From 2e5aa86609ec1cf37bcc204fd7ba6c24c2f49fec Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Tue, 23 Jul 2013 17:38:38 -0400 Subject: lsm: split the xfrm_state_alloc_security() hook implementation The xfrm_state_alloc_security() LSM hook implementation is really a multiplexed hook with two different behaviors depending on the arguments passed to it by the caller. This patch splits the LSM hook implementation into two new hook implementations, which match the LSM hooks in the rest of the kernel: * xfrm_state_alloc * xfrm_state_alloc_acquire Also included in this patch are the necessary changes to the SELinux code; no other LSMs are affected. Signed-off-by: Paul Moore Signed-off-by: Eric Paris --- include/linux/security.h | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 4686491852a7..e5a5e8a41e55 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1039,17 +1039,25 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * @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. @@ -1651,9 +1659,11 @@ struct security_operations { 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); -- cgit v1.2.3 From a5b4bd2874d9032b42db8cc4880058576c561b06 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 24 Sep 2013 10:35:14 +0100 Subject: KEYS: Use bool in make_key_ref() and is_key_possessed() Make make_key_ref() take a bool possession parameter and make is_key_possessed() return a bool. Signed-off-by: David Howells --- include/linux/key.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/key.h b/include/linux/key.h index 4dfde1161c5e..51bce2950de4 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -99,7 +99,7 @@ struct keyring_name; 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); } @@ -109,7 +109,7 @@ static inline struct key *key_ref_to_ptr(const key_ref_t key_ref) 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; } -- cgit v1.2.3 From 16feef4340172b7dbb9cba60850e78fa6388adf1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 24 Sep 2013 10:35:15 +0100 Subject: KEYS: Consolidate the concept of an 'index key' for key access Consolidate the concept of an 'index key' for accessing keys. The index key is the search term needed to find a key directly - basically the key type and the key description. We can add to that the description length. This will be useful when turning a keyring into an associative array rather than just a pointer block. Signed-off-by: David Howells --- include/linux/key.h | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/key.h b/include/linux/key.h index 51bce2950de4..d573e820a23d 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -82,6 +82,12 @@ struct key_owner; 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 @@ -129,7 +135,6 @@ struct key { 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 */ @@ -163,12 +168,18 @@ struct key { #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 */ - /* 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 -- cgit v1.2.3 From 4bdf0bc300314141e5475e145acb8b5ad846f00d Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 24 Sep 2013 10:35:15 +0100 Subject: KEYS: Introduce a search context structure Search functions pass around a bunch of arguments, each of which gets copied with each call. Introduce a search context structure to hold these. Whilst we're at it, create a search flag that indicates whether the search should be directly to the description or whether it should iterate through all keys looking for a non-description match. This will be useful when keyrings use a generic data struct with generic routines to manage their content as the search terms can just be passed through to the iterator callback function. Also, for future use, the data to be supplied to the match function is separated from the description pointer in the search context. This makes it clear which is being supplied. Signed-off-by: David Howells --- include/linux/key-type.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/key-type.h b/include/linux/key-type.h index 518a53afb9ea..f58737bcb050 100644 --- a/include/linux/key-type.h +++ b/include/linux/key-type.h @@ -63,6 +63,11 @@ struct key_type { */ 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); -- cgit v1.2.3 From ccc3e6d9c9aea07a0b60b2b0bfc5b05a704b66d5 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 24 Sep 2013 10:35:16 +0100 Subject: KEYS: Define a __key_get() wrapper to use rather than atomic_inc() Define a __key_get() wrapper to use rather than atomic_inc() on the key usage count as this makes it easier to hook in refcount error debugging. Signed-off-by: David Howells --- include/linux/key.