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(struct pci_dev *dev); diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 430dd963707b..a2e2f1d17e16 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -39,8 +39,8 @@ * @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. @@ -191,4 +191,3 @@ static inline int pci_get_hp_params(struct pci_dev *dev, void pci_configure_slot(struct pci_dev *dev); #endif - diff --git a/include/linux/pcieport_if.h b/include/linux/pcieport_if.h index 9572669eea97..4f1089f2cc98 100644 --- a/include/linux/pcieport_if.h +++ b/include/linux/pcieport_if.h @@ -23,7 +23,7 @@ #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 */ -- cgit v1.2.3 From 8971646294bda65f8666b60cb2cb3d5e172c99bf Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 18 Oct 2013 19:35:25 +0200 Subject: async_memcpy: convert to dmaengine_unmap_data Use the generic unmap object to unmap dma buffers. Cc: Vinod Koul Cc: Tomasz Figa Cc: Dave Jiang Reported-by: Bartlomiej Zolnierkiewicz [bzolnier: add missing unmap->len initialization] [bzolnier: fix whitespace damage] Signed-off-by: Bartlomiej Zolnierkiewicz Signed-off-by: Kyungmin Park [djbw: add DMA_ENGINE=n support] Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 2fe855a7cab1..3782cdb782a8 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -457,6 +457,7 @@ struct dma_async_tx_descriptor { #endif }; +#ifdef CONFIG_DMA_ENGINE static inline void dma_set_unmap(struct dma_async_tx_descriptor *tx, struct dmaengine_unmap_data *unmap) { @@ -464,7 +465,23 @@ static inline void dma_set_unmap(struct dma_async_tx_descriptor *tx, tx->unmap = unmap; } +struct dmaengine_unmap_data * +dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags); void dmaengine_unmap_put(struct dmaengine_unmap_data *unmap); +#else +static inline void dma_set_unmap(struct dma_async_tx_descriptor *tx, + struct dmaengine_unmap_data *unmap) +{ +} +static inline struct dmaengine_unmap_data * +dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags) +{ + return NULL; +} +static inline void dmaengine_unmap_put(struct dmaengine_unmap_data *unmap) +{ +} +#endif static inline void dma_descriptor_unmap(struct dma_async_tx_descriptor *tx) { -- cgit v1.2.3 From 0776ae7b89782124ddd72eafe0b1e0fdcdabe32e Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 18 Oct 2013 19:35:33 +0200 Subject: dmaengine: remove DMA unmap flags Remove no longer needed DMA unmap flags: - DMA_COMPL_SKIP_SRC_UNMAP - DMA_COMPL_SKIP_DEST_UNMAP - DMA_COMPL_SRC_UNMAP_SINGLE - DMA_COMPL_DEST_UNMAP_SINGLE Cc: Vinod Koul Cc: Tomasz Figa Cc: Dave Jiang Signed-off-by: Bartlomiej Zolnierkiewicz Signed-off-by: Kyungmin Park Acked-by: Jon Mason Acked-by: Mark Brown [djbw: clean up straggling skip unmap flags in ntb] Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 3782cdb782a8..491072cb5ba0 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -171,12 +171,6 @@ struct dma_interleaved_template { * @DMA_CTRL_ACK - if clear, the descriptor cannot be reused until the client * acknowledges receipt, i.e. has has a chance to establish any dependency * chains - * @DMA_COMPL_SKIP_SRC_UNMAP - set to disable dma-unmapping the source buffer(s) - * @DMA_COMPL_SKIP_DEST_UNMAP - set to disable dma-unmapping the destination(s) - * @DMA_COMPL_SRC_UNMAP_SINGLE - set to do the source dma-unmapping as single - * (if not set, do the source dma-unmapping as page) - * @DMA_COMPL_DEST_UNMAP_SINGLE - set to do the destination dma-unmapping as single - * (if not set, do the destination dma-unmapping as page) * @DMA_PREP_PQ_DISABLE_P - prevent generation of P while generating Q * @DMA_PREP_PQ_DISABLE_Q - prevent generation of Q while generating P * @DMA_PREP_CONTINUE - indicate to a driver that it is reusing buffers as @@ -188,14 +182,10 @@ struct dma_interleaved_template { enum dma_ctrl_flags { DMA_PREP_INTERRUPT = (1 << 0), DMA_CTRL_ACK = (1 << 1), - DMA_COMPL_SKIP_SRC_UNMAP = (1 << 2), - DMA_COMPL_SKIP_DEST_UNMAP = (1 << 3), - DMA_COMPL_SRC_UNMAP_SINGLE = (1 << 4), - DMA_COMPL_DEST_UNMAP_SINGLE = (1 << 5), - DMA_PREP_PQ_DISABLE_P = (1 << 6), - DMA_PREP_PQ_DISABLE_Q = (1 << 7), - DMA_PREP_CONTINUE = (1 << 8), - DMA_PREP_FENCE = (1 << 9), + DMA_PREP_PQ_DISABLE_P = (1 << 2), + DMA_PREP_PQ_DISABLE_Q = (1 << 3), + DMA_PREP_CONTINUE = (1 << 4), + DMA_PREP_FENCE = (1 << 5), }; /** -- cgit v1.2.3 From 7b1998116bbb2f3e5dd6cb9a8ee6db479b0b50a9 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 11 Nov 2013 22:41:56 +0100 Subject: ACPI / driver core: Store an ACPI device pointer in struct acpi_dev_node Modify struct acpi_dev_node to contain a pointer to struct acpi_device associated with the given device object (that is, its ACPI companion device) instead of an ACPI handle corresponding to it. Introduce two new macros for manipulating that pointer in a CONFIG_ACPI-safe way, ACPI_COMPANION() and ACPI_COMPANION_SET(), and rework the ACPI_HANDLE() macro to take the above changes into account. Drop the ACPI_HANDLE_SET() macro entirely and rework its users to use ACPI_COMPANION_SET() instead. For some of them who used to pass the result of acpi_get_child() directly to ACPI_HANDLE_SET() introduce a helper routine acpi_preset_companion() doing an equivalent thing. The main motivation for doing this is that there are things represented by struct acpi_device objects that don't have valid ACPI handles (so called fixed ACPI hardware features, such as power and sleep buttons) and we would like to create platform device objects for them and "glue" them to their ACPI companions in the usual way (which currently is impossible due to the lack of valid ACPI handles). However, there are more reasons why it may be useful. First, struct acpi_device pointers allow of much better type checking than void pointers which are ACPI handles, so it should be more difficult to write buggy code using modified struct acpi_dev_node and the new macros. Second, the change should help to reduce (over time) the number of places in which the result of ACPI_HANDLE() is passed to acpi_bus_get_device() in order to obtain a pointer to the struct acpi_device associated with the given "physical" device, because now that pointer is returned by ACPI_COMPANION() directly. Finally, the change should make it easier to write generic code that will build both for CONFIG_ACPI set and unset without adding explicit compiler directives to it. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Tested-by: Mika Westerberg # on Haswell Reviewed-by: Mika Westerberg Reviewed-by: Aaron Lu # for ATA and SDIO part --- include/linux/acpi.h | 15 +++++++++++++++ include/linux/device.h | 12 +++--------- 2 files changed, 18 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index b0972c4ce81c..47369aadb1d1 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -44,6 +44,15 @@ #include #include +static inline acpi_handle acpi_device_handle(struct acpi_device *adev) +{ + return adev ? adev->handle : NULL; +} + +#define ACPI_COMPANION(dev) ((dev)->acpi_node.companion) +#define ACPI_COMPANION_SET(dev, adev) ACPI_COMPANION(dev) = (adev) +#define ACPI_HANDLE(dev) acpi_device_handle(ACPI_COMPANION(dev)) + enum acpi_irq_model_id { ACPI_IRQ_MODEL_PIC = 0, ACPI_IRQ_MODEL_IOAPIC, @@ -401,6 +410,10 @@ static inline bool acpi_driver_match_device(struct device *dev, #define acpi_disabled 1 +#define ACPI_COMPANION(dev) (NULL) +#define ACPI_COMPANION_SET(dev, adev) do { } while (0) +#define ACPI_HANDLE(dev) (NULL) + static inline void acpi_early_init(void) { } static inline int early_acpi_boot_init(void) @@ -469,6 +482,8 @@ static inline bool acpi_driver_match_device(struct device *dev, #endif /* !CONFIG_ACPI */ +#define DEVICE_ACPI_HANDLE(dev) ACPI_HANDLE(dev) + #ifdef CONFIG_ACPI void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state, u32 pm1a_ctrl, u32 pm1b_ctrl)); diff --git a/include/linux/device.h b/include/linux/device.h index b025925df7f7..952b01033c32 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -644,9 +644,11 @@ struct device_dma_parameters { unsigned long segment_boundary_mask; }; +struct acpi_device; + struct acpi_dev_node { #ifdef CONFIG_ACPI - void *handle; + struct acpi_device *companion; #endif }; @@ -790,14 +792,6 @@ static inline struct device *kobj_to_dev(struct kobject *kobj) return container_of(kobj, struct device, kobj); } -#ifdef CONFIG_ACPI -#define ACPI_HANDLE(dev) ((dev)->acpi_node.handle) -#define ACPI_HANDLE_SET(dev, _handle_) (dev)->acpi_node.handle = (_handle_) -#else -#define ACPI_HANDLE(dev) (NULL) -#define ACPI_HANDLE_SET(dev, _handle_) do { } while (0) -#endif - /* Get the wakeup routines, which depend on struct device */ #include -- cgit v1.2.3 From 3a83f992490f8235661b768e53bd5f14915420ac Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 14 Nov 2013 23:17:21 +0100 Subject: ACPI: Eliminate the DEVICE_ACPI_HANDLE() macro Since DEVICE_ACPI_HANDLE() is now literally identical to ACPI_HANDLE(), replace it with the latter everywhere and drop its definition from include/acpi.h. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman --- include/linux/acpi.h | 2 -- include/linux/pci-acpi.h | 4 ++-- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 47369aadb1d1..86a3ba99a38d 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -482,8 +482,6 @@ static inline bool acpi_driver_match_device(struct device *dev, #endif /* !CONFIG_ACPI */ -#define DEVICE_ACPI_HANDLE(dev) ACPI_HANDLE(dev) - #ifdef CONFIG_ACPI void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state, u32 pm1a_ctrl, u32 pm1b_ctrl)); diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index d006f0ca60f4..5a462c4e5009 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -27,7 +27,7 @@ static inline acpi_handle acpi_find_root_bridge_handle(struct pci_dev *pdev) while (!pci_is_root_bus(pbus)) pbus = pbus->parent; - return DEVICE_ACPI_HANDLE(pbus->bridge); + return ACPI_HANDLE(pbus->bridge); } static inline acpi_handle acpi_pci_get_bridge_handle(struct pci_bus *pbus) @@ -39,7 +39,7 @@ static inline acpi_handle acpi_pci_get_bridge_handle(struct pci_bus *pbus) else dev = &pbus->self->dev; - return DEVICE_ACPI_HANDLE(dev); + return ACPI_HANDLE(dev); } void acpi_pci_add_bus(struct pci_bus *bus); -- cgit v1.2.3 From 45c42a7f582cc07259bc78910de8b0b1c94094d5 Mon Sep 17 00:00:00 2001 From: Jarkko Nikula Date: Thu, 14 Nov 2013 14:03:51 +0200 Subject: ACPI: Provide acpi_dev_name accessor for struct acpi_device device name struct acpi_device fields are only available when CONFIG_ACPI is set. We may find use for dev_name(&adev->dev) in generic code that is build also without CONFIG_ACPI is set but currently this requires #ifdef CONFIG_ACPI churn. Provide here an accessor that returns dev_name of embedded struct device dev in struct acpi_device or NULL depending on CONFIG_ACPI setting. Signed-off-by: Jarkko Nikula Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 86a3ba99a38d..d9099b15b472 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -53,6 +53,11 @@ static inline acpi_handle acpi_device_handle(struct acpi_device *adev) #define ACPI_COMPANION_SET(dev, adev) ACPI_COMPANION(dev) = (adev) #define ACPI_HANDLE(dev) acpi_device_handle(ACPI_COMPANION(dev)) +static inline const char *acpi_dev_name(struct acpi_device *adev) +{ + return dev_name(&adev->dev); +} + enum acpi_irq_model_id { ACPI_IRQ_MODEL_PIC = 0, ACPI_IRQ_MODEL_IOAPIC, @@ -414,6 +419,11 @@ static inline bool acpi_driver_match_device(struct device *dev, #define ACPI_COMPANION_SET(dev, adev) do { } while (0) #define ACPI_HANDLE(dev) (NULL) +static inline const char *acpi_dev_name(struct acpi_device *adev) +{ + return NULL; +} + static inline void acpi_early_init(void) { } static inline int early_acpi_boot_init(void) -- cgit v1.2.3 From b26d4cd385fc51e8844e2cdf9ba2051f5bba11a5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 25 Oct 2013 18:47:37 -0400 Subject: consolidate simple ->d_delete() instances Rename simple_delete_dentry() to always_delete_dentry() and export it. Export simple_dentry_operations, while we are at it, and get rid of their duplicates Signed-off-by: Al Viro --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index bf5d574ebdf4..121f11f001c0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2622,7 +2622,9 @@ extern int simple_write_begin(struct file *file, struct address_space *mapping, extern int simple_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); +extern int always_delete_dentry(const struct dentry *); extern struct inode *alloc_anon_inode(struct super_block *); +extern const struct dentry_operations simple_dentry_operations; extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); -- cgit v1.2.3 From 2bc74feba12fbf052ec97aee8624c9f13593a9ac Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 25 Oct 2013 16:39:14 -0400 Subject: take read_seqbegin_or_lock() and friends to seqlock.h Signed-off-by: Al Viro --- include/linux/seqlock.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 1e8a8b6e837d..cf87a24c0f92 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -354,6 +354,35 @@ static inline void read_sequnlock_excl(seqlock_t *sl) spin_unlock(&sl->lock); } +/** + * read_seqbegin_or_lock - begin a sequence number check or locking block + * @lock: sequence lock + * @seq : sequence number to be checked + * + * First try it once optimistically without taking the lock. If that fails, + * take the lock. The sequence number is also used as a marker for deciding + * whether to be a reader (even) or writer (odd). + * N.B. seq must be initialized to an even number to begin with. + */ +static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq) +{ + if (!(*seq & 1)) /* Even */ + *seq = read_seqbegin(lock); + else /* Odd */ + read_seqlock_excl(lock); +} + +static inline int need_seqretry(seqlock_t *lock, int seq) +{ + return !(seq & 1) && read_seqretry(lock, seq); +} + +static inline void done_seqretry(seqlock_t *lock, int seq) +{ + if (seq & 1) + read_sequnlock_excl(lock); +} + static inline void read_seqlock_excl_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); -- cgit v1.2.3 From d5b5f391d434c5cc8bcb1ab2d759738797b85f52 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 14 Nov 2013 16:23:04 +0100 Subject: ftrace, perf: Avoid infinite event generation loop Vince's perf-trinity fuzzer found yet another 'interesting' problem. When we sample the irq_work_exit tracepoint with period==1 (or PERF_SAMPLE_PERIOD) and we add an fasync SIGNAL handler we create an infinite event generation loop: ,-> | irq_work_exit() -> | trace_irq_work_exit() -> | ... | __perf_event_overflow() -> (due to fasync) | irq_work_queue() -> (irq_work_list must be empty) '--------- arch_irq_work_raise() Similar things can happen due to regular poll() wakeups if we exceed the ring-buffer wakeup watermark, or have an event_limit. To avoid this, dis-allow sampling this particular tracepoint. In order to achieve this, create a special perf_perm function pointer for each event and call this (when set) on trying to create a tracepoint perf event. [ roasted: use expr... to allow for ',' in your expression ] Reported-by: Vince Weaver Tested-by: Vince Weaver Signed-off-by: Peter Zijlstra Cc: Steven Rostedt Cc: Dave Jones Cc: Frederic Weisbecker Link: http://lkml.kernel.org/r/20131114152304.GC5364@laptop.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/ftrace_event.h | 16 ++++++++++++++++ include/linux/tracepoint.h | 4 ++++ 2 files changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 9abbe630c456..8c9b7a1c4138 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -248,6 +248,9 @@ struct ftrace_event_call { #ifdef CONFIG_PERF_EVENTS int perf_refcount; struct hlist_head __percpu *perf_events; + + int (*perf_perm)(struct ftrace_event_call *, + struct perf_event *); #endif }; @@ -317,6 +320,19 @@ struct ftrace_event_file { } \ early_initcall(trace_init_flags_##name); +#define __TRACE_EVENT_PERF_PERM(name, expr...) \ + static int perf_perm_##name(struct ftrace_event_call *tp_event, \ + struct perf_event *p_event) \ + { \ + return ({ expr; }); \ + } \ + static int __init trace_init_perf_perm_##name(void) \ + { \ + event_##name.perf_perm = &perf_perm_##name; \ + return 0; \ + } \ + early_initcall(trace_init_perf_perm_##name); + #define PERF_MAX_TRACE_SIZE 2048 #define MAX_FILTER_STR_VAL 256 /* Should handle KSYM_SYMBOL_LEN */ diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index ebeab360d851..f16dc0a40049 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -267,6 +267,8 @@ static inline void tracepoint_synchronize_unregister(void) #define TRACE_EVENT_FLAGS(event, flag) +#define TRACE_EVENT_PERF_PERM(event, expr...) + #endif /* DECLARE_TRACE */ #ifndef TRACE_EVENT @@ -399,4 +401,6 @@ static inline void tracepoint_synchronize_unregister(void) #define TRACE_EVENT_FLAGS(event, flag) +#define TRACE_EVENT_PERF_PERM(event, expr...) + #endif /* ifdef TRACE_EVENT (see note above) */ -- cgit v1.2.3 From b972fc308c2763096b61b62169f2167ee0ca5a19 Mon Sep 17 00:00:00 2001 From: Alex Shi Date: Tue, 19 Nov 2013 17:21:52 +0800 Subject: sched: Remove unused variable in 'struct sched_domain' The 'u64 last_update' variable isn't used now, remove it to save a bit of space. Signed-off-by: Alex Shi Signed-off-by: Peter Zijlstra Cc: Morten.Rasmussen@arm.com Cc: linaro-kernel@lists.linaro.org Link: http://lkml.kernel.org/r/1384852912-24791-1-git-send-email-alex.shi@linaro.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index f7efc8604652..b122395bf5f4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -823,8 +823,6 @@ struct sched_domain { unsigned int balance_interval; /* initialise to 1. units in ms. */ unsigned int nr_balance_failed; /* initialise to 0 */ - u64 last_update; - /* idle_balance() stats */ u64 max_newidle_lb_cost; unsigned long next_decay_max_lb_cost; -- cgit v1.2.3 From 94eddfbeaafa3e8040a2c47d370dea0e58e76941 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 19 Nov 2013 09:25:07 -0700 Subject: blk-mq: ensure that we set REQ_IO_STAT so diskstats work If disk stats are enabled on the queue, a request needs to be marked with REQ_IO_STAT for accounting to be active on that request. This fixes an issue with virtio-blk not showing up in /proc/diskstats after the conversion to blk-mq. Add QUEUE_FLAG_MQ_DEFAULT, setting stats and same cpu-group completion on by default. Reported-by: Dave Chinner Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f26ec20f6354..1b135d49b279 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -505,6 +505,9 @@ struct request_queue { (1 << QUEUE_FLAG_SAME_COMP) | \ (1 << QUEUE_FLAG_ADD_RANDOM)) +#define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ + (1 << QUEUE_FLAG_SAME_COMP)) + static inline void queue_lockdep_assert_held(struct request_queue *q) { if (q->queue_lock) -- cgit v1.2.3 From 6bab2c613d7fa70bb8514f89ab7455ede717142b Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 15 Nov 2013 14:15:07 -0800 Subject: genirq: Correct fuzzy and fragile IRQ_RETVAL() definition commit bedd30d986a0 ("genirq: make irqreturn_t an enum") blindly replaced "0" by "IRQ_NONE" in the "IRQ_RETVAL(x)" macro definition. However, as "x" is a condition, "0" meant "boolean false", not an irqreturn_t value. All of this worked, and kept working after the addition of IRQ_WAKE_THREAD, as - both "boolean false" and "IRQ_NONE" are "0" (for the comparison), - "boolean true" and "boolean false" nicely map to the correct values of "IRQ_HANDLED" and "IRQ_NONE" (for the return value). Correct the macro definition for clarity and future-proofness. Signed-off-by: Geert Uytterhoeven Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner --- include/linux/irqreturn.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqreturn.h b/include/linux/irqreturn.h index 714ba08dc092..e374e369fb2f 100644 --- a/include/linux/irqreturn.h +++ b/include/linux/irqreturn.h @@ -14,6 +14,6 @@ enum irqreturn { }; typedef enum irqreturn irqreturn_t; -#define IRQ_RETVAL(x) ((x) != IRQ_NONE) +#define IRQ_RETVAL(x) ((x) ? IRQ_HANDLED : IRQ_NONE) #endif -- cgit v1.2.3 From 694e096fd7c2a7d40760fc9c9dfc826bdd495ea4 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Wed, 13 Nov 2013 12:29:08 -0500 Subject: NFS: Enabling v4.2 should not recompile nfsd and lockd When CONFIG_NFS_V4_2 is toggled nfsd and lockd will be recompiled, instead of only the nfs client. This patch moves a small amount of code into the client directory to avoid unnecessary recompiles. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs4.h | 10 ---------- include/linux/nfs_fs.h | 18 ------------------ 2 files changed, 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index c6f41b616965..ddd84871c0ad 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -410,16 +410,6 @@ enum lock_type4 { #define NFS4_VERSION 4 #define NFS4_MINOR_VERSION 0 -#if defined(CONFIG_NFS_V4_2) -#define NFS4_MAX_MINOR_VERSION 2 -#else -#if defined(CONFIG_NFS_V4_1) -#define NFS4_MAX_MINOR_VERSION 1 -#else -#define NFS4_MAX_MINOR_VERSION 0 -#endif /* CONFIG_NFS_V4_1 */ -#endif /* CONFIG_NFS_V4_2 */ - #define NFS4_DEBUG 1 /* Index of predefined Linux client operations */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 14a48207a304..48997374eaf0 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -506,24 +506,6 @@ extern const struct inode_operations nfs_referral_inode_operations; extern int nfs_mountpoint_expiry_timeout; extern void nfs_release_automount_timer(void); -/* - * linux/fs/nfs/nfs4proc.c - */ -#ifdef CONFIG_NFS_V4_SECURITY_LABEL -extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags); -static inline void nfs4_label_free(struct nfs4_label *label) -{ - if (label) { - kfree(label->label); - kfree(label); - } - return; -} -#else -static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; } -static inline void nfs4_label_free(void *label) {} -#endif - /* * linux/fs/nfs/unlink.c */ -- cgit v1.2.3 From 8b2e9b712f6139df9c754af0d67fecc4bbc88545 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 20 Nov 2013 14:41:47 -0800 Subject: Revert "mm: create a separate slab for page->ptl allocation" This reverts commit ea1e7ed33708c7a760419ff9ded0a6cb90586a50. Al points out that while the commit *does* actually create a separate slab for the page->ptl allocation, that slab is never actually used, and the code continues to use kmalloc/kfree. Damien Wyart points out that the original patch did have the conversion to use kmem_cache_alloc/free, so it got lost somewhere on its way to me. Revert the half-arsed attempt that didn't do anything. If we really do want the special slab (remember: this is all relevant just for debug builds, so it's not necessarily all that critical) we might as well redo the patch fully. Reported-by: Al Viro Acked-by: Andrew Morton Cc: Kirill A Shutemov Signed-off-by: Linus Torvalds --- include/linux/mm.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0548eb201e05..1cedd000cf29 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1318,7 +1318,6 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a #if USE_SPLIT_PTE_PTLOCKS #if BLOATED_SPINLOCKS -void __init ptlock_cache_init(void); extern bool ptlock_alloc(struct page *page); extern void ptlock_free(struct page *page); @@ -1327,7 +1326,6 @@ static inline spinlock_t *ptlock_ptr(struct page *page) return page->ptl; } #else /* BLOATED_SPINLOCKS */ -static inline void ptlock_cache_init(void) {} static inline bool ptlock_alloc(struct page *page) { return true; @@ -1380,17 +1378,10 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } -static inline void ptlock_cache_init(void) {} static inline bool ptlock_init(struct page *page) { return true; } static inline void pte_lock_deinit(struct page *page) {} #endif /* USE_SPLIT_PTE_PTLOCKS */ -static inline void pgtable_init(void) -{ - ptlock_cache_init(); - pgtable_cache_init(); -} - static inline bool pgtable_page_ctor(struct page *page) { inc_zone_page_state(page, NR_PAGETABLE); -- cgit v1.2.3 From f3d3342602f8bcbf37d7c46641cb9bca7618eb1c Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Thu, 21 Nov 2013 03:14:22 +0100 Subject: net: rework recvmsg handler msg_name and msg_namelen logic This patch now always passes msg->msg_namelen as 0. recvmsg handlers must set msg_namelen to the proper size <= sizeof(struct sockaddr_storage) to return msg_name to the user. This prevents numerous uninitialized memory leaks we had in the recvmsg handlers and makes it harder for new code to accidentally leak uninitialized memory. Optimize for the case recvfrom is called with NULL as address. We don't need to copy the address at all, so set it to NULL before invoking the recvmsg handler. We can do so, because all the recvmsg handlers must cope with the case a plain read() is called on them. read() also sets msg_name to NULL. Also document these changes in include/linux/net.h as suggested by David Miller. Changes since RFC: Set msg->msg_name = NULL if user specified a NULL in msg_name but had a non-null msg_namelen in verify_iovec/verify_compat_iovec. This doesn't affect sendto as it would bail out earlier while trying to copy-in the address. It also more naturally reflects the logic by the callers of verify_iovec. With this change in place I could remove " if (!uaddr || msg_sys->msg_namelen == 0) msg->msg_name = NULL ". This change does not alter the user visible error logic as we ignore msg_namelen as long as msg_name is NULL. Also remove two unnecessary curly brackets in ___sys_recvmsg and change comments to netdev style. Cc: David Miller Suggested-by: Eric Dumazet Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/net.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index b292a0435571..4bcee94cef93 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -164,6 +164,14 @@ struct proto_ops { #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); -- cgit v1.2.3 From 3fb69bcadda6263b92dbf8dd74717cba27c77ed9 Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Wed, 20 Nov 2013 16:38:19 -0600 Subject: net/phy: Add the autocross feature for forced links on VSC82x4 Add auto-MDI/MDI-X capability for forced (autonegotiation disabled) 10/100 Mbps speeds on Vitesse VSC82x4 PHYs. Exported previously static function genphy_setup_forced() required by the new config_aneg handler in the Vitesse PHY module. Signed-off-by: Madalin Bucur Signed-off-by: Shruti Kanetkar Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 64ab823f7b74..48a4dc3cb8cf 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -559,6 +559,7 @@ static inline int phy_read_status(struct phy_device *phydev) { 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); -- cgit v1.2.3 From 30b0a105d9f7141e4cbf72ae5511832457d89788 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Thu, 21 Nov 2013 14:31:58 -0800 Subject: mm: thp: give transparent hugepage code a separate copy_page Right now, the migration code in migrate_page_copy() uses copy_huge_page() for hugetlbfs and thp pages: if (PageHuge(page) || PageTransHuge(page)) copy_huge_page(newpage, page); So, yay for code reuse. But: void copy_huge_page(struct page *dst, struct page *src) { struct hstate *h = page_hstate(src); and a non-hugetlbfs page has no page_hstate(). This works 99% of the time because page_hstate() determines the hstate from the page order alone. Since the page order of a THP page matches the default hugetlbfs page order, it works. But, if you change the default huge page size on the boot command-line (say default_hugepagesz=1G), then we might not even *have* a 2MB hstate so page_hstate() returns null and copy_huge_page() oopses pretty fast since copy_huge_page() dereferences the hstate: void copy_huge_page(struct page *dst, struct page *src) { struct hstate *h = page_hstate(src); if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) { ... Mel noticed that the migration code is really the only user of these functions. This moves all the copy code over to migrate.c and makes copy_huge_page() work for THP by checking for it explicitly. I believe the bug was introduced in commit b32967ff101a ("mm: numa: Add THP migration for the NUMA working set scanning fault case") [akpm@linux-foundation.org: fix coding-style and comment text, per Naoya Horiguchi] Signed-off-by: Dave Hansen Acked-by: Mel Gorman Reviewed-by: Naoya Horiguchi Cc: Hillf Danton Cc: Andrea Arcangeli Tested-by: Dave Jiang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index acd2010328f3..85e0c58bdfdf 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -69,7 +69,6 @@ int dequeue_hwpoisoned_huge_page(struct page *page); 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); @@ -140,9 +139,6 @@ static inline int dequeue_hwpoisoned_huge_page(struct page *page) #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) -- cgit v1.2.3 From 27c73ae759774e63313c1fbfeb17ba076cea64c5 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 21 Nov 2013 14:32:02 -0800 Subject: mm: hugetlbfs: fix hugetlbfs optimization Commit 7cb2ef56e6a8 ("mm: fix aio performance regression for database caused by THP") can cause dereference of a dangling pointer if split_huge_page runs during PageHuge() if there are updates to the tail_page->private field. Also it is repeating compound_head twice for hugetlbfs and it is running compound_head+compound_trans_head for THP when a single one is needed in both cases. The new code within the PageSlab() check doesn't need to verify that the THP page size is never bigger than the smallest hugetlbfs page size, to avoid memory corruption. A longstanding theoretical race condition was found while fixing the above (see the change right after the skip_unlock label, that is relevant for the compound_lock path too). By re-establishing the _mapcount tail refcounting for all compound pages, this also fixes the below problem: echo 0 >/sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages BUG: Bad page state in process bash pfn:59a01 page:ffffea000139b038 count:0 mapcount:10 mapping: (null) index:0x0 page flags: 0x1c00000000008000(tail) Modules linked in: CPU: 6 PID: 2018 Comm: bash Not tainted 3.12.0+ #25 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 Call Trace: dump_stack+0x55/0x76 bad_page+0xd5/0x130 free_pages_prepare+0x213/0x280 __free_pages+0x36/0x80 update_and_free_page+0xc1/0xd0 free_pool_huge_page+0xc2/0xe0 set_max_huge_pages.part.58+0x14c/0x220 nr_hugepages_store_common.isra.60+0xd0/0xf0 nr_hugepages_store+0x13/0x20 kobj_attr_store+0xf/0x20 sysfs_write_file+0x189/0x1e0 vfs_write+0xc5/0x1f0 SyS_write+0x55/0xb0 system_call_fastpath+0x16/0x1b Signed-off-by: Khalid Aziz Signed-off-by: Andrea Arcangeli Tested-by: Khalid Aziz Cc: Pravin Shelar Cc: Greg Kroah-Hartman Cc: Ben Hutchings Cc: Christoph Lameter Cc: Johannes Weiner Cc: Mel Gorman Cc: Rik van Riel Cc: Andi Kleen Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 85e0c58bdfdf..9649ff0c63f8 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -31,6 +31,7 @@ struct hugepage_subpool *hugepage_new_subpool(long nr_blocks); 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 *); @@ -103,6 +104,11 @@ static inline int PageHuge(struct page *page) 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) { } -- cgit v1.2.3 From 7aa555bf26763b86332c7a3689701c999834b87a Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 21 Nov 2013 14:32:11 -0800 Subject: mm: place page->pmd_huge_pte to right union I don't know what went wrong, mis-merge or something, but ->pmd_huge_pte placed in wrong union within struct page. In original patch[1] it's placed to union with ->lru and ->slab, but in commit e009bb30c8df ("mm: implement split page table lock for PMD level") it's in union with ->index and ->freelist. That union seems also unused for pages with table tables and safe to re-use, but it's not what I've tested. Let's move it to original place. It fixes indentation at least. :) [1] https://lkml.org/lkml/2013/10/7/288 Signed-off-by: Kirill A. Shutemov Reviewed-by: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 10f5a7272b80..011eb85d7b0f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -65,9 +65,6 @@ struct page { * 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 { @@ -135,6 +132,9 @@ struct page { struct list_head list; /* slobs list of pages */ struct slab *slab_page; /* slab fields */ +#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 */ -- cgit v1.2.3 From 7e3528c3660a2e8602abc7858b0994d611f74bc3 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 22 Nov 2013 18:14:38 -0800 Subject: slab.h: remove duplicate kmalloc declaration and fix kernel-doc warnings Fix kernel-doc warning for duplicate definition of 'kmalloc': Documentation/DocBook/kernel-api.xml:9483: element refentry: validity error : ID API-kmalloc already defined Also combine the kernel-doc info from the 2 kmalloc definitions into one block and remove the "see kcalloc" comment since kmalloc now contains the @flags info. Signed-off-by: Randy Dunlap Acked-by: Christoph Lameter Signed-off-by: Linus Torvalds --- include/linux/slab.h | 102 +++++++++++++++++++++++---------------------------- 1 file changed, 46 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index c2bba248fa63..1e2f4fe12773 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -388,10 +388,55 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) /** * kmalloc - allocate memory * @size: how many bytes of memory are required. - * @flags: the type of memory to allocate (see kcalloc). + * @flags: the type of memory to allocate. * * kmalloc is the normal method of allocating memory * for objects smaller than page size in the kernel. + * + * The @flags argument may be one of: + * + * %GFP_USER - Allocate memory on behalf of user. May sleep. + * + * %GFP_KERNEL - Allocate normal kernel ram. May sleep. + * + * %GFP_ATOMIC - Allocation will not sleep. May use emergency pools. + * For example, use this inside interrupt handlers. + * + * %GFP_HIGHUSER - Allocate pages from high memory. + * + * %GFP_NOIO - Do not do any I/O at all while trying to get memory. + * + * %GFP_NOFS - Do not make any fs calls while trying to get memory. + * + * %GFP_NOWAIT - Allocation will not sleep. + * + * %GFP_THISNODE - Allocate node-local memory only. + * + * %GFP_DMA - Allocation suitable for DMA. + * Should only be used for kmalloc() caches. Otherwise, use a + * slab created with SLAB_DMA. + * + * Also it is possible to set different flags by OR'ing + * in one or more of the following additional @flags: + * + * %__GFP_COLD - Request cache-cold pages instead of + * trying to return cache-warm pages. + * + * %__GFP_HIGH - This allocation has high priority and may use emergency pools. + * + * %__GFP_NOFAIL - Indicate that this allocation is in no way allowed to fail + * (think twice before using). + * + * %__GFP_NORETRY - If memory is not immediately available, + * then give up at once. + * + * %__GFP_NOWARN - If allocation fails, don't issue any warnings. + * + * %__GFP_REPEAT - If allocation fails initially, try once more before failing. + * + * There are other flags available as well, but these are not intended + * for general use, and so are not documented here. For a full list of + * potential flags, always refer to linux/gfp.h. */ static __always_inline void *kmalloc(size_t size, gfp_t flags) { @@ -501,61 +546,6 @@ struct seq_file; int cache_show(struct kmem_cache *s, struct seq_file *m); void print_slabinfo_header(struct seq_file *m); -/** - * kmalloc - allocate memory - * @size: how many bytes of memory are required. - * @flags: the type of memory to allocate. - * - * The @flags argument may be one of: - * - * %GFP_USER - Allocate memory on behalf of user. May sleep. - * - * %GFP_KERNEL - Allocate normal kernel ram. May sleep. - * - * %GFP_ATOMIC - Allocation will not sleep. May use emergency pools. - * For example, use this inside interrupt handlers. - * - * %GFP_HIGHUSER - Allocate pages from high memory. - * - * %GFP_NOIO - Do not do any I/O at all while trying to get memory. - * - * %GFP_NOFS - Do not make any fs calls while trying to get memory. - * - * %GFP_NOWAIT - Allocation will not sleep. - * - * %GFP_THISNODE - Allocate node-local memory only. - * - * %GFP_DMA - Allocation suitable for DMA. - * Should only be used for kmalloc() caches. Otherwise, use a - * slab created with SLAB_DMA. - * - * Also it is possible to set different flags by OR'ing - * in one or more of the following additional @flags: - * - * %__GFP_COLD - Request cache-cold pages instead of - * trying to return cache-warm pages. - * - * %__GFP_HIGH - This allocation has high priority and may use emergency pools. - * - * %__GFP_NOFAIL - Indicate that this allocation is in no way allowed to fail - * (think twice before using). - * - * %__GFP_NORETRY - If memory is not immediately available, - * then give up at once. - * - * %__GFP_NOWARN - If allocation fails, don't issue any warnings. - * - * %__GFP_REPEAT - If allocation fails initially, try once more before failing. - * - * There are other flags available as well, but these are not intended - * for general use, and so are not documented here. For a full list of - * potential flags, always refer to linux/gfp.h. - * - * kmalloc is the normal method of allocating memory - * in the kernel. - */ -static __always_inline void *kmalloc(size_t size, gfp_t flags); - /** * kmalloc_array - allocate memory for an array. * @n: number of elements. -- cgit v1.2.3 From 53e7cac35db5941f42221314c33693e71ffa496b Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Sat, 16 Nov 2013 21:44:52 +0900 Subject: gpiolib: use dedicated flags for GPIO properties GPIO mapping properties were defined using the GPIOF_* flags, which are declared in linux/gpio.h. This file is not included when using the GPIO descriptor interface. This patch declares the flags that can be used as GPIO mappings properties in linux/gpio/driver.h, and uses them in gpiolib, so that no deprecated declarations are used by the GPIO descriptor interface. This patch also allows GPIO_OPEN_DRAIN and GPIO_OPEN_SOURCE to be specified as GPIO mapping properties. Signed-off-by: Alexandre Courbot Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 656a27efb2c8..82eac610ce1a 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -125,6 +125,13 @@ extern struct gpio_chip *gpiochip_find(void *data, int gpiod_lock_as_irq(struct gpio_desc *desc); void gpiod_unlock_as_irq(struct gpio_desc *desc); +enum gpio_lookup_flags { + GPIO_ACTIVE_HIGH = (0 << 0), + GPIO_ACTIVE_LOW = (1 << 0), + GPIO_OPEN_DRAIN = (1 << 1), + GPIO_OPEN_SOURCE = (1 << 2), +}; + /** * Lookup table for associating GPIOs to specific devices and functions using * platform data. @@ -152,9 +159,9 @@ struct gpiod_lookup { */ unsigned int idx; /* - * mask of GPIOF_* values + * mask of GPIO_* values */ - unsigned long flags; + enum gpio_lookup_flags flags; }; /* -- cgit v1.2.3 From 9886e1fd096b8004a25bb8b7e5690ad1408ebc6f Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Mon, 25 Nov 2013 11:49:47 -0700 Subject: ARM: tegra: Provide dummy powergate implementation In order to support increased build test coverage for drivers, implement dummies for the powergate implementation. This will allow the drivers to be built without requiring support for Tegra to be selected. This patch solves the following build errors, which can be triggered in v3.13-rc1 by selecting DRM_TEGRA without ARCH_TEGRA: drivers/built-in.o: In function `gr3d_remove': drivers/gpu/drm/tegra/gr3d.c:321: undefined reference to `tegra_powergate_power_off' drivers/gpu/drm/tegra/gr3d.c:325: undefined reference to `tegra_powergate_power_off' drivers/built-in.o: In function `gr3d_probe': drivers/gpu/drm/tegra/gr3d.c:266: undefined reference to `tegra_powergate_sequence_power_up' drivers/gpu/drm/tegra/gr3d.c:273: undefined reference to `tegra_powergate_sequence_power_up' Signed-off-by: Thierry Reding [swarren, updated commit description] Signed-off-by: Stephen Warren Signed-off-by: Olof Johansson --- include/linux/tegra-powergate.