+ bool found = false;
+ if (codec->subsystem_id >> 16 != 0x17aa)
+ return false;
+ if (ACPI_SUCCESS(acpi_get_devices("LEN0068", acpi_check_cb, &found, NULL)) && found)
+ return true;
+ found = false;
+ return ACPI_SUCCESS(acpi_get_devices("IBM0068", acpi_check_cb, &found, NULL)) && found;
+}
+
static void update_tpacpi_mute_led(void *private_data, int enabled)
{
if (led_set_func)
bool removefunc = false;
if (action == HDA_FIXUP_ACT_PROBE) {
+ if (!is_thinkpad(codec))
+ return;
if (!led_set_func)
led_set_func = symbol_request(tpacpi_led_set);
if (!led_set_func) {
[ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc269_fixup_pincfg_no_hp_to_lineout,
+ .chained = true,
+ .chain_id = ALC269_FIXUP_THINKPAD_ACPI,
},
[ALC269_FIXUP_DELL1_MIC_NO_PRESENCE] = {
.type = HDA_FIXUP_PINS,
[ALC269_FIXUP_LIMIT_INT_MIC_BOOST] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc269_fixup_limit_int_mic_boost,
+ .chained = true,
+ .chain_id = ALC269_FIXUP_THINKPAD_ACPI,
},
[ALC269_FIXUP_LIMIT_INT_MIC_BOOST_MUTE_LED] = {
.type = HDA_FIXUP_FUNC,
[ALC269_FIXUP_THINKPAD_ACPI] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc_fixup_thinkpad_acpi,
- .chained = true,
- .chain_id = ALC269_FIXUP_LIMIT_INT_MIC_BOOST
},
[ALC255_FIXUP_DELL1_MIC_NO_PRESENCE] = {
.type = HDA_FIXUP_PINS,
SND_PCI_QUIRK(0x1028, 0x0608, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0609, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0613, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1028, 0x0614, "Dell Inspiron 3135", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0616, "Dell Vostro 5470", ALC290_FIXUP_MONO_SPEAKERS),
SND_PCI_QUIRK(0x1028, 0x061f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x063f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x17aa, 0x2208, "Thinkpad T431s", ALC269_FIXUP_LENOVO_DOCK),
SND_PCI_QUIRK(0x17aa, 0x220c, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x17aa, 0x2212, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
- SND_PCI_QUIRK(0x17aa, 0x2214, "Thinkpad", ALC269_FIXUP_THINKPAD_ACPI),
+ SND_PCI_QUIRK(0x17aa, 0x2214, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x17aa, 0x2215, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x17aa, 0x501a, "Thinkpad", ALC283_FIXUP_INT_MIC),
SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K),
SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD),
+ SND_PCI_QUIRK_VENDOR(0x17aa, "Thinkpad", ALC269_FIXUP_THINKPAD_ACPI),
SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */
#if 0
ALC668_FIXUP_DELL_MIC_NO_PRESENCE,
ALC668_FIXUP_HEADSET_MODE,
ALC662_FIXUP_BASS_CHMAP,
+ ALC662_FIXUP_BASS_1A,
+ ALC662_FIXUP_BASS_1A_CHMAP,
};
static const struct hda_fixup alc662_fixups[] = {
.chained = true,
.chain_id = ALC662_FIXUP_ASUS_MODE4
},
+ [ALC662_FIXUP_BASS_1A] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ {0x1a, 0x80106111}, /* bass speaker */
+ {}
+ },
+ },
+ [ALC662_FIXUP_BASS_1A_CHMAP] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc662_fixup_bass_chmap,
+ .chained = true,
+ .chain_id = ALC662_FIXUP_BASS_1A,
+ },
};
static const struct snd_pci_quirk alc662_fixup_tbl[] = {
SND_PCI_QUIRK(0x1025, 0x038b, "Acer Aspire 8943G", ALC662_FIXUP_ASPIRE),
