From 332f8840f7095d294f9bb066b175a100bcde214c Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 15 Nov 2007 22:36:07 +0800 Subject: [CRYPTO] ablkcipher: Add distinct ABLKCIPHER type Up until now we have ablkcipher algorithms have been identified as type BLKCIPHER with the ASYNC bit set. This is suboptimal because ablkcipher refers to two things. On the one hand it refers to the top-level ablkcipher interface with requests. On the other hand it refers to and algorithm type underneath. As it is you cannot request a synchronous block cipher algorithm with the ablkcipher interface on top. This is a problem because we want to be able to eventually phase out the blkcipher top-level interface. This patch fixes this by making ABLKCIPHER its own type, just as we have distinct types for HASH and DIGEST. The type it associated with the algorithm implementation only. Which top-level interface is used for synchronous block ciphers is then determined by the mask that's used. If it's a specific mask then the old blkcipher interface is given, otherwise we go with the new ablkcipher interface. Signed-off-by: Herbert Xu --- include/linux/crypto.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index f3110ebe894a..f56ae8721bc9 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -33,10 +33,12 @@ #define CRYPTO_ALG_TYPE_DIGEST 0x00000002 #define CRYPTO_ALG_TYPE_HASH 0x00000003 #define CRYPTO_ALG_TYPE_BLKCIPHER 0x00000004 -#define CRYPTO_ALG_TYPE_COMPRESS 0x00000005 -#define CRYPTO_ALG_TYPE_AEAD 0x00000006 +#define CRYPTO_ALG_TYPE_ABLKCIPHER 0x00000005 +#define CRYPTO_ALG_TYPE_COMPRESS 0x00000008 +#define CRYPTO_ALG_TYPE_AEAD 0x00000009 #define CRYPTO_ALG_TYPE_HASH_MASK 0x0000000e +#define CRYPTO_ALG_TYPE_BLKCIPHER_MASK 0x0000000c #define CRYPTO_ALG_LARVAL 0x00000010 #define CRYPTO_ALG_DEAD 0x00000020 @@ -530,7 +532,7 @@ static inline struct crypto_ablkcipher *crypto_alloc_ablkcipher( { type &= ~CRYPTO_ALG_TYPE_MASK; type |= CRYPTO_ALG_TYPE_BLKCIPHER; - mask |= CRYPTO_ALG_TYPE_MASK; + mask |= CRYPTO_ALG_TYPE_BLKCIPHER_MASK; return __crypto_ablkcipher_cast( crypto_alloc_base(alg_name, type, mask)); @@ -552,7 +554,7 @@ static inline int crypto_has_ablkcipher(const char *alg_name, u32 type, { type &= ~CRYPTO_ALG_TYPE_MASK; type |= CRYPTO_ALG_TYPE_BLKCIPHER; - mask |= CRYPTO_ALG_TYPE_MASK; + mask |= CRYPTO_ALG_TYPE_BLKCIPHER_MASK; return crypto_has_alg(alg_name, type, mask); } @@ -841,9 +843,9 @@ static inline struct crypto_blkcipher *crypto_blkcipher_cast( static inline struct crypto_blkcipher *crypto_alloc_blkcipher( const char *alg_name, u32 type, u32 mask) { - type &= ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_ASYNC); + type &= ~CRYPTO_ALG_TYPE_MASK; type |= CRYPTO_ALG_TYPE_BLKCIPHER; - mask |= CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_ASYNC; + mask |= CRYPTO_ALG_TYPE_MASK; return __crypto_blkcipher_cast(crypto_alloc_base(alg_name, type, mask)); } @@ -861,9 +863,9 @@ static inline void crypto_free_blkcipher(struct crypto_blkcipher *tfm) static inline int crypto_has_blkcipher(const char *alg_name, u32 type, u32 mask) { - type &= ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_ASYNC); + type &= ~CRYPTO_ALG_TYPE_MASK; type |= CRYPTO_ALG_TYPE_BLKCIPHER; - mask |= CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_ASYNC; + mask |= CRYPTO_ALG_TYPE_MASK; return crypto_has_alg(alg_name, type, mask); } -- cgit v1.2.3 From 984e976f5382ff09351ddd3b023937611396d739 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 21 Nov 2007 12:24:45 +0800 Subject: [HWRNG]: move status polling loop to data_present callbacks Handle waiting for new random within the drivers themselves, this allows to use better suited timeouts for the individual rngs. Signed-off-by: Patrick McHardy Acked-by: Michael Buesch Signed-off-by: Herbert Xu --- include/linux/hw_random.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h index 21ea7610e177..85d11916e9ea 100644 --- a/include/linux/hw_random.h +++ b/include/linux/hw_random.h @@ -33,7 +33,7 @@ struct hwrng { const char *name; int (*init)(struct hwrng *rng); void (*cleanup)(struct hwrng *rng); - int (*data_present)(struct hwrng *rng); + int (*data_present)(struct hwrng *rng, int wait); int (*data_read)(struct hwrng *rng, u32 *data); unsigned long priv; -- cgit v1.2.3 From 7ba683a6deba70251756aa5a021cdaa5c875a7a2 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sun, 2 Dec 2007 18:49:21 +1100 Subject: [CRYPTO] aead: Make authsize a run-time parameter As it is authsize is an algorithm paramter which cannot be changed at run-time. This is inconvenient because hardware that implements such algorithms would have to register each authsize that they support separately. Since authsize is a property common to all AEAD algorithms, we can add a function setauthsize that sets it at run-time, just like setkey. This patch does exactly that and also changes authenc so that authsize is no longer a parameter of its template. Signed-off-by: Herbert Xu --- include/linux/crypto.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index f56ae8721bc9..48aa5959abbb 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -187,11 +187,12 @@ struct ablkcipher_alg { struct aead_alg { int (*setkey)(struct crypto_aead *tfm, const u8 *key, unsigned int keylen); + int (*setauthsize)(struct crypto_aead *tfm, unsigned int authsize); int (*encrypt)(struct aead_request *req); int (*decrypt)(struct aead_request *req); unsigned int ivsize; - unsigned int authsize; + unsigned int maxauthsize; }; struct blkcipher_alg { @@ -754,6 +755,8 @@ static inline int crypto_aead_setkey(struct crypto_aead *tfm, const u8 *key, return crypto_aead_crt(tfm)->setkey(tfm, key, keylen); } +int crypto_aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize); + static inline struct crypto_aead *crypto_aead_reqtfm(struct aead_request *req) { return __crypto_aead_cast(req->base.tfm); -- cgit v1.2.3 From 551a09a7a954f720067f207657bbbd26a3fe156a Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sat, 1 Dec 2007 21:47:07 +1100 Subject: [CRYPTO] api: Sanitise mask when allocating ablkcipher/hash When allocating ablkcipher/hash objects, we use a mask that's wider than the usual type mask. This patch sanitises the mask supplied by the user so we don't end up using a narrower mask which may lead to unintended results. Signed-off-by: Herbert Xu --- include/linux/crypto.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 48aa5959abbb..ef7642ed3e42 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -532,6 +532,7 @@ static inline struct crypto_ablkcipher *crypto_alloc_ablkcipher( const char *alg_name, u32 type, u32 mask) { type &= ~CRYPTO_ALG_TYPE_MASK; + mask &= ~CRYPTO_ALG_TYPE_MASK; type |= CRYPTO_ALG_TYPE_BLKCIPHER; mask |= CRYPTO_ALG_TYPE_BLKCIPHER_MASK; @@ -554,6 +555,7 @@ static inline int crypto_has_ablkcipher(const char *alg_name, u32 type, u32 mask) { type &= ~CRYPTO_ALG_TYPE_MASK; + mask &= ~CRYPTO_ALG_TYPE_MASK; type |= CRYPTO_ALG_TYPE_BLKCIPHER; mask |= CRYPTO_ALG_TYPE_BLKCIPHER_MASK; @@ -1086,6 +1088,7 @@ static inline struct crypto_hash *crypto_alloc_hash(const char *alg_name, u32 type, u32 mask) { type &= ~CRYPTO_ALG_TYPE_MASK; + mask &= ~CRYPTO_ALG_TYPE_MASK; type |= CRYPTO_ALG_TYPE_HASH; mask |= CRYPTO_ALG_TYPE_HASH_MASK; @@ -1105,6 +1108,7 @@ static inline void crypto_free_hash(struct crypto_hash *tfm) static inline int crypto_has_hash(const char *alg_name, u32 type, u32 mask) { type &= ~CRYPTO_ALG_TYPE_MASK; + mask &= ~CRYPTO_ALG_TYPE_MASK; type |= CRYPTO_ALG_TYPE_HASH; mask |= CRYPTO_ALG_TYPE_HASH_MASK; -- cgit v1.2.3 From 378f4f51f9fdd8df80ea875320e2bf1d7c6e6e77 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 17 Dec 2007 20:07:31 +0800 Subject: [CRYPTO] skcipher: Add crypto_grab_skcipher interface Note: From now on the collective of ablkcipher/blkcipher/givcipher will be known as skcipher, i.e., symmetric key cipher. The name blkcipher has always been much of a misnomer since it supports stream ciphers too. This patch adds the function crypto_grab_skcipher as a new way of getting an ablkcipher spawn. The problem is that previously we did this in two steps, first getting the algorithm and then calling crypto_init_spawn. This meant that each spawn user had to be aware of what type and mask to use for these two steps. This is difficult and also presents a problem when the type/mask changes as they're about to be for IV generators. The new interface does both steps together just like crypto_alloc_ablkcipher. As a side-effect this also allows us to be stronger on type enforcement for spawns. For now this is only done for ablkcipher but it's trivial to extend for other types. This patch also moves the type/mask logic for skcipher into the helpers crypto_skcipher_type and crypto_skcipher_mask. Finally this patch introduces the function crypto_require_sync to determine whether the user is specifically requesting a sync algorithm. Signed-off-by: Herbert Xu --- include/linux/crypto.h | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index ef7642ed3e42..d6962b409489 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -528,16 +528,26 @@ static inline struct crypto_ablkcipher *__crypto_ablkcipher_cast( return (struct crypto_ablkcipher *)tfm; } -static inline struct crypto_ablkcipher *crypto_alloc_ablkcipher( - const char *alg_name, u32 type, u32 mask) +static inline u32 crypto_skcipher_type(u32 type) { type &= ~CRYPTO_ALG_TYPE_MASK; - mask &= ~CRYPTO_ALG_TYPE_MASK; type |= CRYPTO_ALG_TYPE_BLKCIPHER; + return type; +} + +static inline u32 crypto_skcipher_mask(u32 mask) +{ + mask &= ~CRYPTO_ALG_TYPE_MASK; mask |= CRYPTO_ALG_TYPE_BLKCIPHER_MASK; + return mask; +} +static inline struct crypto_ablkcipher *crypto_alloc_ablkcipher( + const char *alg_name, u32 type, u32 mask) +{ return __crypto_ablkcipher_cast( - crypto_alloc_base(alg_name, type, mask)); + crypto_alloc_base(alg_name, crypto_skcipher_type(type), + crypto_skcipher_mask(mask))); } static inline struct crypto_tfm *crypto_ablkcipher_tfm( @@ -554,12 +564,8 @@ static inline void crypto_free_ablkcipher(struct crypto_ablkcipher *tfm) static inline int crypto_has_ablkcipher(const char *alg_name, u32 type, u32 mask) { - type &= ~CRYPTO_ALG_TYPE_MASK; - mask &= ~CRYPTO_ALG_TYPE_MASK; - type |= CRYPTO_ALG_TYPE_BLKCIPHER; - mask |= CRYPTO_ALG_TYPE_BLKCIPHER_MASK; - - return crypto_has_alg(alg_name, type, mask); + return crypto_has_alg(alg_name, crypto_skcipher_type(type), + crypto_skcipher_mask(mask)); } static inline struct ablkcipher_tfm *crypto_ablkcipher_crt( -- cgit v1.2.3 From 61da88e2b800eed2b03834a73c46cc89ad48716d Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 17 Dec 2007 21:51:27 +0800 Subject: [CRYPTO] skcipher: Add givcrypt operations and givcipher type Different block cipher modes have different requirements for intialisation vectors. For example, CBC can use a simple randomly generated IV while modes such as CTR must use an IV generation mechanisms that give a stronger guarantee on the lack of collisions. Furthermore, disk encryption modes have their own IV generation algorithms. Up until now IV generation has been left to the users of the symmetric key cipher API. This is inconvenient as the number of block cipher modes increase because the user needs to be aware of which mode is supposed to be paired with which IV generation algorithm. Therefore it makes sense to integrate the IV generation into the crypto API. This patch takes the first step in that direction by creating two new ablkcipher operations, givencrypt and givdecrypt that generates an IV before performing the actual encryption or decryption. The operations are currently not exposed to the user. That will be done once the underlying functionality has actually been implemented. It also creates the underlying givcipher type. Algorithms that directly generate IVs would use it instead of ablkcipher. All other algorithms (including all existing ones) would generate a givcipher algorithm upon registration. This givcipher algorithm will be constructed from the geniv string that's stored in every algorithm. That string will locate a template which is instantiated by the blkcipher/ablkcipher algorithm in question to give a givcipher algorithm. Signed-off-by: Herbert Xu --- include/linux/crypto.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index d6962b409489..3656a24ea7f0 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -34,6 +34,7 @@ #define CRYPTO_ALG_TYPE_HASH 0x00000003 #define CRYPTO_ALG_TYPE_BLKCIPHER 0x00000004 #define CRYPTO_ALG_TYPE_ABLKCIPHER 0x00000005 +#define CRYPTO_ALG_TYPE_GIVCIPHER 0x00000006 #define CRYPTO_ALG_TYPE_COMPRESS 0x00000008 #define CRYPTO_ALG_TYPE_AEAD 0x00000009 @@ -99,6 +100,7 @@ struct crypto_blkcipher; struct crypto_hash; struct crypto_tfm; struct crypto_type; +struct skcipher_givcrypt_request; typedef void (*crypto_completion_t)(struct crypto_async_request *req, int err); @@ -178,6 +180,8 @@ struct ablkcipher_alg { unsigned int keylen); int (*encrypt)(struct ablkcipher_request *req); int (*decrypt)(struct ablkcipher_request *req); + int (*givencrypt)(struct skcipher_givcrypt_request *req); + int (*givdecrypt)(struct skcipher_givcrypt_request *req); unsigned int min_keysize; unsigned int max_keysize; @@ -320,6 +324,9 @@ struct ablkcipher_tfm { unsigned int keylen); int (*encrypt)(struct ablkcipher_request *req); int (*decrypt)(struct ablkcipher_request *req); + int (*givencrypt)(struct skcipher_givcrypt_request *req); + int (*givdecrypt)(struct skcipher_givcrypt_request *req); + unsigned int ivsize; unsigned int reqsize; }; -- cgit v1.2.3 From 23508e11ab3bb405dca66bf4d77e488bf2b07b0c Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 27 Nov 2007 21:33:24 +0800 Subject: [CRYPTO] skcipher: Added geniv field This patch introduces the geniv field which indicates the default IV generator for each algorithm. It should point to a string that is not freed as long as the algorithm is registered. Signed-off-by: Herbert Xu --- include/linux/crypto.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 3656a24ea7f0..facafa1bd8ca 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -183,6 +183,8 @@ struct ablkcipher_alg { int (*givencrypt)(struct skcipher_givcrypt_request *req); int (*givdecrypt)(struct skcipher_givcrypt_request *req); + const char *geniv; + unsigned int min_keysize; unsigned int max_keysize; unsigned int ivsize; @@ -209,6 +211,8 @@ struct blkcipher_alg { struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes); + const char *geniv; + unsigned int min_keysize; unsigned int max_keysize; unsigned int ivsize; -- cgit v1.2.3 From ecfc43292f68566c144afca966b46b371c26d56c Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 5 Dec 2007 21:08:36 +1100 Subject: [CRYPTO] skcipher: Add skcipher_geniv_alloc/skcipher_geniv_free This patch creates the infrastructure to help the construction of givcipher templates that wrap around existing blkcipher/ablkcipher algorithms by adding an IV generator to them. Signed-off-by: Herbert Xu --- include/linux/crypto.h | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index facafa1bd8ca..fa7afa9b9f4f 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -52,6 +52,12 @@ */ #define CRYPTO_ALG_NEED_FALLBACK 0x00000100 +/* + * This bit is set for symmetric key ciphers that have already been wrapped + * with a generic IV generator to prevent them from being wrapped again. + */ +#define CRYPTO_ALG_GENIV 0x00000200 + /* * Transform masks and values (for crt_flags). */ @@ -331,6 +337,8 @@ struct ablkcipher_tfm { int (*givencrypt)(struct skcipher_givcrypt_request *req); int (*givdecrypt)(struct skcipher_givcrypt_request *req); + struct crypto_ablkcipher *base; + unsigned int ivsize; unsigned int reqsize; }; @@ -541,14 +549,14 @@ static inline struct crypto_ablkcipher *__crypto_ablkcipher_cast( static inline u32 crypto_skcipher_type(u32 type) { - type &= ~CRYPTO_ALG_TYPE_MASK; + type &= ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV); type |= CRYPTO_ALG_TYPE_BLKCIPHER; return type; } static inline u32 crypto_skcipher_mask(u32 mask) { - mask &= ~CRYPTO_ALG_TYPE_MASK; + mask &= ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV); mask |= CRYPTO_ALG_TYPE_BLKCIPHER_MASK; return mask; } @@ -623,7 +631,9 @@ static inline void crypto_ablkcipher_clear_flags(struct crypto_ablkcipher *tfm, static inline int crypto_ablkcipher_setkey(struct crypto_ablkcipher *tfm, const u8 *key, unsigned int keylen) { - return crypto_ablkcipher_crt(tfm)->setkey(tfm, key, keylen); + struct ablkcipher_tfm *crt = crypto_ablkcipher_crt(tfm); + + return crt->setkey(crt->base, key, keylen); } static inline struct crypto_ablkcipher *crypto_ablkcipher_reqtfm( @@ -655,7 +665,7 @@ static inline unsigned int crypto_ablkcipher_reqsize( static inline void ablkcipher_request_set_tfm( struct ablkcipher_request *req, struct crypto_ablkcipher *tfm) { - req->base.tfm = crypto_ablkcipher_tfm(tfm); + req->base.tfm = crypto_ablkcipher_tfm(crypto_ablkcipher_crt(tfm)->base); } static inline struct ablkcipher_request *ablkcipher_request_cast( -- cgit v1.2.3 From b9c55aa475599183d0eab6833ea23e70c52dd24b Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 4 Dec 2007 12:46:48 +1100 Subject: [CRYPTO] skcipher: Create default givcipher instances This patch makes crypto_alloc_ablkcipher/crypto_grab_skcipher always return algorithms that are capable of generating their own IVs through givencrypt and givdecrypt. Each algorithm may specify its default IV generator through the geniv field. For algorithms that do not set the geniv field, the blkcipher layer will pick a default. Currently it's chainiv for synchronous algorithms and eseqiv for asynchronous algorithms. Note that if these wrappers do not work on an algorithm then that algorithm must specify its own geniv or it can't be used at all. Signed-off-by: Herbert Xu --- include/linux/crypto.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index fa7afa9b9f4f..835dcaf3fe4e 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -561,13 +561,8 @@ static inline u32 crypto_skcipher_mask(u32 mask) return mask; } -static inline struct crypto_ablkcipher *crypto_alloc_ablkcipher( - const char *alg_name, u32 type, u32 mask) -{ - return __crypto_ablkcipher_cast( - crypto_alloc_base(alg_name, crypto_skcipher_type(type), - crypto_skcipher_mask(mask))); -} +struct crypto_ablkcipher *crypto_alloc_ablkcipher(const char *alg_name, + u32 type, u32 mask); static inline struct crypto_tfm *crypto_ablkcipher_tfm( struct crypto_ablkcipher *tfm) -- cgit v1.2.3 From 743edf57272fd420348e148bf94f9e48ed6abb70 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 10 Dec 2007 16:18:01 +0800 Subject: [CRYPTO] aead: Add givcrypt operations This patch adds the underlying givcrypt operations for aead and associated support elements. The rationale is identical to that of the skcipher givcrypt operations, i.e., sometimes only the algorithm knows how the IV should be generated. A new request type aead_givcrypt_request is added which contains an embedded aead_request structure with two new elements to support this operation. The new elements are seq and giv. The seq field should contain a strictly increasing 64-bit integer which may be used by certain IV generators as an input value. The giv field will be used to store the generated IV. It does not need to obey the alignment requirements of the algorithm because it's not used during the operation. The existing iv field must still be available as it will be used to store intermediate IVs and the output IV if chaining is desired. Signed-off-by: Herbert Xu --- include/linux/crypto.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 835dcaf3fe4e..7524928bff93 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -106,6 +106,7 @@ struct crypto_blkcipher; struct crypto_hash; struct crypto_tfm; struct crypto_type; +struct aead_givcrypt_request; struct skcipher_givcrypt_request; typedef void (*crypto_completion_t)(struct crypto_async_request *req, int err); @@ -202,6 +203,8 @@ struct aead_alg { int (*setauthsize)(struct crypto_aead *tfm, unsigned int authsize); int (*encrypt)(struct aead_request *req); int (*decrypt)(struct aead_request *req); + int (*givencrypt)(struct aead_givcrypt_request *req); + int (*givdecrypt)(struct aead_givcrypt_request *req); unsigned int ivsize; unsigned int maxauthsize; @@ -348,6 +351,8 @@ struct aead_tfm { unsigned int keylen); int (*encrypt)(struct aead_request *req); int (*decrypt)(struct aead_request *req); + int (*givencrypt)(struct aead_givcrypt_request *req); + int (*givdecrypt)(struct aead_givcrypt_request *req); unsigned int ivsize; unsigned int authsize; unsigned int reqsize; -- cgit v1.2.3 From 5b6d2d7fdf806f2b5a9352416f9e670911fc4748 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 12 Dec 2007 19:23:36 +0800 Subject: [CRYPTO] aead: Add aead_geniv_alloc/aead_geniv_free This patch creates the infrastructure to help the construction of IV generator templates that wrap around AEAD algorithms by adding an IV generator to them. This is useful for AEAD algorithms with no built-in IV generator or to replace their built-in generator. Signed-off-by: Herbert Xu --- include/linux/crypto.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 7524928bff93..639385a9672d 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -206,6 +206,8 @@ struct aead_alg { int (*givencrypt)(struct aead_givcrypt_request *req); int (*givdecrypt)(struct aead_givcrypt_request *req); + const char *geniv; + unsigned int ivsize; unsigned int maxauthsize; }; @@ -353,6 +355,9 @@ struct aead_tfm { int (*decrypt)(struct aead_request *req); int (*givencrypt)(struct aead_givcrypt_request *req); int (*givdecrypt)(struct aead_givcrypt_request *req); + + struct crypto_aead *base; + unsigned int ivsize; unsigned int authsize; unsigned int reqsize; @@ -781,7 +786,9 @@ static inline void crypto_aead_clear_flags(struct crypto_aead *tfm, u32 flags) static inline int crypto_aead_setkey(struct crypto_aead *tfm, const u8 *key, unsigned int keylen) { - return crypto_aead_crt(tfm)->setkey(tfm, key, keylen); + struct aead_tfm *crt = crypto_aead_crt(tfm); + + return crt->setkey(crt->base, key, keylen); } int crypto_aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize); @@ -809,7 +816,7 @@ static inline unsigned int crypto_aead_reqsize(struct crypto_aead *tfm) static inline void aead_request_set_tfm(struct aead_request *req, struct crypto_aead *tfm) { - req->base.tfm = crypto_aead_tfm(tfm); + req->base.tfm = crypto_aead_tfm(crypto_aead_crt(tfm)->base); } static inline struct aead_request *aead_request_alloc(struct crypto_aead *tfm, -- cgit v1.2.3 From d29ce988aeb459203c74f14747f4f77e1829ef78 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 12 Dec 2007 19:24:27 +0800 Subject: [CRYPTO] aead: Create default givcipher instances This patch makes crypto_alloc_aead always return algorithms that is capable of generating their own IVs through givencrypt and givdecrypt. All existing AEAD algorithms already do. New ones must either supply their own or specify a generic IV generator with the geniv field. Signed-off-by: Herbert Xu --- include/linux/crypto.h | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 639385a9672d..0aba10460201 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -723,15 +723,7 @@ static inline struct crypto_aead *__crypto_aead_cast(struct crypto_tfm *tfm) return (struct crypto_aead *)tfm; } -static inline struct crypto_aead *crypto_alloc_aead(const char *alg_name, - u32 type, u32 mask) -{ - type &= ~CRYPTO_ALG_TYPE_MASK; - type |= CRYPTO_ALG_TYPE_AEAD; - mask |= CRYPTO_ALG_TYPE_MASK; - - return __crypto_aead_cast(crypto_alloc_base(alg_name, type, mask)); -} +struct crypto_aead *crypto_alloc_aead(const char *alg_name, u32 type, u32 mask); static inline struct crypto_tfm *crypto_aead_tfm(struct crypto_aead *tfm) { -- cgit v1.2.3 From 6eb7228421c01ba48a6a88a7a5b3e71cfb70d4a9 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 8 Jan 2008 17:16:44 +1100 Subject: [CRYPTO] api: Set default CRYPTO_MINALIGN to unsigned long long Thanks to David Miller for pointing out that the SLAB (or SLOB/SLUB) cache uses the alignment of unsigned long long if the architecture kmalloc/slab alignment macros are not defined. This patch changes the CRYPTO_MINALIGN so that it uses the same default value. Signed-off-by: Herbert Xu --- include/linux/crypto.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 0aba10460201..5e02d1b46370 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -90,13 +90,11 @@ #define CRYPTO_MINALIGN ARCH_KMALLOC_MINALIGN #elif defined(ARCH_SLAB_MINALIGN) #define CRYPTO_MINALIGN ARCH_SLAB_MINALIGN +#else +#define CRYPTO_MINALIGN __alignof__(unsigned long long) #endif -#ifdef CRYPTO_MINALIGN #define CRYPTO_MINALIGN_ATTR __attribute__ ((__aligned__(CRYPTO_MINALIGN))) -#else -#define CRYPTO_MINALIGN_ATTR -#endif struct scatterlist; struct crypto_ablkcipher; -- cgit v1.2.3 From 11c3e689f1c3a73e3af7b0ea767b1b0626da8033 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Mon, 31 Dec 2007 16:37:00 -0600 Subject: [SCSI] block: Introduce new blk_queue_update_dma_alignment interface The purpose of this is to allow stacked alignment settings, with the ultimate queue alignment being set to the largest alignment requirement in the stack. The reason for this is so that the SCSI mid-layer can relax the default alignment requirements (which are basically causing a lot of superfluous copying to go on in the SG_IO interface) while allowing transports, devices or HBAs to add stricter limits if they need them. Acked-by: Jens Axboe Signed-off-by: James Bottomley --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d18ee67b40f8..81e99e516302 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -766,6 +766,7 @@ extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_prep_rq(struct request_queue *, prep_rq_fn *pfn); extern void blk_queue_merge_bvec(struct request_queue *, merge_bvec_fn *); extern void blk_queue_dma_alignment(struct request_queue *, int); +extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); extern int blk_queue_ordered(struct request_queue *, unsigned, prepare_flush_fn *); -- cgit v1.2.3 From ae8d4ee7ff429136c8b482c3b38ed994c021d3fc Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Sun, 4 Nov 2007 22:05:49 -0500 Subject: libata: Disable ATA8-ACS proposed Trusted Computing features by default Historically word 48 in the identify data was used to mean 32bit I/O was supported for VLB IDE etc. ATA8 reassigns this word to the Trusted Computing Group, where it is used for TCG features. This means that an ATA8 TCG drive is going to trigger 32bit I/O on some systems which will be funny. Anyway we need to sort this out ready for ATA8 so: - Reorder the ata.h header a bit so the ata_version function occurs early in it - Make dword_io check the ATA version - Add an ATA8 version checking TCG presence test While we are at it the current drafts have a flaw where it may not be possible to disable TCG features at boot (and opt out of the trusted model) as TCG intends because it relies on presence of a different optional feature (DCS). Handle this in software by refusing the TCG commands if libata.allow_tpm is not set. (We must make it possible as some environments such as proprietary VDR devices will doubtless want to use it to lock up content) Finally as with CPRM print a warning so that the user knows they may not be able to full access and use the device. Signed-off-by: Alan Cox --- include/linux/ata.h | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index e672e80202a8..3fbe6d7784ab 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -379,7 +379,6 @@ struct ata_taskfile { #define ata_id_has_ncq(id) ((id)[76] & (1 << 8)) #define ata_id_queue_depth(id) (((id)[75] & 0x1f) + 1) #define ata_id_removeable(id) ((id)[0] & (1 << 7)) -#define ata_id_has_dword_io(id) ((id)[48] & (1 << 0)) #define ata_id_has_atapi_AN(id) \ ( (((id)[76] != 0x0000) && ((id)[76] != 0xffff)) && \ ((id)[78] & (1 << 5)) ) @@ -415,6 +414,7 @@ static inline bool ata_id_has_dipm(const u16 *id) return val & (1 << 3); } + static inline int ata_id_has_fua(const u16 *id) { if ((id[84] & 0xC000) != 0x4000) @@ -519,6 +519,26 @@ static inline int ata_id_is_sata(const u16 *id) return ata_id_major_version(id) >= 5 && id[93] == 0; } +static inline int ata_id_has_tpm(const u16 *id) +{ + /* The TPM bits are only valid on ATA8 */ + if (ata_id_major_version(id) < 8) + return 0; + if ((id[48] & 0xC000) != 0x4000) + return 0; + return id[48] & (1 << 0); +} + +static inline int ata_id_has_dword_io(const u16 *id) +{ + /* ATA 8 reuses this flag for "trusted" computing */ + if (ata_id_major_version(id) > 7) + return 0; + if (id[48] & (1 << 0)) + return 1; + return 0; +} + static inline int ata_id_current_chs_valid(const u16 *id) { /* For ATA-1 devices, if the INITIALIZE DEVICE PARAMETERS command -- cgit v1.2.3 From f20ded38aa54b92dd0af32578b8916d0aa2d9e05 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 27 Nov 2007 19:28:52 +0900 Subject: libata: rearrange ATA_DFLAG_* Area for DFLAGs which are cleared on INIT is full. Extend it by 8 bits. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 124033cb5e9b..ca347b018649 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -143,10 +143,10 @@ enum { ATA_DFLAG_NCQ_OFF = (1 << 13), /* device limited to non-NCQ mode */ ATA_DFLAG_SPUNDOWN = (1 << 14), /* XXX: for spindown_compat */ ATA_DFLAG_SLEEPING = (1 << 15), /* device is sleeping */ - ATA_DFLAG_INIT_MASK = (1 << 16) - 1, + ATA_DFLAG_INIT_MASK = (1 << 24) - 1, - ATA_DFLAG_DETACH = (1 << 16), - ATA_DFLAG_DETACHED = (1 << 17), + ATA_DFLAG_DETACH = (1 << 24), + ATA_DFLAG_DETACHED = (1 << 25), ATA_DEV_UNKNOWN = 0, /* unknown device */ ATA_DEV_ATA = 1, /* ATA device */ -- cgit v1.2.3 From 405e66b38797875e80669eaf72d313dbb76533c3 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 27 Nov 2007 19:28:53 +0900 Subject: libata: implement protocol tests Implement protocol tests - ata_is_atapi(), ata_is_nodata(), ata_is_pio(), ata_is_dma(), ata_is_ncq() and ata_is_data() and use them to replace is_atapi_taskfile() and hard coded protocol tests. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/ata.h | 71 +++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 64 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index 3fbe6d7784ab..43fecf62773a 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -324,6 +324,13 @@ enum { ATA_TFLAG_LBA = (1 << 4), /* enable LBA */ ATA_TFLAG_FUA = (1 << 5), /* enable FUA */ ATA_TFLAG_POLLING = (1 << 6), /* set nIEN to 1 and use polling */ + + /* protocol flags */ + ATA_PROT_FLAG_PIO = (1 << 0), /* is PIO */ + ATA_PROT_FLAG_DMA = (1 << 1), /* is DMA */ + ATA_PROT_FLAG_DATA = ATA_PROT_FLAG_PIO | ATA_PROT_FLAG_DMA, + ATA_PROT_FLAG_NCQ = (1 << 2), /* is NCQ */ + ATA_PROT_FLAG_ATAPI = (1 << 3), /* is ATAPI */ }; enum ata_tf_protocols { @@ -373,6 +380,63 @@ struct ata_taskfile { u8 command; /* IO operation */ }; +/* + * protocol tests + */ +static inline unsigned int ata_prot_flags(u8 prot) +{ + switch (prot) { + case ATA_PROT_NODATA: + return 0; + case ATA_PROT_PIO: + return ATA_PROT_FLAG_PIO; + case ATA_PROT_DMA: + return ATA_PROT_FLAG_DMA; + case ATA_PROT_NCQ: + return ATA_PROT_FLAG_DMA | ATA_PROT_FLAG_NCQ; + case ATA_PROT_ATAPI_NODATA: + return ATA_PROT_FLAG_ATAPI; + case ATA_PROT_ATAPI: + return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_PIO; + case ATA_PROT_ATAPI_DMA: + return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_DMA; + } + return 0; +} + +static inline int ata_is_atapi(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_ATAPI; +} + +static inline int ata_is_nodata(u8 prot) +{ + return !(ata_prot_flags(prot) & ATA_PROT_FLAG_DATA); +} + +static inline int ata_is_pio(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_PIO; +} + +static inline int ata_is_dma(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_DMA; +} + +static inline int ata_is_ncq(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_NCQ; +} + +static inline int ata_is_data(u8 prot) +{ + return ata_prot_flags(prot) & ATA_PROT_FLAG_DATA; +} + +/* + * id tests + */ #define ata_id_is_ata(id) (((id)[0] & (1 << 15)) == 0) #define ata_id_has_lba(id) ((id)[49] & (1 << 9)) #define ata_id_has_dma(id) ((id)[49] & (1 << 8)) @@ -594,13 +658,6 @@ static inline int atapi_command_packet_set(const u16 *dev_id) return (dev_id[0] >> 8) & 0x1f; } -static inline int is_atapi_taskfile(const struct ata_taskfile *tf) -{ - return (tf->protocol == ATA_PROT_ATAPI) || - (tf->protocol == ATA_PROT_ATAPI_NODATA) || - (tf->protocol == ATA_PROT_ATAPI_DMA); -} - static inline int is_multi_taskfile(struct ata_taskfile *tf) { return (tf->command == ATA_CMD_READ_MULTI) || -- cgit v1.2.3 From 3884f7b0a8382b89d8ca5da23bd98e3e15fc805b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 27 Nov 2007 19:28:56 +0900 Subject: libata: clean up EH speed down implementation Clean up EH speed down implementation. * is_io boolean variable is replaced eflags. is_io is ATA_EFLAG_IS_IO. * Error categories now have names. * Better comments. * Reorder 5min and 10min rules in ata_eh_speed_down_verdict() * Use local variable @link to cache @dev->link in ata_eh_speed_down() These changes are to improve readability and ease further changes. This patch doesn't introduce any behavior change. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index ca347b018649..74f1255e2524 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -482,7 +482,7 @@ struct ata_port_stats { }; struct ata_ering_entry { - int is_io; + unsigned int eflags; unsigned int err_mask; u64 timestamp; }; -- cgit v1.2.3 From 00115e0f5bc3bfdf3f3855ad89c8895f10458f92 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 27 Nov 2007 19:28:58 +0900 Subject: libata: implement ATA_DFLAG_DUBIOUS_XFER ATA_DFLAG_DUBIOUS_XFER is set whenever data transfer speed or method changes and gets cleared when data transfer command succeeds in the newly configured transfer mode. This will be used to improve speed down logic. Signed-off-by: Tejun Heo --- include/linux/libata.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 74f1255e2524..131fb6625e14 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -143,6 +143,7 @@ enum { ATA_DFLAG_NCQ_OFF = (1 << 13), /* device limited to non-NCQ mode */ ATA_DFLAG_SPUNDOWN = (1 << 14), /* XXX: for spindown_compat */ ATA_DFLAG_SLEEPING = (1 << 15), /* device is sleeping */ + ATA_DFLAG_DUBIOUS_XFER = (1 << 16), /* data transfer not verified */ ATA_DFLAG_INIT_MASK = (1 << 24) - 1, ATA_DFLAG_DETACH = (1 << 24), @@ -560,6 +561,8 @@ struct ata_eh_context { int tries[ATA_MAX_DEVICES]; unsigned int classes[ATA_MAX_DEVICES]; unsigned int did_probe_mask; + unsigned int saved_ncq_enabled; + u8 saved_xfer_mode[ATA_MAX_DEVICES]; }; struct ata_acpi_drive -- cgit v1.2.3 From 6357357cae7794dcb89cace758108dec612e7ed5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 27 Nov 2007 19:43:39 +0900 Subject: libata: export xfermode / PATA timing related functions Export the following xfermode related functions. * ata_pack_xfermask() * ata_unpack_xfermask() * ata_xfer_mask2mode() * ata_xfer_mode2mask() * ata_xfer_mode2shift() * ata_mode_string() * ata_id_xfermask() * ata_timing_find_mode() These functions will be used later by LLD updates. While at it, change unsigned short @speed to u8 @xfer_mode in ata_timing_find_mode() for consistency. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 131fb6625e14..083dd77b120d 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -851,6 +851,15 @@ extern void ata_tf_read(struct ata_port *ap, struct ata_taskfile *tf); extern void ata_tf_to_fis(const struct ata_taskfile *tf, u8 pmp, int is_cmd, u8 *fis); extern void ata_tf_from_fis(const u8 *fis, struct ata_taskfile *tf); +extern unsigned int ata_pack_xfermask(unsigned int pio_mask, + unsigned int mwdma_mask, unsigned int udma_mask); +extern void ata_unpack_xfermask(unsigned int xfer_mask, unsigned int *pio_mask, + unsigned int *mwdma_mask, unsigned int *udma_mask); +extern u8 ata_xfer_mask2mode(unsigned int xfer_mask); +extern unsigned int ata_xfer_mode2mask(u8 xfer_mode); +extern int ata_xfer_mode2shift(unsigned int xfer_mode); +extern const char *ata_mode_string(unsigned int xfer_mask); +extern unsigned int ata_id_xfermask(const u16 *id); extern void ata_noop_dev_select(struct ata_port *ap, unsigned int device); extern void ata_std_dev_select(struct ata_port *ap, unsigned int device); extern u8 ata_check_status(struct ata_port *ap); @@ -920,6 +929,7 @@ extern int ata_cable_unknown(struct ata_port *ap); */ extern unsigned int ata_pio_need_iordy(const struct ata_device *); +extern const struct ata_timing *ata_timing_find_mode(u8 xfer_mode); extern int ata_timing_compute(struct ata_device *, unsigned short, struct ata_timing *, int, int); extern void ata_timing_merge(const struct ata_timing *, -- cgit v1.2.3 From 70cd071e4ecc06c985189665af75c108601fd5a3 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 27 Nov 2007 19:43:40 +0900 Subject: libata: clean up xfermode / PATA timing related stuff * s/ATA_BITS_(PIO|MWDMA|UDMA)/ATA_NR_\1_MODES/g * Consistently use 0xff to indicate invalid transfer mode (0x00 is valid for PIO_SLOW). * Make ata_xfer_mode2mask() return proper mode mask instead of just the highest bit. * Sort ata_timing table in increasing xfermode order and update ata_timing_find_mode() accordingly. This patch doesn't introduce any behavior change. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 083dd77b120d..e2ed3bac8c5b 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -269,17 +269,20 @@ enum { /* encoding various smaller bitmaps into a single * unsigned int bitmap */ - ATA_BITS_PIO = 7, - ATA_BITS_MWDMA = 5, - ATA_BITS_UDMA = 8, + ATA_NR_PIO_MODES = 7, + ATA_NR_MWDMA_MODES = 5, + ATA_NR_UDMA_MODES = 8, ATA_SHIFT_PIO = 0, - ATA_SHIFT_MWDMA = ATA_SHIFT_PIO + ATA_BITS_PIO, - ATA_SHIFT_UDMA = ATA_SHIFT_MWDMA + ATA_BITS_MWDMA, - - ATA_MASK_PIO = ((1 << ATA_BITS_PIO) - 1) << ATA_SHIFT_PIO, - ATA_MASK_MWDMA = ((1 << ATA_BITS_MWDMA) - 1) << ATA_SHIFT_MWDMA, - ATA_MASK_UDMA = ((1 << ATA_BITS_UDMA) - 1) << ATA_SHIFT_UDMA, + ATA_SHIFT_MWDMA = ATA_SHIFT_PIO + ATA_NR_PIO_MODES, + ATA_SHIFT_UDMA = ATA_SHIFT_MWDMA + ATA_NR_MWDMA_MODES, + + ATA_MASK_PIO = ((1 << ATA_NR_PIO_MODES) - 1) + << ATA_SHIFT_PIO, + ATA_MASK_MWDMA = ((1 << ATA_NR_MWDMA_MODES) - 1) + << ATA_SHIFT_MWDMA, + ATA_MASK_UDMA = ((1 << ATA_NR_UDMA_MODES) - 1) + << ATA_SHIFT_UDMA, /* size of buffer to pad xfers ending on unaligned boundaries */ ATA_DMA_PAD_SZ = 4, -- cgit v1.2.3 From 9d3501ab962b1506d93974faf8509251b4a85fbc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 27 Nov 2007 19:43:41 +0900 Subject: libata: kill ata_id_to_dma_mode() ata_id_to_dma_mode() isn't quite generic. The function is basically privately implemented ata_id_xfermask() combined with hardcoded mode printing and configuration which are specific to ata_generic. Kill the function and open code it in generic_set_mode() using generic xfermode handling functions. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index e2ed3bac8c5b..d33702fe78f9 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -890,7 +890,6 @@ extern void ata_id_string(const u16 *id, unsigned char *s, unsigned int ofs, unsigned int len); extern void ata_id_c_string(const u16 *id, unsigned char *s, unsigned int ofs, unsigned int len); -extern void ata_id_to_dma_mode(struct ata_device *dev, u8 unknown); extern void ata_bmdma_setup(struct ata_queued_cmd *qc); extern void ata_bmdma_start(struct ata_queued_cmd *qc); extern void ata_bmdma_stop(struct ata_queued_cmd *qc); -- cgit v1.2.3 From 7dc951aefdc1dc20228691b04867fb6195864d67 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 27 Nov 2007 19:43:42 +0900 Subject: libata: xfer_mask is unsigned long not unsigned int Jeff says xfer_mask is unsigned long not unsigned int. Convert all xfermask fields and handling functions to deal with unsigned longs. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 46 +++++++++++++++++++++++++--------------------- 1 file changed, 25 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index d33702fe78f9..d9eb20c67bb6 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -267,7 +267,7 @@ enum { PORT_DISABLED = 2, /* encoding various smaller bitmaps into a single - * unsigned int bitmap + * unsigned long bitmap */ ATA_NR_PIO_MODES = 7, ATA_NR_MWDMA_MODES = 5, @@ -277,13 +277,6 @@ enum { ATA_SHIFT_MWDMA = ATA_SHIFT_PIO + ATA_NR_PIO_MODES, ATA_SHIFT_UDMA = ATA_SHIFT_MWDMA + ATA_NR_MWDMA_MODES, - ATA_MASK_PIO = ((1 << ATA_NR_PIO_MODES) - 1) - << ATA_SHIFT_PIO, - ATA_MASK_MWDMA = ((1 << ATA_NR_MWDMA_MODES) - 1) - << ATA_SHIFT_MWDMA, - ATA_MASK_UDMA = ((1 << ATA_NR_UDMA_MODES) - 1) - << ATA_SHIFT_UDMA, - /* size of buffer to pad xfers ending on unaligned boundaries */ ATA_DMA_PAD_SZ = 4, ATA_DMA_PAD_BUF_SZ = ATA_DMA_PAD_SZ * ATA_MAX_QUEUE, @@ -355,6 +348,15 @@ enum { ATA_DMA_MASK_CFA = (1 << 2), /* DMA on CF Card */ }; +enum ata_xfer_mask { + ATA_MASK_PIO = ((1LU << ATA_NR_PIO_MODES) - 1) + << ATA_SHIFT_PIO, + ATA_MASK_MWDMA = ((1LU << ATA_NR_MWDMA_MODES) - 1) + << ATA_SHIFT_MWDMA, + ATA_MASK_UDMA = ((1LU << ATA_NR_UDMA_MODES) - 1) + << ATA_SHIFT_UDMA, +}; + enum hsm_task_states { HSM_ST_IDLE, /* no command on going */ HSM_ST_FIRST, /* (waiting the device to) @@ -526,9 +528,9 @@ struct ata_device { unsigned int cdb_len; /* per-dev xfer mask */ - unsigned int pio_mask; - unsigned int mwdma_mask; - unsigned int udma_mask; + unsigned long pio_mask; + unsigned long mwdma_mask; + unsigned long udma_mask; /* for CHS addressing */ u16 cylinders; /* Number of cylinders */ @@ -854,15 +856,16 @@ extern void ata_tf_read(struct ata_port *ap, struct ata_taskfile *tf); extern void ata_tf_to_fis(const struct ata_taskfile *tf, u8 pmp, int is_cmd, u8 *fis); extern void ata_tf_from_fis(const u8 *fis, struct ata_taskfile *tf); -extern unsigned int ata_pack_xfermask(unsigned int pio_mask, - unsigned int mwdma_mask, unsigned int udma_mask); -extern void ata_unpack_xfermask(unsigned int xfer_mask, unsigned int *pio_mask, - unsigned int *mwdma_mask, unsigned int *udma_mask); -extern u8 ata_xfer_mask2mode(unsigned int xfer_mask); -extern unsigned int ata_xfer_mode2mask(u8 xfer_mode); -extern int ata_xfer_mode2shift(unsigned int xfer_mode); -extern const char *ata_mode_string(unsigned int xfer_mask); -extern unsigned int ata_id_xfermask(const u16 *id); +extern unsigned long ata_pack_xfermask(unsigned long pio_mask, + unsigned long mwdma_mask, unsigned long udma_mask); +extern void ata_unpack_xfermask(unsigned long xfer_mask, + unsigned long *pio_mask, unsigned long *mwdma_mask, + unsigned long *udma_mask); +extern u8 ata_xfer_mask2mode(unsigned long xfer_mask); +extern unsigned long ata_xfer_mode2mask(u8 xfer_mode); +extern int ata_xfer_mode2shift(unsigned long xfer_mode); +extern const char *ata_mode_string(unsigned long xfer_mask); +extern unsigned long ata_id_xfermask(const u16 *id); extern void ata_noop_dev_select(struct ata_port *ap, unsigned int device); extern void ata_std_dev_select(struct ata_port *ap, unsigned int device); extern u8 ata_check_status(struct ata_port *ap); @@ -1001,7 +1004,8 @@ extern int ata_pci_prepare_sff_host(struct pci_dev *pdev, const struct ata_port_info * const * ppi, struct ata_host **r_host); extern int pci_test_config_bits(struct pci_dev *pdev, const struct pci_bits *bits); -extern unsigned long ata_pci_default_filter(struct ata_device *, unsigned long); +extern unsigned long ata_pci_default_filter(struct ata_device *dev, + unsigned long xfer_mask); #endif /* CONFIG_PCI */ /* -- cgit v1.2.3 From c88f90c3779cd5e710f2acdf59ad2bd0380de98d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 27 Nov 2007 19:43:48 +0900 Subject: libata: add ATA_CBL_PATA_IGN ATA_CBL_PATA_UNK indicates that the cable type can't be determined from the host side and might be either 80c or 40c. libata applies drive or other generic limit in this case. However, there are controllers where both host and drive side detections are misimplemented and the driver has to rely solely on private method - peeking BIOS or ACPI configuration or using some other private mechanism. This patch adds ATA_CBL_PATA_IGN which tells libata to ignore the cable type completely and just let the LLD determine the transfer mode via host transfer mode masks and ->mode_filter(). Signed-off-by: Tejun Heo Cc: Alan Cox Signed-off-by: Jeff Garzik --- include/linux/ata.h | 7 ++++--- include/linux/libata.h | 1 + 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index 43fecf62773a..c17e9404c88d 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -286,9 +286,10 @@ enum { ATA_CBL_NONE = 0, ATA_CBL_PATA40 = 1, ATA_CBL_PATA80 = 2, - ATA_CBL_PATA40_SHORT = 3, /* 40 wire cable to high UDMA spec */ - ATA_CBL_PATA_UNK = 4, - ATA_CBL_SATA = 5, + ATA_CBL_PATA40_SHORT = 3, /* 40 wire cable to high UDMA spec */ + ATA_CBL_PATA_UNK = 4, /* don't know, maybe 80c? */ + ATA_CBL_PATA_IGN = 5, /* don't know, ignore cable handling */ + ATA_CBL_SATA = 6, /* SATA Status and Control Registers */ SCR_STATUS = 0, diff --git a/include/linux/libata.h b/include/linux/libata.h index d9eb20c67bb6..bdb7c6e13993 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -927,6 +927,7 @@ extern u8 ata_irq_on(struct ata_port *ap); extern int ata_cable_40wire(struct ata_port *ap); extern int ata_cable_80wire(struct ata_port *ap); extern int ata_cable_sata(struct ata_port *ap); +extern int ata_cable_ignore(struct ata_port *ap); extern int ata_cable_unknown(struct ata_port *ap); /* -- cgit v1.2.3 From 7c77fa4d51b1480bcec2e898c94d6912fe063c16 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Dec 2007 16:33:03 +0900 Subject: libata: separate out ata_acpi_gtm_xfermask() from pacpi_discover_modes() Finding out matching transfer mode from ACPI GTM values is useful for other purposes too. Separate out the function and timing tables from pata_acpi::pacpi_discover_modes(). Other than checking shared-configuration bit after doing ata_acpi_gtm() in pacpi_discover_modes() which should be safe, this patch doesn't introduce any behavior change. Signed-off-by: Tejun Heo Cc: Alan Cox Signed-off-by: Jeff Garzik --- include/linux/libata.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index bdb7c6e13993..8022e5b2224d 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -961,6 +961,10 @@ enum { /* libata-acpi.c */ #ifdef CONFIG_ATA_ACPI +extern const unsigned int ata_acpi_pio_cycle[7]; +extern const unsigned int ata_acpi_mwdma_cycle[5]; +extern const unsigned int ata_acpi_udma_cycle[7]; + static inline const struct ata_acpi_gtm *ata_acpi_init_gtm(struct ata_port *ap) { if (ap->pflags & ATA_PFLAG_INIT_GTM_VALID) @@ -970,12 +974,33 @@ static inline const struct ata_acpi_gtm *ata_acpi_init_gtm(struct ata_port *ap) extern int ata_acpi_cbl_80wire(struct ata_port *ap); int ata_acpi_stm(struct ata_port *ap, const struct ata_acpi_gtm *stm); int ata_acpi_gtm(struct ata_port *ap, struct ata_acpi_gtm *stm); +unsigned long ata_acpi_gtm_xfermask(struct ata_device *dev, + const struct ata_acpi_gtm *gtm); + #else static inline const struct ata_acpi_gtm *ata_acpi_init_gtm(struct ata_port *ap) { return NULL; } static inline int ata_acpi_cbl_80wire(struct ata_port *ap) { return 0; } + +static inline int ata_acpi_stm(const struct ata_port *ap, + struct ata_acpi_gtm *stm) +{ + return -ENOSYS; +} + +static inline int ata_acpi_gtm(const struct ata_port *ap, + struct ata_acpi_gtm *stm) +{ + return -ENOSYS; +} + +static inline unsigned int ata_acpi_gtm_xfermask(struct ata_device *dev, + const struct ata_acpi_gtm *gtm) +{ + return 0; +} #endif #ifdef CONFIG_PCI -- cgit v1.2.3 From a0f79b929acaba10d4780acd2543eff20bf4b5b0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Dec 2007 16:33:05 +0900 Subject: libata: implement ata_timing_cycle2mode() and use it in libata-acpi and pata_acpi libata-acpi is using separate timing tables for transfer modes although libata-core has the complete ata_timing table. Implement ata_timing_cycle2mode() to look for matching mode given transfer type and cycle duration and use it in libata-acpi and pata_acpi to replace private timing tables. Signed-off-by: Tejun Heo Cc: Alan Cox Signed-off-by: Jeff Garzik --- include/linux/libata.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 8022e5b2224d..8ede93b5c7a6 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -941,6 +941,7 @@ extern int ata_timing_compute(struct ata_device *, unsigned short, extern void ata_timing_merge(const struct ata_timing *, const struct ata_timing *, struct ata_timing *, unsigned int); +extern u8 ata_timing_cycle2mode(unsigned int xfer_shift, int cycle); enum { ATA_TIMING_SETUP = (1 << 0), @@ -961,10 +962,6 @@ enum { /* libata-acpi.c */ #ifdef CONFIG_ATA_ACPI -extern const unsigned int ata_acpi_pio_cycle[7]; -extern const unsigned int ata_acpi_mwdma_cycle[5]; -extern const unsigned int ata_acpi_udma_cycle[7]; - static inline const struct ata_acpi_gtm *ata_acpi_init_gtm(struct ata_port *ap) { if (ap->pflags & ATA_PFLAG_INIT_GTM_VALID) -- cgit v1.2.3 From 021ee9a6da1cfc57f6a6c769c3c898bdd4753108 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Dec 2007 16:33:06 +0900 Subject: libata: reimplement ata_acpi_cbl_80wire() using ata_acpi_gtm_xfermask() Reimplement ata_acpi_cbl_80wire() using ata_acpi_gtm_xfermask() and while at it relocate the function below ata_acpi_gtm_xfermask(). New ata_acpi_cbl_80wire() implementation takes @gtm, in both pata_via and pata_amd, use the initial GTM value. Both are trying to peek initial BIOS configuration, so using initial caching value makes sense. This fixes ACPI part of cable detection in pata_amd which previously always returned 0 because configuring PIO0 during reset clears DMA configuration. Signed-off-by: Tejun Heo Cc: Alan Cox Signed-off-by: Jeff Garzik --- include/linux/libata.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 8ede93b5c7a6..cc4eaef6f889 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -968,18 +968,16 @@ static inline const struct ata_acpi_gtm *ata_acpi_init_gtm(struct ata_port *ap) return &ap->__acpi_init_gtm; return NULL; } -extern int ata_acpi_cbl_80wire(struct ata_port *ap); int ata_acpi_stm(struct ata_port *ap, const struct ata_acpi_gtm *stm); int ata_acpi_gtm(struct ata_port *ap, struct ata_acpi_gtm *stm); unsigned long ata_acpi_gtm_xfermask(struct ata_device *dev, const struct ata_acpi_gtm *gtm); - +int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm); #else static inline const struct ata_acpi_gtm *ata_acpi_init_gtm(struct ata_port *ap) { return NULL; } -static inline int ata_acpi_cbl_80wire(struct ata_port *ap) { return 0; } static inline int ata_acpi_stm(const struct ata_port *ap, struct ata_acpi_gtm *stm) @@ -998,6 +996,12 @@ static inline unsigned int ata_acpi_gtm_xfermask(struct ata_device *dev, { return 0; } + +static inline int ata_acpi_cbl_80wire(struct ata_port *ap, + const struct ata_acpi_gtm *gtm) +{ + return 0; +} #endif #ifdef CONFIG_PCI -- cgit v1.2.3 From 537b53c1692960b8b3b0324e886fbe48cb9e5c00 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 5 Dec 2007 16:43:04 +0900 Subject: cdrom: add more GPCMD_* constants Add GPCMD_* constants for READ_BUFFER, WRITE_12 and WRITE_BUFFER for completeness. These will be used libata. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/cdrom.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index c6d3e22c0624..fcdc11b9609b 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -451,6 +451,7 @@ struct cdrom_generic_command #define GPCMD_PREVENT_ALLOW_MEDIUM_REMOVAL 0x1e #define GPCMD_READ_10 0x28 #define GPCMD_READ_12 0xa8 +#define GPCMD_READ_BUFFER 0x3c #define GPCMD_READ_BUFFER_CAPACITY 0x5c #define GPCMD_READ_CDVD_CAPACITY 0x25 #define GPCMD_READ_CD 0xbe @@ -480,7 +481,9 @@ struct cdrom_generic_command #define GPCMD_TEST_UNIT_READY 0x00 #define GPCMD_VERIFY_10 0x2f #define GPCMD_WRITE_10 0x2a +#define GPCMD_WRITE_12 0xaa #define GPCMD_WRITE_AND_VERIFY_10 0x2e +#define GPCMD_WRITE_BUFFER 0x3b /* This is listed as optional in ATAPI 2.6, but is (curiously) * missing from Mt. Fuji, Table 57. It _is_ mentioned in Mt. Fuji * Table 377 as an MMC command for SCSi devices though... Most ATAPI -- cgit v1.2.3 From 0dc36888d4422140f9eaf50f24953ec109f750a3 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Dec 2007 16:34:43 -0500 Subject: libata: rename ATA_PROT_ATAPI_* to ATAPI_PROT_* ATA_PROT_ATAPI_* are ugly and naming schemes between ATA_PROT_* and ATA_PROT_ATAPI_* are inconsistent causing confusion. Rename them to ATAPI_PROT_* and make them consistent with ATA counterpart. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/ata.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index c17e9404c88d..bc55471a4b2c 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -341,9 +341,9 @@ enum ata_tf_protocols { ATA_PROT_PIO, /* PIO data xfer */ ATA_PROT_DMA, /* DMA */ ATA_PROT_NCQ, /* NCQ */ - ATA_PROT_ATAPI, /* packet command, PIO data xfer*/ - ATA_PROT_ATAPI_NODATA, /* packet command, no data */ - ATA_PROT_ATAPI_DMA, /* packet command with special DMA sauce */ + ATAPI_PROT_NODATA, /* packet command, no data */ + ATAPI_PROT_PIO, /* packet command, PIO data xfer*/ + ATAPI_PROT_DMA, /* packet command with special DMA sauce */ }; enum ata_ioctls { @@ -395,11 +395,11 @@ static inline unsigned int ata_prot_flags(u8 prot) return ATA_PROT_FLAG_DMA; case ATA_PROT_NCQ: return ATA_PROT_FLAG_DMA | ATA_PROT_FLAG_NCQ; - case ATA_PROT_ATAPI_NODATA: + case ATAPI_PROT_NODATA: return ATA_PROT_FLAG_ATAPI; - case ATA_PROT_ATAPI: + case ATAPI_PROT_PIO: return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_PIO; - case ATA_PROT_ATAPI_DMA: + case ATAPI_PROT_DMA: return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_DMA; } return 0; -- cgit v1.2.3 From ceb0c642624f634c5b4f46b0e22df19be87a2e53 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 5 Dec 2007 16:43:06 +0900 Subject: libata: add ATAPI_* cmd types and implement atapi_cmd_type() Add ATAPI command types - ATAPI_READ, WRITE, RW_BUF, READ_CD and MISC, and implement atapi_cmd_type() which takes SCSI opcode and returns to which class the opcode belongs. This will be used later to improve ATAPI handling. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index cc4eaef6f889..03afcd63202d 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -35,6 +35,7 @@ #include #include #include +#include /* * Define if arch has non-standard setup. This is a _PCI_ standard @@ -346,6 +347,12 @@ enum { ATA_DMA_MASK_ATA = (1 << 0), /* DMA on ATA Disk */ ATA_DMA_MASK_ATAPI = (1 << 1), /* DMA on ATAPI */ ATA_DMA_MASK_CFA = (1 << 2), /* DMA on CF Card */ + + /* ATAPI command types */ + ATAPI_READ = 0, /* READs */ + ATAPI_WRITE = 1, /* WRITEs */ + ATAPI_READ_CD = 2, /* READ CD [MSF] */ + ATAPI_MISC = 3, /* the rest */ }; enum ata_xfer_mask { @@ -1408,6 +1415,27 @@ static inline int ata_try_flush_cache(const struct ata_device *dev) ata_id_has_flush_ext(dev->id); } +static inline int atapi_cmd_type(u8 opcode) +{ + switch (opcode) { + case GPCMD_READ_10: + case GPCMD_READ_12: + return ATAPI_READ; + + case GPCMD_WRITE_10: + case GPCMD_WRITE_12: + case GPCMD_WRITE_AND_VERIFY_10: + return ATAPI_WRITE; + + case GPCMD_READ_CD: + case GPCMD_READ_CD_MSF: + return ATAPI_READ_CD; + + default: + return ATAPI_MISC; + } +} + static inline unsigned int ac_err_mask(u8 status) { if (status & (ATA_BUSY | ATA_DRQ)) -- cgit v1.2.3 From 55dba3120fbcbea6800f9a18503d25f73212a347 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 5 Dec 2007 16:43:07 +0900 Subject: libata: update ->data_xfer hook for ATAPI Depending on how many bytes are transferred as a unit, PIO data transfer may consume more bytes than requested. Knowing how much data is consumed is necessary to determine how much is left for draining. This patch update ->data_xfer such that it returns the number of consumed bytes. While at it, it also makes the following changes. * s/adev/dev/ * use READ/WRITE constants for rw indication * misc clean ups Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 03afcd63202d..7fa96cb4f6db 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -701,7 +701,8 @@ struct ata_port_operations { void (*bmdma_setup) (struct ata_queued_cmd *qc); void (*bmdma_start) (struct ata_queued_cmd *qc); - void (*data_xfer) (struct ata_device *, unsigned char *, unsigned int, int); + unsigned int (*data_xfer) (struct ata_device *dev, unsigned char *buf, + unsigned int buflen, int rw); int (*qc_defer) (struct ata_queued_cmd *qc); void (*qc_prep) (struct ata_queued_cmd *qc); @@ -881,10 +882,10 @@ extern void ata_exec_command(struct ata_port *ap, const struct ata_taskfile *tf) extern int ata_port_start(struct ata_port *ap); extern int ata_sff_port_start(struct ata_port *ap); extern irqreturn_t ata_interrupt(int irq, void *dev_instance); -extern void ata_data_xfer(struct ata_device *adev, unsigned char *buf, - unsigned int buflen, int write_data); -extern void ata_data_xfer_noirq(struct ata_device *adev, unsigned char *buf, - unsigned int buflen, int write_data); +extern unsigned int ata_data_xfer(struct ata_device *dev, + unsigned char *buf, unsigned int buflen, int rw); +extern unsigned int ata_data_xfer_noirq(struct ata_device *dev, + unsigned char *buf, unsigned int buflen, int rw); extern int ata_std_qc_defer(struct ata_queued_cmd *qc); extern void ata_dumb_qc_prep(struct ata_queued_cmd *qc); extern void ata_qc_prep(struct ata_queued_cmd *qc); -- cgit v1.2.3 From 001102d7859be0e7f7b9f2d62b841f2c0f9c2640 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 5 Dec 2007 16:43:09 +0900 Subject: libata: kill non-sg DMA interface With atapi_request_sense() converted to use sg, there's no user of non-sg interface. Kill non-sg interface. * ATA_QCFLAG_SINGLE and ATA_QCFLAG_SG are removed. ATA_QCFLAG_DMAMAP is used instead. (this way no LLD change is necessary) * qc->buf_virt is removed. * ata_sg_init_one() and ata_sg_setup_one() are removed. Signed-off-by: Tejun Heo Cc: Rusty Russel Signed-off-by: Jeff Garzik --- include/linux/libata.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 7fa96cb4f6db..acd90ad78417 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -219,9 +219,7 @@ enum { /* struct ata_queued_cmd flags */ ATA_QCFLAG_ACTIVE = (1 << 0), /* cmd not yet ack'd to scsi lyer */ - ATA_QCFLAG_SG = (1 << 1), /* have s/g table? */ - ATA_QCFLAG_SINGLE = (1 << 2), /* no s/g, just a single buffer */ - ATA_QCFLAG_DMAMAP = ATA_QCFLAG_SG | ATA_QCFLAG_SINGLE, + ATA_QCFLAG_DMAMAP = (1 << 1), /* SG table is DMA mapped */ ATA_QCFLAG_IO = (1 << 3), /* standard IO command */ ATA_QCFLAG_RESULT_TF = (1 << 4), /* result TF requested */ ATA_QCFLAG_CLEAR_EXCL = (1 << 5), /* clear excl_link on completion */ @@ -475,7 +473,6 @@ struct ata_queued_cmd { struct scatterlist sgent; struct scatterlist pad_sgent; - void *buf_virt; /* DO NOT iterate over __sg manually, use ata_for_each_sg() */ struct scatterlist *__sg; @@ -891,8 +888,6 @@ extern void ata_dumb_qc_prep(struct ata_queued_cmd *qc); extern void ata_qc_prep(struct ata_queued_cmd *qc); extern void ata_noop_qc_prep(struct ata_queued_cmd *qc); extern unsigned int ata_qc_issue_prot(struct ata_queued_cmd *qc); -extern void ata_sg_init_one(struct ata_queued_cmd *qc, void *buf, - unsigned int buflen); extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, unsigned int n_elem); extern unsigned int ata_dev_classify(const struct ata_taskfile *tf); -- cgit v1.2.3 From ff2aeb1eb64c8a4770a6304f9addbae9f9828646 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 5 Dec 2007 16:43:11 +0900 Subject: libata: convert to chained sg libata used private sg iterator to handle padding sg. Now that sg can be chained, padding can be handled using standard sg ops. Convert to chained sg. * s/qc->__sg/qc->sg/ * s/qc->pad_sgent/qc->extra_sg[]/. Because chaining consumes one sg entry. There need to be two extra sg entries. The renaming is also for future addition of other extra sg entries. * Padding setup is moved into ata_sg_setup_extra() which is organized in a way that future addition of other extra sg entries is easy. * qc->orig_n_elem is unused and removed. * qc->n_elem now contains the number of sg entries that LLDs should map. qc->mapped_n_elem is added to carry the original number of mapped sgs for unmapping. * The last sg of the original sg list is used to chain to extra sg list. The original last sg is pointed to by qc->last_sg and the content is stored in qc->saved_last_sg. It's restored during ata_sg_clean(). * All sg walking code has been updated. Unnecessary assertions and checks for conditions the core layer already guarantees are removed. Signed-off-by: Tejun Heo Cc: Jens Axboe Signed-off-by: Jeff Garzik --- include/linux/libata.h | 42 ++++++++---------------------------------- 1 file changed, 8 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index acd90ad78417..162f8b5509ac 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -458,7 +458,7 @@ struct ata_queued_cmd { unsigned int tag; unsigned int n_elem; unsigned int n_iter; - unsigned int orig_n_elem; + unsigned int mapped_n_elem; int dma_dir; @@ -471,11 +471,12 @@ struct ata_queued_cmd { struct scatterlist *cursg; unsigned int cursg_ofs; + struct scatterlist *last_sg; + struct scatterlist saved_last_sg; struct scatterlist sgent; - struct scatterlist pad_sgent; + struct scatterlist extra_sg[2]; - /* DO NOT iterate over __sg manually, use ata_for_each_sg() */ - struct scatterlist *__sg; + struct scatterlist *sg; unsigned int err_mask; struct ata_taskfile result_tf; @@ -1123,35 +1124,6 @@ extern void ata_port_pbar_desc(struct ata_port *ap, int bar, ssize_t offset, const char *name); #endif -/* - * qc helpers - */ -static inline struct scatterlist * -ata_qc_first_sg(struct ata_queued_cmd *qc) -{ - qc->n_iter = 0; - if (qc->n_elem) - return qc->__sg; - if (qc->pad_len) - return &qc->pad_sgent; - return NULL; -} - -static inline struct scatterlist * -ata_qc_next_sg(struct scatterlist *sg, struct ata_queued_cmd *qc) -{ - if (sg == &qc->pad_sgent) - return NULL; - if (++qc->n_iter < qc->n_elem) - return sg_next(sg); - if (qc->pad_len) - return &qc->pad_sgent; - return NULL; -} - -#define ata_for_each_sg(sg, qc) \ - for (sg = ata_qc_first_sg(qc); sg; sg = ata_qc_next_sg(sg, qc)) - static inline unsigned int ata_tag_valid(unsigned int tag) { return (tag < ATA_MAX_QUEUE) ? 1 : 0; @@ -1386,15 +1358,17 @@ static inline void ata_tf_init(struct ata_device *dev, struct ata_taskfile *tf) static inline void ata_qc_reinit(struct ata_queued_cmd *qc) { qc->dma_dir = DMA_NONE; - qc->__sg = NULL; + qc->sg = NULL; qc->flags = 0; qc->cursg = NULL; qc->cursg_ofs = 0; qc->nbytes = qc->curbytes = 0; qc->n_elem = 0; + qc->mapped_n_elem = 0; qc->n_iter = 0; qc->err_mask = 0; qc->pad_len = 0; + qc->last_sg = NULL; qc->sect_size = ATA_SECT_SIZE; ata_tf_init(qc->dev, &qc->tf); -- cgit v1.2.3 From 0bcc65ad78ae517de16b2ca07a2891f49d44d156 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 5 Dec 2007 16:43:12 +0900 Subject: libata: make qc->nbytes include extra buffers qc->nbytes didn't use to include extra buffers setup by libata core layer and my be odd. This patch makes qc->nbytes include any extra buffers setup by libata core layer and guaranteed to be aligned on 4 byte boundary. This value is to be used to program the host controller. As this represents the actual length of buffer available to the controller and the controller must be able to deal with short transfers for ATAPI commands which can transfer variable length, this shouldn't break any controllers while making problems like rounding-down and controllers choking up on odd transfer bytes much less likely. The unmodified value is stored in new field qc->raw_nbytes. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 162f8b5509ac..7b7c78e42077 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -466,6 +466,7 @@ struct ata_queued_cmd { unsigned int sect_size; unsigned int nbytes; + unsigned int raw_nbytes; unsigned int curbytes; struct scatterlist *cursg; @@ -1362,7 +1363,7 @@ static inline void ata_qc_reinit(struct ata_queued_cmd *qc) qc->flags = 0; qc->cursg = NULL; qc->cursg_ofs = 0; - qc->nbytes = qc->curbytes = 0; + qc->nbytes = qc->raw_nbytes = qc->curbytes = 0; qc->n_elem = 0; qc->mapped_n_elem = 0; qc->n_iter = 0; -- cgit v1.2.3 From 442eacc362c2576aac8ebfd41b99252e28e0f49c Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Wed, 19 Dec 2007 04:25:10 -0500 Subject: libata: make ata_port_queue_task() an internal function ata_port_queue_task() served a single user: ata_pio_task() Rename to ata_pio_queue_task() and un-export it, as nobody outside of libata-core.c uses it. Signed-off-by: Jeff Garzik --- include/linux/libata.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 7b7c78e42077..ccb055636f37 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -847,8 +847,6 @@ extern int ata_busy_sleep(struct ata_port *ap, unsigned long timeout_pat, unsigned long timeout); extern void ata_wait_after_reset(struct ata_port *ap, unsigned long deadline); extern int ata_wait_ready(struct ata_port *ap, unsigned long deadline); -extern void ata_port_queue_task(struct ata_port *ap, work_func_t fn, - void *data, unsigned long delay); extern u32 ata_wait_register(void __iomem *reg, u32 mask, u32 val, unsigned long interval_msec, unsigned long timeout_msec); -- cgit v1.2.3 From 4ca4e439640cd1d3659cbcf60e7a73c2ae0450b3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 30 Dec 2007 09:32:22 +0000 Subject: libata annotations and fixes Signed-off-by: Al Viro Signed-off-by: Jeff Garzik --- include/linux/ata.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index bc55471a4b2c..78bbacaed8c4 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -354,8 +354,8 @@ enum ata_ioctls { /* core structures */ struct ata_prd { - u32 addr; - u32 flags_len; + __le32 addr; + __le32 flags_len; }; struct ata_taskfile { -- cgit v1.2.3 From 4e6b79fa61091a0ed9b0af0f573cc257772cd88d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 18 Jan 2008 18:36:28 +0900 Subject: libata: factor out ata_pci_activate_sff_host() from ata_pci_one() Factor out ata_pci_activate_sff_host() from ata_pci_one(). This does about the same thing as ata_host_activate() but needs to be separate because SFF controllers use different and multiple IRQs in legacy mode. This will be used to make SFF LLD initialization more flexible. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/libata.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index ccb055636f37..4374c4277780 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1033,6 +1033,9 @@ extern int ata_pci_init_bmdma(struct ata_host *host); extern int ata_pci_prepare_sff_host(struct pci_dev *pdev, const struct ata_port_info * const * ppi, struct ata_host **r_host); +extern int ata_pci_activate_sff_host(struct ata_host *host, + irq_handler_t irq_handler, + struct scsi_host_template *sht); extern int pci_test_config_bits(struct pci_dev *pdev, const struct pci_bits *bits); extern unsigned long ata_pci_default_filter(struct ata_device *dev, unsigned long xfer_mask); -- cgit v1.2.3 From 5e8f757cb2e0f67bf43f71d5180a8bf0ab3484eb Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Sat, 19 Jan 2008 16:07:58 +0000 Subject: ata_generic: Cenatek support Not much to do here. It's an ata memory as disk. Signed-off-by: Alan Cox Signed-off-by: Jeff Garzik --- include/linux/pci_ids.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 7f2215139e9a..1fbd0256e86b 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2066,6 +2066,9 @@ #define PCI_VENDOR_ID_NETCELL 0x169c #define PCI_DEVICE_ID_REVOLUTION 0x0044 +#define PCI_VENDOR_ID_CENATEK 0x16CA +#define PCI_DEVICE_ID_CENATEK_IDE 0x0001 + #define PCI_VENDOR_ID_VITESSE 0x1725 #define PCI_DEVICE_ID_VITESSE_VSC7174 0x7174 -- cgit v1.2.3 From fd1109711d7f76126e7cef947999f139b198dc15 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Wed, 2 Jan 2008 18:48:47 -0600 Subject: [SCSI] attribute_container: update to use the group interface This patch is the beginning of moving the attribute_containers to use attribute groups exclusively. The attr element is now deprecated and will eventually be removed (along with all the hand rolled code for doing exactly what attribute groups do) when all the consumers are converted to attribute groups. Acked-by: Greg Kroah-Hartman Signed-off-by: James Bottomley --- include/linux/attribute_container.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/attribute_container.h b/include/linux/attribute_container.h index 8ff274933948..f5582332af04 100644 --- a/include/linux/attribute_container.h +++ b/include/linux/attribute_container.h @@ -17,6 +17,7 @@ struct attribute_container { struct list_head node; struct klist containers; struct class *class; + struct attribute_group *grp; struct class_device_attribute **attrs; int (*match)(struct attribute_container *, struct device *); #define ATTRIBUTE_CONTAINER_NO_CLASSDEVS 0x01 -- cgit v1.2.3 From d4acd722b7bb5f48b9fc3848e8c2a845b100d84f Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Wed, 31 Oct 2007 09:38:04 -0500 Subject: [SCSI] sysfs: add filter function to groups This patch allows the various users of attribute_groups to selectively allow the appearance of group attributes. The primary consumer of this will be the transport classes in which we currently have elaborate attribute selection algorithms to do this same thing. Acked-by: Greg KH Signed-off-by: James Bottomley --- include/linux/sysfs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 149ab62329e2..802710438a9e 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -32,6 +32,8 @@ struct attribute { struct attribute_group { const char *name; + int (*is_visible)(struct kobject *, + struct attribute *, int); struct attribute **attrs; }; -- cgit v1.2.3 From 81b4e1f6269cea345f17d3aa349ec9beb31a8cd3 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Wed, 16 Jan 2008 17:20:37 -0500 Subject: DMI: move dmi_available declaration to linux/dmi.h Signed-off-by: Len Brown --- include/linux/dmi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmi.h b/include/linux/dmi.h index 00fc7a9c35ec..b1251b2af568 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -78,6 +78,7 @@ extern const struct dmi_device * dmi_find_device(int type, const char *name, extern void dmi_scan_machine(void); extern int dmi_get_year(int field); extern int dmi_name_in_vendors(const char *str); +extern int dmi_available; #else @@ -87,6 +88,7 @@ static inline const struct dmi_device * dmi_find_device(int type, const char *na const struct dmi_device *from) { return NULL; } static inline int dmi_get_year(int year) { return 0; } static inline int dmi_name_in_vendors(const char *s) { return 0; } +#define dmi_available 0 #endif -- cgit v1.2.3 From f89e3b0620a0dc19f313218f55373b9361142203 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Wed, 23 Jan 2008 16:36:45 -0500 Subject: DMI: create dmi_get_slot() This simply allows other sub-systems (such as ACPI) to access and print out slots in static dmi_ident[]. Signed-off-by: Len Brown --- include/linux/dmi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmi.h b/include/linux/dmi.h index b1251b2af568..5b42a659a308 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -79,6 +79,7 @@ extern void dmi_scan_machine(void); extern int dmi_get_year(int field); extern int dmi_name_in_vendors(const char *str); extern int dmi_available; +extern char *dmi_get_slot(int slot); #else @@ -89,6 +90,7 @@ static inline const struct dmi_device * dmi_find_device(int type, const char *na static inline int dmi_get_year(int year) { return 0; } static inline int dmi_name_in_vendors(const char *s) { return 0; } #define dmi_available 0 +static inline char *dmi_get_slot(int slot) { return NULL; } #endif -- cgit v1.2.3 From d4b7dc499daae909e62dc260b95cd618f2970ded Mon Sep 17 00:00:00 2001 From: Len Brown Date: Wed, 23 Jan 2008 20:50:56 -0500 Subject: ACPI: make _OSI(Linux) console messages smarter If BIOS invokes _OSI(Linux), the kernel response depends on what the ACPI DMI list knows about the system, and that is reflectd in dmesg: 1) System unknown to DMI: ACPI: BIOS _OSI(Linux) query ignored ACPI: DMI System Vendor: LENOVO ACPI: DMI Product Name: 7661W1P ACPI: DMI Product Version: ThinkPad T61 ACPI: DMI Board Name: 7661W1P ACPI: DMI BIOS Vendor: LENOVO ACPI: DMI BIOS Date: 10/18/2007 ACPI: Please send DMI info above to linux-acpi@vger.kernel.org ACPI: If "acpi_osi=Linux" works better, please notify linux-acpi@vger.kernel.org 2) System known to DMI, but effect of OSI(Linux) unknown: ACPI: DMI detected: Lenovo ThinkPad T61 ... ACPI: BIOS _OSI(Linux) query ignored via DMI ACPI: If "acpi_osi=Linux" works better, please notify linux-acpi@vger.kernel.org 3) System known to DMI, which disables _OSI(Linux): ACPI: DMI detected: Lenovo ThinkPad T61 ... ACPI: BIOS _OSI(Linux) query ignored via DMI 4) System known to DMI, which enable _OSI(Linux): ACPI: DMI detected: Lenovo ThinkPad T61 ACPI: Added _OSI(Linux) ... ACPI: BIOS _OSI(Linux) query honored via DMI cmdline overrides take precidence over the built-in default and the DMI prescribed default. cmdline "acpi_osi=Linux" results in: ACPI: BIOS _OSI(Linux) query honored via cmdline Signed-off-by: Len Brown --- include/linux/acpi.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index e3c16c981e46..63f2e6ed698f 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -40,6 +40,7 @@ #include #include #include +#include #ifdef CONFIG_ACPI @@ -192,7 +193,9 @@ extern int ec_transaction(u8 command, #endif /*CONFIG_ACPI_EC*/ extern int acpi_blacklisted(void); -extern void acpi_bios_year(char *s); +#ifdef CONFIG_DMI +extern void acpi_dmi_osi_linux(int enable, const struct dmi_system_id *d); +#endif #ifdef CONFIG_ACPI_NUMA int acpi_get_pxm(acpi_handle handle); @@ -226,5 +229,5 @@ static inline int acpi_boot_table_init(void) return 0; } -#endif /* CONFIG_ACPI */ +#endif /* !CONFIG_ACPI */ #endif /*_LINUX_ACPI_H*/ -- cgit v1.2.3 From c9180a57a9ab2d5525faf8815a332364ee9e89b7 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 30 Nov 2007 13:00:35 -0500 Subject: Security: add get, set, and cloning of superblock security information Adds security_get_sb_mnt_opts, security_set_sb_mnt_opts, and security_clont_sb_mnt_opts to the LSM and to SELinux. This will allow filesystems to directly own and control all of their mount options if they so choose. This interface deals only with option identifiers and strings so it should generic enough for any LSM which may come in the future. Filesystems which pass text mount data around in the kernel (almost all of them) need not currently make use of this interface when dealing with SELinux since it will still parse those strings as it always has. I assume future LSM's would do the same. NFS is the primary FS which does not use text mount data and thus must make use of this interface. An LSM would need to implement these functions only if they had mount time options, such as selinux has context= or fscontext=. If the LSM has no mount time options they could simply not implement and let the dummy ops take care of things. An LSM other than SELinux would need to define new option numbers in security.h and any FS which decides to own there own security options would need to be patched to use this new interface for every possible LSM. This is because it was stated to me very clearly that LSM's should not attempt to understand FS mount data and the burdon to understand security should be in the FS which owns the options. Signed-off-by: Eric Paris Acked-by: Stephen D. Smalley Signed-off-by: James Morris --- include/linux/security.