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/key.h b/include/linux/key.h index d573e820a23d..ef596c7af585 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -219,13 +219,17 @@ 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)); -- cgit v1.2.3 From 3cb989501c2688cacbb7dc4b0d353faf838f53a1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 24 Sep 2013 10:35:17 +0100 Subject: Add a generic associative array implementation. Add a generic associative array implementation that can be used as the container for keyrings, thereby massively increasing the capacity available whilst also speeding up searching in keyrings that contain a lot of keys. This may also be useful in FS-Cache for tracking cookies. Documentation is added into Documentation/associative_array.txt Some of the properties of the implementation are: (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 two least significant bits. (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 are labelled as being one of two types (the type is a bool value). This information is stored in the array, but has no consequence to the array itself or its algorithms. (4) Objects require index keys to locate them within the array. (5) Index keys must be unique. Inserting an object with the same key as one already in the array will replace the old object. (6) Index keys can be of any length and can be of different lengths. (7) Index keys should encode the length early on, before any variation due to length is seen. (8) Index keys can include a hash to scatter objects throughout the array. (9) The array can iterated over. The objects will not necessarily come out in key order. (10) The array can be iterated 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. (11) Objects in the array can be looked up by means of their index key. (12) 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. 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. Signed-off-by: David Howells --- include/linux/assoc_array.h | 92 ++++++++++++++++++++ include/linux/assoc_array_priv.h | 182 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 274 insertions(+) create mode 100644 include/linux/assoc_array.h create mode 100644 include/linux/assoc_array_priv.h (limited to 'include/linux') diff --git a/include/linux/assoc_array.h b/include/linux/assoc_array.h new file mode 100644 index 000000000000..9a193b84238a --- /dev/null +++ b/include/linux/assoc_array.h @@ -0,0 +1,92 @@ +/* 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 + +#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 */ diff --git a/include/linux/assoc_array_priv.h b/include/linux/assoc_array_priv.h new file mode 100644 index 000000000000..711275e6681c --- /dev/null +++ b/include/linux/assoc_array_priv.h @@ -0,0 +1,182 @@ +/* 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 + +#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 */ -- cgit v1.2.3 From b2a4df200d570b2c33a57e1ebfa5896e4bc81b69 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 24 Sep 2013 10:35:18 +0100 Subject: KEYS: Expand the capacity of a keyring Expand the capacity of a keyring to be able to hold a lot more keys by using the previously added associative array implementation. Currently the maximum capacity is: (PAGE_SIZE - sizeof(header)) / sizeof(struct key *) which, on a 64-bit system, is a little more 500. However, since this is being used for the NFS uid mapper, we need more than that. The new implementation gives us effectively unlimited capacity. With some alterations, the keyutils testsuite runs successfully to completion after this patch is applied. The alterations are because (a) keyrings that are simply added to no longer appear ordered and (b) some of the errors have changed a bit. Signed-off-by: David Howells --- include/linux/key.