SND_PCI_QUIRK(0x1028, 0x05d8, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x05db, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1028, 0x0625, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0626, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800),
+ SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_BASS_1A_CHMAP),
SND_PCI_QUIRK(0x1043, 0x1477, "ASUS N56VZ", ALC662_FIXUP_BASS_CHMAP),
SND_PCI_QUIRK(0x1043, 0x1bf3, "ASUS N76VZ", ALC662_FIXUP_BASS_CHMAP),
SND_PCI_QUIRK(0x1043, 0x8469, "ASUS mobo", ALC662_FIXUP_NO_JACK_DETECT),
/* Private data for AB8500 device-driver */
struct ab8500_codec_drvdata {
- struct regmap *regmap;
-
/* Sidetone */
long *sid_fir_values;
enum sid_state sid_status;
*/
/* Read a register from the audio-bank of AB8500 */
-static int ab8500_codec_read_reg(void *context, unsigned int reg,
- unsigned int *value)
+static unsigned int ab8500_codec_read_reg(struct snd_soc_codec *codec,
+ unsigned int reg)
{
- struct device *dev = context;
int status;
+ unsigned int value = 0;
u8 value8;
- status = abx500_get_register_interruptible(dev, AB8500_AUDIO,
- reg, &value8);
- *value = (unsigned int)value8;
+ status = abx500_get_register_interruptible(codec->dev, AB8500_AUDIO,
+ reg, &value8);
+ if (status < 0) {
+ dev_err(codec->dev,
+ "%s: ERROR: Register (0x%02x:0x%02x) read failed (%d).\n",
+ __func__, (u8)AB8500_AUDIO, (u8)reg, status);
+ } else {
+ dev_dbg(codec->dev,
+ "%s: Read 0x%02x from register 0x%02x:0x%02x\n",
+ __func__, value8, (u8)AB8500_AUDIO, (u8)reg);
+ value = (unsigned int)value8;
+ }
- return status;
+ return value;
}
/* Write to a register in the audio-bank of AB8500 */
-static int ab8500_codec_write_reg(void *context, unsigned int reg,
- unsigned int value)
+static int ab8500_codec_write_reg(struct snd_soc_codec *codec,
+ unsigned int reg, unsigned int value)
{
- struct device *dev = context;
+ int status;
- return abx500_set_register_interruptible(dev, AB8500_AUDIO,
- reg, value);
-}
+ status = abx500_set_register_interruptible(codec->dev, AB8500_AUDIO,
+ reg, value);
+ if (status < 0)
+ dev_err(codec->dev,
+ "%s: ERROR: Register (%02x:%02x) write failed (%d).\n",
+ __func__, (u8)AB8500_AUDIO, (u8)reg, status);
+ else
+ dev_dbg(codec->dev,
+ "%s: Wrote 0x%02x into register %02x:%02x\n",
+ __func__, (u8)value, (u8)AB8500_AUDIO, (u8)reg);
-static const struct regmap_config ab8500_codec_regmap = {
- .reg_read = ab8500_codec_read_reg,
- .reg_write = ab8500_codec_write_reg,
-};
+ return status;
+}
/*
* Controls - DAPM
dev_dbg(dev, "%s: Enter.\n", __func__);
- snd_soc_codec_set_cache_io(codec, 0, 0, SND_SOC_REGMAP);
-
/* Setup AB8500 according to board-settings */
pdata = dev_get_platdata(dev->parent);
- codec->control_data = drvdata->regmap;
-
if (np) {
if (!pdata)
pdata = devm_kzalloc(dev,
static struct snd_soc_codec_driver ab8500_codec_driver = {
.probe = ab8500_codec_probe,
+ .read = ab8500_codec_read_reg,
+ .write = ab8500_codec_write_reg,
+ .reg_word_size = sizeof(u8),
.controls = ab8500_ctrls,
.num_controls = ARRAY_SIZE(ab8500_ctrls),
.dapm_widgets = ab8500_dapm_widgets,
drvdata->anc_status = ANC_UNCONFIGURED;
dev_set_drvdata(&pdev->dev, drvdata);
- drvdata->regmap = devm_regmap_init(&pdev->dev, NULL, &pdev->dev,
- &ab8500_codec_regmap);
- if (IS_ERR(drvdata->regmap)) {
- status = PTR_ERR(drvdata->regmap);