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index ac050830a873..cbd970a735f2 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -34,6 +34,12 @@ #include #include +/* only a char in selinux superblock security struct flags */ +#define FSCONTEXT_MNT 0x01 +#define CONTEXT_MNT 0x02 +#define ROOTCONTEXT_MNT 0x04 +#define DEFCONTEXT_MNT 0x08 + /* * Bounding set */ @@ -261,6 +267,22 @@ struct request_sock; * Update module state after a successful pivot. * @old_nd contains the nameidata structure for the old root. * @new_nd contains the nameidata structure for the new root. + * @sb_get_mnt_opts: + * Get the security relevant mount options used for a superblock + * @sb the superblock to get security mount options from + * @mount_options array for pointers to mount options + * @mount_flags array of ints specifying what each mount options is + * @num_opts number of options in the arrays + * @sb_set_mnt_opts: + * Set the security relevant mount options used for a superblock + * @sb the superblock to set security mount options for + * @mount_options array for pointers to mount options + * @mount_flags array of ints specifying what each mount options is + * @num_opts number of options in the arrays + * @sb_clone_mnt_opts: + * Copy all security options from a given superblock to another + * @oldsb old superblock which contain information to clone + * @newsb new superblock which needs filled in * * Security hooks for inode operations. * @@ -1242,6 +1264,13 @@ struct security_operations { struct nameidata * new_nd); void (*sb_post_pivotroot) (struct nameidata * old_nd, struct nameidata * new_nd); + int (*sb_get_mnt_opts) (const struct super_block *sb, + char ***mount_options, int **flags, + int *num_opts); + int (*sb_set_mnt_opts) (struct super_block *sb, char **mount_options, + int *flags, int num_opts); + void (*sb_clone_mnt_opts) (const struct super_block *oldsb, + struct super_block *newsb); int (*inode_alloc_security) (struct inode *inode); void (*inode_free_security) (struct inode *inode); @@ -1499,6 +1528,13 @@ void security_sb_post_mountroot(void); void security_sb_post_addmount(struct vfsmount *mnt, struct nameidata *mountpoint_nd); int security_sb_pivotroot(struct nameidata *old_nd, struct nameidata *new_nd); void security_sb_post_pivotroot(struct nameidata *old_nd, struct nameidata *new_nd); +int security_sb_get_mnt_opts(const struct super_block *sb, char ***mount_options, + int **flags, int *num_opts); +int security_sb_set_mnt_opts(struct super_block *sb, char **mount_options, + int *flags, int num_opts); +void security_sb_clone_mnt_opts(const struct super_block *oldsb, + struct super_block *newsb); + int security_inode_alloc(struct inode *inode); void security_inode_free(struct inode *inode); int security_inode_init_security(struct inode *inode, struct inode *dir, -- cgit v1.2.3 From 42d7896ebc5f7268b1fe6bbd20f2282e20ae7895 Mon Sep 17 00:00:00 2001 From: James Morris Date: Wed, 26 Dec 2007 15:12:37 +1100 Subject: Security: remove security.h include from mm.h Remove security.h include from mm.h, as it is only needed for a single extern declaration, and pulls in all kinds of crud. Fine-by-me: David Chinner Acked-by: Eric Paris Signed-off-by: James Morris --- include/linux/mm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1b7b95c67aca..1897ca223eca 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -12,7 +12,6 @@ #include #include #include -#include struct mempolicy; struct anon_vma; @@ -34,6 +33,8 @@ extern int sysctl_legacy_va_layout; #define sysctl_legacy_va_layout 0 #endif +extern unsigned long mmap_min_addr; + #include #include #include -- cgit v1.2.3 From bced95283e9434611cbad8f2ff903cd396eaea72 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Sat, 29 Dec 2007 16:20:25 -0800 Subject: security: remove security_sb_post_mountroot hook The security_sb_post_mountroot() hook is long-since obsolete, and is fundamentally broken: it is never invoked if someone uses initramfs. This is particularly damaging, because the existence of this hook has been used as motivation for not using initramfs. Stephen Smalley confirmed on 2007-07-19 that this hook was originally used by SELinux but can now be safely removed: http://marc.info/?l=linux-kernel&m=118485683612916&w=2 Cc: Stephen Smalley Cc: James Morris Cc: Eric Paris Cc: Chris Wright Signed-off-by: H. Peter Anvin Signed-off-by: James Morris --- include/linux/security.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index cbd970a735f2..2e2c63faead7 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -249,9 +249,6 @@ struct request_sock; * @mnt contains the mounted file system. * @flags contains the new filesystem flags. * @data contains the filesystem-specific data. - * @sb_post_mountroot: - * Update the security module's state when the root filesystem is mounted. - * This hook is only called if the mount was successful. * @sb_post_addmount: * Update the security module's state when a filesystem is mounted. * This hook is called any time a mount is successfully grafetd to @@ -1257,7 +1254,6 @@ struct security_operations { void (*sb_umount_busy) (struct vfsmount * mnt); void (*sb_post_remount) (struct vfsmount * mnt, unsigned long flags, void *data); - void (*sb_post_mountroot) (void); void (*sb_post_addmount) (struct vfsmount * mnt, struct nameidata * mountpoint_nd); int (*sb_pivotroot) (struct nameidata * old_nd, @@ -1524,7 +1520,6 @@ int security_sb_umount(struct vfsmount *mnt, int flags); void security_sb_umount_close(struct vfsmount *mnt); void security_sb_umount_busy(struct vfsmount *mnt); void security_sb_post_remount(struct vfsmount *mnt, unsigned long flags, void *data); -void security_sb_post_mountroot(void); void security_sb_post_addmount(struct vfsmount *mnt, struct nameidata *mountpoint_nd); int security_sb_pivotroot(struct nameidata *old_nd, struct nameidata *new_nd); void security_sb_post_pivotroot(struct nameidata *old_nd, struct nameidata *new_nd); @@ -1813,9 +1808,6 @@ static inline void security_sb_post_remount (struct vfsmount *mnt, unsigned long flags, void *data) { } -static inline void security_sb_post_mountroot (void) -{ } - static inline void security_sb_post_addmount (struct vfsmount *mnt, struct nameidata *mountpoint_nd) { } -- cgit v1.2.3 From 63cb34492351078479b2d4bae6a881806a396286 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 15 Jan 2008 23:47:35 +0000 Subject: security: add a secctx_to_secid() hook Add a secctx_to_secid() LSM hook to go along with the existing secid_to_secctx() LSM hook. This patch also includes the SELinux implementation for this hook. Signed-off-by: Paul Moore Acked-by: Stephen Smalley Signed-off-by: James Morris --- include/linux/security.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 2e2c63faead7..e4a91cb1b187 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1202,6 +1202,10 @@ struct request_sock; * Convert secid to security context. * @secid contains the security ID. * @secdata contains the pointer that stores the converted security context. + * @secctx_to_secid: + * Convert security context to secid. + * @secid contains the pointer to the generated security ID. + * @secdata contains the security context. * * @release_secctx: * Release the security context. @@ -1396,6 +1400,7 @@ struct security_operations { int (*getprocattr)(struct task_struct *p, char *name, char **value); int (*setprocattr)(struct task_struct *p, char *name, void *value, size_t size); int (*secid_to_secctx)(u32 secid, char **secdata, u32 *seclen); + int (*secctx_to_secid)(char *secdata, u32 seclen, u32 *secid); void (*release_secctx)(char *secdata, u32 seclen); #ifdef CONFIG_SECURITY_NETWORK @@ -1634,6 +1639,7 @@ int security_setprocattr(struct task_struct *p, char *name, void *value, size_t int security_netlink_send(struct sock *sk, struct sk_buff *skb); int security_netlink_recv(struct sk_buff *skb, int cap); int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen); +int security_secctx_to_secid(char *secdata, u32 seclen, u32 *secid); void security_release_secctx(char *secdata, u32 seclen); #else /* CONFIG_SECURITY */ @@ -2308,6 +2314,13 @@ static inline int security_secid_to_secctx(u32 secid, char **secdata, u32 *secle return -EOPNOTSUPP; } +static inline int security_secctx_to_secid(char *secdata, + u32 seclen, + u32 *secid) +{ + return -EOPNOTSUPP; +} + static inline void security_release_secctx(char *secdata, u32 seclen) { } -- cgit v1.2.3 From 1996a10948e50e546dc2b64276723c0b64d3173b Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Wed, 23 Jan 2008 00:02:58 +0100 Subject: security/selinux: constify function pointer tables and fields Constify function pointer tables and fields. Signed-off-by: Jan Engelhardt Signed-off-by: James Morris --- include/linux/security.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index e4a91cb1b187..d24974262dc6 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2300,7 +2300,7 @@ static inline struct dentry *securityfs_create_file(const char *name, mode_t mode, struct dentry *parent, void *data, - struct file_operations *fops) + const struct file_operations *fops) { return ERR_PTR(-ENODEV); } -- cgit v1.2.3 From 775b64d2b6ca37697de925f70799c710aab5849a Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 12 Jan 2008 20:40:46 +0100 Subject: PM: Acquire device locks on suspend This patch reorganizes the way suspend and resume notifications are sent to drivers. The major changes are that now the PM core acquires every device semaphore before calling the methods, and calls to device_add() during suspends will fail, while calls to device_del() during suspends will block. It also provides a way to safely remove a suspended device with the help of the PM core, by using the device_pm_schedule_removal() callback introduced specifically for this purpose, and updates two drivers (msr and cpuid) that need to use it. Signed-off-by: Alan Stern Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 2e15822fe409..cf4ae5c5d193 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -521,6 +521,14 @@ extern struct device *device_create(struct class *cls, struct device *parent, dev_t devt, const char *fmt, ...) __attribute__((format(printf,4,5))); extern void device_destroy(struct class *cls, dev_t devt); +#ifdef CONFIG_PM_SLEEP +extern void destroy_suspended_device(struct class *cls, dev_t devt); +#else /* !CONFIG_PM_SLEEP */ +static inline void destroy_suspended_device(struct class *cls, dev_t devt) +{ + device_destroy(cls, devt); +} +#endif /* !CONFIG_PM_SLEEP */ /* * Platform "fixup" functions - allow the platform to have their say -- cgit v1.2.3 From 41ca28ab2abd76dc203e2c3a7cd609607cb927c3 Mon Sep 17 00:00:00 2001 From: Evgeniy Polyakov Date: Mon, 10 Dec 2007 23:03:43 +0300 Subject: kref: add kref_set() This adds kref_set() to the kref api for future use by people who really know what they are doing with krefs... From: Evgeniy Polyakov Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kref.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kref.h b/include/linux/kref.h index 6fee3539893f..5d185635786e 100644 --- a/include/linux/kref.h +++ b/include/linux/kref.h @@ -24,6 +24,7 @@ struct kref { atomic_t refcount; }; +void kref_set(struct kref *kref, int num); void kref_init(struct kref *kref); void kref_get(struct kref *kref); int kref_put(struct kref *kref, void (*release) (struct kref *kref)); -- cgit v1.2.3 From 891f78ea833edd4a1e524e15bfe297a7a84d81a0 Mon Sep 17 00:00:00 2001 From: Tony Jones Date: Tue, 25 Sep 2007 02:03:03 +0200 Subject: DMA: Convert from class_device to device for DMA engine Signed-off-by: Tony Jones Signed-off-by: Dan Williams Cc: Shannon Nelson Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/dmaengine.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index a3b6035b6c86..55c9a6952f44 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -132,7 +132,7 @@ struct dma_chan { /* sysfs */ int chan_id; - struct class_device class_dev; + struct device dev; struct kref refcount; int slow_ref; @@ -142,6 +142,7 @@ struct dma_chan { struct dma_chan_percpu *local; }; +#define to_dma_chan(p) container_of(p, struct dma_chan, dev) void dma_chan_cleanup(struct kref *kref); -- cgit v1.2.3 From 6013c12be8313b3205b41912d965b03f3b06147d Mon Sep 17 00:00:00 2001 From: Tony Jones Date: Tue, 25 Sep 2007 02:03:03 +0200 Subject: pktcdvd: Convert from class_device to device for block/pktcdvd struct class_device is going away, this converts the code to use struct device instead. Signed-off-by: Tony Jones Cc: Peter Osterlund Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/pktcdvd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h index 5ea4f05683f6..04b4d7330e6d 100644 --- a/include/linux/pktcdvd.h +++ b/include/linux/pktcdvd.h @@ -290,7 +290,7 @@ struct pktcdvd_device int write_congestion_off; int write_congestion_on; - struct class_device *clsdev; /* sysfs pktcdvd[0-7] class dev */ + struct device *dev; /* sysfs pktcdvd[0-7] dev */ struct pktcdvd_kobj *kobj_stat; /* sysfs pktcdvd[0-7]/stat/ */ struct pktcdvd_kobj *kobj_wqueue; /* sysfs pktcdvd[0-7]/write_queue/ */ -- cgit v1.2.3 From 7dd817d083b6fc103b9ea4f2b4f4a1c6a09e29a0 Mon Sep 17 00:00:00 2001 From: Tony Jones Date: Tue, 25 Sep 2007 02:03:03 +0200 Subject: tifm: Convert from class_device to device for TI flash media Signed-off-by: Tony Jones Cc: Alex Dubov Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/tifm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tifm.h b/include/linux/tifm.h index 6b3a31805c72..2096b76d0cee 100644 --- a/include/linux/tifm.h +++ b/include/linux/tifm.h @@ -120,7 +120,7 @@ struct tifm_adapter { struct completion *finish_me; struct work_struct media_switcher; - struct class_device cdev; + struct device dev; void (*eject)(struct tifm_adapter *fm, struct tifm_dev *sock); -- cgit v1.2.3 From 7b8712e563df4fefc25d3107fa3fb3abb7331ff4 Mon Sep 17 00:00:00 2001 From: Emil Medve Date: Tue, 30 Oct 2007 14:37:14 -0500 Subject: driver core: Make the dev_*() family of macros in device.h complete Removed duplicates defined elsewhere Signed-off-by: Emil Medve Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index cf4ae5c5d193..dbbbe89e7267 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -565,6 +565,21 @@ extern const char *dev_driver_string(struct device *dev); #define dev_printk(level, dev, format, arg...) \ printk(level "%s %s: " format , dev_driver_string(dev) , (dev)->bus_id , ## arg) +#define dev_emerg(dev, format, arg...) \ + dev_printk(KERN_EMERG , dev , format , ## arg) +#define dev_alert(dev, format, arg...) \ + dev_printk(KERN_ALERT , dev , format , ## arg) +#define dev_crit(dev, format, arg...) \ + dev_printk(KERN_CRIT , dev , format , ## arg) +#define dev_err(dev, format, arg...) \ + dev_printk(KERN_ERR , dev , format , ## arg) +#define dev_warn(dev, format, arg...) \ + dev_printk(KERN_WARNING , dev , format , ## arg) +#define dev_notice(dev, format, arg...) \ + dev_printk(KERN_NOTICE , dev , format , ## arg) +#define dev_info(dev, format, arg...) \ + dev_printk(KERN_INFO , dev , format , ## arg) + #ifdef DEBUG #define dev_dbg(dev, format, arg...) \ dev_printk(KERN_DEBUG , dev , format , ## arg) @@ -586,15 +601,6 @@ dev_vdbg(struct device * dev, const char * fmt, ...) } #endif -#define dev_err(dev, format, arg...) \ - dev_printk(KERN_ERR , dev , format , ## arg) -#define dev_info(dev, format, arg...) \ - dev_printk(KERN_INFO , dev , format , ## arg) -#define dev_warn(dev, format, arg...) \ - dev_printk(KERN_WARNING , dev , format , ## arg) -#define dev_notice(dev, format, arg...) \ - dev_printk(KERN_NOTICE , dev , format , ## arg) - /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ MODULE_ALIAS("char-major-" __stringify(major) "-" __stringify(minor)) -- cgit v1.2.3 From 18041f4775688af073d9b3ab0ffc262c1847e60b Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 3 Dec 2007 21:31:08 -0800 Subject: kobject: make kobject_cleanup be static No one except the kobject core calls it so make the function static. Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 4a0d27f475d7..2d19a079ee79 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -79,8 +79,6 @@ static inline const char * kobject_name(const struct kobject * kobj) } extern void kobject_init(struct kobject *); -extern void kobject_cleanup(struct kobject *); - extern int __must_check kobject_add(struct kobject *); extern void kobject_del(struct kobject *); -- cgit v1.2.3 From e86000d042d23904bbb609af2f8618a541cf129b Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 3 Dec 2007 21:31:08 -0800 Subject: kobject: add kobject_init_ng function This is what the kobject_init function is going to become. Add this to the kernel and then we can convert the tree over to use it. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 2d19a079ee79..bdf4f7c45f19 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -79,6 +79,7 @@ static inline const char * kobject_name(const struct kobject * kobj) } extern void kobject_init(struct kobject *); +extern void kobject_init_ng(struct kobject *kobj, struct kobj_type *ktype); extern int __must_check kobject_add(struct kobject *); extern void kobject_del(struct kobject *); -- cgit v1.2.3 From 244f6cee9a928103132a722292bfa0eb84114b07 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 3 Dec 2007 21:31:08 -0800 Subject: kobject: add kobject_add_ng function This is what the kobject_add function is going to become. Add this to the kernel and then we can convert the tree over to use it. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index bdf4f7c45f19..57eea4cb940d 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -81,6 +81,9 @@ static inline const char * kobject_name(const struct kobject * kobj) extern void kobject_init(struct kobject *); extern void kobject_init_ng(struct kobject *kobj, struct kobj_type *ktype); extern int __must_check kobject_add(struct kobject *); +extern int __must_check kobject_add_ng(struct kobject *kobj, + struct kobject *parent, + const char *fmt, ...); extern void kobject_del(struct kobject *); extern int __must_check kobject_rename(struct kobject *, const char *new_name); -- cgit v1.2.3 From c11c4154e7ff4cebfadad849b1e22689d759c3f4 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 3 Dec 2007 21:31:08 -0800 Subject: kobject: add kobject_init_and_add function Also add a kobject_init_and_add function which bundles up what a lot of the current callers want to do all at once, and it properly handles the memory usages, unlike kobject_register(); Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 57eea4cb940d..e2b8c3dae425 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -84,6 +84,11 @@ extern int __must_check kobject_add(struct kobject *); extern int __must_check kobject_add_ng(struct kobject *kobj, struct kobject *parent, const char *fmt, ...); +extern int __must_check kobject_init_and_add(struct kobject *kobj, + struct kobj_type *ktype, + struct kobject *parent, + const char *fmt, ...); + extern void kobject_del(struct kobject *); extern int __must_check kobject_rename(struct kobject *, const char *new_name); -- cgit v1.2.3 From 3514faca19a6fdc209734431c509631ea92b094e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 16 Oct 2007 10:11:44 -0600 Subject: kobject: remove struct kobj_type from struct kset We don't need a "default" ktype for a kset. We should set this explicitly every time for each kset. This change is needed so that we can make ksets dynamic, and cleans up one of the odd, undocumented assumption that the kset/kobject/ktype model has. This patch is based on a lot of help from Kay Sievers. Nasty bug in the block code was found by Dave Young Cc: Kay Sievers Cc: Dave Young Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index e2b8c3dae425..5031565ab30d 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -135,7 +135,6 @@ struct kset_uevent_ops { * define the attribute callbacks and other common events that happen to * a kobject. * - * @ktype: the struct kobj_type for this specific kset * @list: the list of all kobjects for this kset * @list_lock: a lock for iterating over the kobjects * @kobj: the embedded kobject for this kset (recursion, isn't it fun...) @@ -145,7 +144,6 @@ struct kset_uevent_ops { * desired. */ struct kset { - struct kobj_type *ktype; struct list_head list; spinlock_t list_lock; struct kobject kobj; @@ -173,12 +171,9 @@ static inline void kset_put(struct kset * k) kobject_put(&k->kobj); } -static inline struct kobj_type * get_ktype(struct kobject * k) +static inline struct kobj_type *get_ktype(struct kobject *kobj) { - if (k->kset && k->kset->ktype) - return k->kset->ktype; - else - return k->ktype; + return kobj->ktype; } extern struct kobject * kset_find_obj(struct kset *, const char *); @@ -191,16 +186,14 @@ extern struct kobject * kset_find_obj(struct kset *, const char *); #define set_kset_name(str) .kset = { .kobj = { .k_name = str } } -#define decl_subsys(_name,_type,_uevent_ops) \ +#define decl_subsys(_name,_uevent_ops) \ struct kset _name##_subsys = { \ .kobj = { .k_name = __stringify(_name) }, \ - .ktype = _type, \ .uevent_ops =_uevent_ops, \ } -#define decl_subsys_name(_varname,_name,_type,_uevent_ops) \ +#define decl_subsys_name(_varname,_name,_uevent_ops) \ struct kset _varname##_subsys = { \ .kobj = { .k_name = __stringify(_name) }, \ - .ktype = _type, \ .uevent_ops =_uevent_ops, \ } -- cgit v1.2.3 From 12d03da7c19366268bdbc9fb0cd08d719c0cc283 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 16 Oct 2007 10:11:44 -0600 Subject: kobject: remove kobj_set_kset_s as no one is using it anymore What a confusing name for a macro... Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 5031565ab30d..0b97b3a53917 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -202,24 +202,6 @@ extern struct kset kernel_subsys; /* The global /sys/hypervisor/ subsystem */ extern struct kset hypervisor_subsys; -/* - * Helpers for setting the kset of registered objects. - * Often, a registered object belongs to a kset embedded in a - * subsystem. These do no magic, just make the resulting code - * easier to follow. - */ - -/** - * kobj_set_kset_s(obj,subsys) - set kset for embedded kobject. - * @obj: ptr to some object type. - * @subsys: a subsystem object (not a ptr). - * - * Can be used for any object type with an embedded ->kobj. - */ - -#define kobj_set_kset_s(obj,subsys) \ - (obj)->kobj.kset = &(subsys) - extern int __must_check subsystem_register(struct kset *); extern void subsystem_unregister(struct kset *); -- cgit v1.2.3 From b727c702896f88d2ff6c3e03bd011d7c3dffe3e1 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 27 Sep 2007 14:48:53 -0700 Subject: kset: add kset_create_and_add function Now ksets can be dynamically created on the fly, no static definitions are required. Thanks to Miklos for hints on how to make this work better for the callers. And thanks to Kay for finding some stupid bugs in my original version and pointing out that we need to handle the fact that kobject's can have a kset as a parent and to handle that properly in kobject_add(). Cc: Kay Sievers Cc: Miklos Szeredi Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 0b97b3a53917..f91aeb745664 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -150,11 +150,13 @@ struct kset { struct kset_uevent_ops *uevent_ops; }; - extern void kset_init(struct kset * k); extern int __must_check kset_add(struct kset * k); extern int __must_check kset_register(struct kset * k); extern void kset_unregister(struct kset * k); +extern struct kset * __must_check kset_create_and_add(const char *name, + struct kset_uevent_ops *u, + struct kobject *parent_kobj); static inline struct kset * to_kset(struct kobject * kobj) { -- cgit v1.2.3 From 3f9e3ee9dc3605e5c593b5d708494571fb0d3970 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 5 Nov 2007 13:16:15 -0800 Subject: kobject: add kobject_create_and_add function This lets users create dynamic kobjects much easier. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index f91aeb745664..33e7a6142a75 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -91,6 +91,9 @@ extern int __must_check kobject_init_and_add(struct kobject *kobj, extern void kobject_del(struct kobject *); +extern struct kobject * __must_check kobject_create_and_add(const char *name, + struct kobject *parent); + extern int __must_check kobject_rename(struct kobject *, const char *new_name); extern int __must_check kobject_move(struct kobject *, struct kobject *); -- cgit v1.2.3 From 4ff6abff832fbc6cb1d769f6106c841bc2b09f63 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 5 Nov 2007 22:24:43 -0800 Subject: kobject: get rid of kobject_add_dir kobject_create_and_add is the same as kobject_add_dir, so drop kobject_add_dir. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 33e7a6142a75..7b09136fb211 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -105,7 +105,6 @@ extern void kobject_put(struct kobject *); extern struct kobject *kobject_kset_add_dir(struct kset *kset, struct kobject *, const char *); -extern struct kobject *kobject_add_dir(struct kobject *, const char *); extern char * kobject_get_path(struct kobject *, gfp_t); -- cgit v1.2.3 From 43968d2f1648f4dc92437dc0363a3e88377445b3 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 5 Nov 2007 22:24:43 -0800 Subject: kobject: get rid of kobject_kset_add_dir kobject_kset_add_dir is only called in one place so remove it and use kobject_create() instead. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 7b09136fb211..718b48811288 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -91,6 +91,7 @@ extern int __must_check kobject_init_and_add(struct kobject *kobj, extern void kobject_del(struct kobject *); +extern struct kobject * __must_check kobject_create(void); extern struct kobject * __must_check kobject_create_and_add(const char *name, struct kobject *parent); @@ -103,9 +104,6 @@ extern void kobject_unregister(struct kobject *); extern struct kobject * kobject_get(struct kobject *); extern void kobject_put(struct kobject *); -extern struct kobject *kobject_kset_add_dir(struct kset *kset, - struct kobject *, const char *); - extern char * kobject_get_path(struct kobject *, gfp_t); struct kobj_type { -- cgit v1.2.3 From 00d2666623368ffd39afc875ff8a2eead2a0436c Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 29 Oct 2007 14:17:23 -0600 Subject: kobject: convert main fs kobject to use kobject_create This also renames fs_subsys to fs_kobj to catch all current users with a build error instead of a build warning which can easily be missed. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index b3ec4a496d64..21398a5d688d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1476,7 +1476,7 @@ extern void drop_collected_mounts(struct vfsmount *); extern int vfs_statfs(struct dentry *, struct kstatfs *); /* /sys/fs */ -extern struct kset fs_subsys; +extern struct kobject *fs_kobj; #define FLOCK_VERIFY_READ 1 #define FLOCK_VERIFY_WRITE 2 -- cgit v1.2.3 From 81ace5cd8fcb55e144f496af40d4275b03252456 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 29 Oct 2007 23:22:26 -0500 Subject: kset: convert pci hotplug to use kset_create_and_add This also renames pci_hotplug_slots_subsys to pcis_hotplug_slots_kset catch all current users with a build error instead of a build warning which can easily be missed. Cc: Kay Sievers Cc: Kristen Carlson Accardi Signed-off-by: Greg Kroah-Hartman --- include/linux/pci_hotplug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index ab4cb6ecd47c..8f67e8f2a3cc 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -174,7 +174,7 @@ extern int pci_hp_register (struct hotplug_slot *slot); extern int pci_hp_deregister (struct hotplug_slot *slot); extern int __must_check pci_hp_change_slot_info (struct hotplug_slot *slot, struct hotplug_slot_info *info); -extern struct kset pci_hotplug_slots_subsys; +extern struct kset *pci_hotplug_slots_kset; /* PCI Setting Record (Type 0) */ struct hpp_type0 { -- cgit v1.2.3 From e5e38a86c0bbe8475543f10f0a48393a45df5182 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 29 Oct 2007 23:22:26 -0500 Subject: kset: remove decl_subsys_name The last user of this macro (pci hotplug core) is now switched over to using a dynamic kset, so this macro is no longer needed at all. Cc: Kay Sievers Cc: Kristen Carlson Accardi Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 718b48811288..390ae14b73e8 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -193,11 +193,6 @@ struct kset _name##_subsys = { \ .kobj = { .k_name = __stringify(_name) }, \ .uevent_ops =_uevent_ops, \ } -#define decl_subsys_name(_varname,_name,_uevent_ops) \ -struct kset _varname##_subsys = { \ - .kobj = { .k_name = __stringify(_name) }, \ - .uevent_ops =_uevent_ops, \ -} /* The global /sys/kernel/ subsystem for people to chain off of */ extern struct kset kernel_subsys; -- cgit v1.2.3 From bd35b93d8049ab47b5bfaf6b10ba39badf21d1c3 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 29 Oct 2007 20:13:17 +0100 Subject: kset: convert kernel_subsys to use kset_create Dynamically create the kset instead of declaring it statically. We also rename kernel_subsys to kernel_kset to catch all users of this symbol with a build error instead of an easy-to-ignore build warning. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 390ae14b73e8..bd741e86c11e 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -194,8 +194,8 @@ struct kset _name##_subsys = { \ .uevent_ops =_uevent_ops, \ } -/* The global /sys/kernel/ subsystem for people to chain off of */ -extern struct kset kernel_subsys; +/* The global /sys/kernel/ kset for people to chain off of */ +extern struct kset *kernel_kset; /* The global /sys/hypervisor/ subsystem */ extern struct kset hypervisor_subsys; -- cgit v1.2.3 From 2d72fc00a1fb055e6127ccd30cac3f0eafaa98d0 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 1 Nov 2007 09:29:06 -0600 Subject: kobject: convert /sys/hypervisor to use kobject_create We don't need a kset here, a simple kobject will do just fine, so dynamically create the kobject and use it. We also rename hypervisor_subsys to hypervisor_kset to catch all users of the variable. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index bd741e86c11e..f2483f6fd639 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -196,8 +196,8 @@ struct kset _name##_subsys = { \ /* The global /sys/kernel/ kset for people to chain off of */ extern struct kset *kernel_kset; -/* The global /sys/hypervisor/ subsystem */ -extern struct kset hypervisor_subsys; +/* The global /sys/hypervisor/ kobject for people to chain off of */ +extern struct kobject *hypervisor_kobj; extern int __must_check subsystem_register(struct kset *); extern void subsystem_unregister(struct kset *); -- cgit v1.2.3 From 7405c1e15edfe43b137bfbc5882f1af34d6d414d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 1 Nov 2007 10:39:50 -0700 Subject: kset: convert /sys/module to use kset_create Dynamically create the kset instead of declaring it statically. We also rename module_subsys to module_kset to catch all users of the variable. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/module.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 2cbc0b87e329..fbe930b9b69c 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -574,7 +574,9 @@ struct device_driver; #ifdef CONFIG_SYSFS struct module; -extern struct kset module_subsys; +extern struct kset *module_kset; +extern struct kobj_type module_ktype; +extern int module_sysfs_initialized; int mod_sysfs_init(struct module *mod); int mod_sysfs_setup(struct module *mod, -- cgit v1.2.3 From 039a5dcd2fc45188a2d522df630db4f7ef903a0f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 1 Nov 2007 10:39:50 -0700 Subject: kset: convert /sys/power to use kset_create Dynamically create the kset instead of declaring it statically. We also rename power_subsys to power_kset to catch all users of the variable and we properly export it so that people don't have to guess that it really is present in the system. The pseries code is wierd, why is it createing /sys/power if CONFIG_PM is disabled? Oh well, stupid big boxes ignoring config options... Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index f2483f6fd639..a6dd669cda9d 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -198,6 +198,8 @@ struct kset _name##_subsys = { \ extern struct kset *kernel_kset; /* The global /sys/hypervisor/ kobject for people to chain off of */ extern struct kobject *hypervisor_kobj; +/* The global /sys/power/ kset for people to chain off of */ +extern struct kset *power_kset; extern int __must_check subsystem_register(struct kset *); extern void subsystem_unregister(struct kset *); -- cgit v1.2.3 From 3d8995963dfec66ef6270e729bf75903e9043f9d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 1 Nov 2007 13:31:26 -0700 Subject: kset: convert struct bus_device->devices to use kset_create Dynamically create the kset instead of declaring it statically. Having 3 static kobjects in one structure is not only foolish, but ripe for nasty race conditions if handled improperly. We also rename the field to catch any potential users of it (not that there should be outside of the driver core...) Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index dbbbe89e7267..82c277771376 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -55,7 +55,7 @@ struct bus_type { struct kset subsys; struct kset drivers; - struct kset devices; + struct kset *devices_kset; struct klist klist_devices; struct klist klist_drivers; -- cgit v1.2.3 From 6dcec2511ff55b4abaca7ad3433011a7c04c2430 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 1 Nov 2007 13:31:26 -0700 Subject: kset: convert struct bus_device->drivers to use kset_create Dynamically create the kset instead of declaring it statically. Having 3 static kobjects in one structure is not only foolish, but ripe for nasty race conditions if handled improperly. We also rename the field to catch any potential users of it (not that there should be outside of the driver core...) Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 82c277771376..110ace0dec3f 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -54,7 +54,7 @@ struct bus_type { struct module * owner; struct kset subsys; - struct kset drivers; + struct kset *drivers_kset; struct kset *devices_kset; struct klist klist_devices; struct klist klist_drivers; -- cgit v1.2.3 From 23b5212cc7422f475b82124334b64277b5b43013 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Fri, 2 Nov 2007 13:47:53 +0100 Subject: Driver Core: add kobj_attribute handling Add kobj_sysfs_ops to replace subsys_sysfs_ops. There is no need for special kset operations, we want to be able to use simple attribute operations at any kobject, not only ksets. The whole concept of any default sysfs attribute operations will go away with the upcoming removal of subsys_sysfs_ops. Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index a6dd669cda9d..e694261de90f 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -126,6 +126,16 @@ struct kset_uevent_ops { struct kobj_uevent_env *env); }; +struct kobj_attribute { + struct attribute attr; + ssize_t (*show)(struct kobject *kobj, struct kobj_attribute *attr, + char *buf); + ssize_t (*store)(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count); +}; + +extern struct sysfs_ops kobj_sysfs_ops; + /** * struct kset - a set of kobjects of a specific type, belonging to a specific subsystem. * -- cgit v1.2.3 From eb41d9465cdafee45e0cb30f3b7338646221908e Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Fri, 2 Nov 2007 13:47:53 +0100 Subject: fix struct user_info export's sysfs interaction Clean up the use of ksets and kobjects. Kobjects are instances of objects (like struct user_info), ksets are collections of objects of a similar type (like the uids directory containing the user_info directories). So, use kobjects for the user_info directories, and a kset for the "uids" directory. On object cleanup, the final kobject_put() was missing. Cc: Dhaval Giani Cc: Srivatsa Vaddagiri Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/sched.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index cc14656f8682..d6eacda765ca 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -552,18 +552,13 @@ struct user_struct { #ifdef CONFIG_FAIR_USER_SCHED struct task_group *tg; #ifdef CONFIG_SYSFS - struct kset kset; - struct subsys_attribute user_attr; + struct kobject kobj; struct work_struct work; #endif #endif }; -#ifdef CONFIG_FAIR_USER_SCHED -extern int uids_kobject_init(void); -#else -static inline int uids_kobject_init(void) { return 0; } -#endif +extern int uids_sysfs_init(void); extern struct user_struct *find_user(uid_t); -- cgit v1.2.3 From 9e5f7f9abe18a4f134585a2de016974cbda80539 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 2 Nov 2007 13:20:40 -0700 Subject: firmware: export firmware_kset so that people can use that instead of the braindead firmware_register interface Needed for future firmware subsystem cleanups. In the end, the firmware_register/unregister functions will be deleted entirely, but we need this symbol so that subsystems can migrate over. Cc: Kay Sievers Cc: Matt Domsch Cc: Matt Tolentino Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index e694261de90f..29dc444e3361 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -210,6 +210,8 @@ extern struct kset *kernel_kset; extern struct kobject *hypervisor_kobj; /* The global /sys/power/ kset for people to chain off of */ extern struct kset *power_kset; +/* The global /sys/firmware/ kset for people to chain off of */ +extern struct kset *firmware_kset; extern int __must_check subsystem_register(struct kset *); extern void subsystem_unregister(struct kset *); -- cgit v1.2.3 From 000f2a4d8cfc1e1cbc0aa98136015e7ae7719b46 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Fri, 2 Nov 2007 13:47:53 +0100 Subject: Driver Core: kill subsys_attribute and default sysfs ops Remove the no longer needed subsys_attributes, they are all converted to the more sensical kobj_attributes. There is no longer a magic fallback in sysfs attribute operations, all kobjects which create simple attributes need explicitely a ktype assigned, which tells the core what was intended here. Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 29dc444e3361..29841bb5badb 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -216,15 +216,6 @@ extern struct kset *firmware_kset; extern int __must_check subsystem_register(struct kset *); extern void subsystem_unregister(struct kset *); -struct subsys_attribute { - struct attribute attr; - ssize_t (*show)(struct kset *, char *); - ssize_t (*store)(struct kset *, const char *, size_t); -}; - -extern int __must_check subsys_create_file(struct kset *, - struct subsys_attribute *); - #if defined(CONFIG_HOTPLUG) int kobject_uevent(struct kobject *kobj, enum kobject_action action); int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, -- cgit v1.2.3 From 15f2f9b3a9db65aaf908fe7ee17bbe262ae3550f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 2 Nov 2007 16:19:59 -0700 Subject: firmware: remove firmware_(un)register() These functions are no longer called or needed, so we can remove them. As I rewrote the whole firmware.c file, add my copyright. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 110ace0dec3f..a3b3ff15fc87 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -555,11 +555,6 @@ extern void device_shutdown(void); /* drivers/base/sys.c */ extern void sysdev_shutdown(void); - -/* drivers/base/firmware.c */ -extern int __must_check firmware_register(struct kset *); -extern void firmware_unregister(struct kset *); - /* debugging and troubleshooting/diagnostic helpers. */ extern const char *dev_driver_string(struct device *dev); #define dev_printk(level, dev, format, arg...) \ -- cgit v1.2.3 From f62ed9e33b3ccff54d66b08f82d11940bb9e269b Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 5 Nov 2007 13:16:15 -0800 Subject: firmware: change firmware_kset to firmware_kobj There is no firmware "subsystem" it's just a directory in /sys that other portions of the kernel want to hook into. So make it a kobject not a kset to help alivate anyone who tries to do some odd kset-like things with this. Cc: Kay Sievers Cc: Cornelia Huck Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 29841bb5badb..673623f18464 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -210,8 +210,8 @@ extern struct kset *kernel_kset; extern struct kobject *hypervisor_kobj; /* The global /sys/power/ kset for people to chain off of */ extern struct kset *power_kset; -/* The global /sys/firmware/ kset for people to chain off of */ -extern struct kset *firmware_kset; +/* The global /sys/firmware/ kobject for people to chain off of */ +extern struct kobject *firmware_kobj; extern int __must_check subsystem_register(struct kset *); extern void subsystem_unregister(struct kset *); -- cgit v1.2.3 From 5c03c7ab886859eb195440dbb6ccb8c30c4e84cc Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 2 Nov 2007 16:19:59 -0700 Subject: kset: remove decl_subsys macro This macro is no longer used. ksets should be created dynamically with a call to kset_create_and_add() not declared statically. Yes, there are 5 remaining static struct kset usages in the kernel tree, but they will be fixed up soon. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 673623f18464..9da3523e4a65 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -198,12 +198,6 @@ extern struct kobject * kset_find_obj(struct kset *, const char *); #define set_kset_name(str) .kset = { .kobj = { .k_name = str } } -#define decl_subsys(_name,_uevent_ops) \ -struct kset _name##_subsys = { \ - .kobj = { .k_name = __stringify(_name) }, \ - .uevent_ops =_uevent_ops, \ -} - /* The global /sys/kernel/ kset for people to chain off of */ extern struct kset *kernel_kset; /* The global /sys/hypervisor/ kobject for people to chain off of */ -- cgit v1.2.3 From 0ff21e46630abce11fdaaffabd72bbd4eed5ac2c Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 6 Nov 2007 10:36:58 -0800 Subject: kobject: convert kernel_kset to be a kobject kernel_kset does not need to be a kset, but a much simpler kobject now that we have kobj_attributes. We also rename kernel_kset to kernel_kobj to catch all users of this symbol with a build error instead of an easy-to-ignore build warning. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 9da3523e4a65..0930efdcc094 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -198,8 +198,8 @@ extern struct kobject * kset_find_obj(struct kset *, const char *); #define set_kset_name(str) .kset = { .kobj = { .k_name = str } } -/* The global /sys/kernel/ kset for people to chain off of */ -extern struct kset *kernel_kset; +/* The global /sys/kernel/ kobject for people to chain off of */ +extern struct kobject *kernel_kobj; /* The global /sys/hypervisor/ kobject for people to chain off of */ extern struct kobject *hypervisor_kobj; /* The global /sys/power/ kset for people to chain off of */ -- cgit v1.2.3 From 2fb9113b974c3c7c43e76647bd5077238e274e1c Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 6 Nov 2007 15:03:30 -0800 Subject: kobject: remove subsystem_(un)register functions These functions are no longer used and are the last remants of the old subsystem crap. So delete them for good. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 0930efdcc094..78c851b4e67e 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -207,9 +207,6 @@ extern struct kset *power_kset; /* The global /sys/firmware/ kobject for people to chain off of */ extern struct kobject *firmware_kobj; -extern int __must_check subsystem_register(struct kset *); -extern void subsystem_unregister(struct kset *); - #if defined(CONFIG_HOTPLUG) int kobject_uevent(struct kobject *kobj, enum kobject_action action); int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, -- cgit v1.2.3 From d76e15fb20eeb7632ef38876a884fe3508b2c01d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 27 Nov 2007 11:28:26 -0800 Subject: driver core: make /sys/power a kobject /sys/power should not be a kset, that's overkill. This patch renames it to power_kset and fixes up all usages of it in the tree. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 78c851b4e67e..bb6868475edb 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -202,8 +202,8 @@ extern struct kobject * kset_find_obj(struct kset *, const char *); extern struct kobject *kernel_kobj; /* The global /sys/hypervisor/ kobject for people to chain off of */ extern struct kobject *hypervisor_kobj; -/* The global /sys/power/ kset for people to chain off of */ -extern struct kset *power_kset; +/* The global /sys/power/ kobject for people to chain off of */ +extern struct kobject *power_kobj; /* The global /sys/firmware/ kobject for people to chain off of */ extern struct kobject *firmware_kobj; -- cgit v1.2.3 From 81e7c6a636c81d9eeaeaa732bfbace44535fab00 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 4 Dec 2007 22:41:54 +0000 Subject: UIO: fix kobject usage The uio kobject code is "wierd". This patch should hopefully fix it up to be sane and not leak memory anymore. Cc: Kay Sievers Cc: Thomas Gleixner Cc: Benedikt Spranger Signed-off-by: Hans J. Koch Signed-off-by: Greg Kroah-Hartman --- include/linux/uio_driver.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h index 44c28e94df50..973386d439da 100644 --- a/include/linux/uio_driver.h +++ b/include/linux/uio_driver.h @@ -18,20 +18,22 @@ #include #include +struct uio_map; + /** * struct uio_mem - description of a UIO memory region - * @kobj: kobject for this mapping * @addr: address of the device's memory * @size: size of IO * @memtype: type of memory addr points to * @internal_addr: ioremap-ped version of addr, for driver internal use + * @map: for use by the UIO core only. */ struct uio_mem { - struct kobject kobj; unsigned long addr; unsigned long size; int memtype; void __iomem *internal_addr; + struct uio_map *map; }; #define MAX_UIO_MAPS 5 -- cgit v1.2.3 From cc972e896b303f453f5893ecf8eca0d0e395ab64 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 1 Nov 2007 13:31:26 -0700 Subject: driver core: remove owner field from struct bus_type This isn't used by anything in the driver core, and by no one in the 204 different usages of it in the kernel tree. Remove this field so no one gets any idea that it is needed to be used. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index a3b3ff15fc87..313e0b32bc09 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -51,7 +51,6 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); struct bus_type { const char * name; - struct module * owner; struct kset subsys; struct kset *drivers_kset; -- cgit v1.2.3 From 0fed80f7a63abd7168907267af69ee31f6bcf301 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 1 Nov 2007 19:41:16 -0700 Subject: driver core: add way to get to bus kset This allows an easier way to get to the kset associated with a struct bus_type (you have three to choose from...) This will make it easier to move these fields to be dynamic in a future patch. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 313e0b32bc09..3cc13c32314a 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -117,6 +117,8 @@ extern int bus_unregister_notifier(struct bus_type *bus, #define BUS_NOTIFY_UNBIND_DRIVER 0x00000004 /* driver about to be unbound */ +extern struct kset *bus_get_kset(struct bus_type *bus); + struct device_driver { const char * name; struct bus_type * bus; -- cgit v1.2.3 From b249072ee6897fe4f8d461c7bb4b926223263c28 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 1 Nov 2007 19:41:16 -0700 Subject: driver core: add way to get to bus device klist This allows an easier way to get to the device klist associated with a struct bus_type (you have three to choose from...) This will make it easier to move these fields to be dynamic in a future patch. The only user of this is the PCI core which horribly abuses this interface to rearrange the order of the pci devices. This should be done using the existing bus device walking functions, but that's left for future patches. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 3cc13c32314a..62e695bd3c93 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -118,6 +118,7 @@ extern int bus_unregister_notifier(struct bus_type *bus, unbound */ extern struct kset *bus_get_kset(struct bus_type *bus); +extern struct klist *bus_get_device_klist(struct bus_type *bus); struct device_driver { const char * name; -- cgit v1.2.3 From c6f7e72a3f4641095ade9ded287d910c980c6148 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 1 Nov 2007 19:41:16 -0700 Subject: driver core: remove fields from struct bus_type struct bus_type is static everywhere in the kernel. This moves the kobject in the structure out of it, and a bunch of other private only to the driver core fields are now moved to a private structure. This lets us dynamically create the backing kobject properly and gives us the chance to be able to document to users exactly how to use the struct bus_type as there are no fields they can improperly access. Thanks to Kay for the build fixes on this patch. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 62e695bd3c93..3f24bf46d298 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -35,6 +35,7 @@ struct device_driver; struct class; struct class_device; struct bus_type; +struct bus_type_private; struct bus_attribute { struct attribute attr; @@ -51,15 +52,6 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); struct bus_type { const char * name; - - struct kset subsys; - struct kset *drivers_kset; - struct kset *devices_kset; - struct klist klist_devices; - struct klist klist_drivers; - - struct blocking_notifier_head bus_notifier; - struct bus_attribute * bus_attrs; struct device_attribute * dev_attrs; struct driver_attribute * drv_attrs; @@ -75,7 +67,7 @@ struct bus_type { int (*resume_early)(struct device * dev); int (*resume)(struct device * dev); - unsigned int drivers_autoprobe:1; + struct bus_type_private *p; }; extern int __must_check bus_register(struct bus_type * bus); -- cgit v1.2.3 From 57c745340a60c51d2b9af3d4dcf7e0ede284855b Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Wed, 5 Dec 2007 12:50:23 +0100 Subject: driver core: Introduce default attribute groups. This is lot like default attributes for devices (and indeed, a lot of the code is lifted from there). Signed-off-by: Cornelia Huck Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 3f24bf46d298..d974dda4aa51 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -129,6 +129,7 @@ struct device_driver { void (*shutdown) (struct device * dev); int (*suspend) (struct device * dev, pm_message_t state); int (*resume) (struct device * dev); + struct attribute_group **groups; }; -- cgit v1.2.3 From cbe9c595f1de2e2a98403be2c14bfbc2486e84c4 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 19 Dec 2007 15:54:39 -0400 Subject: Driver: add driver_add_kobj for looney iseries_veth driver The iseries driver wants to hang kobjects off of its driver, so, to preserve backwards compatibility, we need to add a call to the driver core to allow future changes to work properly. Hopefully no one uses this function in the future and the iseries_veth driver authors come to their senses so I can remove this hack... Cc: Dave Larson Cc: Santiago Leon Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index d974dda4aa51..721ee318d57b 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -156,6 +156,10 @@ extern int __must_check driver_create_file(struct device_driver *, struct driver_attribute *); extern void driver_remove_file(struct device_driver *, struct driver_attribute *); +extern int __must_check driver_add_kobj(struct device_driver *drv, + struct kobject *kobj, + const char *fmt, ...); + extern int __must_check driver_for_each_device(struct device_driver * drv, struct device *start, void *data, int (*fn)(struct device *, void *)); -- cgit v1.2.3 From c63469a3985a9771c18a916b8d42845d044ea0b1 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 28 Nov 2007 12:23:18 -0800 Subject: Driver core: move the driver specific module code into the driver core The module driver specific code should belong in the driver core, not in the kernel/ directory. So move this code. This is done in preparation for some struct device_driver rework that should be confined to the driver core code only. This also lets us keep from exporting these functions, as no external code should ever be calling it. Thanks to Andrew Morton for the !CONFIG_MODULES fix. Signed-off-by: Greg Kroah-Hartman --- include/linux/module.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index fbe930b9b69c..c97bdb7eb957 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -609,21 +609,6 @@ static inline void module_remove_modinfo_attrs(struct module *mod) #endif /* CONFIG_SYSFS */ -#if defined(CONFIG_SYSFS) && defined(CONFIG_MODULES) - -void module_add_driver(struct module *mod, struct device_driver *drv); -void module_remove_driver(struct device_driver *drv); - -#else /* not both CONFIG_SYSFS && CONFIG_MODULES */ - -static inline void module_add_driver(struct module *mod, struct device_driver *drv) -{ } - -static inline void module_remove_driver(struct device_driver *drv) -{ } - -#endif - #define symbol_request(x) try_then_request_module(symbol_get(x), "symbol:" #x) /* BELOW HERE ALL THESE ARE OBSOLETE AND WILL VANISH */ -- cgit v1.2.3 From e5dd12784617f0f1fae5f96a7fac1ec4c49fadbe Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 28 Nov 2007 15:59:15 -0800 Subject: Driver core: move the static kobject out of struct driver This patch removes the kobject, and a few other driver-core-only fields out of struct driver and into the driver core only. Now drivers can be safely create on the stack or statically (like they currently are.) Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 721ee318d57b..92ba3a874627 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -32,6 +32,7 @@ struct device; struct device_driver; +struct driver_private; struct class; struct class_device; struct bus_type; @@ -113,16 +114,11 @@ extern struct kset *bus_get_kset(struct bus_type *bus); extern struct klist *bus_get_device_klist(struct bus_type *bus); struct device_driver { - const char * name; - struct bus_type * bus; - - struct kobject kobj; - struct klist klist_devices; - struct klist_node knode_bus; + const char *name; + struct bus_type *bus; - struct module * owner; - const char * mod_name; /* used for built-in modules */ - struct module_kobject * mkobj; + struct module *owner; + const char *mod_name; /* used for built-in modules */ int (*probe) (struct device * dev); int (*remove) (struct device * dev); @@ -130,6 +126,8 @@ struct device_driver { int (*suspend) (struct device * dev, pm_message_t state); int (*resume) (struct device * dev); struct attribute_group **groups; + + struct driver_private *p; }; -- cgit v1.2.3 From edfaa7c36574f1bf09c65ad602412db9da5f96bf Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Mon, 21 May 2007 22:08:01 +0200 Subject: Driver core: convert block from raw kobjects to core devices This moves the block devices to /sys/class/block. It will create a flat list of all block devices, with the disks and partitions in one directory. For compatibility /sys/block is created and contains symlinks to the disks. /sys/class/block |-- sda -> ../../devices/pci0000:00/0000:00:1f.2/host0/target0:0:0/0:0:0:0/block/sda |-- sda1 -> ../../devices/pci0000:00/0000:00:1f.2/host0/target0:0:0/0:0:0:0/block/sda/sda1 |-- sda10 -> ../../devices/pci0000:00/0000:00:1f.2/host0/target0:0:0/0:0:0:0/block/sda/sda10 |-- sda5 -> ../../devices/pci0000:00/0000:00:1f.2/host0/target0:0:0/0:0:0:0/block/sda/sda5 |-- sda6 -> ../../devices/pci0000:00/0000:00:1f.2/host0/target0:0:0/0:0:0:0/block/sda/sda6 |-- sda7 -> ../../devices/pci0000:00/0000:00:1f.2/host0/target0:0:0/0:0:0:0/block/sda/sda7 |-- sda8 -> ../../devices/pci0000:00/0000:00:1f.2/host0/target0:0:0/0:0:0:0/block/sda/sda8 |-- sda9 -> ../../devices/pci0000:00/0000:00:1f.2/host0/target0:0:0/0:0:0:0/block/sda/sda9 `-- sr0 -> ../../devices/pci0000:00/0000:00:1f.2/host1/target1:0:0/1:0:0:0/block/sr0 /sys/block/ |-- sda -> ../devices/pci0000:00/0000:00:1f.2/host0/target0:0:0/0:0:0:0/block/sda `-- sr0 -> ../devices/pci0000:00/0000:00:1f.2/host1/target1:0:0/1:0:0:0/block/sr0 Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/genhd.h | 37 +++++++++++++++++++++++-------------- 1 file changed, 23 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index a47b8025d399..1dbea0ac5693 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -10,9 +10,19 @@ */ #include +#include #ifdef CONFIG_BLOCK +#define kobj_to_dev(k) container_of(k, struct device, kobj) +#define dev_to_disk(device) container_of(device, struct gendisk, dev) +#define dev_to_part(device) container_of(device, struct hd_struct, dev) + +extern struct device_type disk_type; +extern struct device_type part_type; +extern struct kobject *block_depr; +extern struct class block_class; + enum { /* These three have identical behaviour; use the second one if DOS FDISK gets confused about extended/logical partitions starting past cylinder 1023. */ @@ -84,7 +94,7 @@ struct partition { struct hd_struct { sector_t start_sect; sector_t nr_sects; - struct kobject kobj; + struct device dev; struct kobject *holder_dir; unsigned ios[2], sectors[2]; /* READs and WRITEs */ int policy, partno; @@ -117,15 +127,14 @@ struct gendisk { * disks that can't be partitioned. */ char disk_name[32]; /* name of major driver */ struct hd_struct **part; /* [indexed by minor] */ - int part_uevent_suppress; struct block_device_operations *fops; struct request_queue *queue; void *private_data; sector_t capacity; int flags; - struct device *driverfs_dev; - struct kobject kobj; + struct device *driverfs_dev; // FIXME: remove + struct device dev; struct kobject *holder_dir; struct kobject *slave_dir; @@ -143,13 +152,6 @@ struct gendisk { struct work_struct async_notify; }; -/* Structure for sysfs attributes on block devices */ -struct disk_attribute { - struct attribute attr; - ssize_t (*show)(struct gendisk *, char *); - ssize_t (*store)(struct gendisk *, const char *, size_t); -}; - /* * Macros to operate on percpu disk statistics: * @@ -411,7 +413,8 @@ struct unixware_disklabel { #define ADDPART_FLAG_RAID 1 #define ADDPART_FLAG_WHOLEDISK 2 -char *disk_name (struct gendisk *hd, int part, char *buf); +extern dev_t blk_lookup_devt(const char *name); +extern char *disk_name (struct gendisk *hd, int part, char *buf); extern int rescan_partitions(struct gendisk *disk, struct block_device *bdev); extern void add_partition(struct gendisk *, int, sector_t, sector_t, int); @@ -423,12 +426,12 @@ extern struct gendisk *alloc_disk(int minors); extern struct kobject *get_disk(struct gendisk *disk); extern void put_disk(struct gendisk *disk); extern void genhd_media_change_notify(struct gendisk *disk); -extern void blk_register_region(dev_t dev, unsigned long range, +extern void blk_register_region(dev_t devt, unsigned long range, struct module *module, struct kobject *(*probe)(dev_t, int *, void *), int (*lock)(dev_t, void *), void *data); -extern void blk_unregister_region(dev_t dev, unsigned long range); +extern void blk_unregister_region(dev_t devt, unsigned long range); static inline struct block_device *bdget_disk(struct gendisk *disk, int index) { @@ -441,6 +444,12 @@ static inline struct block_device *bdget_disk(struct gendisk *disk, int index) static inline void printk_all_partitions(void) { } +static inline dev_t blk_lookup_devt(const char *name) +{ + dev_t devt = MKDEV(0, 0); + return devt; +} + #endif /* CONFIG_BLOCK */ #endif -- cgit v1.2.3 From 9e7bbccd0290e720e0874443932869c55f63d5a8 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 17 Dec 2007 23:05:35 -0700 Subject: Kobject: remove kobject_add() as no one uses it anymore The old kobject_add() function is on longer in use, so let us remove it from the public scope (kset mess in the kobject.c file still uses it, but that can be cleaned up later very simply.) Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index bb6868475edb..8b0aa715fa2f 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -80,7 +80,6 @@ static inline const char * kobject_name(const struct kobject * kobj) extern void kobject_init(struct kobject *); extern void kobject_init_ng(struct kobject *kobj, struct kobj_type *ktype); -extern int __must_check kobject_add(struct kobject *); extern int __must_check kobject_add_ng(struct kobject *kobj, struct kobject *parent, const char *fmt, ...); -- cgit v1.2.3 From b2d6db5878a0832659ed58476357eea2db915550 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 17 Dec 2007 23:05:35 -0700 Subject: Kobject: rename kobject_add_ng() to kobject_add() Now that the old kobject_add() function is gone, rename kobject_add_ng() to kobject_add() to clean up the namespace. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 8b0aa715fa2f..84c5afd58899 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -80,9 +80,9 @@ static inline const char * kobject_name(const struct kobject * kobj) extern void kobject_init(struct kobject *); extern void kobject_init_ng(struct kobject *kobj, struct kobj_type *ktype); -extern int __must_check kobject_add_ng(struct kobject *kobj, - struct kobject *parent, - const char *fmt, ...); +extern int __must_check kobject_add(struct kobject *kobj, + struct kobject *parent, + const char *fmt, ...); extern int __must_check kobject_init_and_add(struct kobject *kobj, struct kobj_type *ktype, struct kobject *parent, -- cgit v1.2.3 From e1543ddf739b22a8c4218716ad50c26b3e147403 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 17 Dec 2007 23:05:35 -0700 Subject: Kobject: remove kobject_init() as no one uses it anymore The old kobject_init() function is on longer in use, so let us remove it from the public scope (kset mess in the kobject.c file still uses it, but that can be cleaned up later very simply.) Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 84c5afd58899..53458b674fae 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -78,7 +78,6 @@ static inline const char * kobject_name(const struct kobject * kobj) return kobj->k_name; } -extern void kobject_init(struct kobject *); extern void kobject_init_ng(struct kobject *kobj, struct kobj_type *ktype); extern int __must_check kobject_add(struct kobject *kobj, struct kobject *parent, -- cgit v1.2.3 From f9cb074bff8e762ef24c44678a5a7d907f82fbeb Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 17 Dec 2007 23:05:35 -0700 Subject: Kobject: rename kobject_init_ng() to kobject_init() Now that the old kobject_init() function is gone, rename kobject_init_ng() to kobject_init() to clean up the namespace. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 53458b674fae..d9d8c368f044 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -78,7 +78,7 @@ static inline const char * kobject_name(const struct kobject * kobj) return kobj->k_name; } -extern void kobject_init_ng(struct kobject *kobj, struct kobj_type *ktype); +extern void kobject_init(struct kobject *kobj, struct kobj_type *ktype); extern int __must_check kobject_add(struct kobject *kobj, struct kobject *parent, const char *fmt, ...); -- cgit v1.2.3 From 6d06adfaf82d154023141ddc0c9de18b6a49090b Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 19 Dec 2007 11:26:50 -0800 Subject: Kobject: remove kobject_register() The function is no longer used by anyone in the kernel, and it prevents the proper sending of the kobject uevent after the needed files are set up by the caller. kobject_init_and_add() can be used in its place. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index d9d8c368f044..259084758617 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -96,7 +96,6 @@ extern struct kobject * __must_check kobject_create_and_add(const char *name, extern int __must_check kobject_rename(struct kobject *, const char *new_name); extern int __must_check kobject_move(struct kobject *, struct kobject *); -extern int __must_check kobject_register(struct kobject *); extern void kobject_unregister(struct kobject *); extern struct kobject * kobject_get(struct kobject *); -- cgit v1.2.3 From 12e339ac6e31a34fe42396aec8fb1c0b43caf61e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 9 Apr 2002 12:14:34 -0700 Subject: Kset: remove kset_add function No one is calling this anymore, so just remove it and hard-code the one internal-use of it. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 259084758617..63967da073af 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -158,7 +158,6 @@ struct kset { }; extern void kset_init(struct kset * k); -extern int __must_check kset_add(struct kset * k); extern int __must_check kset_register(struct kset * k); extern void kset_unregister(struct kset * k); extern struct kset * __must_check kset_create_and_add(const char *name, -- cgit v1.2.3 From 0f4dafc0563c6c49e17fe14b3f5f356e4c4b8806 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Wed, 19 Dec 2007 01:40:42 +0100 Subject: Kobject: auto-cleanup on final unref We save the current state in the object itself, so we can do proper cleanup when the last reference is dropped. If the initial reference is dropped, the object will be removed from sysfs if needed, if an "add" event was sent, "remove" will be send, and the allocated resources are released. This allows us to clean up some driver core usage as well as allowing us to do other such changes to the rest of the kernel. Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 63967da073af..be03ce83f9cc 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -68,6 +68,11 @@ struct kobject { struct kset * kset; struct kobj_type * ktype; struct sysfs_dirent * sd; + unsigned int state_initialized:1; + unsigned int state_name_set:1; + unsigned int state_in_sysfs:1; + unsigned int state_add_uevent_sent:1; + unsigned int state_remove_uevent_sent:1; }; extern int kobject_set_name(struct kobject *, const char *, ...) -- cgit v1.2.3 From 528a4bf1d5ffed310d26fc1d82d45c02949f71cf Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 20 Dec 2007 08:13:05 -0800 Subject: Kobject: remove kobject_unregister() as no one uses it anymore There are no in-kernel users of kobject_unregister() so it should be removed. Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index be03ce83f9cc..504ac0eb4412 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -101,8 +101,6 @@ extern struct kobject * __must_check kobject_create_and_add(const char *name, extern int __must_check kobject_rename(struct kobject *, const char *new_name); extern int __must_check kobject_move(struct kobject *, struct kobject *); -extern void kobject_unregister(struct kobject *); - extern struct kobject * kobject_get(struct kobject *); extern void kobject_put(struct kobject *); -- cgit v1.2.3 From af5ca3f4ec5cc4432a42a73b050dd8898ce8fd00 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Thu, 20 Dec 2007 02:09:39 +0100 Subject: Driver core: change sysdev classes to use dynamic kobject names All kobjects require a dynamically allocated name now. We no longer need to keep track if the name is statically assigned, we can just unconditionally free() all kobject names on cleanup. Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 13 ++----------- include/linux/sysdev.h | 1 + 2 files changed, 3 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 504ac0eb4412..4adbe1d83081 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -61,7 +61,7 @@ enum kobject_action { }; struct kobject { - const char * k_name; + const char *name; struct kref kref; struct list_head entry; struct kobject * parent; @@ -69,7 +69,6 @@ struct kobject { struct kobj_type * ktype; struct sysfs_dirent * sd; unsigned int state_initialized:1; - unsigned int state_name_set:1; unsigned int state_in_sysfs:1; unsigned int state_add_uevent_sent:1; unsigned int state_remove_uevent_sent:1; @@ -80,7 +79,7 @@ extern int kobject_set_name(struct kobject *, const char *, ...) static inline const char * kobject_name(const struct kobject * kobj) { - return kobj->k_name; + return kobj->name; } extern void kobject_init(struct kobject *kobj, struct kobj_type *ktype); @@ -189,14 +188,6 @@ static inline struct kobj_type *get_ktype(struct kobject *kobj) extern struct kobject * kset_find_obj(struct kset *, const char *); - -/* - * Use this when initializing an embedded kset with no other - * fields to initialize. - */ -#define set_kset_name(str) .kset = { .kobj = { .k_name = str } } - - /* The global /sys/kernel/ kobject for people to chain off of */ extern struct kobject *kernel_kobj; /* The global /sys/hypervisor/ kobject for people to chain off of */ diff --git a/include/linux/sysdev.h b/include/linux/sysdev.h index e285746588d6..f752e73bf977 100644 --- a/include/linux/sysdev.h +++ b/include/linux/sysdev.h @@ -29,6 +29,7 @@ struct sys_device; struct sysdev_class { + const char *name; struct list_head drivers; /* Default operations for these types of devices */ -- cgit v1.2.3 From ae72cddb2338bc36b991674a56a7bf70ae104d9e Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Fri, 11 Jan 2008 17:24:53 +1100 Subject: Driver Core: constify the name passed to platform_device_register_simple This name is just passed to platform_device_alloc which has its parameter declared const. Signed-off-by: Stephen Rothwell Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index e80804316cdb..3261681c82a4 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -35,7 +35,7 @@ extern struct resource *platform_get_resource_byname(struct platform_device *, u extern int platform_get_irq_byname(struct platform_device *, char *); extern int platform_add_devices(struct platform_device **, int); -extern struct platform_device *platform_device_register_simple(char *, int id, +extern struct platform_device *platform_device_register_simple(const char *, int id, struct resource *, unsigned int); extern struct platform_device *platform_device_alloc(const char *name, int id); -- cgit v1.2.3 From fd04897bb20be29d60f7e426a053545aebeaa61a Mon Sep 17 00:00:00 2001 From: Dave Young Date: Tue, 22 Jan 2008 15:27:08 +0800 Subject: Driver Core: add class iteration api Add the following class iteration functions for driver use: class_for_each_device class_find_device class_for_each_child class_find_child Signed-off-by: Dave Young Acked-by: Cornelia Huck Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 92ba3a874627..cdaf57bf4d19 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -177,8 +177,7 @@ struct class { struct list_head devices; struct list_head interfaces; struct kset class_dirs; - struct semaphore sem; /* locks both the children and interfaces lists */ - + struct semaphore sem; /* locks children, devices, interfaces */ struct class_attribute * class_attrs; struct class_device_attribute * class_dev_attrs; struct device_attribute * dev_attrs; @@ -196,6 +195,12 @@ struct class { extern int __must_check class_register(struct class *); extern void class_unregister(struct class *); +extern int class_for_each_device(struct class *class, void *data, + int (*fn)(struct device *dev, void *data)); +extern struct device *class_find_device(struct class *class, void *data, + int (*match)(struct device *, void *)); +extern struct class_device *class_find_child(struct class *class, void *data, + int (*match)(struct class_device *, void *)); struct class_attribute { -- cgit v1.2.3 From d462943afee8bff610258a82dba666e8ab72c9c8 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 24 Jan 2008 21:04:46 -0800 Subject: Driver core: fix coding style issues in device.h Finally clean up the odd spaces and other mess in device.h Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 283 +++++++++++++++++++++++++------------------------ 1 file changed, 145 insertions(+), 138 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index cdaf57bf4d19..1880208964d6 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -25,7 +25,8 @@ #include #define DEVICE_NAME_SIZE 50 -#define DEVICE_NAME_HALF __stringify(20) /* Less than half to accommodate slop */ +/* DEVICE_NAME_HALF is really less than half to accommodate slop */ +#define DEVICE_NAME_HALF __stringify(20) #define DEVICE_ID_SIZE 32 #define BUS_ID_SIZE KOBJ_NAME_LEN @@ -40,52 +41,53 @@ struct bus_type_private; struct bus_attribute { struct attribute attr; - ssize_t (*show)(struct bus_type *, char * buf); - ssize_t (*store)(struct bus_type *, const char * buf, size_t count); + ssize_t (*show)(struct bus_type *bus, char *buf); + ssize_t (*store)(struct bus_type *bus, const char *buf, size_t count); }; -#define BUS_ATTR(_name,_mode,_show,_store) \ -struct bus_attribute bus_attr_##_name = __ATTR(_name,_mode,_show,_store) +#define BUS_ATTR(_name, _mode, _show, _store) \ +struct bus_attribute bus_attr_##_name = __ATTR(_name, _mode, _show, _store) extern int __must_check bus_create_file(struct bus_type *, struct bus_attribute *); extern void bus_remove_file(struct bus_type *, struct bus_attribute *); struct bus_type { - const char * name; - struct bus_attribute * bus_attrs; - struct device_attribute * dev_attrs; - struct driver_attribute * drv_attrs; - - int (*match)(struct device * dev, struct device_driver * drv); - int (*uevent)(struct device *dev, struct kobj_uevent_env *env); - int (*probe)(struct device * dev); - int (*remove)(struct device * dev); - void (*shutdown)(struct device * dev); - - int (*suspend)(struct device * dev, pm_message_t state); - int (*suspend_late)(struct device * dev, pm_message_t state); - int (*resume_early)(struct device * dev); - int (*resume)(struct device * dev); + const char *name; + struct bus_attribute *bus_attrs; + struct device_attribute *dev_attrs; + struct driver_attribute *drv_attrs; + + int (*match)(struct device *dev, struct device_driver *drv); + int (*uevent)(struct device *dev, struct kobj_uevent_env *env); + int (*probe)(struct device *dev); + int (*remove)(struct device *dev); + void (*shutdown)(struct device *dev); + + int (*suspend)(struct device *dev, pm_message_t state); + int (*suspend_late)(struct device *dev, pm_message_t state); + int (*resume_early)(struct device *dev); + int (*resume)(struct device *dev); struct bus_type_private *p; }; -extern int __must_check bus_register(struct bus_type * bus); -extern void bus_unregister(struct bus_type * bus); +extern int __must_check bus_register(struct bus_type *bus); +extern void bus_unregister(struct bus_type *bus); -extern int __must_check bus_rescan_devices(struct bus_type * bus); +extern int __must_check bus_rescan_devices(struct bus_type *bus); /* iterator helpers for buses */ -int bus_for_each_dev(struct bus_type * bus, struct device * start, void * data, - int (*fn)(struct device *, void *)); -struct device * bus_find_device(struct bus_type *bus, struct device *start, - void *data, int (*match)(struct device *, void *)); +int bus_for_each_dev(struct bus_type *bus, struct device *start, void *data, + int (*fn)(struct device *dev, void *data)); +struct device *bus_find_device(struct bus_type *bus, struct device *start, + void *data, + int (*match)(struct device *dev, void *data)); int __must_check bus_for_each_drv(struct bus_type *bus, - struct device_driver *start, void *data, - int (*fn)(struct device_driver *, void *)); + struct device_driver *start, void *data, + int (*fn)(struct device_driver *, void *)); /* * Bus notifiers: Get notified of addition/removal of devices @@ -120,57 +122,63 @@ struct device_driver { struct module *owner; const char *mod_name; /* used for built-in modules */ - int (*probe) (struct device * dev); - int (*remove) (struct device * dev); - void (*shutdown) (struct device * dev); - int (*suspend) (struct device * dev, pm_message_t state); - int (*resume) (struct device * dev); + int (*probe) (struct device *dev); + int (*remove) (struct device *dev); + void (*shutdown) (struct device *dev); + int (*suspend) (struct device *dev, pm_message_t state); + int (*resume) (struct device *dev); struct attribute_group **groups; struct driver_private *p; }; -extern int __must_check driver_register(struct device_driver * drv); -extern void driver_unregister(struct device_driver * drv); +extern int __must_check driver_register(struct device_driver *drv); +extern void driver_unregister(struct device_driver *drv); -extern struct device_driver * get_driver(struct device_driver * drv); -extern void put_driver(struct device_driver * drv); -extern struct device_driver *driver_find(const char *name, struct bus_type *bus); +extern struct device_driver *get_driver(struct device_driver *drv); +extern void put_driver(struct device_driver *drv); +extern struct device_driver *driver_find(const char *name, + struct bus_type *bus); extern int driver_probe_done(void); /* sysfs interface for exporting driver attributes */ struct driver_attribute { - struct attribute attr; - ssize_t (*show)(struct device_driver *, char * buf); - ssize_t (*store)(struct device_driver *, const char * buf, size_t count); + struct attribute attr; + ssize_t (*show)(struct device_driver *driver, char *buf); + ssize_t (*store)(struct device_driver *driver, const char *buf, + size_t count); }; -#define DRIVER_ATTR(_name,_mode,_show,_store) \ -struct driver_attribute driver_attr_##_name = __ATTR(_name,_mode,_show,_store) +#define DRIVER_ATTR(_name, _mode, _show, _store) \ +struct driver_attribute driver_attr_##_name = \ + __ATTR(_name, _mode, _show, _store) -extern int __must_check driver_create_file(struct device_driver *, - struct driver_attribute *); -extern void driver_remove_file(struct device_driver *, struct driver_attribute *); +extern int __must_check driver_create_file(struct device_driver *driver, + struct driver_attribute *attr); +extern void driver_remove_file(struct device_driver *driver, + struct driver_attribute *attr); extern int __must_check driver_add_kobj(struct device_driver *drv, struct kobject *kobj, const char *fmt, ...); -extern int __must_check driver_for_each_device(struct device_driver * drv, - struct device *start, void *data, - int (*fn)(struct device *, void *)); -struct device * driver_find_device(struct device_driver *drv, - struct device *start, void *data, - int (*match)(struct device *, void *)); +extern int __must_check driver_for_each_device(struct device_driver *drv, + struct device *start, + void *data, + int (*fn)(struct device *dev, + void *)); +struct device *driver_find_device(struct device_driver *drv, + struct device *start, void *data, + int (*match)(struct device *dev, void *data)); /* * device classes */ struct class { - const char * name; - struct module * owner; + const char *name; + struct module *owner; struct kset subsys; struct list_head children; @@ -178,23 +186,23 @@ struct class { struct list_head interfaces; struct kset class_dirs; struct semaphore sem; /* locks children, devices, interfaces */ - struct class_attribute * class_attrs; - struct class_device_attribute * class_dev_attrs; - struct device_attribute * dev_attrs; + struct class_attribute *class_attrs; + struct class_device_attribute *class_dev_attrs; + struct device_attribute *dev_attrs; - int (*uevent)(struct class_device *dev, struct kobj_uevent_env *env); - int (*dev_uevent)(struct device *dev, struct kobj_uevent_env *env); + int (*uevent)(struct class_device *dev, struct kobj_uevent_env *env); + int (*dev_uevent)(struct device *dev, struct kobj_uevent_env *env); - void (*release)(struct class_device *dev); - void (*class_release)(struct class *class); - void (*dev_release)(struct device *dev); + void (*release)(struct class_device *dev); + void (*class_release)(struct class *class); + void (*dev_release)(struct device *dev); - int (*suspend)(struct device *, pm_message_t state); - int (*resume)(struct device *); + int (*suspend)(struct device *dev, pm_message_t state); + int (*resume)(struct device *dev); }; -extern int __must_check class_register(struct class *); -extern void class_unregister(struct class *); +extern int __must_check class_register(struct class *class); +extern void class_unregister(struct class *class); extern int class_for_each_device(struct class *class, void *data, int (*fn)(struct device *dev, void *data)); extern struct device *class_find_device(struct class *class, void *data, @@ -204,27 +212,28 @@ extern struct class_device *class_find_child(struct class *class, void *data, struct class_attribute { - struct attribute attr; - ssize_t (*show)(struct class *, char * buf); - ssize_t (*store)(struct class *, const char * buf, size_t count); + struct attribute attr; + ssize_t (*show)(struct class *class, char *buf); + ssize_t (*store)(struct class *class, const char *buf, size_t count); }; -#define CLASS_ATTR(_name,_mode,_show,_store) \ -struct class_attribute class_attr_##_name = __ATTR(_name,_mode,_show,_store) +#define CLASS_ATTR(_name, _mode, _show, _store) \ +struct class_attribute class_attr_##_name = __ATTR(_name, _mode, _show, _store) -extern int __must_check class_create_file(struct class *, - const struct class_attribute *); -extern void class_remove_file(struct class *, const struct class_attribute *); +extern int __must_check class_create_file(struct class *class, + const struct class_attribute *attr); +extern void class_remove_file(struct class *class, + const struct class_attribute *attr); struct class_device_attribute { - struct attribute attr; - ssize_t (*show)(struct class_device *, char * buf); - ssize_t (*store)(struct class_device *, const char * buf, size_t count); + struct attribute attr; + ssize_t (*show)(struct class_device *, char *buf); + ssize_t (*store)(struct class_device *, const char *buf, size_t count); }; -#define CLASS_DEVICE_ATTR(_name,_mode,_show,_store) \ +#define CLASS_DEVICE_ATTR(_name, _mode, _show, _store) \ struct class_device_attribute class_device_attr_##_name = \ - __ATTR(_name,_mode,_show,_store) + __ATTR(_name, _mode, _show, _store) extern int __must_check class_device_create_file(struct class_device *, const struct class_device_attribute *); @@ -257,26 +266,24 @@ struct class_device { struct list_head node; struct kobject kobj; - struct class * class; /* required */ - dev_t devt; /* dev_t, creates the sysfs "dev" */ - struct device * dev; /* not necessary, but nice to have */ - void * class_data; /* class-specific data */ - struct class_device *parent; /* parent of this child device, if there is one */ - struct attribute_group ** groups; /* optional groups */ - - void (*release)(struct class_device *dev); - int (*uevent)(struct class_device *dev, struct kobj_uevent_env *env); - char class_id[BUS_ID_SIZE]; /* unique to this class */ + struct class *class; + dev_t devt; + struct device *dev; + void *class_data; + struct class_device *parent; + struct attribute_group **groups; + + void (*release)(struct class_device *dev); + int (*uevent)(struct class_device *dev, struct kobj_uevent_env *env); + char class_id[BUS_ID_SIZE]; }; -static inline void * -class_get_devdata (struct class_device *dev) +static inline void *class_get_devdata(struct class_device *dev) { return dev->class_data; } -static inline void -class_set_devdata (struct class_device *dev, void *data) +static inline void class_set_devdata(struct class_device *dev, void *data) { dev->class_data = data; } @@ -288,10 +295,10 @@ extern void class_device_initialize(struct class_device *); extern int __must_check class_device_add(struct class_device *); extern void class_device_del(struct class_device *); -extern struct class_device * class_device_get(struct class_device *); +extern struct class_device *class_device_get(struct class_device *); extern void class_device_put(struct class_device *); -extern void class_device_remove_file(struct class_device *, +extern void class_device_remove_file(struct class_device *, const struct class_device_attribute *); extern int __must_check class_device_create_bin_file(struct class_device *, struct bin_attribute *); @@ -318,7 +325,7 @@ extern struct class_device *class_device_create(struct class *cls, dev_t devt, struct device *device, const char *fmt, ...) - __attribute__((format(printf,5,6))); + __attribute__((format(printf, 5, 6))); extern void class_device_destroy(struct class *cls, dev_t devt); /* @@ -335,8 +342,8 @@ struct device_type { struct attribute_group **groups; int (*uevent)(struct device *dev, struct kobj_uevent_env *env); void (*release)(struct device *dev); - int (*suspend)(struct device * dev, pm_message_t state); - int (*resume)(struct device * dev); + int (*suspend)(struct device *dev, pm_message_t state); + int (*resume)(struct device *dev); }; /* interface for exporting device attributes */ @@ -348,18 +355,19 @@ struct device_attribute { const char *buf, size_t count); }; -#define DEVICE_ATTR(_name,_mode,_show,_store) \ -struct device_attribute dev_attr_##_name = __ATTR(_name,_mode,_show,_store) +#define DEVICE_ATTR(_name, _mode, _show, _store) \ +struct device_attribute dev_attr_##_name = __ATTR(_name, _mode, _show, _store) extern int __must_check device_create_file(struct device *device, - struct device_attribute * entry); -extern void device_remove_file(struct device * dev, struct device_attribute * attr); + struct device_attribute *entry); +extern void device_remove_file(struct device *dev, + struct device_attribute *attr); extern int __must_check device_create_bin_file(struct device *dev, struct bin_attribute *attr); extern void device_remove_bin_file(struct device *dev, struct bin_attribute *attr); extern int device_schedule_callback_owner(struct device *dev, - void (*func)(struct device *), struct module *owner); + void (*func)(struct device *dev), struct module *owner); /* This is a macro to avoid include problems with THIS_MODULE */ #define device_schedule_callback(dev, func) \ @@ -370,21 +378,21 @@ typedef void (*dr_release_t)(struct device *dev, void *res); typedef int (*dr_match_t)(struct device *dev, void *res, void *match_data); #ifdef CONFIG_DEBUG_DEVRES -extern void * __devres_alloc(dr_release_t release, size_t size, gfp_t gfp, +extern void *__devres_alloc(dr_release_t release, size_t size, gfp_t gfp, const char *name); #define devres_alloc(release, size, gfp) \ __devres_alloc(release, size, gfp, #release) #else -extern void * devres_alloc(dr_release_t release, size_t size, gfp_t gfp); +extern void *devres_alloc(dr_release_t release, size_t size, gfp_t gfp); #endif extern void devres_free(void *res); extern void devres_add(struct device *dev, void *res); -extern void * devres_find(struct device *dev, dr_release_t release, - dr_match_t match, void *match_data); -extern void * devres_get(struct device *dev, void *new_res, +extern void *devres_find(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); -extern void * devres_remove(struct device *dev, dr_release_t release, - dr_match_t match, void *match_data); +extern void *devres_get(struct device *dev, void *new_res, + dr_match_t match, void *match_data); +extern void *devres_remove(struct device *dev, dr_release_t release, + dr_match_t match, void *match_data); extern int devres_destroy(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); @@ -401,7 +409,7 @@ extern void devm_kfree(struct device *dev, void *p); struct device { struct klist klist_children; - struct klist_node knode_parent; /* node in sibling list */ + struct klist_node knode_parent; /* node in sibling list */ struct klist_node knode_driver; struct klist_node knode_bus; struct device *parent; @@ -416,7 +424,7 @@ struct device { * its driver. */ - struct bus_type * bus; /* type of bus device is on */ + struct bus_type *bus; /* type of bus device is on */ struct device_driver *driver; /* which driver has allocated this device */ void *driver_data; /* data private to the driver */ @@ -447,10 +455,10 @@ struct device { /* class_device migration path */ struct list_head node; struct class *class; - dev_t devt; /* dev_t, creates the sysfs "dev" */ + dev_t devt; /* dev_t, creates the sysfs "dev" */ struct attribute_group **groups; /* optional groups */ - void (*release)(struct device * dev); + void (*release)(struct device *dev); }; #ifdef CONFIG_NUMA @@ -472,14 +480,12 @@ static inline void set_dev_node(struct device *dev, int node) } #endif -static inline void * -dev_get_drvdata (struct device *dev) +static inline void *dev_get_drvdata(struct device *dev) { return dev->driver_data; } -static inline void -dev_set_drvdata (struct device *dev, void *data) +static inline void dev_set_drvdata(struct device *dev, void *data) { dev->driver_data = data; } @@ -494,15 +500,15 @@ void driver_init(void); /* * High level routines for use by the bus drivers */ -extern int __must_check device_register(struct device * dev); -extern void device_unregister(struct device * dev); -extern void device_initialize(struct device * dev); -extern int __must_check device_add(struct device * dev); -extern void device_del(struct device * dev); -extern int device_for_each_child(struct device *, void *, - int (*fn)(struct device *, void *)); -extern struct device *device_find_child(struct device *, void *data, - int (*match)(struct device *, void *)); +extern int __must_check device_register(struct device *dev); +extern void device_unregister(struct device *dev); +extern void device_initialize(struct device *dev); +extern int __must_check device_add(struct device *dev); +extern void device_del(struct device *dev); +extern int device_for_each_child(struct device *dev, void *data, + int (*fn)(struct device *dev, void *data)); +extern struct device *device_find_child(struct device *dev, void *data, + int (*match)(struct device *dev, void *data)); extern int device_rename(struct device *dev, char *new_name); extern int device_move(struct device *dev, struct device *new_parent); @@ -511,8 +517,8 @@ extern int device_move(struct device *dev, struct device *new_parent); * for information on use. */ extern int __must_check device_bind_driver(struct device *dev); -extern void device_release_driver(struct device * dev); -extern int __must_check device_attach(struct device * dev); +extern void device_release_driver(struct device *dev); +extern int __must_check device_attach(struct device *dev); extern int __must_check driver_attach(struct device_driver *drv); extern int __must_check device_reprobe(struct device *dev); @@ -521,7 +527,7 @@ extern int __must_check device_reprobe(struct device *dev); */ extern struct device *device_create(struct class *cls, struct device *parent, dev_t devt, const char *fmt, ...) - __attribute__((format(printf,4,5))); + __attribute__((format(printf, 4, 5))); extern void device_destroy(struct class *cls, dev_t devt); #ifdef CONFIG_PM_SLEEP extern void destroy_suspended_device(struct class *cls, dev_t devt); @@ -538,17 +544,17 @@ static inline void destroy_suspended_device(struct class *cls, dev_t devt) * know about. */ /* Notify platform of device discovery */ -extern int (*platform_notify)(struct device * dev); +extern int (*platform_notify)(struct device *dev); -extern int (*platform_notify_remove)(struct device * dev); +extern int (*platform_notify_remove)(struct device *dev); /** * get_device - atomically increment the reference count for the device. * */ -extern struct device * get_device(struct device * dev); -extern void put_device(struct device * dev); +extern struct device *get_device(struct device *dev); +extern void put_device(struct device *dev); /* drivers/base/power/shutdown.c */ @@ -560,7 +566,8 @@ extern void sysdev_shutdown(void); /* debugging and troubleshooting/diagnostic helpers. */ extern const char *dev_driver_string(struct device *dev); #define dev_printk(level, dev, format, arg...) \ - printk(level "%s %s: " format , dev_driver_string(dev) , (dev)->bus_id , ## arg) + printk(level "%s %s: " format , dev_driver_string(dev) , \ + (dev)->bus_id , ## arg) #define dev_emerg(dev, format, arg...) \ dev_printk(KERN_EMERG , dev , format , ## arg) @@ -582,7 +589,7 @@ extern const char *dev_driver_string(struct device *dev); dev_printk(KERN_DEBUG , dev , format , ## arg) #else static inline int __attribute__ ((format (printf, 2, 3))) -dev_dbg(struct device * dev, const char * fmt, ...) +dev_dbg(struct device *dev, const char *fmt, ...) { return 0; } @@ -592,7 +599,7 @@ dev_dbg(struct device * dev, const char * fmt, ...) #define dev_vdbg dev_dbg #else static inline int __attribute__ ((format (printf, 2, 3))) -dev_vdbg(struct device * dev, const char * fmt, ...) +dev_vdbg(struct device *dev, const char *fmt, ...) { return 0; } -- cgit v1.2.3 From 79a6ee42fd81be9abc6bdab08f932875924b26a5 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 24 Jan 2008 21:27:06 -0800 Subject: Kobject: fix coding style issues in kobject.h Finally clean up the odd spaces and other mess in kobject.h Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 67 +++++++++++++++++++++++++------------------------ 1 file changed, 34 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 4adbe1d83081..caa3f411f15d 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -3,15 +3,14 @@ * * Copyright (c) 2002-2003 Patrick Mochel * Copyright (c) 2002-2003 Open Source Development Labs - * Copyright (c) 2006-2007 Greg Kroah-Hartman - * Copyright (c) 2006-2007 Novell Inc. + * Copyright (c) 2006-2008 Greg Kroah-Hartman + * Copyright (c) 2006-2008 Novell Inc. * * This file is released under the GPLv2. * - * * Please read Documentation/kobject.txt before using the kobject * interface, ESPECIALLY the parts about reference counts and object - * destructors. + * destructors. */ #ifndef _KOBJECT_H_ @@ -64,20 +63,20 @@ struct kobject { const char *name; struct kref kref; struct list_head entry; - struct kobject * parent; - struct kset * kset; - struct kobj_type * ktype; - struct sysfs_dirent * sd; + struct kobject *parent; + struct kset *kset; + struct kobj_type *ktype; + struct sysfs_dirent *sd; unsigned int state_initialized:1; unsigned int state_in_sysfs:1; unsigned int state_add_uevent_sent:1; unsigned int state_remove_uevent_sent:1; }; -extern int kobject_set_name(struct kobject *, const char *, ...) - __attribute__((format(printf,2,3))); +extern int kobject_set_name(struct kobject *kobj, const char *name, ...) + __attribute__((format(printf, 2, 3))); -static inline const char * kobject_name(const struct kobject * kobj) +static inline const char *kobject_name(const struct kobject *kobj) { return kobj->name; } @@ -91,7 +90,7 @@ extern int __must_check kobject_init_and_add(struct kobject *kobj, struct kobject *parent, const char *fmt, ...); -extern void kobject_del(struct kobject *); +extern void kobject_del(struct kobject *kobj); extern struct kobject * __must_check kobject_create(void); extern struct kobject * __must_check kobject_create_and_add(const char *name, @@ -100,15 +99,15 @@ extern struct kobject * __must_check kobject_create_and_add(const char *name, extern int __must_check kobject_rename(struct kobject *, const char *new_name); extern int __must_check kobject_move(struct kobject *, struct kobject *); -extern struct kobject * kobject_get(struct kobject *); -extern void kobject_put(struct kobject *); +extern struct kobject *kobject_get(struct kobject *kobj); +extern void kobject_put(struct kobject *kobj); -extern char * kobject_get_path(struct kobject *, gfp_t); +extern char *kobject_get_path(struct kobject *kobj, gfp_t flag); struct kobj_type { - void (*release)(struct kobject *); - struct sysfs_ops * sysfs_ops; - struct attribute ** default_attrs; + void (*release)(struct kobject *kobj); + struct sysfs_ops *sysfs_ops; + struct attribute **default_attrs; }; struct kobj_uevent_env { @@ -153,30 +152,30 @@ extern struct sysfs_ops kobj_sysfs_ops; * desired. */ struct kset { - struct list_head list; - spinlock_t list_lock; - struct kobject kobj; - struct kset_uevent_ops *uevent_ops; + struct list_head list; + spinlock_t list_lock; + struct kobject kobj; + struct kset_uevent_ops *uevent_ops; }; -extern void kset_init(struct kset * k); -extern int __must_check kset_register(struct kset * k); -extern void kset_unregister(struct kset * k); +extern void kset_init(struct kset *kset); +extern int __must_check kset_register(struct kset *kset); +extern void kset_unregister(struct kset *kset); extern struct kset * __must_check kset_create_and_add(const char *name, struct kset_uevent_ops *u, struct kobject *parent_kobj); -static inline struct kset * to_kset(struct kobject * kobj) +static inline struct kset *to_kset(struct kobject *kobj) { - return kobj ? container_of(kobj,struct kset,kobj) : NULL; + return kobj ? container_of(kobj, struct kset, kobj) : NULL; } -static inline struct kset * kset_get(struct kset * k) +static inline struct kset *kset_get(struct kset *k) { return k ? to_kset(kobject_get(&k->kobj)) : NULL; } -static inline void kset_put(struct kset * k) +static inline void kset_put(struct kset *k) { kobject_put(&k->kobj); } @@ -186,7 +185,7 @@ static inline struct kobj_type *get_ktype(struct kobject *kobj) return kobj->ktype; } -extern struct kobject * kset_find_obj(struct kset *, const char *); +extern struct kobject *kset_find_obj(struct kset *, const char *); /* The global /sys/kernel/ kobject for people to chain off of */ extern struct kobject *kernel_kobj; @@ -208,18 +207,20 @@ int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...) int kobject_action_type(const char *buf, size_t count, enum kobject_action *type); #else -static inline int kobject_uevent(struct kobject *kobj, enum kobject_action action) +static inline int kobject_uevent(struct kobject *kobj, + enum kobject_action action) { return 0; } static inline int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, char *envp[]) { return 0; } -static inline int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...) +static inline int add_uevent_var(struct kobj_uevent_env *env, + const char *format, ...) { return 0; } static inline int kobject_action_type(const char *buf, size_t count, - enum kobject_action *type) + enum kobject_action *type) { return -EINVAL; } #endif -- cgit v1.2.3 From 6b2d7700266b9402e12824e11e0099ae6a4a6a79 Mon Sep 17 00:00:00 2001 From: Srivatsa Vaddagiri Date: Fri, 25 Jan 2008 21:08:00 +0100 Subject: sched: group scheduler, fix fairness of cpu bandwidth allocation for task groups The current load balancing scheme isn't good enough for precise group fairness. For example: on a 8-cpu system, I created 3 groups as under: a = 8 tasks (cpu.shares = 1024) b = 4 tasks (cpu.shares = 1024) c = 3 tasks (cpu.shares = 1024) a, b and c are task groups that have equal weight. We would expect each of the groups to receive 33.33% of cpu bandwidth under a fair scheduler. This is what I get with the latest scheduler git tree: Signed-off-by: Ingo Molnar -------------------------------------------------------------------------------- Col1 | Col2 | Col3 | Col4 ------|---------|-------|------------------------------------------------------- a | 277.676 | 57.8% | 54.1% 54.1% 54.1% 54.2% 56.7% 62.2% 62.8% 64.5% b | 116.108 | 24.2% | 47.4% 48.1% 48.7% 49.3% c | 86.326 | 18.0% | 47.5% 47.9% 48.5% -------------------------------------------------------------------------------- Explanation of o/p: Col1 -> Group name Col2 -> Cumulative execution time (in seconds) received by all tasks of that group in a 60sec window across 8 cpus Col3 -> CPU bandwidth received by the group in the 60sec window, expressed in percentage. Col3 data is derived as: Col3 = 100 * Col2 / (NR_CPUS * 60) Col4 -> CPU bandwidth received by each individual task of the group. Col4 = 100 * cpu_time_recd_by_task / 60 [I can share the test case that produces a similar o/p if reqd] The deviation from desired group fairness is as below: a = +24.47% b = -9.13% c = -15.33% which is quite high. After the patch below is applied, here are the results: -------------------------------------------------------------------------------- Col1 | Col2 | Col3 | Col4 ------|---------|-------|------------------------------------------------------- a | 163.112 | 34.0% | 33.2% 33.4% 33.5% 33.5% 33.7% 34.4% 34.8% 35.3% b | 156.220 | 32.5% | 63.3% 64.5% 66.1% 66.5% c | 160.653 | 33.5% | 85.8% 90.6% 91.4% -------------------------------------------------------------------------------- Deviation from desired group fairness is as below: a = +0.67% b = -0.83% c = +0.17% which is far better IMO. Most of other runs have yielded a deviation within +-2% at the most, which is good. Why do we see bad (group) fairness with current scheuler? ========================================================= Currently cpu's weight is just the summation of individual task weights. This can yield incorrect results. For ex: consider three groups as below on a 2-cpu system: CPU0 CPU1 --------------------------- A (10) B(5) C(5) --------------------------- Group A has 10 tasks, all on CPU0, Group B and C have 5 tasks each all of which are on CPU1. Each task has the same weight (NICE_0_LOAD = 1024). The current scheme would yield a cpu weight of 10240 (10*1024) for each cpu and the load balancer will think both CPUs are perfectly balanced and won't move around any tasks. This, however, would yield this bandwidth: A = 50% B = 25% C = 25% which is not the desired result. What's changing in the patch? ============================= - How cpu weights are calculated when CONFIF_FAIR_GROUP_SCHED is defined (see below) - API Change - Two tunables introduced in sysfs (under SCHED_DEBUG) to control the frequency at which the load balance monitor thread runs. The basic change made in this patch is how cpu weight (rq->load.weight) is calculated. Its now calculated as the summation of group weights on a cpu, rather than summation of task weights. Weight exerted by a group on a cpu is dependent on the shares allocated to it and also the number of tasks the group has on that cpu compared to the total number of (runnable) tasks the group has in the system. Let, W(K,i) = Weight of group K on cpu i T(K,i) = Task load present in group K's cfs_rq on cpu i T(K) = Total task load of group K across various cpus S(K) = Shares allocated to group K NRCPUS = Number of online cpus in the scheduler domain to which group K is assigned. Then, W(K,i) = S(K) * NRCPUS * T(K,i) / T(K) A load balance monitor thread is created at bootup, which periodically runs and adjusts group's weight on each cpu. To avoid its overhead, two min/max tunables are introduced (under SCHED_DEBUG) to control the rate at which it runs. Fixes from: Peter Zijlstra - don't start the load_balance_monitor when there is only a single cpu. - rename the kthread because its currently longer than TASK_COMM_LEN Signed-off-by: Srivatsa Vaddagiri Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index d6eacda765ca..288245f83bd4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1453,6 +1453,10 @@ extern unsigned int sysctl_sched_child_runs_first; extern unsigned int sysctl_sched_features; extern unsigned int sysctl_sched_migration_cost; extern unsigned int sysctl_sched_nr_migrate; +#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP) +extern unsigned int sysctl_sched_min_bal_int_shares; +extern unsigned int sysctl_sched_max_bal_int_shares; +#endif int sched_nr_latency_handler(struct ctl_table *table, int write, struct file *file, void __user *buffer, size_t *length, -- cgit v1.2.3 From d221938c049f4845da13c8593132595a6b9222a8 Mon Sep 17 00:00:00 2001 From: Gautham R Shenoy Date: Fri, 25 Jan 2008 21:08:01 +0100 Subject: cpu-hotplug: refcount based cpu hotplug This patch implements a Refcount + Waitqueue based model for cpu-hotplug. Now, a thread which wants to prevent cpu-hotplug, will bump up a global refcount and the thread which wants to perform a cpu-hotplug operation will block till the global refcount goes to zero. The readers, if any, during an ongoing cpu-hotplug operation are blocked until the cpu-hotplug operation is over. Signed-off-by: Gautham R Shenoy Signed-off-by: Paul Jackson [For !CONFIG_HOTPLUG_CPU ] Signed-off-by: Ingo Molnar --- include/linux/cpu.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 92f2029a34f3..a40247e4d462 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -83,6 +83,9 @@ static inline void unregister_cpu_notifier(struct notifier_block *nb) #endif /* CONFIG_SMP */ extern struct sysdev_class cpu_sysdev_class; +extern void cpu_hotplug_init(void); +extern void cpu_maps_update_begin(void); +extern void cpu_maps_update_done(void); #ifdef CONFIG_HOTPLUG_CPU /* Stop CPUs going up and down. */ -- cgit v1.2.3 From 86ef5c9a8edd78e6bf92879f32329d89b2d55b5a Mon Sep 17 00:00:00 2001 From: Gautham R Shenoy Date: Fri, 25 Jan 2008 21:08:02 +0100 Subject: cpu-hotplug: replace lock_cpu_hotplug() with get_online_cpus() Replace all lock_cpu_hotplug/unlock_cpu_hotplug from the kernel and use get_online_cpus and put_online_cpus instead as it highlights the refcount semantics in these operations. The new API guarantees protection against the cpu-hotplug operation, but it doesn't guarantee serialized access to any of the local data structures. Hence the changes needs to be reviewed. In case of pseries_add_processor/pseries_remove_processor, use cpu_maps_update_begin()/cpu_maps_update_done() as we're modifying the cpu_present_map there. Signed-off-by: Gautham R Shenoy Signed-off-by: Ingo Molnar --- include/linux/cpu.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index a40247e4d462..3a3ff1c5cbef 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -100,8 +100,8 @@ static inline void cpuhotplug_mutex_unlock(struct mutex *cpu_hp_mutex) mutex_unlock(cpu_hp_mutex); } -extern void lock_cpu_hotplug(void); -extern void unlock_cpu_hotplug(void); +extern void get_online_cpus(void); +extern void put_online_cpus(void); #define hotcpu_notifier(fn, pri) { \ static struct notifier_block fn##_nb = \ { .notifier_call = fn, .priority = pri }; \ @@ -118,8 +118,8 @@ static inline void cpuhotplug_mutex_lock(struct mutex *cpu_hp_mutex) static inline void cpuhotplug_mutex_unlock(struct mutex *cpu_hp_mutex) { } -#define lock_cpu_hotplug() do { } while (0) -#define unlock_cpu_hotplug() do { } while (0) +#define get_online_cpus() do { } while (0) +#define put_online_cpus() do { } while (0) #define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0) /* These aren't inline functions due to a GCC bug. */ #define register_hotcpu_notifier(nb) ({ (void)(nb); 0; }) -- cgit v1.2.3 From 95402b3829010fe1e208f44e4a158ccade88969a Mon Sep 17 00:00:00 2001 From: Gautham R Shenoy Date: Fri, 25 Jan 2008 21:08:02 +0100 Subject: cpu-hotplug: replace per-subsystem mutexes with get_online_cpus() This patch converts the known per-subsystem mutexes to get_online_cpus put_online_cpus. It also eliminates the CPU_LOCK_ACQUIRE and CPU_LOCK_RELEASE hotplug notification events. Signed-off-by: Gautham R Shenoy Signed-off-by: Ingo Molnar --- include/linux/notifier.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 0c40cc0b4a36..5dfbc684ce7d 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -207,9 +207,7 @@ static inline int notifier_to_errno(int ret) #define CPU_DOWN_PREPARE 0x0005 /* CPU (unsigned)v going down */ #define CPU_DOWN_FAILED 0x0006 /* CPU (unsigned)v NOT going down */ #define CPU_DEAD 0x0007 /* CPU (unsigned)v dead */ -#define CPU_LOCK_ACQUIRE 0x0008 /* Acquire all hotcpu locks */ -#define CPU_LOCK_RELEASE 0x0009 /* Release all hotcpu locks */ -#define CPU_DYING 0x000A /* CPU (unsigned)v not running any task, +#define CPU_DYING 0x0008 /* CPU (unsigned)v not running any task, * not handling interrupts, soon dead */ /* Used for CPU hotplug events occuring while tasks are frozen due to a suspend -- cgit v1.2.3 From d0d23b5432fe61229dd3641c5e94d4130bc4e61b Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 25 Jan 2008 21:08:02 +0100 Subject: cpu-hotplug: fix build on !CONFIG_SMP fix build on !CONFIG_SMP. Signed-off-by: Ingo Molnar --- include/linux/cpu.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 3a3ff1c5cbef..0be8d65bc3c8 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -71,19 +71,25 @@ static inline void unregister_cpu_notifier(struct notifier_block *nb) int cpu_up(unsigned int cpu); +extern void cpu_hotplug_init(void); + #else static inline int register_cpu_notifier(struct notifier_block *nb) { return 0; } + static inline void unregister_cpu_notifier(struct notifier_block *nb) { } +static inline void cpu_hotplug_init(void) +{ +} + #endif /* CONFIG_SMP */ extern struct sysdev_class cpu_sysdev_class; -extern void cpu_hotplug_init(void); extern void cpu_maps_update_begin(void); extern void cpu_maps_update_done(void); -- cgit v1.2.3 From 82a1fcb90287052aabfa235e7ffc693ea003fe69 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 25 Jan 2008 21:08:02 +0100 Subject: softlockup: automatically detect hung TASK_UNINTERRUPTIBLE tasks this patch extends the soft-lockup detector to automatically detect hung TASK_UNINTERRUPTIBLE tasks. Such hung tasks are printed the following way: ------------------> INFO: task prctl:3042 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message prctl D fd5e3793 0 3042 2997 f6050f38 00000046 00000001 fd5e3793 00000009 c06d8264 c06dae80 00000286 f6050f40 f6050f00 f7d34d90 f7d34fc8 c1e1be80 00000001 f6050000 00000000 f7e92d00 00000286 f6050f18 c0489d1a f6050f40 00006605 00000000 c0133a5b Call Trace: [] schedule_timeout+0x6d/0x8b [] schedule_timeout_uninterruptible+0x15/0x17 [] msleep+0x10/0x16 [] sys_prctl+0x30/0x1e2 [] sysenter_past_esp+0x5f/0xa5 ======================= 2 locks held by prctl/3042: #0: (&sb->s_type->i_mutex_key#5){--..}, at: [] do_fsync+0x38/0x7a #1: (jbd_handle){--..}, at: [] journal_start+0xc7/0xe9 <------------------ the current default timeout is 120 seconds. Such messages are printed up to 10 times per bootup. If the system has crashed already then the messages are not printed. if lockdep is enabled then all held locks are printed as well. this feature is a natural extension to the softlockup-detector (kernel locked up without scheduling) and to the NMI watchdog (kernel locked up with IRQs disabled). [ Gautham R Shenoy : CPU hotplug fixes. ] [ Andrew Morton : build warning fix. ] Signed-off-by: Ingo Molnar Signed-off-by: Arjan van de Ven --- include/linux/debug_locks.h | 5 +++++ include/linux/sched.h | 10 ++++++++++ 2 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index 1678a5de7013..f4a5871767f5 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -47,6 +47,7 @@ struct task_struct; #ifdef CONFIG_LOCKDEP extern void debug_show_all_locks(void); +extern void __debug_show_held_locks(struct task_struct *task); extern void debug_show_held_locks(struct task_struct *task); extern void debug_check_no_locks_freed(const void *from, unsigned long len); extern void debug_check_no_locks_held(struct task_struct *task); @@ -55,6 +56,10 @@ static inline void debug_show_all_locks(void) { } +static inline void __debug_show_held_locks(struct task_struct *task) +{ +} + static inline void debug_show_held_locks(struct task_struct *task) { } diff --git a/include/linux/sched.h b/include/linux/sched.h index 288245f83bd4..0846f1f9e196 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -258,12 +258,17 @@ extern void account_process_tick(struct task_struct *task, int user); extern void update_process_times(int user); extern void scheduler_tick(void); +extern void sched_show_task(struct task_struct *p); + #ifdef CONFIG_DETECT_SOFTLOCKUP extern void softlockup_tick(void); extern void spawn_softlockup_task(void); extern void touch_softlockup_watchdog(void); extern void touch_all_softlockup_watchdogs(void); extern int softlockup_thresh; +extern unsigned long sysctl_hung_task_check_count; +extern unsigned long sysctl_hung_task_timeout_secs; +extern long sysctl_hung_task_warnings; #else static inline void softlockup_tick(void) { @@ -1041,6 +1046,11 @@ struct task_struct { /* ipc stuff */ struct sysv_sem sysvsem; #endif +#ifdef CONFIG_DETECT_SOFTLOCKUP +/* hung task detection */ + unsigned long last_switch_timestamp; + unsigned long last_switch_count; +#endif /* CPU-specific state of this task */ struct thread_struct thread; /* filesystem information */ -- cgit v1.2.3 From 73fe6aae84400e2b475e2a1dc4e8592cd3ed6e69 Mon Sep 17 00:00:00 2001 From: Gregory Haskins Date: Fri, 25 Jan 2008 21:08:07 +0100 Subject: sched: add RT-balance cpu-weight Some RT tasks (particularly kthreads) are bound to one specific CPU. It is fairly common for two or more bound tasks to get queued up at the same time. Consider, for instance, softirq_timer and softirq_sched. A timer goes off in an ISR which schedules softirq_thread to run at RT50. Then the timer handler determines that it's time to smp-rebalance the system so it schedules softirq_sched to run. So we are in a situation where we have two RT50 tasks queued, and the system will go into rt-overload condition to request other CPUs for help. This causes two problems in the current code: 1) If a high-priority bound task and a low-priority unbounded task queue up behind the running task, we will fail to ever relocate the unbounded task because we terminate the search on the first unmovable task. 2) We spend precious futile cycles in the fast-path trying to pull overloaded tasks over. It is therefore optimial to strive to avoid the overhead all together if we can cheaply detect the condition before overload even occurs. This patch tries to achieve this optimization by utilizing the hamming weight of the task->cpus_allowed mask. A weight of 1 indicates that the task cannot be migrated. We will then utilize this information to skip non-migratable tasks and to eliminate uncessary rebalance attempts. We introduce a per-rq variable to count the number of migratable tasks that are currently running. We only go into overload if we have more than one rt task, AND at least one of them is migratable. In addition, we introduce a per-task variable to cache the cpus_allowed weight, since the hamming calculation is probably relatively expensive. We only update the cached value when the mask is updated which should be relatively infrequent, especially compared to scheduling frequency in the fast path. Signed-off-by: Gregory Haskins Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- include/linux/init_task.h | 1 + include/linux/sched.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index cae35b6b9aec..572c65bcc80f 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -130,6 +130,7 @@ extern struct group_info init_groups; .normal_prio = MAX_PRIO-20, \ .policy = SCHED_NORMAL, \ .cpus_allowed = CPU_MASK_ALL, \ + .nr_cpus_allowed = NR_CPUS, \ .mm = NULL, \ .active_mm = &init_mm, \ .run_list = LIST_HEAD_INIT(tsk.run_list), \ diff --git a/include/linux/sched.h b/include/linux/sched.h index 0846f1f9e196..b07a2cf76401 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -847,6 +847,7 @@ struct sched_class { void (*set_curr_task) (struct rq *rq); void (*task_tick) (struct rq *rq, struct task_struct *p); void (*task_new) (struct rq *rq, struct task_struct *p); + void (*set_cpus_allowed)(struct task_struct *p, cpumask_t *newmask); }; struct load_weight { @@ -956,6 +957,7 @@ struct task_struct { unsigned int policy; cpumask_t cpus_allowed; + int nr_cpus_allowed; unsigned int time_slice; #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) -- cgit v1.2.3 From e7693a362ec84bb5b6fd441d8a8b4b9d568a7a0c Mon Sep 17 00:00:00 2001 From: Gregory Haskins Date: Fri, 25 Jan 2008 21:08:09 +0100 Subject: sched: de-SCHED_OTHER-ize the RT path The current wake-up code path tries to determine if it can optimize the wake-up to "this_cpu" by computing load calculations. The problem is that these calculations are only relevant to SCHED_OTHER tasks where load is king. For RT tasks, priority is king. So the load calculation is completely wasted bandwidth. Therefore, we create a new sched_class interface to help with pre-wakeup routing decisions and move the load calculation as a function of CFS task's class. Signed-off-by: Gregory Haskins Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b07a2cf76401..6fbbf38555ac 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -827,6 +827,7 @@ struct sched_class { void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup); void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep); void (*yield_task) (struct rq *rq); + int (*select_task_rq)(struct task_struct *p, int sync); void (*check_preempt_curr) (struct rq *rq, struct task_struct *p); -- cgit v1.2.3 From 57d885fea0da0e9541d7730a9e1dcf734981a173 Mon Sep 17 00:00:00 2001 From: Gregory Haskins Date: Fri, 25 Jan 2008 21:08:18 +0100 Subject: sched: add sched-domain roots We add the notion of a root-domain which will be used later to rescope global variables to per-domain variables. Each exclusive cpuset essentially defines an island domain by fully partitioning the member cpus from any other cpuset. However, we currently still maintain some policy/state as global variables which transcend all cpusets. Consider, for instance, rt-overload state. Whenever a new exclusive cpuset is created, we also create a new root-domain object and move each cpu member to the root-domain's span. By default the system creates a single root-domain with all cpus as members (mimicking the global state we have today). We add some plumbing for storing class specific data in our root-domain. Whenever a RQ is switching root-domains (because of repartitioning) we give each sched_class the opportunity to remove any state from its old domain and add state to the new one. This logic doesn't have any clients yet but it will later in the series. Signed-off-by: Gregory Haskins CC: Christoph Lameter CC: Paul Jackson CC: Simon Derr Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6fbbf38555ac..2e69f19369e4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -849,6 +849,9 @@ struct sched_class { void (*task_tick) (struct rq *rq, struct task_struct *p); void (*task_new) (struct rq *rq, struct task_struct *p); void (*set_cpus_allowed)(struct task_struct *p, cpumask_t *newmask); + + void (*join_domain)(struct rq *rq); + void (*leave_domain)(struct rq *rq); }; struct load_weight { -- cgit v1.2.3 From 52d853431e8d9dc17ba94792123a3fe2bc039831 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 25 Jan 2008 21:08:20 +0100 Subject: sched: reactivate fork balancing reactivate fork balancing. Signed-off-by: Ingo Molnar --- include/linux/topology.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index 47729f18bfdf..b6c073d8b709 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -103,6 +103,7 @@ .forkexec_idx = 0, \ .flags = SD_LOAD_BALANCE \ | SD_BALANCE_NEWIDLE \ + | SD_BALANCE_FORK \ | SD_BALANCE_EXEC \ | SD_WAKE_AFFINE \ | SD_WAKE_IDLE \ @@ -134,6 +135,7 @@ .forkexec_idx = 1, \ .flags = SD_LOAD_BALANCE \ | SD_BALANCE_NEWIDLE \ + | SD_BALANCE_FORK \ | SD_BALANCE_EXEC \ | SD_WAKE_AFFINE \ | SD_WAKE_IDLE \ @@ -165,6 +167,7 @@ .forkexec_idx = 1, \ .flags = SD_LOAD_BALANCE \ | SD_BALANCE_NEWIDLE \ + | SD_BALANCE_FORK \ | SD_BALANCE_EXEC \ | SD_WAKE_AFFINE \ | BALANCE_FOR_PKG_POWER,\ -- cgit v1.2.3 From 32525d022ad52a5c14e80e130260431e16e294b6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 25 Jan 2008 21:08:20 +0100 Subject: sched: whitespace cleanups in topology.h whitespace cleanups in topology.h. Signed-off-by: Ingo Molnar --- include/linux/topology.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index b6c073d8b709..2352f46160d3 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -5,7 +5,7 @@ * * Copyright (C) 2002, IBM Corp. * - * All rights reserved. + * All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by -- cgit v1.2.3 From 9a897c5a6701bcb6f099f7ca20194999102729fd Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 25 Jan 2008 21:08:22 +0100 Subject: sched: RT-balance, replace hooks with pre/post schedule and wakeup methods To make the main sched.c code more agnostic to the schedule classes. Instead of having specific hooks in the schedule code for the RT class balancing. They are replaced with a pre_schedule, post_schedule and task_wake_up methods. These methods may be used by any of the classes but currently, only the sched_rt class implements them. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2e69f19369e4..c67d2c2f0111 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -843,6 +843,9 @@ struct sched_class { int (*move_one_task) (struct rq *this_rq, int this_cpu, struct rq *busiest, struct sched_domain *sd, enum cpu_idle_type idle); + void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); + void (*post_schedule) (struct rq *this_rq); + void (*task_wake_up) (struct rq *this_rq, struct task_struct *task); #endif void (*set_curr_task) (struct rq *rq); -- cgit v1.2.3 From cb46984504048db946cd551c261df4e70d59a8ea Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 25 Jan 2008 21:08:22 +0100 Subject: sched: RT-balance, add new methods to sched_class Dmitry Adamushko found that the current implementation of the RT balancing code left out changes to the sched_setscheduler and rt_mutex_setprio. This patch addresses this issue by adding methods to the schedule classes to handle being switched out of (switched_from) and being switched into (switched_to) a sched_class. Also a method for changing of priorities is also added (prio_changed). This patch also removes some duplicate logic between rt_mutex_setprio and sched_setscheduler. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- include/linux/sched.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index c67d2c2f0111..f2044e707004 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -855,6 +855,13 @@ struct sched_class { void (*join_domain)(struct rq *rq); void (*leave_domain)(struct rq *rq); + + void (*switched_from) (struct rq *this_rq, struct task_struct *task, + int running); + void (*switched_to) (struct rq *this_rq, struct task_struct *task, + int running); + void (*prio_changed) (struct rq *this_rq, struct task_struct *task, + int oldprio, int running); }; struct load_weight { -- cgit v1.2.3 From c2d727aa2ff17a1c8e5ed1e5e231bb8579b27e82 Mon Sep 17 00:00:00 2001 From: Dipankar Sarma Date: Fri, 25 Jan 2008 21:08:23 +0100 Subject: Preempt-RCU: Use softirq instead of tasklets for This patch makes RCU use softirq instead of tasklets. It also adds a memory barrier after raising the softirq inorder to ensure that the cpu sees the most recently updated value of rcu->cur while processing callbacks. The discussion of the related theoretical race pointed out by James Huang can be found here --> http://lkml.org/lkml/2007/11/20/603 Signed-off-by: Gautham R Shenoy Signed-off-by: Steven Rostedt Signed-off-by: Dipankar Sarma Reviewed-by: Steven Rostedt Signed-off-by: Ingo Molnar --- include/linux/interrupt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 2306920fa388..c3db4a00f1fa 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -256,6 +256,7 @@ enum #ifdef CONFIG_HIGH_RES_TIMERS HRTIMER_SOFTIRQ, #endif + RCU_SOFTIRQ, /* Preferable RCU should always be the last softirq */ }; /* softirq mask and active fields moved to irq_cpustat_t in -- cgit v1.2.3 From 01c1c660f4b8086cad7a62345fd04290f3d82c8f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 25 Jan 2008 21:08:24 +0100 Subject: Preempt-RCU: reorganize RCU code into rcuclassic.c and rcupdate.c This patch re-organizes the RCU code to enable multiple implementations of RCU. Users of RCU continues to include rcupdate.h and the RCU interfaces remain the same. This is in preparation for subsequently merging the preemptible RCU implementation. Signed-off-by: Gautham R Shenoy Signed-off-by: Dipankar Sarma Signed-off-by: Paul E. McKenney Reviewed-by: Steven Rostedt Signed-off-by: Ingo Molnar --- include/linux/rcuclassic.h | 161 +++++++++++++++++++++++++++++++++++++++++++ include/linux/rcupdate.h | 168 +++++++++++++-------------------------------- 2 files changed, 210 insertions(+), 119 deletions(-) create mode 100644 include/linux/rcuclassic.h (limited to 'include/linux') diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h new file mode 100644 index 000000000000..2b8b045a51d5 --- /dev/null +++ b/include/linux/rcuclassic.h @@ -0,0 +1,161 @@ +/* + * Read-Copy Update mechanism for mutual exclusion (classic version) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright IBM Corporation, 2001 + * + * Author: Dipankar Sarma + * + * Based on the original work by Paul McKenney + * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. + * Papers: + * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf + * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001) + * + * For detailed explanation of Read-Copy Update mechanism see - + * Documentation/RCU + * + */ + +#ifndef __LINUX_RCUCLASSIC_H +#define __LINUX_RCUCLASSIC_H + +#ifdef __KERNEL__ + +#include +#include +#include +#include +#include +#include + + +/* Global control variables for rcupdate callback mechanism. */ +struct rcu_ctrlblk { + long cur; /* Current batch number. */ + long completed; /* Number of the last completed batch */ + int next_pending; /* Is the next batch already waiting? */ + + int signaled; + + spinlock_t lock ____cacheline_internodealigned_in_smp; + cpumask_t cpumask; /* CPUs that need to switch in order */ + /* for current batch to proceed. */ +} ____cacheline_internodealigned_in_smp; + +/* Is batch a before batch b ? */ +static inline int rcu_batch_before(long a, long b) +{ + return (a - b) < 0; +} + +/* Is batch a after batch b ? */ +static inline int rcu_batch_after(long a, long b) +{ + return (a - b) > 0; +} + +/* + * Per-CPU data for Read-Copy UPdate. + * nxtlist - new callbacks are added here + * curlist - current batch for which quiescent cycle started if any + */ +struct rcu_data { + /* 1) quiescent state handling : */ + long quiescbatch; /* Batch # for grace period */ + int passed_quiesc; /* User-mode/idle loop etc. */ + int qs_pending; /* core waits for quiesc state */ + + /* 2) batch handling */ + long batch; /* Batch # for current RCU batch */ + struct rcu_head *nxtlist; + struct rcu_head **nxttail; + long qlen; /* # of queued callbacks */ + struct rcu_head *curlist; + struct rcu_head **curtail; + struct rcu_head *donelist; + struct rcu_head **donetail; + long blimit; /* Upper limit on a processed batch */ + int cpu; + struct rcu_head barrier; +}; + +DECLARE_PER_CPU(struct rcu_data, rcu_data); +DECLARE_PER_CPU(struct rcu_data, rcu_bh_data); + +/* + * Increment the quiescent state counter. + * The counter is a bit degenerated: We do not need to know + * how many quiescent states passed, just if there was at least + * one since the start of the grace period. Thus just a flag. + */ +static inline void rcu_qsctr_inc(int cpu) +{ + struct rcu_data *rdp = &per_cpu(rcu_data, cpu); + rdp->passed_quiesc = 1; +} +static inline void rcu_bh_qsctr_inc(int cpu) +{ + struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu); + rdp->passed_quiesc = 1; +} + +extern int rcu_pending(int cpu); +extern int rcu_needs_cpu(int cpu); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +extern struct lockdep_map rcu_lock_map; +# define rcu_read_acquire() \ + lock_acquire(&rcu_lock_map, 0, 0, 2, 1, _THIS_IP_) +# define rcu_read_release() lock_release(&rcu_lock_map, 1, _THIS_IP_) +#else +# define rcu_read_acquire() do { } while (0) +# define rcu_read_release() do { } while (0) +#endif + +#define __rcu_read_lock() \ + do { \ + preempt_disable(); \ + __acquire(RCU); \ + rcu_read_acquire(); \ + } while (0) +#define __rcu_read_unlock() \ + do { \ + rcu_read_release(); \ + __release(RCU); \ + preempt_enable(); \ + } while (0) +#define __rcu_read_lock_bh() \ + do { \ + local_bh_disable(); \ + __acquire(RCU_BH); \ + rcu_read_acquire(); \ + } while (0) +#define __rcu_read_unlock_bh() \ + do { \ + rcu_read_release(); \ + __release(RCU_BH); \ + local_bh_enable(); \ + } while (0) + +#define __synchronize_sched() synchronize_rcu() + +extern void __rcu_init(void); +extern void rcu_check_callbacks(int cpu, int user); +extern void rcu_restart_cpu(int cpu); + +#endif /* __KERNEL__ */ +#endif /* __LINUX_RCUCLASSIC_H */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index cc24a01df940..12aa13e13150 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -15,7 +15,7 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. * - * Copyright (C) IBM Corporation, 2001 + * Copyright IBM Corporation, 2001 * * Author: Dipankar Sarma * @@ -53,96 +53,14 @@ struct rcu_head { void (*func)(struct rcu_head *head); }; +#include + #define RCU_HEAD_INIT { .next = NULL, .func = NULL } #define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT #define INIT_RCU_HEAD(ptr) do { \ (ptr)->next = NULL; (ptr)->func = NULL; \ } while (0) - - -/* Global control variables for rcupdate callback mechanism. */ -struct rcu_ctrlblk { - long cur; /* Current batch number. */ - long completed; /* Number of the last completed batch */ - int next_pending; /* Is the next batch already waiting? */ - - int signaled; - - spinlock_t lock ____cacheline_internodealigned_in_smp; - cpumask_t cpumask; /* CPUs that need to switch in order */ - /* for current batch to proceed. */ -} ____cacheline_internodealigned_in_smp; - -/* Is batch a before batch b ? */ -static inline int rcu_batch_before(long a, long b) -{ - return (a - b) < 0; -} - -/* Is batch a after batch b ? */ -static inline int rcu_batch_after(long a, long b) -{ - return (a - b) > 0; -} - -/* - * Per-CPU data for Read-Copy UPdate. - * nxtlist - new callbacks are added here - * curlist - current batch for which quiescent cycle started if any - */ -struct rcu_data { - /* 1) quiescent state handling : */ - long quiescbatch; /* Batch # for grace period */ - int passed_quiesc; /* User-mode/idle loop etc. */ - int qs_pending; /* core waits for quiesc state */ - - /* 2) batch handling */ - long batch; /* Batch # for current RCU batch */ - struct rcu_head *nxtlist; - struct rcu_head **nxttail; - long qlen; /* # of queued callbacks */ - struct rcu_head *curlist; - struct rcu_head **curtail; - struct rcu_head *donelist; - struct rcu_head **donetail; - long blimit; /* Upper limit on a processed batch */ - int cpu; - struct rcu_head barrier; -}; - -DECLARE_PER_CPU(struct rcu_data, rcu_data); -DECLARE_PER_CPU(struct rcu_data, rcu_bh_data); - -/* - * Increment the quiescent state counter. - * The counter is a bit degenerated: We do not need to know - * how many quiescent states passed, just if there was at least - * one since the start of the grace period. Thus just a flag. - */ -static inline void rcu_qsctr_inc(int cpu) -{ - struct rcu_data *rdp = &per_cpu(rcu_data, cpu); - rdp->passed_quiesc = 1; -} -static inline void rcu_bh_qsctr_inc(int cpu) -{ - struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu); - rdp->passed_quiesc = 1; -} - -extern int rcu_pending(int cpu); -extern int rcu_needs_cpu(int cpu); - -#ifdef CONFIG_DEBUG_LOCK_ALLOC -extern struct lockdep_map rcu_lock_map; -# define rcu_read_acquire() lock_acquire(&rcu_lock_map, 0, 0, 2, 1, _THIS_IP_) -# define rcu_read_release() lock_release(&rcu_lock_map, 1, _THIS_IP_) -#else -# define rcu_read_acquire() do { } while (0) -# define rcu_read_release() do { } while (0) -#endif - /** * rcu_read_lock - mark the beginning of an RCU read-side critical section. * @@ -172,24 +90,13 @@ extern struct lockdep_map rcu_lock_map; * * It is illegal to block while in an RCU read-side critical section. */ -#define rcu_read_lock() \ - do { \ - preempt_disable(); \ - __acquire(RCU); \ - rcu_read_acquire(); \ - } while(0) +#define rcu_read_lock() __rcu_read_lock() /** * rcu_read_unlock - marks the end of an RCU read-side critical section. * * See rcu_read_lock() for more information. */ -#define rcu_read_unlock() \ - do { \ - rcu_read_release(); \ - __release(RCU); \ - preempt_enable(); \ - } while(0) /* * So where is rcu_write_lock()? It does not exist, as there is no @@ -200,6 +107,7 @@ extern struct lockdep_map rcu_lock_map; * used as well. RCU does not care how the writers keep out of each * others' way, as long as they do so. */ +#define rcu_read_unlock() __rcu_read_unlock() /** * rcu_read_lock_bh - mark the beginning of a softirq-only RCU critical section @@ -212,24 +120,14 @@ extern struct lockdep_map rcu_lock_map; * can use just rcu_read_lock(). * */ -#define rcu_read_lock_bh() \ - do { \ - local_bh_disable(); \ - __acquire(RCU_BH); \ - rcu_read_acquire(); \ - } while(0) +#define rcu_read_lock_bh() __rcu_read_lock_bh() /* * rcu_read_unlock_bh - marks the end of a softirq-only RCU critical section * * See rcu_read_lock_bh() for more information. */ -#define rcu_read_unlock_bh() \ - do { \ - rcu_read_release(); \ - __release(RCU_BH); \ - local_bh_enable(); \ - } while(0) +#define rcu_read_unlock_bh() __rcu_read_unlock_bh() /* * Prevent the compiler from merging or refetching accesses. The compiler @@ -293,21 +191,53 @@ extern struct lockdep_map rcu_lock_map; * In "classic RCU", these two guarantees happen to be one and * the same, but can differ in realtime RCU implementations. */ -#define synchronize_sched() synchronize_rcu() +#define synchronize_sched() __synchronize_sched() + +/** + * call_rcu - Queue an RCU callback for invocation after a grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual update function to be invoked after the grace period + * + * The update function will be invoked some time after a full grace + * period elapses, in other words after all currently executing RCU + * read-side critical sections have completed. RCU read-side critical + * sections are delimited by rcu_read_lock() and rcu_read_unlock(), + * and may be nested. + */ +extern void call_rcu(struct rcu_head *head, + void (*func)(struct rcu_head *head)); + +/** + * call_rcu_bh - Queue an RCU for invocation after a quicker grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual update function to be invoked after the grace period + * + * The update function will be invoked some time after a full grace + * period elapses, in other words after all currently executing RCU + * read-side critical sections have completed. call_rcu_bh() assumes + * that the read-side critical sections end on completion of a softirq + * handler. This means that read-side critical sections in process + * context must not be interrupted by softirqs. This interface is to be + * used when most of the read-side critical sections are in softirq context. + * RCU read-side critical sections are delimited by : + * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context. + * OR + * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. + * These may be nested. + */ +extern void call_rcu_bh(struct rcu_head *head, + void (*func)(struct rcu_head *head)); + +/* Exported common interfaces */ +extern void synchronize_rcu(void); +extern void rcu_barrier(void); +/* Internal to kernel */ extern void rcu_init(void); extern void rcu_check_callbacks(int cpu, int user); -extern void rcu_restart_cpu(int cpu); + extern long rcu_batches_completed(void); extern long rcu_batches_completed_bh(void); -/* Exported interfaces */ -extern void FASTCALL(call_rcu(struct rcu_head *head, - void (*func)(struct rcu_head *head))); -extern void FASTCALL(call_rcu_bh(struct rcu_head *head, - void (*func)(struct rcu_head *head))); -extern void synchronize_rcu(void); -extern void rcu_barrier(void); - #endif /* __KERNEL__ */ #endif /* __LINUX_RCUPDATE_H */ -- cgit v1.2.3 From e260be673a15b6125068270e0216a3bfbfc12f87 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 25 Jan 2008 21:08:24 +0100 Subject: Preempt-RCU: implementation This patch implements a new version of RCU which allows its read-side critical sections to be preempted. It uses a set of counter pairs to keep track of the read-side critical sections and flips them when all tasks exit read-side critical section. The details of this implementation can be found in this paper - http://www.rdrop.com/users/paulmck/RCU/OLSrtRCU.2006.08.11a.pdf and the article- http://lwn.net/Articles/253651/ This patch was developed as a part of the -rt kernel development and meant to provide better latencies when read-side critical sections of RCU don't disable preemption. As a consequence of keeping track of RCU readers, the readers have a slight overhead (optimizations in the paper). This implementation co-exists with the "classic" RCU implementations and can be switched to at compiler. Also includes RCU tracing summarized in debugfs. [ akpm@linux-foundation.org: build fixes on non-preempt architectures ] Signed-off-by: Gautham R Shenoy Signed-off-by: Dipankar Sarma Signed-off-by: Paul E. McKenney Reviewed-by: Steven Rostedt Signed-off-by: Ingo Molnar --- include/linux/rcuclassic.h | 3 ++ include/linux/rcupdate.h | 11 +++-- include/linux/rcupreempt.h | 86 ++++++++++++++++++++++++++++++++++ include/linux/rcupreempt_trace.h | 99 ++++++++++++++++++++++++++++++++++++++++ include/linux/sched.h | 5 ++ 5 files changed, 200 insertions(+), 4 deletions(-) create mode 100644 include/linux/rcupreempt.h create mode 100644 include/linux/rcupreempt_trace.h (limited to 'include/linux') diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h index 2b8b045a51d5..4d6624260b4c 100644 --- a/include/linux/rcuclassic.h +++ b/include/linux/rcuclassic.h @@ -157,5 +157,8 @@ extern void __rcu_init(void); extern void rcu_check_callbacks(int cpu, int user); extern void rcu_restart_cpu(int cpu); +extern long rcu_batches_completed(void); +extern long rcu_batches_completed_bh(void); + #endif /* __KERNEL__ */ #endif /* __LINUX_RCUCLASSIC_H */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 12aa13e13150..d32c14de270e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -53,7 +53,11 @@ struct rcu_head { void (*func)(struct rcu_head *head); }; +#ifdef CONFIG_CLASSIC_RCU #include +#else /* #ifdef CONFIG_CLASSIC_RCU */ +#include +#endif /* #else #ifdef CONFIG_CLASSIC_RCU */ #define RCU_HEAD_INIT { .next = NULL, .func = NULL } #define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT @@ -231,13 +235,12 @@ extern void call_rcu_bh(struct rcu_head *head, /* Exported common interfaces */ extern void synchronize_rcu(void); extern void rcu_barrier(void); +extern long rcu_batches_completed(void); +extern long rcu_batches_completed_bh(void); /* Internal to kernel */ extern void rcu_init(void); -extern void rcu_check_callbacks(int cpu, int user); - -extern long rcu_batches_completed(void); -extern long rcu_batches_completed_bh(void); +extern int rcu_needs_cpu(int cpu); #endif /* __KERNEL__ */ #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/rcupreempt.h b/include/linux/rcupreempt.h new file mode 100644 index 000000000000..ece8eb3e4151 --- /dev/null +++ b/include/linux/rcupreempt.h @@ -0,0 +1,86 @@ +/* + * Read-Copy Update mechanism for mutual exclusion (RT implementation) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2006 + * + * Author: Paul McKenney + * + * Based on the original work by Paul McKenney + * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. + * Papers: + * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf + * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001) + * + * For detailed explanation of Read-Copy Update mechanism see - + * Documentation/RCU + * + */ + +#ifndef __LINUX_RCUPREEMPT_H +#define __LINUX_RCUPREEMPT_H + +#ifdef __KERNEL__ + +#include +#include +#include +#include +#include +#include + +#define rcu_qsctr_inc(cpu) +#define rcu_bh_qsctr_inc(cpu) +#define call_rcu_bh(head, rcu) call_rcu(head, rcu) + +extern void __rcu_read_lock(void); +extern void __rcu_read_unlock(void); +extern int rcu_pending(int cpu); +extern int rcu_needs_cpu(int cpu); + +#define __rcu_read_lock_bh() { rcu_read_lock(); local_bh_disable(); } +#define __rcu_read_unlock_bh() { local_bh_enable(); rcu_read_unlock(); } + +extern void __synchronize_sched(void); + +extern void __rcu_init(void); +extern void rcu_check_callbacks(int cpu, int user); +extern void rcu_restart_cpu(int cpu); +extern long rcu_batches_completed(void); + +/* + * Return the number of RCU batches processed thus far. Useful for debug + * and statistic. The _bh variant is identifcal to straight RCU + */ +static inline long rcu_batches_completed_bh(void) +{ + return rcu_batches_completed(); +} + +#ifdef CONFIG_RCU_TRACE +struct rcupreempt_trace; +extern long *rcupreempt_flipctr(int cpu); +extern long rcupreempt_data_completed(void); +extern int rcupreempt_flip_flag(int cpu); +extern int rcupreempt_mb_flag(int cpu); +extern char *rcupreempt_try_flip_state_name(void); +extern struct rcupreempt_trace *rcupreempt_trace_cpu(int cpu); +#endif + +struct softirq_action; + +#endif /* __KERNEL__ */ +#endif /* __LINUX_RCUPREEMPT_H */ diff --git a/include/linux/rcupreempt_trace.h b/include/linux/rcupreempt_trace.h new file mode 100644 index 000000000000..21cd6b2a5c42 --- /dev/null +++ b/include/linux/rcupreempt_trace.h @@ -0,0 +1,99 @@ +/* + * Read-Copy Update mechanism for mutual exclusion (RT implementation) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2006 + * + * Author: Paul McKenney + * + * Based on the original work by Paul McKenney + * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. + * Papers: + * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf + * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001) + * + * For detailed explanation of the Preemptible Read-Copy Update mechanism see - + * http://lwn.net/Articles/253651/ + */ + +#ifndef __LINUX_RCUPREEMPT_TRACE_H +#define __LINUX_RCUPREEMPT_TRACE_H + +#ifdef __KERNEL__ +#include +#include + +#include + +/* + * PREEMPT_RCU data structures. + */ + +struct rcupreempt_trace { + long next_length; + long next_add; + long wait_length; + long wait_add; + long done_length; + long done_add; + long done_remove; + atomic_t done_invoked; + long rcu_check_callbacks; + atomic_t rcu_try_flip_1; + atomic_t rcu_try_flip_e1; + long rcu_try_flip_i1; + long rcu_try_flip_ie1; + long rcu_try_flip_g1; + long rcu_try_flip_a1; + long rcu_try_flip_ae1; + long rcu_try_flip_a2; + long rcu_try_flip_z1; + long rcu_try_flip_ze1; + long rcu_try_flip_z2; + long rcu_try_flip_m1; + long rcu_try_flip_me1; + long rcu_try_flip_m2; +}; + +#ifdef CONFIG_RCU_TRACE +#define RCU_TRACE(fn, arg) fn(arg); +#else +#define RCU_TRACE(fn, arg) +#endif + +extern void rcupreempt_trace_move2done(struct rcupreempt_trace *trace); +extern void rcupreempt_trace_move2wait(struct rcupreempt_trace *trace); +extern void rcupreempt_trace_try_flip_1(struct rcupreempt_trace *trace); +extern void rcupreempt_trace_try_flip_e1(struct rcupreempt_trace *trace); +extern void rcupreempt_trace_try_flip_i1(struct rcupreempt_trace *trace); +extern void rcupreempt_trace_try_flip_ie1(struct rcupreempt_trace *trace); +extern void rcupreempt_trace_try_flip_g1(struct rcupreempt_trace *trace); +extern void rcupreempt_trace_try_flip_a1(struct rcupreempt_trace *trace); +extern void rcupreempt_trace_try_flip_ae1(struct rcupreempt_trace *trace); +extern void rcupreempt_trace_try_flip_a2(struct rcupreempt_trace *trace); +extern void rcupreempt_trace_try_flip_z1(struct rcupreempt_trace *trace); +extern void rcupreempt_trace_try_flip_ze1(struct rcupreempt_trace *trace); +extern void rcupreempt_trace_try_flip_z2(struct rcupreempt_trace *trace); +extern void rcupreempt_trace_try_flip_m1(struct rcupreempt_trace *trace); +extern void rcupreempt_trace_try_flip_me1(struct rcupreempt_trace *trace); +extern void rcupreempt_trace_try_flip_m2(struct rcupreempt_trace *trace); +extern void rcupreempt_trace_check_callbacks(struct rcupreempt_trace *trace); +extern void rcupreempt_trace_done_remove(struct rcupreempt_trace *trace); +extern void rcupreempt_trace_invoke(struct rcupreempt_trace *trace); +extern void rcupreempt_trace_next_add(struct rcupreempt_trace *trace); + +#endif /* __KERNEL__ */ +#endif /* __LINUX_RCUPREEMPT_TRACE_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index f2044e707004..72e1b8ecfbe1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -974,6 +974,11 @@ struct task_struct { int nr_cpus_allowed; unsigned int time_slice; +#ifdef CONFIG_PREEMPT_RCU + int rcu_read_lock_nesting; + int rcu_flipctr_idx; +#endif /* #ifdef CONFIG_PREEMPT_RCU */ + #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) struct sched_info sched_info; #endif -- cgit v1.2.3 From fa717060f1ab7eb6570f2fb49136f838fc9195a9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 25 Jan 2008 21:08:27 +0100 Subject: sched: sched_rt_entity Move the task_struct members specific to rt scheduling together. A future optimization could be to put sched_entity and sched_rt_entity into a union. Signed-off-by: Peter Zijlstra CC: Srivatsa Vaddagiri Signed-off-by: Ingo Molnar --- include/linux/init_task.h | 5 +++-- include/linux/sched.h | 8 ++++++-- 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 572c65bcc80f..ee65d87bedb7 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -133,9 +133,10 @@ extern struct group_info init_groups; .nr_cpus_allowed = NR_CPUS, \ .mm = NULL, \ .active_mm = &init_mm, \ - .run_list = LIST_HEAD_INIT(tsk.run_list), \ + .rt = { \ + .run_list = LIST_HEAD_INIT(tsk.rt.run_list), \ + .time_slice = HZ, }, \ .ioprio = 0, \ - .time_slice = HZ, \ .tasks = LIST_HEAD_INIT(tsk.tasks), \ .ptrace_children= LIST_HEAD_INIT(tsk.ptrace_children), \ .ptrace_list = LIST_HEAD_INIT(tsk.ptrace_list), \ diff --git a/include/linux/sched.h b/include/linux/sched.h index 72e1b8ecfbe1..a06d09ebd5c6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -929,6 +929,11 @@ struct sched_entity { #endif }; +struct sched_rt_entity { + struct list_head run_list; + unsigned int time_slice; +}; + struct task_struct { volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */ void *stack; @@ -945,9 +950,9 @@ struct task_struct { #endif int prio, static_prio, normal_prio; - struct list_head run_list; const struct sched_class *sched_class; struct sched_entity se; + struct sched_rt_entity rt; #ifdef CONFIG_PREEMPT_NOTIFIERS /* list of struct preempt_notifier: */ @@ -972,7 +977,6 @@ struct task_struct { unsigned int policy; cpumask_t cpus_allowed; int nr_cpus_allowed; - unsigned int time_slice; #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; -- cgit v1.2.3 From 78f2c7db6068fd6ef75b8c120f04a388848eacb5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 25 Jan 2008 21:08:27 +0100 Subject: sched: SCHED_FIFO/SCHED_RR watchdog timer Introduce a new rlimit that allows the user to set a runtime timeout on real-time tasks their slice. Once this limit is exceeded the task will receive SIGXCPU. So it measures runtime since the last sleep. Input and ideas by Thomas Gleixner and Lennart Poettering. Signed-off-by: Peter Zijlstra CC: Lennart Poettering CC: Michael Kerrisk CC: Ulrich Drepper Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index a06d09ebd5c6..fe3f8fbc614e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -932,6 +932,7 @@ struct sched_entity { struct sched_rt_entity { struct list_head run_list; unsigned int time_slice; + unsigned long timeout; }; struct task_struct { -- cgit v1.2.3 From 02b67cc3ba36bdba351d6c3a00593f4ec550d9d3 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 25 Jan 2008 21:08:28 +0100 Subject: sched: do not do cond_resched() when CONFIG_PREEMPT Why do we even have cond_resched when real preemption is on? It seems to be a waste of space and time. remove cond_resched with CONFIG_PREEMPT on. Signed-off-by: Ingo Molnar --- include/linux/kernel.h | 4 ++-- include/linux/sched.h | 13 ++++++++++++- 2 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 94bc99656963..a7283c9beadf 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -105,8 +105,8 @@ struct user; * supposed to. */ #ifdef CONFIG_PREEMPT_VOLUNTARY -extern int cond_resched(void); -# define might_resched() cond_resched() +extern int _cond_resched(void); +# define might_resched() _cond_resched() #else # define might_resched() do { } while (0) #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index fe3f8fbc614e..7907845c2348 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1885,7 +1885,18 @@ static inline int need_resched(void) * cond_resched_lock() will drop the spinlock before scheduling, * cond_resched_softirq() will enable bhs before scheduling. */ -extern int cond_resched(void); +#ifdef CONFIG_PREEMPT +static inline int cond_resched(void) +{ + return 0; +} +#else +extern int _cond_resched(void); +static inline int cond_resched(void) +{ + return _cond_resched(); +} +#endif extern int cond_resched_lock(spinlock_t * lock); extern int cond_resched_softirq(void); -- cgit v1.2.3 From 8f4d37ec073c17e2d4aa8851df5837d798606d6f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 25 Jan 2008 21:08:29 +0100 Subject: sched: high-res preemption tick Use HR-timers (when available) to deliver an accurate preemption tick. The regular scheduler tick that runs at 1/HZ can be too coarse when nice level are used. The fairness system will still keep the cpu utilisation 'fair' by then delaying the task that got an excessive amount of CPU time but try to minimize this by delivering preemption points spot-on. The average frequency of this extra interrupt is sched_latency / nr_latency. Which need not be higher than 1/HZ, its just that the distribution within the sched_latency period is important. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- include/linux/hrtimer.h | 9 +++++++++ include/linux/sched.h | 3 ++- 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 7a9398e19704..ecc8e2685e2b 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -217,6 +217,11 @@ static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer) return timer->base->get_time(); } +static inline int hrtimer_is_hres_active(struct hrtimer *timer) +{ + return timer->base->cpu_base->hres_active; +} + /* * The resolution of the clocks. The resolution value is returned in * the clock_getres() system call to give application programmers an @@ -248,6 +253,10 @@ static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer) return timer->base->softirq_time; } +static inline int hrtimer_is_hres_active(struct hrtimer *timer) +{ + return 0; +} #endif extern ktime_t ktime_get(void); diff --git a/include/linux/sched.h b/include/linux/sched.h index 7907845c2348..43e0339d65fc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -257,6 +257,7 @@ extern void trap_init(void); extern void account_process_tick(struct task_struct *task, int user); extern void update_process_times(int user); extern void scheduler_tick(void); +extern void hrtick_resched(void); extern void sched_show_task(struct task_struct *p); @@ -849,7 +850,7 @@ struct sched_class { #endif void (*set_curr_task) (struct rq *rq); - void (*task_tick) (struct rq *rq, struct task_struct *p); + void (*task_tick) (struct rq *rq, struct task_struct *p, int queued); void (*task_new) (struct rq *rq, struct task_struct *p); void (*set_cpus_allowed)(struct task_struct *p, cpumask_t *newmask); -- cgit v1.2.3 From fa85ae2418e6843953107cd6a06f645752829bc0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 25 Jan 2008 21:08:29 +0100 Subject: sched: rt time limit Very simple time limit on the realtime scheduling classes. Allow the rq's realtime class to consume sched_rt_ratio of every sched_rt_period slice. If the class exceeds this quota the fair class will preempt the realtime class. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 43e0339d65fc..d5ea144df836 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1490,6 +1490,8 @@ extern unsigned int sysctl_sched_child_runs_first; extern unsigned int sysctl_sched_features; extern unsigned int sysctl_sched_migration_cost; extern unsigned int sysctl_sched_nr_migrate; +extern unsigned int sysctl_sched_rt_period; +extern unsigned int sysctl_sched_rt_ratio; #if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP) extern unsigned int sysctl_sched_min_bal_int_shares; extern unsigned int sysctl_sched_max_bal_int_shares; -- cgit v1.2.3 From 6f505b16425a51270058e4a93441fe64de3dd435 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 25 Jan 2008 21:08:30 +0100 Subject: sched: rt group scheduling Extend group scheduling to also cover the realtime classes. It uses the time limiting introduced by the previous patch to allow multiple realtime groups. The hard time limit is required to keep behaviour deterministic. The algorithms used make the realtime scheduler O(tg), linear scaling wrt the number of task groups. This is the worst case behaviour I can't seem to get out of, the avg. case of the algorithms can be improved, I focused on correctness and worst case. [ akpm@linux-foundation.org: move side-effects out of BUG_ON(). ] Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- include/linux/init_task.h | 5 +++-- include/linux/sched.h | 10 +++++++++- 2 files changed, 12 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index ee65d87bedb7..796019b22b6f 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -130,12 +130,13 @@ extern struct group_info init_groups; .normal_prio = MAX_PRIO-20, \ .policy = SCHED_NORMAL, \ .cpus_allowed = CPU_MASK_ALL, \ - .nr_cpus_allowed = NR_CPUS, \ .mm = NULL, \ .active_mm = &init_mm, \ .rt = { \ .run_list = LIST_HEAD_INIT(tsk.rt.run_list), \ - .time_slice = HZ, }, \ + .time_slice = HZ, \ + .nr_cpus_allowed = NR_CPUS, \ + }, \ .ioprio = 0, \ .tasks = LIST_HEAD_INIT(tsk.tasks), \ .ptrace_children= LIST_HEAD_INIT(tsk.ptrace_children), \ diff --git a/include/linux/sched.h b/include/linux/sched.h index d5ea144df836..04eecbf0241e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -934,6 +934,15 @@ struct sched_rt_entity { struct list_head run_list; unsigned int time_slice; unsigned long timeout; + int nr_cpus_allowed; + +#ifdef CONFIG_FAIR_GROUP_SCHED + struct sched_rt_entity *parent; + /* rq on which this entity is (to be) queued: */ + struct rt_rq *rt_rq; + /* rq "owned" by this entity/group: */ + struct rt_rq *my_q; +#endif }; struct task_struct { @@ -978,7 +987,6 @@ struct task_struct { unsigned int policy; cpumask_t cpus_allowed; - int nr_cpus_allowed; #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; -- cgit v1.2.3 From 48d5e258216f1c7713633439beb98a38c7290649 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 25 Jan 2008 21:08:31 +0100 Subject: sched: rt throttling vs no_hz We need to teach no_hz about the rt throttling because its tick driven. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 04eecbf0241e..acadcab89ef9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -230,6 +230,8 @@ static inline int select_nohz_load_balancer(int cpu) } #endif +extern unsigned long rt_needs_cpu(int cpu); + /* * Only dump TASK_* tasks. (0 for all tasks) */ -- cgit v1.2.3 From d3d74453c34f8fd87674a8cf5b8a327c68f22e99 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 25 Jan 2008 21:08:31 +0100 Subject: hrtimer: fixup the HRTIMER_CB_IRQSAFE_NO_SOFTIRQ fallback Currently all highres=off timers are run from softirq context, but HRTIMER_CB_IRQSAFE_NO_SOFTIRQ timers expect to run from irq context. Fix this up by splitting it similar to the highres=on case. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- include/linux/hrtimer.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index ecc8e2685e2b..49067f14fac1 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -115,10 +115,8 @@ struct hrtimer { enum hrtimer_restart (*function)(struct hrtimer *); struct hrtimer_clock_base *base; unsigned long state; -#ifdef CONFIG_HIGH_RES_TIMERS enum hrtimer_cb_mode cb_mode; struct list_head cb_entry; -#endif #ifdef CONFIG_TIMER_STATS void *start_site; char start_comm[16]; @@ -194,10 +192,10 @@ struct hrtimer_cpu_base { spinlock_t lock; struct lock_class_key lock_key; struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; + struct list_head cb_pending; #ifdef CONFIG_HIGH_RES_TIMERS ktime_t expires_next; int hres_active; - struct list_head cb_pending; unsigned long nr_events; #endif }; @@ -319,6 +317,7 @@ extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, /* Soft interrupt function to run the hrtimer queues: */ extern void hrtimer_run_queues(void); +extern void hrtimer_run_pending(void); /* Bootup initialization: */ extern void __init hrtimers_init(void); -- cgit v1.2.3 From 6478d8800b75253b2a934ddcb734e13ade023ad0 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 25 Jan 2008 21:08:33 +0100 Subject: sched: remove the !PREEMPT_BKL code remove the !PREEMPT_BKL code. this removes 160 lines of legacy code. Signed-off-by: Ingo Molnar --- include/linux/hardirq.h | 6 +----- include/linux/smp_lock.h | 14 +------------- 2 files changed, 2 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 8d302298a161..2961ec788046 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -72,11 +72,7 @@ #define in_softirq() (softirq_count()) #define in_interrupt() (irq_count()) -#if defined(CONFIG_PREEMPT) && !defined(CONFIG_PREEMPT_BKL) -# define in_atomic() ((preempt_count() & ~PREEMPT_ACTIVE) != kernel_locked()) -#else -# define in_atomic() ((preempt_count() & ~PREEMPT_ACTIVE) != 0) -#endif +#define in_atomic() ((preempt_count() & ~PREEMPT_ACTIVE) != 0) #ifdef CONFIG_PREEMPT # define PREEMPT_CHECK_OFFSET 1 diff --git a/include/linux/smp_lock.h b/include/linux/smp_lock.h index 58962c51dee1..aab3a4cff4e1 100644 --- a/include/linux/smp_lock.h +++ b/include/linux/smp_lock.h @@ -17,22 +17,10 @@ extern void __lockfunc __release_kernel_lock(void); __release_kernel_lock(); \ } while (0) -/* - * Non-SMP kernels will never block on the kernel lock, - * so we are better off returning a constant zero from - * reacquire_kernel_lock() so that the compiler can see - * it at compile-time. - */ -#if defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT_BKL) -# define return_value_on_smp return -#else -# define return_value_on_smp -#endif - static inline int reacquire_kernel_lock(struct task_struct *task) { if (unlikely(task->lock_depth >= 0)) - return_value_on_smp __reacquire_kernel_lock(); + return __reacquire_kernel_lock(); return 0; } -- cgit v1.2.3 From e118adef232e637a8f091c1ded2fbf44fcf3ecc8 Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Fri, 25 Jan 2008 21:08:34 +0100 Subject: timers: don't #error on higher HZ values For some crazy reason (trying to work around hw problem in i810) I wanted to use HZ around 4000. Signed-off-by: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- include/linux/jiffies.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 8b080024bbc1..7ba9e47bf061 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -29,6 +29,12 @@ # define SHIFT_HZ 9 #elif HZ >= 768 && HZ < 1536 # define SHIFT_HZ 10 +#elif HZ >= 1536 && HZ < 3072 +# define SHIFT_HZ 11 +#elif HZ >= 3072 && HZ < 6144 +# define SHIFT_HZ 12 +#elif HZ >= 6144 && HZ < 12288 +# define SHIFT_HZ 13 #else # error You lose. #endif -- cgit v1.2.3 From 9745512ce79de686df354dc70a8d1a74d801892d Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Fri, 25 Jan 2008 21:08:34 +0100 Subject: sched: latencytop support LatencyTOP kernel infrastructure; it measures latencies in the scheduler and tracks it system wide and per process. Signed-off-by: Arjan van de Ven Signed-off-by: Ingo Molnar --- include/linux/latencytop.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/sched.h | 5 +++++ include/linux/stacktrace.h | 3 +++ 3 files changed, 52 insertions(+) create mode 100644 include/linux/latencytop.h (limited to 'include/linux') diff --git a/include/linux/latencytop.h b/include/linux/latencytop.h new file mode 100644 index 000000000000..901c2d6377a8 --- /dev/null +++ b/include/linux/latencytop.h @@ -0,0 +1,44 @@ +/* + * latencytop.h: Infrastructure for displaying latency + * + * (C) Copyright 2008 Intel Corporation + * Author: Arjan van de Ven + * + */ + +#ifndef _INCLUDE_GUARD_LATENCYTOP_H_ +#define _INCLUDE_GUARD_LATENCYTOP_H_ + +#ifdef CONFIG_LATENCYTOP + +#define LT_SAVECOUNT 32 +#define LT_BACKTRACEDEPTH 12 + +struct latency_record { + unsigned long backtrace[LT_BACKTRACEDEPTH]; + unsigned int count; + unsigned long time; + unsigned long max; +}; + + +struct task_struct; + +void account_scheduler_latency(struct task_struct *task, int usecs, int inter); + +void clear_all_latency_tracing(struct task_struct *p); + +#else + +static inline void +account_scheduler_latency(struct task_struct *task, int usecs, int inter) +{ +} + +static inline void clear_all_latency_tracing(struct task_struct *p) +{ +} + +#endif + +#endif diff --git a/include/linux/sched.h b/include/linux/sched.h index acadcab89ef9..dfc76e172f3f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -88,6 +88,7 @@ struct sched_param { #include #include #include +#include #include @@ -1220,6 +1221,10 @@ struct task_struct { int make_it_fail; #endif struct prop_local_single dirties; +#ifdef CONFIG_LATENCYTOP + int latency_record_count; + struct latency_record latency_record[LT_SAVECOUNT]; +#endif }; /* diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index e7fa657d0c49..5da9794b2d78 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -9,10 +9,13 @@ struct stack_trace { }; extern void save_stack_trace(struct stack_trace *trace); +extern void save_stack_trace_tsk(struct task_struct *tsk, + struct stack_trace *trace); extern void print_stack_trace(struct stack_trace *trace, int spaces); #else # define save_stack_trace(trace) do { } while (0) +# define save_stack_trace_tsk(tsk, trace) do { } while (0) # define print_stack_trace(trace, spaces) do { } while (0) #endif -- cgit v1.2.3 From 90739081ef8d5495d50abba9c5d333be9acd872a Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 25 Jan 2008 21:08:34 +0100 Subject: softlockup: fix signedness fix softlockup tunables signedness. mark tunables read-mostly. Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index dfc76e172f3f..53534f90a96a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -269,10 +269,10 @@ extern void softlockup_tick(void); extern void spawn_softlockup_task(void); extern void touch_softlockup_watchdog(void); extern void touch_all_softlockup_watchdogs(void); -extern int softlockup_thresh; +extern unsigned long softlockup_thresh; extern unsigned long sysctl_hung_task_check_count; extern unsigned long sysctl_hung_task_timeout_secs; -extern long sysctl_hung_task_warnings; +extern unsigned long sysctl_hung_task_warnings; #else static inline void softlockup_tick(void) { -- cgit v1.2.3 From 286100a6cf1c1f692e5f81d14b364ff12b7662f5 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 25 Jan 2008 21:08:34 +0100 Subject: sched, futex: detach sched.h and futex.h Signed-off-by: Alexey Dobriyan Signed-off-by: Ingo Molnar --- include/linux/futex.h | 6 +++++- include/linux/sched.h | 2 +- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/futex.h b/include/linux/futex.h index 92d420fe03f8..1a15f8e237a7 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -1,8 +1,12 @@ #ifndef _LINUX_FUTEX_H #define _LINUX_FUTEX_H -#include +#include +#include +struct inode; +struct mm_struct; +struct task_struct; union ktime; /* Second argument to futex syscall */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 53534f90a96a..734f6d8f6ed5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -78,7 +78,6 @@ struct sched_param { #include #include #include -#include #include #include @@ -94,6 +93,7 @@ struct sched_param { struct exec_domain; struct futex_pi_state; +struct robust_list_head; struct bio; /* -- cgit v1.2.3 From 6d082592b62689fb91578d0338d04a9f50991990 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Fri, 25 Jan 2008 21:08:35 +0100 Subject: sched: keep total / count stats in addition to the max for Right now, the linux kernel (with scheduler statistics enabled) keeps track of the maximum time a process is waiting to be scheduled. While the maximum is a very useful metric, tracking average and total is equally useful (at least for latencytop) to figure out the accumulated effect of scheduler delays. The accumulated effect is important to judge the performance impact of scheduler tuning/behavior. Signed-off-by: Arjan van de Ven Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 734f6d8f6ed5..df5b24ee80b3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -895,6 +895,8 @@ struct sched_entity { #ifdef CONFIG_SCHEDSTATS u64 wait_start; u64 wait_max; + u64 wait_count; + u64 wait_sum; u64 sleep_start; u64 sleep_max; -- cgit v1.2.3 From 05e997197e459a03df577ba49c34c1820957ee4a Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 30 Oct 2007 05:41:54 -0300 Subject: V4L/DVB (6487): i2c-id: add M52790 driver ID Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/i2c-id.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index e18017d45758..adbdc6da39ca 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -125,6 +125,7 @@ #define I2C_DRIVERID_LM4857 92 /* LM4857 Audio Amplifier */ #define I2C_DRIVERID_VP27SMPX 93 /* Panasonic VP27s tuner internal MPX */ #define I2C_DRIVERID_CS4270 94 /* Cirrus Logic 4270 audio codec */ +#define I2C_DRIVERID_M52790 95 /* Mitsubishi M52790SP/FP AV switch */ #define I2C_DRIVERID_I2CDEV 900 #define I2C_DRIVERID_ARP 902 /* SMBus ARP Client */ -- cgit v1.2.3 From 0b394def21e7d3bd02aeee5570473582ce7984ec Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 18 Dec 2007 19:27:31 -0300 Subject: V4L/DVB (6868): i2c-id.h: add I2C_DRIVERID_CS5345 Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/i2c-id.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index adbdc6da39ca..c7a51a196f51 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -126,6 +126,7 @@ #define I2C_DRIVERID_VP27SMPX 93 /* Panasonic VP27s tuner internal MPX */ #define I2C_DRIVERID_CS4270 94 /* Cirrus Logic 4270 audio codec */ #define I2C_DRIVERID_M52790 95 /* Mitsubishi M52790SP/FP AV switch */ +#define I2C_DRIVERID_CS5345 96 /* cs5345 audio processor */ #define I2C_DRIVERID_I2CDEV 900 #define I2C_DRIVERID_ARP 902 /* SMBus ARP Client */ -- cgit v1.2.3 From 1c029fd658baa2442e8e51dc9c819301cad95777 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:05 +0100 Subject: ide: remove ->dma_master field from ide_hwif_t (take 5) * Convert cmd64x, hpt366 and pdc202xx_old host drivers to use pci_resource_start(hwif->pci_dev, 4) instead of hwif->dma_master. * Remove no longer needed ->dma_master field from ide_hwif_t. v2: * Use the more readable 'hwif->dma_base - (hwif->channel * 8)' instead of pci_resource_start(hwif->pci_dev, 4). v3: * Use hwif->extra_base in hpt366/pdc20xx_old + some cosmetic fixups over v2 (suggested by Sergei). v4: * Correct offsets in hpt3xxn_set_clock(). v5: * Use hwif->extra_base in hpt366 for _real_ this time. (Noticed by Sergei) Acked-by: Sergei Shtylyov Cc: Jeff Garzik Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 9a6a41e7079f..1fb03b630676 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -766,7 +766,6 @@ typedef struct hwif_s { int rqsize; /* max sectors per request */ int irq; /* our irq number */ - unsigned long dma_master; /* reference base addr dmabase */ unsigned long dma_base; /* base addr for dma ports */ unsigned long dma_command; /* dma command register */ unsigned long dma_vendor1; /* dma vendor 1 register */ -- cgit v1.2.3 From cd2a2d969761c26542095c01324201ca0b3ee896 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:06 +0100 Subject: ide: remove task_ioreg_t typedef (take 2) Remove task_ioreg_t typedef from the kernel code (but leave it in for #ifndef/#endif __KERNEL__ case). While at it also move sata_ioreg_t typedef under #ifndef/#endif __KERNEL__. v2: Remove name of the second parameter from ide_execute_command() declaration. (Noticed by Sergei). Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/hdreg.h | 46 +++++++++++++++++++++++----------------------- include/linux/ide.h | 7 ++++--- 2 files changed, 27 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hdreg.h b/include/linux/hdreg.h index 818c6afc1091..3bcb88560418 100644 --- a/include/linux/hdreg.h +++ b/include/linux/hdreg.h @@ -87,10 +87,10 @@ #ifndef __KERNEL__ #define IDE_TASKFILE_STD_OUT_FLAGS 0xFE #define IDE_HOB_STD_OUT_FLAGS 0x3C -#endif typedef unsigned char task_ioreg_t; typedef unsigned long sata_ioreg_t; +#endif typedef union ide_reg_valid_s { unsigned all : 16; @@ -116,8 +116,8 @@ typedef union ide_reg_valid_s { } ide_reg_valid_t; typedef struct ide_task_request_s { - task_ioreg_t io_ports[8]; - task_ioreg_t hob_ports[8]; + __u8 io_ports[8]; + __u8 hob_ports[8]; ide_reg_valid_t out_flags; ide_reg_valid_t in_flags; int data_phase; @@ -133,32 +133,32 @@ typedef struct ide_ioctl_request_s { } ide_ioctl_request_t; struct hd_drive_cmd_hdr { - task_ioreg_t command; - task_ioreg_t sector_number; - task_ioreg_t feature; - task_ioreg_t sector_count; + __u8 command; + __u8 sector_number; + __u8 feature; + __u8 sector_count; }; typedef struct hd_drive_task_hdr { - task_ioreg_t data; - task_ioreg_t feature; - task_ioreg_t sector_count; - task_ioreg_t sector_number; - task_ioreg_t low_cylinder; - task_ioreg_t high_cylinder; - task_ioreg_t device_head; - task_ioreg_t command; + __u8 data; + __u8 feature; + __u8 sector_count; + __u8 sector_number; + __u8 low_cylinder; + __u8 high_cylinder; + __u8 device_head; + __u8 command; } task_struct_t; typedef struct hd_drive_hob_hdr { - task_ioreg_t data; - task_ioreg_t feature; - task_ioreg_t sector_count; - task_ioreg_t sector_number; - task_ioreg_t low_cylinder; - task_ioreg_t high_cylinder; - task_ioreg_t device_head; - task_ioreg_t control; + __u8 data; + __u8 feature; + __u8 sector_count; + __u8 sector_number; + __u8 low_cylinder; + __u8 high_cylinder; + __u8 device_head; + __u8 control; } hob_struct_t; #define TASKFILE_INVALID 0x7fff diff --git a/include/linux/ide.h b/include/linux/ide.h index 1fb03b630676..66a38f101175 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1019,7 +1019,8 @@ int ide_end_dequeued_request(ide_drive_t *drive, struct request *rq, extern void ide_set_handler (ide_drive_t *drive, ide_handler_t *handler, unsigned int timeout, ide_expiry_t *expiry); -extern void ide_execute_command(ide_drive_t *, task_ioreg_t cmd, ide_handler_t *, unsigned int, ide_expiry_t *); +void ide_execute_command(ide_drive_t *, u8, ide_handler_t *, unsigned int, + ide_expiry_t *); ide_startstop_t __ide_error(ide_drive_t *, struct request *, u8, u8); @@ -1068,8 +1069,8 @@ typedef struct ide_task_s { * struct hd_drive_hob_hdr hobf; * hob_struct_t hobf; */ - task_ioreg_t tfRegister[8]; - task_ioreg_t hobRegister[8]; + u8 tfRegister[8]; + u8 hobRegister[8]; ide_reg_valid_t tf_out_flags; ide_reg_valid_t tf_in_flags; int data_phase; -- cgit v1.2.3 From 650d841d9e053a618dd8ce753422f91b493cf2f6 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:06 +0100 Subject: ide: add struct ide_taskfile (take 2) * Don't set write-only ide_task_t.hobRegister[6] and ide_task_t.hobRegister[7] in idedisk_set_max_address_ext(). * Add struct ide_taskfile and use it in ide_task_t instead of tfRegister[] and hobRegister[]. * Remove no longer needed IDE_CONTROL_OFFSET_HOB define. * Add #ifndef/#endif __KERNEL__ around definitions of {task,hob}_struct_t. While at it: * Use ATA_LBA define for LBA bit (0x40) as suggested by Tejun Heo. v2: * Add missing newlines. (Noticed by Sergei) * Use ~ATA_LBA instead of 0xBF. (Noticed by Sergei) * Use unnamed unions for error/feature and status/command. (Suggested by Sergei). There should be no functionality changes caused by this patch. Acked-by: Sergei Shtylyov Cc: Tejun Heo Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/hdreg.h | 4 +++- include/linux/ide.h | 43 +++++++++++++++++++++++++++++++++---------- 2 files changed, 36 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hdreg.h b/include/linux/hdreg.h index 3bcb88560418..df17bf767d98 100644 --- a/include/linux/hdreg.h +++ b/include/linux/hdreg.h @@ -117,7 +117,7 @@ typedef union ide_reg_valid_s { typedef struct ide_task_request_s { __u8 io_ports[8]; - __u8 hob_ports[8]; + __u8 hob_ports[8]; /* bytes 6 and 7 are unused */ ide_reg_valid_t out_flags; ide_reg_valid_t in_flags; int data_phase; @@ -139,6 +139,7 @@ struct hd_drive_cmd_hdr { __u8 sector_count; }; +#ifndef __KERNEL__ typedef struct hd_drive_task_hdr { __u8 data; __u8 feature; @@ -160,6 +161,7 @@ typedef struct hd_drive_hob_hdr { __u8 device_head; __u8 control; } hob_struct_t; +#endif #define TASKFILE_INVALID 0x7fff #define TASKFILE_48 0x8000 diff --git a/include/linux/ide.h b/include/linux/ide.h index 66a38f101175..69b78bb39caf 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -103,8 +103,6 @@ typedef unsigned char byte; /* used everywhere */ #define IDE_FEATURE_OFFSET IDE_ERROR_OFFSET #define IDE_COMMAND_OFFSET IDE_STATUS_OFFSET -#define IDE_CONTROL_OFFSET_HOB (7) - #define IDE_DATA_REG (HWIF(drive)->io_ports[IDE_DATA_OFFSET]) #define IDE_ERROR_REG (HWIF(drive)->io_ports[IDE_ERROR_OFFSET]) #define IDE_NSECTOR_REG (HWIF(drive)->io_ports[IDE_NSECTOR_OFFSET]) @@ -1062,15 +1060,40 @@ extern void ide_end_drive_cmd(ide_drive_t *, u8, u8); */ extern int ide_wait_cmd(ide_drive_t *, u8, u8, u8, u8, u8 *); +struct ide_taskfile { + u8 hob_data; /* 0: high data byte (for TASKFILE IOCTL) */ + + u8 hob_feature; /* 1-5: additional data to support LBA48 */ + u8 hob_nsect; + u8 hob_lbal; + u8 hob_lbam; + u8 hob_lbah; + + u8 data; /* 6: low data byte (for TASKFILE IOCTL) */ + + union { /*  7: */ + u8 error; /* read: error */ + u8 feature; /* write: feature */ + }; + + u8 nsect; /* 8: number of sectors */ + u8 lbal; /* 9: LBA low */ + u8 lbam; /* 10: LBA mid */ + u8 lbah; /* 11: LBA high */ + + u8 device; /* 12: device select */ + + union { /* 13: */ + u8 status; /*  read: status  */ + u8 command; /* write: command */ + }; +}; + typedef struct ide_task_s { -/* - * struct hd_drive_task_hdr tf; - * task_struct_t tf; - * struct hd_drive_hob_hdr hobf; - * hob_struct_t hobf; - */ - u8 tfRegister[8]; - u8 hobRegister[8]; + union { + struct ide_taskfile tf; + u8 tf_array[14]; + }; ide_reg_valid_t tf_out_flags; ide_reg_valid_t tf_in_flags; int data_phase; -- cgit v1.2.3 From 9e42237f26cf517a3f682505f03a3a8d89b3b35d Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:07 +0100 Subject: ide: add ide_tf_load() helper Based on the earlier work by Tejun Heo. * Add 'tf_flags' field (for taskfile flags) to ide_task_t. * Add IDE_TFLAG_LBA48 taskfile flag for LBA48 taskfiles. * Add IDE_TFLAG_NO_SELECT_MASK taskfile flag for __ide_do_rw_disk() which doesn't use SELECT_MASK() (looks like a bug but it requires some more investigation). * Split off ide_tf_load() helper from do_rw_taskfile(). * Convert __ide_do_rw_disk() to use ide_tf_load(). There should be no functionality changes caused by this patch. Cc: Tejun Heo Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 69b78bb39caf..e25fd0b1dd79 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1060,6 +1060,11 @@ extern void ide_end_drive_cmd(ide_drive_t *, u8, u8); */ extern int ide_wait_cmd(ide_drive_t *, u8, u8, u8, u8, u8 *); +enum { + IDE_TFLAG_LBA48 = (1 << 0), + IDE_TFLAG_NO_SELECT_MASK = (1 << 1), +}; + struct ide_taskfile { u8 hob_data; /* 0: high data byte (for TASKFILE IOCTL) */ @@ -1094,6 +1099,7 @@ typedef struct ide_task_s { struct ide_taskfile tf; u8 tf_array[14]; }; + u8 tf_flags; ide_reg_valid_t tf_out_flags; ide_reg_valid_t tf_in_flags; int data_phase; @@ -1104,6 +1110,8 @@ typedef struct ide_task_s { void *special; /* valid_t generally */ } ide_task_t; +void ide_tf_load(ide_drive_t *, ide_task_t *); + extern u32 ide_read_24(ide_drive_t *); extern void SELECT_DRIVE(ide_drive_t *); -- cgit v1.2.3 From 9a3c49be5c5f7388eefb712be9a383904140532e Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:07 +0100 Subject: ide: add ide_no_data_taskfile() helper * Add ide_no_data_taskfile() helper and convert ide_raw_taskfile() w/ NO DATA protocol users to use it instead. * Set ->data_phase explicitly in ide_no_data_taskfile() (TASKFILE_NO_DATA is defined as 0x0000). * Unexport task_no_data_intr(). Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index e25fd0b1dd79..11bfbc40c50a 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1140,6 +1140,8 @@ extern ide_startstop_t pre_task_out_intr(ide_drive_t *, struct request *); extern int ide_raw_taskfile(ide_drive_t *, ide_task_t *, u8 *); +int ide_no_data_taskfile(ide_drive_t *, ide_task_t *); + int ide_taskfile_ioctl(ide_drive_t *, unsigned int, unsigned long); int ide_cmd_ioctl(ide_drive_t *, unsigned int, unsigned long); int ide_task_ioctl(ide_drive_t *, unsigned int, unsigned long); -- cgit v1.2.3 From 74095a91ed02f6727b62d4416be00a041f2d7436 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:07 +0100 Subject: ide: use do_rw_taskfile() in flagged_taskfile() Based on the earlier work by Tejun Heo. * Move setting IDE_TFLAG_LBA48 taskfile flag from do_rw_taskfile() function to the callers. * Add IDE_TFLAG_FLAGGED taskfile flag for flagged taskfiles coming from ide_taskfile_ioctl(). Check it instead of ->tf_out_flags.all. * Add IDE_TFLAG_OUT_DATA taskfile flag to indicate the need to load IDE data register in ide_tf_load(). * Add IDE_TFLAG_OUT_* taskfile flags to indicate the need to load particular IDE taskfile registers in ide_tf_load(). * Update do_rw_taskfile() and ide_tf_load() users to set respective IDE_TFLAG_OUT_* taksfile flags. * Add task_dma_ok() helper. * Use IDE_TFLAG_FLAGGED taskfile flag to select HIHI mask in ide_tf_load(). * Use do_rw_taskfile() in flagged_taskfile(). * Remove no longer needed 'tf_out_flags' field from ide_task_t. There should be no functionality changes caused by this patch. Cc: Tejun Heo Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 11bfbc40c50a..6dfee2a46f1b 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1063,6 +1063,28 @@ extern int ide_wait_cmd(ide_drive_t *, u8, u8, u8, u8, u8 *); enum { IDE_TFLAG_LBA48 = (1 << 0), IDE_TFLAG_NO_SELECT_MASK = (1 << 1), + IDE_TFLAG_FLAGGED = (1 << 2), + IDE_TFLAG_OUT_DATA = (1 << 3), + IDE_TFLAG_OUT_HOB_FEATURE = (1 << 4), + IDE_TFLAG_OUT_HOB_NSECT = (1 << 5), + IDE_TFLAG_OUT_HOB_LBAL = (1 << 6), + IDE_TFLAG_OUT_HOB_LBAM = (1 << 7), + IDE_TFLAG_OUT_HOB_LBAH = (1 << 8), + IDE_TFLAG_OUT_HOB = IDE_TFLAG_OUT_HOB_FEATURE | + IDE_TFLAG_OUT_HOB_NSECT | + IDE_TFLAG_OUT_HOB_LBAL | + IDE_TFLAG_OUT_HOB_LBAM | + IDE_TFLAG_OUT_HOB_LBAH, + IDE_TFLAG_OUT_FEATURE = (1 << 9), + IDE_TFLAG_OUT_NSECT = (1 << 10), + IDE_TFLAG_OUT_LBAL = (1 << 11), + IDE_TFLAG_OUT_LBAM = (1 << 12), + IDE_TFLAG_OUT_LBAH = (1 << 13), + IDE_TFLAG_OUT_TF = IDE_TFLAG_OUT_FEATURE | + IDE_TFLAG_OUT_NSECT | + IDE_TFLAG_OUT_LBAL | + IDE_TFLAG_OUT_LBAM | + IDE_TFLAG_OUT_LBAH, }; struct ide_taskfile { @@ -1099,8 +1121,7 @@ typedef struct ide_task_s { struct ide_taskfile tf; u8 tf_array[14]; }; - u8 tf_flags; - ide_reg_valid_t tf_out_flags; + u16 tf_flags; ide_reg_valid_t tf_in_flags; int data_phase; int command_type; -- cgit v1.2.3 From 4ee06b7e677da4c75f2fcc5fd850543852d18bf2 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:08 +0100 Subject: ide: remove stale ide.h "configuration options" Remove stale ide.h "configuration options": * INITIAL_MULT_COUNT - always defined to 0 * SUPPORT_SLOW_DATA_PORTS - unused * OK_TO_RESET_CONTROLLER - always defined to 1 * DISABLE_IRQ_NOSYNC - always defined to 0 Leave SUPPORT_VLB_SYNC (defined to 0 for CRIS and FRV, otherwise to 1) for now but disallow overriding it by . There should be no functionality changes caused by this patch. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 27 ++++----------------------- 1 file changed, 4 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 6dfee2a46f1b..0b088f18d422 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -27,25 +27,10 @@ #include #include -/****************************************************************************** - * IDE driver configuration options (play with these as desired): - * - * REALLY_SLOW_IO can be defined in ide.c and ide-cd.c, if necessary - */ -#define INITIAL_MULT_COUNT 0 /* off=0; on=2,4,8,16,32, etc.. */ - -#ifndef SUPPORT_SLOW_DATA_PORTS /* 1 to support slow data ports */ -#define SUPPORT_SLOW_DATA_PORTS 1 /* 0 to reduce kernel size */ -#endif -#ifndef SUPPORT_VLB_SYNC /* 1 to support weird 32-bit chips */ -#define SUPPORT_VLB_SYNC 1 /* 0 to reduce kernel size */ -#endif -#ifndef OK_TO_RESET_CONTROLLER /* 1 needed for good error recovery */ -#define OK_TO_RESET_CONTROLLER 1 /* 0 for use with AH2372A/B interface */ -#endif - -#ifndef DISABLE_IRQ_NOSYNC -#define DISABLE_IRQ_NOSYNC 0 +#if defined(CRIS) || defined(FRV) +# define SUPPORT_VLB_SYNC 0 +#else +# define SUPPORT_VLB_SYNC 1 #endif /* @@ -55,10 +40,6 @@ #define IDE_NO_IRQ (-1) -/* - * "No user-serviceable parts" beyond this point :) - *****************************************************************************/ - typedef unsigned char byte; /* used everywhere */ /* -- cgit v1.2.3 From 807e35d695690011faa1ce3ad67dfc23c1e39bdc Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:10 +0100 Subject: ide: use ide_tf_load() in execute_drive_cmd() * Add IDE_TFLAG_OUT_DEVICE taskfile flag to indicate the need of writing the Device register and handle it in ide_tf_load(). Update ide_tf_load() and {do_rw,flagged}_taskfile() users accordingly. * Use struct ide_taskfile and ide_tf_load() in execute_drive_cmd(). * Make the debugging code dump all taskfile registers for both REQ_ATA_TYPE_{CMD,TASK} requests and move it to ide_tf_load() so it also covers REQ_ATA_TYPE_TASKFILE requests. There should be no functionality changes caused by this patch (unless DEBUG is defined). Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 0b088f18d422..e1f652c6440c 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1066,6 +1066,7 @@ enum { IDE_TFLAG_OUT_LBAL | IDE_TFLAG_OUT_LBAM | IDE_TFLAG_OUT_LBAH, + IDE_TFLAG_OUT_DEVICE = (1 << 14), }; struct ide_taskfile { -- cgit v1.2.3 From 29ed2a5f8c4380959f18e9cbaff13bc61e09889c Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:11 +0100 Subject: ide: remove REQ_TYPE_ATA_TASK Based on the earlier work by Tejun Heo. All users are gone so we can finally remove it. Cc: Tejun Heo Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d18ee67b40f8..40ee1706caa3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -144,7 +144,6 @@ enum rq_cmd_type_bits { * private REQ_LB opcodes to differentiate what type of request this is */ REQ_TYPE_ATA_CMD, - REQ_TYPE_ATA_TASK, REQ_TYPE_ATA_TASKFILE, REQ_TYPE_ATA_PC, }; -- cgit v1.2.3 From 6a2144146aa2e0eb60e48ba73ac0e1c51346edf6 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:11 +0100 Subject: ide: CPU endianness doesn't matter for special_t special_t is used only internally by the IDE subsystem (it isn't related to hardware registers and isn't exported to the user-space). Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index e1f652c6440c..c6ffc2028fb5 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -306,23 +306,12 @@ static inline void ide_init_hwif_ports(hw_regs_t *hw, typedef union { unsigned all : 8; struct { -#if defined(__LITTLE_ENDIAN_BITFIELD) unsigned set_geometry : 1; unsigned recalibrate : 1; unsigned set_multmode : 1; unsigned set_tune : 1; unsigned serviced : 1; unsigned reserved : 3; -#elif defined(__BIG_ENDIAN_BITFIELD) - unsigned reserved : 3; - unsigned serviced : 1; - unsigned set_tune : 1; - unsigned set_multmode : 1; - unsigned recalibrate : 1; - unsigned set_geometry : 1; -#else -#error "Please fix " -#endif } b; } special_t; -- cgit v1.2.3 From 22c525b976778cce5bb6f8fdcc70046168c54b1a Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:11 +0100 Subject: ide: remove ata_status_t and atapi_status_t Remove ata_status_t (unused) and atapi_status_t. While at it: * replace 'HWIF(drive)' by 'drive->hwif' (or just 'hwif' where possible) Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 44 -------------------------------------------- 1 file changed, 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index c6ffc2028fb5..921cf717f22a 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -365,50 +365,6 @@ typedef union { } b; } select_t, ata_select_t; -/* - * The ATA-IDE Status Register. - * The ATAPI Status Register. - * - * check : Error occurred - * idx : Index Error - * corr : Correctable error occurred - * drq : Data is request by the device - * dsc : Disk Seek Complete : ata - * : Media access command finished : atapi - * df : Device Fault : ata - * : Reserved : atapi - * drdy : Ready, Command Mode Capable : ata - * : Ignored for ATAPI commands : atapi - * bsy : Disk is Busy - * : The device has access to the command block - */ -typedef union { - unsigned all :8; - struct { -#if defined(__LITTLE_ENDIAN_BITFIELD) - unsigned check :1; - unsigned idx :1; - unsigned corr :1; - unsigned drq :1; - unsigned dsc :1; - unsigned df :1; - unsigned drdy :1; - unsigned bsy :1; -#elif defined(__BIG_ENDIAN_BITFIELD) - unsigned bsy :1; - unsigned drdy :1; - unsigned df :1; - unsigned dsc :1; - unsigned drq :1; - unsigned corr :1; - unsigned idx :1; - unsigned check :1; -#else -#error "Please fix " -#endif - } b; -} ata_status_t, atapi_status_t; - /* * ATAPI Feature Register * -- cgit v1.2.3 From 0e38a66a1e69821ab57a06d5a7b11f0df9275bf4 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:12 +0100 Subject: ide: remove atapi_error_t (take 2) Remove atapi_error_t. While at it: * replace 'HWIF(drive)' by 'drive->hwif' v2: * Add {ILI,EOM,LFS}_ERR defines to . Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/hdreg.h | 3 +++ include/linux/ide.h | 30 ------------------------------ 2 files changed, 3 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hdreg.h b/include/linux/hdreg.h index df17bf767d98..0521f1234f15 100644 --- a/include/linux/hdreg.h +++ b/include/linux/hdreg.h @@ -44,7 +44,9 @@ /* Bits for HD_ERROR */ #define MARK_ERR 0x01 /* Bad address mark */ +#define ILI_ERR 0x01 /* Illegal Length Indication (ATAPI) */ #define TRK0_ERR 0x02 /* couldn't find track 0 */ +#define EOM_ERR 0x02 /* End Of Media (ATAPI) */ #define ABRT_ERR 0x04 /* Command aborted */ #define MCR_ERR 0x08 /* media change request */ #define ID_ERR 0x10 /* ID field not found */ @@ -52,6 +54,7 @@ #define ECC_ERR 0x40 /* Uncorrectable ECC error */ #define BBD_ERR 0x80 /* pre-EIDE meaning: block marked bad */ #define ICRC_ERR 0x80 /* new meaning: CRC error during transfer */ +#define LFS_ERR 0xf0 /* Last Failed Sense (ATAPI) */ /* Bits of HD_NSECTOR */ #define CD 0x01 diff --git a/include/linux/ide.h b/include/linux/ide.h index 921cf717f22a..0c1b0aaa2865 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -416,36 +416,6 @@ typedef union { } b; } atapi_ireason_t; -/* - * The ATAPI error register. - * - * ili : Illegal Length Indication - * eom : End Of Media Detected - * abrt : Aborted command - As defined by ATA - * mcr : Media Change Requested - As defined by ATA - * sense_key : Sense key of the last failed packet command - */ -typedef union { - unsigned all :8; - struct { -#if defined(__LITTLE_ENDIAN_BITFIELD) - unsigned ili :1; - unsigned eom :1; - unsigned abrt :1; - unsigned mcr :1; - unsigned sense_key :4; -#elif defined(__BIG_ENDIAN_BITFIELD) - unsigned sense_key :4; - unsigned mcr :1; - unsigned abrt :1; - unsigned eom :1; - unsigned ili :1; -#else -#error "Please fix " -#endif - } b; -} atapi_error_t; - /* * Status returned from various ide_ functions */ -- cgit v1.2.3 From e5f9f5a89a01abc2b9c09747452aeb9218d6bffd Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:12 +0100 Subject: ide: remove atapi_feature_t Remove atapi_feature_t. While at it: * replace 'HWIF(drive)' by 'hwif' Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 27 --------------------------- 1 file changed, 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 0c1b0aaa2865..a638dde17e77 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -365,33 +365,6 @@ typedef union { } b; } select_t, ata_select_t; -/* - * ATAPI Feature Register - * - * dma : Using DMA or PIO - * reserved321 : Reserved - * reserved654 : Reserved (Tag Type) - * reserved7 : Reserved - */ -typedef union { - unsigned all :8; - struct { -#if defined(__LITTLE_ENDIAN_BITFIELD) - unsigned dma :1; - unsigned reserved321 :3; - unsigned reserved654 :3; - unsigned reserved7 :1; -#elif defined(__BIG_ENDIAN_BITFIELD) - unsigned reserved7 :1; - unsigned reserved654 :3; - unsigned reserved321 :3; - unsigned dma :1; -#else -#error "Please fix " -#endif - } b; -} atapi_feature_t; - /* * ATAPI Interrupt Reason Register. * -- cgit v1.2.3 From 790d1239898d4f893112280decd344d90f43ee96 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:12 +0100 Subject: ide: remove ata_nsector_t, ata_data_t and atapi_bcount_t Remove ata_nsector_t, ata_data_t (unused) and atapi_bcount_t. While at it: * replace 'HWIF(drive)' by 'hwif' Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index a638dde17e77..cf1a5aaebd9e 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -315,26 +315,6 @@ typedef union { } b; } special_t; -/* - * ATA DATA Register Special. - * ATA NSECTOR Count Register(). - * ATAPI Byte Count Register. - */ -typedef union { - unsigned all :16; - struct { -#if defined(__LITTLE_ENDIAN_BITFIELD) - unsigned low :8; /* LSB */ - unsigned high :8; /* MSB */ -#elif defined(__BIG_ENDIAN_BITFIELD) - unsigned high :8; /* MSB */ - unsigned low :8; /* LSB */ -#else -#error "Please fix " -#endif - } b; -} ata_nsector_t, ata_data_t, atapi_bcount_t; - /* * ATA-IDE Select Register, aka Device-Head * -- cgit v1.2.3 From 8e7657ae0f56c14882e53ffdae8055c2b1624de1 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:12 +0100 Subject: ide: remove atapi_ireason_t (take 3) Remove atapi_ireason_t. While at it: * replace 'HWIF(drive)' by 'drive->hwif' (or just 'hwif' where possible) v2: * v1 had CD and IO bits reversed in many places. * Use CD and IO defines from . v3: * Fix incorrect "(ireason & IO) == test_bit()". (Noticed by Sergei) Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 24 ------------------------ 1 file changed, 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index cf1a5aaebd9e..790ffa7f6949 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -345,30 +345,6 @@ typedef union { } b; } select_t, ata_select_t; -/* - * ATAPI Interrupt Reason Register. - * - * cod : Information transferred is command (1) or data (0) - * io : The device requests us to read (1) or write (0) - * reserved : Reserved - */ -typedef union { - unsigned all :8; - struct { -#if defined(__LITTLE_ENDIAN_BITFIELD) - unsigned cod :1; - unsigned io :1; - unsigned reserved :6; -#elif defined(__BIG_ENDIAN_BITFIELD) - unsigned reserved :6; - unsigned io :1; - unsigned cod :1; -#else -#error "Please fix " -#endif - } b; -} atapi_ireason_t; - /* * Status returned from various ide_ functions */ -- cgit v1.2.3 From 2fc573881957337c4ea1c84b92d2f27d076cad57 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:13 +0100 Subject: ide: add ide_pktcmd_tf_load() helper Add ide_pktcmd_tf_load() helper and convert ATAPI device drivers to use it. There should be no functionality changes caused by this patch. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 790ffa7f6949..20969eb1789a 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -968,6 +968,8 @@ extern void QUIRK_LIST(ide_drive_t *); extern int drive_is_ready(ide_drive_t *); +void ide_pktcmd_tf_load(ide_drive_t *, u32, u16, u8); + /* * taskfile io for disks for now...and builds request from ide_ioctl */ -- cgit v1.2.3 From cd3dbc99da337f2130f3cb2691fbb65c8bf22337 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:13 +0100 Subject: ide: remove QUIRK_LIST() Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 20969eb1789a..7a144c9ee098 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -964,7 +964,6 @@ extern u32 ide_read_24(ide_drive_t *); extern void SELECT_DRIVE(ide_drive_t *); extern void SELECT_INTERRUPT(ide_drive_t *); extern void SELECT_MASK(ide_drive_t *, int); -extern void QUIRK_LIST(ide_drive_t *); extern int drive_is_ready(ide_drive_t *); -- cgit v1.2.3 From f919790f8c929ab1b392ad1a0c2e1b53337b5071 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:13 +0100 Subject: ide: remove SELECT_INTERRUPT() Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 7a144c9ee098..e80351878b8b 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -962,7 +962,6 @@ void ide_tf_load(ide_drive_t *, ide_task_t *); extern u32 ide_read_24(ide_drive_t *); extern void SELECT_DRIVE(ide_drive_t *); -extern void SELECT_INTERRUPT(ide_drive_t *); extern void SELECT_MASK(ide_drive_t *, int); extern int drive_is_ready(ide_drive_t *); -- cgit v1.2.3 From 7299a3918442dc9a5abb71b9f65b1dd17637c8c0 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:14 +0100 Subject: ide: remove hwif->intrproc Given that: * hpt366.c::hpt3xx_intrproc() is the only user of hwif->intrproc * hpt366.c::hpt3xx_quirkproc() sets drive->quirk_list to 1 for quirky drives which is a value unique to hpt366 host driver we can remove hwif->intproc and just check for drive->quirk_list == 1 in ide_do_request(). Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index e80351878b8b..90f83b65eb8f 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -524,8 +524,6 @@ typedef struct hwif_s { void (*pre_reset)(ide_drive_t *); /* routine to reset controller after a disk reset */ void (*resetproc)(ide_drive_t *); - /* special interrupt handling for shared pci interrupts */ - void (*intrproc)(ide_drive_t *); /* special host masking for drive selection */ void (*maskproc)(ide_drive_t *, int); /* check host's drive quirk list */ -- cgit v1.2.3 From ac026ff254b32915bb14ba97a23b4019d137f181 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:14 +0100 Subject: ide: remove 'command_type' field from ide_task_t * Add 'data_buf' and 'nsect' variables in ide_taskfile_ioctl() to cache data buffer pointer and number of sectors to transfer (this allows us to have only one ide_diag_taskfile() call). * Add IDE_TFLAG_WRITE taskfile flag and use it to check whether the REQ_RW request flag should be set. * Move ->command_type handling from ide_diag_taskfile() to ide_taskfile_ioctl() and use ->req_cmd instead of ->command_type. * Add 'nsect' parameter to ide_raw_taskfile(). * Merge ide_diag_taskfile() into ide_raw_taskfile(). * Initialize ->data_phase explicitly in idedisk_prepare_flush(), ide_start_power_step() and ide_disk_special(). * Remove no longer needed 'command_type' field from ide_task_t. * Add #ifndef/#endif __KERNEL__ to around no longer used by kernel IDE_DRIVE_TASK_* and TASKFILE_* defines. There should be no functionality changes caused by this patch. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/hdreg.h | 13 +++++++------ include/linux/ide.h | 5 ++--- 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hdreg.h b/include/linux/hdreg.h index 0521f1234f15..ff43f8d6b5b3 100644 --- a/include/linux/hdreg.h +++ b/include/linux/hdreg.h @@ -73,13 +73,13 @@ #define HDIO_DRIVE_HOB_HDR_SIZE (8 * sizeof(__u8)) #define HDIO_DRIVE_TASK_HDR_SIZE (8 * sizeof(__u8)) -#define IDE_DRIVE_TASK_INVALID -1 #define IDE_DRIVE_TASK_NO_DATA 0 +#ifndef __KERNEL__ +#define IDE_DRIVE_TASK_INVALID -1 #define IDE_DRIVE_TASK_SET_XFER 1 - #define IDE_DRIVE_TASK_IN 2 - #define IDE_DRIVE_TASK_OUT 3 +#endif #define IDE_DRIVE_TASK_RAW_WRITE 4 /* @@ -166,9 +166,6 @@ typedef struct hd_drive_hob_hdr { } hob_struct_t; #endif -#define TASKFILE_INVALID 0x7fff -#define TASKFILE_48 0x8000 - #define TASKFILE_NO_DATA 0x0000 #define TASKFILE_IN 0x0001 @@ -183,12 +180,16 @@ typedef struct hd_drive_hob_hdr { #define TASKFILE_IN_DMAQ 0x0080 #define TASKFILE_OUT_DMAQ 0x0100 +#ifndef __KERNEL__ #define TASKFILE_P_IN 0x0200 #define TASKFILE_P_OUT 0x0400 #define TASKFILE_P_IN_DMA 0x0800 #define TASKFILE_P_OUT_DMA 0x1000 #define TASKFILE_P_IN_DMAQ 0x2000 #define TASKFILE_P_OUT_DMAQ 0x4000 +#define TASKFILE_48 0x8000 +#define TASKFILE_INVALID 0x7fff +#endif /* ATA/ATAPI Commands pre T13 Spec */ #define WIN_NOP 0x00 diff --git a/include/linux/ide.h b/include/linux/ide.h index 90f83b65eb8f..7485fc705ca4 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -909,6 +909,7 @@ enum { IDE_TFLAG_OUT_LBAM | IDE_TFLAG_OUT_LBAH, IDE_TFLAG_OUT_DEVICE = (1 << 14), + IDE_TFLAG_WRITE = (1 << 15), }; struct ide_taskfile { @@ -948,7 +949,6 @@ typedef struct ide_task_s { u16 tf_flags; ide_reg_valid_t tf_in_flags; int data_phase; - int command_type; ide_pre_handler_t *prehandler; ide_handler_t *handler; struct request *rq; /* copy of request */ @@ -983,8 +983,7 @@ extern ide_startstop_t task_no_data_intr(ide_drive_t *); extern ide_startstop_t task_in_intr(ide_drive_t *); extern ide_startstop_t pre_task_out_intr(ide_drive_t *, struct request *); -extern int ide_raw_taskfile(ide_drive_t *, ide_task_t *, u8 *); - +int ide_raw_taskfile(ide_drive_t *, ide_task_t *, u8 *, u16); int ide_no_data_taskfile(ide_drive_t *, ide_task_t *); int ide_taskfile_ioctl(ide_drive_t *, unsigned int, unsigned long); -- cgit v1.2.3 From 866e2ec9ce525de0e7c10d02ead8d85af27adffd Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:14 +0100 Subject: ide: remove 'tf_in_flags' field from ide_task_t * Add IDE_TFLAG_IN_DATA taskfile flag to indicate the need of reading IDE_DATA_REG in ide_end_drive_cmd(). Set the new flag in ide_taskfile_ioctl() if ->in_flags.b.data is set. * Add IDE_TFLAG_FLAGGED_SET_IN_FLAGS taskfile flag to indicate the need of modifying ->in_flags in ide_taskfile_ioctl(). Set the new flag in flagged_taskfile() and move the code modifying ->tf_in_flags to ide_taskfile_ioctl(). While at it remove the bogus comment: ->tf_in_flags (except .b.data) have no effect on selection of registers to read. * Remove no longer needed 'tf_in_flags' field from ide_task_t. As the result we finally have the internals of HDIO_DRIVE_TASKFILE ioctl separated from the core IDE code. There should be no functionality changes caused by this patch. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 7485fc705ca4..c23ef2df2cbb 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -910,6 +910,8 @@ enum { IDE_TFLAG_OUT_LBAH, IDE_TFLAG_OUT_DEVICE = (1 << 14), IDE_TFLAG_WRITE = (1 << 15), + IDE_TFLAG_FLAGGED_SET_IN_FLAGS = (1 << 16), + IDE_TFLAG_IN_DATA = (1 << 17), }; struct ide_taskfile { @@ -946,8 +948,7 @@ typedef struct ide_task_s { struct ide_taskfile tf; u8 tf_array[14]; }; - u16 tf_flags; - ide_reg_valid_t tf_in_flags; + u32 tf_flags; int data_phase; ide_pre_handler_t *prehandler; ide_handler_t *handler; -- cgit v1.2.3 From 1edee60e9d994f2b9a79b1333be39790683541fe Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:15 +0100 Subject: ide: merge flagged_taskfile() into do_rw_taskfile() Based on the earlier work by Tejun Heo. task->data_phase == TASKFILE_MULTI_{IN,OUT} vs drive->mult_count == 0 check is needed also for ide_taskfile_ioctl() requests that don't have IDE_TFLAG_FLAGGED taskfile flag set. Cc: Tejun Heo Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index c23ef2df2cbb..849447572a6b 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -972,11 +972,6 @@ void ide_pktcmd_tf_load(ide_drive_t *, u32, u16, u8); */ extern ide_startstop_t do_rw_taskfile(ide_drive_t *, ide_task_t *); -/* - * Special Flagged Register Validation Caller - */ -extern ide_startstop_t flagged_taskfile(ide_drive_t *, ide_task_t *); - extern ide_startstop_t set_multmode_intr(ide_drive_t *); extern ide_startstop_t set_geometry_intr(ide_drive_t *); extern ide_startstop_t recal_intr(ide_drive_t *); -- cgit v1.2.3 From 10d90157c83d4b6743c9063c36f9e7f27aa254b6 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:16 +0100 Subject: ide: convert do_rw_taskfile() to use ->data_phase * Use task->data_phase in do_rw_taskfile() to decide what to do. * task->prehandler is only used by TASKFILE[_MULTI]_OUT so just use pre_task_out_intr() directly and remove no longer needed 'prehandler' field from ide_task_t. * Remove no longer needed ide_pre_handler_t type. There should be no functionality changes caused by this patch. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 849447572a6b..2c28fb75915a 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -626,7 +626,6 @@ typedef struct hwif_s { /* * internal ide interrupt handler type */ -typedef ide_startstop_t (ide_pre_handler_t)(ide_drive_t *, struct request *); typedef ide_startstop_t (ide_handler_t)(ide_drive_t *); typedef int (ide_expiry_t)(ide_drive_t *); @@ -950,7 +949,6 @@ typedef struct ide_task_s { }; u32 tf_flags; int data_phase; - ide_pre_handler_t *prehandler; ide_handler_t *handler; struct request *rq; /* copy of request */ void *special; /* valid_t generally */ -- cgit v1.2.3 From 1192e528e064ebb9a578219731d2b0f78ca3c1ec Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:16 +0100 Subject: ide: use ->data_phase to set ->handler in do_rw_taskfile() * Use ->data_phase to set ->handler in do_rw_taskfile() instead of setting ->handler in callers of ide_raw_taskfile()/do_rw_taskfile(). * Unexport task_no_data_intr() and make it static. There should be no functionality changes caused by this patch. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 2c28fb75915a..5d675f172037 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -973,7 +973,6 @@ extern ide_startstop_t do_rw_taskfile(ide_drive_t *, ide_task_t *); extern ide_startstop_t set_multmode_intr(ide_drive_t *); extern ide_startstop_t set_geometry_intr(ide_drive_t *); extern ide_startstop_t recal_intr(ide_drive_t *); -extern ide_startstop_t task_no_data_intr(ide_drive_t *); extern ide_startstop_t task_in_intr(ide_drive_t *); extern ide_startstop_t pre_task_out_intr(ide_drive_t *, struct request *); -- cgit v1.2.3 From 57d7366b78b74a9eef873e8212c03d8c2033a764 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:16 +0100 Subject: ide: remove 'handler' field from ide_task_t (take 2) * Add IDE_TFLAG_CUSTOM_HANDLER taskfile flag and use it for internal requests which require custom handlers. Check the flag in do_rw_taskfile() and set handler accordingly. * Cleanup ide_init_{specify,restore,setmult}_cmd() and rename it to ide_tf_set_{specify,restore,setmult}_cmd(). * Make {set_geometry,recal,set_multmode}_intr() static. * Remove no longer needed 'handler' field from ide_task_t. v2: * 'handler' in do_rw_taskfile() must be set to NULL initially. There should be no functionality changes caused by this patch. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 5d675f172037..721c9d8f41a2 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -911,6 +911,7 @@ enum { IDE_TFLAG_WRITE = (1 << 15), IDE_TFLAG_FLAGGED_SET_IN_FLAGS = (1 << 16), IDE_TFLAG_IN_DATA = (1 << 17), + IDE_TFLAG_CUSTOM_HANDLER = (1 << 18), }; struct ide_taskfile { @@ -949,7 +950,6 @@ typedef struct ide_task_s { }; u32 tf_flags; int data_phase; - ide_handler_t *handler; struct request *rq; /* copy of request */ void *special; /* valid_t generally */ } ide_task_t; @@ -970,9 +970,6 @@ void ide_pktcmd_tf_load(ide_drive_t *, u32, u16, u8); */ extern ide_startstop_t do_rw_taskfile(ide_drive_t *, ide_task_t *); -extern ide_startstop_t set_multmode_intr(ide_drive_t *); -extern ide_startstop_t set_geometry_intr(ide_drive_t *); -extern ide_startstop_t recal_intr(ide_drive_t *); extern ide_startstop_t task_in_intr(ide_drive_t *); extern ide_startstop_t pre_task_out_intr(ide_drive_t *, struct request *); -- cgit v1.2.3 From f6e29e35cc0f9facf2eb0b0454f9b09021b5aa6f Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:16 +0100 Subject: ide-disk: use do_rw_taskfile() (take 2) * Add IDE_TFLAG_DMA_PIO_FALLBACK taskfile flag to indicate the need to skip loading taskfile registers in do_rw_taskfile(). * Export do_rw_taskfile(). * Convert __ide_do_rw_disk() to use do_rw_taskfile(). * Unexport ide_tf_load(). * Unexport {pre_task_out,task_in}_intr() and make it static. * Remove incorrect comment about do_rw_taskfile() from . There should be no functionality changes caused by this patch. v2: * Add missing blk_fs_request() check to task_dma_ok() (for VDMA). Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 721c9d8f41a2..c333a7528d94 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -912,6 +912,7 @@ enum { IDE_TFLAG_FLAGGED_SET_IN_FLAGS = (1 << 16), IDE_TFLAG_IN_DATA = (1 << 17), IDE_TFLAG_CUSTOM_HANDLER = (1 << 18), + IDE_TFLAG_DMA_PIO_FALLBACK = (1 << 19), }; struct ide_taskfile { @@ -965,13 +966,7 @@ extern int drive_is_ready(ide_drive_t *); void ide_pktcmd_tf_load(ide_drive_t *, u32, u16, u8); -/* - * taskfile io for disks for now...and builds request from ide_ioctl - */ -extern ide_startstop_t do_rw_taskfile(ide_drive_t *, ide_task_t *); - -extern ide_startstop_t task_in_intr(ide_drive_t *); -extern ide_startstop_t pre_task_out_intr(ide_drive_t *, struct request *); +ide_startstop_t do_rw_taskfile(ide_drive_t *, ide_task_t *); int ide_raw_taskfile(ide_drive_t *, ide_task_t *, u8 *, u16); int ide_no_data_taskfile(ide_drive_t *, ide_task_t *); -- cgit v1.2.3 From c2b57cdc1d2976444d451a2a2e43e11b61ed0638 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:17 +0100 Subject: ide: add ide_tf_read() helper * Factor out code reading taskfile registers from ide_end_drive_cmd() to the new ide_tf_read() helper. * Add IDE_TFLAG_IN_* taskfile flags to indicate the need to load particular IDE taskfile register in ide_tf_read(). * Update ide_end_drive_cmd() to set respective IDE_TFLAG_IN_* taksfile flags. * Add ide_get_lba_addr() for getting LBA sector address from taskfile struct. * Factor out code getting sector address from ide_dump_ata_status() to the new ide_dump_sector() function. * Convert ide_dump_sector() to use ide_tf_read() and ide_get_lba_addr(). * Remove no longer needed ide_read_24(). The only change in functionality caused by this patch is that ide_dump_ata_status() no longer prints "high"/"low" parts of LBA48 sector address (of course LBA48 sector address is still printed). Cc: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index c333a7528d94..67f98c096c03 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -913,6 +913,27 @@ enum { IDE_TFLAG_IN_DATA = (1 << 17), IDE_TFLAG_CUSTOM_HANDLER = (1 << 18), IDE_TFLAG_DMA_PIO_FALLBACK = (1 << 19), + IDE_TFLAG_IN_HOB_FEATURE = (1 << 20), + IDE_TFLAG_IN_HOB_NSECT = (1 << 21), + IDE_TFLAG_IN_HOB_LBAL = (1 << 22), + IDE_TFLAG_IN_HOB_LBAM = (1 << 23), + IDE_TFLAG_IN_HOB_LBAH = (1 << 24), + IDE_TFLAG_IN_HOB_LBA = IDE_TFLAG_IN_HOB_LBAL | + IDE_TFLAG_IN_HOB_LBAM | + IDE_TFLAG_IN_HOB_LBAH, + IDE_TFLAG_IN_HOB = IDE_TFLAG_IN_HOB_FEATURE | + IDE_TFLAG_IN_HOB_NSECT | + IDE_TFLAG_IN_HOB_LBA, + IDE_TFLAG_IN_NSECT = (1 << 25), + IDE_TFLAG_IN_LBAL = (1 << 26), + IDE_TFLAG_IN_LBAM = (1 << 27), + IDE_TFLAG_IN_LBAH = (1 << 28), + IDE_TFLAG_IN_LBA = IDE_TFLAG_IN_LBAL | + IDE_TFLAG_IN_LBAM | + IDE_TFLAG_IN_LBAH, + IDE_TFLAG_IN_TF = IDE_TFLAG_IN_NSECT | + IDE_TFLAG_IN_LBA, + IDE_TFLAG_IN_DEVICE = (1 << 29), }; struct ide_taskfile { @@ -956,8 +977,7 @@ typedef struct ide_task_s { } ide_task_t; void ide_tf_load(ide_drive_t *, ide_task_t *); - -extern u32 ide_read_24(ide_drive_t *); +void ide_tf_read(ide_drive_t *, ide_task_t *); extern void SELECT_DRIVE(ide_drive_t *); extern void SELECT_MASK(ide_drive_t *, int); -- cgit v1.2.3 From a501633c7d44087e806597d3a213d735346edd51 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:17 +0100 Subject: ide-disk: use ide_get_lba_addr() * Export ide_get_lba_addr(). * Convert idedisk_{read_native,set}_max_address() to use ide_get_lba_addr(). * Remove incorrect comment from idedisk_read_native_max_address() (noticed by Sergei). There should be no functionality changes caused by this patch. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 67f98c096c03..ecaa96e613dc 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1238,6 +1238,7 @@ static inline int ide_dev_is_sata(struct hd_driveid *id) return 0; } +u64 ide_get_lba_addr(struct ide_taskfile *, int); u8 ide_dump_status(ide_drive_t *, const char *, u8); typedef struct ide_pio_timings_s { -- cgit v1.2.3 From 3071a9d00b8684899d93f368e670c4de0293df29 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:17 +0100 Subject: ide: make 'extra' field in struct ide_port_info u8 The maximum value used currently for 'extra' field in struct ide_port_info is 240. Make 'extra' u8 so it packs nicely together with enablebits[] and 'chipset' fields (ide_pci_enablebit_t is 3 bytes and hwif_chipset_t is 1 byte). Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index ecaa96e613dc..6f5b6b5e9c1d 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1111,7 +1111,7 @@ struct ide_port_info { void (*fixup)(ide_hwif_t *); ide_pci_enablebit_t enablebits[2]; hwif_chipset_t chipset; - unsigned int extra; + u8 extra; u32 host_flags; u8 pio_mask; u8 swdma_mask; -- cgit v1.2.3 From 4db90a145292327b95b03f6dcd3352327235cc36 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Fri, 25 Jan 2008 22:17:18 +0100 Subject: ide: add IDE_HFLAG_ABUSE_SET_DMA_MODE host flag * Add IDE_HFLAG_ABUSE_SET_DMA_MODE host flag and use it to decide what to do with transfer modes < XFER_PIO_0 in ide_set_xfer_rate(). * Set IDE_HFLAG_ABUSE_SET_DMA_MODE in host drivers that need it (aec62xx, amd74xx, cs5520, cs5535, hpt34x, hpt366, pdc202xx_old, serverworks, tc86c001 and via82cxxx) and cleanup ->set_dma_mode methods in host drivers that don't (IDE core code guarantees that ->set_dma_mode will be called only for modes which are present in SWDMA/MWDMA/UDMA masks). While at it: * Add IDE_HFLAGS_HPT34X/HPT3XX/PDC202XX/SVWKS define in hpt34x/hpt366/pdc202xx_old/serverworks host driver. There should be no functionality changes caused by this patch. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 6f5b6b5e9c1d..1e4409937ec3 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1094,6 +1094,7 @@ enum { IDE_HFLAG_IO_32BIT = (1 << 24), /* unmask IRQs */ IDE_HFLAG_UNMASK_IRQS = (1 << 25), + IDE_HFLAG_ABUSE_SET_DMA_MODE = (1 << 26), }; #ifdef CONFIG_BLK_DEV_OFFBOARD -- cgit v1.2.3 From d69a3ad6a0e47b2aa9b2b2ddfd385752132a4d34 Mon Sep 17 00:00:00 2001 From: Joel Becker Date: Fri, 5 Oct 2007 14:31:44 -0700 Subject: dlm: Split lock mode and flag constants into a sharable header. This allows others to use the DLM constants without being tied to the function API of fs/dlm. Signed-off-by: Joel Becker Signed-off-by: Steven Whitehouse Signed-off-by: David Teigland Signed-off-by: Mark Fasheh --- include/linux/Kbuild | 1 + include/linux/dlm.h | 140 +------------------------------------ include/linux/dlmconstants.h | 159 +++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 162 insertions(+), 138 deletions(-) create mode 100644 include/linux/dlmconstants.h (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index f30fa92a44a1..bd694f779346 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -49,6 +49,7 @@ header-y += comstats.h header-y += const.h header-y += cgroupstats.h header-y += cycx_cfm.h +header-y += dlmconstants.h header-y += dlm_device.h header-y += dlm_netlink.h header-y += dm-ioctl.h diff --git a/include/linux/dlm.h b/include/linux/dlm.h index be9d278761e0..c743fbc769db 100644 --- a/include/linux/dlm.h +++ b/include/linux/dlm.h @@ -19,148 +19,12 @@ * routines and structures to use DLM lockspaces */ -/* - * Lock Modes - */ +/* Lock levels and flags are here */ +#include -#define DLM_LOCK_IV -1 /* invalid */ -#define DLM_LOCK_NL 0 /* null */ -#define DLM_LOCK_CR 1 /* concurrent read */ -#define DLM_LOCK_CW 2 /* concurrent write */ -#define DLM_LOCK_PR 3 /* protected read */ -#define DLM_LOCK_PW 4 /* protected write */ -#define DLM_LOCK_EX 5 /* exclusive */ - -/* - * Maximum size in bytes of a dlm_lock name - */ #define DLM_RESNAME_MAXLEN 64 -/* - * Flags to dlm_lock - * - * DLM_LKF_NOQUEUE - * - * Do not queue the lock request on the wait queue if it cannot be granted - * immediately. If the lock cannot be granted because of this flag, DLM will - * either return -EAGAIN from the dlm_lock call or will return 0 from - * dlm_lock and -EAGAIN in the lock status block when the AST is executed. - * - * DLM_LKF_CANCEL - * - * Used to cancel a pending lock request or conversion. A converting lock is - * returned to its previously granted mode. - * - * DLM_LKF_CONVERT - * - * Indicates a lock conversion request. For conversions the name and namelen - * are ignored and the lock ID in the LKSB is used to identify the lock. - * - * DLM_LKF_VALBLK - * - * Requests DLM to return the current contents of the lock value block in the - * lock status block. When this flag is set in a lock conversion from PW or EX - * modes, DLM assigns the value specified in the lock status block to the lock - * value block of the lock resource. The LVB is a DLM_LVB_LEN size array - * containing application-specific information. - * - * DLM_LKF_QUECVT - * - * Force a conversion request to be queued, even if it is compatible with - * the granted modes of other locks on the same resource. - * - * DLM_LKF_IVVALBLK - * - * Invalidate the lock value block. - * - * DLM_LKF_CONVDEADLK - * - * Allows the dlm to resolve conversion deadlocks internally by demoting the - * granted mode of a converting lock to NL. The DLM_SBF_DEMOTED flag is - * returned for a conversion that's been effected by this. - * - * DLM_LKF_PERSISTENT - * - * Only relevant to locks originating in userspace. A persistent lock will not - * be removed if the process holding the lock exits. - * - * DLM_LKF_NODLCKWT - * - * Do not cancel the lock if it gets into conversion deadlock. - * Exclude this lock from being monitored due to DLM_LSFL_TIMEWARN. - * - * DLM_LKF_NODLCKBLK - * - * net yet implemented - * - * DLM_LKF_EXPEDITE - * - * Used only with new requests for NL mode locks. Tells the lock manager - * to grant the lock, ignoring other locks in convert and wait queues. - * - * DLM_LKF_NOQUEUEBAST - * - * Send blocking AST's before returning -EAGAIN to the caller. It is only - * used along with the NOQUEUE flag. Blocking AST's are not sent for failed - * NOQUEUE requests otherwise. - * - * DLM_LKF_HEADQUE - * - * Add a lock to the head of the convert or wait queue rather than the tail. - * - * DLM_LKF_NOORDER - * - * Disregard the standard grant order rules and grant a lock as soon as it - * is compatible with other granted locks. - * - * DLM_LKF_ORPHAN - * - * not yet implemented - * - * DLM_LKF_ALTPR - * - * If the requested mode cannot be granted immediately, try to grant the lock - * in PR mode instead. If this alternate mode is granted instead of the - * requested mode, DLM_SBF_ALTMODE is returned in the lksb. - * - * DLM_LKF_ALTCW - * - * The same as ALTPR, but the alternate mode is CW. - * - * DLM_LKF_FORCEUNLOCK - * - * Unlock the lock even if it is converting or waiting or has sublocks. - * Only really for use by the userland device.c code. - * - */ - -#define DLM_LKF_NOQUEUE 0x00000001 -#define DLM_LKF_CANCEL 0x00000002 -#define DLM_LKF_CONVERT 0x00000004 -#define DLM_LKF_VALBLK 0x00000008 -#define DLM_LKF_QUECVT 0x00000010 -#define DLM_LKF_IVVALBLK 0x00000020 -#define DLM_LKF_CONVDEADLK 0x00000040 -#define DLM_LKF_PERSISTENT 0x00000080 -#define DLM_LKF_NODLCKWT 0x00000100 -#define DLM_LKF_NODLCKBLK 0x00000200 -#define DLM_LKF_EXPEDITE 0x00000400 -#define DLM_LKF_NOQUEUEBAST 0x00000800 -#define DLM_LKF_HEADQUE 0x00001000 -#define DLM_LKF_NOORDER 0x00002000 -#define DLM_LKF_ORPHAN 0x00004000 -#define DLM_LKF_ALTPR 0x00008000 -#define DLM_LKF_ALTCW 0x00010000 -#define DLM_LKF_FORCEUNLOCK 0x00020000 -#define DLM_LKF_TIMEOUT 0x00040000 - -/* - * Some return codes that are not in errno.h - */ - -#define DLM_ECANCEL 0x10001 -#define DLM_EUNLOCK 0x10002 typedef void dlm_lockspace_t; diff --git a/include/linux/dlmconstants.h b/include/linux/dlmconstants.h new file mode 100644 index 000000000000..fddb3d3ff321 --- /dev/null +++ b/include/linux/dlmconstants.h @@ -0,0 +1,159 @@ +/****************************************************************************** +******************************************************************************* +** +** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. +** Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. +** +** This copyrighted material is made available to anyone wishing to use, +** modify, copy, or redistribute it subject to the terms and conditions +** of the GNU General Public License v.2. +** +******************************************************************************* +******************************************************************************/ + +#ifndef __DLMCONSTANTS_DOT_H__ +#define __DLMCONSTANTS_DOT_H__ + +/* + * Constants used by DLM interface. + */ + +/* + * Lock Modes + */ + +#define DLM_LOCK_IV (-1) /* invalid */ +#define DLM_LOCK_NL 0 /* null */ +#define DLM_LOCK_CR 1 /* concurrent read */ +#define DLM_LOCK_CW 2 /* concurrent write */ +#define DLM_LOCK_PR 3 /* protected read */ +#define DLM_LOCK_PW 4 /* protected write */ +#define DLM_LOCK_EX 5 /* exclusive */ + + +/* + * Flags to dlm_lock + * + * DLM_LKF_NOQUEUE + * + * Do not queue the lock request on the wait queue if it cannot be granted + * immediately. If the lock cannot be granted because of this flag, DLM will + * either return -EAGAIN from the dlm_lock call or will return 0 from + * dlm_lock and -EAGAIN in the lock status block when the AST is executed. + * + * DLM_LKF_CANCEL + * + * Used to cancel a pending lock request or conversion. A converting lock is + * returned to its previously granted mode. + * + * DLM_LKF_CONVERT + * + * Indicates a lock conversion request. For conversions the name and namelen + * are ignored and the lock ID in the LKSB is used to identify the lock. + * + * DLM_LKF_VALBLK + * + * Requests DLM to return the current contents of the lock value block in the + * lock status block. When this flag is set in a lock conversion from PW or EX + * modes, DLM assigns the value specified in the lock status block to the lock + * value block of the lock resource. The LVB is a DLM_LVB_LEN size array + * containing application-specific information. + * + * DLM_LKF_QUECVT + * + * Force a conversion request to be queued, even if it is compatible with + * the granted modes of other locks on the same resource. + * + * DLM_LKF_IVVALBLK + * + * Invalidate the lock value block. + * + * DLM_LKF_CONVDEADLK + * + * Allows the dlm to resolve conversion deadlocks internally by demoting the + * granted mode of a converting lock to NL. The DLM_SBF_DEMOTED flag is + * returned for a conversion that's been effected by this. + * + * DLM_LKF_PERSISTENT + * + * Only relevant to locks originating in userspace. A persistent lock will not + * be removed if the process holding the lock exits. + * + * DLM_LKF_NODLCKWT + * + * Do not cancel the lock if it gets into conversion deadlock. + * Exclude this lock from being monitored due to DLM_LSFL_TIMEWARN. + * + * DLM_LKF_NODLCKBLK + * + * net yet implemented + * + * DLM_LKF_EXPEDITE + * + * Used only with new requests for NL mode locks. Tells the lock manager + * to grant the lock, ignoring other locks in convert and wait queues. + * + * DLM_LKF_NOQUEUEBAST + * + * Send blocking AST's before returning -EAGAIN to the caller. It is only + * used along with the NOQUEUE flag. Blocking AST's are not sent for failed + * NOQUEUE requests otherwise. + * + * DLM_LKF_HEADQUE + * + * Add a lock to the head of the convert or wait queue rather than the tail. + * + * DLM_LKF_NOORDER + * + * Disregard the standard grant order rules and grant a lock as soon as it + * is compatible with other granted locks. + * + * DLM_LKF_ORPHAN + * + * not yet implemented + * + * DLM_LKF_ALTPR + * + * If the requested mode cannot be granted immediately, try to grant the lock + * in PR mode instead. If this alternate mode is granted instead of the + * requested mode, DLM_SBF_ALTMODE is returned in the lksb. + * + * DLM_LKF_ALTCW + * + * The same as ALTPR, but the alternate mode is CW. + * + * DLM_LKF_FORCEUNLOCK + * + * Unlock the lock even if it is converting or waiting or has sublocks. + * Only really for use by the userland device.c code. + * + */ + +#define DLM_LKF_NOQUEUE 0x00000001 +#define DLM_LKF_CANCEL 0x00000002 +#define DLM_LKF_CONVERT 0x00000004 +#define DLM_LKF_VALBLK 0x00000008 +#define DLM_LKF_QUECVT 0x00000010 +#define DLM_LKF_IVVALBLK 0x00000020 +#define DLM_LKF_CONVDEADLK 0x00000040 +#define DLM_LKF_PERSISTENT 0x00000080 +#define DLM_LKF_NODLCKWT 0x00000100 +#define DLM_LKF_NODLCKBLK 0x00000200 +#define DLM_LKF_EXPEDITE 0x00000400 +#define DLM_LKF_NOQUEUEBAST 0x00000800 +#define DLM_LKF_HEADQUE 0x00001000 +#define DLM_LKF_NOORDER 0x00002000 +#define DLM_LKF_ORPHAN 0x00004000 +#define DLM_LKF_ALTPR 0x00008000 +#define DLM_LKF_ALTCW 0x00010000 +#define DLM_LKF_FORCEUNLOCK 0x00020000 +#define DLM_LKF_TIMEOUT 0x00040000 + +/* + * Some return codes that are not in errno.h + */ + +#define DLM_ECANCEL 0x10001 +#define DLM_EUNLOCK 0x10002 + +#endif /* __DLMCONSTANTS_DOT_H__ */ -- cgit v1.2.3 From a0832798c05241f15e793805b6024919c07b8292 Mon Sep 17 00:00:00 2001 From: Tzachi Perelstein Date: Mon, 12 Nov 2007 19:38:51 +0200 Subject: [I2C] Split mv643xx I2C platform support The motivation for this change is to allow other chips, like the Marvell Orion ARM SoC family, to use the existing i2c-mv64xxx driver. Signed-off-by: Tzachi Perelstein Acked-by: Nicolas Pitre Acked-by: Dale Farnsworth Acked-by: Mark A. Greer Acked-by: Jean Delvare --- include/linux/mv643xx.h | 10 +--------- include/linux/mv643xx_i2c.h | 23 +++++++++++++++++++++++ 2 files changed, 24 insertions(+), 9 deletions(-) create mode 100644 include/linux/mv643xx_i2c.h (limited to 'include/linux') diff --git a/include/linux/mv643xx.h b/include/linux/mv643xx.h index d2ae6185f03b..69327b7b4ce4 100644 --- a/include/linux/mv643xx.h +++ b/include/linux/mv643xx.h @@ -15,6 +15,7 @@ #include #include +#include /****************************************/ /* Processor Address Space */ @@ -863,7 +864,6 @@ /* I2C Registers */ /****************************************/ -#define MV64XXX_I2C_CTLR_NAME "mv64xxx_i2c" #define MV64XXX_I2C_OFFSET 0xc000 #define MV64XXX_I2C_REG_BLOCK_SIZE 0x0020 @@ -968,14 +968,6 @@ struct mpsc_pdata { u32 brg_clk_freq; }; -/* i2c Platform Device, Driver Data */ -struct mv64xxx_i2c_pdata { - u32 freq_m; - u32 freq_n; - u32 timeout; /* In milliseconds */ - u32 retries; -}; - /* Watchdog Platform Device, Driver Data */ #define MV64x60_WDT_NAME "mv64x60_wdt" diff --git a/include/linux/mv643xx_i2c.h b/include/linux/mv643xx_i2c.h new file mode 100644 index 000000000000..adb629b15477 --- /dev/null +++ b/include/linux/mv643xx_i2c.h @@ -0,0 +1,23 @@ +/* + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#ifndef _MV64XXX_I2C_H_ +#define _MV64XXX_I2C_H_ + +#include + +#define MV64XXX_I2C_CTLR_NAME "mv64xxx_i2c" + +/* i2c Platform Device, Driver Data */ +struct mv64xxx_i2c_pdata { + u32 freq_m; + u32 freq_n; + u32 timeout; /* In milliseconds */ + u32 retries; +}; + +#endif /*_MV64XXX_I2C_H_*/ -- cgit v1.2.3 From 2f0a8df40ff008822e5570b3323c56622cd92c95 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 22 Nov 2007 16:58:08 +0100 Subject: [I2C] i2c-mv64xxx: Don't set i2c_adapter.retries I2C adapter drivers are supposed to handle retries on nack by themselves if they do, so there's no point in setting .retries if they don't. As this retry mechanism is going away (at least in its current form), clean this up now so that we don't get build failures later. Signed-off-by: Jean Delvare Acked-by: Mark A. Greer --- include/linux/mv643xx_i2c.