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/key.h b/include/linux/key.h index ef596c7af585..2417f789d29b 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -22,6 +22,7 @@ #include #include #include +#include #ifdef __KERNEL__ #include @@ -196,11 +197,13 @@ struct key { * 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; + } payload; + struct assoc_array keys; + }; }; extern struct key *key_alloc(struct key_type *type, -- cgit v1.2.3 From ab3c3587f8cda9083209a61dbe3a4407d3cada10 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 24 Sep 2013 10:35:18 +0100 Subject: KEYS: Implement a big key type that can save to tmpfs Implement a big key type that can save its contents to tmpfs and thus swapspace when memory is tight. This is useful for Kerberos ticket caches. Signed-off-by: David Howells Tested-by: Simo Sorce --- include/linux/key.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/key.h b/include/linux/key.h index 2417f789d29b..010dbb618aca 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -201,6 +201,7 @@ struct key { unsigned long value; void __rcu *rcudata; void *data; + void *data2[2]; } payload; struct assoc_array keys; }; -- cgit v1.2.3 From f36f8c75ae2e7d4da34f4c908cebdb4aa42c977e Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 24 Sep 2013 10:35:19 +0100 Subject: KEYS: Add per-user_namespace registers for persistent per-UID kerberos caches Add support for per-user_namespace registers of persistent per-UID kerberos caches held within the kernel. This allows the kerberos cache to be retained beyond the life of all a user's processes so that the user's cron jobs can work. The kerberos cache is envisioned as a keyring/key tree looking something like: struct user_namespace \___ .krb_cache keyring - The register \___ _krb.0 keyring - Root's Kerberos cache \___ _krb.5000 keyring - User 5000's Kerberos cache \___ _krb.5001 keyring - User 5001's Kerberos cache \___ tkt785 big_key - A ccache blob \___ tkt12345 big_key - Another ccache blob Or possibly: struct user_namespace \___ .krb_cache keyring - The register \___ _krb.0 keyring - Root's Kerberos cache \___ _krb.5000 keyring - User 5000's Kerberos cache \___ _krb.5001 keyring - User 5001's Kerberos cache \___ tkt785 keyring - A ccache \___ krbtgt/REDHAT.COM@REDHAT.COM big_key \___ http/REDHAT.COM@REDHAT.COM user \___ afs/REDHAT.COM@REDHAT.COM user \___ nfs/REDHAT.COM@REDHAT.COM user \___ krbtgt/KERNEL.ORG@KERNEL.ORG big_key \___ http/KERNEL.ORG@KERNEL.ORG big_key What goes into a particular Kerberos cache is entirely up to userspace. Kernel support is limited to giving you the Kerberos cache keyring that you want. The user asks for their Kerberos cache by: krb_cache = keyctl_get_krbcache(uid, dest_keyring); The uid is -1 or the user's own UID for the user's own cache or the uid of some other user's cache (requires CAP_SETUID). This permits rpc.gssd or whatever to mess with the cache. The cache returned is a keyring named "_krb." that the possessor can read, search, clear, invalidate, unlink from and add links to. Active LSMs get a chance to rule on whether the caller is permitted to make a link. Each uid's cache keyring is created when it first accessed and is given a timeout that is extended each time this function is called so that the keyring goes away after a while. The timeout is configurable by sysctl but defaults to three days. Each user_namespace struct gets a lazily-created keyring that serves as the register. The cache keyrings are added to it. This means that standard key search and garbage collection facilities are available. The user_namespace struct's register goes away when it does and anything left in it is then automatically gc'd. Signed-off-by: David Howells Tested-by: Simo Sorce cc: Serge E. Hallyn cc: Eric W. Biederman --- include/linux/user_namespace.