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tegra-powergate.h b/include/linux/tegra-powergate.h index c98cfa406952..fd4498329c7c 100644 --- a/include/linux/tegra-powergate.h +++ b/include/linux/tegra-powergate.h @@ -45,6 +45,7 @@ struct clk; #define TEGRA_POWERGATE_3D0 TEGRA_POWERGATE_3D +#ifdef CONFIG_ARCH_TEGRA int tegra_powergate_is_powered(int id); int tegra_powergate_power_on(int id); int tegra_powergate_power_off(int id); @@ -52,5 +53,31 @@ int tegra_powergate_remove_clamping(int id); /* Must be called with clk disabled, and returns with clk enabled */ int tegra_powergate_sequence_power_up(int id, struct clk *clk); +#else +static inline int tegra_powergate_is_powered(int id) +{ + return -ENOSYS; +} + +static inline int tegra_powergate_power_on(int id) +{ + return -ENOSYS; +} + +static inline int tegra_powergate_power_off(int id) +{ + return -ENOSYS; +} + +static inline int tegra_powergate_remove_clamping(int id) +{ + return -ENOSYS; +} + +static inline int tegra_powergate_sequence_power_up(int id, struct clk *clk) +{ + return -ENOSYS; +} +#endif #endif /* _MACH_TEGRA_POWERGATE_H_ */ -- cgit v1.2.3 From ecf61c78bd787b9dfb4a6b1dfb7561c2a95c5c17 Mon Sep 17 00:00:00 2001 From: Michal Marek Date: Mon, 11 Nov 2013 14:40:35 +0100 Subject: PCI: Omit PCI ID macro strings to shorten quirk names Pasting the verbatim PCI_(VENDOR|DEVICE)_* macros in the __pci_fixup_* symbol names results in insanely long names such as __pci_fixup_resumePCI_VENDOR_ID_SERVERWORKSPCI_DEVICE_ID_SERVERWORKS_HT1000SBquirk_disable_broadcom_boot_interrupt When Link-Time Optimization adds its numeric suffix to such symbol, it overflows the namebuf[KSYM_NAME_LEN] array in kernel/kallsyms.c. Use the line number instead to create (nearly) unique symbol names. Reported-by: Joe Mario Signed-off-by: Michal Marek Signed-off-by: Bjorn Helgaas Cc: Andi Kleen --- include/linux/pci.h | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 1084a15175e0..eb8078aeadc8 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1567,65 +1567,65 @@ enum pci_fixup_pass { /* Anonymous variables would be nice... */ #define DECLARE_PCI_FIXUP_SECTION(section, name, vendor, device, class, \ class_shift, hook) \ - static const struct pci_fixup __pci_fixup_##name __used \ + static const struct pci_fixup __PASTE(__pci_fixup_##name,__LINE__) __used \ __attribute__((__section__(#section), aligned((sizeof(void *))))) \ = { vendor, device, class, class_shift, hook }; #define DECLARE_PCI_FIXUP_CLASS_EARLY(vendor, device, class, \ class_shift, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_early, \ - vendor##device##hook, vendor, device, class, class_shift, hook) + hook, vendor, device, class, class_shift, hook) #define DECLARE_PCI_FIXUP_CLASS_HEADER(vendor, device, class, \ class_shift, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_header, \ - vendor##device##hook, vendor, device, class, class_shift, hook) + hook, vendor, device, class, class_shift, hook) #define DECLARE_PCI_FIXUP_CLASS_FINAL(vendor, device, class, \ class_shift, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_final, \ - vendor##device##hook, vendor, device, class, class_shift, hook) + hook, vendor, device, class, class_shift, hook) #define DECLARE_PCI_FIXUP_CLASS_ENABLE(vendor, device, class, \ class_shift, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_enable, \ - vendor##device##hook, vendor, device, class, class_shift, hook) + hook, vendor, device, class, class_shift, hook) #define DECLARE_PCI_FIXUP_CLASS_RESUME(vendor, device, class, \ class_shift, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_resume, \ - resume##vendor##device##hook, vendor, device, class, \ + resume##hook, vendor, device, class, \ class_shift, hook) #define DECLARE_PCI_FIXUP_CLASS_RESUME_EARLY(vendor, device, class, \ class_shift, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_resume_early, \ - resume_early##vendor##device##hook, vendor, device, \ + resume_early##hook, vendor, device, \ class, class_shift, hook) #define DECLARE_PCI_FIXUP_CLASS_SUSPEND(vendor, device, class, \ class_shift, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_suspend, \ - suspend##vendor##device##hook, vendor, device, class, \ + suspend##hook, vendor, device, class, \ class_shift, hook) #define DECLARE_PCI_FIXUP_EARLY(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_early, \ - vendor##device##hook, vendor, device, PCI_ANY_ID, 0, hook) + hook, vendor, device, PCI_ANY_ID, 0, hook) #define DECLARE_PCI_FIXUP_HEADER(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_header, \ - vendor##device##hook, vendor, device, PCI_ANY_ID, 0, hook) + hook, vendor, device, PCI_ANY_ID, 0, hook) #define DECLARE_PCI_FIXUP_FINAL(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_final, \ - vendor##device##hook, vendor, device, PCI_ANY_ID, 0, hook) + hook, vendor, device, PCI_ANY_ID, 0, hook) #define DECLARE_PCI_FIXUP_ENABLE(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_enable, \ - vendor##device##hook, vendor, device, PCI_ANY_ID, 0, hook) + hook, vendor, device, PCI_ANY_ID, 0, hook) #define DECLARE_PCI_FIXUP_RESUME(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_resume, \ - resume##vendor##device##hook, vendor, device, \ + resume##hook, vendor, device, \ PCI_ANY_ID, 0, hook) #define DECLARE_PCI_FIXUP_RESUME_EARLY(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_resume_early, \ - resume_early##vendor##device##hook, vendor, device, \ + resume_early##hook, vendor, device, \ PCI_ANY_ID, 0, hook) #define DECLARE_PCI_FIXUP_SUSPEND(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_suspend, \ - suspend##vendor##device##hook, vendor, device, \ + suspend##hook, vendor, device, \ PCI_ANY_ID, 0, hook) #ifdef CONFIG_PCI_QUIRKS -- cgit v1.2.3 From 5a87182aa21d6d5d306840feab9321818dd3e2a3 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 27 Nov 2013 09:09:42 +0530 Subject: cpufreq: suspend governors on system suspend/hibernate This patch adds cpufreq suspend/resume calls to dpm_{suspend|resume}_noirq() for handling suspend/resume of cpufreq governors. Lan Tianyu (Intel) & Jinhyuk Choi (Broadcom) found anr issue where tunables configuration for clusters/sockets with non-boot CPUs was getting lost after suspend/resume, as we were notifying governors with CPUFREQ_GOV_POLICY_EXIT on removal of the last cpu for that policy and so deallocating memory for tunables. This is fixed by this patch as we don't allow any operation on governors after device suspend and before device resume now. Reported-and-tested-by: Lan Tianyu Reported-by: Jinhyuk Choi Signed-off-by: Viresh Kumar [rjw: Changelog, minor cleanups] Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 5bd6ab9b0c27..91716658e9a1 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -272,6 +272,14 @@ cpufreq_verify_within_cpu_limits(struct cpufreq_policy *policy) policy->cpuinfo.max_freq); } +#ifdef CONFIG_CPU_FREQ +void cpufreq_suspend(void); +void cpufreq_resume(void); +#else +static inline void cpufreq_suspend(void) {} +static inline void cpufreq_resume(void) {} +#endif + /********************************************************************* * CPUFREQ NOTIFIER INTERFACE * *********************************************************************/ -- cgit v1.2.3 From e0d59733f6b1796b8d6692642c87d7dd862c3e3a Mon Sep 17 00:00:00 2001 From: Seiji Aguchi Date: Wed, 30 Oct 2013 15:27:26 -0400 Subject: efivars, efi-pstore: Hold off deletion of sysfs entry until the scan is completed Currently, when mounting pstore file system, a read callback of efi_pstore driver runs mutiple times as below. - In the first read callback, scan efivar_sysfs_list from head and pass a kmsg buffer of a entry to an upper pstore layer. - In the second read callback, rescan efivar_sysfs_list from the entry and pass another kmsg buffer to it. - Repeat the scan and pass until the end of efivar_sysfs_list. In this process, an entry is read across the multiple read function calls. To avoid race between the read and erasion, the whole process above is protected by a spinlock, holding in open() and releasing in close(). At the same time, kmemdup() is called to pass the buffer to pstore filesystem during it. And then, it causes a following lockdep warning. To make the dynamic memory allocation runnable without taking spinlock, holding off a deletion of sysfs entry if it happens while scanning it via efi_pstore, and deleting it after the scan is completed. To implement it, this patch introduces two flags, scanning and deleting, to efivar_entry. On the code basis, it seems that all the scanning and deleting logic is not needed because __efivars->lock are not dropped when reading from the EFI variable store. But, the scanning and deleting logic is still needed because an efi-pstore and a pstore filesystem works as follows. In case an entry(A) is found, the pointer is saved to psi->data. And efi_pstore_read() passes the entry(A) to a pstore filesystem by releasing __efivars->lock. And then, the pstore filesystem calls efi_pstore_read() again and the same entry(A), which is saved to psi->data, is used for resuming to scan a sysfs-list. So, to protect the entry(A), the logic is needed. [ 1.143710] ------------[ cut here ]------------ [ 1.144058] WARNING: CPU: 1 PID: 1 at kernel/lockdep.c:2740 lockdep_trace_alloc+0x104/0x110() [ 1.144058] DEBUG_LOCKS_WARN_ON(irqs_disabled_flags(flags)) [ 1.144058] Modules linked in: [ 1.144058] CPU: 1 PID: 1 Comm: systemd Not tainted 3.11.0-rc5 #2 [ 1.144058] 0000000000000009 ffff8800797e9ae0 ffffffff816614a5 ffff8800797e9b28 [ 1.144058] ffff8800797e9b18 ffffffff8105510d 0000000000000080 0000000000000046 [ 1.144058] 00000000000000d0 00000000000003af ffffffff81ccd0c0 ffff8800797e9b78 [ 1.144058] Call Trace: [ 1.144058] [] dump_stack+0x54/0x74 [ 1.144058] [] warn_slowpath_common+0x7d/0xa0 [ 1.144058] [] warn_slowpath_fmt+0x4c/0x50 [ 1.144058] [] ? vsscanf+0x57f/0x7b0 [ 1.144058] [] lockdep_trace_alloc+0x104/0x110 [ 1.144058] [] __kmalloc_track_caller+0x50/0x280 [ 1.144058] [] ? efi_pstore_read_func.part.1+0x12b/0x170 [ 1.144058] [] kmemdup+0x20/0x50 [ 1.144058] [] efi_pstore_read_func.part.1+0x12b/0x170 [ 1.144058] [] ? efi_pstore_read_func.part.1+0x170/0x170 [ 1.144058] [] efi_pstore_read_func+0xb4/0xe0 [ 1.144058] [] __efivar_entry_iter+0xfb/0x120 [ 1.144058] [] efi_pstore_read+0x3f/0x50 [ 1.144058] [] pstore_get_records+0x9a/0x150 [ 1.158207] [] ? selinux_d_instantiate+0x1c/0x20 [ 1.158207] [] ? parse_options+0x80/0x80 [ 1.158207] [] pstore_fill_super+0xa5/0xc0 [ 1.158207] [] mount_single+0xa2/0xd0 [ 1.158207] [] pstore_mount+0x18/0x20 [ 1.158207] [] mount_fs+0x39/0x1b0 [ 1.158207] [] ? __alloc_percpu+0x10/0x20 [ 1.158207] [] vfs_kern_mount+0x63/0xf0 [ 1.158207] [] do_mount+0x23e/0xa20 [ 1.158207] [] ? strndup_user+0x4b/0xf0 [ 1.158207] [] SyS_mount+0x83/0xc0 [ 1.158207] [] system_call_fastpath+0x16/0x1b [ 1.158207] ---[ end trace 61981bc62de9f6f4 ]--- Signed-off-by: Seiji Aguchi Tested-by: Madper Xie Cc: stable@kernel.org Signed-off-by: Matt Fleming --- include/linux/efi.