- dev_err(&pdev->dev, "%s: Failed to allocate regmap: %d\n",
- __func__, status);
- return status;
- }
-
dev_dbg(&pdev->dev, "%s: Register codec.\n", __func__);
status = snd_soc_register_codec(&pdev->dev, &ab8500_codec_driver,
ab8500_codec_dai,
/* Clear any pending completions */
try_wait_for_completion(&fll->ok);
+ regmap_update_bits(arizona->regmap, fll->base + 1,
+ ARIZONA_FLL1_FREERUN, 0);
regmap_update_bits(arizona->regmap, fll->base + 1,
ARIZONA_FLL1_ENA, ARIZONA_FLL1_ENA);
if (use_sync)
struct arizona *arizona = fll->arizona;
bool change;
+ regmap_update_bits(arizona->regmap, fll->base + 1,
+ ARIZONA_FLL1_FREERUN, ARIZONA_FLL1_FREERUN);
regmap_update_bits_check(arizona->regmap, fll->base + 1,
ARIZONA_FLL1_ENA, 0, &change);
regmap_update_bits(arizona->regmap, fll->base + 0x11,
struct arizona_fll fll[2];
};
+static const struct reg_default wm5110_sysclk_revd_patch[] = {
+ { 0x3093, 0x1001 },
+ { 0x30E3, 0x1301 },
+ { 0x3133, 0x1201 },
+ { 0x3183, 0x1501 },
+ { 0x31D3, 0x1401 },
+};
+
+static int wm5110_sysclk_ev(struct snd_soc_dapm_widget *w,
+ struct snd_kcontrol *kcontrol, int event)
+{
+ struct snd_soc_codec *codec = w->codec;
+ struct arizona *arizona = dev_get_drvdata(codec->dev->parent);
+ struct regmap *regmap = codec->control_data;
+ const struct reg_default *patch = NULL;
+ int i, patch_size;
+
+ switch (arizona->rev) {
+ case 3:
+ patch = wm5110_sysclk_revd_patch;
+ patch_size = ARRAY_SIZE(wm5110_sysclk_revd_patch);
+ break;
+ default:
+ return 0;
+ }
+
+ switch (event) {
+ case SND_SOC_DAPM_POST_PMU:
+ if (patch)
+ for (i = 0; i < patch_size; i++)
+ regmap_write(regmap, patch[i].reg,
+ patch[i].def);
+ break;
+
+ default:
+ break;
+ }
+
+ return 0;
+}
+
static DECLARE_TLV_DB_SCALE(ana_tlv, 0, 100, 0);
static DECLARE_TLV_DB_SCALE(eq_tlv, -1200, 100, 0);
static DECLARE_TLV_DB_SCALE(digital_tlv, -6400, 50, 0);
static const struct snd_soc_dapm_widget wm5110_dapm_widgets[] = {
SND_SOC_DAPM_SUPPLY("SYSCLK", ARIZONA_SYSTEM_CLOCK_1, ARIZONA_SYSCLK_ENA_SHIFT,
- 0, NULL, 0),
+ 0, wm5110_sysclk_ev, SND_SOC_DAPM_POST_PMU),
SND_SOC_DAPM_SUPPLY("ASYNCCLK", ARIZONA_ASYNC_CLOCK_1,
ARIZONA_ASYNC_CLK_ENA_SHIFT, 0, NULL, 0),
SND_SOC_DAPM_SUPPLY("OPCLK", ARIZONA_OUTPUT_SYSTEM_CLOCK,
return;
}
+ dma_async_issue_pending(dma->chan);
}
-
- dma_async_issue_pending(dma->chan);
}
int rsnd_dma_available(struct rsnd_dma *dma)
struct rsnd_mod *mod,
struct rsnd_dai_stream *io)
{
- struct rsnd_priv *priv = rsnd_mod_to_priv(mod);
- struct device *dev = rsnd_priv_to_dev(priv);
-
- if (!mod) {
- dev_err(dev, "NULL mod\n");
+ if (!mod)
return -EIO;
- }
if (!list_empty(&mod->list)) {
+ struct rsnd_priv *priv = rsnd_mod_to_priv(mod);
+ struct device *dev = rsnd_priv_to_dev(priv);
+
dev_err(dev, "%s%d is not empty\n",
rsnd_mod_name(mod),
rsnd_mod_id(mod));
return 0;
id = rsnd_mod_id(mod);
- if (id < 0 || id > ARRAY_SIZE(routes))
+ if (id < 0 || id >= ARRAY_SIZE(routes))
return -EIO;
/*
int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len)
{
- return kvm_write_guest_page(kvm, gfn, (const void *) empty_zero_page,
- offset, len);
+ const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0)));
+
+ return kvm_write_guest_page(kvm, gfn, zero_page, offset, len);
}
EXPORT_SYMBOL_GPL(kvm_clear_guest_page);
projects / linux-drm-fsl-dcu.git / commitdiff