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 4db29859464f..4836ba3c1cd8 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -27,6 +27,12 @@ struct user_namespace { 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; -- cgit v1.2.3 From 008643b86c5f33c115c84ccdda1725cac3ad50ad Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 30 Aug 2013 16:07:37 +0100 Subject: KEYS: Add a 'trusted' flag and a 'trusted only' flag Add KEY_FLAG_TRUSTED to indicate that a key either comes from a trusted source or had a cryptographic signature chain that led back to a trusted key the kernel already possessed. Add KEY_FLAGS_TRUSTED_ONLY to indicate that a keyring will only accept links to keys marked with KEY_FLAGS_TRUSTED. Signed-off-by: David Howells Reviewed-by: Kees Cook --- include/linux/key-type.h | 1 + include/linux/key.h | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/key-type.h b/include/linux/key-type.h index f58737bcb050..a74c3a84dfdd 100644 --- a/include/linux/key-type.h +++ b/include/linux/key-type.h @@ -45,6 +45,7 @@ struct key_preparsed_payload { 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, diff --git a/include/linux/key.h b/include/linux/key.h index 010dbb618aca..80d677483e31 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -168,6 +168,8 @@ struct 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 key type and key description string * - the desc is used to match a key against search criteria @@ -218,6 +220,7 @@ 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); -- cgit v1.2.3 From 68126702b419fd26ef4946e314bb3a1f57d3a53f Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Thu, 24 Oct 2013 10:07:42 +0900 Subject: slab: overloading the RCU head over the LRU for RCU free With build-time size checking, we can overload the RCU head over the LRU of struct page to free pages of a slab in rcu context. This really help to implement to overload the struct slab over the struct page and this eventually reduce memory usage and cache footprint of the SLAB. Acked-by: Andi Kleen Acked-by: Christoph Lameter Signed-off-by: Joonsoo Kim Signed-off-by: Pekka Enberg --- include/linux/mm_types.h | 3 +++ include/linux/slab.h | 9 ++++++++- 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index faf4b7c1ad12..959cb369b197 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -130,6 +130,9 @@ struct page { 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 + */ }; /* Remainder is not double word aligned */ diff --git a/include/linux/slab.h b/include/linux/slab.h index 6c5cc0ea8713..caaad51fee1f 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -51,7 +51,14 @@ * } * 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 */ -- cgit v1.2.3 From 8456a648cf44f14365f1f44de90a3da2526a4776 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Thu, 24 Oct 2013 10:07:49 +0900 Subject: slab: use struct page for slab management Now, there are a few field in struct slab, so we can overload these over struct page. This will save some memory and reduce cache footprint. After this change, slabp_cache and slab_size no longer related to a struct slab, so rename them as freelist_cache and freelist_size. These changes are just mechanical ones and there is no functional change. Acked-by: Andi Kleen Acked-by: Christoph Lameter Signed-off-by: Joonsoo Kim Signed-off-by: Pekka Enberg --- include/linux/mm_types.h | 21 +++++++++++++-------- include/linux/slab_def.h | 4 ++-- 2 files changed, 15 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 959cb369b197..95bf0c5a7eb9 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -42,18 +42,22 @@ struct page { /* 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 @@ -109,6 +113,7 @@ struct page { }; atomic_t _count; /* Usage count, see below. */ }; + unsigned int active; /* SLAB */ }; }; diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index cd401580bdd3..ca82e8ff89fa 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -41,8 +41,8 @@ struct kmem_cache { 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); -- cgit v1.2.3 From adfedd9a32e4e3490c0060576fd824881572b72a Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Wed, 16 Oct 2013 13:29:02 +0530 Subject: dmaengine: use DMA_COMPLETE for dma completion status the DMA_SUCCESS is a misnomer as dmaengine indicates the transfer is complete and gives no guarantee of the transfer success. Hence we should use DMA_COMPLTE instead of DMA_SUCCESS Acked-by: Dan Williams Acked-by: Linus Walleij Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 0bc727534108..120e64c96478 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -45,13 +45,13 @@ static inline int dma_submit_error(dma_cookie_t cookie) /** * enum dma_status - DMA transaction status - * @DMA_SUCCESS: transaction completed successfully + * @DMA_COMPLETE: transaction completed * @DMA_IN_PROGRESS: transaction not yet processed * @DMA_PAUSED: transaction is paused * @DMA_ERROR: transaction failed */ enum dma_status { - DMA_SUCCESS, + DMA_SUCCESS = 0, DMA_COMPLETE = 0, DMA_IN_PROGRESS, DMA_PAUSED, DMA_ERROR, @@ -979,10 +979,10 @@ static inline enum dma_status dma_async_is_complete(dma_cookie_t cookie, { if (last_complete <= last_used) { if ((cookie <= last_complete) || (cookie > last_used)) - return DMA_SUCCESS; + return DMA_COMPLETE; } else { if ((cookie <= last_complete) && (cookie > last_used)) - return DMA_SUCCESS; + return DMA_COMPLETE; } return DMA_IN_PROGRESS; } @@ -1013,11 +1013,11 @@ static inline struct dma_chan *dma_find_channel(enum dma_transaction_type tx_typ } static inline enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie) { - return DMA_SUCCESS; + return DMA_COMPLETE; } static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx) { - return DMA_SUCCESS; + return DMA_COMPLETE; } static inline void dma_issue_pending_all(void) { -- cgit v1.2.3 From 7db5f7274a0b065abdc358be2a44b4a911d75707 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 17 Oct 2013 07:29:57 +0530 Subject: dmaengine: remove unused DMA_SUCCESS after all the users are converted Acked-by: Dan Williams Acked-by: Linus Walleij Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 120e64c96478..4b460a683968 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -51,7 +51,7 @@ static inline int dma_submit_error(dma_cookie_t cookie) * @DMA_ERROR: transaction failed */ enum dma_status { - DMA_SUCCESS = 0, DMA_COMPLETE = 0, + DMA_COMPLETE, DMA_IN_PROGRESS, DMA_PAUSED, DMA_ERROR, -- cgit v1.2.3 From 0b6b098efcddac2bf4e2a895c9b655560bbfcee4 Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Fri, 25 Oct 2013 12:14:15 +0200 Subject: padata: make the sequence counter an atomic_t Using a spinlock to atomically increase a counter sounds wrong -- we've atomic_t for this! Also move 'seq_nr' to a different cache line than 'lock' to reduce cache line trashing. This has the nice side effect of decreasing the size of struct parallel_data from 192 to 128 bytes for a x86-64 build, e.g. occupying only two instead of three cache lines. Those changes results in a 5% performance increase on an IPsec test run using pcrypt. Btw. the seq_lock spinlock was never explicitly initialized -- one more reason to get rid of it. Signed-off-by: Mathias Krause Acked-by: Steffen Klassert Signed-off-by: Herbert Xu --- include/linux/padata.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/padata.h b/include/linux/padata.h index 86292beebfe2..438694650471 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -129,10 +129,9 @@ struct parallel_data { struct padata_serial_queue __percpu *squeue; atomic_t reorder_objects; atomic_t refcnt; + atomic_t seq_nr; struct padata_cpumask cpumask; spinlock_t lock ____cacheline_aligned; - spinlock_t seq_lock; - unsigned int seq_nr; unsigned int processed; struct timer_list timer; }; -- cgit v1.2.3 From db60d8da8f643586c95f8fc3e383954f8c57f1f3 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Wed, 30 Oct 2013 18:22:30 +0530 Subject: dmanengine: fix edma driver to not define DMA_COMPLETE edma header defines DMA_COMPLETE, this causes issues as commit adfedd9a32e4 move DMA_SUCCESS to DMA_COMPLETE. edma should properly namespace its defines and needs a future fix Reported-by: Olof Johansson Signed-off-by: Vinod Koul --- include/linux/platform_data/edma.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/edma.h b/include/linux/platform_data/edma.h index 179fb91bb5f2..f50821cb64be 100644 --- a/include/linux/platform_data/edma.h +++ b/include/linux/platform_data/edma.h @@ -67,10 +67,10 @@ struct edmacc_param { #define ITCCHEN BIT(23) /*ch_status paramater of callback function possible values*/ -#define DMA_COMPLETE 1 -#define DMA_CC_ERROR 2 -#define DMA_TC1_ERROR 3 -#define DMA_TC2_ERROR 4 +#define EDMA_DMA_COMPLETE 1 +#define EDMA_DMA_CC_ERROR 2 +#define EDMA_DMA_TC1_ERROR 3 +#define EDMA_DMA_TC2_ERROR 4 enum address_mode { INCR = 0, -- cgit v1.2.3 From ec7f68e07bf10198717b7824c78201b46bbf1956 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Wed, 30 Oct 2013 22:48:00 +0000 Subject: iio: hid_Sensors: fix crash during trigger unregister We can't store the trigger instance created by iio_trigger_alloc, in trig field of iio_device structure. This needs to be stored in the driver private data. Othewise it can result in crash during module unload. Hence created a trig_ptr in the common data structure for each HID sensor IIO driver and storing here. Signed-off-by: Srinivas Pandruvada Signed-off-by: Jonathan Cameron --- include/linux/hid-sensor-hub.