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mv643xx_i2c.h b/include/linux/mv643xx_i2c.h index adb629b15477..5db5152e9de5 100644 --- a/include/linux/mv643xx_i2c.h +++ b/include/linux/mv643xx_i2c.h @@ -17,7 +17,6 @@ struct mv64xxx_i2c_pdata { u32 freq_m; u32 freq_n; u32 timeout; /* In milliseconds */ - u32 retries; }; #endif /*_MV64XXX_I2C_H_*/ -- cgit v1.2.3 From 8704de8f296fcf6a4b2ff6bfd9a63974ad909b3e Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Sat, 26 Jan 2008 20:13:00 +0100 Subject: cy82c693: add ->set_dma_mode method * Fix SWDMA/MWDMA masks in cy82c693_chipset. * Add IDE_HFLAG_CY82C693 host flag and use it in ide_tune_dma() to check whether the DMA should be enabled even if ide_max_dma_mode() fails. * Convert cy82c693_dma_enable() to become cy82c693_set_dma_mode() and remove no longer needed cy82c693_ide_dma_on(). Then set IDE_HFLAG_CY82C693 instead of IDE_HFLAG_TRUST_BIOS_FOR_DMA in cy82c693_chipset. * Bump driver version. As a result of this patch cy82c693 driver will configure and use DMA on all SWDMA0-2 and MWDMA0-2 capable ATA devices instead of relying on BIOS. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 1e4409937ec3..bf106d569cfc 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1095,6 +1095,8 @@ enum { /* unmask IRQs */ IDE_HFLAG_UNMASK_IRQS = (1 << 25), IDE_HFLAG_ABUSE_SET_DMA_MODE = (1 << 26), + /* host is CY82C693 */ + IDE_HFLAG_CY82C693 = (1 << 27), }; #ifdef CONFIG_BLK_DEV_OFFBOARD -- cgit v1.2.3 From 4a546e046d562bcd389149591fa5a534c8f832ca Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Sat, 26 Jan 2008 20:13:01 +0100 Subject: ide: remove ->ide_dma_on and ->dma_off_quietly methods from ide_hwif_t * Make ide_dma_off_quietly() and __ide_dma_on() always available. * Drop "__" prefix from __ide_dma_on(). * Check for presence of ->dma_host_on instead of ->ide_dma_on. * Convert all users of ->ide_dma_on and ->dma_off_quietly methods to use ide_dma_on() and ide_dma_off_quietly() instead. * Remove no longer needed ->ide_dma_on and ->dma_off_quietly methods from ide_hwif_t. * Make ide_dma_on() void. There should be no functionality changes caused by this patch. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index bf106d569cfc..140864d63aed 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -546,8 +546,6 @@ typedef struct hwif_s { void (*dma_exec_cmd)(ide_drive_t *, u8); void (*dma_start)(ide_drive_t *); int (*ide_dma_end)(ide_drive_t *drive); - int (*ide_dma_on)(ide_drive_t *drive); - void (*dma_off_quietly)(ide_drive_t *drive); int (*ide_dma_test_irq)(ide_drive_t *drive); void (*ide_dma_clear_irq)(ide_drive_t *drive); void (*dma_host_on)(ide_drive_t *drive); @@ -1149,7 +1147,9 @@ static inline u8 ide_max_dma_mode(ide_drive_t *drive) return ide_find_dma_mode(drive, XFER_UDMA_6); } +void ide_dma_off_quietly(ide_drive_t *); void ide_dma_off(ide_drive_t *); +void ide_dma_on(ide_drive_t *); int ide_set_dma(ide_drive_t *); ide_startstop_t ide_dma_intr(ide_drive_t *); @@ -1161,9 +1161,7 @@ extern int ide_release_dma(ide_hwif_t *); extern void ide_setup_dma(ide_hwif_t *, unsigned long, unsigned int); void ide_dma_host_off(ide_drive_t *); -void ide_dma_off_quietly(ide_drive_t *); void ide_dma_host_on(ide_drive_t *); -extern int __ide_dma_on(ide_drive_t *); extern int ide_dma_setup(ide_drive_t *); extern void ide_dma_start(ide_drive_t *); extern int __ide_dma_end(ide_drive_t *); @@ -1175,7 +1173,9 @@ extern void ide_dma_timeout(ide_drive_t *); static inline int ide_id_dma_bug(ide_drive_t *drive) { return 0; } static inline u8 ide_find_dma_mode(ide_drive_t *drive, u8 speed) { return 0; } static inline u8 ide_max_dma_mode(ide_drive_t *drive) { return 0; } +static inline void ide_dma_off_quietly(ide_drive_t *drive) { ; } static inline void ide_dma_off(ide_drive_t *drive) { ; } +static inline void ide_dma_on(ide_drive_t *drive) { ; } static inline void ide_dma_verbose(ide_drive_t *drive) { ; } static inline int ide_set_dma(ide_drive_t *drive) { return 1; } #endif /* CONFIG_BLK_DEV_IDEDMA */ -- cgit v1.2.3 From 15ce926ada545cb078711bd9a18c083c93fa01d7 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Sat, 26 Jan 2008 20:13:03 +0100 Subject: ide: merge ->dma_host_{on,off} methods into ->dma_host_set method Merge ->dma_host_{on,off} methods into ->dma_host_set method which takes 'int on' argument. There should be no functionality changes caused by this patch. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 140864d63aed..ffb76d0d0814 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -542,14 +542,13 @@ typedef struct hwif_s { void (*atapi_input_bytes)(ide_drive_t *, void *, u32); void (*atapi_output_bytes)(ide_drive_t *, void *, u32); + void (*dma_host_set)(ide_drive_t *, int); int (*dma_setup)(ide_drive_t *); void (*dma_exec_cmd)(ide_drive_t *, u8); void (*dma_start)(ide_drive_t *); int (*ide_dma_end)(ide_drive_t *drive); int (*ide_dma_test_irq)(ide_drive_t *drive); void (*ide_dma_clear_irq)(ide_drive_t *drive); - void (*dma_host_on)(ide_drive_t *drive); - void (*dma_host_off)(ide_drive_t *drive); void (*dma_lost_irq)(ide_drive_t *drive); void (*dma_timeout)(ide_drive_t *drive); @@ -1160,8 +1159,7 @@ extern void ide_destroy_dmatable(ide_drive_t *); extern int ide_release_dma(ide_hwif_t *); extern void ide_setup_dma(ide_hwif_t *, unsigned long, unsigned int); -void ide_dma_host_off(ide_drive_t *); -void ide_dma_host_on(ide_drive_t *); +void ide_dma_host_set(ide_drive_t *, int); extern int ide_dma_setup(ide_drive_t *); extern void ide_dma_start(ide_drive_t *); extern int __ide_dma_end(ide_drive_t *); -- cgit v1.2.3 From f01393e48c44e30f7c9a36c8b98a07b0232580fe Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Sat, 26 Jan 2008 20:13:03 +0100 Subject: ide: merge ->fixup and ->quirkproc methods * Assign drive->quirk_list in ->quirkproc implementations: - hpt366.c::hpt3xx_quirkproc() - pdc202xx_new.c::pdcnew_quirkproc() - pdc202xx_old.c::pdc202xx_quirkproc() * Make ->quirkproc void. * Move calling ->quirkproc from do_identify() to probe_hwif(). * Convert it821x_fixups() to it821x_quirkproc() in it821x.c. * Convert siimage_fixup() to sil_quirkproc() in siimage.c, also remove no longer needed drive->present check from is_dev_seagate_sata(). * Convert ide_undecoded_slave() to accept 'drive' instead of 'hwif' as an argument. Then convert ide_register_hw() to accept 'quirkproc' argument instead of 'fixup' one. * Remove no longer needed ->fixup method. Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index ffb76d0d0814..dd50a5c5ec10 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -199,7 +199,8 @@ typedef struct hw_regs_s { struct hwif_s * ide_find_port(unsigned long); -int ide_register_hw(hw_regs_t *, void (*)(struct hwif_s *), int, +struct ide_drive_s; +int ide_register_hw(hw_regs_t *, void (*)(struct ide_drive_s *), int, struct hwif_s **); void ide_setup_ports( hw_regs_t *hw, @@ -527,15 +528,13 @@ typedef struct hwif_s { /* special host masking for drive selection */ void (*maskproc)(ide_drive_t *, int); /* check host's drive quirk list */ - int (*quirkproc)(ide_drive_t *); + void (*quirkproc)(ide_drive_t *); /* driver soft-power interface */ int (*busproc)(ide_drive_t *, int); #endif u8 (*mdma_filter)(ide_drive_t *); u8 (*udma_filter)(ide_drive_t *); - void (*fixup)(struct hwif_s *); - void (*ata_input_data)(ide_drive_t *, void *, u32); void (*ata_output_data)(ide_drive_t *, void *, u32); @@ -1108,7 +1107,6 @@ struct ide_port_info { void (*init_iops)(ide_hwif_t *); void (*init_hwif)(ide_hwif_t *); void (*init_dma)(ide_hwif_t *, unsigned long); - void (*fixup)(ide_hwif_t *); ide_pci_enablebit_t enablebits[2]; hwif_chipset_t chipset; u8 extra; @@ -1203,7 +1201,7 @@ extern void ide_unregister (unsigned int index); void ide_register_region(struct gendisk *); void ide_unregister_region(struct gendisk *); -void ide_undecoded_slave(ide_hwif_t *); +void ide_undecoded_slave(ide_drive_t *); int ide_device_add(u8 idx[4]); -- cgit v1.2.3 From 151575e4644f917d3a9f83c777ac3543284954f8 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Sat, 26 Jan 2008 20:13:05 +0100 Subject: ide: remove ideprobe_init() * Rename ide_device_add() to ide_device_add_all() and make it accept 'u8 idx[MAX_HWIFS]' instead of 'u8 idx[4]' as an argument. * Add ide_device_add() wrapper for ide_device_add_all(). * Convert ide_generic_init() to use ide_device_add_all(). * Remove no longer needed ideprobe_init(). There should be no functionality changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index dd50a5c5ec10..d7c0f9a8bd9e 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1011,8 +1011,6 @@ extern void do_ide_request(struct request_queue *); void ide_init_disk(struct gendisk *, ide_drive_t *); -extern int ideprobe_init(void); - #ifdef CONFIG_IDEPCI_PCIBUS_ORDER extern void ide_scan_pcibus(int scan_direction) __init; extern int __ide_pci_register_driver(struct pci_driver *driver, struct module *owner, const char *mod_name); @@ -1203,6 +1201,7 @@ void ide_unregister_region(struct gendisk *); void ide_undecoded_slave(ide_drive_t *); +int ide_device_add_all(u8 idx[MAX_HWIFS]); int ide_device_add(u8 idx[4]); static inline void *ide_get_hwifdata (ide_hwif_t * hwif) -- cgit v1.2.3 From b0d5bc27ce995adaafbc114b92fa76815025c94e Mon Sep 17 00:00:00 2001 From: Olof Johansson Date: Sat, 26 Jan 2008 20:13:05 +0100 Subject: ide: Fix build break caused by "ide: remove ideprobe_init()" Fix build break of powerpc holly_defconfig: In file included from arch/powerpc/platforms/embedded6xx/holly.c:24: include/linux/ide.h:1206: error: 'CONFIG_IDE_MAX_HWIFS' undeclared here (not in a function) There's no need to have a sized array in the prototype, might as well turn it into a pointer. It could probably be argued that large parts of the include file can be covered under #ifdef CONFIG_IDE, but that's a larger undertaking. Signed-off-by: Olof Johansson Cc: Andrew Morton Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index d7c0f9a8bd9e..ce9b16f38c08 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1201,7 +1201,7 @@ void ide_unregister_region(struct gendisk *); void ide_undecoded_slave(ide_drive_t *); -int ide_device_add_all(u8 idx[MAX_HWIFS]); +int ide_device_add_all(u8 *idx); int ide_device_add(u8 idx[4]); static inline void *ide_get_hwifdata (ide_hwif_t * hwif) -- cgit v1.2.3 From 57c802e84f9c759c3d1794a9dbe81bc10444df62 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Sat, 26 Jan 2008 20:13:05 +0100 Subject: ide: add ide_init_port_hw() helper * Add ide_init_port_hw() helper. * rapide.c: convert rapide_locate_hwif() to rapide_setup_ports() and use ide_init_port_hw(). * ide_platform.c: convert plat_ide_locate_hwif() to plat_ide_setup_ports() and use ide_init_port_hw(). * sgiioc4.c: use ide_init_port_hw(). * pmac.c: add 'hw_regs_t *hw' argument to pmac_ide_setup_device(), setup 'hw' in pmac_ide_{macio,pci}_attach() and use ide_init_port_hw() in pmac_ide_setup_device(). This patch is a preparation for the future changes in the IDE probing code. There should be no functionality changes caused by this patch. Cc: Russell King Cc: Anton Vorontsov Cc: Jeremy Higdon Cc: Benjamin Herrenschmidt Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index ce9b16f38c08..de94a526ef9e 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -198,6 +198,7 @@ typedef struct hw_regs_s { } hw_regs_t; struct hwif_s * ide_find_port(unsigned long); +void ide_init_port_hw(struct hwif_s *, hw_regs_t *); struct ide_drive_s; int ide_register_hw(hw_regs_t *, void (*)(struct ide_drive_s *), int, -- cgit v1.2.3 From cbb010c180294a5242a7681555c28737d9dd26ab Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Sat, 26 Jan 2008 20:13:06 +0100 Subject: ide: drop 'initializing' argument from ide_register_hw() * Rename init_hwif_data() to ide_init_port_data() and export it. * For all users of ide_register_hw() with 'initializing' argument set hwif->present and hwif->hold are always zero so convert these host drivers to use ide_find_port()+ide_init_port_data()+ide_init_port_hw() instead (also no need for init_hwif_default() call since the setup done by it gets over-ridden by ide_init_port_hw() call). * Drop 'initializing' argument from ide_register_hw(). Cc: Geert Uytterhoeven Cc: Roman Zippel Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index de94a526ef9e..9c037a0f2af2 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -198,10 +198,11 @@ typedef struct hw_regs_s { } hw_regs_t; struct hwif_s * ide_find_port(unsigned long); +void ide_init_port_data(struct hwif_s *, unsigned int); void ide_init_port_hw(struct hwif_s *, hw_regs_t *); struct ide_drive_s; -int ide_register_hw(hw_regs_t *, void (*)(struct ide_drive_s *), int, +int ide_register_hw(hw_regs_t *, void (*)(struct ide_drive_s *), struct hwif_s **); void ide_setup_ports( hw_regs_t *hw, -- cgit v1.2.3 From ade2daf9c6e57845fe83a24e0a9fa1c03c6e91b1 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Sat, 26 Jan 2008 20:13:07 +0100 Subject: ide: make remaining built-in only IDE host drivers modular (take 2) * Make remaining built-in only IDE host drivers modular, add ide-scan-pci.c file for probing PCI host drivers registered with IDE core (special case for built-in IDE and CONFIG_IDEPCI_PCIBUS_ORDER=y) and then take care of the ordering in which all IDE host drivers are probed when IDE is built-in during link time. * Move probing of gayle, falconide, macide, q40ide and buddha (m68k arch specific) host drivers, before PCI ones (no PCI on m68k), ide-cris (cris arch specific), cmd640 (x86 arch specific) and pmac (ppc arch specific). * Move probing of ide-cris (cris arch specific) host driver before cmd640 (x86 arch specific). * Move probing of mpc8xx (ppc specific) host driver before ide-pnp (depends on ISA and none of ppc platform that use mpc8xx supports ISA) and ide-h8300 (h8300 arch specific). * Add "probe_vlb" kernel parameter to cmd640 host driver and update Documentation/ide.txt accordingly. * Make IDE_ARM config option visible so it can also be disabled if needed. * Remove bogus comment from ide.c while at it. v2: * Fix two issues spotted by Sergei: - replace ENOMEM error value by ENOENT in ide-h8300 host driver - fix MODULE_PARM_DESC() in cmd640 host driver Cc: Sergei Shtylyov Cc: Mikael Starvik Cc: Geert Uytterhoeven Cc: Roman Zippel Cc: Benjamin Herrenschmidt Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 9c037a0f2af2..735737500f8f 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1014,7 +1014,8 @@ extern void do_ide_request(struct request_queue *); void ide_init_disk(struct gendisk *, ide_drive_t *); #ifdef CONFIG_IDEPCI_PCIBUS_ORDER -extern void ide_scan_pcibus(int scan_direction) __init; +extern int ide_scan_direction; +int __init ide_scan_pcibus(void); extern int __ide_pci_register_driver(struct pci_driver *driver, struct module *owner, const char *mod_name); #define ide_pci_register_driver(d) __ide_pci_register_driver(d, THIS_MODULE, KBUILD_MODNAME) #else -- cgit v1.2.3 From 81ca691981da718727281238b435dcf1528d2fda Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Sat, 26 Jan 2008 20:13:08 +0100 Subject: ide: add ide_set_irq() inline helper There should be no functionality changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 735737500f8f..74f1ef9c6d94 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1302,4 +1302,9 @@ static inline ide_drive_t *ide_get_paired_drive(ide_drive_t *drive) return &hwif->drives[(drive->dn ^ 1) & 1]; } +static inline void ide_set_irq(ide_drive_t *drive, int on) +{ + drive->hwif->OUTB(drive->ctl | (on ? 0 : 2), IDE_CONTROL_REG); +} + #endif /* _IDE_H */ -- cgit v1.2.3 From 9e47be0c97f7357b80e91dc0632e9cce2eb025e0 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Sat, 26 Jan 2008 20:13:09 +0100 Subject: ide: remove broken disk byte-swapping support Remove broken disk byte-swapping support: - it can cause a data corruption on SMP (or if using PREEMPT on UP) - all data coming from disk are byte-swapped by taskfile_*_data() which results in incorrect identify data being reported by /proc/ide/ and IOCTLs - "hdx=bswap/byteswap" kernel parameter has been broken on m68k host drivers (including Atari/Q40 ones) since 2.5.x days (because of 'hwif' zero-ing) - byte-swapping is limited to PIO transfers (for working with TiVo disks on x86 machines using user-space solutions or dm-byteswap should result in much better performance because DMA can be used) For previous discussions please see: http://www.ussg.iu.edu/hypermail/linux/kernel/0201.0/0768.html http://lkml.org/lkml/2004/2/28/111 [ I have dm-byteswap device mapper target if somebody is interested (patch is for 2.6.4 though but I'll dust it off if needed). ] Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 74f1ef9c6d94..f94cf036bd95 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -394,7 +394,6 @@ typedef struct ide_drive_s { u8 state; /* retry state */ u8 waiting_for_dma; /* dma currently in progress */ u8 unmask; /* okay to unmask other irqs */ - u8 bswap; /* byte swap data */ u8 noflush; /* don't attempt flushes */ u8 dsc_overlap; /* DSC overlap */ u8 nice1; /* give potential excess bandwidth */ -- cgit v1.2.3 From 35cf2b94d0ecb7034cfa05dd725721538bbb83fc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 26 Jan 2008 20:13:10 +0100 Subject: ide: fix ->io_32bit race in ide_taskfile_ioctl() In ide_taskfile_ioctl(), there was a race condition involving drive->io_32bit. It was cleared and restored during ioctl requests but there was no synchronization with other requests. So, other requests could execute with the altered ->io_32bit setting or updated drive->io_32bit could be overwritten by ide_taskfile_ioctl(). This patch adds IDE_TFLAG_IO_16BIT flag to indicate to ide_pio_datablock() that 16-bit I/O is needed regardless of drive->io_32bit settting. Bart: - ported it over recent IDE changes Signed-off-by: Tejun Heo Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index f94cf036bd95..c1a8b8bb93ab 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -931,6 +931,8 @@ enum { IDE_TFLAG_IN_TF = IDE_TFLAG_IN_NSECT | IDE_TFLAG_IN_LBA, IDE_TFLAG_IN_DEVICE = (1 << 29), + /* force 16-bit I/O operations */ + IDE_TFLAG_IO_16BIT = (1 << 30), }; struct ide_taskfile { -- cgit v1.2.3 From 657cc1a8f6cd6a9e2974cba3af9fccd8c25e06ad Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Sat, 26 Jan 2008 20:13:10 +0100 Subject: ide: set IDE_TFLAG_IN_* flags before queuing/executing command * Add IDE_TFLAG_{HOB,TF,DEVICE} defines. * Set IDE_TFLAG_IN_* flags in {do_rw,ide_no_data,ide_raw}_taskfile() users. * Remove no longer needed ->tf_flags setup from ide_end_drive_cmd(). There should be no functionality changes caused by this patch. Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index c1a8b8bb93ab..02493dbb156d 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -931,6 +931,12 @@ enum { IDE_TFLAG_IN_TF = IDE_TFLAG_IN_NSECT | IDE_TFLAG_IN_LBA, IDE_TFLAG_IN_DEVICE = (1 << 29), + IDE_TFLAG_HOB = IDE_TFLAG_OUT_HOB | + IDE_TFLAG_IN_HOB, + IDE_TFLAG_TF = IDE_TFLAG_OUT_TF | + IDE_TFLAG_IN_TF, + IDE_TFLAG_DEVICE = IDE_TFLAG_OUT_DEVICE | + IDE_TFLAG_IN_DEVICE, /* force 16-bit I/O operations */ IDE_TFLAG_IO_16BIT = (1 << 30), }; -- cgit v1.2.3 From 4d7a984bdcbdda69fc6b2a4a655415140270aa7b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 26 Jan 2008 20:13:11 +0100 Subject: ide: task_end_request() fix task_end_request() modified to always call ide_end_drive_cmd() for taskfile requests. Previously, ide_end_drive_cmd() was called only when IDE_TFLAG_FLAGGED was set. Also, ide_dma_intr() is modified to use task_end_request(). Enables TASKFILE ioctls to get valid register outputs on successful completion. Bart: - ported it over recent IDE changes Signed-off-by: Tejun Heo Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 02493dbb156d..6192564fcc5a 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -993,6 +993,8 @@ void ide_pktcmd_tf_load(ide_drive_t *, u32, u16, u8); ide_startstop_t do_rw_taskfile(ide_drive_t *, ide_task_t *); +void task_end_request(ide_drive_t *, struct request *, u8); + int ide_raw_taskfile(ide_drive_t *, ide_task_t *, u8 *, u16); int ide_no_data_taskfile(ide_drive_t *, ide_task_t *); -- cgit v1.2.3 From 4906f3b4cddc3e4d62955ed386598561f95602c0 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Sat, 26 Jan 2008 20:13:11 +0100 Subject: ide: kill DATA_READY define Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 6192564fcc5a..7615a6244a51 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -107,7 +107,6 @@ typedef unsigned char byte; /* used everywhere */ #define BAD_W_STAT (BAD_R_STAT | WRERR_STAT) #define BAD_STAT (BAD_R_STAT | DRQ_STAT) #define DRIVE_READY (READY_STAT | SEEK_STAT) -#define DATA_READY (DRQ_STAT) #define BAD_CRC (ABRT_ERR | ICRC_ERR) -- cgit v1.2.3 From 2624565caacedd740fce7803fe2c162842aa5df4 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Sat, 26 Jan 2008 20:13:11 +0100 Subject: ide: use wait_drive_not_busy() in drive_cmd_intr() (take 2) Use wait_drive_not_busy() in drive_cmd_intr(). v2: * Fix wait_drive_not_busy() comment (noticed by Sergei). Acked-by: Sergei Shtylyov Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 7615a6244a51..c889a6e91c5c 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -994,6 +994,8 @@ ide_startstop_t do_rw_taskfile(ide_drive_t *, ide_task_t *); void task_end_request(ide_drive_t *, struct request *, u8); +u8 wait_drive_not_busy(ide_drive_t *); + int ide_raw_taskfile(ide_drive_t *, ide_task_t *, u8 *, u16); int ide_no_data_taskfile(ide_drive_t *, ide_task_t *); -- cgit v1.2.3 From 34f5d5ae35240a11846875d76eb935875ab0c366 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Sat, 26 Jan 2008 20:13:12 +0100 Subject: ide: switch set_xfer_rate() to use REQ_TYPE_ATA_TASKFILE requests Based on the earlier work by Tejun Heo. Switch set_xfer_rate() to use REQ_TYPE_ATA_TASKFILE requests and make ide_wait_cmd() static. There should be no functionality changes caused by this patch. Cc: Tejun Heo Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/ide.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index c889a6e91c5c..27cb39de2ae2 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -870,14 +870,6 @@ extern int ide_do_drive_cmd(ide_drive_t *, struct request *, ide_action_t); extern void ide_end_drive_cmd(ide_drive_t *, u8, u8); -/* - * Issue ATA command and wait for completion. - * Use for implementing commands in kernel - * - * (ide_drive_t *drive, u8 cmd, u8 nsect, u8 feature, u8 sectors, u8 *buf) - */ -extern int ide_wait_cmd(ide_drive_t *, u8, u8, u8, u8, u8 *); - enum { IDE_TFLAG_LBA48 = (1 << 0), IDE_TFLAG_NO_SELECT_MASK = (1 << 1), -- cgit v1.2.3 From 7267c3377443322588cddaf457cf106839a60463 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Sat, 26 Jan 2008 20:13:13 +0100 Subject: ide: remove REQ_TYPE_ATA_CMD Based on the earlier work by Tejun Heo. All users are gone so we can finally remove it. Cc: Tejun Heo Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bd20a4e8663a..49b7a4c31a6d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -143,7 +143,6 @@ enum rq_cmd_type_bits { * use REQ_TYPE_SPECIAL and use rq->cmd[0] with the range of driver * private REQ_LB opcodes to differentiate what type of request this is */ - REQ_TYPE_ATA_CMD, REQ_TYPE_ATA_TASKFILE, REQ_TYPE_ATA_PC, }; -- cgit v1.2.3 From eee87d3196c9a7ac3422f4298e2250ca68d791c1 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sun, 27 Jan 2008 18:14:45 +0100 Subject: i2c: the scheduled I2C RTC driver removal This patch contains the scheduled removal of legacy I2C RTC drivers with replacement drivers. Signed-off-by: Adrian Bunk Signed-off-by: Jean Delvare --- include/linux/i2c-id.h | 2 -- include/linux/m41t00.h | 50 -------------------------------------------------- 2 files changed, 52 deletions(-) delete mode 100644 include/linux/m41t00.h (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index c7a51a196f51..10c8edd7795c 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -83,7 +83,6 @@ #define I2C_DRIVERID_SAA7114 49 /* video decoder */ #define I2C_DRIVERID_ZR36120 50 /* Zoran 36120 video encoder */ #define I2C_DRIVERID_24LC32A 51 /* Microchip 24LC32A 32k EEPROM */ -#define I2C_DRIVERID_STM41T00 52 /* real time clock */ #define I2C_DRIVERID_UDA1342 53 /* UDA1342 audio codec */ #define I2C_DRIVERID_ADV7170 54 /* video encoder */ #define I2C_DRIVERID_MAX1617 56 /* temp sensor */ @@ -95,7 +94,6 @@ #define I2C_DRIVERID_TDA7313 62 /* TDA7313 audio processor */ #define I2C_DRIVERID_MAX6900 63 /* MAX6900 real-time clock */ #define I2C_DRIVERID_SAA7114H 64 /* video decoder */ -#define I2C_DRIVERID_DS1374 65 /* DS1374 real time clock */ #define I2C_DRIVERID_TDA9874 66 /* TV sound decoder */ #define I2C_DRIVERID_SAA6752HS 67 /* MPEG2 encoder */ #define I2C_DRIVERID_TVEEPROM 68 /* TV EEPROM */ diff --git a/include/linux/m41t00.h b/include/linux/m41t00.h deleted file mode 100644 index b423360ca38e..000000000000 --- a/include/linux/m41t00.h +++ /dev/null @@ -1,50 +0,0 @@ -/* - * Definitions for the ST M41T00 family of i2c rtc chips. - * - * Author: Mark A. Greer - * - * 2005, 2006 (c) MontaVista Software, Inc. This file is licensed under - * the terms of the GNU General Public License version 2. This program - * is licensed "as is" without any warranty of any kind, whether express - * or implied. - */ - -#ifndef _M41T00_H -#define _M41T00_H - -#define M41T00_DRV_NAME "m41t00" -#define M41T00_I2C_ADDR 0x68 - -#define M41T00_TYPE_M41T00 0 -#define M41T00_TYPE_M41T81 81 -#define M41T00_TYPE_M41T85 85 - -struct m41t00_platform_data { - u8 type; - u8 i2c_addr; - u8 sqw_freq; -}; - -/* SQW output disabled, this is default value by power on */ -#define M41T00_SQW_DISABLE (0) - -#define M41T00_SQW_32KHZ (1<<4) /* 32.768 KHz */ -#define M41T00_SQW_8KHZ (2<<4) /* 8.192 KHz */ -#define M41T00_SQW_4KHZ (3<<4) /* 4.096 KHz */ -#define M41T00_SQW_2KHZ (4<<4) /* 2.048 KHz */ -#define M41T00_SQW_1KHZ (5<<4) /* 1.024 KHz */ -#define M41T00_SQW_512HZ (6<<4) /* 512 Hz */ -#define M41T00_SQW_256HZ (7<<4) /* 256 Hz */ -#define M41T00_SQW_128HZ (8<<4) /* 128 Hz */ -#define M41T00_SQW_64HZ (9<<4) /* 64 Hz */ -#define M41T00_SQW_32HZ (10<<4) /* 32 Hz */ -#define M41T00_SQW_16HZ (11<<4) /* 16 Hz */ -#define M41T00_SQW_8HZ (12<<4) /* 8 Hz */ -#define M41T00_SQW_4HZ (13<<4) /* 4 Hz */ -#define M41T00_SQW_2HZ (14<<4) /* 2 Hz */ -#define M41T00_SQW_1HZ (15<<4) /* 1 Hz */ - -extern ulong m41t00_get_rtc_time(void); -extern int m41t00_set_rtc_time(ulong nowtime); - -#endif /* _M41T00_H */ -- cgit v1.2.3 From 7e8b99251be8b6f992baa88e3a6ba3c4ae01660b Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sun, 27 Jan 2008 18:14:46 +0100 Subject: i2c: some overdue driver removal This patch contains the overdue removal of three I2C drivers. [JD: In fact only i2c-ixp4xx can be removed at the moment, the other two platforms don't implement the generic GPIO layer yet.] Signed-off-by: Adrian Bunk Signed-off-by: Jean Delvare --- include/linux/i2c-id.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index 10c8edd7795c..6bab140a4505 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -191,7 +191,6 @@ #define I2C_HW_B_OMAHA 0x010014 /* Omaha I2C interface (ARM) */ #define I2C_HW_B_GUIDE 0x010015 /* Guide bit-basher */ #define I2C_HW_B_IXP2000 0x010016 /* GPIO on IXP2000 systems */ -#define I2C_HW_B_IXP4XX 0x010017 /* GPIO on IXP4XX systems */ #define I2C_HW_B_S3VIA 0x010018 /* S3Via ProSavage adapter */ #define I2C_HW_B_ZR36067 0x010019 /* Zoran-36057/36067 based boards */ #define I2C_HW_B_PCILYNX 0x01001a /* TI PCILynx I2C adapter */ -- cgit v1.2.3 From bfb6df24facfde7ec6191edbba798777efb3c375 Mon Sep 17 00:00:00 2001 From: "Mark M. Hoffman" Date: Sun, 27 Jan 2008 18:14:46 +0100 Subject: i2c: Constify client address data This patch allows much of the I2C client address data to move from initdata into text. Signed-off-by: Mark M. Hoffman Signed-off-by: Jean Delvare --- include/linux/i2c.h | 100 ++++++++++++++++++++++------------------------------ 1 file changed, 43 insertions(+), 57 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index a100c9f8eb7c..37c14b08d61a 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -357,10 +357,10 @@ static inline void i2c_set_adapdata (struct i2c_adapter *dev, void *data) * command line */ struct i2c_client_address_data { - unsigned short *normal_i2c; - unsigned short *probe; - unsigned short *ignore; - unsigned short **forces; + const unsigned short *normal_i2c; + const unsigned short *probe; + const unsigned short *ignore; + const unsigned short * const *forces; }; /* Internal numbers to terminate lists */ @@ -405,7 +405,7 @@ extern void i2c_clients_command(struct i2c_adapter *adap, * specific address (unless a 'force' matched); */ extern int i2c_probe(struct i2c_adapter *adapter, - struct i2c_client_address_data *address_data, + const struct i2c_client_address_data *address_data, int (*found_proc) (struct i2c_adapter *, int, int)); extern struct i2c_adapter* i2c_get_adapter(int id); @@ -598,104 +598,93 @@ I2C_CLIENT_MODULE_PARM(probe, "List of adapter,address pairs to scan " \ "additionally"); \ I2C_CLIENT_MODULE_PARM(ignore, "List of adapter,address pairs not to " \ "scan"); \ -static struct i2c_client_address_data addr_data = { \ +const static struct i2c_client_address_data addr_data = { \ .normal_i2c = normal_i2c, \ .probe = probe, \ .ignore = ignore, \ .forces = forces, \ } +#define I2C_CLIENT_FORCE_TEXT \ + "List of adapter,address pairs to boldly assume to be present" + /* These are the ones you want to use in your own drivers. Pick the one which matches the number of devices the driver differenciates between. */ -#define I2C_CLIENT_INSMOD \ - I2C_CLIENT_MODULE_PARM(force, \ - "List of adapter,address pairs to boldly assume " \ - "to be present"); \ - static unsigned short *forces[] = { \ - force, \ - NULL \ - }; \ +#define I2C_CLIENT_INSMOD \ +I2C_CLIENT_MODULE_PARM(force, I2C_CLIENT_FORCE_TEXT); \ +static const unsigned short * const forces[] = { force, NULL }; \ I2C_CLIENT_INSMOD_COMMON #define I2C_CLIENT_INSMOD_1(chip1) \ enum chips { any_chip, chip1 }; \ -I2C_CLIENT_MODULE_PARM(force, "List of adapter,address pairs to " \ - "boldly assume to be present"); \ +I2C_CLIENT_MODULE_PARM(force, I2C_CLIENT_FORCE_TEXT); \ I2C_CLIENT_MODULE_PARM_FORCE(chip1); \ -static unsigned short *forces[] = { force, force_##chip1, NULL }; \ +static const unsigned short * const forces[] = { force, \ + force_##chip1, NULL }; \ I2C_CLIENT_INSMOD_COMMON #define I2C_CLIENT_INSMOD_2(chip1, chip2) \ enum chips { any_chip, chip1, chip2 }; \ -I2C_CLIENT_MODULE_PARM(force, "List of adapter,address pairs to " \ - "boldly assume to be present"); \ +I2C_CLIENT_MODULE_PARM(force, I2C_CLIENT_FORCE_TEXT); \ I2C_CLIENT_MODULE_PARM_FORCE(chip1); \ I2C_CLIENT_MODULE_PARM_FORCE(chip2); \ -static unsigned short *forces[] = { force, force_##chip1, \ - force_##chip2, NULL }; \ +static const unsigned short * const forces[] = { force, \ + force_##chip1, force_##chip2, NULL }; \ I2C_CLIENT_INSMOD_COMMON #define I2C_CLIENT_INSMOD_3(chip1, chip2, chip3) \ enum chips { any_chip, chip1, chip2, chip3 }; \ -I2C_CLIENT_MODULE_PARM(force, "List of adapter,address pairs to " \ - "boldly assume to be present"); \ +I2C_CLIENT_MODULE_PARM(force, I2C_CLIENT_FORCE_TEXT); \ I2C_CLIENT_MODULE_PARM_FORCE(chip1); \ I2C_CLIENT_MODULE_PARM_FORCE(chip2); \ I2C_CLIENT_MODULE_PARM_FORCE(chip3); \ -static unsigned short *forces[] = { force, force_##chip1, \ - force_##chip2, force_##chip3, \ - NULL }; \ +static const unsigned short * const forces[] = { force, \ + force_##chip1, force_##chip2, force_##chip3, NULL }; \ I2C_CLIENT_INSMOD_COMMON #define I2C_CLIENT_INSMOD_4(chip1, chip2, chip3, chip4) \ enum chips { any_chip, chip1, chip2, chip3, chip4 }; \ -I2C_CLIENT_MODULE_PARM(force, "List of adapter,address pairs to " \ - "boldly assume to be present"); \ +I2C_CLIENT_MODULE_PARM(force, I2C_CLIENT_FORCE_TEXT); \ I2C_CLIENT_MODULE_PARM_FORCE(chip1); \ I2C_CLIENT_MODULE_PARM_FORCE(chip2); \ I2C_CLIENT_MODULE_PARM_FORCE(chip3); \ I2C_CLIENT_MODULE_PARM_FORCE(chip4); \ -static unsigned short *forces[] = { force, force_##chip1, \ - force_##chip2, force_##chip3, \ - force_##chip4, NULL}; \ +static const unsigned short * const forces[] = { force, \ + force_##chip1, force_##chip2, force_##chip3, \ + force_##chip4, NULL}; \ I2C_CLIENT_INSMOD_COMMON #define I2C_CLIENT_INSMOD_5(chip1, chip2, chip3, chip4, chip5) \ enum chips { any_chip, chip1, chip2, chip3, chip4, chip5 }; \ -I2C_CLIENT_MODULE_PARM(force, "List of adapter,address pairs to " \ - "boldly assume to be present"); \ +I2C_CLIENT_MODULE_PARM(force, I2C_CLIENT_FORCE_TEXT); \ I2C_CLIENT_MODULE_PARM_FORCE(chip1); \ I2C_CLIENT_MODULE_PARM_FORCE(chip2); \ I2C_CLIENT_MODULE_PARM_FORCE(chip3); \ I2C_CLIENT_MODULE_PARM_FORCE(chip4); \ I2C_CLIENT_MODULE_PARM_FORCE(chip5); \ -static unsigned short *forces[] = { force, force_##chip1, \ - force_##chip2, force_##chip3, \ - force_##chip4, force_##chip5, \ - NULL }; \ +static const unsigned short * const forces[] = { force, \ + force_##chip1, force_##chip2, force_##chip3, \ + force_##chip4, force_##chip5, NULL }; \ I2C_CLIENT_INSMOD_COMMON #define I2C_CLIENT_INSMOD_6(chip1, chip2, chip3, chip4, chip5, chip6) \ enum chips { any_chip, chip1, chip2, chip3, chip4, chip5, chip6 }; \ -I2C_CLIENT_MODULE_PARM(force, "List of adapter,address pairs to " \ - "boldly assume to be present"); \ +I2C_CLIENT_MODULE_PARM(force, I2C_CLIENT_FORCE_TEXT); \ I2C_CLIENT_MODULE_PARM_FORCE(chip1); \ I2C_CLIENT_MODULE_PARM_FORCE(chip2); \ I2C_CLIENT_MODULE_PARM_FORCE(chip3); \ I2C_CLIENT_MODULE_PARM_FORCE(chip4); \ I2C_CLIENT_MODULE_PARM_FORCE(chip5); \ I2C_CLIENT_MODULE_PARM_FORCE(chip6); \ -static unsigned short *forces[] = { force, force_##chip1, \ - force_##chip2, force_##chip3, \ - force_##chip4, force_##chip5, \ - force_##chip6, NULL }; \ +static const unsigned short * const forces[] = { force, \ + force_##chip1, force_##chip2, force_##chip3, \ + force_##chip4, force_##chip5, force_##chip6, NULL }; \ I2C_CLIENT_INSMOD_COMMON #define I2C_CLIENT_INSMOD_7(chip1, chip2, chip3, chip4, chip5, chip6, chip7) \ enum chips { any_chip, chip1, chip2, chip3, chip4, chip5, chip6, \ chip7 }; \ -I2C_CLIENT_MODULE_PARM(force, "List of adapter,address pairs to " \ - "boldly assume to be present"); \ +I2C_CLIENT_MODULE_PARM(force, I2C_CLIENT_FORCE_TEXT); \ I2C_CLIENT_MODULE_PARM_FORCE(chip1); \ I2C_CLIENT_MODULE_PARM_FORCE(chip2); \ I2C_CLIENT_MODULE_PARM_FORCE(chip3); \ @@ -703,18 +692,16 @@ I2C_CLIENT_MODULE_PARM_FORCE(chip4); \ I2C_CLIENT_MODULE_PARM_FORCE(chip5); \ I2C_CLIENT_MODULE_PARM_FORCE(chip6); \ I2C_CLIENT_MODULE_PARM_FORCE(chip7); \ -static unsigned short *forces[] = { force, force_##chip1, \ - force_##chip2, force_##chip3, \ - force_##chip4, force_##chip5, \ - force_##chip6, force_##chip7, \ - NULL }; \ +static const unsigned short * const forces[] = { force, \ + force_##chip1, force_##chip2, force_##chip3, \ + force_##chip4, force_##chip5, force_##chip6, \ + force_##chip7, NULL }; \ I2C_CLIENT_INSMOD_COMMON #define I2C_CLIENT_INSMOD_8(chip1, chip2, chip3, chip4, chip5, chip6, chip7, chip8) \ enum chips { any_chip, chip1, chip2, chip3, chip4, chip5, chip6, \ chip7, chip8 }; \ -I2C_CLIENT_MODULE_PARM(force, "List of adapter,address pairs to " \ - "boldly assume to be present"); \ +I2C_CLIENT_MODULE_PARM(force, I2C_CLIENT_FORCE_TEXT); \ I2C_CLIENT_MODULE_PARM_FORCE(chip1); \ I2C_CLIENT_MODULE_PARM_FORCE(chip2); \ I2C_CLIENT_MODULE_PARM_FORCE(chip3); \ @@ -723,11 +710,10 @@ I2C_CLIENT_MODULE_PARM_FORCE(chip5); \ I2C_CLIENT_MODULE_PARM_FORCE(chip6); \ I2C_CLIENT_MODULE_PARM_FORCE(chip7); \ I2C_CLIENT_MODULE_PARM_FORCE(chip8); \ -static unsigned short *forces[] = { force, force_##chip1, \ - force_##chip2, force_##chip3, \ - force_##chip4, force_##chip5, \ - force_##chip6, force_##chip7, \ - force_##chip8, NULL }; \ +static const unsigned short * const forces[] = { force, \ + force_##chip1, force_##chip2, force_##chip3, \ + force_##chip4, force_##chip5, force_##chip6, \ + force_##chip7, force_##chip8, NULL }; \ I2C_CLIENT_INSMOD_COMMON #endif /* __KERNEL__ */ #endif /* _LINUX_I2C_H */ -- cgit v1.2.3 From bdc511f438f6ca40307e06edda00331e6ac0f813 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 27 Jan 2008 18:14:48 +0100 Subject: i2c: Use the driver model reference counting Don't implement our own reference counting mechanism for i2c clients when the driver model already has one. Signed-off-by: Jean Delvare Cc: David Brownell --- include/linux/i2c.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 37c14b08d61a..f7cd2f370c39 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -155,7 +155,6 @@ struct i2c_driver { * generic enough to hide second-sourcing and compatible revisions. * @adapter: manages the bus segment hosting this I2C device * @driver: device's driver, hence pointer to access routines - * @usage_count: counts current number of users of this client * @dev: Driver model device node for the slave. * @irq: indicates the IRQ generated by this device (if any) * @driver_name: Identifies new-style driver used with this device; also @@ -175,8 +174,6 @@ struct i2c_client { char name[I2C_NAME_SIZE]; struct i2c_adapter *adapter; /* the adapter we sit on */ struct i2c_driver *driver; /* and our access routines */ - int usage_count; /* How many accesses currently */ - /* to the client */ struct device dev; /* the device structure */ int irq; /* irq issued by device (or -1) */ char driver_name[KOBJ_NAME_LEN]; -- cgit v1.2.3 From e48d33193d94175f012c3ed606a1d1e574ed726a Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 27 Jan 2008 18:14:48 +0100 Subject: i2c: Change prototypes of refcounting functions Use more standard prototypes for i2c_use_client() and i2c_release_client(). The former now returns a pointer to the client, and the latter no longer returns anything. This matches what all other subsystems do. Signed-off-by: Jean Delvare Cc: David Brownell --- include/linux/i2c.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index f7cd2f370c39..78a305bed8eb 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -386,11 +386,8 @@ static inline int i2c_add_driver(struct i2c_driver *driver) extern int i2c_attach_client(struct i2c_client *); extern int i2c_detach_client(struct i2c_client *); -/* Should be used to make sure that client-struct is valid and that it - is okay to access the i2c-client. - returns -ENODEV if client has gone in the meantime */ -extern int i2c_use_client(struct i2c_client *); -extern int i2c_release_client(struct i2c_client *); +extern struct i2c_client *i2c_use_client(struct i2c_client *client); +extern void i2c_release_client(struct i2c_client *client); /* call the i2c_client->command() of all attached clients with * the given arguments */ -- cgit v1.2.3 From 87c6c22945e5d68eb96dd1e5cb26185253cd5b9d Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 27 Jan 2008 18:14:48 +0100 Subject: i2c: Drop redundant i2c_adapter.list i2c_adapter.list is superfluous, this list duplicates the one maintained by the driver core. Drop it. Signed-off-by: Jean Delvare Acked-by: David Brownell --- include/linux/i2c.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 78a305bed8eb..5fa7e180501d 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -317,7 +317,6 @@ struct i2c_adapter { int nr; struct list_head clients; - struct list_head list; char name[48]; struct completion dev_released; }; -- cgit v1.2.3 From 026526f5afcd421dce110f53e4c4e2b9e78753c2 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 27 Jan 2008 18:14:49 +0100 Subject: i2c: Drop redundant i2c_driver.list i2c_driver.list is superfluous, this list duplicates the one maintained by the driver core. Drop it. Signed-off-by: Jean Delvare Acked-by: David Brownell --- include/linux/i2c.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 5fa7e180501d..0fc59efd80e4 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -140,7 +140,6 @@ struct i2c_driver { int (*command)(struct i2c_client *client,unsigned int cmd, void *arg); struct device_driver driver; - struct list_head list; }; #define to_i2c_driver(d) container_of(d, struct i2c_driver, driver) -- cgit v1.2.3 From 6d16bfb5e81d3925a7efb38b5cc3e0021b57d03a Mon Sep 17 00:00:00 2001 From: David Brownell Date: Sun, 27 Jan 2008 18:14:49 +0100 Subject: i2c/tps65010: move header to Move the tps65010 header file from the OMAP arch directory to the more generic directory, and remove the spurious dependency of this driver on OMAP. Signed-off-by: David Brownell Signed-off-by: Jean Delvare --- include/linux/i2c/tps65010.h | 156 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 156 insertions(+) create mode 100644 include/linux/i2c/tps65010.h (limited to 'include/linux') diff --git a/include/linux/i2c/tps65010.h b/include/linux/i2c/tps65010.h new file mode 100644 index 000000000000..7021635ed6a0 --- /dev/null +++ b/include/linux/i2c/tps65010.h @@ -0,0 +1,156 @@ +/* linux/i2c/tps65010.h + * + * Functions to access TPS65010 power management device. + * + * Copyright (C) 2004 Dirk Behme + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN + * NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, + * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT + * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF + * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON + * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF + * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#ifndef __LINUX_I2C_TPS65010_H +#define __LINUX_I2C_TPS65010_H + +/* + * ---------------------------------------------------------------------------- + * Registers, all 8 bits + * ---------------------------------------------------------------------------- + */ + +#define TPS_CHGSTATUS 0x01 +# define TPS_CHG_USB (1 << 7) +# define TPS_CHG_AC (1 << 6) +# define TPS_CHG_THERM (1 << 5) +# define TPS_CHG_TERM (1 << 4) +# define TPS_CHG_TAPER_TMO (1 << 3) +# define TPS_CHG_CHG_TMO (1 << 2) +# define TPS_CHG_PRECHG_TMO (1 << 1) +# define TPS_CHG_TEMP_ERR (1 << 0) +#define TPS_REGSTATUS 0x02 +# define TPS_REG_ONOFF (1 << 7) +# define TPS_REG_COVER (1 << 6) +# define TPS_REG_UVLO (1 << 5) +# define TPS_REG_NO_CHG (1 << 4) /* tps65013 */ +# define TPS_REG_PG_LD02 (1 << 3) +# define TPS_REG_PG_LD01 (1 << 2) +# define TPS_REG_PG_MAIN (1 << 1) +# define TPS_REG_PG_CORE (1 << 0) +#define TPS_MASK1 0x03 +#define TPS_MASK2 0x04 +#define TPS_ACKINT1 0x05 +#define TPS_ACKINT2 0x06 +#define TPS_CHGCONFIG 0x07 +# define TPS_CHARGE_POR (1 << 7) /* 65010/65012 */ +# define TPS65013_AUA (1 << 7) /* 65011/65013 */ +# define TPS_CHARGE_RESET (1 << 6) +# define TPS_CHARGE_FAST (1 << 5) +# define TPS_CHARGE_CURRENT (3 << 3) +# define TPS_VBUS_500MA (1 << 2) +# define TPS_VBUS_CHARGING (1 << 1) +# define TPS_CHARGE_ENABLE (1 << 0) +#define TPS_LED1_ON 0x08 +#define TPS_LED1_PER 0x09 +#define TPS_LED2_ON 0x0a +#define TPS_LED2_PER 0x0b +#define TPS_VDCDC1 0x0c +# define TPS_ENABLE_LP (1 << 3) +#define TPS_VDCDC2 0x0d +#define TPS_VREGS1 0x0e +# define TPS_LDO2_ENABLE (1 << 7) +# define TPS_LDO2_OFF (1 << 6) +# define TPS_VLDO2_3_0V (3 << 4) +# define TPS_VLDO2_2_75V (2 << 4) +# define TPS_VLDO2_2_5V (1 << 4) +# define TPS_VLDO2_1_8V (0 << 4) +# define TPS_LDO1_ENABLE (1 << 3) +# define TPS_LDO1_OFF (1 << 2) +# define TPS_VLDO1_3_0V (3 << 0) +# define TPS_VLDO1_2_75V (2 << 0) +# define TPS_VLDO1_2_5V (1 << 0) +# define TPS_VLDO1_ADJ (0 << 0) +#define TPS_MASK3 0x0f +#define TPS_DEFGPIO 0x10 + +/* + * ---------------------------------------------------------------------------- + * Macros used by exported functions + * ---------------------------------------------------------------------------- + */ + +#define LED1 1 +#define LED2 2 +#define OFF 0 +#define ON 1 +#define BLINK 2 +#define GPIO1 1 +#define GPIO2 2 +#define GPIO3 3 +#define GPIO4 4 +#define LOW 0 +#define HIGH 1 + +/* + * ---------------------------------------------------------------------------- + * Exported functions + * ---------------------------------------------------------------------------- + */ + +/* Draw from VBUS: + * 0 mA -- DON'T DRAW (might supply power instead) + * 100 mA -- usb unit load (slowest charge rate) + * 500 mA -- usb high power (fast battery charge) + */ +extern int tps65010_set_vbus_draw(unsigned mA); + +/* tps65010_set_gpio_out_value parameter: + * gpio: GPIO1, GPIO2, GPIO3 or GPIO4 + * value: LOW or HIGH + */ +extern int tps65010_set_gpio_out_value(unsigned gpio, unsigned value); + +/* tps65010_set_led parameter: + * led: LED1 or LED2 + * mode: ON, OFF or BLINK + */ +extern int tps65010_set_led(unsigned led, unsigned mode); + +/* tps65010_set_vib parameter: + * value: ON or OFF + */ +extern int tps65010_set_vib(unsigned value); + +/* tps65010_set_low_pwr parameter: + * mode: ON or OFF + */ +extern int tps65010_set_low_pwr(unsigned mode); + +/* tps65010_config_vregs1 parameter: + * value to be written to VREGS1 register + * Note: The complete register is written, set all bits you need + */ +extern int tps65010_config_vregs1(unsigned value); + +/* tps65013_set_low_pwr parameter: + * mode: ON or OFF + */ +extern int tps65013_set_low_pwr(unsigned mode); + +#endif /* __LINUX_I2C_TPS65010_H */ + -- cgit v1.2.3 From 7bca0871ca332ad5373a0fd26886e3cfbafa822c Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Sun, 27 Jan 2008 18:14:50 +0100 Subject: i2c: Discard unused driver IDs Discard all I2C driver IDs that aren't used anywhere. That's not just a couple of them, but more like 49 or one quarter of all defined IDs! And this is just a first pass, next will come all IDs that are set but never used, or used but never set. Signed-off-by: Jean Delvare --- include/linux/i2c-id.h | 60 -------------------------------------------------- 1 file changed, 60 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h index 6bab140a4505..f922b060158b 100644 --- a/include/linux/i2c-id.h +++ b/include/linux/i2c-id.h @@ -33,23 +33,13 @@ #define I2C_DRIVERID_MSP3400 1 #define I2C_DRIVERID_TUNER 2 -#define I2C_DRIVERID_VIDEOTEX 3 /* please rename */ #define I2C_DRIVERID_TDA8425 4 /* stereo sound processor */ #define I2C_DRIVERID_TEA6420 5 /* audio matrix switch */ #define I2C_DRIVERID_TEA6415C 6 /* video matrix switch */ #define I2C_DRIVERID_TDA9840 7 /* stereo sound processor */ #define I2C_DRIVERID_SAA7111A 8 /* video input processor */ -#define I2C_DRIVERID_SAA5281 9 /* videotext decoder */ -#define I2C_DRIVERID_SAA7112 10 /* video decoder, image scaler */ -#define I2C_DRIVERID_SAA7120 11 /* video encoder */ -#define I2C_DRIVERID_SAA7121 12 /* video encoder */ #define I2C_DRIVERID_SAA7185B 13 /* video encoder */ -#define I2C_DRIVERID_CH7003 14 /* digital pc to tv encoder */ -#define I2C_DRIVERID_PCF8574A 15 /* i2c expander - 8 bit in/out */ -#define I2C_DRIVERID_PCF8582C 16 /* eeprom */ -#define I2C_DRIVERID_AT24Cxx 17 /* eeprom 1/2/4/8/16 K */ #define I2C_DRIVERID_TEA6300 18 /* audio mixer */ -#define I2C_DRIVERID_BT829 19 /* pc to tv encoder */ #define I2C_DRIVERID_TDA9850 20 /* audio mixer */ #define I2C_DRIVERID_TDA9855 21 /* audio mixer */ #define I2C_DRIVERID_SAA7110 22 /* video decoder */ @@ -60,40 +50,19 @@ #define I2C_DRIVERID_TDA7432 27 /* Stereo sound processor */ #define I2C_DRIVERID_TVMIXER 28 /* Mixer driver for tv cards */ #define I2C_DRIVERID_TVAUDIO 29 /* Generic TV sound driver */ -#define I2C_DRIVERID_DPL3518 30 /* Dolby decoder chip */ #define I2C_DRIVERID_TDA9873 31 /* TV sound decoder chip */ #define I2C_DRIVERID_TDA9875 32 /* TV sound decoder chip */ #define I2C_DRIVERID_PIC16C54_PV9 33 /* Audio mux/ir receiver */ - -#define I2C_DRIVERID_SBATT 34 /* Smart Battery Device */ -#define I2C_DRIVERID_SBS 35 /* SB System Manager */ -#define I2C_DRIVERID_VES1893 36 /* VLSI DVB-S decoder */ -#define I2C_DRIVERID_VES1820 37 /* VLSI DVB-C decoder */ -#define I2C_DRIVERID_SAA7113 38 /* video decoder */ -#define I2C_DRIVERID_TDA8444 39 /* octuple 6-bit DAC */ #define I2C_DRIVERID_BT819 40 /* video decoder */ #define I2C_DRIVERID_BT856 41 /* video encoder */ #define I2C_DRIVERID_VPX3220 42 /* video decoder+vbi/vtxt */ -#define I2C_DRIVERID_DRP3510 43 /* ADR decoder (Astra Radio) */ -#define I2C_DRIVERID_SP5055 44 /* Satellite tuner */ -#define I2C_DRIVERID_STV0030 45 /* Multipurpose switch */ -#define I2C_DRIVERID_SAA7108 46 /* video decoder, image scaler */ -#define I2C_DRIVERID_DS1307 47 /* DS1307 real time clock */ #define I2C_DRIVERID_ADV7175 48 /* ADV 7175/7176 video encoder */ #define I2C_DRIVERID_SAA7114 49 /* video decoder */ -#define I2C_DRIVERID_ZR36120 50 /* Zoran 36120 video encoder */ -#define I2C_DRIVERID_24LC32A 51 /* Microchip 24LC32A 32k EEPROM */ -#define I2C_DRIVERID_UDA1342 53 /* UDA1342 audio codec */ #define I2C_DRIVERID_ADV7170 54 /* video encoder */ -#define I2C_DRIVERID_MAX1617 56 /* temp sensor */ #define I2C_DRIVERID_SAA7191 57 /* video decoder */ #define I2C_DRIVERID_INDYCAM 58 /* SGI IndyCam */ -#define I2C_DRIVERID_BT832 59 /* CMOS camera video processor */ -#define I2C_DRIVERID_TDA9887 60 /* TDA988x IF-PLL demodulator */ #define I2C_DRIVERID_OVCAMCHIP 61 /* OmniVision CMOS image sens. */ -#define I2C_DRIVERID_TDA7313 62 /* TDA7313 audio processor */ #define I2C_DRIVERID_MAX6900 63 /* MAX6900 real-time clock */ -#define I2C_DRIVERID_SAA7114H 64 /* video decoder */ #define I2C_DRIVERID_TDA9874 66 /* TV sound decoder */ #define I2C_DRIVERID_SAA6752HS 67 /* MPEG2 encoder */ #define I2C_DRIVERID_TVEEPROM 68 /* TV EEPROM */ @@ -112,7 +81,6 @@ #define I2C_DRIVERID_DS1672 81 /* Dallas/Maxim DS1672 RTC */ #define I2C_DRIVERID_X1205 82 /* Xicor/Intersil X1205 RTC */ #define I2C_DRIVERID_PCF8563 83 /* Philips PCF8563 RTC */ -#define I2C_DRIVERID_RS5C372 84 /* Ricoh RS5C372 RTC */ #define I2C_DRIVERID_BT866 85 /* Conexant bt866 video encoder */ #define I2C_DRIVERID_KS0127 86 /* Samsung ks0127 video decoder */ #define I2C_DRIVERID_TLV320AIC23B 87 /* TI TLV320AIC23B audio codec */ @@ -127,8 +95,6 @@ #define I2C_DRIVERID_CS5345 96 /* cs5345 audio processor */ #define I2C_DRIVERID_I2CDEV 900 -#define I2C_DRIVERID_ARP 902 /* SMBus ARP Client */ -#define I2C_DRIVERID_ALERT 903 /* SMBus Alert Responder Client */ /* IDs -- Use DRIVERIDs 1000-1999 for sensors. These were originally in sensors.h in the lm_sensors package */ @@ -174,22 +140,15 @@ /* --- Bit algorithm adapters */ #define I2C_HW_B_LP 0x010000 /* Parallel port Philips style */ -#define I2C_HW_B_SER 0x010002 /* Serial line interface */ #define I2C_HW_B_BT848 0x010005 /* BT848 video boards */ -#define I2C_HW_B_WNV 0x010006 /* Winnov Videums */ #define I2C_HW_B_VIA 0x010007 /* Via vt82c586b */ #define I2C_HW_B_HYDRA 0x010008 /* Apple Hydra Mac I/O */ #define I2C_HW_B_G400 0x010009 /* Matrox G400 */ #define I2C_HW_B_I810 0x01000a /* Intel I810 */ #define I2C_HW_B_VOO 0x01000b /* 3dfx Voodoo 3 / Banshee */ -#define I2C_HW_B_PPORT 0x01000c /* Primitive parallel port adapter */ -#define I2C_HW_B_SAVG 0x01000d /* Savage 4 */ #define I2C_HW_B_SCX200 0x01000e /* Nat'l Semi SCx200 I2C */ #define I2C_HW_B_RIVA 0x010010 /* Riva based graphics cards */ #define I2C_HW_B_IOC 0x010011 /* IOC bit-wiggling */ -#define I2C_HW_B_TSUNA 0x010012 /* DEC Tsunami chipset */ -#define I2C_HW_B_OMAHA 0x010014 /* Omaha I2C interface (ARM) */ -#define I2C_HW_B_GUIDE 0x010015 /* Guide bit-basher */ #define I2C_HW_B_IXP2000 0x010016 /* GPIO on IXP2000 systems */ #define I2C_HW_B_S3VIA 0x010018 /* S3Via ProSavage adapter */ #define I2C_HW_B_ZR36067 0x010019 /* Zoran-36057/36067 based boards */ @@ -204,22 +163,11 @@ #define I2C_HW_B_CX23885 0x010022 /* conexant 23885 based tv cards (bus1) */ /* --- PCF 8584 based algorithms */ -#define I2C_HW_P_LP 0x020000 /* Parallel port interface */ -#define I2C_HW_P_ISA 0x020001 /* generic ISA Bus inteface card */ #define I2C_HW_P_ELEK 0x020002 /* Elektor ISA Bus inteface card */ /* --- PCA 9564 based algorithms */ #define I2C_HW_A_ISA 0x1a0000 /* generic ISA Bus interface card */ -/* --- ACPI Embedded controller algorithms */ -#define I2C_HW_ACPI_EC 0x1f0000 - -/* --- MPC824x PowerPC adapters */ -#define I2C_HW_MPC824X 0x100001 /* Motorola 8240 / 8245 */ - -/* --- MPC8xx PowerPC adapters */ -#define I2C_HW_MPC8XX_EPON 0x110000 /* Eponymous MPC8xx I2C adapter */ - /* --- PowerPC on-chip adapters */ #define I2C_HW_OCP 0x120000 /* IBM on-chip I2C adapter */ @@ -228,7 +176,6 @@ /* --- SGI adapters */ #define I2C_HW_SGI_VINO 0x160000 -#define I2C_HW_SGI_MACE 0x160001 /* --- XSCALE on-chip adapters */ #define I2C_HW_IOP3XX 0x140000 @@ -252,17 +199,10 @@ #define I2C_HW_SMBUS_W9968CF 0x04000d #define I2C_HW_SMBUS_OV511 0x04000e /* OV511(+) USB 1.1 webcam ICs */ #define I2C_HW_SMBUS_OV518 0x04000f /* OV518(+) USB 1.1 webcam ICs */ -#define I2C_HW_SMBUS_OV519 0x040010 /* OV519 USB 1.1 webcam IC */ #define I2C_HW_SMBUS_OVFX2 0x040011 /* Cypress/OmniVision FX2 webcam */ #define I2C_HW_SMBUS_CAFE 0x040012 /* Marvell 88ALP01 "CAFE" cam */ #define I2C_HW_SMBUS_ALI1563 0x040013 -/* --- ISA pseudo-adapter */ -#define I2C_HW_ISA 0x050000 - -/* --- IPMB adapter */ -#define I2C_HW_IPMB 0x0c0000 - /* --- MCP107 adapter */ #define I2C_HW_MPC107 0x0d0000 -- cgit v1.2.3 From 9b766b814d6a5f31ca1e9da1ebc08164b9352941 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Sun, 27 Jan 2008 18:14:51 +0100 Subject: i2c: Stop using the redundant client list The i2c_adapter.clients list of i2c_client nodes duplicates driver model state. This patch starts removing that list, letting us remove most existing users of those i2c-core lists. * The core I2C code now iterates over the driver model's list instead of the i2c-internal one in some places where it's safe: - Passing a command/ioctl to each client, a mechanims used almost exclusively by DVB adapters; - Device address checking, in both i2c-core and i2c-dev. * Provide i2c_verify_client() to use with driver model iterators. * Flag the relevant i2c_adapter and i2c_client fields as deprecated, to help prevent new users from appearing. For the moment the list needs to stick around, since some issues show up when deleting devices created by legacy I2C drivers. (They don't follow standard driver model rules. Removing those devices can cause self-deadlocks.) Signed-off-by: David Brownell Signed-off-by: Jean Delvare --- include/linux/i2c.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 0fc59efd80e4..731928ae972c 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -158,7 +158,7 @@ struct i2c_driver { * @irq: indicates the IRQ generated by this device (if any) * @driver_name: Identifies new-style driver used with this device; also * used as the module name for hotplug/coldplug modprobe support. - * @list: list of active/busy clients + * @list: list of active/busy clients (DEPRECATED) * @released: used to synchronize client releases & detaches and references * * An i2c_client identifies a single device (i.e. chip) connected to an @@ -176,11 +176,13 @@ struct i2c_client { struct device dev; /* the device structure */ int irq; /* irq issued by device (or -1) */ char driver_name[KOBJ_NAME_LEN]; - struct list_head list; + struct list_head list; /* DEPRECATED */ struct completion released; }; #define to_i2c_client(d) container_of(d, struct i2c_client, dev) +extern struct i2c_client *i2c_verify_client(struct device *dev); + static inline struct i2c_client *kobj_to_i2c_client(struct kobject *kobj) { struct device * const dev = container_of(kobj, struct device, kobj); @@ -315,7 +317,7 @@ struct i2c_adapter { struct device dev; /* the adapter device */ int nr; - struct list_head clients; + struct list_head clients; /* DEPRECATED */ char name[48]; struct completion dev_released; }; -- cgit v1.2.3 From e9f1373b643887f63878d1169b310c9acc534cd5 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Sun, 27 Jan 2008 18:14:52 +0100 Subject: i2c: Add i2c_new_dummy() utility This adds a i2c_new_dummy() primitive to help work with devices that consume multiple addresses, which include many I2C eeproms and at least one RTC. Signed-off-by: David Brownell Signed-off-by: Jean Delvare --- include/linux/i2c.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 731928ae972c..76014f8f3c60 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -259,6 +259,12 @@ i2c_new_probed_device(struct i2c_adapter *adap, struct i2c_board_info *info, unsigned short const *addr_list); +/* For devices that use several addresses, use i2c_new_dummy() to make + * client handles for the extra addresses. + */ +extern struct i2c_client * +i2c_new_dummy(struct i2c_adapter *adap, u16 address, const char *type); + extern void i2c_unregister_device(struct i2c_client *); /* Mainboard arch_initcall() code should register all its I2C devices. -- cgit v1.2.3 From 1f9ffc049d7a88c8489b883b6fc0a25185062002 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 27 Jan 2008 10:29:20 -0800 Subject: Driver core: add bus_find_device_by_name function The driver core, and some other parts of the kernel just want to find a device based on a name for a specific bus. Give them a simple wrapper to prevent them from having to always roll their own. This will be used in the PPC patch later in this series. Cc: Paul Mackerras Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 1880208964d6..db375be333c7 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -84,6 +84,9 @@ int bus_for_each_dev(struct bus_type *bus, struct device *start, void *data, struct device *bus_find_device(struct bus_type *bus, struct device *start, void *data, int (*match)(struct device *dev, void *data)); +struct device *bus_find_device_by_name(struct bus_type *bus, + struct device *start, + const char *name); int __must_check bus_for_each_drv(struct bus_type *bus, struct device_driver *start, void *data, -- cgit v1.2.3 From 6da127ad0918f93ea93678dad62ce15ffed18797 Mon Sep 17 00:00:00 2001 From: Christof Schmitt Date: Fri, 11 Jan 2008 10:09:43 +0100 Subject: blktrace: Add blktrace ioctls to SCSI generic devices Since the SCSI layer uses the request queues from the block layer, blktrace can also be used to trace the requests to all SCSI devices (like SCSI tape drives), not only disks. The only missing part is the ioctl interface to start and stop tracing. This patch adds the SETUP, START, STOP and TEARDOWN ioctls from blktrace to the sg device files. With this change, blktrace can be used for SCSI devices like for disks, e.g.: blktrace -d /dev/sg1 -o - | blkparse -i - Signed-off-by: Christof Schmitt Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 7e11d23ac36a..06dadba349ac 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -148,7 +148,7 @@ extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *); extern void blk_trace_shutdown(struct request_queue *); extern void __blk_add_trace(struct blk_trace *, sector_t, int, int, u32, int, int, void *); extern int do_blk_trace_setup(struct request_queue *q, - struct block_device *bdev, struct blk_user_trace_setup *buts); + char *name, dev_t dev, struct blk_user_trace_setup *buts); /** @@ -282,6 +282,11 @@ static inline void blk_add_trace_remap(struct request_queue *q, struct bio *bio, __blk_add_trace(bt, from, bio->bi_size, bio->bi_rw, BLK_TA_REMAP, !bio_flagged(bio, BIO_UPTODATE), sizeof(r), &r); } +extern int blk_trace_setup(request_queue_t *q, char *name, dev_t dev, + char __user *arg); +extern int blk_trace_startstop(request_queue_t *q, int start); +extern int blk_trace_remove(request_queue_t *q); + #else /* !CONFIG_BLK_DEV_IO_TRACE */ #define blk_trace_ioctl(bdev, cmd, arg) (-ENOTTY) #define blk_trace_shutdown(q) do { } while (0) @@ -290,7 +295,10 @@ static inline void blk_add_trace_remap(struct request_queue *q, struct bio *bio, #define blk_add_trace_generic(q, rq, rw, what) do { } while (0) #define blk_add_trace_pdu_int(q, what, bio, pdu) do { } while (0) #define blk_add_trace_remap(q, bio, dev, f, t) do {} while (0) -#define do_blk_trace_setup(q, bdev, buts) (-ENOTTY) +#define do_blk_trace_setup(q, name, dev, buts) (-ENOTTY) +#define blk_trace_setup(q, name, dev, arg) (-ENOTTY) +#define blk_trace_startstop(q, start) (-ENOTTY) +#define blk_trace_remove(q) (-ENOTTY) #endif /* CONFIG_BLK_DEV_IO_TRACE */ #endif /* __KERNEL__ */ #endif -- cgit v1.2.3 From 482eb689169948e9f4966fbae6be4d6bc0bfa818 Mon Sep 17 00:00:00 2001 From: Pete Wyckoff Date: Tue, 1 Jan 2008 10:23:02 -0500 Subject: block: allow queue dma_alignment of zero Let queue_dma_alignment return 0 if it was specifically set to 0. This permits devices with no particular alignment restrictions to use arbitrary user space buffers without copying. Signed-off-by: Pete Wyckoff Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 49b7a4c31a6d..c7a3ab575c24 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -836,12 +836,7 @@ static inline int bdev_hardsect_size(struct block_device *bdev) static inline int queue_dma_alignment(struct request_queue *q) { - int retval = 511; - - if (q && q->dma_alignment) - retval = q->dma_alignment; - - return retval; + return q ? q->dma_alignment : 511; } /* assumes size > 256 */ -- cgit v1.2.3 From 0db9299f48ebd4a860d6ad4e1d36ac50671d48e7 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 30 Nov 2007 09:16:50 +0100 Subject: SG: Move functions to lib/scatterlist.c and add sg chaining allocator helpers Manually doing chained sg lists is not trivial, so add some helpers to make sure that drivers get it right. Signed-off-by: Jens Axboe --- include/linux/scatterlist.h | 125 +++++++++----------------------------------- 1 file changed, 25 insertions(+), 100 deletions(-) (limited to 'include/linux') diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index e3ff21dbac53..e9cb103417b2 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -7,6 +7,12 @@ #include #include +struct sg_table { + struct scatterlist *sgl; /* the list */ + unsigned int nents; /* number of mapped entries */ + unsigned int orig_nents; /* original size of list */ +}; + /* * Notes on SG table design. * @@ -106,71 +112,12 @@ static inline void sg_set_buf(struct scatterlist *sg, const void *buf, sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf)); } -/** - * sg_next - return the next scatterlist entry in a list - * @sg: The current sg entry - * - * Description: - * Usually the next entry will be @sg@ + 1, but if this sg element is part - * of a chained scatterlist, it could jump to the start of a new - * scatterlist array. - * - **/ -static inline struct scatterlist *sg_next(struct scatterlist *sg) -{ -#ifdef CONFIG_DEBUG_SG - BUG_ON(sg->sg_magic != SG_MAGIC); -#endif - if (sg_is_last(sg)) - return NULL; - - sg++; - if (unlikely(sg_is_chain(sg))) - sg = sg_chain_ptr(sg); - - return sg; -} - /* * Loop over each sg element, following the pointer to a new list if necessary */ #define for_each_sg(sglist, sg, nr, __i) \ for (__i = 0, sg = (sglist); __i < (nr); __i++, sg = sg_next(sg)) -/** - * sg_last - return the last scatterlist entry in a list - * @sgl: First entry in the scatterlist - * @nents: Number of entries in the scatterlist - * - * Description: - * Should only be used casually, it (currently) scan the entire list - * to get the last entry. - * - * Note that the @sgl@ pointer passed in need not be the first one, - * the important bit is that @nents@ denotes the number of entries that - * exist from @sgl@. - * - **/ -static inline struct scatterlist *sg_last(struct scatterlist *sgl, - unsigned int nents) -{ -#ifndef ARCH_HAS_SG_CHAIN - struct scatterlist *ret = &sgl[nents - 1]; -#else - struct scatterlist *sg, *ret = NULL; - unsigned int i; - - for_each_sg(sgl, sg, nents, i) - ret = sg; - -#endif -#ifdef CONFIG_DEBUG_SG - BUG_ON(sgl[0].sg_magic != SG_MAGIC); - BUG_ON(!sg_is_last(ret)); -#endif - return ret; -} - /** * sg_chain - Chain two sglists together * @prv: First scatterlist @@ -222,47 +169,6 @@ static inline void sg_mark_end(struct scatterlist *sg) sg->page_link &= ~0x01; } -/** - * sg_init_table - Initialize SG table - * @sgl: The SG table - * @nents: Number of entries in table - * - * Notes: - * If this is part of a chained sg table, sg_mark_end() should be - * used only on the last table part. - * - **/ -static inline void sg_init_table(struct scatterlist *sgl, unsigned int nents) -{ - memset(sgl, 0, sizeof(*sgl) * nents); -#ifdef CONFIG_DEBUG_SG - { - unsigned int i; - for (i = 0; i < nents; i++) - sgl[i].sg_magic = SG_MAGIC; - } -#endif - sg_mark_end(&sgl[nents - 1]); -} - -/** - * sg_init_one - Initialize a single entry sg list - * @sg: SG entry - * @buf: Virtual address for IO - * @buflen: IO length - * - * Notes: - * This should not be used on a single entry that is part of a larger - * table. Use sg_init_table() for that. - * - **/ -static inline void sg_init_one(struct scatterlist *sg, const void *buf, - unsigned int buflen) -{ - sg_init_table(sg, 1); - sg_set_buf(sg, buf, buflen); -} - /** * sg_phys - Return physical address of an sg entry * @sg: SG entry @@ -293,4 +199,23 @@ static inline void *sg_virt(struct scatterlist *sg) return page_address(sg_page(sg)) + sg->offset; } +struct scatterlist *sg_next(struct scatterlist *); +struct scatterlist *sg_last(struct scatterlist *s, unsigned int); +void sg_init_table(struct scatterlist *, unsigned int); +void sg_init_one(struct scatterlist *, const void *, unsigned int); + +typedef struct scatterlist *(sg_alloc_fn)(unsigned int, gfp_t); +typedef void (sg_free_fn)(struct scatterlist *, unsigned int); + +void __sg_free_table(struct sg_table *, sg_free_fn *); +void sg_free_table(struct sg_table *); +int __sg_alloc_table(struct sg_table *, unsigned int, gfp_t, sg_alloc_fn *); +int sg_alloc_table(struct sg_table *, unsigned int, gfp_t); + +/* + * Maximum number of entries that will be allocated in one piece, if + * a list larger than this is required then chaining will be utilized. + */ +#define SG_MAX_SINGLE_ALLOC (PAGE_SIZE / sizeof(struct scatterlist)) + #endif /* _LINUX_SCATTERLIST_H */ -- cgit v1.2.3 From 336cdb4003200a90f4fc52a4e9ccc2baa570fffb Mon Sep 17 00:00:00 2001 From: Kiyoshi Ueda Date: Tue, 11 Dec 2007 17:40:30 -0500 Subject: blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda Signed-off-by: Jun'ichi Nomura Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 49b7a4c31a6d..3b212f02db8d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -537,6 +537,8 @@ enum { #define blk_fua_rq(rq) ((rq)->cmd_flags & REQ_FUA) #define blk_bidi_rq(rq) ((rq)->next_rq != NULL) #define blk_empty_barrier(rq) (blk_barrier_rq(rq) && blk_fs_request(rq) && !(rq)->hard_nr_sectors) +/* rq->queuelist of dequeued request must be list_empty() */ +#define blk_queued_rq(rq) (!list_empty(&(rq)->queuelist)) #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) @@ -724,6 +726,8 @@ static inline void blk_run_address_space(struct address_space *mapping) * for parts of the original function. This prevents * code duplication in drivers. */ +extern int blk_end_request(struct request *rq, int error, int nr_bytes); +extern int __blk_end_request(struct request *rq, int error, int nr_bytes); extern int end_that_request_first(struct request *, int, int); extern int end_that_request_chunk(struct request *, int, int); extern void end_that_request_last(struct request *, int); -- cgit v1.2.3 From 3b11313a6c2a42425bf06e92528bda6affd58dec Mon Sep 17 00:00:00 2001 From: Kiyoshi Ueda Date: Tue, 11 Dec 2007 17:41:17 -0500 Subject: blk_end_request: add/export functions to get request size (take 4) This patch adds/exports functions to get the size of request in bytes. They are useful because blk_end_request interfaces take bytes as a completed I/O size instead of sectors. Signed-off-by: Kiyoshi Ueda Signed-off-by: Jun'ichi Nomura Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3b212f02db8d..aa2341df7932 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -736,6 +736,14 @@ extern void end_queued_request(struct request *, int); extern void end_dequeued_request(struct request *, int); extern void blk_complete_request(struct request *); +/* + * blk_end_request() takes bytes instead of sectors as a complete size. + * blk_rq_bytes() returns bytes left to complete in the entire request. + * blk_rq_cur_bytes() returns bytes left to complete in the current segment. + */ +extern unsigned int blk_rq_bytes(struct request *rq); +extern unsigned int blk_rq_cur_bytes(struct request *rq); + /* * end_that_request_first/chunk() takes an uptodate argument. we account * any value <= as an io error. 0 means -EIO for compatability reasons, -- cgit v1.2.3 From e19a3ab058fe91c8c54d43dc56dccf7eb386478e Mon Sep 17 00:00:00 2001 From: Kiyoshi Ueda Date: Tue, 11 Dec 2007 17:51:02 -0500 Subject: blk_end_request: add callback feature (take 4) This patch adds a variant of the interface, blk_end_request_callback(), which has driver callback feature. Drivers may need to do special works between end_that_request_first() and end_that_request_last(). For such drivers, blk_end_request_callback() allows it to pass a callback function which is called between end_that_request_first() and end_that_request_last(). This interface is only for fallback of other blk_end_request interfaces. Drivers should avoid their tricky behaviors and use other interfaces as much as possible. Currently, only one driver, ide-cd, needs this interface. So this interface should/will be removed, after the driver removes such tricky behaviors. o ide-cd (cdrom_newpc_intr()) In PIO mode, cdrom_newpc_intr() needs to defer end_that_request_last() until the device clears DRQ_STAT and raises an interrupt after end_that_request_first(). So end_that_request_first() and end_that_request_last() are called separately in cdrom_newpc_intr(). This means blk_end_request_callback() has to return without completing request even if no leftover in the request. To satisfy the requirement, callback function has return value so that drivers can tell blk_end_request_callback() to return without completing request. Signed-off-by: Kiyoshi Ueda Signed-off-by: Jun'ichi Nomura Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index aa2341df7932..63fe7542b3fa 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -734,6 +734,8 @@ extern void end_that_request_last(struct request *, int); extern void end_request(struct request *, int); extern void end_queued_request(struct request *, int); extern void end_dequeued_request(struct request *, int); +extern int blk_end_request_callback(struct request *rq, int error, int nr_bytes, + int (drv_callback)(struct request *)); extern void blk_complete_request(struct request *); /* -- cgit v1.2.3 From e3a04fe34a3ec81ddeddb6c73fb7299716cffbb0 Mon Sep 17 00:00:00 2001 From: Kiyoshi Ueda Date: Tue, 11 Dec 2007 17:51:46 -0500 Subject: blk_end_request: add bidi completion interface (take 4) This patch adds a variant of the interface, blk_end_bidi_request(), which completes a bidi request. Bidi request must be completed as a whole, both rq and rq->next_rq at once. So the interface has 2 arguments for completion size. As for ->end_io, only rq->end_io is called (rq->next_rq->end_io is not called). So if special completion handling is needed, the handler must be set to rq->end_io. And the handler must take care of freeing next_rq too, since the interface doesn't care of it if rq->end_io is not NULL. Cc: Boaz Harrosh Signed-off-by: Kiyoshi Ueda Signed-off-by: Jun'ichi Nomura Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 63fe7542b3fa..029b7097f9e5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -728,6 +728,8 @@ static inline void blk_run_address_space(struct address_space *mapping) */ extern int blk_end_request(struct request *rq, int error, int nr_bytes); extern int __blk_end_request(struct request *rq, int error, int nr_bytes); +extern int blk_end_bidi_request(struct request *rq, int error, int nr_bytes, + int bidi_bytes); extern int end_that_request_first(struct request *, int, int); extern int end_that_request_chunk(struct request *, int, int); extern void end_that_request_last(struct request *, int); -- cgit v1.2.3 From 3bcddeac1c4c7e6fb90531b80f236b1a05dfe514 Mon Sep 17 00:00:00 2001 From: Kiyoshi Ueda Date: Tue, 11 Dec 2007 17:52:28 -0500 Subject: blk_end_request: remove/unexport end_that_request_* (take 4) This patch removes the following functions: o end_that_request_first() o end_that_request_chunk() and stops exporting the functions below: o end_that_request_last() Cc: Boaz Harrosh Signed-off-by: Kiyoshi Ueda Signed-off-by: Jun'ichi Nomura Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 029b7097f9e5..0c39ac75bed4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -718,21 +718,18 @@ static inline void blk_run_address_space(struct address_space *mapping) } /* - * end_request() and friends. Must be called with the request queue spinlock - * acquired. All functions called within end_request() _must_be_ atomic. + * blk_end_request() and friends. + * __blk_end_request() and end_request() must be called with + * the request queue spinlock acquired. * * Several drivers define their own end_request and call - * end_that_request_first() and end_that_request_last() - * for parts of the original function. This prevents - * code duplication in drivers. + * blk_end_request() for parts of the original function. + * This prevents code duplication in drivers. */ extern int blk_end_request(struct request *rq, int error, int nr_bytes); extern int __blk_end_request(struct request *rq, int error, int nr_bytes); extern int blk_end_bidi_request(struct request *rq, int error, int nr_bytes, int bidi_bytes); -extern int end_that_request_first(struct request *, int, int); -extern int end_that_request_chunk(struct request *, int, int); -extern void end_that_request_last(struct request *, int); extern void end_request(struct request *, int); extern void end_queued_request(struct request *, int); extern void end_dequeued_request(struct request *, int); -- cgit v1.2.3 From 5450d3e1d68f10be087f0855d8bad5458b50ecbe Mon Sep 17 00:00:00 2001 From: Kiyoshi Ueda Date: Tue, 11 Dec 2007 17:53:03 -0500 Subject: blk_end_request: cleanup 'uptodate' related code (take 4) This patch converts 'uptodate' arguments of no longer exported interfaces, end_that_request_first/last, to 'error', and removes internal conversions for it in blk_end_request interfaces. Also, this patch removes no longer needed end_io_error(). Cc: Boaz Harrosh Signed-off-by: Kiyoshi Ueda Signed-off-by: Jun'ichi Nomura Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0c39ac75bed4..0ea82d222046 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -745,14 +745,6 @@ extern void blk_complete_request(struct request *); extern unsigned int blk_rq_bytes(struct request *rq); extern unsigned int blk_rq_cur_bytes(struct request *rq); -/* - * end_that_request_first/chunk() takes an uptodate argument. we account - * any value <= as an io error. 