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index bc5687d0f315..11ce6784a196 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -801,6 +801,8 @@ struct efivar_entry { struct efi_variable var; struct list_head list; struct kobject kobj; + bool scanning; + bool deleting; }; @@ -866,6 +868,8 @@ void efivar_run_worker(void); #if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE) int efivars_sysfs_init(void); +#define EFIVARS_DATA_SIZE_MAX 1024 + #endif /* CONFIG_EFI_VARS */ #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From 23fd78d76415729b338ff1802a0066b4a62f7fb8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 2 Dec 2013 11:24:18 +0000 Subject: KEYS: Fix multiple key add into associative array If sufficient keys (or keyrings) are added into a keyring such that a node in the associative array's tree overflows (each node has a capacity N, currently 16) and such that all N+1 keys have the same index key segment for that level of the tree (the level'th nibble of the index key), then assoc_array_insert() calls ops->diff_objects() to indicate at which bit position the two index keys vary. However, __key_link_begin() passes a NULL object to assoc_array_insert() with the intention of supplying the correct pointer later before we commit the change. This means that keyring_diff_objects() is given a NULL pointer as one of its arguments which it does not expect. This results in an oops like the attached. With the previous patch to fix the keyring hash function, this can be forced much more easily by creating a keyring and only adding keyrings to it. Add any other sort of key and a different insertion path is taken - all 16+1 objects must want to cluster in the same node slot. This can be tested by: r=`keyctl newring sandbox @s` for ((i=0; i<=16; i++)); do keyctl newring ring$i $r; done This should work fine, but oopses when the 17th keyring is added. Since ops->diff_objects() is always called with the first pointer pointing to the object to be inserted (ie. the NULL pointer), we can fix the problem by changing the to-be-inserted object pointer to point to the index key passed into assoc_array_insert() instead. Whilst we're at it, we also switch the arguments so that they are the same as for ->compare_object(). BUG: unable to handle kernel NULL pointer dereference at 0000000000000088 IP: [] hash_key_type_and_desc+0x18/0xb0 ... RIP: 0010:[] hash_key_type_and_desc+0x18/0xb0 ... Call Trace: [] keyring_diff_objects+0x21/0xd2 [] assoc_array_insert+0x3b6/0x908 [] __key_link_begin+0x78/0xe5 [] key_create_or_update+0x17d/0x36a [] SyS_add_key+0x123/0x183 [] tracesys+0xdd/0xe2 Signed-off-by: David Howells Tested-by: Stephen Gallagher --- include/linux/assoc_array.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/assoc_array.h b/include/linux/assoc_array.h index 9a193b84238a..a89df3be1686 100644 --- a/include/linux/assoc_array.h +++ b/include/linux/assoc_array.h @@ -41,10 +41,10 @@ struct assoc_array_ops { /* 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) + /* How different is an object from an index key, to a bit position in + * their keys? (or -1 if they're the same) */ - int (*diff_objects)(const void *a, const void *b); + int (*diff_objects)(const void *object, const void *index_key); /* Method to free an object. */ void (*free_object)(void *object); -- cgit v1.2.3 From c7277090927a5e71871e799a355ed2940f6c8fc6 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Mon, 2 Dec 2013 11:24:19 +0000 Subject: security: shmem: implement kernel private shmem inodes We have a problem where the big_key key storage implementation uses a shmem backed inode to hold the key contents. Because of this detail of implementation LSM checks are being done between processes trying to read the keys and the tmpfs backed inode. The LSM checks are already being handled on the key interface level and should not be enforced at the inode level (since the inode is an implementation detail, not a part of the security model) This patch implements a new function shmem_kernel_file_setup() which returns the equivalent to shmem_file_setup() only the underlying inode has S_PRIVATE set. This means that all LSM checks for the inode in question are skipped. It should only be used for kernel internal operations where the inode is not exposed to userspace without proper LSM checking. It is possible that some other users of shmem_file_setup() should use the new interface, but this has not been explored. Reproducing this bug is a little bit difficult. The steps I used on Fedora are: (1) Turn off selinux enforcing: setenforce 0 (2) Create a huge key k=`dd if=/dev/zero bs=8192 count=1 | keyctl padd big_key test-key @s` (3) Access the key in another context: runcon system_u:system_r:httpd_t:s0-s0:c0.c1023 keyctl print $k >/dev/null (4) Examine the audit logs: ausearch -m AVC -i --subject httpd_t | audit2allow If the last command's output includes a line that looks like: allow httpd_t user_tmpfs_t:file { open read }; There was an inode check between httpd and the tmpfs filesystem. With this patch no such denial will be seen. (NOTE! you should clear your audit log if you have tested for this previously) (Please return you box to enforcing) Signed-off-by: Eric Paris Signed-off-by: David Howells cc: Hugh Dickins cc: linux-mm@kvack.org --- include/linux/shmem_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 30aa0dc60d75..9d55438bc4ad 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -47,6 +47,8 @@ extern int shmem_init(void); extern int shmem_fill_super(struct super_block *sb, void *data, int silent); extern struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); +extern struct file *shmem_kernel_file_setup(const char *name, loff_t size, + unsigned long flags); extern int shmem_zero_setup(struct vm_area_struct *); extern int shmem_lock(struct file *file, int lock, struct user_struct *user); extern void shmem_unlock_mapping(struct address_space *mapping); -- cgit v1.2.3 From 35773dac5f862cb1c82ea151eba3e2f6de51ec3e Mon Sep 17 00:00:00 2001 From: David Laight Date: Mon, 11 Nov 2013 12:26:54 +0000 Subject: usb: xhci: Link TRB must not occur within a USB payload burst Section 4.11.7.1 of rev 1.0 of the xhci specification states that a link TRB can only occur at a boundary between underlying USB frames (512 bytes for high speed devices). If this isn't done the USB frames aren't formatted correctly and, for example, the USB3 ethernet ax88179_178a card will stop sending (while still receiving) when running a netperf tcp transmit test with (say) and 8k buffer. This should be a candidate for stable, the ax88179_178a driver defaults to gso and tso enabled so it passes a lot of fragmented skb to the USB stack. Notes from Sarah: Discussion: http://marc.info/?l=linux-usb&m=138384509604981&w=2 This patch fixes a long-standing xHCI driver bug that was revealed by a change in 3.12 in the usb-net driver. Commit 638c5115a794981441246fa8fa5d95c1875af5ba "USBNET: support DMA SG" added support to use bulk endpoint scatter-gather (urb->sg). Only the USB ethernet drivers trigger this bug, because the mass storage driver sends sg list entries in page-sized chunks. This patch only fixes the issue for bulk endpoint scatter-gather. The problem will still occur for periodic endpoints, because hosts will interpret no-op transfers as a request to skip a service interval, which is not what we want. Luckily, the USB core isn't set up for scatter-gather on isochronous endpoints, and no USB drivers use scatter-gather for interrupt endpoints. Document this known limitation so that developers won't try to use urb->sg for interrupt endpoints until this issue is fixed. The more comprehensive fix would be to allow link TRBs in the middle of the endpoint ring and revert this patch, but that fix would touch too much code to be allowed in for stable. This patch should be backported to kernels as old as 3.12, that contain the commit 638c5115a794981441246fa8fa5d95c1875af5ba "USBNET: support DMA SG". Without this patch, the USB network device gets wedged, and stops sending packets. Mark Lord confirms this patch fixes the regression: http://marc.info/?l=linux-netdev&m=138487107625966&w=2 Signed-off-by: David Laight Signed-off-by: Sarah Sharp Tested-by: Mark Lord Cc: stable@vger.kernel.org --- include/linux/usb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 7454865ad148..512ab162832c 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1264,6 +1264,8 @@ typedef void (*usb_complete_t)(struct urb *); * @sg: scatter gather buffer list, the buffer size of each element in * the list (except the last) must be divisible by the endpoint's * max packet size if no_sg_constraint isn't set in 'struct usb_bus' + * (FIXME: scatter-gather under xHCI is broken for periodic transfers. + * Do not use urb->sg for interrupt endpoints for now, only bulk.) * @num_mapped_sgs: (internal) number of mapped sg entries * @num_sgs: number of entries in the sg list * @transfer_buffer_length: How big is transfer_buffer. The transfer may -- cgit v1.2.3 From 8496e85c20e7836b3dec97780e40f420a3ae2801 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 1 Dec 2013 02:34:37 +0100 Subject: PCI / tg3: Give up chip reset and carrier loss handling if PCI device is not present Modify tg3_chip_reset() and tg3_close() to check if the PCI network adapter device is accessible at all in order to skip poking it or trying to handle a carrier loss in vain when that's not the case. Introduce a special PCI helper function pci_device_is_present() for this purpose. Of course, this uncovers the lack of the appropriate RTNL locking in tg3_suspend() and tg3_resume(), so add that locking in there too. These changes prevent tg3 from burning a CPU at 100% load level for solid several seconds after the Thunderbolt link is disconnected from a Matrox DS1 docking station. Signed-off-by: Rafael J. Wysocki Acked-by: Michael Chan Signed-off-by: David S. Miller --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 1084a15175e0..25a389566e47 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -960,6 +960,7 @@ void pci_update_resource(struct pci_dev *dev, int resno); int __must_check pci_assign_resource(struct pci_dev *dev, int i); int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align); int pci_select_bars(struct pci_dev *dev, unsigned long flags); +bool pci_device_is_present(struct pci_dev *pdev); /* ROM control related routines */ int pci_enable_rom(struct pci_dev *pdev); -- cgit v1.2.3 From 9f740ffa8134aaef770f964485dac3ed6780d8b7 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Wed, 27 Nov 2013 22:19:00 +0000 Subject: HID: hid-sensor-hub: Add logical min and max Exporting logical minimum and maximum of HID fields as part of the hid sensor attribute info. This can be used for range checking and to calculate enumeration base for NAry fields of HID sensor hub. Signed-off-by: Srinivas Pandruvada Signed-off-by: Jonathan Cameron --- include/linux/hid-sensor-hub.