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h index a265af294ea4..206a2af6b62b 100644 --- a/include/linux/hid-sensor-hub.h +++ b/include/linux/hid-sensor-hub.h @@ -21,6 +21,8 @@ #include #include +#include +#include /** * struct hid_sensor_hub_attribute_info - Attribute info @@ -184,6 +186,7 @@ struct hid_sensor_common { struct platform_device *pdev; unsigned usage_id; bool data_ready; + struct iio_trigger *trigger; struct hid_sensor_hub_attribute_info poll; struct hid_sensor_hub_attribute_info report_state; struct hid_sensor_hub_attribute_info power_state; -- cgit v1.2.3 From b0fed40214ce79ef70d97584ebdf13f89786da0e Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 22 May 2013 12:54:49 -0400 Subject: audit: implement generic feature setting and retrieving The audit_status structure was not designed with extensibility in mind. Define a new AUDIT_SET_FEATURE message type which takes a new structure of bits where things can be enabled/disabled/locked one at a time. This structure should be able to grow in the future while maintaining forward and backward compatibility (based loosly on the ideas from capabilities and prctl) This does not actually add any features, but is just infrastructure to allow new on/off types of audit system features. Signed-off-by: Eric Paris Signed-off-by: Richard Guy Briggs Signed-off-by: Eric Paris --- include/linux/audit.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 729a4d165bcc..7b31bec9bccb 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -73,6 +73,8 @@ struct audit_field { 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); -- cgit v1.2.3 From d9cfea91e97d5d19f9d69beaa844f5fe56a6adc6 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Wed, 30 Oct 2013 17:56:13 -0400 Subject: audit: move audit_aux_data_execve contents into audit_context union audit_bprm() was being called to add an AUDIT_EXECVE record to the audit context every time search_binary_handler() was recursively called. Only one reference is necessary, so just update it. Move the the contents of audit_aux_data_execve into the union in audit_context, removing dependence on a kmalloc along the way. Reported-by: Oleg Nesterov Cc: Eric Paris Signed-off-by: Richard Guy Briggs Signed-off-by: Eric Paris --- include/linux/audit.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 7b31bec9bccb..08b38bf13eb9 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -209,7 +209,7 @@ static inline int audit_get_sessionid(struct task_struct *tsk) 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); @@ -241,7 +241,7 @@ static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid static inline int audit_bprm(struct linux_binprm *bprm) { if (unlikely(!audit_dummy_context())) - return __audit_bprm(bprm); + __audit_bprm(bprm); return 0; } static inline int audit_socketcall(int nargs, unsigned long *args) -- cgit v1.2.3 From 9410d228a4cf434305306746bb799fb7acdd8648 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Wed, 30 Oct 2013 18:05:24 -0400 Subject: audit: call audit_bprm() only once to add AUDIT_EXECVE information Move the audit_bprm() call from search_binary_handler() to exec_binprm(). This allows us to get rid of the mm member of struct audit_aux_data_execve since bprm->mm will equal current->mm. This also mitigates the issue that ->argc could be modified by the load_binary() call in search_binary_handler(). audit_bprm() was being called to add an AUDIT_EXECVE record to the audit context every time search_binary_handler() was recursively called. Only one reference is necessary. Reported-by: Oleg Nesterov Cc: Eric Paris Signed-off-by: Richard Guy Briggs Signed-off-by: Eric Paris --- This patch is against 3.11, but was developed on Oleg's post-3.11 patches that introduce exec_binprm(). --- include/linux/audit.