0 means -EIO for compatability reasons, - * any other < 0 value is the direct error type. An uptodate value of - * 1 indicates successful io completion - */ -#define end_io_error(uptodate) (unlikely((uptodate) <= 0)) - static inline void blkdev_dequeue_request(struct request *req) { elv_dequeue_request(req->q, req); -- cgit v1.2.3 From fd0928df98b9578be8a786ac0cb78a47a5e17a20 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 24 Jan 2008 08:52:45 +0100 Subject: ioprio: move io priority from task_struct to io_context This is where it belongs and then it doesn't take up space for a process that doesn't do IO. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 81 ++++------------------------------------------- include/linux/init_task.h | 1 - include/linux/iocontext.h | 79 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/ioprio.h | 13 ++++---- include/linux/sched.h | 1 - 5 files changed, 93 insertions(+), 82 deletions(-) create mode 100644 include/linux/iocontext.h (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 49b7a4c31a6d..510a18ba1ec5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -34,83 +34,10 @@ struct sg_io_hdr; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ -/* - * This is the per-process anticipatory I/O scheduler state. - */ -struct as_io_context { - spinlock_t lock; - - void (*dtor)(struct as_io_context *aic); /* destructor */ - void (*exit)(struct as_io_context *aic); /* called on task exit */ - - unsigned long state; - atomic_t nr_queued; /* queued reads & sync writes */ - atomic_t nr_dispatched; /* number of requests gone to the drivers */ - - /* IO History tracking */ - /* Thinktime */ - unsigned long last_end_request; - unsigned long ttime_total; - unsigned long ttime_samples; - unsigned long ttime_mean; - /* Layout pattern */ - unsigned int seek_samples; - sector_t last_request_pos; - u64 seek_total; - sector_t seek_mean; -}; - -struct cfq_queue; -struct cfq_io_context { - struct rb_node rb_node; - void *key; - - struct cfq_queue *cfqq[2]; - - struct io_context *ioc; - - unsigned long last_end_request; - sector_t last_request_pos; - - unsigned long ttime_total; - unsigned long ttime_samples; - unsigned long ttime_mean; - - unsigned int seek_samples; - u64 seek_total; - sector_t seek_mean; - - struct list_head queue_list; - - void (*dtor)(struct io_context *); /* destructor */ - void (*exit)(struct io_context *); /* called on task exit */ -}; - -/* - * This is the per-process I/O subsystem state. It is refcounted and - * kmalloc'ed. Currently all fields are modified in process io context - * (apart from the atomic refcount), so require no locking. - */ -struct io_context { - atomic_t refcount; - struct task_struct *task; - - unsigned int ioprio_changed; - - /* - * For request batching - */ - unsigned long last_waited; /* Time last woken after wait for request */ - int nr_batch_requests; /* Number of requests left in the batch */ - - struct as_io_context *aic; - struct rb_root cic_root; - void *ioc_data; -}; - void put_io_context(struct io_context *ioc); void exit_io_context(void); struct io_context *get_io_context(gfp_t gfp_flags, int node); +struct io_context *alloc_io_context(gfp_t gfp_flags, int node); void copy_io_context(struct io_context **pdst, struct io_context **psrc); void swap_io_context(struct io_context **ioc1, struct io_context **ioc2); @@ -894,6 +821,12 @@ static inline void exit_io_context(void) { } +static inline int put_io_context(struct io_context *ioc) +{ + return 1; +} + + #endif /* CONFIG_BLOCK */ #endif diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 796019b22b6f..e6b3f7080679 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -137,7 +137,6 @@ extern struct group_info init_groups; .time_slice = HZ, \ .nr_cpus_allowed = NR_CPUS, \ }, \ - .ioprio = 0, \ .tasks = LIST_HEAD_INIT(tsk.tasks), \ .ptrace_children= LIST_HEAD_INIT(tsk.ptrace_children), \ .ptrace_list = LIST_HEAD_INIT(tsk.ptrace_list), \ diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h new file mode 100644 index 000000000000..186807ea62e2 --- /dev/null +++ b/include/linux/iocontext.h @@ -0,0 +1,79 @@ +#ifndef IOCONTEXT_H +#define IOCONTEXT_H + +/* + * This is the per-process anticipatory I/O scheduler state. + */ +struct as_io_context { + spinlock_t lock; + + void (*dtor)(struct as_io_context *aic); /* destructor */ + void (*exit)(struct as_io_context *aic); /* called on task exit */ + + unsigned long state; + atomic_t nr_queued; /* queued reads & sync writes */ + atomic_t nr_dispatched; /* number of requests gone to the drivers */ + + /* IO History tracking */ + /* Thinktime */ + unsigned long last_end_request; + unsigned long ttime_total; + unsigned long ttime_samples; + unsigned long ttime_mean; + /* Layout pattern */ + unsigned int seek_samples; + sector_t last_request_pos; + u64 seek_total; + sector_t seek_mean; +}; + +struct cfq_queue; +struct cfq_io_context { + struct rb_node rb_node; + void *key; + + struct cfq_queue *cfqq[2]; + + struct io_context *ioc; + + unsigned long last_end_request; + sector_t last_request_pos; + + unsigned long ttime_total; + unsigned long ttime_samples; + unsigned long ttime_mean; + + unsigned int seek_samples; + u64 seek_total; + sector_t seek_mean; + + struct list_head queue_list; + + void (*dtor)(struct io_context *); /* destructor */ + void (*exit)(struct io_context *); /* called on task exit */ +}; + +/* + * This is the per-process I/O subsystem state. It is refcounted and + * kmalloc'ed. Currently all fields are modified in process io context + * (apart from the atomic refcount), so require no locking. + */ +struct io_context { + atomic_t refcount; + struct task_struct *task; + + unsigned short ioprio; + unsigned short ioprio_changed; + + /* + * For request batching + */ + unsigned long last_waited; /* Time last woken after wait for request */ + int nr_batch_requests; /* Number of requests left in the batch */ + + struct as_io_context *aic; + struct rb_root cic_root; + void *ioc_data; +}; + +#endif diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index baf29387cab4..2a3bb1bb7433 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -2,6 +2,7 @@ #define IOPRIO_H #include +#include /* * Gives us 8 prio classes with 13-bits of data for each class @@ -45,18 +46,18 @@ enum { * the cpu scheduler nice value to an io priority */ #define IOPRIO_NORM (4) -static inline int task_ioprio(struct task_struct *task) +static inline int task_ioprio(struct io_context *ioc) { - if (ioprio_valid(task->ioprio)) - return IOPRIO_PRIO_DATA(task->ioprio); + if (ioprio_valid(ioc->ioprio)) + return IOPRIO_PRIO_DATA(ioc->ioprio); return IOPRIO_NORM; } -static inline int task_ioprio_class(struct task_struct *task) +static inline int task_ioprio_class(struct io_context *ioc) { - if (ioprio_valid(task->ioprio)) - return IOPRIO_PRIO_CLASS(task->ioprio); + if (ioprio_valid(ioc->ioprio)) + return IOPRIO_PRIO_CLASS(ioc->ioprio); return IOPRIO_CLASS_BE; } diff --git a/include/linux/sched.h b/include/linux/sched.h index df5b24ee80b3..80837e7d527e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -975,7 +975,6 @@ struct task_struct { struct hlist_head preempt_notifiers; #endif - unsigned short ioprio; /* * fpu_counter contains the number of consecutive context switches * that the FPU is used. If this is over a threshold, the lazy fpu -- cgit v1.2.3 From d38ecf935fcb10264a6bc190855d9595165e6eeb Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 24 Jan 2008 08:53:35 +0100 Subject: io context sharing: preliminary support Detach task state from ioc, instead keep track of how many processes are accessing the ioc. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- include/linux/iocontext.h | 22 ++++++++++++++++++---- 2 files changed, 19 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 510a18ba1ec5..2483a05231c7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -34,7 +34,7 @@ struct sg_io_hdr; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ -void put_io_context(struct io_context *ioc); +int put_io_context(struct io_context *ioc); void exit_io_context(void); struct io_context *get_io_context(gfp_t gfp_flags, int node); struct io_context *alloc_io_context(gfp_t gfp_flags, int node); diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index 186807ea62e2..cd44d458124a 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -54,13 +54,15 @@ struct cfq_io_context { }; /* - * This is the per-process I/O subsystem state. It is refcounted and - * kmalloc'ed. Currently all fields are modified in process io context - * (apart from the atomic refcount), so require no locking. + * I/O subsystem state of the associated processes. It is refcounted + * and kmalloc'ed. These could be shared between processes. */ struct io_context { atomic_t refcount; - struct task_struct *task; + atomic_t nr_tasks; + + /* all the fields below are protected by this lock */ + spinlock_t lock; unsigned short ioprio; unsigned short ioprio_changed; @@ -76,4 +78,16 @@ struct io_context { void *ioc_data; }; +static inline struct io_context *ioc_task_link(struct io_context *ioc) +{ + /* + * if ref count is zero, don't allow sharing (ioc is going away, it's + * a race). + */ + if (ioc && atomic_inc_not_zero(&ioc->refcount)) + return ioc; + + return NULL; +} + #endif -- cgit v1.2.3 From 4ac845a2e9a816ed5a7b301f56dcc0a3d0b1ba4d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 24 Jan 2008 08:44:49 +0100 Subject: block: cfq: make the io contect sharing lockless The io context sharing introduced a per-ioc spinlock, that would protect the cfq io context lookup. That is a regression from the original, since we never needed any locking there because the ioc/cic were process private. The cic lookup is changed from an rbtree construct to a radix tree, which we can then use RCU to make the reader side lockless. That is the performance critical path, modifying the radix tree is only done on process creation (when that process first does IO, actually) and on process exit (if that process has done IO). As it so happens, radix trees are also much faster for this type of lookup where the key is a pointer. It's a very sparse tree. Signed-off-by: Jens Axboe --- include/linux/iocontext.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index cd44d458124a..593b222d9dcc 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -1,6 +1,8 @@ #ifndef IOCONTEXT_H #define IOCONTEXT_H +#include + /* * This is the per-process anticipatory I/O scheduler state. */ @@ -29,8 +31,8 @@ struct as_io_context { struct cfq_queue; struct cfq_io_context { - struct rb_node rb_node; void *key; + unsigned long dead_key; struct cfq_queue *cfqq[2]; @@ -74,7 +76,7 @@ struct io_context { int nr_batch_requests; /* Number of requests left in the batch */ struct as_io_context *aic; - struct rb_root cic_root; + struct radix_tree_root radix_root; void *ioc_data; }; -- cgit v1.2.3 From fadad878cc0640cc9cd5569998bf54b693f7b38b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 24 Jan 2008 08:54:47 +0100 Subject: kernel: add CLONE_IO to specifically request sharing of IO contexts syslets (or other threads/processes that want io context sharing) can set this to enforce sharing of io context. Signed-off-by: Jens Axboe --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 80837e7d527e..2d0546e884ea 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -27,6 +27,7 @@ #define CLONE_NEWUSER 0x10000000 /* New user namespace */ #define CLONE_NEWPID 0x20000000 /* New pid namespace */ #define CLONE_NEWNET 0x40000000 /* New network namespace */ +#define CLONE_IO 0x80000000 /* Clone io context */ /* * Scheduling policies -- cgit v1.2.3 From fa0ccd837e3dddb44c7db2f128a8bb7e4eabc21a Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Thu, 10 Jan 2008 11:30:36 -0600 Subject: block: implement drain buffers These DMA drain buffer implementations in drivers are pretty horrible to do in terms of manipulating the scatterlist. Plus they're being done at least in drivers/ide and drivers/ata, so we now have code duplication. The one use case for this, as I understand it is AHCI controllers doing PIO mode to mmc devices but translating this to DMA at the controller level. So, what about adding a callback to the block layer that permits the adding of the drain buffer for the problem devices. The idea is that you'd do this in slave_configure after you find one of these devices. The beauty of doing it in the block layer is that it quietly adds the drain buffer to the end of the sg list, so it automatically gets mapped (and unmapped) without anything unusual having to be done to the scatterlist in driver/scsi or drivers/ata and without any alteration to the transfer length. Signed-off-by: James Bottomley Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c7a3ab575c24..e542c8fd9215 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -429,6 +429,8 @@ struct request_queue unsigned int max_segment_size; unsigned long seg_boundary_mask; + void *dma_drain_buffer; + unsigned int dma_drain_size; unsigned int dma_alignment; struct blk_queue_tag *queue_tags; @@ -760,6 +762,8 @@ extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_hardsect_size(struct request_queue *, unsigned short); extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b); +extern int blk_queue_dma_drain(struct request_queue *q, void *buf, + unsigned int size); extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_prep_rq(struct request_queue *, prep_rq_fn *pfn); extern void blk_queue_merge_bvec(struct request_queue *, merge_bvec_fn *); -- cgit v1.2.3 From 7cedb1f17fb7f4374d11501f61656ae9d3ba47e9 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Sun, 13 Jan 2008 14:15:28 -0600 Subject: SG: work with the SCSI fixed maximum allocations. SCSI sg table allocation has a maximum size (of SCSI_MAX_SG_SEGMENTS, currently 128) and this will cause a BUG_ON() in SCSI if something tries an allocation over it. This patch adds a size limit to the chaining allocator to allow the specification of the maximum allocation size for chaining, so we always chain in units of the maximum SCSI allocation size. Signed-off-by: James Bottomley Signed-off-by: Jens Axboe --- include/linux/scatterlist.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index e9cb103417b2..a3d567a974e8 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -207,9 +207,10 @@ void sg_init_one(struct scatterlist *, const void *, unsigned int); typedef struct scatterlist *(sg_alloc_fn)(unsigned int, gfp_t); typedef void (sg_free_fn)(struct scatterlist *, unsigned int); -void __sg_free_table(struct sg_table *, sg_free_fn *); +void __sg_free_table(struct sg_table *, unsigned int, sg_free_fn *); void sg_free_table(struct sg_table *); -int __sg_alloc_table(struct sg_table *, unsigned int, gfp_t, sg_alloc_fn *); +int __sg_alloc_table(struct sg_table *, unsigned int, unsigned int, gfp_t, + sg_alloc_fn *); int sg_alloc_table(struct sg_table *, unsigned int, gfp_t); /* -- cgit v1.2.3 From 81e1a875505f2963f4d22f7e7ade39d764755f9b Mon Sep 17 00:00:00 2001 From: Michel Daenzer Date: Wed, 24 Oct 2007 16:30:34 +0200 Subject: HID: Rename some code identifiers from PowerBook specific to Apple generic Preserve identifiers exposed in build and run time configuration though in order not to break existing configurations. This is in preparation for adding support for Apple aluminum USB keyboards. Signed-off-by: Michel Daenzer Signed-off-by: Jiri Kosina --- include/linux/hid.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 6e35b92b1d2c..833f2af8aab9 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -267,10 +267,10 @@ struct hid_item { #define HID_QUIRK_2WHEEL_MOUSE_HACK_5 0x00000100 #define HID_QUIRK_2WHEEL_MOUSE_HACK_ON 0x00000200 #define HID_QUIRK_MIGHTYMOUSE 0x00000400 -#define HID_QUIRK_POWERBOOK_HAS_FN 0x00000800 -#define HID_QUIRK_POWERBOOK_FN_ON 0x00001000 +#define HID_QUIRK_APPLE_HAS_FN 0x00000800 +#define HID_QUIRK_APPLE_FN_ON 0x00001000 #define HID_QUIRK_INVERT_HWHEEL 0x00002000 -#define HID_QUIRK_POWERBOOK_ISO_KEYBOARD 0x00004000 +#define HID_QUIRK_APPLE_ISO_KEYBOARD 0x00004000 #define HID_QUIRK_BAD_RELATIVE_KEYS 0x00008000 #define HID_QUIRK_SKIP_OUTPUT_REPORTS 0x00010000 #define HID_QUIRK_IGNORE_MOUSE 0x00020000 @@ -469,7 +469,7 @@ struct hid_device { /* device report descriptor */ /* handler for raw output data, used by hidraw */ int (*hid_output_raw_report) (struct hid_device *, __u8 *, size_t); #ifdef CONFIG_USB_HIDINPUT_POWERBOOK - unsigned long pb_pressed_fn[BITS_TO_LONGS(KEY_CNT)]; + unsigned long apple_pressed_fn[BITS_TO_LONGS(KEY_CNT)]; unsigned long pb_pressed_numlock[BITS_TO_LONGS(KEY_CNT)]; #endif }; -- cgit v1.2.3 From c80e5ffac0579499ca28444155118ffcdd9b8d7e Mon Sep 17 00:00:00 2001 From: Pavel Troller Date: Mon, 29 Oct 2007 11:13:46 +0100 Subject: HID: Implement horizontal wheel handling for A4 Tech X5-005D This mouse distinguishes horizontal wheel from vertical by a special "pseudo event" GenericDesktop.00b8, with values of 0 for vertical and 8 for horizontal wheel. Because this event is supplied by the parser too late, we need to delay a wheel event, wait for this one and send either REL_WHEEL or REL_HWHEEL to input depending on the event value. Signed-off-by: Pavel Troller Signed-off-by: Jiri Kosina --- include/linux/hid.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 833f2af8aab9..991bbcdc1ca7 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -281,6 +281,7 @@ struct hid_item { #define HID_QUIRK_LOGITECH_IGNORE_DOUBLED_WHEEL 0x00400000 #define HID_QUIRK_LOGITECH_EXPANDED_KEYMAP 0x00800000 #define HID_QUIRK_IGNORE_HIDINPUT 0x01000000 +#define HID_QUIRK_2WHEEL_MOUSE_HACK_B8 0x02000000 /* * Separate quirks for runtime report descriptor fixup @@ -456,6 +457,8 @@ struct hid_device { /* device report descriptor */ void *driver_data; + __s32 delayed_value; /* For A4 Tech mice hwheel quirk */ + /* device-specific function pointers */ int (*hidinput_input_event) (struct input_dev *, unsigned int, unsigned int, int); int (*hid_open) (struct hid_device *); -- cgit v1.2.3 From af9e0eacdc072ba28fd139b90de27023d9cb0598 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Wed, 14 Nov 2007 12:13:26 +0100 Subject: HID: add full support for Genius KB-29E Genius KB-29E has broken report descriptor, which causes some of the Consumer usages to appear incorrectly as Button usages. We fix it by fixing the report descriptor before it is being parsed. Also a few of the keys violate the HUT standard, so they need a special handling. They currently fall into "Reserved" range as per HUT 1.12. Reported-by: Szekeres Istvan Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 991bbcdc1ca7..c67eeb516040 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -292,6 +292,7 @@ struct hid_item { #define HID_QUIRK_RDESC_SWAPPED_MIN_MAX 0x00000004 #define HID_QUIRK_RDESC_PETALYNX 0x00000008 #define HID_QUIRK_RDESC_MACBOOK_JIS 0x00000010 +#define HID_QUIRK_RDESC_BUTTON_CONSUMER 0x00000020 /* * This is the global environment of the parser. This information is -- cgit v1.2.3 From 10bd065facb2594bd508597ef464d401b212f379 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Thu, 22 Nov 2007 15:18:18 +0100 Subject: HID: refactor mapping to input subsystem for quirky devices Currently, the handling of mapping between hid and input for devices that don't conform to HUT 1.12 specification is very messy -- no per-device handling, no blacklists, conditions on idVendor and idProduct placed all over the code. This patch moves all the device-specific input mapping to a separate file, and introduces a blacklist-style handling for non-standard device-specific mappings. Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index c67eeb516040..cd5d562b1b7c 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -524,6 +524,7 @@ extern void hidinput_disconnect(struct hid_device *); int hid_set_field(struct hid_field *, unsigned, __s32); int hid_input_report(struct hid_device *, int type, u8 *, int, int); int hidinput_find_field(struct hid_device *hid, unsigned int type, unsigned int code, struct hid_field **field); +int hidinput_mapping_quirks(struct hid_usage *, struct input_dev *, unsigned long *, int *); void hid_input_field(struct hid_device *hid, struct hid_field *field, __u8 *data, int interrupt); void hid_output_report(struct hid_report *report, __u8 *data); void hid_free_device(struct hid_device *device); -- cgit v1.2.3 From 87bc2aa9933afc032a93490e1642918121e7470b Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Fri, 23 Nov 2007 13:16:02 +0100 Subject: HID: separate hid-input event quirks from generic code This patch separates also the hid-input quirks that have to be applied at the time the event occurs, so that the generic code handling HUT-compliant devices is not messed up by them too much. Signed-off-by: Jiri Kosina --- include/linux/hid.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index cd5d562b1b7c..dca5804836f3 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -525,6 +525,8 @@ int hid_set_field(struct hid_field *, unsigned, __s32); int hid_input_report(struct hid_device *, int type, u8 *, int, int); int hidinput_find_field(struct hid_device *hid, unsigned int type, unsigned int code, struct hid_field **field); int hidinput_mapping_quirks(struct hid_usage *, struct input_dev *, unsigned long *, int *); +void hidinput_event_quirks(struct hid_device *, struct hid_field *, struct hid_usage *, __s32); +int hidinput_apple_event(struct hid_device *, struct input_dev *, struct hid_usage *, __s32); void hid_input_field(struct hid_device *hid, struct hid_field *field, __u8 *data, int interrupt); void hid_output_report(struct hid_report *report, __u8 *data); void hid_free_device(struct hid_device *device); -- cgit v1.2.3 From 36ccaad640737899b069a9a93a82765f0e675a20 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Mon, 26 Nov 2007 13:18:00 +0100 Subject: HID: hid-input quirk for BTC 8193 BTC 8193 keyboard handles its scrollwheel in very non-standard way. It produces two non-standard usages for scrolling up and down, in both cases with postive value equaling to 1. We handle this by temporary mapping, which we then catch in quirk event handler, and remap to negative HWHEEL even in order to introduce correct behavior. Also the button requires special mapping, as it triggers standard-violating usage code. Reported in kernel.org bugzilla #9385 Reported-by: Kir Kolyshkin Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index dca5804836f3..33ec33389b37 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -282,6 +282,7 @@ struct hid_item { #define HID_QUIRK_LOGITECH_EXPANDED_KEYMAP 0x00800000 #define HID_QUIRK_IGNORE_HIDINPUT 0x01000000 #define HID_QUIRK_2WHEEL_MOUSE_HACK_B8 0x02000000 +#define HID_QUIRK_HWHEEL_WHEEL_INVERT 0x04000000 /* * Separate quirks for runtime report descriptor fixup -- cgit v1.2.3 From 628edcde87592a7ac6e72b555bb03ea265bcfbd2 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Mon, 26 Nov 2007 13:26:33 +0100 Subject: HID: proper handling of MS 4k and 6k devices This removes ugly macros IS_* to distinguish devices that need special handling in hid-input, and establish proper quirks for them. Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 33ec33389b37..24f04cd742de 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -283,6 +283,7 @@ struct hid_item { #define HID_QUIRK_IGNORE_HIDINPUT 0x01000000 #define HID_QUIRK_2WHEEL_MOUSE_HACK_B8 0x02000000 #define HID_QUIRK_HWHEEL_WHEEL_INVERT 0x04000000 +#define HID_QUIRK_MICROSOFT_KEYS 0x08000000 /* * Separate quirks for runtime report descriptor fixup -- cgit v1.2.3 From 70d215c4a7dfbddc138a2dd726d8f80f3e6d2622 Mon Sep 17 00:00:00 2001 From: Fengguang Wu Date: Fri, 7 Dec 2007 16:35:14 +0800 Subject: HID: the `bit' in hidinput_mapping_quirks() is an out parameter Fix a panic, by changing hidinput_mapping_quirks(,, unsigned long *bit,) to hidinput_mapping_quirks(,, unsigned long **bit,) The `bit' in this function is an out parameter. Signed-off-by: Fengguang Wu Signed-off-by: Andrew Morton Signed-off-by: Jiri Kosina --- include/linux/hid.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 24f04cd742de..6a70b788ee9c 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -526,7 +526,7 @@ extern void hidinput_disconnect(struct hid_device *); int hid_set_field(struct hid_field *, unsigned, __s32); int hid_input_report(struct hid_device *, int type, u8 *, int, int); int hidinput_find_field(struct hid_device *hid, unsigned int type, unsigned int code, struct hid_field **field); -int hidinput_mapping_quirks(struct hid_usage *, struct input_dev *, unsigned long *, int *); +int hidinput_mapping_quirks(struct hid_usage *, struct input_dev *, unsigned long **, int *); void hidinput_event_quirks(struct hid_device *, struct hid_field *, struct hid_usage *, __s32); int hidinput_apple_event(struct hid_device *, struct input_dev *, struct hid_usage *, __s32); void hid_input_field(struct hid_device *hid, struct hid_field *field, __u8 *data, int interrupt); -- cgit v1.2.3 From fe56caa97e626cc6d6e18adbd5ccd1a9aa9a4fcf Mon Sep 17 00:00:00 2001 From: Robert Schedel Date: Wed, 26 Dec 2007 00:57:40 +0100 Subject: HID: Support Samsung IR remote Samsung USB remotes (0419:0001) are rejected by kernel 2.6.23, because the report descriptor from the remote contains a 48 bit HID report field. HID 1.11 states: Fields may span at most 4 bytes. This patch, based on 2.6.23, fixes this by modifying the internal report descriptor in hid-quirks.c. Additional user space support (e.g. LIRC) is required to fetch the information from the hiddev interface. The burden to reconstruct the data is moved into userspace (lirc through hiddev). There is no need to set HID_QUIRK_HIDDEV quirk, as the device has also output applications, which trigger the creation of hiddev device automatically. Signed-off-by: Robert Schedel Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 6a70b788ee9c..3902690647b0 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -295,6 +295,7 @@ struct hid_item { #define HID_QUIRK_RDESC_PETALYNX 0x00000008 #define HID_QUIRK_RDESC_MACBOOK_JIS 0x00000010 #define HID_QUIRK_RDESC_BUTTON_CONSUMER 0x00000020 +#define HID_QUIRK_RDESC_SAMSUNG_REMOTE 0x00000040 /* * This is the global environment of the parser. This information is -- cgit v1.2.3 From 7998a731664ac4988b349e70669bac11e3b3a3ac Mon Sep 17 00:00:00 2001 From: "Robert P. J. Day" Date: Mon, 31 Dec 2007 14:58:38 +0100 Subject: A few corrections to include/linux/Kbuild auxvec.h, i2c-dev.h and vt.h *should* be unifdef'ed i2o-dev.h does not need unifdef'ing Signed-off-by: Robert P. J. Day Cc: David Woodhouse Signed-off-by: Andrew Morton Signed-off-by: Sam Ravnborg --- include/linux/Kbuild | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index bd694f779346..ad99ce9f9169 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -34,7 +34,6 @@ header-y += atmsap.h header-y += atmsvc.h header-y += atm_zatm.h header-y += auto_fs4.h -header-y += auxvec.h header-y += ax25.h header-y += b1lli.h header-y += baycom.h @@ -73,7 +72,7 @@ header-y += gen_stats.h header-y += gigaset_dev.h header-y += hdsmart.h header-y += hysdn_if.h -header-y += i2c-dev.h +header-y += i2o-dev.h header-y += i8k.h header-y += if_arcnet.h header-y += if_bonding.h @@ -158,7 +157,6 @@ header-y += veth.h header-y += video_decoder.h header-y += video_encoder.h header-y += videotext.h -header-y += vt.h header-y += x25.h unifdef-y += acct.h @@ -173,6 +171,7 @@ unifdef-y += atm.h unifdef-y += atm_tcp.h unifdef-y += audit.h unifdef-y += auto_fs.h +unifdef-y += auxvec.h unifdef-y += binfmts.h unifdef-y += capability.h unifdef-y += capi.h @@ -214,7 +213,7 @@ unifdef-y += hdreg.h unifdef-y += hiddev.h unifdef-y += hpet.h unifdef-y += i2c.h -unifdef-y += i2o-dev.h +unifdef-y += i2c-dev.h unifdef-y += icmp.h unifdef-y += icmpv6.h unifdef-y += if_addr.h @@ -349,6 +348,7 @@ unifdef-y += videodev.h unifdef-y += virtio_config.h unifdef-y += virtio_blk.h unifdef-y += virtio_net.h +unifdef-y += vt.h unifdef-y += wait.h unifdef-y += wanrouter.h unifdef-y += watchdog.h -- cgit v1.2.3 From f3fe866d59d707c7a2bba0b23add078e19edb3dc Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 20 Jan 2008 18:54:48 +0100 Subject: compiler.h: introduce __section() Add a new helper: __section() that makes a section definition much shorter and more readable. Signed-off-by: Sam Ravnborg --- include/linux/compiler.h | 5 +++++ include/linux/init.h | 26 +++++++++++++------------- 2 files changed, 18 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index c68b67b86ef1..e0114a61268f 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -175,4 +175,9 @@ extern void __chk_io_ptr(const volatile void __iomem *); #define __cold #endif +/* Simple shorthand for a section definition */ +#ifndef __section +# define __section(S) __attribute__ ((__section__(#S))) +#endif + #endif /* __LINUX_COMPILER_H */ diff --git a/include/linux/init.h b/include/linux/init.h index 5141381a7527..998076818402 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -40,10 +40,10 @@ /* These are for everybody (although not all archs will actually discard it in modules) */ -#define __init __attribute__ ((__section__ (".init.text"))) __cold -#define __initdata __attribute__ ((__section__ (".init.data"))) -#define __exitdata __attribute__ ((__section__(".exit.data"))) -#define __exit_call __attribute_used__ __attribute__ ((__section__ (".exitcall.exit"))) +#define __init __section(.init.text) __cold +#define __initdata __section(.init.data) +#define __exitdata __section(.exit.data) +#define __exit_call __attribute_used__ __section(.exitcall.exit) /* modpost check for section mismatches during the kernel build. * A section mismatch happens when there are references from a @@ -55,14 +55,14 @@ * the init/exit section (code or data) is valid and will teach modpost * not to issue a warning. * The markers follow same syntax rules as __init / __initdata. */ -#define __init_refok noinline __attribute__ ((__section__ (".text.init.refok"))) -#define __initdata_refok __attribute__ ((__section__ (".data.init.refok"))) -#define __exit_refok noinline __attribute__ ((__section__ (".exit.text.refok"))) +#define __init_refok noinline __section(.text.init.refok) +#define __initdata_refok __section(.data.init.refok) +#define __exit_refok noinline __section(.exit.text.refok) #ifdef MODULE -#define __exit __attribute__ ((__section__(".exit.text"))) __cold +#define __exit __section(.exit.text) __cold #else -#define __exit __attribute_used__ __attribute__ ((__section__(".exit.text"))) __cold +#define __exit __attribute_used__ __section(.exit.text) __cold #endif /* For assembly routines */ @@ -142,11 +142,11 @@ void prepare_namespace(void); #define console_initcall(fn) \ static initcall_t __initcall_##fn \ - __attribute_used__ __attribute__((__section__(".con_initcall.init")))=fn + __attribute_used__ __section(.con_initcall.init)=fn #define security_initcall(fn) \ static initcall_t __initcall_##fn \ - __attribute_used__ __attribute__((__section__(".security_initcall.init"))) = fn + __attribute_used__ __section(.security_initcall.init) = fn struct obs_kernel_param { const char *str; @@ -164,7 +164,7 @@ struct obs_kernel_param { static char __setup_str_##unique_id[] __initdata __aligned(1) = str; \ static struct obs_kernel_param __setup_##unique_id \ __attribute_used__ \ - __attribute__((__section__(".init.setup"))) \ + __section(.init.setup) \ __attribute__((aligned((sizeof(long))))) \ = { __setup_str_##unique_id, fn, early } @@ -242,7 +242,7 @@ void __init parse_early_param(void); #endif /* Data marked not to be saved by software suspend */ -#define __nosavedata __attribute__ ((__section__ (".data.nosave"))) +#define __nosavedata __section(.data.nosave) /* This means "can be init if no module support, otherwise module load may call it." */ -- cgit v1.2.3 From eb8f689046b857874e964463619f09df06d59fad Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sun, 20 Jan 2008 20:07:28 +0100 Subject: Use separate sections for __dev/__cpu/__mem code/data Introducing separate sections for __dev* (HOTPLUG), __cpu* (HOTPLUG_CPU) and __mem* (MEMORY_HOTPLUG) allows us to do a much more reliable Section mismatch check in modpost. We are no longer dependent on the actual configuration of for example HOTPLUG. This has the effect that all users see much more Section mismatch warnings than before because they were almost all hidden when HOTPLUG was enabled. The advantage of this is that when building a piece of code then it is much more likely that the Section mismatch errors are spotted and the warnings will be felt less random of nature. Signed-off-by: Sam Ravnborg Cc: Greg KH Cc: Randy Dunlap Cc: Adrian Bunk --- include/linux/init.h | 77 ++++++++++++++++++++++++++-------------------------- 1 file changed, 38 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index 998076818402..dcb66c76bd48 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -60,18 +60,54 @@ #define __exit_refok noinline __section(.exit.text.refok) #ifdef MODULE -#define __exit __section(.exit.text) __cold +#define __exitused #else -#define __exit __attribute_used__ __section(.exit.text) __cold +#define __exitused __used #endif +#define __exit __section(.exit.text) __exitused __cold + +/* Used for HOTPLUG */ +#define __devinit __section(.devinit.text) __cold +#define __devinitdata __section(.devinit.data) +#define __devinitconst __section(.devinit.rodata) +#define __devexit __section(.devexit.text) __exitused __cold +#define __devexitdata __section(.devexit.data) +#define __devexitconst __section(.devexit.rodata) + +/* Used for HOTPLUG_CPU */ +#define __cpuinit __section(.cpuinit.text) __cold +#define __cpuinitdata __section(.cpuinit.data) +#define __cpuinitconst __section(.cpuinit.rodata) +#define __cpuexit __section(.cpuexit.text) __exitused __cold +#define __cpuexitdata __section(.cpuexit.data) +#define __cpuexitconst __section(.cpuexit.rodata) + +/* Used for MEMORY_HOTPLUG */ +#define __meminit __section(.meminit.text) __cold +#define __meminitdata __section(.meminit.data) +#define __meminitconst __section(.meminit.rodata) +#define __memexit __section(.memexit.text) __exitused __cold +#define __memexitdata __section(.memexit.data) +#define __memexitconst __section(.memexit.rodata) + /* For assembly routines */ #define __INIT .section ".init.text","ax" #define __INIT_REFOK .section ".text.init.refok","ax" #define __FINIT .previous + #define __INITDATA .section ".init.data","aw" #define __INITDATA_REFOK .section ".data.init.refok","aw" +#define __DEVINIT .section ".devinit.text", "ax" +#define __DEVINITDATA .section ".devinit.data", "aw" + +#define __CPUINIT .section ".cpuinit.text", "ax" +#define __CPUINITDATA .section ".cpuinit.data", "aw" + +#define __MEMINIT .section ".meminit.text", "ax" +#define __MEMINITDATA .section ".meminit.data", "aw" + #ifndef __ASSEMBLY__ /* * Used for initialization calls.. @@ -254,43 +290,6 @@ void __init parse_early_param(void); #define __initdata_or_module __initdata #endif /*CONFIG_MODULES*/ -#ifdef CONFIG_HOTPLUG -#define __devinit -#define __devinitdata -#define __devexit -#define __devexitdata -#else -#define __devinit __init -#define __devinitdata __initdata -#define __devexit __exit -#define __devexitdata __exitdata -#endif - -#ifdef CONFIG_HOTPLUG_CPU -#define __cpuinit -#define __cpuinitdata -#define __cpuexit -#define __cpuexitdata -#else -#define __cpuinit __init -#define __cpuinitdata __initdata -#define __cpuexit __exit -#define __cpuexitdata __exitdata -#endif - -#if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_ACPI_HOTPLUG_MEMORY) \ - || defined(CONFIG_ACPI_HOTPLUG_MEMORY_MODULE) -#define __meminit -#define __meminitdata -#define __memexit -#define __memexitdata -#else -#define __meminit __init -#define __meminitdata __initdata -#define __memexit __exit -#define __memexitdata __exitdata -#endif - /* Functions marked as __devexit may be discarded at kernel link time, depending on config options. Newer versions of binutils detect references from retained sections to discarded sections and flag an error. Pointers to -- cgit v1.2.3 From 3ff6eecca4e5c49a5d1dd8b58ea0e20102ce08f0 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Thu, 24 Jan 2008 22:16:20 +0100 Subject: remove __attribute_used__ Remove the deprecated __attribute_used__. [Introduce __section in a few places to silence checkpatch /sam] Signed-off-by: Adrian Bunk Signed-off-by: Sam Ravnborg --- include/linux/compiler-gcc3.h | 2 -- include/linux/compiler-gcc4.h | 1 - include/linux/compiler.h | 4 ---- include/linux/elfnote.h | 2 +- include/linux/init.h | 11 +++++------ include/linux/module.h | 4 ++-- include/linux/moduleparam.h | 4 ++-- include/linux/pci.h | 2 +- 8 files changed, 11 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc3.h b/include/linux/compiler-gcc3.h index 2d8c0f48f55e..e5eb795f78a1 100644 --- a/include/linux/compiler-gcc3.h +++ b/include/linux/compiler-gcc3.h @@ -7,10 +7,8 @@ #if __GNUC_MINOR__ >= 3 # define __used __attribute__((__used__)) -# define __attribute_used__ __used /* deprecated */ #else # define __used __attribute__((__unused__)) -# define __attribute_used__ __used /* deprecated */ #endif #if __GNUC_MINOR__ >= 4 diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h index ee7ca5de970c..0ab3a3232330 100644 --- a/include/linux/compiler-gcc4.h +++ b/include/linux/compiler-gcc4.h @@ -15,7 +15,6 @@ #endif #define __used __attribute__((__used__)) -#define __attribute_used__ __used /* deprecated */ #define __must_check __attribute__((warn_unused_result)) #define __compiler_offsetof(a,b) __builtin_offsetof(a,b) #define __always_inline inline __attribute__((always_inline)) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index e0114a61268f..d0e17e1657dc 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -126,10 +126,6 @@ extern void __chk_io_ptr(const volatile void __iomem *); * Mark functions that are referenced only in inline assembly as __used so * the code is emitted even though it appears to be unreferenced. */ -#ifndef __attribute_used__ -# define __attribute_used__ /* deprecated */ -#endif - #ifndef __used # define __used /* unimplemented */ #endif diff --git a/include/linux/elfnote.h b/include/linux/elfnote.h index e831759b2fb5..278e3ef05336 100644 --- a/include/linux/elfnote.h +++ b/include/linux/elfnote.h @@ -76,7 +76,7 @@ typeof(desc) _desc \ __attribute__((aligned(sizeof(Elf##size##_Word)))); \ } _ELFNOTE_PASTE(_note_, unique) \ - __attribute_used__ \ + __used \ __attribute__((section(".note." name), \ aligned(sizeof(Elf##size##_Word)), \ unused)) = { \ diff --git a/include/linux/init.h b/include/linux/init.h index dcb66c76bd48..dde1eaa7766b 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -43,7 +43,7 @@ #define __init __section(.init.text) __cold #define __initdata __section(.init.data) #define __exitdata __section(.exit.data) -#define __exit_call __attribute_used__ __section(.exitcall.exit) +#define __exit_call __used __section(.exitcall.exit) /* modpost check for section mismatches during the kernel build. * A section mismatch happens when there are references from a @@ -144,7 +144,7 @@ void prepare_namespace(void); */ #define __define_initcall(level,fn,id) \ - static initcall_t __initcall_##fn##id __attribute_used__ \ + static initcall_t __initcall_##fn##id __used \ __attribute__((__section__(".initcall" level ".init"))) = fn /* @@ -178,11 +178,11 @@ void prepare_namespace(void); #define console_initcall(fn) \ static initcall_t __initcall_##fn \ - __attribute_used__ __section(.con_initcall.init)=fn + __used __section(.con_initcall.init) = fn #define security_initcall(fn) \ static initcall_t __initcall_##fn \ - __attribute_used__ __section(.security_initcall.init) = fn + __used __section(.security_initcall.init) = fn struct obs_kernel_param { const char *str; @@ -199,8 +199,7 @@ struct obs_kernel_param { #define __setup_param(str, unique_id, fn, early) \ static char __setup_str_##unique_id[] __initdata __aligned(1) = str; \ static struct obs_kernel_param __setup_##unique_id \ - __attribute_used__ \ - __section(.init.setup) \ + __used __section(.init.setup) \ __attribute__((aligned((sizeof(long))))) \ = { __setup_str_##unique_id, fn, early } diff --git a/include/linux/module.h b/include/linux/module.h index c97bdb7eb957..404838184ea5 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -178,7 +178,7 @@ void *__symbol_get_gpl(const char *symbol); #define __CRC_SYMBOL(sym, sec) \ extern void *__crc_##sym __attribute__((weak)); \ static const unsigned long __kcrctab_##sym \ - __attribute_used__ \ + __used \ __attribute__((section("__kcrctab" sec), unused)) \ = (unsigned long) &__crc_##sym; #else @@ -193,7 +193,7 @@ void *__symbol_get_gpl(const char *symbol); __attribute__((section("__ksymtab_strings"))) \ = MODULE_SYMBOL_PREFIX #sym; \ static const struct kernel_symbol __ksymtab_##sym \ - __attribute_used__ \ + __used \ __attribute__((section("__ksymtab" sec), unused)) \ = { (unsigned long)&sym, __kstrtab_##sym } diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 13410b20600f..8126e55c5bdc 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -18,7 +18,7 @@ #define __module_cat(a,b) ___module_cat(a,b) #define __MODULE_INFO(tag, name, info) \ static const char __module_cat(name,__LINE__)[] \ - __attribute_used__ \ + __used \ __attribute__((section(".modinfo"),unused)) = __stringify(tag) "=" info #else /* !MODULE */ #define __MODULE_INFO(tag, name, info) @@ -72,7 +72,7 @@ struct kparam_array BUILD_BUG_ON_ZERO((perm) < 0 || (perm) > 0777 || ((perm) & 2)); \ static const char __param_str_##name[] = prefix #name; \ static struct kernel_param const __param_##name \ - __attribute_used__ \ + __used \ __attribute__ ((unused,__section__ ("__param"),aligned(sizeof(void *)))) \ = { __param_str_##name, perm, set, get, { arg } } diff --git a/include/linux/pci.h b/include/linux/pci.h index 0dd93bb62fbe..ae1006322f80 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -867,7 +867,7 @@ enum pci_fixup_pass { /* Anonymous variables would be nice... */ #define DECLARE_PCI_FIXUP_SECTION(section, name, vendor, device, hook) \ - static const struct pci_fixup __pci_fixup_##name __attribute_used__ \ + static const struct pci_fixup __pci_fixup_##name __used \ __attribute__((__section__(#section))) = { vendor, device, hook }; #define DECLARE_PCI_FIXUP_EARLY(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_early, \ -- cgit v1.2.3 From 312b1485fb509c9bc32eda28ad29537896658cb8 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Mon, 28 Jan 2008 20:21:15 +0100 Subject: Introduce new section reference annotations tags: __ref, __refdata, __refconst Today we have the following annotations for functions/data referencing __init/__exit functions / data: __init_refok => for init functions __initdata_refok => for init data __exit_refok => for exit functions There is really no difference between the __init and __exit versions and simplify it and to introduce a shorter annotation the following new annotations are introduced: __ref => for functions (code) that references __*init / __*exit __refdata => for variables __refconst => for const variables Whit this annotation is it more obvious what the annotation is for and there is no longer the arbitary division between __init and __exit code. The mechanishm is the same as before - a special section is created which is made part of the usual sections in the linker script. We will start to see annotations like this: -static struct pci_serial_quirk pci_serial_quirks[] = { +static const struct pci_serial_quirk pci_serial_quirks[] __refconst = { ----------------- -static struct notifier_block __cpuinitdata cpuid_class_cpu_notifier = +static struct notifier_block cpuid_class_cpu_notifier __refdata = ---------------- -static int threshold_cpu_callback(struct notifier_block *nfb, +static int __ref threshold_cpu_callback(struct notifier_block *nfb, [The above is just random samples]. Note: No modifications were needed in modpost to support the new sections due to the newly introduced blacklisting. Signed-off-by: Sam Ravnborg --- include/linux/init.h | 34 +++++++++++++++++++++++++++------- 1 file changed, 27 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index dde1eaa7766b..2efbda016741 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -52,12 +52,26 @@ * when early init has completed so all such references are potential bugs. * For exit sections the same issue exists. * The following markers are used for the cases where the reference to - * the init/exit section (code or data) is valid and will teach modpost - * not to issue a warning. + * the *init / *exit section (code or data) is valid and will teach + * modpost not to issue a warning. * The markers follow same syntax rules as __init / __initdata. */ -#define __init_refok noinline __section(.text.init.refok) -#define __initdata_refok __section(.data.init.refok) -#define __exit_refok noinline __section(.exit.text.refok) +#define __ref __section(.ref.text) noinline +#define __refdata __section(.ref.data) +#define __refconst __section(.ref.rodata) + +/* backward compatibility note + * A few places hardcode the old section names: + * .text.init.refok + * .data.init.refok + * .exit.text.refok + * They should be converted to use the defines from this file + */ + +/* compatibility defines */ +#define __init_refok __ref +#define __initdata_refok __refdata +#define __exit_refok __ref + #ifdef MODULE #define __exitused @@ -93,11 +107,9 @@ /* For assembly routines */ #define __INIT .section ".init.text","ax" -#define __INIT_REFOK .section ".text.init.refok","ax" #define __FINIT .previous #define __INITDATA .section ".init.data","aw" -#define __INITDATA_REFOK .section ".data.init.refok","aw" #define __DEVINIT .section ".devinit.text", "ax" #define __DEVINITDATA .section ".devinit.data", "aw" @@ -108,6 +120,14 @@ #define __MEMINIT .section ".meminit.text", "ax" #define __MEMINITDATA .section ".meminit.data", "aw" +/* silence warnings when references are OK */ +#define __REF .section ".ref.text", "ax" +#define __REFDATA .section ".ref.data", "aw" +#define __REFCONST .section ".ref.rodata", "aw" +/* backward compatibility */ +#define __INIT_REFOK .section __REF +#define __INITDATA_REFOK .section __REFDATA + #ifndef __ASSEMBLY__ /* * Used for initialization calls.. -- cgit v1.2.3 From bbdfc2f70610bebb841d0874dc901c648308e43a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 6 Nov 2007 23:29:47 -0800 Subject: [SPLICE]: Don't assume regular pages in splice_to_pipe() Allow caller to pass in a release function, there might be other resources that need releasing as well. Needed for network receive. Signed-off-by: Jens Axboe Signed-off-by: David S. Miller --- include/linux/splice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/splice.h b/include/linux/splice.h index 33e447f98a54..528dcb93c2f2 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -53,6 +53,7 @@ struct splice_pipe_desc { int nr_pages; /* number of pages in map */ unsigned int flags; /* splice flags */ const struct pipe_buf_operations *ops;/* ops associated with output pipe */ + void (*spd_release)(struct splice_pipe_desc *, unsigned int); }; typedef int (splice_actor)(struct pipe_inode_info *, struct pipe_buffer *, -- cgit v1.2.3 From 9c55e01c0cc835818475a6ce8c4d684df9949ac8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 6 Nov 2007 23:30:13 -0800 Subject: [TCP]: Splice receive support. Support for network splice receive. Signed-off-by: Jens Axboe Signed-off-by: David S. Miller --- include/linux/net.h | 3 +++ include/linux/skbuff.h | 6 ++++++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 596131ea46f4..0235d917d5c3 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -22,6 +22,7 @@ #include struct poll_table_struct; +struct pipe_inode_info; struct inode; struct net; @@ -172,6 +173,8 @@ struct proto_ops { struct vm_area_struct * vma); ssize_t (*sendpage) (struct socket *sock, struct page *page, 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); }; struct net_proto_family { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bddd50bd6878..d39f53ef66bb 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -95,6 +95,7 @@ struct net_device; struct scatterlist; +struct pipe_inode_info; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) struct nf_conntrack { @@ -1559,6 +1560,11 @@ extern int skb_store_bits(struct sk_buff *skb, int offset, extern __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len, __wsum csum); +extern int skb_splice_bits(struct sk_buff *skb, + unsigned int offset, + struct pipe_inode_info *pipe, + unsigned int len, + unsigned int flags); extern void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); extern void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); -- cgit v1.2.3 From 6e23ae2a48750bda407a4a58f52a4865d7308bf5 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 19 Nov 2007 18:53:30 -0800 Subject: [NETFILTER]: Introduce NF_INET_ hook values The IPv4 and IPv6 hook values are identical, yet some code tries to figure out the "correct" value by looking at the address family. Introduce NF_INET_* values for both IPv4 and IPv6. The old values are kept in a #ifndef __KERNEL__ section for userspace compatibility. Signed-off-by: Patrick McHardy Acked-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/netfilter.h | 9 +++++++++ include/linux/netfilter/x_tables.h | 4 ++-- include/linux/netfilter_ipv4.h | 2 +- include/linux/netfilter_ipv4/ip_tables.h | 8 ++++---- include/linux/netfilter_ipv6.h | 3 +-- include/linux/netfilter_ipv6/ip6_tables.h | 8 ++++---- 6 files changed, 21 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 16adac688af5..25fc12260340 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -39,6 +39,15 @@ #define NFC_ALTERED 0x8000 #endif +enum nf_inet_hooks { + NF_INET_PRE_ROUTING, + NF_INET_LOCAL_IN, + NF_INET_FORWARD, + NF_INET_LOCAL_OUT, + NF_INET_POST_ROUTING, + NF_INET_NUMHOOKS +}; + #ifdef __KERNEL__ #ifdef CONFIG_NETFILTER diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 03e6ce979eaa..9657c4ee70fc 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -265,8 +265,8 @@ struct xt_table_info unsigned int initial_entries; /* Entry points and underflows */ - unsigned int hook_entry[NF_IP_NUMHOOKS]; - unsigned int underflow[NF_IP_NUMHOOKS]; + unsigned int hook_entry[NF_INET_NUMHOOKS]; + unsigned int underflow[NF_INET_NUMHOOKS]; /* ipt_entry tables: one per CPU */ char *entries[NR_CPUS]; diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index 1a63adf5c4c1..9a10092e358c 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -36,7 +36,6 @@ #define NFC_IP_DST_PT 0x0400 /* Something else about the proto */ #define NFC_IP_PROTO_UNKNOWN 0x2000 -#endif /* ! __KERNEL__ */ /* IP Hooks */ /* After promisc drops, checksum checks. */ @@ -50,6 +49,7 @@ /* Packets about to hit the wire. */ #define NF_IP_POST_ROUTING 4 #define NF_IP_NUMHOOKS 5 +#endif /* ! __KERNEL__ */ enum nf_ip_hook_priorities { NF_IP_PRI_FIRST = INT_MIN, diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index d79ed69cbc1f..54da61603eff 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -156,10 +156,10 @@ struct ipt_getinfo unsigned int valid_hooks; /* Hook entry points: one per netfilter hook. */ - unsigned int hook_entry[NF_IP_NUMHOOKS]; + unsigned int hook_entry[NF_INET_NUMHOOKS]; /* Underflow points. */ - unsigned int underflow[NF_IP_NUMHOOKS]; + unsigned int underflow[NF_INET_NUMHOOKS]; /* Number of entries */ unsigned int num_entries; @@ -185,10 +185,10 @@ struct ipt_replace unsigned int size; /* Hook entry points. */ - unsigned int hook_entry[NF_IP_NUMHOOKS]; + unsigned int hook_entry[NF_INET_NUMHOOKS]; /* Underflow points. */ - unsigned int underflow[NF_IP_NUMHOOKS]; + unsigned int underflow[NF_INET_NUMHOOKS]; /* Information about old entries: */ /* Number of counters (must be equal to current number of entries). */ diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 66ca8e3100dc..3475a65dae9b 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -40,8 +40,6 @@ #define NFC_IP6_DST_PT 0x0400 /* Something else about the proto */ #define NFC_IP6_PROTO_UNKNOWN 0x2000 -#endif /* ! __KERNEL__ */ - /* IP6 Hooks */ /* After promisc drops, checksum checks. */ @@ -55,6 +53,7 @@ /* Packets about to hit the wire. */ #define NF_IP6_POST_ROUTING 4 #define NF_IP6_NUMHOOKS 5 +#endif /* ! __KERNEL__ */ enum nf_ip6_hook_priorities { diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 7dc481ce7cba..2e98654188b3 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -216,10 +216,10 @@ struct ip6t_getinfo unsigned int valid_hooks; /* Hook entry points: one per netfilter hook. */ - unsigned int hook_entry[NF_IP6_NUMHOOKS]; + unsigned int hook_entry[NF_INET_NUMHOOKS]; /* Underflow points. */ - unsigned int underflow[NF_IP6_NUMHOOKS]; + unsigned int underflow[NF_INET_NUMHOOKS]; /* Number of entries */ unsigned int num_entries; @@ -245,10 +245,10 @@ struct ip6t_replace unsigned int size; /* Hook entry points. */ - unsigned int hook_entry[NF_IP6_NUMHOOKS]; + unsigned int hook_entry[NF_INET_NUMHOOKS]; /* Underflow points. */ - unsigned int underflow[NF_IP6_NUMHOOKS]; + unsigned int underflow[NF_INET_NUMHOOKS]; /* Information about old entries: */ /* Number of counters (must be equal to current number of entries). */ -- cgit v1.2.3 From 2a8cc6c89039e0530a3335954253b76ed0f9339a Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Wed, 14 Nov 2007 15:56:23 +0900 Subject: [IPV6] ADDRCONF: Support RFC3484 configurable address selection policy table. Policy table is implemented as an RCU linear list since we do not expect large list nor frequent updates. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/if_addrlabel.h | 32 ++++++++++++++++++++++++++++++++ include/linux/rtnetlink.h | 7 +++++++ 2 files changed, 39 insertions(+) create mode 100644 include/linux/if_addrlabel.h (limited to 'include/linux') diff --git a/include/linux/if_addrlabel.h b/include/linux/if_addrlabel.h new file mode 100644 index 000000000000..9fe79c95dd28 --- /dev/null +++ b/include/linux/if_addrlabel.h @@ -0,0 +1,32 @@ +/* + * if_addrlabel.h - netlink interface for address labels + * + * Copyright (C)2007 USAGI/WIDE Project, All Rights Reserved. + * + * Authors: + * YOSHIFUJI Hideaki @ USAGI/WIDE + */ + +#ifndef __LINUX_IF_ADDRLABEL_H +#define __LINUX_IF_ADDRLABEL_H + +struct ifaddrlblmsg +{ + __u8 ifal_family; /* Address family */ + __u8 __ifal_reserved; /* Reserved */ + __u8 ifal_prefixlen; /* Prefix length */ + __u8 ifal_flags; /* Flags */ + __u32 ifal_index; /* Link index */ + __u32 ifal_seq; /* sequence number */ +}; + +enum +{ + IFAL_ADDRESS = 1, + IFAL_LABEL = 2, + __IFAL_MAX +}; + +#define IFAL_MAX (__IFAL_MAX - 1) + +#endif diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 4e81836191df..e20dcc89a836 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -100,6 +100,13 @@ enum { RTM_NEWNDUSEROPT = 68, #define RTM_NEWNDUSEROPT RTM_NEWNDUSEROPT + RTM_NEWADDRLABEL = 72, +#define RTM_NEWADDRLABEL RTM_NEWADDRLABEL + RTM_DELADDRLABEL, +#define RTM_NEWADDRLABEL RTM_NEWADDRLABEL + RTM_GETADDRLABEL, +#define RTM_GETADDRLABEL RTM_GETADDRLABEL + __RTM_MAX, #define RTM_MAX (((__RTM_MAX + 3) & ~3) - 1) }; -- cgit v1.2.3 From a47e5a988a575e64c8c9bae65a1dfe3dca7cba32 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 15 Nov 2007 19:41:46 -0800 Subject: [TCP]: Convert highest_sack to sk_buff to allow direct access MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It is going to replace the sack fastpath hint quite soon... :-) Signed-off-by: Ilpo Järvinen Signed-off-by: David S. Miller --- include/linux/tcp.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index bac17c59b24e..34acee662230 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -332,8 +332,10 @@ struct tcp_sock { struct tcp_sack_block_wire recv_sack_cache[4]; - u32 highest_sack; /* Start seq of globally highest revd SACK - * (validity guaranteed only if sacked_out > 0) */ + struct sk_buff *highest_sack; /* highest skb with SACK received + * (validity guaranteed only if + * sacked_out > 0) + */ /* from STCP, retrans queue hinting */ struct sk_buff* lost_skb_hint; -- cgit v1.2.3 From fd6dad616d4fe2f08d690f25ca76b0102158fb3a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 15 Nov 2007 19:49:47 -0800 Subject: [TCP]: Earlier SACK block verification & simplify access to them MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Ilpo Järvinen Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 34acee662230..794497c7d755 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -330,7 +330,7 @@ struct tcp_sock { struct tcp_sack_block duplicate_sack[1]; /* D-SACK block */ struct tcp_sack_block selective_acks[4]; /* The SACKS themselves*/ - struct tcp_sack_block_wire recv_sack_cache[4]; + struct tcp_sack_block recv_sack_cache[4]; struct sk_buff *highest_sack; /* highest skb with SACK received * (validity guaranteed only if -- cgit v1.2.3 From 68f8353b480e5f2e136c38a511abdbb88eaa8ce2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 15 Nov 2007 19:50:37 -0800 Subject: [TCP]: Rewrite SACK block processing & sack_recv_cache use MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Key points of this patch are: - In case new SACK information is advance only type, no skb processing below previously discovered highest point is done - Optimize cases below highest point too since there's no need to always go up to highest point (which is very likely still present in that SACK), this is not entirely true though because I'm dropping the fastpath_skb_hint which could previously optimize those cases even better. Whether that's significant, I'm not too sure. Currently it will provide skipping by walking. Combined with RB-tree, all skipping would become fast too regardless of window size (can be done incrementally later). Previously a number of cases in TCP SACK processing fails to take advantage of costly stored information in sack_recv_cache, most importantly, expected events such as cumulative ACK and new hole ACKs. Processing on such ACKs result in rather long walks building up latencies (which easily gets nasty when window is huge). Those latencies are often completely unnecessary compared with the amount of _new_ information received, usually for cumulative ACK there's no new information at all, yet TCP walks whole queue unnecessary potentially taking a number of costly cache misses on the way, etc.! Since the inclusion of highest_sack, there's a lot information that is very likely redundant (SACK fastpath hint stuff, fackets_out, highest_sack), though there's no ultimate guarantee that they'll remain the same whole the time (in all unearthly scenarios). Take advantage of this knowledge here and drop fastpath hint and use direct access to highest SACKed skb as a replacement. Effectively "special cased" fastpath is dropped. This change adds some complexity to introduce better coveraged "fastpath", though the added complexity should make TCP behave more cache friendly. The current ACK's SACK blocks are compared against each cached block individially and only ranges that are new are then scanned by the high constant walk. For other parts of write queue, even when in previously known part of the SACK blocks, a faster skip function is used (if necessary at all). In addition, whenever possible, TCP fast-forwards to highest_sack skb that was made available by an earlier patch. In typical case, no other things but this fast-forward and mandatory markings after that occur making the access pattern quite similar to the former fastpath "special case". DSACKs are special case that must always be walked. The local to recv_sack_cache copying could be more intelligent w.r.t DSACKs which are likely to be there only once but that is left to a separate patch. Signed-off-by: Ilpo Järvinen Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 794497c7d755..08027f1d7f31 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -343,10 +343,7 @@ struct tcp_sock { struct sk_buff *scoreboard_skb_hint; struct sk_buff *retransmit_skb_hint; struct sk_buff *forward_skb_hint; - struct sk_buff *fastpath_skb_hint; - int fastpath_cnt_hint; /* Lags behind by current skb's pcount - * compared to respective fackets_out */ int lost_cnt_hint; int retransmit_cnt_hint; -- cgit v1.2.3 From cd05acfe65ed2cf2db683fa9a6adb8d35635263b Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Sun, 16 Dec 2007 15:59:24 -0800 Subject: [CAN]: Allocate protocol numbers for PF_CAN This patch adds a protocol/address family number, ARP hardware type, ethernet packet type, and a line discipline number for the SocketCAN implementation. Signed-off-by: Oliver Hartkopp Signed-off-by: Urs Thuermann Signed-off-by: David S. Miller --- include/linux/if.h | 4 +++- include/linux/if_arp.h | 1 + include/linux/if_ether.h | 1 + include/linux/socket.h | 2 ++ include/linux/tty.h | 3 ++- 5 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if.h b/include/linux/if.h index 32bf419351f1..186070d5c544 100644 --- a/include/linux/if.h +++ b/include/linux/if.h @@ -50,7 +50,9 @@ #define IFF_LOWER_UP 0x10000 /* driver signals L1 up */ #define IFF_DORMANT 0x20000 /* driver signals dormant */ -#define IFF_VOLATILE (IFF_LOOPBACK|IFF_POINTOPOINT|IFF_BROADCAST|\ +#define IFF_ECHO 0x40000 /* echo sent packets */ + +#define IFF_VOLATILE (IFF_LOOPBACK|IFF_POINTOPOINT|IFF_BROADCAST|IFF_ECHO|\ IFF_MASTER|IFF_SLAVE|IFF_RUNNING|IFF_LOWER_UP|IFF_DORMANT) /* Private (from user) interface flags (netdevice->priv_flags). */ diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index ed7b93c3083a..296e8e86e91d 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -52,6 +52,7 @@ #define ARPHRD_ROSE 270 #define ARPHRD_X25 271 /* CCITT X.25 */ #define ARPHRD_HWX25 272 /* Boards with X.25 in firmware */ +#define ARPHRD_CAN 280 /* Controller Area Network */ #define ARPHRD_PPP 512 #define ARPHRD_CISCO 513 /* Cisco HDLC */ #define ARPHRD_HDLC ARPHRD_CISCO diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index 5f9297793661..cc002cbbdc26 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -90,6 +90,7 @@ #define ETH_P_WAN_PPP 0x0007 /* Dummy type for WAN PPP frames*/ #define ETH_P_PPP_MP 0x0008 /* Dummy type for PPP MP frames */ #define ETH_P_LOCALTALK 0x0009 /* Localtalk pseudo type */ +#define ETH_P_CAN 0x000C /* Controller Area Network */ #define ETH_P_PPPTALK 0x0010 /* Dummy type for Atalk over PPP*/ #define ETH_P_TR_802_2 0x0011 /* 802.2 frames */ #define ETH_P_MOBITEX 0x0015 /* Mobitex (kaz@cafe.net) */ diff --git a/include/linux/socket.h b/include/linux/socket.h index c22ef1c1afb8..eb5bdd59a644 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -185,6 +185,7 @@ struct ucred { #define AF_PPPOX 24 /* PPPoX sockets */ #define AF_WANPIPE 25 /* Wanpipe API Sockets */ #define AF_LLC 26 /* Linux LLC */ +#define AF_CAN 29 /* Controller Area Network */ #define AF_TIPC 30 /* TIPC sockets */ #define AF_BLUETOOTH 31 /* Bluetooth sockets */ #define AF_IUCV 32 /* IUCV sockets */ @@ -220,6 +221,7 @@ struct ucred { #define PF_PPPOX AF_PPPOX #define PF_WANPIPE AF_WANPIPE #define PF_LLC AF_LLC +#define PF_CAN AF_CAN #define PF_TIPC AF_TIPC #define PF_BLUETOOTH AF_BLUETOOTH #define PF_IUCV AF_IUCV diff --git a/include/linux/tty.h b/include/linux/tty.h index defd2ab72449..402de892b3ed 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -23,7 +23,7 @@ */ #define NR_UNIX98_PTY_DEFAULT 4096 /* Default maximum for Unix98 ptys */ #define NR_UNIX98_PTY_MAX (1 << MINORBITS) /* Absolute limit */ -#define NR_LDISCS 17 +#define NR_LDISCS 18 /* line disciplines */ #define N_TTY 0 @@ -44,6 +44,7 @@ #define N_SYNC_PPP 14 /* synchronous PPP */ #define N_HCI 15 /* Bluetooth HCI UART */ #define N_GIGASET_M101 16 /* Siemens Gigaset M101 serial DECT adapter */ +#define N_SLCAN 17 /* Serial / USB serial CAN Adaptors */ /* * This character is the same as _POSIX_VDISABLE: it cannot be used as -- cgit v1.2.3 From 0d66548a10cbbe0ef256852d63d30603f0f73f9b Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Fri, 16 Nov 2007 15:52:17 -0800 Subject: [CAN]: Add PF_CAN core module This patch adds the CAN core functionality but no protocols or drivers. No protocol implementations are included here. They come as separate patches. Protocol numbers are already in include/linux/can.h. Signed-off-by: Oliver Hartkopp Signed-off-by: Urs Thuermann Signed-off-by: David S. Miller --- include/linux/can.h | 111 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/can/core.h | 64 ++++++++++++++++++++++++++ include/linux/can/error.h | 93 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 268 insertions(+) create mode 100644 include/linux/can.h create mode 100644 include/linux/can/core.h create mode 100644 include/linux/can/error.h (limited to 'include/linux') diff --git a/include/linux/can.h b/include/linux/can.h new file mode 100644 index 000000000000..d18333302cbd --- /dev/null +++ b/include/linux/can.h @@ -0,0 +1,111 @@ +/* + * linux/can.h + * + * Definitions for CAN network layer (socket addr / CAN frame / CAN filter) + * + * Authors: Oliver Hartkopp + * Urs Thuermann + * Copyright (c) 2002-2007 Volkswagen Group Electronic Research + * All rights reserved. + * + * Send feedback to + * + */ + +#ifndef CAN_H +#define CAN_H + +#include +#include + +/* controller area network (CAN) kernel definitions */ + +/* special address description flags for the CAN_ID */ +#define CAN_EFF_FLAG 0x80000000U /* EFF/SFF is set in the MSB */ +#define CAN_RTR_FLAG 0x40000000U /* remote transmission request */ +#define CAN_ERR_FLAG 0x20000000U /* error frame */ + +/* valid bits in CAN ID for frame formats */ +#define CAN_SFF_MASK 0x000007FFU /* standard frame format (SFF) */ +#define CAN_EFF_MASK 0x1FFFFFFFU /* extended frame format (EFF) */ +#define CAN_ERR_MASK 0x1FFFFFFFU /* omit EFF, RTR, ERR flags */ + +/* + * Controller Area Network Identifier structure + * + * bit 0-28 : CAN identifier (11/29 bit) + * bit 29 : error frame flag (0 = data frame, 1 = error frame) + * bit 30 : remote transmission request flag (1 = rtr frame) + * bit 31 : frame format flag (0 = standard 11 bit, 1 = extended 29 bit) + */ +typedef __u32 canid_t; + +/* + * Controller Area Network Error Frame Mask structure + * + * bit 0-28 : error class mask (see include/linux/can/error.h) + * bit 29-31 : set to zero + */ +typedef __u32 can_err_mask_t; + +/** + * struct can_frame - basic CAN frame structure + * @can_id: the CAN ID of the frame and CAN_*_FLAG flags, see above. + * @can_dlc: the data length field of the CAN frame + * @data: the CAN frame payload. + */ +struct can_frame { + canid_t can_id; /* 32 bit CAN_ID + EFF/RTR/ERR flags */ + __u8 can_dlc; /* data length code: 0 .. 8 */ + __u8 data[8] __attribute__((aligned(8))); +}; + +/* particular protocols of the protocol family PF_CAN */ +#define CAN_RAW 1 /* RAW sockets */ +#define CAN_BCM 2 /* Broadcast Manager */ +#define CAN_TP16 3 /* VAG Transport Protocol v1.6 */ +#define CAN_TP20 4 /* VAG Transport Protocol v2.0 */ +#define CAN_MCNET 5 /* Bosch MCNet */ +#define CAN_ISOTP 6 /* ISO 15765-2 Transport Protocol */ +#define CAN_NPROTO 7 + +#define SOL_CAN_BASE 100 + +/** + * struct sockaddr_can - the sockaddr structure for CAN sockets + * @can_family: address family number AF_CAN. + * @can_ifindex: CAN network interface index. + * @can_addr: protocol specific address information + */ +struct sockaddr_can { + sa_family_t can_family; + int can_ifindex; + union { + /* transport protocol class address information (e.g. ISOTP) */ + struct { canid_t rx_id, tx_id; } tp; + + /* reserved for future CAN protocols address information */ + } can_addr; +}; + +/** + * struct can_filter - CAN ID based filter in can_register(). + * @can_id: relevant bits of CAN ID which are not masked out. + * @can_mask: CAN mask (see description) + * + * Description: + * A filter matches, when + * + * & mask == can_id & mask + * + * The filter can be inverted (CAN_INV_FILTER bit set in can_id) or it can + * filter for error frames (CAN_ERR_FLAG bit set in mask). + */ +struct can_filter { + canid_t can_id; + canid_t can_mask; +}; + +#define CAN_INV_FILTER 0x20000000U /* to be set in can_filter.can_id */ + +#endif /* CAN_H */ diff --git a/include/linux/can/core.h b/include/linux/can/core.h new file mode 100644 index 000000000000..e9ca210ffa5b --- /dev/null +++ b/include/linux/can/core.h @@ -0,0 +1,64 @@ +/* + * linux/can/core.h + * + * Protoypes and definitions for CAN protocol modules using the PF_CAN core + * + * Authors: Oliver Hartkopp + * Urs Thuermann + * Copyright (c) 2002-2007 Volkswagen Group Electronic Research + * All rights reserved. + * + * Send feedback to + * + */ + +#ifndef CAN_CORE_H +#define CAN_CORE_H + +#include +#include +#include + +#define CAN_VERSION "20071116" + +/* increment this number each time you change some user-space interface */ +#define CAN_ABI_VERSION "8" + +#define CAN_VERSION_STRING "rev " CAN_VERSION " abi " CAN_ABI_VERSION + +#define DNAME(dev) ((dev) ? (dev)->name : "any") + +/** + * struct can_proto - CAN protocol structure + * @type: type argument in socket() syscall, e.g. SOCK_DGRAM. + * @protocol: protocol number in socket() syscall. + * @capability: capability needed to open the socket, or -1 for no restriction. + * @ops: pointer to struct proto_ops for sock->ops. + * @prot: pointer to struct proto structure. + */ +struct can_proto { + int type; + int protocol; + int capability; + struct proto_ops *ops; + struct proto *prot; +}; + +/* function prototypes for the CAN networklayer core (af_can.c) */ + +extern int can_proto_register(struct can_proto *cp); +extern void can_proto_unregister(struct can_proto *cp); + +extern int can_rx_register(struct net_device *dev, canid_t can_id, + canid_t mask, + void (*func)(struct sk_buff *, void *), + void *data, char *ident); + +extern void can_rx_unregister(struct net_device *dev, canid_t can_id, + canid_t mask, + void (*func)(struct sk_buff *, void *), + void *data); + +extern int can_send(struct sk_buff *skb, int loop); + +#endif /* CAN_CORE_H */ diff --git a/include/linux/can/error.h b/include/linux/can/error.h new file mode 100644 index 000000000000..d4127fd9e681 --- /dev/null +++ b/include/linux/can/error.h @@ -0,0 +1,93 @@ +/* + * linux/can/error.h + * + * Definitions of the CAN error frame to be filtered and passed to the user. + * + * Author: Oliver Hartkopp + * Copyright (c) 2002-2007 Volkswagen Group Electronic Research + * All rights reserved. + * + * Send feedback to + * + */ + +#ifndef CAN_ERROR_H +#define CAN_ERROR_H + +#define CAN_ERR_DLC 8 /* dlc for error frames */ + +/* error class (mask) in can_id */ +#define CAN_ERR_TX_TIMEOUT 0x00000001U /* TX timeout (by netdevice driver) */ +#define CAN_ERR_LOSTARB 0x00000002U /* lost arbitration / data[0] */ +#define CAN_ERR_CRTL 0x00000004U /* controller problems / data[1] */ +#define CAN_ERR_PROT 0x00000008U /* protocol violations / data[2..3] */ +#define CAN_ERR_TRX 0x00000010U /* transceiver status / data[4] */ +#define CAN_ERR_ACK 0x00000020U /* received no ACK on transmission */ +#define CAN_ERR_BUSOFF 0x00000040U /* bus off */ +#define CAN_ERR_BUSERROR 0x00000080U /* bus error (may flood!) */ +#define CAN_ERR_RESTARTED 0x00000100U /* controller restarted */ + +/* arbitration lost in bit ... / data[0] */ +#define CAN_ERR_LOSTARB_UNSPEC 0x00 /* unspecified */ + /* else bit number in bitstream */ + +/* error status of CAN-controller / data[1] */ +#define CAN_ERR_CRTL_UNSPEC 0x00 /* unspecified */ +#define CAN_ERR_CRTL_RX_OVERFLOW 0x01 /* RX buffer overflow */ +#define CAN_ERR_CRTL_TX_OVERFLOW 0x02 /* TX buffer overflow */ +#define CAN_ERR_CRTL_RX_WARNING 0x04 /* reached warning level for RX errors */ +#define CAN_ERR_CRTL_TX_WARNING 0x08 /* reached warning level for TX errors */ +#define CAN_ERR_CRTL_RX_PASSIVE 0x10 /* reached error passive status RX */ +#define CAN_ERR_CRTL_TX_PASSIVE 0x20 /* reached error passive status TX */ + /* (at least one error counter exceeds */ + /* the protocol-defined level of 127) */ + +/* error in CAN protocol (type) / data[2] */ +#define CAN_ERR_PROT_UNSPEC 0x00 /* unspecified */ +#define CAN_ERR_PROT_BIT 0x01 /* single bit error */ +#define CAN_ERR_PROT_FORM 0x02 /* frame format error */ +#define CAN_ERR_PROT_STUFF 0x04 /* bit stuffing error */ +#define CAN_ERR_PROT_BIT0 0x08 /* unable to send dominant bit */ +#define CAN_ERR_PROT_BIT1 0x10 /* unable to send recessive bit */ +#define CAN_ERR_PROT_OVERLOAD 0x20 /* bus overload */ +#define CAN_ERR_PROT_ACTIVE 0x40 /* active error announcement */ +#define CAN_ERR_PROT_TX 0x80 /* error occured on transmission */ + +/* error in CAN protocol (location) / data[3] */ +#define CAN_ERR_PROT_LOC_UNSPEC 0x00 /* unspecified */ +#define CAN_ERR_PROT_LOC_SOF 0x03 /* start of frame */ +#define CAN_ERR_PROT_LOC_ID28_21 0x02 /* ID bits 28 - 21 (SFF: 10 - 3) */ +#define CAN_ERR_PROT_LOC_ID20_18 0x06 /* ID bits 20 - 18 (SFF: 2 - 0 )*/ +#define CAN_ERR_PROT_LOC_SRTR 0x04 /* substitute RTR (SFF: RTR) */ +#define CAN_ERR_PROT_LOC_IDE 0x05 /* identifier extension */ +#define CAN_ERR_PROT_LOC_ID17_13 0x07 /* ID bits 17-13 */ +#define CAN_ERR_PROT_LOC_ID12_05 0x0F /* ID bits 12-5 */ +#define CAN_ERR_PROT_LOC_ID04_00 0x0E /* ID bits 4-0 */ +#define CAN_ERR_PROT_LOC_RTR 0x0C /* RTR */ +#define CAN_ERR_PROT_LOC_RES1 0x0D /* reserved bit 1 */ +#define CAN_ERR_PROT_LOC_RES0 0x09 /* reserved bit 0 */ +#define CAN_ERR_PROT_LOC_DLC 0x0B /* data length code */ +#define CAN_ERR_PROT_LOC_DATA 0x0A /* data section */ +#define CAN_ERR_PROT_LOC_CRC_SEQ 0x08 /* CRC sequence */ +#define CAN_ERR_PROT_LOC_CRC_DEL 0x18 /* CRC delimiter */ +#define CAN_ERR_PROT_LOC_ACK 0x19 /* ACK slot */ +#define CAN_ERR_PROT_LOC_ACK_DEL 0x1B /* ACK delimiter */ +#define CAN_ERR_PROT_LOC_EOF 0x1A /* end of frame */ +#define CAN_ERR_PROT_LOC_INTERM 0x12 /* intermission */ + +/* error status of CAN-transceiver / data[4] */ +/* CANH CANL */ +#define CAN_ERR_TRX_UNSPEC 0x00 /* 0000 0000 */ +#define CAN_ERR_TRX_CANH_NO_WIRE 0x04 /* 0000 0100 */ +#define CAN_ERR_TRX_CANH_SHORT_TO_BAT 0x05 /* 0000 0101 */ +#define CAN_ERR_TRX_CANH_SHORT_TO_VCC 0x06 /* 0000 0110 */ +#define CAN_ERR_TRX_CANH_SHORT_TO_GND 0x07 /* 0000 0111 */ +#define CAN_ERR_TRX_CANL_NO_WIRE 0x40 /* 0100 0000 */ +#define CAN_ERR_TRX_CANL_SHORT_TO_BAT 0x50 /* 0101 0000 */ +#define CAN_ERR_TRX_CANL_SHORT_TO_VCC 0x60 /* 0110 0000 */ +#define CAN_ERR_TRX_CANL_SHORT_TO_GND 0x70 /* 0111 0000 */ +#define CAN_ERR_TRX_CANL_SHORT_TO_CANH 0x80 /* 1000 0000 */ + +/* controller specific additional information / data[5..7] */ + +#endif /* CAN_ERROR_H */ -- cgit v1.2.3 From c18ce101f2e47d97ace125033e2896895a6db3dd Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Fri, 16 Nov 2007 15:53:09 -0800 Subject: [CAN]: Add raw protocol This patch adds the CAN raw protocol. Signed-off-by: Oliver Hartkopp Signed-off-by: Urs Thuermann Signed-off-by: David S. Miller --- include/linux/can/raw.