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h index 206a2af6b62b..b914ca3f57ba 100644 --- a/include/linux/hid-sensor-hub.h +++ b/include/linux/hid-sensor-hub.h @@ -42,6 +42,8 @@ struct hid_sensor_hub_attribute_info { s32 units; s32 unit_expo; s32 size; + s32 logical_minimum; + s32 logical_maximum; }; /** -- cgit v1.2.3 From 751d17e23a9f7c8e0bca5c0b2e8d39af655ecd2a Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Wed, 27 Nov 2013 22:19:00 +0000 Subject: iio: hid-sensors: Fix power and report state In the original HID sensor hub firmwares all Named array enums were to 0-based. But the most recent hub implemented as 1-based, because of the implementation by one of the major OS vendor. Using logical minimum for the field as the base of enum. So we add logical minimum to the selector values before setting those fields. Some sensor hub FWs already changed logical minimum from 0 to 1 to reflect this and hope every other vendor will follow. There is no easy way to add a common HID quirk for NAry elements, even if the standard specifies these field as NAry, the collection used to describe selectors is still just "logical". Signed-off-by: Srinivas Pandruvada Signed-off-by: Jonathan Cameron --- include/linux/hid-sensor-ids.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid-sensor-ids.h b/include/linux/hid-sensor-ids.h index 4f945d3ed49f..8323775ac21d 100644 --- a/include/linux/hid-sensor-ids.h +++ b/include/linux/hid-sensor-ids.h @@ -117,4 +117,16 @@ #define HID_USAGE_SENSOR_PROP_REPORT_STATE 0x200316 #define HID_USAGE_SENSOR_PROY_POWER_STATE 0x200319 +/* Power state enumerations */ +#define HID_USAGE_SENSOR_PROP_POWER_STATE_UNDEFINED_ENUM 0x00 +#define HID_USAGE_SENSOR_PROP_POWER_STATE_D0_FULL_POWER_ENUM 0x01 +#define HID_USAGE_SENSOR_PROP_POWER_STATE_D1_LOW_POWER_ENUM 0x02 +#define HID_USAGE_SENSOR_PROP_POWER_STATE_D2_STANDBY_WITH_WAKE_ENUM 0x03 +#define HID_USAGE_SENSOR_PROP_POWER_STATE_D3_SLEEP_WITH_WAKE_ENUM 0x04 +#define HID_USAGE_SENSOR_PROP_POWER_STATE_D4_POWER_OFF_ENUM 0x05 + +/* Report State enumerations */ +#define HID_USAGE_SENSOR_PROP_REPORTING_STATE_NO_EVENTS_ENUM 0x00 +#define HID_USAGE_SENSOR_PROP_REPORTING_STATE_ALL_EVENTS_ENUM 0x01 + #endif -- cgit v1.2.3 From 7ce5a27f2ef8ed4f8f892f46391f933c0e2ac0f1 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 2 Dec 2013 17:26:05 -0500 Subject: Revert "net: Handle CHECKSUM_COMPLETE more adequately in pskb_trim_rcsum()." This reverts commit 018c5bba052b3a383d83cf0c756da0e7bc748397. It causes regressions for people using chips driven by the sungem driver. Suspicion is that the skb->csum value isn't being adjusted properly. The change also has a bug in that if __pskb_trim() fails, we'll leave a corruped skb->csum value in there. We would really need to revert it to it's original value in that case. Signed-off-by: David S. Miller --- include/linux/skbuff.h | 39 ++++++++++++++++++--------------------- 1 file changed, 18 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bec1cc7d5e3c..215b5ea1cb30 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2263,6 +2263,24 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb, unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); +/** + * pskb_trim_rcsum - trim received skb and update checksum + * @skb: buffer to trim + * @len: new length + * + * This is exactly the same as pskb_trim except that it ensures the + * checksum of received packets are still valid after the operation. + */ + +static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) +{ + if (likely(len >= skb->len)) + return 0; + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->ip_summed = CHECKSUM_NONE; + return __pskb_trim(skb, len); +} + #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ skb != (struct sk_buff *)(queue); \ @@ -2360,27 +2378,6 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum); -/** - * pskb_trim_rcsum - trim received skb and update checksum - * @skb: buffer to trim - * @len: new length - * - * This is exactly the same as pskb_trim except that it ensures the - * checksum of received packets are still valid after the operation. - */ - -static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) -{ - if (likely(len >= skb->len)) - return 0; - if (skb->ip_summed == CHECKSUM_COMPLETE) { - __wsum adj = skb_checksum(skb, len, skb->len - len, 0); - - skb->csum = csum_sub(skb->csum, adj); - } - return __pskb_trim(skb, len); -} - static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) { -- cgit v1.2.3 From 471e42ad148c05d091219096726d751684ebf918 Mon Sep 17 00:00:00 2001 From: Thomas Pugliese Date: Mon, 2 Dec 2013 15:39:45 -0600 Subject: usb: wusbcore: fix deadlock in wusbhc_gtk_rekey When multiple wireless USB devices are connected and one of the devices disconnects, the host will distribute a new group key to the remaining devicese using wusbhc_gtk_rekey. wusbhc_gtk_rekey takes the wusbhc->mutex and holds it while it submits a URB to set the new key. This causes a deadlock in wa_urb_enqueue when it calls a device lookup helper function that takes the same lock. This patch changes wusbhc_gtk_rekey to submit a work item to set the GTK so that the URB is submitted without holding wusbhc->mutex. Signed-off-by: Thomas Pugliese Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/wusb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/wusb.h b/include/linux/usb/wusb.h index 0c4d4ca370ec..eeb28329fa3c 100644 --- a/include/linux/usb/wusb.h +++ b/include/linux/usb/wusb.h @@ -271,6 +271,8 @@ static inline u8 wusb_key_index(int index, int type, int originator) #define WUSB_KEY_INDEX_TYPE_GTK 2 #define WUSB_KEY_INDEX_ORIGINATOR_HOST 0 #define WUSB_KEY_INDEX_ORIGINATOR_DEVICE 1 +/* bits 0-3 used for the key index. */ +#define WUSB_KEY_INDEX_MAX 15 /* A CCM Nonce, defined in WUSB1.0[6.4.1] */ struct aes_ccm_nonce { -- cgit v1.2.3 From c9a9972b6f093e4e2f81f58892a7523df894144d Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Mon, 25 Nov 2013 18:34:24 +0900 Subject: gpiolib: add missing declarations Add declaration of 'struct of_phandle_args' to avoid the following warning: In file included from arch/arm/mach-tegra/board-paz00.c:21:0: include/linux/gpio/driver.h:102:17: warning: 'struct of_phandle_args' declared inside parameter list include/linux/gpio/driver.h:102:17: warning: its scope is only this definition or declaration, which is probably not what you want Also proactively add other definitions/includes that could be missing in other contexts. Signed-off-by: Alexandre Courbot Reported-by: Stephen Warren Reviewed-by: Mika Westerberg Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 82eac610ce1a..3ea2cf6b0e6c 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -2,9 +2,12 @@ #define __LINUX_GPIO_DRIVER_H #include +#include struct device; struct gpio_desc; +struct of_phandle_args; +struct device_node; struct seq_file; /** -- cgit v1.2.3 From 1431fb31ecbaba1b5718006128f0f2ed0b94e1c3 Mon Sep 17 00:00:00 2001 From: Paul Durrant Date: Tue, 3 Dec 2013 17:39:29 +0000 Subject: xen-netback: fix fragment detection in checksum setup The code to detect fragments in checksum_setup() was missing for IPv4 and too eager for IPv6. (It transpires that Windows seems to send IPv6 packets with a fragment header even if they are not a fragment - i.e. offset is zero, and M bit is not set). This patch also incorporates a fix to callers of maybe_pull_tail() where skb->network_header was being erroneously added to the length argument. Signed-off-by: Paul Durrant Signed-off-by: Zoltan Kiss Cc: Wei Liu Cc: Ian Campbell Cc: David Vrabel cc: David Miller Acked-by: Wei Liu Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 5d89d1b808a6..c56c350324e4 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -4,6 +4,7 @@ #include #define ipv6_optlen(p) (((p)->hdrlen+1) << 3) +#define ipv6_authlen(p) (((p)->hdrlen+2) << 2) /* * This structure contains configuration options per IPv6 link. */ -- cgit v1.2.3 From 4fc9bbf98fd66f879e628d8537ba7c240be2b58e Mon Sep 17 00:00:00 2001 From: Khalid Aziz Date: Wed, 27 Nov 2013 15:19:25 -0700 Subject: PCI: Disable Bus Master only on kexec reboot Add a flag to tell the PCI subsystem that kernel is shutting down in preparation to kexec a kernel. Add code in PCI subsystem to use this flag to clear Bus Master bit on PCI devices only in case of kexec reboot. This fixes a power-off problem on Acer Aspire V5-573G and likely other machines and avoids any other issues caused by clearing Bus Master bit on PCI devices in normal shutdown path. The problem was introduced by b566a22c2332 ("PCI: disable Bus Master on PCI device shutdown"). This patch is based on discussion at http://marc.info/?l=linux-pci&m=138425645204355&w=2 Link: https://bugzilla.kernel.org/show_bug.cgi?id=63861 Reported-by: Chang Liu Signed-off-by: Khalid Aziz Signed-off-by: Bjorn Helgaas Acked-by: Konstantin Khlebnikov Cc: stable@vger.kernel.org # v3.5+ --- include/linux/kexec.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index d78d28a733b1..5fd33dc1fe3a 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -198,6 +198,9 @@ extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; extern size_t vmcoreinfo_size; extern size_t vmcoreinfo_max_size; +/* flag to track if kexec reboot is in progress */ +extern bool kexec_in_progress; + int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, unsigned long long *crash_size, unsigned long long *crash_base); int parse_crashkernel_high(char *cmdline, unsigned long long system_ram, -- cgit v1.2.3 From 12205a4b79bef56ef618a4b7caa840c5c971cff2 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 8 Dec 2013 01:04:17 +0100 Subject: Revert "cpufreq: suspend governors on system suspend/hibernate" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 5a87182aa21d (cpufreq: suspend governors on system suspend/hibernate) causes hibernation problems to happen on Bjørn Mork's and Paul Bolle's systems, so revert it. Fixes: 5a87182aa21d (cpufreq: suspend governors on system suspend/hibernate) Reported-by: Bjørn Mork Reported-by: Paul Bolle Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index ee5fe9d77ae8..dc196bbcf227 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -280,14 +280,6 @@ cpufreq_verify_within_cpu_limits(struct cpufreq_policy *policy) policy->cpuinfo.max_freq); } -#ifdef CONFIG_CPU_FREQ -void cpufreq_suspend(void); -void cpufreq_resume(void); -#else -static inline void cpufreq_suspend(void) {} -static inline void cpufreq_resume(void) {} -#endif - /********************************************************************* * CPUFREQ NOTIFIER INTERFACE * *********************************************************************/ -- cgit v1.2.3 From 503cf95c061a0551eb684da364509297efbe55d9 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Tue, 10 Dec 2013 14:56:06 -0800 Subject: x86, build, icc: Remove uninitialized_var() from compiler-intel.h When compiling with icc, ends up included because the icc environment defines __GNUC__. Thus, we neither need nor want to have this macro defined in both compiler-gcc.h and compiler-intel.h, and the fact that they are inconsistent just makes the compiler spew warnings. Reported-by: Sunil K. Pandey Cc: Kevin B. Smith Signed-off-by: H. Peter Anvin Link: http://lkml.kernel.org/n/tip-0mbwou1zt7pafij09b897lg3@git.kernel.org Cc: --- include/linux/compiler-intel.