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 08b38bf13eb9..a40641954c29 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -238,11 +238,10 @@ static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid 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())) __audit_bprm(bprm); - return 0; } static inline int audit_socketcall(int nargs, unsigned long *args) { @@ -369,10 +368,8 @@ static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) 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; -- cgit v1.2.3 From a941f8360f200d6849b292f9dc50250bca531c0e Mon Sep 17 00:00:00 2001 From: Zhi Yong Wu Date: Fri, 8 Nov 2013 20:47:36 +0800 Subject: mm, slub: fix the typo in include/linux/slub_def.h Acked-by: Christoph Lameter Signed-off-by: Zhi Yong Wu Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 027276fa8713..2dc4e78fc234 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -17,7 +17,7 @@ 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 */ -- cgit v1.2.3 From d38a8c622a1b382336c3e152c6caf4e11d1f1b2a Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 18 Oct 2013 19:35:23 +0200 Subject: dmaengine: prepare for generic 'unmap' data Add a hook for a common dma unmap implementation to enable removal of the per driver custom unmap code. (A reworked version of Bartlomiej Zolnierkiewicz's patches to remove the custom callbacks and the size increase of dma_async_tx_descriptor for drivers that don't care about raid). Cc: Vinod Koul Cc: Tomasz Figa Cc: Dave Jiang [bzolnier: prepare pl330 driver for adding missing unmap while at it] Signed-off-by: Bartlomiej Zolnierkiewicz Signed-off-by: Kyungmin Park Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 0bc727534108..9070050fbcd8 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -413,6 +413,17 @@ void dma_chan_cleanup(struct kref *kref); typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param); typedef void (*dma_async_tx_callback)(void *dma_async_param); + +struct dmaengine_unmap_data { + u8 to_cnt; + u8 from_cnt; + u8 bidi_cnt; + struct device *dev; + struct kref kref; + size_t len; + dma_addr_t addr[0]; +}; + /** * struct dma_async_tx_descriptor - async transaction descriptor * ---dma generic offload fields--- @@ -438,6 +449,7 @@ struct dma_async_tx_descriptor { dma_cookie_t (*tx_submit)(struct dma_async_tx_descriptor *tx); dma_async_tx_callback callback; void *callback_param; + struct dmaengine_unmap_data *unmap; #ifdef CONFIG_ASYNC_TX_ENABLE_CHANNEL_SWITCH struct dma_async_tx_descriptor *next; struct dma_async_tx_descriptor *parent; @@ -445,6 +457,20 @@ struct dma_async_tx_descriptor { #endif }; +static inline void dma_set_unmap(struct dma_async_tx_descriptor *tx, + struct dmaengine_unmap_data *unmap) +{ + kref_get(&unmap->kref); + tx->unmap = unmap; +} + +static inline void dma_descriptor_unmap(struct dma_async_tx_descriptor *tx) +{ + if (tx->unmap) { + tx->unmap = NULL; + } +} + #ifndef CONFIG_ASYNC_TX_ENABLE_CHANNEL_SWITCH static inline void txd_lock(struct dma_async_tx_descriptor *txd) { -- cgit v1.2.3 From 45c463ae924c62af4aa64ded1ca831f334a1db65 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 18 Oct 2013 19:35:24 +0200 Subject: dmaengine: reference counted unmap data Hang a common 'unmap' object off of dma descriptors for the purpose of providing a unified unmapping interface. The lifetime of a mapping may span multiple descriptors, so these unmap objects are reference counted by related descriptor. Cc: Vinod Koul Cc: Tomasz Figa Cc: Dave Jiang [bzolnier: fix IS_ENABLED() check] [bzolnier: fix release ordering in dmaengine_destroy_unmap_pool()] [bzolnier: fix check for success in dmaengine_init_unmap_pool()] [bzolnier: use mempool_free() instead of kmem_cache_free()] [bzolnier: add missing unmap->len initializations] [bzolnier: add __init tag to dmaengine_init_unmap_pool()] Signed-off-by: Bartlomiej Zolnierkiewicz Signed-off-by: Kyungmin Park [djbw: move DMAENGINE=n support to this patch for async_tx] Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 9070050fbcd8..2fe855a7cab1 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -464,9 +464,12 @@ static inline void dma_set_unmap(struct dma_async_tx_descriptor *tx, tx->unmap = unmap; } +void dmaengine_unmap_put(struct dmaengine_unmap_data *unmap); + static inline void dma_descriptor_unmap(struct dma_async_tx_descriptor *tx) { if (tx->unmap) { + dmaengine_unmap_put(tx->unmap); tx->unmap = NULL; } } -- cgit v1.2.3 From 82e06c811163c4d853ed335d56c3378088bc89cc Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Thu, 14 Nov 2013 15:16:16 +1100 Subject: wait: add wait_event_cmd() Add a new API wait_event_cmd(). It's a variant of wait_even() with two commands executed. One is executed before sleep, another after sleep. Modified to match use wait.h approach based on suggestion by Peter Zijlstra - neilb Signed-off-by: Shaohua Li Signed-off-by: NeilBrown --- include/linux/wait.