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100644 include/linux/can/raw.h (limited to 'include/linux') diff --git a/include/linux/can/raw.h b/include/linux/can/raw.h new file mode 100644 index 000000000000..b2a0f87492c5 --- /dev/null +++ b/include/linux/can/raw.h @@ -0,0 +1,31 @@ +/* + * linux/can/raw.h + * + * Definitions for raw CAN sockets + * + * Authors: Oliver Hartkopp + * Urs Thuermann + * Copyright (c) 2002-2007 Volkswagen Group Electronic Research + * All rights reserved. + * + * Send feedback to + * + */ + +#ifndef CAN_RAW_H +#define CAN_RAW_H + +#include + +#define SOL_CAN_RAW (SOL_CAN_BASE + CAN_RAW) + +/* for socket options affecting the socket (not the global system) */ + +enum { + CAN_RAW_FILTER = 1, /* set 0 .. n can_filter(s) */ + CAN_RAW_ERR_FILTER, /* set filter for error frames */ + CAN_RAW_LOOPBACK, /* local loopback (default:on) */ + CAN_RAW_RECV_OWN_MSGS /* receive my own msgs (default:off) */ +}; + +#endif -- cgit v1.2.3 From ffd980f976e7fd666c2e61bf8ab35107efd11828 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Fri, 16 Nov 2007 15:53:52 -0800 Subject: [CAN]: Add broadcast manager (bcm) protocol This patch adds the CAN broadcast manager (bcm) protocol. Signed-off-by: Oliver Hartkopp Signed-off-by: Urs Thuermann Signed-off-by: David S. Miller --- include/linux/can/bcm.h | 65 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 65 insertions(+) create mode 100644 include/linux/can/bcm.h (limited to 'include/linux') diff --git a/include/linux/can/bcm.h b/include/linux/can/bcm.h new file mode 100644 index 000000000000..7ade33a0ff03 --- /dev/null +++ b/include/linux/can/bcm.h @@ -0,0 +1,65 @@ +/* + * linux/can/bcm.h + * + * Definitions for CAN Broadcast Manager (BCM) + * + * Author: Oliver Hartkopp + * Copyright (c) 2002-2007 Volkswagen Group Electronic Research + * All rights reserved. + * + * Send feedback to + * + */ + +#ifndef CAN_BCM_H +#define CAN_BCM_H + +/** + * struct bcm_msg_head - head of messages to/from the broadcast manager + * @opcode: opcode, see enum below. + * @flags: special flags, see below. + * @count: number of frames to send before changing interval. + * @ival1: interval for the first @count frames. + * @ival2: interval for the following frames. + * @can_id: CAN ID of frames to be sent or received. + * @nframes: number of frames appended to the message head. + * @frames: array of CAN frames. + */ +struct bcm_msg_head { + int opcode; + int flags; + int count; + struct timeval ival1, ival2; + canid_t can_id; + int nframes; + struct can_frame frames[0]; +}; + +enum { + TX_SETUP = 1, /* create (cyclic) transmission task */ + TX_DELETE, /* remove (cyclic) transmission task */ + TX_READ, /* read properties of (cyclic) transmission task */ + TX_SEND, /* send one CAN frame */ + RX_SETUP, /* create RX content filter subscription */ + RX_DELETE, /* remove RX content filter subscription */ + RX_READ, /* read properties of RX content filter subscription */ + TX_STATUS, /* reply to TX_READ request */ + TX_EXPIRED, /* notification on performed transmissions (count=0) */ + RX_STATUS, /* reply to RX_READ request */ + RX_TIMEOUT, /* cyclic message is absent */ + RX_CHANGED /* updated CAN frame (detected content change) */ +}; + +#define SETTIMER 0x0001 +#define STARTTIMER 0x0002 +#define TX_COUNTEVT 0x0004 +#define TX_ANNOUNCE 0x0008 +#define TX_CP_CAN_ID 0x0010 +#define RX_FILTER_ID 0x0020 +#define RX_CHECK_DLC 0x0040 +#define RX_NO_AUTOTIMER 0x0080 +#define RX_ANNOUNCE_RESUME 0x0100 +#define TX_RESET_MULTI_IDX 0x0200 +#define RX_RTR_FRAME 0x0400 + +#endif /* CAN_BCM_H */ -- cgit v1.2.3 From 4195e31780a20e09c6e793c2d96390e05309e226 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Thu, 27 Dec 2007 16:50:06 -0800 Subject: [CAN]: Fix plain integer definitions in userspace header. This patch fixes the use of plain integers instead of __u32 in a struct that is visible from kernel space and user space. Thanks to Sam Ravnborg for pointing out the wrong plain int usage. Signed-off-by: Oliver Hartkopp Acked-by: Sam Ravnborg Signed-off-by: David S. Miller --- include/linux/can/bcm.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/can/bcm.h b/include/linux/can/bcm.h index 7ade33a0ff03..7f293273c444 100644 --- a/include/linux/can/bcm.h +++ b/include/linux/can/bcm.h @@ -26,12 +26,12 @@ * @frames: array of CAN frames. */ struct bcm_msg_head { - int opcode; - int flags; - int count; + __u32 opcode; + __u32 flags; + __u32 count; struct timeval ival1, ival2; canid_t can_id; - int nframes; + __u32 nframes; struct can_frame frames[0]; }; -- cgit v1.2.3 From 1f98eefae8ca451d317b1602f2cedf7515b032ff Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Thu, 27 Dec 2007 16:51:46 -0800 Subject: [CAN]: Add missing Kbuild entries This patch adds the missing Kbuild entries and the missing Kbuild file in include/linux/can for the CAN subsystem. Signed-off-by: Oliver Hartkopp Acked-by: Sam Ravnborg Signed-off-by: David S. Miller --- include/linux/Kbuild | 2 ++ include/linux/can/Kbuild | 3 +++ 2 files changed, 5 insertions(+) create mode 100644 include/linux/can/Kbuild (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index bd694f779346..a85e87fd60d7 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -1,4 +1,5 @@ header-y += byteorder/ +header-y += can/ header-y += dvb/ header-y += hdlc/ header-y += isdn/ @@ -41,6 +42,7 @@ header-y += baycom.h header-y += bfs_fs.h header-y += blkpg.h header-y += bpqether.h +header-y += can.h header-y += cdk.h header-y += chio.h header-y += coda_psdev.h diff --git a/include/linux/can/Kbuild b/include/linux/can/Kbuild new file mode 100644 index 000000000000..eff898aac02b --- /dev/null +++ b/include/linux/can/Kbuild @@ -0,0 +1,3 @@ +header-y += raw.h +header-y += bcm.h +header-y += error.h -- cgit v1.2.3 From 0953864160bdd28dfe45fd46fa462b4d2d53cb96 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Mon, 19 Nov 2007 19:23:29 -0800 Subject: [NETPOLL]: no need to store local_mac The local_mac is managed by the network device, no need to keep a spare copy and all the management problems that could cause. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netpoll.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 20250d963d72..e3d79593fb3a 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -20,7 +20,7 @@ struct netpoll { u32 local_ip, remote_ip; u16 local_port, remote_port; - u8 local_mac[ETH_ALEN], remote_mac[ETH_ALEN]; + u8 remote_mac[ETH_ALEN]; }; struct netpoll_info { -- cgit v1.2.3 From c7b6ea24b43afb5749cb704e143df19d70e23dea Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Mon, 19 Nov 2007 19:37:09 -0800 Subject: [NETPOLL]: Don't need rx_flags. The rx_flags variable is redundant. Turning rx on/off is done via setting the rx_np pointer. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netpoll.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index e3d79593fb3a..a0525a1f4715 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -25,7 +25,6 @@ struct netpoll { struct netpoll_info { atomic_t refcnt; - int rx_flags; spinlock_t rx_lock; struct netpoll *rx_np; /* netpoll that registered an rx_hook */ struct sk_buff_head arp_tx; /* list of arp requests to reply to */ @@ -51,12 +50,12 @@ static inline int netpoll_rx(struct sk_buff *skb) unsigned long flags; int ret = 0; - if (!npinfo || (!npinfo->rx_np && !npinfo->rx_flags)) + if (!npinfo || !npinfo->rx_np) return 0; spin_lock_irqsave(&npinfo->rx_lock, flags); - /* check rx_flags again with the lock held */ - if (npinfo->rx_flags && __netpoll_rx(skb)) + /* check rx_np again with the lock held */ + if (npinfo->rx_np && __netpoll_rx(skb)) ret = 1; spin_unlock_irqrestore(&npinfo->rx_lock, flags); -- cgit v1.2.3 From c237899d1f8c5bfcfc9d6204052e0e065827ff75 Mon Sep 17 00:00:00 2001 From: Michael Wu Date: Tue, 30 Oct 2007 16:50:05 -0400 Subject: ieee80211: Add IEEE80211_MAX_FRAME_LEN to linux/ieee80211.h This patch adds IEEE80211_MAX_FRAME_LEN which is useful for drivers trying to determine how much to allocate for their RX buffers. It also updates the comment on IEEE80211_MAX_DATA_LEN based on revisions in 802.11e. IEEE80211_MAX_FRAG_THRESHOLD and IEEE80211_MAX_RTS_THRESHOLD are also revised due to the new maximum frame size. Signed-off-by: Michael Wu Signed-off-by: John W. Linville Signed-off-by: David S. Miller --- include/linux/ieee80211.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 30621c27159f..214821af3d5b 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -81,18 +81,18 @@ /* miscellaneous IEEE 802.11 constants */ -#define IEEE80211_MAX_FRAG_THRESHOLD 2346 -#define IEEE80211_MAX_RTS_THRESHOLD 2347 +#define IEEE80211_MAX_FRAG_THRESHOLD 2352 +#define IEEE80211_MAX_RTS_THRESHOLD 2353 #define IEEE80211_MAX_AID 2007 #define IEEE80211_MAX_TIM_LEN 251 -#define IEEE80211_MAX_DATA_LEN 2304 /* Maximum size for the MA-UNITDATA primitive, 802.11 standard section 6.2.1.1.2. - The figure in section 7.1.2 suggests a body size of up to 2312 - bytes is allowed, which is a bit confusing, I suspect this - represents the 2304 bytes of real data, plus a possible 8 bytes of - WEP IV and ICV. (this interpretation suggested by Ramiro Barreiro) */ + 802.11e clarifies the figure in section 7.1.2. The frame body is + up to 2304 octets long (maximum MSDU size) plus any crypt overhead. */ +#define IEEE80211_MAX_DATA_LEN 2304 +/* 30 byte 4 addr hdr, 2 byte QoS, 2304 byte MSDU, 12 byte crypt, 4 byte FCS */ +#define IEEE80211_MAX_FRAME_LEN 2352 #define IEEE80211_MAX_SSID_LEN 32 -- cgit v1.2.3 From 97c53cacf00d1f5aa04adabfebcc806ca8b22b10 Mon Sep 17 00:00:00 2001 From: "Denis V. Lunev" Date: Mon, 19 Nov 2007 22:26:51 -0800 Subject: [NET]: Make rtnetlink infrastructure network namespace aware (v3) After this patch none of the netlink callback support anything except the initial network namespace but the rtnetlink infrastructure now handles multiple network namespaces. Changes from v2: - IPv6 addrlabel processing Changes from v1: - no need for special rtnl_unlock handling - fixed IPv6 ndisc Signed-off-by: Denis V. Lunev Signed-off-by: Eric W. Biederman Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index e20dcc89a836..b014f6b7fe29 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -620,11 +620,11 @@ extern int __rtattr_parse_nested_compat(struct rtattr *tb[], int maxattr, ({ data = RTA_PAYLOAD(rta) >= len ? RTA_DATA(rta) : NULL; \ __rtattr_parse_nested_compat(tb, max, rta, len); }) -extern int rtnetlink_send(struct sk_buff *skb, u32 pid, u32 group, int echo); -extern int rtnl_unicast(struct sk_buff *skb, u32 pid); -extern int rtnl_notify(struct sk_buff *skb, u32 pid, u32 group, +extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo); +extern int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid); +extern int rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group, struct nlmsghdr *nlh, gfp_t flags); -extern void rtnl_set_sk_err(u32 group, int error); +extern void rtnl_set_sk_err(struct net *net, u32 group, int error); extern int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics); extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, u32 ts, u32 tsage, long expires, -- cgit v1.2.3 From e372c41401993b45c721c4d92730e7e0a79f7c1b Mon Sep 17 00:00:00 2001 From: "Denis V. Lunev" Date: Mon, 19 Nov 2007 22:31:54 -0800 Subject: [NET]: Consolidate net namespace related proc files creation. Signed-off-by: Denis V. Lunev Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/linux/seq_file.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index ebbc02b325fc..648dfeb444db 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -63,5 +63,18 @@ extern struct list_head *seq_list_start_head(struct list_head *head, extern struct list_head *seq_list_next(void *v, struct list_head *head, loff_t *ppos); +struct net; +struct seq_net_private { + struct net *net; +}; + +int seq_open_net(struct inode *, struct file *, + const struct seq_operations *, int); +int seq_release_net(struct inode *, struct file *); +static inline struct net *seq_file_net(struct seq_file *seq) +{ + return ((struct seq_net_private *)seq->private)->net; +} + #endif #endif -- cgit v1.2.3 From 6b4e324164c683a7b4c1bd0be4d85f9a5a0f0e90 Mon Sep 17 00:00:00 2001 From: Ron Rindjunsky Date: Wed, 14 Nov 2007 19:57:38 +0200 Subject: mac80211: adding 802.11n definitions in ieee80211.h This patch adds several structs and definitions to ieee80211.h to support 802.11n draft specifications. As 802.11n depends on and extends the 802.11e standard in several issues, there are also several definitions that belong to 802.11e. Signed-off-by: Ron Rindjunsky Signed-off-by: John W. Linville Signed-off-by: David S. Miller --- include/linux/ieee80211.h | 134 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 134 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 214821af3d5b..3e641590d0c8 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -54,6 +54,8 @@ #define IEEE80211_STYPE_ACTION 0x00D0 /* control */ +#define IEEE80211_STYPE_BACK_REQ 0x0080 +#define IEEE80211_STYPE_BACK 0x0090 #define IEEE80211_STYPE_PSPOLL 0x00A0 #define IEEE80211_STYPE_RTS 0x00B0 #define IEEE80211_STYPE_CTS 0x00C0 @@ -185,6 +187,25 @@ struct ieee80211_mgmt { u8 new_chan; u8 switch_count; } __attribute__((packed)) chan_switch; + struct{ + u8 action_code; + u8 dialog_token; + __le16 capab; + __le16 timeout; + __le16 start_seq_num; + } __attribute__((packed)) addba_req; + struct{ + u8 action_code; + u8 dialog_token; + __le16 status; + __le16 capab; + __le16 timeout; + } __attribute__((packed)) addba_resp; + struct{ + u8 action_code; + __le16 params; + __le16 reason_code; + } __attribute__((packed)) delba; } u; } __attribute__ ((packed)) action; } u; @@ -205,6 +226,66 @@ struct ieee80211_cts { u8 ra[6]; } __attribute__ ((packed)); +/** + * struct ieee80211_bar - HT Block Ack Request + * + * This structure refers to "HT BlockAckReq" as + * described in 802.11n draft section 7.2.1.7.1 + */ +struct ieee80211_bar { + __le16 frame_control; + __le16 duration; + __u8 ra[6]; + __u8 ta[6]; + __u16 control; + __u16 start_seq_num; +} __attribute__((packed)); + +/** + * struct ieee80211_ht_cap - HT capabilities + * + * This structure refers to "HT capabilities element" as + * described in 802.11n draft section 7.3.2.52 + */ +struct ieee80211_ht_cap { + __le16 cap_info; + u8 ampdu_params_info; + u8 supp_mcs_set[16]; + __le16 extended_ht_cap_info; + __le32 tx_BF_cap_info; + u8 antenna_selection_info; +} __attribute__ ((packed)); + +/** + * struct ieee80211_ht_cap - HT additional information + * + * This structure refers to "HT information element" as + * described in 802.11n draft section 7.3.2.53 + */ +struct ieee80211_ht_addt_info { + u8 control_chan; + u8 ht_param; + __le16 operation_mode; + __le16 stbc_param; + u8 basic_set[16]; +} __attribute__ ((packed)); + +/* 802.11n HT capabilities masks */ +#define IEEE80211_HT_CAP_SUP_WIDTH 0x0002 +#define IEEE80211_HT_CAP_MIMO_PS 0x000C +#define IEEE80211_HT_CAP_GRN_FLD 0x0010 +#define IEEE80211_HT_CAP_SGI_20 0x0020 +#define IEEE80211_HT_CAP_SGI_40 0x0040 +#define IEEE80211_HT_CAP_DELAY_BA 0x0400 +#define IEEE80211_HT_CAP_MAX_AMSDU 0x0800 +#define IEEE80211_HT_CAP_AMPDU_FACTOR 0x03 +#define IEEE80211_HT_CAP_AMPDU_DENSITY 0x1C +/* 802.11n HT IE masks */ +#define IEEE80211_HT_IE_CHA_SEC_OFFSET 0x03 +#define IEEE80211_HT_IE_CHA_WIDTH 0x04 +#define IEEE80211_HT_IE_HT_PROTECTION 0x0003 +#define IEEE80211_HT_IE_NON_GF_STA_PRSNT 0x0004 +#define IEEE80211_HT_IE_NON_HT_STA_PRSNT 0x0010 /* Authentication algorithms */ #define WLAN_AUTH_OPEN 0 @@ -271,6 +352,18 @@ enum ieee80211_statuscode { WLAN_STATUS_UNSUPP_RSN_VERSION = 44, WLAN_STATUS_INVALID_RSN_IE_CAP = 45, WLAN_STATUS_CIPHER_SUITE_REJECTED = 46, + /* 802.11e */ + WLAN_STATUS_UNSPECIFIED_QOS = 32, + WLAN_STATUS_ASSOC_DENIED_NOBANDWIDTH = 33, + WLAN_STATUS_ASSOC_DENIED_LOWACK = 34, + WLAN_STATUS_ASSOC_DENIED_UNSUPP_QOS = 35, + WLAN_STATUS_REQUEST_DECLINED = 37, + WLAN_STATUS_INVALID_QOS_PARAM = 38, + WLAN_STATUS_CHANGE_TSPEC = 39, + WLAN_STATUS_WAIT_TS_DELAY = 47, + WLAN_STATUS_NO_DIRECT_LINK = 48, + WLAN_STATUS_STA_NOT_PRESENT = 49, + WLAN_STATUS_STA_NOT_QSTA = 50, }; @@ -301,6 +394,16 @@ enum ieee80211_reasoncode { WLAN_REASON_INVALID_RSN_IE_CAP = 22, WLAN_REASON_IEEE8021X_FAILED = 23, WLAN_REASON_CIPHER_SUITE_REJECTED = 24, + /* 802.11e */ + WLAN_REASON_DISASSOC_UNSPECIFIED_QOS = 32, + WLAN_REASON_DISASSOC_QAP_NO_BANDWIDTH = 33, + WLAN_REASON_DISASSOC_LOW_ACK = 34, + WLAN_REASON_DISASSOC_QAP_EXCEED_TXOP = 35, + WLAN_REASON_QSTA_LEAVE_QBSS = 36, + WLAN_REASON_QSTA_NOT_USE = 37, + WLAN_REASON_QSTA_REQUIRE_SETUP = 38, + WLAN_REASON_QSTA_TIMEOUT = 39, + WLAN_REASON_QSTA_CIPHER_NOT_SUPP = 45, }; @@ -319,6 +422,15 @@ enum ieee80211_eid { WLAN_EID_HP_PARAMS = 8, WLAN_EID_HP_TABLE = 9, WLAN_EID_REQUEST = 10, + /* 802.11e */ + WLAN_EID_QBSS_LOAD = 11, + WLAN_EID_EDCA_PARAM_SET = 12, + WLAN_EID_TSPEC = 13, + WLAN_EID_TCLAS = 14, + WLAN_EID_SCHEDULE = 15, + WLAN_EID_TS_DELAY = 43, + WLAN_EID_TCLAS_PROCESSING = 44, + WLAN_EID_QOS_CAPA = 46, /* 802.11h */ WLAN_EID_PWR_CONSTRAINT = 32, WLAN_EID_PWR_CAPABILITY = 33, @@ -333,6 +445,9 @@ enum ieee80211_eid { /* 802.11g */ WLAN_EID_ERP_INFO = 42, WLAN_EID_EXT_SUPP_RATES = 50, + /* 802.11n */ + WLAN_EID_HT_CAPABILITY = 45, + WLAN_EID_HT_EXTRA_INFO = 61, /* 802.11i */ WLAN_EID_RSN = 48, WLAN_EID_WPA = 221, @@ -341,6 +456,25 @@ enum ieee80211_eid { WLAN_EID_QOS_PARAMETER = 222 }; +/* Action category code */ +enum ieee80211_category { + WLAN_CATEGORY_SPECTRUM_MGMT = 0, + WLAN_CATEGORY_QOS = 1, + WLAN_CATEGORY_DLS = 2, + WLAN_CATEGORY_BACK = 3, + WLAN_CATEGORY_WMM = 17, +}; + +/* BACK action code */ +enum ieee80211_back_actioncode { + WLAN_ACTION_ADDBA_REQ = 0, + WLAN_ACTION_ADDBA_RESP = 1, + WLAN_ACTION_DELBA = 2, +}; + +/* A-MSDU 802.11n */ +#define IEEE80211_QOS_CONTROL_A_MSDU_PRESENT 0x0080 + /* cipher suite selectors */ #define WLAN_CIPHER_SUITE_USE_GROUP 0x000FAC00 #define WLAN_CIPHER_SUITE_WEP40 0x000FAC01 -- cgit v1.2.3 From de4d1db369785c29d68915edfee0cb70e8199f4c Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 21 Nov 2007 22:02:58 +0800 Subject: [LIB]: Introduce struct pcounter This just generalises what was introduced by Eric Dumazet for the struct proto inuse field in 286ab3d46058840d68e5d7d52e316c1f7e98c59f: [NET]: Define infrastructure to keep 'inuse' changes in an efficent SMP/NUMA way. Please look at the comment in there to see the rationale. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/pcounter.h | 102 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 102 insertions(+) create mode 100644 include/linux/pcounter.h (limited to 'include/linux') diff --git a/include/linux/pcounter.h b/include/linux/pcounter.h new file mode 100644 index 000000000000..620aaded4e94 --- /dev/null +++ b/include/linux/pcounter.h @@ -0,0 +1,102 @@ +#ifndef __LINUX_PCOUNTER_H +#define __LINUX_PCOUNTER_H + +struct pcounter { +#ifdef CONFIG_SMP + void (*add)(struct pcounter *self, int inc); + int (*getval)(const struct pcounter *self); + int *per_cpu_values; +#else + int val; +#endif +}; + +/* + * Special macros to let pcounters use a fast version of {getvalue|add} + * using a static percpu variable per pcounter instead of an allocated one, + * saving one dereference. + * This might be changed if/when dynamic percpu vars become fast. + */ +#ifdef CONFIG_SMP +#include +#include + +#define DEFINE_PCOUNTER(NAME) \ +static DEFINE_PER_CPU(int, NAME##_pcounter_values); \ +static void NAME##_pcounter_add(struct pcounter *self, int inc) \ +{ \ + __get_cpu_var(NAME##_pcounter_values) += inc; \ +} \ + \ +static int NAME##_pcounter_getval(const struct pcounter *self) \ +{ \ + int res = 0, cpu; \ + \ + for_each_possible_cpu(cpu) \ + res += per_cpu(NAME##_pcounter_values, cpu); \ + return res; \ +} + +#define PCOUNTER_MEMBER_INITIALIZER(NAME, MEMBER) \ + MEMBER = { \ + .add = NAME##_pcounter_add, \ + .getval = NAME##_pcounter_getval, \ + } + +extern void pcounter_def_add(struct pcounter *self, int inc); +extern int pcounter_def_getval(const struct pcounter *self); + +static inline int pcounter_alloc(struct pcounter *self) +{ + int rc = 0; + if (self->add == NULL) { + self->per_cpu_values = alloc_percpu(int); + if (self->per_cpu_values != NULL) { + self->add = pcounter_def_add; + self->getval = pcounter_def_getval; + } else + rc = 1; + } + return rc; +} + +static inline void pcounter_free(struct pcounter *self) +{ + if (self->per_cpu_values != NULL) { + free_percpu(self->per_cpu_values); + self->per_cpu_values = NULL; + self->getval = NULL; + self->add = NULL; + } +} + +static inline void pcounter_add(struct pcounter *self, int inc) +{ + self->add(self, inc); +} + +static inline int pcounter_getval(const struct pcounter *self) +{ + return self->getval(self); +} + +#else /* CONFIG_SMP */ + +static inline void pcounter_add(struct pcounter *self, int inc) +{ + self->value += inc; +} + +static inline int pcounter_getval(const struct pcounter *self) +{ + return self->val; +} + +#define DEFINE_PCOUNTER(NAME) +#define PCOUNTER_MEMBER_INITIALIZER(NAME, MEMBER) +#define pcounter_alloc(self) 0 +#define pcounter_free(self) + +#endif /* CONFIG_SMP */ + +#endif /* __LINUX_PCOUNTER_H */ -- cgit v1.2.3 From 9b91ad2747891767c0efb4fb965c5dfed8d4f88e Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Tue, 20 Nov 2007 21:56:37 -0200 Subject: [DCCP]: Make PARTOPEN an autonomous state This decouples PARTOPEN from TCP-specific stream-states. It thus addresses the FIXME. The code has been checked with regard to dependency on PARTOPEN and FIN_WAIT1 states (to which PARTOPEN previously was mapped): there is no difference, as PARTOPEN is always referred to directly (i.e. not via the mapping to TCP state). Signed-off-by: Gerrit Renker Signed-off-by: Ian McDonald Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/dccp.h | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 333c3ea82a5d..a0073268808f 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -229,21 +229,13 @@ struct dccp_so_feat { enum dccp_state { DCCP_OPEN = TCP_ESTABLISHED, DCCP_REQUESTING = TCP_SYN_SENT, - DCCP_PARTOPEN = TCP_FIN_WAIT1, /* FIXME: - This mapping is horrible, but TCP has - no matching state for DCCP_PARTOPEN, - as TCP_SYN_RECV is already used by - DCCP_RESPOND, why don't stop using TCP - mapping of states? OK, now we don't use - sk_stream_sendmsg anymore, so doesn't - seem to exist any reason for us to - do the TCP mapping here */ DCCP_LISTEN = TCP_LISTEN, DCCP_RESPOND = TCP_SYN_RECV, DCCP_CLOSING = TCP_CLOSING, DCCP_TIME_WAIT = TCP_TIME_WAIT, DCCP_CLOSED = TCP_CLOSE, - DCCP_MAX_STATES = TCP_MAX_STATES, + DCCP_PARTOPEN = TCP_MAX_STATES, + DCCP_MAX_STATES }; #define DCCP_STATE_MASK 0xf @@ -252,12 +244,12 @@ enum dccp_state { enum { DCCPF_OPEN = TCPF_ESTABLISHED, DCCPF_REQUESTING = TCPF_SYN_SENT, - DCCPF_PARTOPEN = TCPF_FIN_WAIT1, DCCPF_LISTEN = TCPF_LISTEN, DCCPF_RESPOND = TCPF_SYN_RECV, DCCPF_CLOSING = TCPF_CLOSING, DCCPF_TIME_WAIT = TCPF_TIME_WAIT, DCCPF_CLOSED = TCPF_CLOSE, + DCCPF_PARTOPEN = 1 << DCCP_PARTOPEN, }; static inline struct dccp_hdr *dccp_hdr(const struct sk_buff *skb) -- cgit v1.2.3 From e7d0362dd41e760f340c1b500646cc92522bd9d5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 26 Nov 2007 23:34:54 +0800 Subject: [PCOUNTER] Fix build error without CONFIG_SMP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I keep getting this build error and couldn't find anyone fixing it in archives. ...Maybe all net developers except me build just SMP kernels :-). In file included from include/net/sock.h:50, from ipc/mqueue.c:35: include/linux/pcounter.h: In function 'pcounter_add': include/linux/pcounter.h:87: error: 'struct pcounter' has no member named 'value' make[1]: *** [ipc/mqueue.o] Error 1 make: *** [ipc] Error 2 Signed-off-by: Ilpo Järvinen Acked-by: Arnaldo Carvalho de Melo Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/pcounter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pcounter.h b/include/linux/pcounter.h index 620aaded4e94..9c4760a328f3 100644 --- a/include/linux/pcounter.h +++ b/include/linux/pcounter.h @@ -84,7 +84,7 @@ static inline int pcounter_getval(const struct pcounter *self) static inline void pcounter_add(struct pcounter *self, int inc) { - self->value += inc; + self->val += inc; } static inline int pcounter_getval(const struct pcounter *self) -- cgit v1.2.3 From 8d8ad9d7c4bfe79bc91b7fc419ecfb9dcdfe6a51 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Mon, 26 Nov 2007 20:10:50 +0800 Subject: [NET]: Name magic constants in sock_wake_async() The sock_wake_async() performs a bit different actions depending on "how" argument. Unfortunately this argument ony has numerical magic values. I propose to give names to their constants to help people reading this function callers understand what's going on without looking into this function all the time. I suppose this is 2.6.25 material, but if it's not (or the naming seems poor/bad/awful), I can rework it against the current net-2.6 tree. Signed-off-by: Pavel Emelyanov Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/net.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 0235d917d5c3..f95f12c5840c 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -186,6 +186,13 @@ struct net_proto_family { struct iovec; struct kvec; +enum { + SOCK_WAKE_IO, + SOCK_WAKE_WAITD, + SOCK_WAKE_SPACE, + SOCK_WAKE_URG, +}; + extern int sock_wake_async(struct socket *sk, int how, int band); extern int sock_register(const struct net_proto_family *fam); extern void sock_unregister(int family); -- cgit v1.2.3 From c7dc89c0ac8e7c3796bff91becf58ccdbcaf9f18 Mon Sep 17 00:00:00 2001 From: "Fred L. Templin" Date: Thu, 29 Nov 2007 22:11:40 +1100 Subject: [IPV6]: Add RFC4214 support This patch includes support for the Intra-Site Automatic Tunnel Addressing Protocol (ISATAP) per RFC4214. It uses the SIT module, and is configured using extensions to the "iproute2" utility. The diffs are specific to the Linux 2.6.24-rc2 kernel distribution. This version includes the diff for ./include/linux/if.h which was missing in the v2.4 submission and is needed to make the patch compile. The patch has been installed, compiled and tested in a clean 2.6.24-rc2 kernel build area. Signed-off-by: Fred L. Templin Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/if.h | 1 + include/linux/if_tunnel.h | 3 +++ include/linux/in.h | 8 ++++++++ 3 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if.h b/include/linux/if.h index 186070d5c544..5c9d1fa93fef 100644 --- a/include/linux/if.h +++ b/include/linux/if.h @@ -63,6 +63,7 @@ #define IFF_MASTER_ALB 0x10 /* bonding master, balance-alb. */ #define IFF_BONDING 0x20 /* bonding master or slave */ #define IFF_SLAVE_NEEDARP 0x40 /* need ARPs for validation */ +#define IFF_ISATAP 0x80 /* ISATAP interface (RFC4214) */ #define IF_GET_IFACE 0x0001 /* for querying only */ #define IF_GET_PROTO 0x0002 diff --git a/include/linux/if_tunnel.h b/include/linux/if_tunnel.h index 660b5010c2d9..228eb4eb3129 100644 --- a/include/linux/if_tunnel.h +++ b/include/linux/if_tunnel.h @@ -17,6 +17,9 @@ #define GRE_FLAGS __constant_htons(0x00F8) #define GRE_VERSION __constant_htons(0x0007) +/* i_flags values for SIT mode */ +#define SIT_ISATAP 0x0001 + struct ip_tunnel_parm { char name[IFNAMSIZ]; diff --git a/include/linux/in.h b/include/linux/in.h index 3975cbf52f20..a8f00cac8f79 100644 --- a/include/linux/in.h +++ b/include/linux/in.h @@ -253,6 +253,14 @@ struct sockaddr_in { #define ZERONET(x) (((x) & htonl(0xff000000)) == htonl(0x00000000)) #define LOCAL_MCAST(x) (((x) & htonl(0xFFFFFF00)) == htonl(0xE0000000)) +/* Special-Use IPv4 Addresses (RFC3330) */ +#define PRIVATE_10(x) (((x) & htonl(0xff000000)) == htonl(0x0A000000)) +#define LINKLOCAL_169(x) (((x) & htonl(0xffff0000)) == htonl(0xA9FE0000)) +#define PRIVATE_172(x) (((x) & htonl(0xfff00000)) == htonl(0xAC100000)) +#define TEST_192(x) (((x) & htonl(0xffffff00)) == htonl(0xC0000200)) +#define ANYCAST_6TO4(x) (((x) & htonl(0xffffff00)) == htonl(0xC0586300)) +#define PRIVATE_192(x) (((x) & htonl(0xffff0000)) == htonl(0xC0A80000)) +#define TEST_198(x) (((x) & htonl(0xfffe0000)) == htonl(0xC6120000)) #endif #endif /* _LINUX_IN_H */ -- cgit v1.2.3 From f11135a3442996d78dad99933bfdb90d1f6588d3 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Wed, 28 Nov 2007 11:34:53 -0200 Subject: [DCCP]: Dedicated auxiliary states to support passive-close This adds two auxiliary states to deal with passive closes: * PASSIVE_CLOSE (reached from OPEN via reception of Close) and * PASSIVE_CLOSEREQ (reached from OPEN via reception of CloseReq) as internal intermediate states. These states are used to allow a receiver to process unread data before acknowledging the received connection-termination-request (the Close/CloseReq). Without such support, it will happen that passively-closed sockets enter CLOSED state while there is still unprocessed data in the queue; leading to unexpected and erratic API behaviour. PASSIVE_CLOSE has been mapped into TCPF_CLOSE_WAIT, so that the code will seamlessly work with inet_accept() (which tests for this state). The state names are thanks to Arnaldo, who suggested this naming scheme following an earlier revision of this patch. Signed-off-by: Gerrit Renker Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/dccp.h | 56 ++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 39 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index a0073268808f..8b3f9ad3cf04 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -227,29 +227,51 @@ struct dccp_so_feat { #include enum dccp_state { - DCCP_OPEN = TCP_ESTABLISHED, - DCCP_REQUESTING = TCP_SYN_SENT, - DCCP_LISTEN = TCP_LISTEN, - DCCP_RESPOND = TCP_SYN_RECV, - DCCP_CLOSING = TCP_CLOSING, - DCCP_TIME_WAIT = TCP_TIME_WAIT, - DCCP_CLOSED = TCP_CLOSE, - DCCP_PARTOPEN = TCP_MAX_STATES, + DCCP_OPEN = TCP_ESTABLISHED, + DCCP_REQUESTING = TCP_SYN_SENT, + DCCP_LISTEN = TCP_LISTEN, + DCCP_RESPOND = TCP_SYN_RECV, + /* + * States involved in closing a DCCP connection: + * 1) ACTIVE_CLOSEREQ is entered by a server sending a CloseReq. + * + * 2) CLOSING can have three different meanings (RFC 4340, 8.3): + * a. Client has performed active-close, has sent a Close to the server + * from state OPEN or PARTOPEN, and is waiting for the final Reset + * (in this case, SOCK_DONE == 1). + * b. Client is asked to perform passive-close, by receiving a CloseReq + * in (PART)OPEN state. It sends a Close and waits for final Reset + * (in this case, SOCK_DONE == 0). + * c. Server performs an active-close as in (a), keeps TIMEWAIT state. + * + * 3) The following intermediate states are employed to give passively + * closing nodes a chance to process their unread data: + * - PASSIVE_CLOSE (from OPEN => CLOSED) and + * - PASSIVE_CLOSEREQ (from (PART)OPEN to CLOSING; case (b) above). + */ + DCCP_ACTIVE_CLOSEREQ = TCP_FIN_WAIT1, + DCCP_PASSIVE_CLOSE = TCP_CLOSE_WAIT, /* any node receiving a Close */ + DCCP_CLOSING = TCP_CLOSING, + DCCP_TIME_WAIT = TCP_TIME_WAIT, + DCCP_CLOSED = TCP_CLOSE, + DCCP_PARTOPEN = TCP_MAX_STATES, + DCCP_PASSIVE_CLOSEREQ, /* clients receiving CloseReq */ DCCP_MAX_STATES }; -#define DCCP_STATE_MASK 0xf +#define DCCP_STATE_MASK 0x1f #define DCCP_ACTION_FIN (1<<7) enum { - DCCPF_OPEN = TCPF_ESTABLISHED, - DCCPF_REQUESTING = TCPF_SYN_SENT, - DCCPF_LISTEN = TCPF_LISTEN, - DCCPF_RESPOND = TCPF_SYN_RECV, - DCCPF_CLOSING = TCPF_CLOSING, - DCCPF_TIME_WAIT = TCPF_TIME_WAIT, - DCCPF_CLOSED = TCPF_CLOSE, - DCCPF_PARTOPEN = 1 << DCCP_PARTOPEN, + DCCPF_OPEN = TCPF_ESTABLISHED, + DCCPF_REQUESTING = TCPF_SYN_SENT, + DCCPF_LISTEN = TCPF_LISTEN, + DCCPF_RESPOND = TCPF_SYN_RECV, + DCCPF_ACTIVE_CLOSEREQ = TCPF_FIN_WAIT1, + DCCPF_CLOSING = TCPF_CLOSING, + DCCPF_TIME_WAIT = TCPF_TIME_WAIT, + DCCPF_CLOSED = TCPF_CLOSE, + DCCPF_PARTOPEN = (1 << DCCP_PARTOPEN), }; static inline struct dccp_hdr *dccp_hdr(const struct sk_buff *skb) -- cgit v1.2.3 From 0c869620762fea4b3acf6502d9e80840b27ec642 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Wed, 28 Nov 2007 11:59:48 -0200 Subject: [DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/dccp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 8b3f9ad3cf04..312b989c7edb 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -260,7 +260,6 @@ enum dccp_state { }; #define DCCP_STATE_MASK 0x1f -#define DCCP_ACTION_FIN (1<<7) enum { DCCPF_OPEN = TCPF_ESTABLISHED, -- cgit v1.2.3 From a99a00cf1adef2d3dce745c93c9cc8b0a1612c50 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 30 Nov 2007 01:14:30 +1100 Subject: [NET]: Move netfilter checksum helpers to net/core/utils.c This allows to get rid of the CONFIG_NETFILTER dependency of NET_ACT_NAT. This patch redefines the old names to keep the noise low, the next patch converts all users. Signed-off-by: Patrick McHardy Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/netfilter.h | 25 ++++--------------------- 1 file changed, 4 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 25fc12260340..e2bf6d2ffb6c 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -298,27 +298,10 @@ extern void nf_invalidate_cache(int pf); Returns true or false. */ extern int skb_make_writable(struct sk_buff *skb, unsigned int writable_len); -static inline void nf_csum_replace4(__sum16 *sum, __be32 from, __be32 to) -{ - __be32 diff[] = { ~from, to }; - - *sum = csum_fold(csum_partial((char *)diff, sizeof(diff), ~csum_unfold(*sum))); -} - -static inline void nf_csum_replace2(__sum16 *sum, __be16 from, __be16 to) -{ - nf_csum_replace4(sum, (__force __be32)from, (__force __be32)to); -} - -extern void nf_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, - __be32 from, __be32 to, int pseudohdr); - -static inline void nf_proto_csum_replace2(__sum16 *sum, struct sk_buff *skb, - __be16 from, __be16 to, int pseudohdr) -{ - nf_proto_csum_replace4(sum, skb, (__force __be32)from, - (__force __be32)to, pseudohdr); -} +#define nf_csum_replace4 csum_replace4 +#define nf_csum_replace2 csum_replace2 +#define nf_proto_csum_replace4 inet_proto_csum_replace4 +#define nf_proto_csum_replace2 inet_proto_csum_replace2 struct nf_afinfo { unsigned short family; -- cgit v1.2.3 From be0ea7d5da3d99140bde7e5cea328eb111731700 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 30 Nov 2007 01:17:11 +1100 Subject: [NETFILTER]: Convert old checksum helper names Kill the defines again, convert to the new checksum helper names and remove the dependency of NET_ACT_NAT on NETFILTER. Signed-off-by: Patrick McHardy Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/netfilter.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index e2bf6d2ffb6c..f42e4362d50d 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -298,11 +298,6 @@ extern void nf_invalidate_cache(int pf); Returns true or false. */ extern int skb_make_writable(struct sk_buff *skb, unsigned int writable_len); -#define nf_csum_replace4 csum_replace4 -#define nf_csum_replace2 csum_replace2 -#define nf_proto_csum_replace4 inet_proto_csum_replace4 -#define nf_proto_csum_replace2 inet_proto_csum_replace2 - struct nf_afinfo { unsigned short family; __sum16 (*checksum)(struct sk_buff *skb, unsigned int hook, -- cgit v1.2.3 From 29e796fd4de54b8f5bc30d897611210ece4fd0f2 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 30 Nov 2007 23:50:18 +1100 Subject: sysctl: Add register_sysctl_paths function There are a number of modules that register a sysctl table somewhere deeply nested in the sysctl hierarchy, such as fs/nfs, fs/xfs, dev/cdrom, etc. They all specify several dummy ctl_tables for the path name. This patch implements register_sysctl_path that takes an additional path name, and makes up dummy sysctl nodes for each component. This patch was originally written by Olaf Kirch and brought to my attention and reworked some by Olaf Hering. I have changed a few additional things so the bugs are mine. After converting all of the easy callers Olaf Hering observed allyesconfig ARCH=i386, the patch reduces the final binary size by 9369 bytes. .text +897 .data -7008 text data bss dec hex filename 26959310 4045899 4718592 35723801 2211a19 ../vmlinux-vanilla 26960207 4038891 4718592 35717690 221023a ../O-allyesconfig/vmlinux So this change is both a space savings and a code simplification. CC: Olaf Kirch CC: Olaf Hering Signed-off-by: Eric W. Biederman Cc: Serge Hallyn Cc: Daniel Lezcano Cc: Cedric Le Goater Cc: Pavel Emelyanov Signed-off-by: Andrew Morton Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/sysctl.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 4f5047df8a9e..3b6e2c9fbb2e 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -1059,7 +1059,15 @@ struct ctl_table_header struct completion *unregistering; }; +/* struct ctl_path describes where in the hierarchy a table is added */ +struct ctl_path { + const char *procname; + int ctl_name; +}; + struct ctl_table_header *register_sysctl_table(struct ctl_table * table); +struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, + struct ctl_table *table); void unregister_sysctl_table(struct ctl_table_header * table); int sysctl_check_table(struct ctl_table *table); -- cgit v1.2.3 From 23eb06de7d2d333a0f7ebba2da663e00c9c9483e Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 30 Nov 2007 23:52:10 +1100 Subject: sysctl: Remember the ctl_table we passed to register_sysctl_paths By doing this we allow users of register_sysctl_paths that build and dynamically allocate their ctl_table to be simpler. This allows them to just remember the ctl_table_header returned from register_sysctl_paths from which they can now find the ctl_table array they need to free. Signed-off-by: Eric W. Biederman Cc: Serge Hallyn Cc: Daniel Lezcano Cc: Cedric Le Goater Cc: Pavel Emelyanov Signed-off-by: Andrew Morton Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/sysctl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 3b6e2c9fbb2e..77de3bfd8744 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -1057,6 +1057,7 @@ struct ctl_table_header struct list_head ctl_entry; int used; struct completion *unregistering; + struct ctl_table *ctl_table_arg; }; /* struct ctl_path describes where in the hierarchy a table is added */ -- cgit v1.2.3 From e51b6ba077791f2f8c876022b37419be7a2ceec3 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 30 Nov 2007 23:54:00 +1100 Subject: sysctl: Infrastructure for per namespace sysctls This patch implements the basic infrastructure for per namespace sysctls. A list of lists of sysctl headers is added, allowing each namespace to have it's own list of sysctl headers. Each list of sysctl headers has a lookup function to find the first sysctl header in the list, allowing the lists to have a per namespace instance. register_sysct_root is added to tell sysctl.c about additional lists of sysctl_headers. As all of the users are expected to be in kernel no unregister function is provided. sysctl_head_next is updated to walk through the list of lists. __register_sysctl_paths is added to add a new sysctl table on a non-default sysctl list. The only intrusive part of this patch is propagating the information to decided which list of sysctls to use for sysctl_check_table. Signed-off-by: Eric W. Biederman Cc: Serge Hallyn Cc: Daniel Lezcano Cc: Cedric Le Goater Cc: Pavel Emelyanov Signed-off-by: Andrew Morton Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/sysctl.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 77de3bfd8744..89faebfe48b8 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -945,7 +945,10 @@ enum /* For the /proc/sys support */ struct ctl_table; +struct nsproxy; extern struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev); +extern struct ctl_table_header *__sysctl_head_next(struct nsproxy *namespaces, + struct ctl_table_header *prev); extern void sysctl_head_finish(struct ctl_table_header *prev); extern int sysctl_perm(struct ctl_table *table, int op); @@ -1049,6 +1052,13 @@ struct ctl_table void *extra2; }; +struct ctl_table_root { + struct list_head root_list; + struct list_head header_list; + struct list_head *(*lookup)(struct ctl_table_root *root, + struct nsproxy *namespaces); +}; + /* struct ctl_table_header is used to maintain dynamic lists of struct ctl_table trees. */ struct ctl_table_header @@ -1058,6 +1068,7 @@ struct ctl_table_header int used; struct completion *unregistering; struct ctl_table *ctl_table_arg; + struct ctl_table_root *root; }; /* struct ctl_path describes where in the hierarchy a table is added */ @@ -1066,12 +1077,16 @@ struct ctl_path { int ctl_name; }; +void register_sysctl_root(struct ctl_table_root *root); +struct ctl_table_header *__register_sysctl_paths( + struct ctl_table_root *root, struct nsproxy *namespaces, + const struct ctl_path *path, struct ctl_table *table); struct ctl_table_header *register_sysctl_table(struct ctl_table * table); struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, struct ctl_table *table); void unregister_sysctl_table(struct ctl_table_header * table); -int sysctl_check_table(struct ctl_table *table); +int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table); #else /* __KERNEL__ */ -- cgit v1.2.3 From 338e8a79262c3709e314fbcc7ca193323e534934 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Tue, 4 Dec 2007 23:21:50 -0800 Subject: [NETFILTER]: x_tables: add TCPOPTSTRIP target Signed-off-by: Sven Schnelle Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/xt_TCPOPTSTRIP.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 include/linux/netfilter/xt_TCPOPTSTRIP.h (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_TCPOPTSTRIP.h b/include/linux/netfilter/xt_TCPOPTSTRIP.h new file mode 100644 index 000000000000..2db543214ff5 --- /dev/null +++ b/include/linux/netfilter/xt_TCPOPTSTRIP.h @@ -0,0 +1,13 @@ +#ifndef _XT_TCPOPTSTRIP_H +#define _XT_TCPOPTSTRIP_H + +#define tcpoptstrip_set_bit(bmap, idx) \ + (bmap[(idx) >> 5] |= 1U << (idx & 31)) +#define tcpoptstrip_test_bit(bmap, idx) \ + (((1U << (idx & 31)) & bmap[(idx) >> 5]) != 0) + +struct xt_tcpoptstrip_target_info { + u_int32_t strip_bmap[8]; +}; + +#endif /* _XT_TCPOPTSTRIP_H */ -- cgit v1.2.3 From 259d4e41f3ec25f22169daece42729f597b89f9a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 4 Dec 2007 23:24:56 -0800 Subject: [NETFILTER]: x_tables: struct xt_table_info diet Instead of using a big array of NR_CPUS entries, we can compute the size needed at runtime, using nr_cpu_ids This should save some ram (especially on David's machines where NR_CPUS=4096 : 32 KB can be saved per table, and 64KB for dynamically allocated ones (because of slab/slub alignements) ) In particular, the 'bootstrap' tables are not any more static (in data section) but on stack as their size is now very small. This also should reduce the size used on stack in compat functions (get_info() declares an automatic variable, that could be bigger than kernel stack size for big NR_CPUS) Signed-off-by: Eric Dumazet Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 9657c4ee70fc..e305f2d0d4d1 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -269,9 +269,12 @@ struct xt_table_info unsigned int underflow[NF_INET_NUMHOOKS]; /* ipt_entry tables: one per CPU */ - char *entries[NR_CPUS]; + /* Note : this field MUST be the last one, see XT_TABLE_INFO_SZ */ + char *entries[1]; }; +#define XT_TABLE_INFO_SZ (offsetof(struct xt_table_info, entries) \ + + nr_cpu_ids * sizeof(char *)) extern int xt_register_target(struct xt_target *target); extern void xt_unregister_target(struct xt_target *target); extern int xt_register_targets(struct xt_target *target, unsigned int n); -- cgit v1.2.3 From 0265ab44bacc1a1e0e3f5873d8ca2d5a29e33db2 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Tue, 4 Dec 2007 23:27:38 -0800 Subject: [NETFILTER]: merge ipt_owner/ip6t_owner in xt_owner xt_owner merges ipt_owner and ip6t_owner, and adds a flag to match on socket (non-)existence. Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/Kbuild | 1 + include/linux/netfilter/xt_owner.h | 16 ++++++++++++++++ 2 files changed, 17 insertions(+) create mode 100644 include/linux/netfilter/xt_owner.h (limited to 'include/linux') diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild index b87e83a5e070..1e6900278318 100644 --- a/include/linux/netfilter/Kbuild +++ b/include/linux/netfilter/Kbuild @@ -26,6 +26,7 @@ header-y += xt_limit.h header-y += xt_mac.h header-y += xt_mark.h header-y += xt_multiport.h +header-y += xt_owner.h header-y += xt_pkttype.h header-y += xt_policy.h header-y += xt_realm.h diff --git a/include/linux/netfilter/xt_owner.h b/include/linux/netfilter/xt_owner.h new file mode 100644 index 000000000000..eacd34efebd5 --- /dev/null +++ b/include/linux/netfilter/xt_owner.h @@ -0,0 +1,16 @@ +#ifndef _XT_OWNER_MATCH_H +#define _XT_OWNER_MATCH_H + +enum { + XT_OWNER_UID = 1 << 0, + XT_OWNER_GID = 1 << 1, + XT_OWNER_SOCKET = 1 << 2, +}; + +struct xt_owner_match_info { + u_int32_t uid; + u_int32_t gid; + u_int8_t match, invert; +}; + +#endif /* _XT_OWNER_MATCH_H */ -- cgit v1.2.3 From e2cf5ecbea861ff05105bbd40f4f0d7823d9e213 Mon Sep 17 00:00:00 2001 From: Laszlo Attila Toth Date: Tue, 4 Dec 2007 23:30:18 -0800 Subject: [NETFILTER]: ipt_addrtype: limit address type checking to an interface Addrtype match has a new revision (1), which lets address type checking limited to the interface the current packet belongs to. Either incoming or outgoing interface can be used depending on the current hook. In the FORWARD hook two maches should be used if both interfaces have to be checked. The new structure is ipt_addrtype_info_v1. Revision 0 lets older userspace programs use the match as earlier. ipt_addrtype_info is used. Signed-off-by: Laszlo Attila Toth Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ipt_addrtype.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ipt_addrtype.h b/include/linux/netfilter_ipv4/ipt_addrtype.h index 166ed01a8122..446de6aef983 100644 --- a/include/linux/netfilter_ipv4/ipt_addrtype.h +++ b/include/linux/netfilter_ipv4/ipt_addrtype.h @@ -1,6 +1,20 @@ #ifndef _IPT_ADDRTYPE_H #define _IPT_ADDRTYPE_H +enum { + IPT_ADDRTYPE_INVERT_SOURCE = 0x0001, + IPT_ADDRTYPE_INVERT_DEST = 0x0002, + IPT_ADDRTYPE_LIMIT_IFACE_IN = 0x0004, + IPT_ADDRTYPE_LIMIT_IFACE_OUT = 0x0008, +}; + +struct ipt_addrtype_info_v1 { + u_int16_t source; /* source-type mask */ + u_int16_t dest; /* dest-type mask */ + u_int32_t flags; +}; + +/* revision 0 */ struct ipt_addrtype_info { u_int16_t source; /* source-type mask */ u_int16_t dest; /* dest-type mask */ -- cgit v1.2.3 From f1095ab51d4297d4a84b64a65c71054183a73486 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Tue, 4 Dec 2007 23:38:30 -0800 Subject: [NETFILTER]: IPv6 capable xt_tos v1 match Extends the xt_dscp match by xt_tos v1 to add support for selectively matching any bit in the IPv4 TOS and IPv6 Priority fields. (ipt_tos and xt_dscp only accepted a limited range of possible values.) Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/xt_dscp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_dscp.h b/include/linux/netfilter/xt_dscp.h index 1da61e6acaf7..f49bc1a648dc 100644 --- a/include/linux/netfilter/xt_dscp.h +++ b/include/linux/netfilter/xt_dscp.h @@ -20,4 +20,10 @@ struct xt_dscp_info { u_int8_t invert; }; +struct xt_tos_match_info { + u_int8_t tos_mask; + u_int8_t tos_value; + u_int8_t invert; +}; + #endif /* _XT_DSCP_H */ -- cgit v1.2.3 From 5c350e5a380333c64da8580fa134a2fd8e71fea4 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Tue, 4 Dec 2007 23:39:09 -0800 Subject: [NETFILTER]: IPv6 capable xt_TOS v1 target Extends the xt_DSCP target by xt_TOS v1 to add support for selectively setting and flipping any bit in the IPv4 TOS and IPv6 Priority fields. (ipt_TOS and xt_DSCP only accepted a limited range of possible values.) Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/xt_DSCP.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_DSCP.h b/include/linux/netfilter/xt_DSCP.h index 3c7c963997bd..14da1968e2c6 100644 --- a/include/linux/netfilter/xt_DSCP.h +++ b/include/linux/netfilter/xt_DSCP.h @@ -17,4 +17,9 @@ struct xt_DSCP_info { u_int8_t dscp; }; +struct xt_tos_target_info { + u_int8_t tos_value; + u_int8_t tos_mask; +}; + #endif /* _XT_DSCP_TARGET_H */ -- cgit v1.2.3 From 5859034d7eb8793d3d78d3af515c4175e7b9d03a Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 4 Dec 2007 23:40:05 -0800 Subject: [NETFILTER]: x_tables: add RATEEST target Add new rate estimator target (using gen_estimator). In combination with the rateest match (next patch) this can be used for load-based multipath routing. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/Kbuild | 1 + include/linux/netfilter/xt_RATEEST.h | 11 +++++++++++ 2 files changed, 12 insertions(+) create mode 100644 include/linux/netfilter/xt_RATEEST.h (limited to 'include/linux') diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild index 1e6900278318..707a15854430 100644 --- a/include/linux/netfilter/Kbuild +++ b/include/linux/netfilter/Kbuild @@ -10,6 +10,7 @@ header-y += xt_DSCP.h header-y += xt_MARK.h header-y += xt_NFLOG.h header-y += xt_NFQUEUE.h +header-y += xt_RATEEST.h header-y += xt_SECMARK.h header-y += xt_TCPMSS.h header-y += xt_comment.h diff --git a/include/linux/netfilter/xt_RATEEST.h b/include/linux/netfilter/xt_RATEEST.h new file mode 100644 index 000000000000..670f2e49d4fb --- /dev/null +++ b/include/linux/netfilter/xt_RATEEST.h @@ -0,0 +1,11 @@ +#ifndef _XT_RATEEST_TARGET_H +#define _XT_RATEEST_TARGET_H + +struct xt_rateest_target_info { + char name[IFNAMSIZ]; + int8_t interval; + u_int8_t ewma_log; + struct xt_rateest *est __attribute__((aligned(8))); +}; + +#endif /* _XT_RATEEST_TARGET_H */ -- cgit v1.2.3 From 50c164a81f1c0dfad056f99e5685537fdd0f07dd Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 4 Dec 2007 13:02:19 +0100 Subject: [NETFILTER]: x_tables: add rateest match Add rate estimator match. The rate estimator match can match on estimated rates by the RATEEST target. It supports matching on absolute bps/pps values, comparing two rate estimators and matching on the difference between two rate estimators. This is what I use to route outgoing data connections from a FTP server over two lines based on the available bandwidth: # estimate outgoing rates iptables -t mangle -A POSTROUTING -o eth0 -j RATEEST --rateest-name eth0 \ --rateest-interval 250ms \ --rateest-ewma 0.5s iptables -t mangle -A POSTROUTING -o ppp0 -j RATEEST --rateest-name ppp0 \ --rateest-interval 250ms \ --rateest-ewma 0.5s # mark based on available bandwidth iptables -t mangle -A BALANCE -m state --state NEW \ -m helper --helper ftp \ -m rateest --rateest-delta \ --rateest1 eth0 \ --rateest-bps1 2.5mbit \ --rateest-gt \ --rateest2 ppp0 \ --rateest-bps2 2mbit \ -j CONNMARK --set-mark 0x1 iptables -t mangle -A BALANCE -m state --state NEW \ -m helper --helper ftp \ -m rateest --rateest-delta \ --rateest1 ppp0 \ --rateest-bps1 2mbit \ --rateest-gt \ --rateest2 eth0 \ --rateest-bps2 2.5mbit \ -j CONNMARK --set-mark 0x2 iptables -t mangle -A BALANCE -j CONNMARK --restore-mark Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/Kbuild | 1 + include/linux/netfilter/xt_rateest.h | 33 +++++++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+) create mode 100644 include/linux/netfilter/xt_rateest.h (limited to 'include/linux') diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild index 707a15854430..ac9e6429f747 100644 --- a/include/linux/netfilter/Kbuild +++ b/include/linux/netfilter/Kbuild @@ -30,6 +30,7 @@ header-y += xt_multiport.h header-y += xt_owner.h header-y += xt_pkttype.h header-y += xt_policy.h +header-y += xt_rateest.h header-y += xt_realm.h header-y += xt_sctp.h header-y += xt_state.h diff --git a/include/linux/netfilter/xt_rateest.h b/include/linux/netfilter/xt_rateest.h new file mode 100644 index 000000000000..51948e15aea2 --- /dev/null +++ b/include/linux/netfilter/xt_rateest.h @@ -0,0 +1,33 @@ +#ifndef _XT_RATEEST_MATCH_H +#define _XT_RATEEST_MATCH_H + +enum xt_rateest_match_flags { + XT_RATEEST_MATCH_INVERT = 1<<0, + XT_RATEEST_MATCH_ABS = 1<<1, + XT_RATEEST_MATCH_REL = 1<<2, + XT_RATEEST_MATCH_DELTA = 1<<3, + XT_RATEEST_MATCH_BPS = 1<<4, + XT_RATEEST_MATCH_PPS = 1<<5, +}; + +enum xt_rateest_match_mode { + XT_RATEEST_MATCH_NONE, + XT_RATEEST_MATCH_EQ, + XT_RATEEST_MATCH_LT, + XT_RATEEST_MATCH_GT, +}; + +struct xt_rateest_match_info { + char name1[IFNAMSIZ]; + char name2[IFNAMSIZ]; + u_int16_t flags; + u_int16_t mode; + u_int32_t bps1; + u_int32_t pps1; + u_int32_t bps2; + u_int32_t pps2; + struct xt_rateest *est1 __attribute__((aligned(8))); + struct xt_rateest *est2 __attribute__((aligned(8))); +}; + +#endif /* _XT_RATEEST_MATCH_H */ -- cgit v1.2.3 From 1841a4c7ae106b7a3e2521db55f4d8bb8a0988d5 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 5 Dec 2007 01:22:05 -0800 Subject: [NETFILTER]: nf_ct_h323: remove ipv6 module dependency nf_conntrack_h323 needs ip6_route_output for the call forwarding filter. Add a ->route function to nf_afinfo and use that to avoid pulling in the ipv6 module. Fix the #ifdef for the IPv6 code while I'm at it - the IPv6 support is only needed when IPv6 conntrack is enabled. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index f42e4362d50d..9bfc7d4f5868 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -298,10 +298,12 @@ extern void nf_invalidate_cache(int pf); Returns true or false. */ extern int skb_make_writable(struct sk_buff *skb, unsigned int writable_len); +struct flowi; struct nf_afinfo { unsigned short family; __sum16 (*checksum)(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); + int (*route)(struct dst_entry **dst, struct flowi *fl); void (*saveroute)(const struct sk_buff *skb, struct nf_info *info); int (*reroute)(struct sk_buff *skb, -- cgit v1.2.3 From e3ac5298159c5286cef86f0865d4fa6a606bd391 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 5 Dec 2007 01:23:57 -0800 Subject: [NETFILTER]: nf_queue: make queue_handler const Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 9bfc7d4f5868..c2c3fafa5fd0 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -281,11 +281,11 @@ struct nf_queue_handler { void *data; char *name; }; -extern int nf_register_queue_handler(int pf, - struct nf_queue_handler *qh); +extern int nf_register_queue_handler(int pf, + const struct nf_queue_handler *qh); extern int nf_unregister_queue_handler(int pf, - struct nf_queue_handler *qh); -extern void nf_unregister_queue_handlers(struct nf_queue_handler *qh); + const struct nf_queue_handler *qh); +extern void nf_unregister_queue_handlers(const struct nf_queue_handler *qh); extern void nf_reinject(struct sk_buff *skb, struct nf_info *info, unsigned int verdict); -- cgit v1.2.3 From f9d8928f8340ab8e76f1da4799cb19a6ff58b83d Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 5 Dec 2007 01:24:30 -0800 Subject: [NETFILTER]: nf_queue: remove unused data pointer Remove the data pointer from struct nf_queue_handler. It has never been used and is useless for the only handler that really matters, nfnetlink_queue, since the handler is shared between all instances. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index c2c3fafa5fd0..1ba60112ab83 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -277,8 +277,7 @@ int compat_nf_getsockopt(struct sock *sk, int pf, int optval, /* Packet queuing */ struct nf_queue_handler { int (*outfn)(struct sk_buff *skb, struct nf_info *info, - unsigned int queuenum, void *data); - void *data; + unsigned int queuenum); char *name; }; extern int nf_register_queue_handler(int pf, -- cgit v1.2.3 From c01cd429fc118c5db92475c5f08b307718aa4efc Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 5 Dec 2007 01:24:48 -0800 Subject: [NETFILTER]: nf_queue: move queueing related functions/struct to seperate header Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter.h | 32 ++------------------------------ 1 file changed, 2 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 1ba60112ab83..5fe4ef401cc8 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -101,19 +101,6 @@ struct nf_sockopt_ops struct module *owner; }; -/* Each queued (to userspace) skbuff has one of these. */ -struct nf_info -{ - /* The ops struct which sent us to userspace. */ - struct nf_hook_ops *elem; - - /* If we're sent to userspace, this keeps housekeeping info */ - int pf; - unsigned int hook; - struct net_device *indev, *outdev; - int (*okfn)(struct sk_buff *); -}; - /* Function to register/unregister hook points. */ int nf_register_hook(struct nf_hook_ops *reg); void nf_unregister_hook(struct nf_hook_ops *reg); @@ -274,21 +261,6 @@ int compat_nf_setsockopt(struct sock *sk, int pf, int optval, int compat_nf_getsockopt(struct sock *sk, int pf, int optval, char __user *opt, int *len); -/* Packet queuing */ -struct nf_queue_handler { - int (*outfn)(struct sk_buff *skb, struct nf_info *info, - unsigned int queuenum); - char *name; -}; -extern int nf_register_queue_handler(int pf, - const struct nf_queue_handler *qh); -extern int nf_unregister_queue_handler(int pf, - const struct nf_queue_handler *qh); -extern void nf_unregister_queue_handlers(const struct nf_queue_handler *qh); -extern void nf_reinject(struct sk_buff *skb, - struct nf_info *info, - unsigned int verdict); - /* FIXME: Before cache is ever used, this must be implemented for real. */ extern void nf_invalidate_cache(int pf); @@ -298,6 +270,8 @@ extern void nf_invalidate_cache(int pf); extern int skb_make_writable(struct sk_buff *skb, unsigned int writable_len); struct flowi; +struct nf_info; + struct nf_afinfo { unsigned short family; __sum16 (*checksum)(struct sk_buff *skb, unsigned int hook, @@ -334,8 +308,6 @@ nf_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, extern int nf_register_afinfo(struct nf_afinfo *afinfo); extern void nf_unregister_afinfo(struct nf_afinfo *afinfo); -#define nf_info_reroute(x) ((void *)x + sizeof(struct nf_info)) - #include extern void (*ip_nat_decode_session)(struct sk_buff *, struct flowi *); -- cgit v1.2.3 From 02f014d88831f73b895c1fe09badb66c88e932d3 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 5 Dec 2007 01:26:33 -0800 Subject: [NETFILTER]: nf_queue: move list_head/skb/id to struct nf_info Move common fields for queue management to struct nf_info and rename it to struct nf_queue_entry. The avoids one allocation/free per packet and simplifies the code a bit. Alternatively we could add some private room at the tail, but since all current users use identical structs this seems easier. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 5fe4ef401cc8..f25eec595807 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -270,7 +270,7 @@ extern void nf_invalidate_cache(int pf); extern int skb_make_writable(struct sk_buff *skb, unsigned int writable_len); struct flowi; -struct nf_info; +struct nf_queue_entry; struct nf_afinfo { unsigned short family; @@ -278,9 +278,9 @@ struct nf_afinfo { unsigned int dataoff, u_int8_t protocol); int (*route)(struct dst_entry **dst, struct flowi *fl); void (*saveroute)(const struct sk_buff *skb, - struct nf_info *info); + struct nf_queue_entry *entry); int (*reroute)(struct sk_buff *skb, - const struct nf_info *info); + const struct nf_queue_entry *entry); int route_key_size; }; -- cgit v1.2.3 From 36f0bebd9865dc7e327777fca34b75e65cbfd1a6 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Thu, 24 Jan 2008 17:04:49 -0800 Subject: [TR]: Use ctl paths to register net/token-ring/ table The same thing for token-ring - use ctl paths and get rid of external references on the tr_table. Unfortunately, I couldn't split this patch into cleanup and use-the-paths parts. As a lame excuse I can say, that the cleanup is just moving the tr_table from one file to another - closet to a single variable, that this ctl table tunes. Since the source file becomes empty after the move, I remove it. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/linux/if_tr.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_tr.h b/include/linux/if_tr.h index 046e9d95ba9a..5bcec8b2c5e2 100644 --- a/include/linux/if_tr.h +++ b/include/linux/if_tr.h @@ -49,9 +49,6 @@ static inline struct trh_hdr *tr_hdr(const struct sk_buff *skb) { return (struct trh_hdr *)skb_mac_header(skb); } -#ifdef CONFIG_SYSCTL -extern struct ctl_table tr_table[]; -#endif #endif /* This is an Token-Ring LLC structure */ -- cgit v1.2.3 From 08913681e484f3f0db949dd0809012e089846216 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Wed, 5 Dec 2007 01:42:49 -0800 Subject: [NET]: Remove the empty net_table I have removed all the entries from this table (core_table, ipv4_table and tr_table), so now we can safely drop it. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/linux/net.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index f95f12c5840c..c414d90e647b 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -337,7 +337,6 @@ static const struct proto_ops name##_ops = { \ #ifdef CONFIG_SYSCTL #include -extern ctl_table net_table[]; extern int net_msg_cost; extern int net_msg_burst; #endif -- cgit v1.2.3 From 68dd299bc84dede6aef32e6f4777a676314f5d21 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Wed, 5 Dec 2007 01:44:58 -0800 Subject: [INET]: Merge sys.net.ipv4.ip_forward and sys.net.ipv4.conf.all.forwarding AFAIS these two entries should do the same thing - change the forwarding state on ipv4_devconf and on all the devices. I propose to merge the handlers together using ctl paths. The inet_forward_change() is static after this and I move it higher to be closer to other "propagation" helpers and to avoid diff making patches based on { and } matching :) i.e. - make them easier to read. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index d83fee2dc643..dd093ea4c489 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -135,7 +135,6 @@ extern struct in_device *inetdev_by_index(int); extern __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope); extern __be32 inet_confirm_addr(const struct net_device *dev, __be32 dst, __be32 local, int scope); extern struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); -extern void inet_forward_change(void); static __inline__ int inet_ifa_match(__be32 addr, struct in_ifaddr *ifa) { -- cgit v1.2.3 From 27ab2568649d5ba6c5a20212079b7c4f6da4ca0d Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 5 Dec 2007 01:51:58 -0800 Subject: [UDP]: Avoid repeated counting of checksum errors due to peeking Currently it is possible for two processes to peek on the same socket and end up incrementing the error counter twice for the same packet. This patch fixes it by making skb_kill_datagram return whether it succeeded in unlinking the packet and only incrementing the counter if it did. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d39f53ef66bb..17b3f70fbbc3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1549,7 +1549,7 @@ extern int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb, int hlen, struct iovec *iov); extern void skb_free_datagram(struct sock *sk, struct sk_buff *skb); -extern void skb_kill_datagram(struct sock *sk, struct sk_buff *skb, +extern int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); extern __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum); -- cgit v1.2.3 From a59322be07c964e916d15be3df473fb7ba20c41e Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 5 Dec 2007 01:53:40 -0800 Subject: [UDP]: Only increment counter on first peek/recv The previous move of the the UDP inDatagrams counter caused each peek of the same packet to be counted separately. This may be undesirable. This patch fixes this by adding a bit to sk_buff to record whether this packet has already been seen through skb_recv_datagram. We then only increment the counter when the packet is seen for the first time. The only dodgy part is the fact that skb_recv_datagram doesn't have a good way of returning this new bit of information. So I've added a new function __skb_recv_datagram that does return this and made skb_recv_datagram a wrapper around it. The plan is to eventually replace all uses of skb_recv_datagram with this new function at which time it can be renamed its proper name. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 17b3f70fbbc3..c618fbf7d173 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -288,6 +288,7 @@ struct sk_buff { __u8 pkt_type:3, fclone:2, ipvs_property:1, + peeked:1, nf_trace:1; __be16 protocol; @@ -1538,6 +1539,8 @@ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) skb = skb->prev) +extern struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, + int *peeked, int *err); extern struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock, int *err); extern unsigned int datagram_poll(struct file *file, struct socket *sock, -- cgit v1.2.3 From f4d900a2cae94256f56be7769734100c7054bf00 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 5 Dec 2007 03:31:53 -0800 Subject: [NETLINK]: Mark attribute construction exception unlikely Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index d5bfaba595c7..2aee0f510876 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -245,7 +245,7 @@ __nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len, int flags) } #define NLMSG_NEW(skb, pid, seq, type, len, flags) \ -({ if (skb_tailroom(skb) < (int)NLMSG_SPACE(len)) \ +({ if (unlikely(skb_tailroom(skb) < (int)NLMSG_SPACE(len))) \ goto nlmsg_failure; \ __nlmsg_put(skb, pid, seq, type, len, flags); }) -- cgit v1.2.3 From b8e1f9b5c37e77cc8f978a58859b35fe5edd5542 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Sat, 8 Dec 2007 00:12:33 -0800 Subject: [NET] sysctl: make sysctl_somaxconn per-namespace Just move the variable on the struct net and adjust its usage. Others sysctls from sys.net.core table are more difficult to virtualize (i.e. make them per-namespace), but I'll look at them as well a bit later. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/linux/socket.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index eb5bdd59a644..bd2b30a74e76 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -24,7 +24,6 @@ struct __kernel_sockaddr_storage { #include /* pid_t */ #include /* __user */ -extern int sysctl_somaxconn; #ifdef CONFIG_PROC_FS struct seq_file; extern void socket_seq_show(struct seq_file *seq); -- cgit v1.2.3 From 01ecfe9ba63aa0f23bbdb15371916ba4d5382330 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Tue, 11 Dec 2007 02:16:47 -0800 Subject: [IPV4]: Cleanup IN_DEV_MFORWARD macro This is essentially IN_DEV_ANDCONF with proper arguments. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index dd093ea4c489..962a062b44ff 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -78,9 +78,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) (max(IPV4_DEVCONF_ALL(attr), IN_DEV_CONF_GET((in_dev), attr))) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) -#define IN_DEV_MFORWARD(in_dev) (IPV4_DEVCONF_ALL(MC_FORWARDING) && \ - IPV4_DEVCONF((in_dev)->cnf, \ - MC_FORWARDING)) +#define IN_DEV_MFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), MC_FORWARDING) #define IN_DEV_RPFILTER(in_dev) IN_DEV_ANDCONF((in_dev), RP_FILTER) #define IN_DEV_SOURCE_ROUTE(in_dev) IN_DEV_ANDCONF((in_dev), \ ACCEPT_SOURCE_ROUTE) -- cgit v1.2.3 From d5422efe680fc55010c6ddca2370ca9548a96355 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 12 Dec 2007 10:44:16 -0800 Subject: [IPSEC]: Added xfrm_decode_session_reverse and xfrmX_policy_check_reverse RFC 4301 requires us to relookup ICMP traffic that does not match any policies using the reverse of its payload. This patch adds the functions xfrm_decode_session_reverse and xfrmX_policy_check_reverse so we can get the reverse flow to perform such a lookup. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/xfrm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index b58adc52448d..c0e41e02234f 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -114,6 +114,7 @@ enum XFRM_POLICY_IN = 0, XFRM_POLICY_OUT = 1, XFRM_POLICY_FWD = 2, + XFRM_POLICY_MASK = 3, XFRM_POLICY_MAX = 3 }; -- cgit v1.2.3 From 8b7817f3a959ed99d7443afc12f78a7e1fcc2063 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 12 Dec 2007 10:44:43 -0800 Subject: [IPSEC]: Add ICMP host relookup support RFC 4301 requires us to relookup ICMP traffic that does not match any policies using the reverse of its payload. This patch implements this for ICMP traffic that originates from or terminates on localhost. This is activated on outbound with the new policy flag XFRM_POLICY_ICMP, and on inbound by the new state flag XFRM_STATE_ICMP. On inbound the policy check is now performed by the ICMP protocol so that it can repeat the policy check where necessary. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/xfrm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index c0e41e02234f..1131eabfaa2a 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -329,6 +329,7 @@ struct xfrm_usersa_info { #define XFRM_STATE_DECAP_DSCP 2 #define XFRM_STATE_NOPMTUDISC 4 #define XFRM_STATE_WILDRECV 8 +#define XFRM_STATE_ICMP 16 }; struct xfrm_usersa_id { @@ -363,6 +364,8 @@ struct xfrm_userpolicy_info { #define XFRM_POLICY_BLOCK 1 __u8 flags; #define XFRM_POLICY_LOCALOK 1 /* Allow user to override global policy */ + /* Automatically expand selector to include matching ICMP payloads. */ +#define XFRM_POLICY_ICMP 2 __u8 share; }; -- cgit v1.2.3 From b8599d20708fa3bde1e414689f3474560c2d990b Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Thu, 13 Dec 2007 12:25:01 -0200 Subject: [DCCP]: Support for server holding timewait state This adds a socket option and signalling support for the case where the server holds timewait state on closing the connection, as described in RFC 4340, 8.3. Since holding timewait state at the server is the non-usual case, it is enabled via a socket option. Documentation for this socket option has been added. The setsockopt statement has been made resilient against different possible cases of expressing boolean `true' values using a suggestion by Ian McDonald. Signed-off-by: Gerrit Renker Signed-off-by: Ian McDonald Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/dccp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 312b989c7edb..c676021603f5 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -205,6 +205,7 @@ struct dccp_so_feat { #define DCCP_SOCKOPT_CHANGE_L 3 #define DCCP_SOCKOPT_CHANGE_R 4 #define DCCP_SOCKOPT_GET_CUR_MPS 5 +#define DCCP_SOCKOPT_SERVER_TIMEWAIT 6 #define DCCP_SOCKOPT_SEND_CSCOV 10 #define DCCP_SOCKOPT_RECV_CSCOV 11 #define DCCP_SOCKOPT_CCID_RX_INFO 128 @@ -492,6 +493,7 @@ struct dccp_ackvec; * @dccps_role - role of this sock, one of %dccp_role * @dccps_hc_rx_insert_options - receiver wants to add options when acking * @dccps_hc_tx_insert_options - sender wants to add options when sending + * @dccps_server_timewait - server holds timewait state on close (RFC 4340, 8.3) * @dccps_xmit_timer - timer for when CCID is not ready to send * @dccps_syn_rtt - RTT sample from Request/Response exchange (in usecs) */ @@ -528,6 +530,7 @@ struct dccp_sock { enum dccp_role dccps_role:2; __u8 dccps_hc_rx_insert_options:1; __u8 dccps_hc_tx_insert_options:1; + __u8 dccps_server_timewait:1; struct timer_list dccps_xmit_timer; }; -- cgit v1.2.3 From 8b819412481494fb6861c08d360b75fabcbbfbbf Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Thu, 13 Dec 2007 12:29:24 -0200 Subject: [DCCP]: Allow to parse options on Request Sockets The option parsing code currently only parses on full sk's. This causes a problem for options sent during the initial handshake (in particular timestamps and feature-negotiation options). Therefore, this patch extends the option parsing code with an additional argument for request_socks: if it is non-NULL, options are parsed on the request socket, otherwise the normal path (parsing on the sk) is used. Subsequent patches, which implement feature negotiation during connection setup, make use of this facility. Signed-off-by: Gerrit Renker Signed-off-by: Ian McDonald Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/dccp.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index c676021603f5..7214031461d3 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -407,8 +407,6 @@ struct dccp_opt_pend { extern void dccp_minisock_init(struct dccp_minisock *dmsk); -extern int dccp_parse_options(struct sock *sk, struct sk_buff *skb); - struct dccp_request_sock { struct inet_request_sock dreq_inet_rsk; __u64 dreq_iss; @@ -423,6 +421,9 @@ static inline struct dccp_request_sock *dccp_rsk(const struct request_sock *req) extern struct inet_timewait_death_row dccp_death_row; +extern int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, + struct sk_buff *skb); + struct dccp_options_received { u32 dccpor_ndp; /* only 24 bits */ u32 dccpor_timestamp; -- cgit v1.2.3 From b4d4f7c70fd3361c6c889752e08ea9be304cf5f4 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Thu, 13 Dec 2007 12:37:19 -0200 Subject: [DCCP]: Handle timestamps on Request/Response exchange separately In DCCP, timestamps can occur on packets anytime, CCID3 uses a timestamp(/echo) on the Request/Response exchange. This patch addresses the following situation: * timestamps are recorded on the listening socket; * Responses are sent from dccp_request_sockets; * suppose two connections reach the listening socket with very small time in between: * the first timestamp value gets overwritten by the second connection request. This is not really good, so this patch separates timestamps into * those which are received by the server during the initial handshake (on dccp_request_sock); * those which are received by the client or the client after connection establishment. As before, a timestamp of 0 is regarded as indicating that no (meaningful) timestamp has been received (in addition, a warning message is printed if hosts send 0-valued timestamps). The timestamp-echoing now works as follows: * when a timestamp is present on the initial Request, it is placed into dreq, due to the call to dccp_parse_options in dccp_v{4,6}_conn_request; * when a timestamp is present on the Ack leading from RESPOND => OPEN, it is copied over from the request_sock into the child cocket in dccp_create_openreq_child; * timestamps received on an (established) dccp_sock are treated as before. Since Elapsed Time is measured in hundredths of milliseconds (13.2), the new dccp_timestamp() function is used, as it is expected that the time between receiving the timestamp and sending the timestamp echo will be very small against the wrap-around time. As a byproduct, this allows smaller timestamping-time fields. Furthermore, inserting the Timestamp Echo option has been taken out of the block starting with '!dccp_packet_without_ack()', since Timestamp Echo can be carried on any packet (5.8 and 13.3). Signed-off-by: Gerrit Renker Acked-by: Ian McDonald Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/dccp.