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index 973ce10c40b6..dc1bd3dcf11f 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -28,8 +28,6 @@ #endif -#define uninitialized_var(x) x - #ifndef __HAVE_BUILTIN_BSWAP16__ /* icc has this, but it's called _bswap16 */ #define __HAVE_BUILTIN_BSWAP16__ -- cgit v1.2.3 From 12663bfc97c8b3fdb292428105dd92d563164050 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Sat, 7 Dec 2013 17:26:27 -0500 Subject: net: unix: allow set_peek_off to fail unix_dgram_recvmsg() will hold the readlock of the socket until recv is complete. In the same time, we may try to setsockopt(SO_PEEK_OFF) which will hang until unix_dgram_recvmsg() will complete (which can take a while) without allowing us to break out of it, triggering a hung task spew. Instead, allow set_peek_off to fail, this way userspace will not hang. Signed-off-by: Sasha Levin Acked-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/linux/net.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 4bcee94cef93..69be3e6079c8 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -181,7 +181,7 @@ struct proto_ops { int offset, size_t size, int flags); ssize_t (*splice_read)(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); - void (*set_peek_off)(struct sock *sk, int val); + int (*set_peek_off)(struct sock *sk, int val); }; #define DECLARE_SOCKADDR(type, dst, src) \ -- cgit v1.2.3 From 4bd7b5127bd02c12c1cc837a7a0b6ce295eb2505 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Tue, 10 Dec 2013 02:20:41 +0300 Subject: micrel: add support for KSZ8041RNLI Renesas R-Car development boards use KSZ8041RNLI PHY which for some reason has ID of 0x00221537 that is not documented for KSZ8041-family PHYs and does not match the documented ID of 0x0022151x (where 'x' is the revision). We have to add the new #define PHY_ID_* and new ksphy_driver[] entry, almost the same as KSZ8041 one, differing only in the 'phy_id' and 'name' fields. Signed-off-by: Sergei Shtylyov Tested-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- include/linux/micrel_phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index ad05ce60c1c9..2e5b194b9b19 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -22,6 +22,8 @@ #define PHY_ID_KSZ8021 0x00221555 #define PHY_ID_KSZ8031 0x00221556 #define PHY_ID_KSZ8041 0x00221510 +/* undocumented */ +#define PHY_ID_KSZ8041RNLI 0x00221537 #define PHY_ID_KSZ8051 0x00221550 /* same id: ks8001 Rev. A/B, and ks8721 Rev 3. */ #define PHY_ID_KSZ8001 0x0022161A -- cgit v1.2.3 From a5c21dcefa1c3d759457a604b3cfc4af29c8713f Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 12 Dec 2013 17:40:21 +0000 Subject: dcache: allow word-at-a-time name hashing with big-endian CPUs When explicitly hashing the end of a string with the word-at-a-time interface, we have to be careful which end of the word we pick up. On big-endian CPUs, the upper-bits will contain the data we're after, so ensure we generate our masks accordingly (and avoid hashing whatever random junk may have been sitting after the string). This patch adds a new dcache helper, bytemask_from_count, which creates a mask appropriate for the CPU endianness. Cc: Al Viro Signed-off-by: Will Deacon Signed-off-by: Linus Torvalds --- include/linux/dcache.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 57e87e749a48..bf72e9ac6de0 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -29,8 +29,10 @@ struct vfsmount; /* The hash is always the low bits of hash_len */ #ifdef __LITTLE_ENDIAN #define HASH_LEN_DECLARE u32 hash; u32 len; + #define bytemask_from_count(cnt) (~(~0ul << (cnt)*8)) #else #define HASH_LEN_DECLARE u32 len; u32 hash; + #define bytemask_from_count(cnt) (~(~0ul >> (cnt)*8)) #endif /* -- cgit v1.2.3 From a0a9663dd2146d54339237764e1bfc60e8a39328 Mon Sep 17 00:00:00 2001 From: Sebastian Siewior Date: Thu, 12 Dec 2013 10:15:59 +0100 Subject: net: make neigh_priv_len in struct net_device 16bit instead of 8bit neigh_priv_len is defined as u8. With all debug enabled struct ipoib_neigh has 200 bytes. The largest part is sk_buff_head with 96 bytes and here the spinlock with 72 bytes. The size value still fits in this u8 leaving some room for more. On -RT struct ipoib_neigh put on weight and has 392 bytes. The main reason is sk_buff_head with 288 and the fatty here is spinlock with 192 bytes. This does no longer fit into into neigh_priv_len and gcc complains. This patch changes neigh_priv_len from being 8bit to 16bit. Since the following element (dev_id) is 16bit followed by a spinlock which is aligned, the struct remains with a total size of 3200 (allmodconfig) / 2048 (with as much debug off as possible) bytes on x86-64. On x86-32 the struct is 1856 (allmodconfig) / 1216 (with as much debug off as possible) bytes long. The numbers were gained with and without the patch to prove that this change does not increase the size of the struct. Cc: Steven Rostedt Cc: Thomas Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7f0ed423a360..d9a550bf3e8e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1255,7 +1255,7 @@ struct net_device { unsigned char perm_addr[MAX_ADDR_LEN]; /* permanent hw address */ unsigned char addr_assign_type; /* hw address assignment type */ unsigned char addr_len; /* hardware address length */ - unsigned char neigh_priv_len; + unsigned short neigh_priv_len; unsigned short dev_id; /* Used to differentiate devices * that share the same link * layer address -- cgit v1.2.3 From f40386a4e976acb2bd3e0f9ead11e8e769acbe98 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 12 Dec 2013 17:12:19 -0800 Subject: include/linux/hugetlb.h: make isolate_huge_page() an inline With CONFIG_HUGETLBFS=n: mm/migrate.c: In function `do_move_page_to_node_array': include/linux/hugetlb.h:140:33: warning: statement with no effect [-Wunused-value] #define isolate_huge_page(p, l) false ^ mm/migrate.c:1170:4: note: in expansion of macro `isolate_huge_page' isolate_huge_page(page, &pagelist); Reported-by: Borislav Petkov Tested-by: Borislav Petkov Signed-off-by: Naoya Horiguchi Acked-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 9649ff0c63f8..bd7e98752222 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -142,7 +142,10 @@ static inline int dequeue_hwpoisoned_huge_page(struct page *page) return 0; } -#define isolate_huge_page(p, l) false +static inline bool isolate_huge_page(struct page *page, struct list_head *list) +{ + return false; +} #define putback_active_hugepage(p) do {} while (0) #define is_hugepage_active(x) false -- cgit v1.2.3 From 386e79066f04850352f144e67edfd5b636c0f95c Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Thu, 12 Dec 2013 17:12:24 -0800 Subject: include/linux/kernel.h: make might_fault() a nop for !MMU The machine cannot fault if !MUU, so make might_fault() a nop for !MMU. This fixes below build error if !CONFIG_MMU && (CONFIG_PROVE_LOCKING=y || CONFIG_DEBUG_ATOMIC_SLEEP=y): arch/arm/kernel/built-in.o: In function `arch_ptrace': arch/arm/kernel/ptrace.c:852: undefined reference to `might_fault' arch/arm/kernel/built-in.o: In function `restore_sigframe': arch/arm/kernel/signal.c:173: undefined reference to `might_fault' ... arch/arm/kernel/built-in.o:arch/arm/kernel/signal.c:177: more undefined references to `might_fault' follow make: *** [vmlinux] Error 1 Signed-off-by: Axel Lin Acked-by: Michael S. Tsirkin Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d4e98d13eff4..ecb87544cc5d 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -193,7 +193,8 @@ extern int _cond_resched(void); (__x < 0) ? -__x : __x; \ }) -#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP) +#if defined(CONFIG_MMU) && \ + (defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP)) void might_fault(void); #else static inline void might_fault(void) { } -- cgit v1.2.3 From 3e1e4a5f3a324502c27c4e8808e06ac2ea842360 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 12 Dec 2013 17:12:31 -0800 Subject: mfd/rtc: s5m: fix register updating by adding regmap for RTC Rename old regmap field of "struct sec_pmic_dev" to "regmap_pmic" and add new regmap for RTC. On S5M8767A registers were not properly updated and read due to usage of the same regmap as the PMIC. This could be observed in various hangs, e.g. in infinite loop during waiting for UDR field change. On this chip family the RTC has different I2C address than PMIC so additional regmap is needed. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Kyungmin Park Reviewed-by: Mark Brown Acked-by: Sangbeom Kim Cc: Samuel Ortiz Cc: Lee Jones Cc: Liam Girdwood Cc: Alessandro Zummo Cc: Marek Szyprowski Cc: Geert Uytterhoeven Cc: Kyungmin Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mfd/samsung/core.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index 2d0c9071bcfb..cab2dd279076 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -39,7 +39,8 @@ enum sec_device_type { struct sec_pmic_dev { struct device *dev; struct sec_platform_data *pdata; - struct regmap *regmap; + struct regmap *regmap_pmic; + struct regmap *regmap_rtc; struct i2c_client *i2c; struct i2c_client *rtc; -- cgit v1.2.3