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 61939ba30aa0..eaa00b10abaa 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -278,6 +278,31 @@ do { \ __ret; \ }) +#define __wait_event_cmd(wq, condition, cmd1, cmd2) \ + (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ + cmd1; schedule(); cmd2) + +/** + * wait_event_cmd - sleep until a condition gets true + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * cmd1: the command will be executed before sleep + * cmd2: the command will be executed after sleep + * + * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the + * @condition evaluates to true. The @condition is checked each time + * the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + */ +#define wait_event_cmd(wq, condition, cmd1, cmd2) \ +do { \ + if (condition) \ + break; \ + __wait_event_cmd(wq, condition, cmd1, cmd2); \ +} while (0) + #define __wait_event_interruptible(wq, condition) \ ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule()) -- cgit v1.2.3 From f7625980f5820edd1a73536e1a03bcbc1f889fec Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 14 Nov 2013 11:28:18 -0700 Subject: PCI: Fix whitespace, capitalization, and spelling errors Fix whitespace, capitalization, and spelling errors. No functional change. I know "busses" is not an error, but "buses" was more common, so I used it consistently. Signed-off-by: Marta Rybczynska (pci_reset_bridge_secondary_bus()) Signed-off-by: Bjorn Helgaas Acked-by: Rafael J. Wysocki --- include/linux/msi.h | 10 ++++----- include/linux/pci.h | 55 ++++++++++++++++++++++----------------------- include/linux/pci_hotplug.h | 5 ++--- include/linux/pcieport_if.h | 2 +- 4 files changed, 35 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 87cce50bd121..009b02481436 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -26,11 +26,11 @@ struct msi_desc { 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 */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 835ec7bf6c05..1084a15175e0 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -32,7 +32,6 @@ #include #include -/* Include the ID list */ #include /* @@ -42,9 +41,10 @@ * * 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 */ @@ -153,10 +153,10 @@ enum pcie_reset_state { /* 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 }; @@ -259,13 +259,13 @@ struct pci_dev { 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 @@ -300,7 +300,7 @@ struct pci_dev { 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 */ @@ -317,7 +317,7 @@ struct pci_dev { 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; @@ -326,7 +326,7 @@ struct pci_dev { 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; @@ -371,7 +371,6 @@ static inline struct pci_dev *pci_physfn(struct pci_dev *dev) if (dev->is_virtfn) dev = dev->physfn; #endif - return dev; } @@ -456,7 +455,7 @@ struct pci_bus { 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 */ @@ -468,7 +467,7 @@ struct pci_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. @@ -510,7 +509,7 @@ static inline bool pci_dev_msi_enabled(struct pci_dev *pci_dev) { return false; #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) { @@ -561,11 +560,12 @@ struct pci_dynids { 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; @@ -609,7 +609,6 @@ struct pci_error_handlers { void (*resume)(struct pci_dev *dev); }; -/* ---------------------------------------------------------------- */ struct module; struct pci_driver { @@ -713,10 +712,10 @@ extern enum pcie_bus_config_types pcie_bus_config; 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); @@ -724,7 +723,7 @@ void pcibios_add_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 */ @@ -1258,7 +1257,7 @@ void pci_cfg_access_unlock(struct pci_dev *dev); /* * 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 @@ -1672,7 +1671,7 @@ extern u8 pci_cache_line_size; 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(s