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 7214031461d3..484e45c7c89a 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -407,11 +407,23 @@ struct dccp_opt_pend { extern void dccp_minisock_init(struct dccp_minisock *dmsk); +/** + * struct dccp_request_sock - represent DCCP-specific connection request + * @dreq_inet_rsk: structure inherited from + * @dreq_iss: initial sequence number sent on the Response (RFC 4340, 7.1) + * @dreq_isr: initial sequence number received on the Request + * @dreq_service: service code present on the Request (there is just one) + * The following two fields are analogous to the ones in dccp_sock: + * @dreq_timestamp_echo: last received timestamp to echo (13.1) + * @dreq_timestamp_echo: the time of receiving the last @dreq_timestamp_echo + */ struct dccp_request_sock { struct inet_request_sock dreq_inet_rsk; __u64 dreq_iss; __u64 dreq_isr; __be32 dreq_service; + __u32 dreq_timestamp_echo; + __u32 dreq_timestamp_time; }; static inline struct dccp_request_sock *dccp_rsk(const struct request_sock *req) @@ -477,8 +489,8 @@ struct dccp_ackvec; * @dccps_gar - greatest valid ack number received on a non-Sync; initialized to %dccps_iss * @dccps_service - first (passive sock) or unique (active sock) service code * @dccps_service_list - second .. last service code on passive socket - * @dccps_timestamp_time - time of latest TIMESTAMP option * @dccps_timestamp_echo - latest timestamp received on a TIMESTAMP option + * @dccps_timestamp_time - time of receiving latest @dccps_timestamp_echo * @dccps_l_ack_ratio - feature-local Ack Ratio * @dccps_r_ack_ratio - feature-remote Ack Ratio * @dccps_pcslen - sender partial checksum coverage (via sockopt) @@ -514,8 +526,8 @@ struct dccp_sock { __u64 dccps_gar; __be32 dccps_service; struct dccp_service_list *dccps_service_list; - ktime_t dccps_timestamp_time; __u32 dccps_timestamp_echo; + __u32 dccps_timestamp_time; __u16 dccps_l_ack_ratio; __u16 dccps_r_ack_ratio; __u16 dccps_pcslen; -- cgit v1.2.3 From 586f12115264b767ea6a48ce081ca25a39c1e3dd Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Sun, 16 Dec 2007 13:32:48 -0800 Subject: [IPV4]: Switch users of ipv4_devconf(_all) to use the pernet one These are scattered over the code, but almost all the "critical" places already have the proper struct net at hand except for snmp proc showing function and routing rtnl handler. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 962a062b44ff..b3c5081de02d 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -44,7 +44,8 @@ struct in_device }; #define IPV4_DEVCONF(cnf, attr) ((cnf).data[NET_IPV4_CONF_ ## attr - 1]) -#define IPV4_DEVCONF_ALL(attr) IPV4_DEVCONF(ipv4_devconf, attr) +#define IPV4_DEVCONF_ALL(net, attr) \ + IPV4_DEVCONF((*(net)->ipv4.devconf_all), attr) static inline int ipv4_devconf_get(struct in_device *in_dev, int index) { @@ -71,11 +72,14 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) ipv4_devconf_set((in_dev), NET_IPV4_CONF_ ## attr, (val)) #define IN_DEV_ANDCONF(in_dev, attr) \ - (IPV4_DEVCONF_ALL(attr) && IN_DEV_CONF_GET((in_dev), attr)) + (IPV4_DEVCONF_ALL(in_dev->dev->nd_net, attr) && \ + IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_ORCONF(in_dev, attr) \ - (IPV4_DEVCONF_ALL(attr) || IN_DEV_CONF_GET((in_dev), attr)) + (IPV4_DEVCONF_ALL(in_dev->dev->nd_net, attr) || \ + IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_MAXCONF(in_dev, attr) \ - (max(IPV4_DEVCONF_ALL(attr), IN_DEV_CONF_GET((in_dev), attr))) + (max(IPV4_DEVCONF_ALL(in_dev->dev->nd_net, attr), \ + IN_DEV_CONF_GET((in_dev), attr))) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) #define IN_DEV_MFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), MC_FORWARDING) -- cgit v1.2.3 From 2658fa803111dae1353602e7f586de8e537803e2 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Sun, 16 Dec 2007 13:42:49 -0800 Subject: [IPV4]: Create ipv4_is_(__be32 addr) functions Change IPV4 specific macros LOOPBACK MULTICAST LOCAL_MCAST BADCLASS and ZERONET macros to inline functions ipv4_is_(__be32 addr) Adds type safety and arguably some readability. Changes since last submission: Removed ipv4_addr_octets function Used hex constants Converted recently added rfc3330 macros Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/linux/in.h | 87 ++++++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 74 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/in.h b/include/linux/in.h index a8f00cac8f79..f8d607379017 100644 --- a/include/linux/in.h +++ b/include/linux/in.h @@ -246,21 +246,82 @@ struct sockaddr_in { #include #ifdef __KERNEL__ -/* Some random defines to make it easier in the kernel.. */ -#define LOOPBACK(x) (((x) & htonl(0xff000000)) == htonl(0x7f000000)) -#define MULTICAST(x) (((x) & htonl(0xf0000000)) == htonl(0xe0000000)) -#define BADCLASS(x) (((x) & htonl(0xf0000000)) == htonl(0xf0000000)) -#define ZERONET(x) (((x) & htonl(0xff000000)) == htonl(0x00000000)) -#define LOCAL_MCAST(x) (((x) & htonl(0xFFFFFF00)) == htonl(0xE0000000)) + +static inline bool ipv4_is_loopback(__be32 addr) +{ + return (addr & htonl(0xff000000)) == htonl(0x7f000000); +} + +static inline bool ipv4_is_multicast(__be32 addr) +{ + return (addr & htonl(0xf0000000)) == htonl(0xe0000000); +} + +static inline bool ipv4_is_local_multicast(__be32 addr) +{ + return (addr & htonl(0xffffff00)) == htonl(0xe0000000); +} + +static inline bool ipv4_is_badclass(__be32 addr) +{ + return (addr & htonl(0xf0000000)) == htonl(0xf0000000); +} + +static inline bool ipv4_is_zeronet(__be32 addr) +{ + return (addr & htonl(0xff000000)) == htonl(0x00000000); +} + +#define LOOPBACK(x) ipv4_is_loopback(x) +#define MULTICAST(x) ipv4_is_multicast(x) +#define BADCLASS(x) ipv4_is_badclass(x) +#define ZERONET(x) ipv4_is_zeronet(x) +#define LOCAL_MCAST(x) ipv4_is_local_multicast(x) /* Special-Use IPv4 Addresses (RFC3330) */ -#define PRIVATE_10(x) (((x) & htonl(0xff000000)) == htonl(0x0A000000)) -#define LINKLOCAL_169(x) (((x) & htonl(0xffff0000)) == htonl(0xA9FE0000)) -#define PRIVATE_172(x) (((x) & htonl(0xfff00000)) == htonl(0xAC100000)) -#define TEST_192(x) (((x) & htonl(0xffffff00)) == htonl(0xC0000200)) -#define ANYCAST_6TO4(x) (((x) & htonl(0xffffff00)) == htonl(0xC0586300)) -#define PRIVATE_192(x) (((x) & htonl(0xffff0000)) == htonl(0xC0A80000)) -#define TEST_198(x) (((x) & htonl(0xfffe0000)) == htonl(0xC6120000)) + +static inline bool ipv4_is_private_10(__be32 addr) +{ + return (addr & htonl(0xff000000)) == htonl(0x0a000000); +} + +static inline bool ipv4_is_private_172(__be32 addr) +{ + return (addr & htonl(0xfff00000)) == htonl(0xac100000); +} + +static inline bool ipv4_is_private_192(__be32 addr) +{ + return (addr & htonl(0xffff0000)) == htonl(0xc0a80000); +} + +static inline bool ipv4_is_linklocal_169(__be32 addr) +{ + return (addr & htonl(0xffff0000)) == htonl(0xa9fe0000); +} + +static inline bool ipv4_is_anycast_6to4(__be32 addr) +{ + return (addr & htonl(0xffffff00)) == htonl(0xc0586300); +} + +static inline bool ipv4_is_test_192(__be32 addr) +{ + return (addr & htonl(0xffffff00)) == htonl(0xc0000200); +} + +static inline bool ipv4_is_test_198(__be32 addr) +{ + return (addr & htonl(0xfffe0000)) == htonl(0xc6120000); +} #endif +#define PRIVATE_10(x) ipv4_is_private_10(x) +#define LINKLOCAL_169(x) ipv4_is_linklocal_169(x) +#define PRIVATE_172(x) ipv4_is_private_172(x) +#define TEST_192(x) ipv4_is_test_192(x) +#define ANYCAST_6TO4(x) ipv4_is_anycast_6to4(x) +#define PRIVATE_192(x) ipv4_is_private_192(x) +#define TEST_198(x) ipv4_is_test_198(x) + #endif /* _LINUX_IN_H */ -- cgit v1.2.3 From 2d4d29802ff76de5af6123ef26c24ab512181223 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Sun, 16 Dec 2007 13:48:11 -0800 Subject: [IPV4]: Remove unused IPV4TYPE macros Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/linux/in.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/in.h b/include/linux/in.h index f8d607379017..27d8a5ae9f75 100644 --- a/include/linux/in.h +++ b/include/linux/in.h @@ -272,12 +272,6 @@ static inline bool ipv4_is_zeronet(__be32 addr) return (addr & htonl(0xff000000)) == htonl(0x00000000); } -#define LOOPBACK(x) ipv4_is_loopback(x) -#define MULTICAST(x) ipv4_is_multicast(x) -#define BADCLASS(x) ipv4_is_badclass(x) -#define ZERONET(x) ipv4_is_zeronet(x) -#define LOCAL_MCAST(x) ipv4_is_local_multicast(x) - /* Special-Use IPv4 Addresses (RFC3330) */ static inline bool ipv4_is_private_10(__be32 addr) @@ -316,12 +310,4 @@ static inline bool ipv4_is_test_198(__be32 addr) } #endif -#define PRIVATE_10(x) ipv4_is_private_10(x) -#define LINKLOCAL_169(x) ipv4_is_linklocal_169(x) -#define PRIVATE_172(x) ipv4_is_private_172(x) -#define TEST_192(x) ipv4_is_test_192(x) -#define ANYCAST_6TO4(x) ipv4_is_anycast_6to4(x) -#define PRIVATE_192(x) ipv4_is_private_192(x) -#define TEST_198(x) ipv4_is_test_198(x) - #endif /* _LINUX_IN_H */ -- cgit v1.2.3 From 374fdfbc67837c1f4369eedb0f371ce3e6cce832 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 12 Dec 2007 10:25:07 -0500 Subject: introduce WEXT scan capabilities Introduce scan capabilities to WEXT so that userspace can do intelligent things with scan behavior such as handling hidden SSIDs more gracefully. If the driver reports a specific scan capability, the driver must respect the options specified in the iw_scan_req structure when handling the SIOCSIWSCAN call, unless it's mode or state does not allow it to do so, in which case it must return an error. This version switches to Dave Kilroy's suggestion of claiming unused padding space for the scan_capa field. Signed-off-by: Dan Williams Signed-off-by: John W. Linville Signed-off-by: David S. Miller --- include/linux/wireless.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wireless.h b/include/linux/wireless.h index 0987aa7a6cf5..74e84caa1e20 100644 --- a/include/linux/wireless.h +++ b/include/linux/wireless.h @@ -541,6 +541,16 @@ /* Maximum size of returned data */ #define IW_SCAN_MAX_DATA 4096 /* In bytes */ +/* Scan capability flags - in (struct iw_range *)->scan_capa */ +#define IW_SCAN_CAPA_NONE 0x00 +#define IW_SCAN_CAPA_ESSID 0x01 +#define IW_SCAN_CAPA_BSSID 0x02 +#define IW_SCAN_CAPA_CHANNEL 0x04 +#define IW_SCAN_CAPA_MODE 0x08 +#define IW_SCAN_CAPA_RATE 0x10 +#define IW_SCAN_CAPA_TYPE 0x20 +#define IW_SCAN_CAPA_TIME 0x40 + /* Max number of char in custom event - use multiple of them if needed */ #define IW_CUSTOM_MAX 256 /* In bytes */ @@ -963,6 +973,9 @@ struct iw_range __u16 old_num_channels; __u8 old_num_frequency; + /* Scan capabilities */ + __u8 scan_capa; /* IW_SCAN_CAPA_* bit field */ + /* Wireless event capability bitmasks */ __u32 event_capa[6]; -- cgit v1.2.3 From 8956695131b8a7878891667469899d667eb5892b Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 17 Dec 2007 21:46:40 -0800 Subject: [NETFILTER]: x_tables: make xt_compat_match_from_user usable in iterator macros Make xt_compat_match_from_user return an int to make it usable in the *tables iterator macros and kill a now unnecessary wrapper function. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index e305f2d0d4d1..616e6f4ede59 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -382,8 +382,8 @@ extern void xt_compat_lock(int af); extern void xt_compat_unlock(int af); extern int xt_compat_match_offset(struct xt_match *match); -extern void xt_compat_match_from_user(struct xt_entry_match *m, - void **dstptr, int *size); +extern int xt_compat_match_from_user(struct xt_entry_match *m, + void **dstptr, int *size); extern int xt_compat_match_to_user(struct xt_entry_match *m, void __user **dstptr, int *size); -- cgit v1.2.3 From 89c002d66aafab93814b38d8dae43fa50aec390a Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 17 Dec 2007 21:46:59 -0800 Subject: [NETFILTER]: {ip,ip6,arp}_tables: consolidate iterator macros Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 43 ++++++++++++++++++++++++ include/linux/netfilter_arp/arp_tables.h | 17 ++-------- include/linux/netfilter_ipv4/ip_tables.h | 55 ++++--------------------------- include/linux/netfilter_ipv6/ip6_tables.h | 36 +++----------------- 4 files changed, 55 insertions(+), 96 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 616e6f4ede59..8ab754e14ec0 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -126,6 +126,49 @@ struct xt_counters_info #define XT_INV_PROTO 0x40 /* Invert the sense of PROTO. */ +/* fn returns 0 to continue iteration */ +#define XT_MATCH_ITERATE(type, e, fn, args...) \ +({ \ + unsigned int __i; \ + int __ret = 0; \ + struct xt_entry_match *__m; \ + \ + for (__i = sizeof(type); \ + __i < (e)->target_offset; \ + __i += __m->u.match_size) { \ + __m = (void *)e + __i; \ + \ + __ret = fn(__m , ## args); \ + if (__ret != 0) \ + break; \ + } \ + __ret; \ +}) + +/* fn returns 0 to continue iteration */ +#define XT_ENTRY_ITERATE_CONTINUE(type, entries, size, n, fn, args...) \ +({ \ + unsigned int __i, __n; \ + int __ret = 0; \ + type *__entry; \ + \ + for (__i = 0, __n = 0; __i < (size); \ + __i += __entry->next_offset, __n++) { \ + __entry = (void *)(entries) + __i; \ + if (__n < n) \ + continue; \ + \ + __ret = fn(__entry , ## args); \ + if (__ret != 0) \ + break; \ + } \ + __ret; \ +}) + +/* fn returns 0 to continue iteration */ +#define XT_ENTRY_ITERATE(type, entries, size, fn, args...) \ + XT_ENTRY_ITERATE_CONTINUE(type, entries, size, 0, fn, args) + #ifdef __KERNEL__ #include diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index 2fc73fa8e37f..e44811b9be6c 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -217,21 +217,8 @@ static __inline__ struct arpt_entry_target *arpt_get_target(struct arpt_entry *e } /* fn returns 0 to continue iteration */ -#define ARPT_ENTRY_ITERATE(entries, size, fn, args...) \ -({ \ - unsigned int __i; \ - int __ret = 0; \ - struct arpt_entry *__entry; \ - \ - for (__i = 0; __i < (size); __i += __entry->next_offset) { \ - __entry = (void *)(entries) + __i; \ - \ - __ret = fn(__entry , ## args); \ - if (__ret != 0) \ - break; \ - } \ - __ret; \ -}) +#define ARPT_ENTRY_ITERATE(entries, size, fn, args...) \ + XT_ENTRY_ITERATE(struct arpt_entry, entries, size, fn, ## args) /* * Main firewall chains definitions and global var's definitions. diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 54da61603eff..1e0cfca7f354 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -229,60 +229,17 @@ ipt_get_target(struct ipt_entry *e) } /* fn returns 0 to continue iteration */ -#define IPT_MATCH_ITERATE(e, fn, args...) \ -({ \ - unsigned int __i; \ - int __ret = 0; \ - struct ipt_entry_match *__match; \ - \ - for (__i = sizeof(struct ipt_entry); \ - __i < (e)->target_offset; \ - __i += __match->u.match_size) { \ - __match = (void *)(e) + __i; \ - \ - __ret = fn(__match , ## args); \ - if (__ret != 0) \ - break; \ - } \ - __ret; \ -}) +#define IPT_MATCH_ITERATE(e, fn, args...) \ + XT_MATCH_ITERATE(struct ipt_entry, e, fn, ## args) /* fn returns 0 to continue iteration */ -#define IPT_ENTRY_ITERATE(entries, size, fn, args...) \ -({ \ - unsigned int __i; \ - int __ret = 0; \ - struct ipt_entry *__entry; \ - \ - for (__i = 0; __i < (size); __i += __entry->next_offset) { \ - __entry = (void *)(entries) + __i; \ - \ - __ret = fn(__entry , ## args); \ - if (__ret != 0) \ - break; \ - } \ - __ret; \ -}) +#define IPT_ENTRY_ITERATE(entries, size, fn, args...) \ + XT_ENTRY_ITERATE(struct ipt_entry, entries, size, fn, ## args) /* fn returns 0 to continue iteration */ #define IPT_ENTRY_ITERATE_CONTINUE(entries, size, n, fn, args...) \ -({ \ - unsigned int __i, __n; \ - int __ret = 0; \ - struct ipt_entry *__entry; \ - \ - for (__i = 0, __n = 0; __i < (size); \ - __i += __entry->next_offset, __n++) { \ - __entry = (void *)(entries) + __i; \ - if (__n < n) \ - continue; \ - \ - __ret = fn(__entry , ## args); \ - if (__ret != 0) \ - break; \ - } \ - __ret; \ -}) + XT_ENTRY_ITERATE_CONTINUE(struct ipt_entry, entries, size, n, fn, \ + ## args) /* * Main firewall chains definitions and global var's definitions. diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 2e98654188b3..8257b52015f3 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -289,40 +289,12 @@ ip6t_get_target(struct ip6t_entry *e) } /* fn returns 0 to continue iteration */ -#define IP6T_MATCH_ITERATE(e, fn, args...) \ -({ \ - unsigned int __i; \ - int __ret = 0; \ - struct ip6t_entry_match *__m; \ - \ - for (__i = sizeof(struct ip6t_entry); \ - __i < (e)->target_offset; \ - __i += __m->u.match_size) { \ - __m = (void *)(e) + __i; \ - \ - __ret = fn(__m , ## args); \ - if (__ret != 0) \ - break; \ - } \ - __ret; \ -}) +#define IP6T_MATCH_ITERATE(e, fn, args...) \ + XT_MATCH_ITERATE(struct ip6t_entry, e, fn, ## args) /* fn returns 0 to continue iteration */ -#define IP6T_ENTRY_ITERATE(entries, size, fn, args...) \ -({ \ - unsigned int __i; \ - int __ret = 0; \ - struct ip6t_entry *__e; \ - \ - for (__i = 0; __i < (size); __i += __e->next_offset) { \ - __e = (void *)(entries) + __i; \ - \ - __ret = fn(__e , ## args); \ - if (__ret != 0) \ - break; \ - } \ - __ret; \ -}) +#define IP6T_ENTRY_ITERATE(entries, size, fn, args...) \ + XT_ENTRY_ITERATE(struct ip6t_entry, entries, size, fn, ## args) /* * Main firewall chains definitions and global var's definitions. -- cgit v1.2.3 From 73cd598df46a73d6f02063f2520df115a9b88aa5 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 17 Dec 2007 21:47:32 -0800 Subject: [NETFILTER]: ip_tables: fix compat types Use compat types and compat iterators when dealing with compat entries for clarity. This doesn't actually make a difference for ip_tables, but is needed for ip6_tables and arp_tables. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv4/ip_tables.h | 25 ++++++++++++++++++++----- 1 file changed, 20 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 1e0cfca7f354..45fcad91e67b 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -236,11 +236,6 @@ ipt_get_target(struct ipt_entry *e) #define IPT_ENTRY_ITERATE(entries, size, fn, args...) \ XT_ENTRY_ITERATE(struct ipt_entry, entries, size, fn, ## args) -/* fn returns 0 to continue iteration */ -#define IPT_ENTRY_ITERATE_CONTINUE(entries, size, n, fn, args...) \ - XT_ENTRY_ITERATE_CONTINUE(struct ipt_entry, entries, size, n, fn, \ - ## args) - /* * Main firewall chains definitions and global var's definitions. */ @@ -316,8 +311,28 @@ struct compat_ipt_entry unsigned char elems[0]; }; +/* Helper functions */ +static inline struct ipt_entry_target * +compat_ipt_get_target(struct compat_ipt_entry *e) +{ + return (void *)e + e->target_offset; +} + #define COMPAT_IPT_ALIGN(s) COMPAT_XT_ALIGN(s) +/* fn returns 0 to continue iteration */ +#define COMPAT_IPT_MATCH_ITERATE(e, fn, args...) \ + XT_MATCH_ITERATE(struct compat_ipt_entry, e, fn, ## args) + +/* fn returns 0 to continue iteration */ +#define COMPAT_IPT_ENTRY_ITERATE(entries, size, fn, args...) \ + XT_ENTRY_ITERATE(struct compat_ipt_entry, entries, size, fn, ## args) + +/* fn returns 0 to continue iteration */ +#define COMPAT_IPT_ENTRY_ITERATE_CONTINUE(entries, size, n, fn, args...) \ + XT_ENTRY_ITERATE_CONTINUE(struct compat_ipt_entry, entries, size, n, \ + fn, ## args) + #endif /* CONFIG_COMPAT */ #endif /*__KERNEL__*/ #endif /* _IPTABLES_H */ -- cgit v1.2.3 From b386d9f5960a9afce7f077edf2095fccfbb1a8e6 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 17 Dec 2007 21:47:48 -0800 Subject: [NETFILTER]: ip_tables: move compat offset calculation to x_tables Its needed by ip6_tables and arp_tables as well. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 8ab754e14ec0..b99ede51318a 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -424,6 +424,10 @@ struct compat_xt_counters_info extern void xt_compat_lock(int af); extern void xt_compat_unlock(int af); +extern int xt_compat_add_offset(int af, unsigned int offset, short delta); +extern void xt_compat_flush_offsets(int af); +extern short xt_compat_calc_jump(int af, unsigned int offset); + extern int xt_compat_match_offset(struct xt_match *match); extern int xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, int *size); -- cgit v1.2.3 From 3bc3fe5eed5e866c0871db6d745f3bf58af004ef Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 17 Dec 2007 21:50:37 -0800 Subject: [NETFILTER]: ip6_tables: add compat support Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv6/ip6_tables.h | 35 +++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 8257b52015f3..c1124826bf29 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -326,5 +326,40 @@ extern int ip6_masked_addrcmp(const struct in6_addr *addr1, #define IP6T_ALIGN(s) (((s) + (__alignof__(struct ip6t_entry)-1)) & ~(__alignof__(struct ip6t_entry)-1)) +#ifdef CONFIG_COMPAT +#include + +struct compat_ip6t_entry +{ + struct ip6t_ip6 ipv6; + compat_uint_t nfcache; + u_int16_t target_offset; + u_int16_t next_offset; + compat_uint_t comefrom; + struct compat_xt_counters counters; + unsigned char elems[0]; +}; + +static inline struct ip6t_entry_target * +compat_ip6t_get_target(struct compat_ip6t_entry *e) +{ + return (void *)e + e->target_offset; +} + +#define COMPAT_IP6T_ALIGN(s) COMPAT_XT_ALIGN(s) + +/* fn returns 0 to continue iteration */ +#define COMPAT_IP6T_MATCH_ITERATE(e, fn, args...) \ + XT_MATCH_ITERATE(struct compat_ip6t_entry, e, fn, ## args) + +/* fn returns 0 to continue iteration */ +#define COMPAT_IP6T_ENTRY_ITERATE(entries, size, fn, args...) \ + XT_ENTRY_ITERATE(struct compat_ip6t_entry, entries, size, fn, ## args) + +#define COMPAT_IP6T_ENTRY_ITERATE_CONTINUE(entries, size, n, fn, args...) \ + XT_ENTRY_ITERATE_CONTINUE(struct compat_ip6t_entry, entries, size, n, \ + fn, ## args) + +#endif /* CONFIG_COMPAT */ #endif /*__KERNEL__*/ #endif /* _IP6_TABLES_H */ -- cgit v1.2.3 From 06e1374a7ed45f1788353a2944a20133adc55649 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 17 Dec 2007 21:53:40 -0800 Subject: [NETFILTER]: ip6_tables: use XT_ALIGN Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv6/ip6_tables.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index c1124826bf29..110801d699ee 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -324,7 +324,7 @@ extern int ip6_masked_addrcmp(const struct in6_addr *addr1, const struct in6_addr *mask, const struct in6_addr *addr2); -#define IP6T_ALIGN(s) (((s) + (__alignof__(struct ip6t_entry)-1)) & ~(__alignof__(struct ip6t_entry)-1)) +#define IP6T_ALIGN(s) XT_ALIGN(s) #ifdef CONFIG_COMPAT #include -- cgit v1.2.3 From 0495cf957bfacbca123cb4c4e1c4cf0e265f522e Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 17 Dec 2007 21:55:34 -0800 Subject: [NETFILTER]: arp_tables: use XT_ALIGN Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_arp/arp_tables.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index e44811b9be6c..7ade26b025a4 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -280,6 +280,6 @@ extern unsigned int arpt_do_table(struct sk_buff *skb, const struct net_device *out, struct arpt_table *table); -#define ARPT_ALIGN(s) (((s) + (__alignof__(struct arpt_entry)-1)) & ~(__alignof__(struct arpt_entry)-1)) +#define ARPT_ALIGN(s) XT_ALIGN(s) #endif /*__KERNEL__*/ #endif /* _ARPTABLES_H */ -- cgit v1.2.3 From d6a2ba07c31b0497fc82a8c175400ea8747da2ef Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 17 Dec 2007 22:26:54 -0800 Subject: [NETFILTER]: arp_tables: add compat support Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_arp/arp_tables.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index 7ade26b025a4..53dd4df27aa1 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -281,5 +281,36 @@ extern unsigned int arpt_do_table(struct sk_buff *skb, struct arpt_table *table); #define ARPT_ALIGN(s) XT_ALIGN(s) + +#ifdef CONFIG_COMPAT +#include + +struct compat_arpt_entry +{ + struct arpt_arp arp; + u_int16_t target_offset; + u_int16_t next_offset; + compat_uint_t comefrom; + struct compat_xt_counters counters; + unsigned char elems[0]; +}; + +static inline struct arpt_entry_target * +compat_arpt_get_target(struct compat_arpt_entry *e) +{ + return (void *)e + e->target_offset; +} + +#define COMPAT_ARPT_ALIGN(s) COMPAT_XT_ALIGN(s) + +/* fn returns 0 to continue iteration */ +#define COMPAT_ARPT_ENTRY_ITERATE(entries, size, fn, args...) \ + XT_ENTRY_ITERATE(struct compat_arpt_entry, entries, size, fn, ## args) + +#define COMPAT_ARPT_ENTRY_ITERATE_CONTINUE(entries, size, n, fn, args...) \ + XT_ENTRY_ITERATE_CONTINUE(struct compat_arpt_entry, entries, size, n, \ + fn, ## args) + +#endif /* CONFIG_COMPAT */ #endif /*__KERNEL__*/ #endif /* _ARPTABLES_H */ -- cgit v1.2.3 From 13eae15a244bb29beaa47bf86a24fd29ca7f8a4c Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 17 Dec 2007 22:28:00 -0800 Subject: [NETFILTER]: ctnetlink: add support for NAT sequence adjustments The combination of NAT and helpers may produce TCP sequence adjustments. In failover setups, this information needs to be replicated in order to achieve a successful recovery of mangled, related connections. This patch is particularly useful for conntrackd, see: http://people.netfilter.org/pablo/conntrack-tools/ Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nf_conntrack_common.h | 4 ++++ include/linux/netfilter/nfnetlink_conntrack.h | 10 ++++++++++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 9e0dae07861e..19747e8f71cf 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -129,6 +129,10 @@ enum ip_conntrack_events /* Mark is set */ IPCT_MARK_BIT = 12, IPCT_MARK = (1 << IPCT_MARK_BIT), + + /* NAT sequence adjustment */ + IPCT_NATSEQADJ_BIT = 13, + IPCT_NATSEQADJ = (1 << IPCT_NATSEQADJ_BIT), }; enum ip_conntrack_expect_events { diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index 4affa3fe78e0..c19d976b1b75 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -37,6 +37,8 @@ enum ctattr_type { CTA_ID, CTA_NAT_DST, CTA_TUPLE_MASTER, + CTA_NAT_SEQ_ADJ_ORIG, + CTA_NAT_SEQ_ADJ_REPLY, __CTA_MAX }; #define CTA_MAX (__CTA_MAX - 1) @@ -119,6 +121,14 @@ enum ctattr_protonat { }; #define CTA_PROTONAT_MAX (__CTA_PROTONAT_MAX - 1) +enum ctattr_natseq { + CTA_NAT_SEQ_CORRECTION_POS, + CTA_NAT_SEQ_OFFSET_BEFORE, + CTA_NAT_SEQ_OFFSET_AFTER, + __CTA_NAT_SEQ_MAX +}; +#define CTA_NAT_SEQ_MAX (__CTA_NAT_SEQ_MAX - 1) + enum ctattr_expect { CTA_EXPECT_UNSPEC, CTA_EXPECT_MASTER, -- cgit v1.2.3 From 37fccd8577d38e249dde71512fb38d2f6a4d9d3c Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 17 Dec 2007 22:28:41 -0800 Subject: [NETFILTER]: ctnetlink: add support for secmark This patch adds support for James Morris' connsecmark. Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nf_conntrack_common.h | 4 ++++ include/linux/netfilter/nfnetlink_conntrack.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 19747e8f71cf..bad1eb760f61 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -133,6 +133,10 @@ enum ip_conntrack_events /* NAT sequence adjustment */ IPCT_NATSEQADJ_BIT = 13, IPCT_NATSEQADJ = (1 << IPCT_NATSEQADJ_BIT), + + /* Secmark is set */ + IPCT_SECMARK_BIT = 14, + IPCT_SECMARK = (1 << IPCT_SECMARK_BIT), }; enum ip_conntrack_expect_events { diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index c19d976b1b75..e3e1533aba2d 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -39,6 +39,7 @@ enum ctattr_type { CTA_TUPLE_MASTER, CTA_NAT_SEQ_ADJ_ORIG, CTA_NAT_SEQ_ADJ_REPLY, + CTA_SECMARK, __CTA_MAX }; #define CTA_MAX (__CTA_MAX - 1) -- cgit v1.2.3 From f01ffbd6e7d001ccf9168b33507958a51ce0ffcf Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 17 Dec 2007 22:38:49 -0800 Subject: [NETFILTER]: nf_log: move logging stuff to seperate header Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter.h | 55 ----------------------------------------------- 1 file changed, 55 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index f25eec595807..368b7ed1f1bf 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -124,61 +124,6 @@ extern struct ctl_table nf_net_ipv4_netfilter_sysctl_path[]; extern struct list_head nf_hooks[NPROTO][NF_MAX_HOOKS]; -/* those NF_LOG_* defines and struct nf_loginfo are legacy definitios that will - * disappear once iptables is replaced with pkttables. Please DO NOT use them - * for any new code! */ -#define NF_LOG_TCPSEQ 0x01 /* Log TCP sequence numbers */ -#define NF_LOG_TCPOPT 0x02 /* Log TCP options */ -#define NF_LOG_IPOPT 0x04 /* Log IP options */ -#define NF_LOG_UID 0x08 /* Log UID owning local socket */ -#define NF_LOG_MASK 0x0f - -#define NF_LOG_TYPE_LOG 0x01 -#define NF_LOG_TYPE_ULOG 0x02 - -struct nf_loginfo { - u_int8_t type; - union { - struct { - u_int32_t copy_len; - u_int16_t group; - u_int16_t qthreshold; - } ulog; - struct { - u_int8_t level; - u_int8_t logflags; - } log; - } u; -}; - -typedef void nf_logfn(unsigned int pf, - unsigned int hooknum, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct nf_loginfo *li, - const char *prefix); - -struct nf_logger { - struct module *me; - nf_logfn *logfn; - char *name; -}; - -/* Function to register/unregister log function. */ -int nf_log_register(int pf, struct nf_logger *logger); -void nf_log_unregister(struct nf_logger *logger); -void nf_log_unregister_pf(int pf); - -/* Calls the registered backend logging function */ -void nf_log_packet(int pf, - unsigned int hooknum, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - struct nf_loginfo *li, - const char *fmt, ...); - int nf_hook_slow(int pf, unsigned int hook, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct sk_buff *), int thresh); -- cgit v1.2.3 From 76aa1ce139f649e432272f6ad75204b763ef13bd Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 17 Dec 2007 22:41:52 -0800 Subject: [NETFILTER]: nfnetlink_log: include GID in netlink message Similar to Maciej Soltysiak's ipt_LOG patch, include GID in addition to UID in netlink message. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink_log.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_log.h b/include/linux/netfilter/nfnetlink_log.h index 5966afa026e9..a85721332924 100644 --- a/include/linux/netfilter/nfnetlink_log.h +++ b/include/linux/netfilter/nfnetlink_log.h @@ -47,6 +47,7 @@ enum nfulnl_attr_type { NFULA_UID, /* user id of socket */ NFULA_SEQ, /* instance-local sequence number */ NFULA_SEQ_GLOBAL, /* global sequence number */ + NFULA_GID, /* group id of socket */ __NFULA_MAX }; -- cgit v1.2.3 From 90a9ba8dd90bcffe279d3272545bccba6dcc8d7c Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 17 Dec 2007 22:42:09 -0800 Subject: [NETFILTER]: Kill function prototype for non-existing function Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 368b7ed1f1bf..bd4a2dd54233 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -206,9 +206,6 @@ int compat_nf_setsockopt(struct sock *sk, int pf, int optval, int compat_nf_getsockopt(struct sock *sk, int pf, int optval, char __user *opt, int *len); -/* FIXME: Before cache is ever used, this must be implemented for real. */ -extern void nf_invalidate_cache(int pf); - /* Call this before modifying an existing packet: ensures it is modifiable and linear to the point you care about (writable_len). Returns true or false. */ -- cgit v1.2.3 From 1e796fda00f06bac584f0e4ad8750ab9430d79d3 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 17 Dec 2007 22:42:27 -0800 Subject: [NETFILTER]: constify nf_afinfo Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index bd4a2dd54233..0947424d01d6 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -226,8 +226,8 @@ struct nf_afinfo { int route_key_size; }; -extern struct nf_afinfo *nf_afinfo[]; -static inline struct nf_afinfo *nf_get_afinfo(unsigned short family) +extern const struct nf_afinfo *nf_afinfo[NPROTO]; +static inline const struct nf_afinfo *nf_get_afinfo(unsigned short family) { return rcu_dereference(nf_afinfo[family]); } @@ -236,7 +236,7 @@ static inline __sum16 nf_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol, unsigned short family) { - struct nf_afinfo *afinfo; + const struct nf_afinfo *afinfo; __sum16 csum = 0; rcu_read_lock(); @@ -247,8 +247,8 @@ nf_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, return csum; } -extern int nf_register_afinfo(struct nf_afinfo *afinfo); -extern void nf_unregister_afinfo(struct nf_afinfo *afinfo); +extern int nf_register_afinfo(const struct nf_afinfo *afinfo); +extern void nf_unregister_afinfo(const struct nf_afinfo *afinfo); #include extern void (*ip_nat_decode_session)(struct sk_buff *, struct flowi *); -- cgit v1.2.3 From 051578ccbcdad3b24b621dfb652194e36759e8d5 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 17 Dec 2007 22:42:51 -0800 Subject: [NETFILTER]: nf_nat: properly use RCU for ip_nat_decode_session We need to use rcu_assign_pointer/rcu_dereference to avoid races. Also remove an obsolete CONFIG_IP_NAT_NEEDED ifdef. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 0947424d01d6..1a8487325a4f 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -256,11 +256,16 @@ extern void (*ip_nat_decode_session)(struct sk_buff *, struct flowi *); static inline void nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, int family) { -#if defined(CONFIG_IP_NF_NAT_NEEDED) || defined(CONFIG_NF_NAT_NEEDED) +#ifdef CONFIG_NF_NAT_NEEDED void (*decodefn)(struct sk_buff *, struct flowi *); - if (family == AF_INET && (decodefn = ip_nat_decode_session) != NULL) - decodefn(skb, fl); + if (family == AF_INET) { + rcu_read_lock(); + decodefn = rcu_dereference(ip_nat_decode_session); + if (decodefn) + decodefn(skb, fl); + rcu_read_unlock(); + } #endif } -- cgit v1.2.3 From 643a2c15a407faf08101a20e1a3461160711899d Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Mon, 17 Dec 2007 22:43:50 -0800 Subject: [NETFILTER]: Introduce nf_inet_address A few netfilter modules provide their own union of IPv4 and IPv6 address storage. Will unify that in this patch series. (1/4): Rename union nf_conntrack_address to union nf_inet_addr and move it to x_tables.h. Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter.h | 6 ++++++ include/linux/netfilter/nf_conntrack_h323.h | 6 +++--- 2 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 1a8487325a4f..d190d560de61 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -48,6 +48,12 @@ enum nf_inet_hooks { NF_INET_NUMHOOKS }; +union nf_inet_addr { + u_int32_t all[4]; + __be32 ip; + __be32 ip6[4]; +}; + #ifdef __KERNEL__ #ifdef CONFIG_NETFILTER diff --git a/include/linux/netfilter/nf_conntrack_h323.h b/include/linux/netfilter/nf_conntrack_h323.h index aabd24ac7631..26f9226ea72b 100644 --- a/include/linux/netfilter/nf_conntrack_h323.h +++ b/include/linux/netfilter/nf_conntrack_h323.h @@ -31,7 +31,7 @@ struct nf_conn; extern int get_h225_addr(struct nf_conn *ct, unsigned char *data, TransportAddress *taddr, - union nf_conntrack_address *addr, __be16 *port); + union nf_inet_addr *addr, __be16 *port); extern void nf_conntrack_h245_expect(struct nf_conn *new, struct nf_conntrack_expect *this); extern void nf_conntrack_q931_expect(struct nf_conn *new, @@ -39,12 +39,12 @@ extern void nf_conntrack_q931_expect(struct nf_conn *new, extern int (*set_h245_addr_hook) (struct sk_buff *skb, unsigned char **data, int dataoff, H245_TransportAddress *taddr, - union nf_conntrack_address *addr, + union nf_inet_addr *addr, __be16 port); extern int (*set_h225_addr_hook) (struct sk_buff *skb, unsigned char **data, int dataoff, TransportAddress *taddr, - union nf_conntrack_address *addr, + union nf_inet_addr *addr, __be16 port); extern int (*set_sig_addr_hook) (struct sk_buff *skb, struct nf_conn *ct, -- cgit v1.2.3 From 22c2d8bca212a655c120fd6617328ffa3480afad Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Mon, 17 Dec 2007 22:44:47 -0800 Subject: [NETFILTER]: xt_connlimit: use the new union nf_inet_addr Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/xt_connlimit.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_connlimit.h b/include/linux/netfilter/xt_connlimit.h index 37e933c9987d..315d2dce9da6 100644 --- a/include/linux/netfilter/xt_connlimit.h +++ b/include/linux/netfilter/xt_connlimit.h @@ -5,8 +5,13 @@ struct xt_connlimit_data; struct xt_connlimit_info { union { - __be32 v4_mask; - __be32 v6_mask[4]; + union nf_inet_addr mask; +#ifndef __KERNEL__ + union { + __be32 v4_mask; + __be32 v6_mask[4]; + }; +#endif }; unsigned int limit, inverse; -- cgit v1.2.3 From 558f82ef6e0d25e87f7468c07b6db1fbbf95a855 Mon Sep 17 00:00:00 2001 From: Masahide NAKAMURA Date: Thu, 20 Dec 2007 20:42:57 -0800 Subject: [XFRM]: Define packet dropping statistics. This statistics is shown factor dropped by transformation at /proc/net/xfrm_stat for developer. It is a counter designed from current transformation source code and defined as linux private MIB. See Documentation/networking/xfrm_proc.txt for the detail. Signed-off-by: Masahide NAKAMURA Signed-off-by: David S. Miller --- include/linux/snmp.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/snmp.h b/include/linux/snmp.h index 89f0c2b5f405..86d3effb2836 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -217,4 +217,35 @@ enum __LINUX_MIB_MAX }; +/* linux Xfrm mib definitions */ +enum +{ + LINUX_MIB_XFRMNUM = 0, + LINUX_MIB_XFRMINERROR, /* XfrmInError */ + LINUX_MIB_XFRMINBUFFERERROR, /* XfrmInBufferError */ + LINUX_MIB_XFRMINHDRERROR, /* XfrmInHdrError */ + LINUX_MIB_XFRMINNOSTATES, /* XfrmInNoStates */ + LINUX_MIB_XFRMINSTATEPROTOERROR, /* XfrmInStateProtoError */ + LINUX_MIB_XFRMINSTATEMODEERROR, /* XfrmInStateModeError */ + LINUX_MIB_XFRMINSEQOUTOFWINDOW, /* XfrmInSeqOutOfWindow */ + LINUX_MIB_XFRMINSTATEEXPIRED, /* XfrmInStateExpired */ + LINUX_MIB_XFRMINSTATEMISMATCH, /* XfrmInStateMismatch */ + LINUX_MIB_XFRMINSTATEINVALID, /* XfrmInStateInvalid */ + LINUX_MIB_XFRMINTMPLMISMATCH, /* XfrmInTmplMismatch */ + LINUX_MIB_XFRMINNOPOLS, /* XfrmInNoPols */ + LINUX_MIB_XFRMINPOLBLOCK, /* XfrmInPolBlock */ + LINUX_MIB_XFRMINPOLERROR, /* XfrmInPolError */ + LINUX_MIB_XFRMOUTERROR, /* XfrmOutError */ + LINUX_MIB_XFRMOUTBUNDLEGENERROR, /* XfrmOutBundleGenError */ + LINUX_MIB_XFRMOUTBUNDLECHECKERROR, /* XfrmOutBundleCheckError */ + LINUX_MIB_XFRMOUTNOSTATES, /* XfrmOutNoStates */ + LINUX_MIB_XFRMOUTSTATEPROTOERROR, /* XfrmOutStateProtoError */ + LINUX_MIB_XFRMOUTSTATEMODEERROR, /* XfrmOutStateModeError */ + LINUX_MIB_XFRMOUTSTATEEXPIRED, /* XfrmOutStateExpired */ + LINUX_MIB_XFRMOUTPOLBLOCK, /* XfrmOutPolBlock */ + LINUX_MIB_XFRMOUTPOLDEAD, /* XfrmOutPolDead */ + LINUX_MIB_XFRMOUTPOLERROR, /* XfrmOutPolError */ + __LINUX_MIB_XFRMMAX +}; + #endif /* _LINUX_SNMP_H */ -- cgit v1.2.3 From 41ade00f21a72d30911c6351a93823a491fffa39 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 19 Dec 2007 02:03:29 +0100 Subject: cfg80211/nl80211: introduce key handling This introduces key handling to cfg80211/nl80211. Default and group keys can be added, changed and removed; sequence counters for each key can be retrieved. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville Signed-off-by: David S. Miller --- include/linux/nl80211.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 538ee1dd3d0a..8dc807d9c29a 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -37,6 +37,16 @@ * userspace to request deletion of a virtual interface, then requires * attribute %NL80211_ATTR_IFINDEX. * + * @NL80211_CMD_GET_KEY: Get sequence counter information for a key specified + * by %NL80211_ATTR_KEY_IDX and/or %NL80211_ATTR_MAC. + * @NL80211_CMD_SET_KEY: Set key attributes %NL80211_ATTR_KEY_DEFAULT or + * %NL80211_ATTR_KEY_THRESHOLD. + * @NL80211_CMD_NEW_KEY: add a key with given %NL80211_ATTR_KEY_DATA, + * %NL80211_ATTR_KEY_IDX, %NL80211_ATTR_MAC and %NL80211_ATTR_KEY_CIPHER + * attributes. + * @NL80211_CMD_DEL_KEY: delete a key identified by %NL80211_ATTR_KEY_IDX + * or %NL80211_ATTR_MAC. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -54,6 +64,11 @@ enum nl80211_commands { NL80211_CMD_NEW_INTERFACE, NL80211_CMD_DEL_INTERFACE, + NL80211_CMD_GET_KEY, + NL80211_CMD_SET_KEY, + NL80211_CMD_NEW_KEY, + NL80211_CMD_DEL_KEY, + /* add commands here */ /* used to define NL80211_CMD_MAX below */ @@ -75,6 +90,17 @@ enum nl80211_commands { * @NL80211_ATTR_IFNAME: network interface name * @NL80211_ATTR_IFTYPE: type of virtual interface, see &enum nl80211_iftype * + * @NL80211_ATTR_MAC: MAC address (various uses) + * + * @NL80211_ATTR_KEY_DATA: (temporal) key data; for TKIP this consists of + * 16 bytes encryption key followed by 8 bytes each for TX and RX MIC + * keys + * @NL80211_ATTR_KEY_IDX: key ID (u8, 0-3) + * @NL80211_ATTR_KEY_CIPHER: key cipher suite (u32, as defined by IEEE 802.11 + * section 7.3.2.25.1, e.g. 0x000FAC04) + * @NL80211_ATTR_KEY_SEQ: transmit key sequence number (IV/PN) for TKIP and + * CCMP keys, each six bytes in little endian + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -89,6 +115,14 @@ enum nl80211_attrs { NL80211_ATTR_IFNAME, NL80211_ATTR_IFTYPE, + NL80211_ATTR_MAC, + + NL80211_ATTR_KEY_DATA, + NL80211_ATTR_KEY_IDX, + NL80211_ATTR_KEY_CIPHER, + NL80211_ATTR_KEY_SEQ, + NL80211_ATTR_KEY_DEFAULT, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From ed1b6cc7f80f831e192704b05b9917f9cc37be15 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 19 Dec 2007 02:03:32 +0100 Subject: cfg80211/nl80211: add beacon settings This adds the necessary API to cfg80211/nl80211 to allow changing beaconing settings. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville Signed-off-by: David S. Miller --- include/linux/nl80211.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 8dc807d9c29a..f1e455a8b4de 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -47,6 +47,15 @@ * @NL80211_CMD_DEL_KEY: delete a key identified by %NL80211_ATTR_KEY_IDX * or %NL80211_ATTR_MAC. * + * @NL80211_CMD_GET_BEACON: retrieve beacon information (returned in a + * %NL80222_CMD_NEW_BEACON message) + * @NL80211_CMD_SET_BEACON: set the beacon on an access point interface + * using the %NL80211_ATTR_BEACON_INTERVAL, %NL80211_ATTR_DTIM_PERIOD, + * %NL80211_BEACON_HEAD and %NL80211_BEACON_TAIL attributes. + * @NL80211_CMD_NEW_BEACON: add a new beacon to an access point interface, + * parameters are like for %NL80211_CMD_SET_BEACON. + * @NL80211_CMD_DEL_BEACON: remove the beacon, stop sending it + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -69,6 +78,11 @@ enum nl80211_commands { NL80211_CMD_NEW_KEY, NL80211_CMD_DEL_KEY, + NL80211_CMD_GET_BEACON, + NL80211_CMD_SET_BEACON, + NL80211_CMD_NEW_BEACON, + NL80211_CMD_DEL_BEACON, + /* add commands here */ /* used to define NL80211_CMD_MAX below */ @@ -101,6 +115,11 @@ enum nl80211_commands { * @NL80211_ATTR_KEY_SEQ: transmit key sequence number (IV/PN) for TKIP and * CCMP keys, each six bytes in little endian * + * @NL80211_ATTR_BEACON_INTERVAL: beacon interval in TU + * @NL80211_ATTR_DTIM_PERIOD: DTIM period for beaconing + * @NL80211_ATTR_BEACON_HEAD: portion of the beacon before the TIM IE + * @NL80211_ATTR_BEACON_TAIL: portion of the beacon after the TIM IE + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -123,6 +142,11 @@ enum nl80211_attrs { NL80211_ATTR_KEY_SEQ, NL80211_ATTR_KEY_DEFAULT, + NL80211_ATTR_BEACON_INTERVAL, + NL80211_ATTR_DTIM_PERIOD, + NL80211_ATTR_BEACON_HEAD, + NL80211_ATTR_BEACON_TAIL, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From 5727ef1b2e797a1922f5bc239b6afb2b4cfb80bc Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 19 Dec 2007 02:03:34 +0100 Subject: cfg80211/nl80211: station handling This patch adds station handling to cfg80211/nl80211. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville Signed-off-by: David S. Miller --- include/linux/nl80211.h | 68 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 68 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index f1e455a8b4de..85e2d7d1f9e3 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -6,6 +6,18 @@ * Copyright 2006, 2007 Johannes Berg */ +/** + * DOC: Station handling + * + * Stations are added per interface, but a special case exists with VLAN + * interfaces. When a station is bound to an AP interface, it may be moved + * into a VLAN identified by a VLAN interface index (%NL80211_ATTR_STA_VLAN). + * The station is still assumed to belong to the AP interface it was added + * to. + * + * TODO: need more info? + */ + /** * enum nl80211_commands - supported nl80211 commands * @@ -56,6 +68,16 @@ * parameters are like for %NL80211_CMD_SET_BEACON. * @NL80211_CMD_DEL_BEACON: remove the beacon, stop sending it * + * @NL80211_CMD_GET_STATION: Get station attributes for station identified by + * %NL80211_ATTR_MAC on the interface identified by %NL80211_ATTR_IFINDEX. + * @NL80211_CMD_SET_STATION: Set station attributes for station identified by + * %NL80211_ATTR_MAC on the interface identified by %NL80211_ATTR_IFINDEX. + * @NL80211_CMD_NEW_STATION: Add a station with given attributes to the + * the interface identified by %NL80211_ATTR_IFINDEX. + * @NL80211_CMD_DEL_STATION: Remove a station identified by %NL80211_ATTR_MAC + * or, if no MAC address given, all stations, on the interface identified + * by %NL80211_ATTR_IFINDEX. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -83,6 +105,11 @@ enum nl80211_commands { NL80211_CMD_NEW_BEACON, NL80211_CMD_DEL_BEACON, + NL80211_CMD_GET_STATION, + NL80211_CMD_SET_STATION, + NL80211_CMD_NEW_STATION, + NL80211_CMD_DEL_STATION, + /* add commands here */ /* used to define NL80211_CMD_MAX below */ @@ -120,6 +147,17 @@ enum nl80211_commands { * @NL80211_ATTR_BEACON_HEAD: portion of the beacon before the TIM IE * @NL80211_ATTR_BEACON_TAIL: portion of the beacon after the TIM IE * + * @NL80211_ATTR_STA_AID: Association ID for the station (u16) + * @NL80211_ATTR_STA_FLAGS: flags, nested element with NLA_FLAG attributes of + * &enum nl80211_sta_flags. + * @NL80211_ATTR_STA_LISTEN_INTERVAL: listen interval as defined by + * IEEE 802.11 7.3.1.6 (u16). + * @NL80211_ATTR_STA_SUPPORTED_RATES: supported rates, array of supported + * rates as defined by IEEE 802.11 7.3.2.2 but without the length + * restriction (at most %NL80211_MAX_SUPP_RATES). + * @NL80211_ATTR_STA_VLAN: interface index of VLAN interface to move station + * to, or the AP interface the station was originally added to to. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -147,12 +185,20 @@ enum nl80211_attrs { NL80211_ATTR_BEACON_HEAD, NL80211_ATTR_BEACON_TAIL, + NL80211_ATTR_STA_AID, + NL80211_ATTR_STA_FLAGS, + NL80211_ATTR_STA_LISTEN_INTERVAL, + NL80211_ATTR_STA_SUPPORTED_RATES, + NL80211_ATTR_STA_VLAN, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, NL80211_ATTR_MAX = __NL80211_ATTR_AFTER_LAST - 1 }; +#define NL80211_MAX_SUPP_RATES 32 + /** * enum nl80211_iftype - (virtual) interface types * @@ -184,4 +230,26 @@ enum nl80211_iftype { NL80211_IFTYPE_MAX = __NL80211_IFTYPE_AFTER_LAST - 1 }; +/** + * enum nl80211_sta_flags - station flags + * + * Station flags. When a station is added to an AP interface, it is + * assumed to be already associated (and hence authenticated.) + * + * @NL80211_STA_FLAG_AUTHORIZED: station is authorized (802.1X) + * @NL80211_STA_FLAG_SHORT_PREAMBLE: station is capable of receiving frames + * with short barker preamble + * @NL80211_STA_FLAG_WME: station is WME/QoS capable + */ +enum nl80211_sta_flags { + __NL80211_STA_FLAG_INVALID, + NL80211_STA_FLAG_AUTHORIZED, + NL80211_STA_FLAG_SHORT_PREAMBLE, + NL80211_STA_FLAG_WME, + + /* keep last */ + __NL80211_STA_FLAG_AFTER_LAST, + NL80211_STA_FLAG_MAX = __NL80211_STA_FLAG_AFTER_LAST - 1 +}; + #endif /* __LINUX_NL80211_H */ -- cgit v1.2.3 From fd5b74dcb88cfc109d6576b22deaef6f47f82c12 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 19 Dec 2007 02:03:36 +0100 Subject: cfg80211/nl80211: implement station attribute retrieval After a station is added to the kernel's structures, userspace has to be able to retrieve statistics about that station, especially whether the station was idle and how much bytes were transferred to and from it. This adds the necessary code to nl80211. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville Signed-off-by: David S. Miller --- include/linux/nl80211.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 85e2d7d1f9e3..9fecf902419c 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -157,6 +157,9 @@ enum nl80211_commands { * restriction (at most %NL80211_MAX_SUPP_RATES). * @NL80211_ATTR_STA_VLAN: interface index of VLAN interface to move station * to, or the AP interface the station was originally added to to. + * @NL80211_ATTR_STA_STATS: statistics for a station, part of station info + * given for %NL80211_CMD_GET_STATION, nested attribute containing + * info as possible, see &enum nl80211_sta_stats. * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -190,6 +193,7 @@ enum nl80211_attrs { NL80211_ATTR_STA_LISTEN_INTERVAL, NL80211_ATTR_STA_SUPPORTED_RATES, NL80211_ATTR_STA_VLAN, + NL80211_ATTR_STA_STATS, /* add attributes here, update the policy in nl80211.c */ @@ -252,4 +256,28 @@ enum nl80211_sta_flags { NL80211_STA_FLAG_MAX = __NL80211_STA_FLAG_AFTER_LAST - 1 }; +/** + * enum nl80211_sta_stats - station statistics + * + * These attribute types are used with %NL80211_ATTR_STA_STATS + * when getting information about a station. + * + * @__NL80211_STA_STAT_INVALID: attribute number 0 is reserved + * @NL80211_STA_STAT_INACTIVE_TIME: time since last activity (u32, msecs) + * @NL80211_STA_STAT_RX_BYTES: total received bytes (u32, from this station) + * @NL80211_STA_STAT_TX_BYTES: total transmitted bytes (u32, to this station) + * @__NL80211_STA_STAT_AFTER_LAST: internal + * @NL80211_STA_STAT_MAX: highest possible station stats attribute + */ +enum nl80211_sta_stats { + __NL80211_STA_STAT_INVALID, + NL80211_STA_STAT_INACTIVE_TIME, + NL80211_STA_STAT_RX_BYTES, + NL80211_STA_STAT_TX_BYTES, + + /* keep last */ + __NL80211_STA_STAT_AFTER_LAST, + NL80211_STA_STAT_MAX = __NL80211_STA_STAT_AFTER_LAST - 1 +}; + #endif /* __LINUX_NL80211_H */ -- cgit v1.2.3 From 7ffc49a6ee92b7138c2ee28073a8e10e58335d62 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Mon, 24 Dec 2007 21:28:09 -0800 Subject: [ETH]: Combine format_addr() with print_mac(). print_mac() used many most net drivers and format_addr() used by net-sysfs.c are very similar and they can be intergrated. format_addr() is also identically redefined in the qla4xxx iscsi driver. Export a new function sysfs_format_mac() to be used by net-sysfs, qla4xxx and others in the future. Both print_mac() and sysfs_format_mac() call _format_mac_addr() to do the formatting. Changed print_mac() to use unsigned char * to be consistent with net_device struct's dev_addr. Added buffer length overrun checking as suggested by Joe Perches. Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- include/linux/if_ether.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index cc002cbbdc26..7a1e011b8a2c 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -124,12 +124,14 @@ int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr); extern struct ctl_table ether_table[]; #endif +extern ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len); + /* * Display a 6 byte device address (MAC) in a readable format. */ -#define MAC_FMT "%02x:%02x:%02x:%02x:%02x:%02x" -extern char *print_mac(char *buf, const u8 *addr); -#define DECLARE_MAC_BUF(var) char var[18] __maybe_unused +extern char *print_mac(char *buf, const unsigned char *addr); +#define MAC_BUF_SIZE 18 +#define DECLARE_MAC_BUF(var) char var[MAC_BUF_SIZE] __maybe_unused #endif -- cgit v1.2.3 From ef39592f786b6d56d9faf988a3f18786eeb050b3 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Sun, 30 Dec 2007 23:16:06 -0800 Subject: [ATM]: Convert struct class_device to struct device Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman Signed-off-by: Chas Williams --- include/linux/atmdev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index 2096e5c72827..a3d07c29d16c 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -359,7 +359,7 @@ struct atm_dev { struct proc_dir_entry *proc_entry; /* proc entry */ char *proc_name; /* proc entry name */ #endif - struct class_device class_dev; /* sysfs class device */ + struct device class_dev; /* sysfs device */ struct list_head dev_list; /* linkage */ }; @@ -461,7 +461,7 @@ static inline void atm_dev_put(struct atm_dev *dev) BUG_ON(!test_bit(ATM_DF_REMOVED, &dev->flags)); if (dev->ops->dev_close) dev->ops->dev_close(dev); - class_device_put(&dev->class_dev); + put_device(&dev->class_dev); } } -- cgit v1.2.3 From 097b19a9987204b898299260ee3ebff4cf716800 Mon Sep 17 00:00:00 2001 From: Eric Kinzie Date: Sun, 30 Dec 2007 23:17:53 -0800 Subject: [ATM]: [br2864] routed support Signed-off-by: Chas Williams Signed-off-by: David S. Miller --- include/linux/atmbr2684.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/atmbr2684.h b/include/linux/atmbr2684.h index 969fb6c9e1cc..ccdab6c216cd 100644 --- a/include/linux/atmbr2684.h +++ b/include/linux/atmbr2684.h @@ -14,6 +14,9 @@ #define BR2684_MEDIA_FDDI (3) #define BR2684_MEDIA_802_6 (4) /* 802.6 */ + /* used only at device creation: */ +#define BR2684_FLAG_ROUTED (1<<16) /* payload is routed, not bridged */ + /* * Is there FCS inbound on this VC? This currently isn't supported. */ @@ -35,6 +38,14 @@ #define BR2684_ENCAPS_LLC (1) #define BR2684_ENCAPS_AUTODETECT (2) /* Unsuported */ +/* + * Is this VC bridged or routed? + */ + +#define BR2684_PAYLOAD_ROUTED (0) +#define BR2684_PAYLOAD_BRIDGED (1) + + /* * This is for the ATM_NEWBACKENDIF call - these are like socket families: * the first element of the structure is the backend number and the rest @@ -42,7 +53,7 @@ */ struct atm_newif_br2684 { atm_backend_t backend_num; /* ATM_BACKEND_BR2684 */ - int media; /* BR2684_MEDIA_* */ + int media; /* BR2684_MEDIA_*, flags in upper bits */ char ifname[IFNAMSIZ]; int mtu; }; @@ -95,6 +106,11 @@ struct br2684_filter_set { struct br2684_filter filter; }; +enum br2684_payload { + p_routed = BR2684_PAYLOAD_ROUTED, + p_bridged = BR2684_PAYLOAD_BRIDGED, +}; + #define BR2684_SETFILT _IOW( 'a', ATMIOC_BACKEND + 0, \ struct br2684_filter_set) -- cgit v1.2.3 From fb64c735a52f396aa261844b851cd820a80dee46 Mon Sep 17 00:00:00 2001 From: Chas Williams Date: Sun, 30 Dec 2007 23:18:29 -0800 Subject: [ATM]: [br2864] whitespace cleanup Signed-off-by: Chas Williams Signed-off-by: David S. Miller --- include/linux/atmbr2684.h | 43 +++++++++++++++++++++---------------------- 1 file changed, 21 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atmbr2684.h b/include/linux/atmbr2684.h index ccdab6c216cd..52bf72affbba 100644 --- a/include/linux/atmbr2684.h +++ b/include/linux/atmbr2684.h @@ -15,7 +15,7 @@ #define BR2684_MEDIA_802_6 (4) /* 802.6 */ /* used only at device creation: */ -#define BR2684_FLAG_ROUTED (1<<16) /* payload is routed, not bridged */ +#define BR2684_FLAG_ROUTED (1<<16) /* payload is routed, not bridged */ /* * Is there FCS inbound on this VC? This currently isn't supported. @@ -45,17 +45,16 @@ #define BR2684_PAYLOAD_ROUTED (0) #define BR2684_PAYLOAD_BRIDGED (1) - /* * This is for the ATM_NEWBACKENDIF call - these are like socket families: * the first element of the structure is the backend number and the rest * is per-backend specific */ struct atm_newif_br2684 { - atm_backend_t backend_num; /* ATM_BACKEND_BR2684 */ - int media; /* BR2684_MEDIA_*, flags in upper bits */ - char ifname[IFNAMSIZ]; - int mtu; + atm_backend_t backend_num; /* ATM_BACKEND_BR2684 */ + int media; /* BR2684_MEDIA_*, flags in upper bits */ + char ifname[IFNAMSIZ]; + int mtu; }; /* @@ -66,10 +65,10 @@ struct atm_newif_br2684 { #define BR2684_FIND_BYNUM (1) #define BR2684_FIND_BYIFNAME (2) struct br2684_if_spec { - int method; /* BR2684_FIND_* */ + int method; /* BR2684_FIND_* */ union { - char ifname[IFNAMSIZ]; - int devnum; + char ifname[IFNAMSIZ]; + int devnum; } spec; }; @@ -79,16 +78,16 @@ struct br2684_if_spec { * is per-backend specific */ struct atm_backend_br2684 { - atm_backend_t backend_num; /* ATM_BACKEND_BR2684 */ + atm_backend_t backend_num; /* ATM_BACKEND_BR2684 */ struct br2684_if_spec ifspec; - int fcs_in; /* BR2684_FCSIN_* */ - int fcs_out; /* BR2684_FCSOUT_* */ - int fcs_auto; /* 1: fcs_{in,out} disabled if no FCS rx'ed */ - int encaps; /* BR2684_ENCAPS_* */ - int has_vpiid; /* 1: use vpn_id - Unsupported */ - __u8 vpn_id[7]; - int send_padding; /* unsupported */ - int min_size; /* we will pad smaller packets than this */ + int fcs_in; /* BR2684_FCSIN_* */ + int fcs_out; /* BR2684_FCSOUT_* */ + int fcs_auto; /* 1: fcs_{in,out} disabled if no FCS rx'ed */ + int encaps; /* BR2684_ENCAPS_* */ + int has_vpiid; /* 1: use vpn_id - Unsupported */ + __u8 vpn_id[7]; + int send_padding; /* unsupported */ + int min_size; /* we will pad smaller packets than this */ }; /* @@ -97,8 +96,8 @@ struct atm_backend_br2684 { * efficient per-if in/out filters, this support will be removed */ struct br2684_filter { - __be32 prefix; /* network byte order */ - __be32 netmask; /* 0 = disable filter */ + __be32 prefix; /* network byte order */ + __be32 netmask; /* 0 = disable filter */ }; struct br2684_filter_set { @@ -107,8 +106,8 @@ struct br2684_filter_set { }; enum br2684_payload { - p_routed = BR2684_PAYLOAD_ROUTED, - p_bridged = BR2684_PAYLOAD_BRIDGED, + p_routed = BR2684_PAYLOAD_ROUTED, + p_bridged = BR2684_PAYLOAD_BRIDGED, }; #define BR2684_SETFILT _IOW( 'a', ATMIOC_BACKEND + 0, \ -- cgit v1.2.3 From f1862b0ae2294f6970f695abf02392d025e02dbe Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sun, 27 Jan 2008 23:04:43 -0800 Subject: [SHAPER]: The scheduled shaper removal. This patch contains the scheduled removal of the shaper driver. Signed-off-by: Adrian Bunk Acked-by: Alan Cox Signed-off-by: David S. Miller --- include/linux/Kbuild | 1 - include/linux/if_shaper.h | 51 ----------------------------------------------- 2 files changed, 52 deletions(-) delete mode 100644 include/linux/if_shaper.h (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index a85e87fd60d7..bc33a5c87d64 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -231,7 +231,6 @@ unifdef-y += if_ltalk.h unifdef-y += if_link.h unifdef-y += if_pppol2tp.h unifdef-y += if_pppox.h -unifdef-y += if_shaper.h unifdef-y += if_tr.h unifdef-y += if_tun.h unifdef-y += if_vlan.h diff --git a/include/linux/if_shaper.h b/include/linux/if_shaper.h deleted file mode 100644 index 3b1b7ba19825..000000000000 --- a/include/linux/if_shaper.h +++ /dev/null @@ -1,51 +0,0 @@ -#ifndef __LINUX_SHAPER_H -#define __LINUX_SHAPER_H - -#ifdef __KERNEL__ - -#define SHAPER_QLEN 10 -/* - * This is a bit speed dependent (read it shouldn't be a constant!) - * - * 5 is about right for 28.8 upwards. Below that double for every - * halving of speed or so. - ie about 20 for 9600 baud. - */ -#define SHAPER_LATENCY (5*HZ) -#define SHAPER_MAXSLIP 2 -#define SHAPER_BURST (HZ/50) /* Good for >128K then */ - -struct shaper -{ - struct sk_buff_head sendq; - __u32 bytespertick; - __u32 bitspersec; - __u32 shapelatency; - __u32 shapeclock; - unsigned long recovery; /* Time we can next clock a packet out on - an empty queue */ - spinlock_t lock; - struct net_device *dev; - struct net_device_stats* (*get_stats)(struct net_device *dev); - struct timer_list timer; -}; - -#endif - -#define SHAPER_SET_DEV 0x0001 -#define SHAPER_SET_SPEED 0x0002 -#define SHAPER_GET_DEV 0x0003 -#define SHAPER_GET_SPEED 0x0004 - -struct shaperconf -{ - __u16 ss_cmd; - union - { - char ssu_name[14]; - __u32 ssu_speed; - } ss_u; -#define ss_speed ss_u.ssu_speed -#define ss_name ss_u.ssu_name -}; - -#endif -- cgit v1.2.3 From 571e7682026fd0e25833d103a3eeb74be29bf199 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 3 Jan 2008 20:41:28 -0800 Subject: [LIB] pcounter : unline too big functions Before pushing pcounter to Linus tree, I would like to make some adjustments. Goal is to reduce kernel text size, by unlining too big functions. When a pcounter is bound to a statically defined per_cpu variable, we define two small helpers functions. (No more folding function using the fat for_each_possible_cpu(cpu) ... ) static DEFINE_PER_CPU(int, NAME##_pcounter_values); static void NAME##_pcounter_add(struct pcounter *self, int val) { __get_cpu_var(NAME##_pcounter_values) += val; } static int NAME##_pcounter_getval(const struct pcounter *self, int cpu) { return per_cpu(NAME##_pcounter_values, cpu); } Fast path is therefore unchanged, while folding/alloc/free is now unlined. This saves 228 bytes on i386 Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/pcounter.h | 80 ++++++++++++++++-------------------------------- 1 file changed, 26 insertions(+), 54 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pcounter.h b/include/linux/pcounter.h index 9c4760a328f3..a82d9f2628ca 100644 --- a/include/linux/pcounter.h +++ b/include/linux/pcounter.h @@ -1,41 +1,39 @@ #ifndef __LINUX_PCOUNTER_H #define __LINUX_PCOUNTER_H - +/* + * Using a dynamic percpu 'int' variable has a cost : + * 1) Extra dereference + * Current per_cpu_ptr() implementation uses an array per 'percpu variable'. + * 2) memory cost of NR_CPUS*(32+sizeof(void *)) instead of num_possible_cpus()*4 + * + * This pcounter implementation is an abstraction to be able to use + * either a static or a dynamic per cpu variable. + * One dynamic per cpu variable gets a fast & cheap implementation, we can + * change pcounter implementation too. + */ struct pcounter { #ifdef CONFIG_SMP void (*add)(struct pcounter *self, int inc); - int (*getval)(const struct pcounter *self); + int (*getval)(const struct pcounter *self, int cpu); int *per_cpu_values; #else int val; #endif }; -/* - * Special macros to let pcounters use a fast version of {getvalue|add} - * using a static percpu variable per pcounter instead of an allocated one, - * saving one dereference. - * This might be changed if/when dynamic percpu vars become fast. - */ #ifdef CONFIG_SMP -#include #include -#define DEFINE_PCOUNTER(NAME) \ -static DEFINE_PER_CPU(int, NAME##_pcounter_values); \ -static void NAME##_pcounter_add(struct pcounter *self, int inc) \ -{ \ - __get_cpu_var(NAME##_pcounter_values) += inc; \ -} \ - \ -static int NAME##_pcounter_getval(const struct pcounter *self) \ -{ \ - int res = 0, cpu; \ - \ - for_each_possible_cpu(cpu) \ - res += per_cpu(NAME##_pcounter_values, cpu); \ - return res; \ -} +#define DEFINE_PCOUNTER(NAME) \ +static DEFINE_PER_CPU(int, NAME##_pcounter_values); \ +static void NAME##_pcounter_add(struct pcounter *self, int val) \ +{ \ + __get_cpu_var(NAME##_pcounter_values) += val; \ +} \ +static int NAME##_pcounter_getval(const struct pcounter *self, int cpu) \ +{ \ + return per_cpu(NAME##_pcounter_values, cpu); \ +} \ #define PCOUNTER_MEMBER_INITIALIZER(NAME, MEMBER) \ MEMBER = { \ @@ -43,42 +41,16 @@ static int NAME##_pcounter_getval(const struct pcounter *self) \ .getval = NAME##_pcounter_getval, \ } -extern void pcounter_def_add(struct pcounter *self, int inc); -extern int pcounter_def_getval(const struct pcounter *self); - -static inline int pcounter_alloc(struct pcounter *self) -{ - int rc = 0; - if (self->add == NULL) { - self->per_cpu_values = alloc_percpu(int); - if (self->per_cpu_values != NULL) { - self->add = pcounter_def_add; - self->getval = pcounter_def_getval; - } else - rc = 1; - } - return rc; -} - -static inline void pcounter_free(struct pcounter *self) -{ - if (self->per_cpu_values != NULL) { - free_percpu(self->per_cpu_values); - self->per_cpu_values = NULL; - self->getval = NULL; - self->add = NULL; - } -} static inline void pcounter_add(struct pcounter *self, int inc) { self->add(self, inc); } -static inline int pcounter_getval(const struct pcounter *self) -{ - return self->getval(self); -} +extern int pcounter_getval(const struct pcounter *self); +extern int pcounter_alloc(struct pcounter *self); +extern void pcounter_free(struct pcounter *self); + #else /* CONFIG_SMP */ -- cgit v1.2.3 From 96a899655e2c3ba53f083eda69706ee4eb05271f Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 4 Jan 2008 01:59:20 -0800 Subject: [CONNECTOR]: Cleanup struct cn_queue_dev Struct member netlink_groups is never used, and I don't see how it can be useful. Signed-off-by: Li Zefan Signed-off-by: David S. Miller --- include/linux/connector.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/connector.h b/include/linux/connector.h index 13fc4541bf23..7e18311d655e 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -112,7 +112,6 @@ struct cn_queue_dev { struct list_head queue_list; spinlock_t queue_lock; - int netlink_groups; struct sock *nls; }; -- cgit v1.2.3 From 6e32814bc89e7103e2b75b841155faf51f60a8f1 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 4 Jan 2008 01:59:42 -0800 Subject: [CONNECTOR]: Cleanup struct cn_callback_entry - 'cb' is a fake struct member. In a previous patch struct cn_callback was renamed to cn_callback_id, so 'cb' should have been deleted at that time. - 'nls' isn't used and is redundant, we can retrieve this data through cn_callback_entry.pdev->nls. - 'seq' and 'group' should be u32, as they are declared to be u32 in other places. Signed-off-by: Li Zefan Signed-off-by: David S. Miller --- include/linux/connector.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/connector.h b/include/linux/connector.h index 7e18311d655e..da6dd957f908 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -132,15 +132,13 @@ struct cn_callback_data { struct cn_callback_entry { struct list_head callback_entry; - struct cn_callback *cb; struct work_struct work; struct cn_queue_dev *pdev; struct cn_callback_id id; struct cn_callback_data data; - int seq, group; - struct sock *nls; + u32 seq, group; }; struct cn_ctl_entry { -- cgit v1.2.3 From 07db218396650933abff3c5c1ad1e2a6e0cfedeb Mon Sep 17 00:00:00 2001 From: Ron Rindjunsky Date: Tue, 25 Dec 2007 17:00:33 +0200 Subject: mac80211: A-MPDU Rx adding basic functionality This patch adds the basic needed abilities and functions for A-MPDU Rx session changed functions: - ieee80211_sta_process_addba_request - Rx A-MPDU initialization enabled - ieee80211_stop - stops all A-MPDU Rx in case interface goes down added functions: - ieee80211_send_delba - used for sending out Del BA in A-MPDU sessions - ieee80211_sta_stop_rx_BA_session - stopping Rx A-MPDU session - sta_rx_agg_session_timer_expired - stops A-MPDU Rx use if load is too low Signed-off-by: Ron Rindjunsky Signed-off-by: John W. Linville Signed-off-by: David S. Miller --- include/linux/ieee80211.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 3e641590d0c8..4d5a4c9dcba7 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -472,6 +472,13 @@ enum ieee80211_back_actioncode { WLAN_ACTION_DELBA = 2, }; +/* BACK (block-ack) parties */ +enum ieee80211_back_parties { + WLAN_BACK_RECIPIENT = 0, + WLAN_BACK_INITIATOR = 1, + WLAN_BACK_TIMER = 2, +}; + /* A-MSDU 802.11n */ #define IEEE80211_QOS_CONTROL_A_MSDU_PRESENT 0x0080 -- cgit v1.2.3 From f0b5a0dcf125ce43855961ef4f965a91112bea23 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 8 Jan 2008 23:54:43 -0800 Subject: [VLAN]: Avoid expensive divides We can avoid divides (as seen with CONFIG_CC_OPTIMIZE_FOR_SIZE=y on x86) changing vlan_group_get_device()/vlan_group_set_device() id parameter from signed to unsigned. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 976d4b1067d1..4562105fdb2b 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -81,14 +81,16 @@ struct vlan_group { struct rcu_head rcu; }; -static inline struct net_device *vlan_group_get_device(struct vlan_group *vg, int vlan_id) +static inline struct net_device *vlan_group_get_device(struct vlan_group *vg, + unsigned int vlan_id) { struct net_device **array; array = vg->vlan_devices_arrays[vlan_id / VLAN_GROUP_ARRAY_PART_LEN]; return array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN]; } -static inline void vlan_group_set_device(struct vlan_group *vg, int vlan_id, +static inline void vlan_group_set_device(struct vlan_group *vg, + unsigned int vlan_id, struct net_device *dev) { struct net_device **array; -- cgit v1.2.3 From b3fd3ffe39d830e7c24ef63b7f28703b485da2e3 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Wed, 9 Jan 2008 00:34:02 -0800 Subject: [NETFILTER]: Use the ctl paths instead of hand-made analogue The conntracks subsystem has a similar infrastructure to maintain ctl_paths, but since we already have it on the generic level, I think it's OK to switch to using it. So, basically, this patch just replaces the ctl_table-s with ctl_path-s, nf_register_sysctl_table with register_sysctl_paths() and removes no longer needed code. After this the net/netfilter/nf_sysctl.c file contains the paths only. Signed-off-by: Pavel Emelyanov Acked-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index d190d560de61..c41f6438095d 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -120,12 +120,8 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg); #ifdef CONFIG_SYSCTL /* Sysctl registration */ -struct ctl_table_header *nf_register_sysctl_table(struct ctl_table *path, - struct ctl_table *table); -void nf_unregister_sysctl_table(struct ctl_table_header *header, - struct ctl_table *table); -extern struct ctl_table nf_net_netfilter_sysctl_path[]; -extern struct ctl_table nf_net_ipv4_netfilter_sysctl_path[]; +extern struct ctl_path nf_net_netfilter_sysctl_path[]; +extern struct ctl_path nf_net_ipv4_netfilter_sysctl_path[]; #endif /* CONFIG_SYSCTL */ extern struct list_head nf_hooks[NPROTO][NF_MAX_HOOKS]; -- cgit v1.2.3 From e5d69b9f4a6ce17f0d09595da45e37b870fee5ae Mon Sep 17 00:00:00 2001 From: "Denis V. Lunev" Date: Thu, 10 Jan 2008 03:51:41 -0800 Subject: [ATM]: Oops reading net/atm/arp cat /proc/net/atm/arp causes the NULL pointer dereference in the get_proc_net+0xc/0x3a. This happens as proc_get_net believes that the parent proc dir entry contains struct net. Fix this assumption for "net/atm" case. The problem is introduced by the commit c0097b07abf5f92ab135d024dd41bd2aada1512f from Eric W. Biederman/Daniel Lezcano. Signed-off-by: Denis V. Lunev Signed-off-by: David S. Miller --- include/linux/proc_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index a5316829215b..8f92546b403d 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -201,6 +201,8 @@ static inline struct proc_dir_entry *create_proc_info_entry(const char *name, extern struct proc_dir_entry *proc_net_fops_create(struct net *net, const char *name, mode_t mode, const struct file_operations *fops); extern void proc_net_remove(struct net *net, const char *name); +extern struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name, + struct proc_dir_entry *parent); #else -- cgit v1.2.3 From ba749ae98d5aa9d2ce9a7facde0deed454f92230 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 12 Jan 2008 21:30:23 -0800 Subject: [XFRM]: alg_key_len should be unsigned to avoid integer divides alg_key_len is currently defined as 'signed int'. This unfortunatly leads to integer divides in several paths. Converting it to unsigned is safe and saves 208 bytes of text on i386. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/xfrm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index 1131eabfaa2a..f8507eed0b79 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -92,7 +92,7 @@ struct xfrm_replay_state struct xfrm_algo { char alg_name[64]; - int alg_key_len; /* in bits */ + unsigned int alg_key_len; /* in bits */ char alg_key[0]; }; -- cgit v1.2.3 From 3f4afb6443aaa1d69b2d8f0461c8191e40d54c3c Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sat, 12 Jan 2008 21:31:29 -0800 Subject: [XFRM]: Fix struct xfrm_algo code formatting. Realign struct members. Signed-off-by: David S. Miller --- include/linux/xfrm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index f8507eed0b79..9b5b00c4ef9d 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -91,9 +91,9 @@ struct xfrm_replay_state }; struct xfrm_algo { - char alg_name[64]; + char alg_name[64]; unsigned int alg_key_len; /* in bits */ - char alg_key[0]; + char alg_key[0]; }; struct xfrm_stats { -- cgit v1.2.3 From 9bd85e32644d4d3744117b0a196ad4382f8acf35 Mon Sep 17 00:00:00 2001 From: "Denis V. Lunev" Date: Mon, 14 Jan 2008 23:05:55 -0800 Subject: [IPV4]: Remove extra argument from arp_ignore. arp_ignore has two arguments: dev & in_dev. dev is used for inet_confirm_addr calling only. inet_confirm_addr, in turn, either gets in_dev from the device passed or iterates over all network devices if the device passed is NULL. It seems logical to directly pass in_dev into inet_confirm_addr. Signed-off-by: Denis V. Lunev Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index b3c5081de02d..45f373107530 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -135,7 +135,7 @@ extern int devinet_ioctl(unsigned int cmd, void __user *); extern void devinet_init(void); extern struct in_device *inetdev_by_index(int); extern __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope); -extern __be32 inet_confirm_addr(const struct net_device *dev, __be32 dst, __be32 local, int scope); +extern __be32 inet_confirm_addr(struct in_device *in_dev, __be32 dst, __be32 local, int scope); extern struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); static __inline__ int inet_ifa_match(__be32 addr, struct in_ifaddr *ifa) -- cgit v1.2.3 From 8b6f3f62fea7b85fce8f7d12aabba7b191bf60d2 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Mon, 14 Jan 2008 23:33:14 -0800 Subject: [NETFILTER]: Annotate start of kernel fields in NF headers Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/xt_RATEEST.h | 2 ++ include/linux/netfilter/xt_connlimit.h | 2 +- include/linux/netfilter/xt_hashlimit.h | 2 +- include/linux/netfilter/xt_quota.h | 2 ++ include/linux/netfilter/xt_rateest.h | 2 ++ include/linux/netfilter/xt_statistic.h | 1 + include/linux/netfilter/xt_string.h | 2 ++ include/linux/netfilter_ipv4/ipt_CLUSTERIP.h | 1 + 8 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_RATEEST.h b/include/linux/netfilter/xt_RATEEST.h index 670f2e49d4fb..f79e3133cbea 100644 --- a/include/linux/netfilter/xt_RATEEST.h +++ b/include/linux/netfilter/xt_RATEEST.h @@ -5,6 +5,8 @@ struct xt_rateest_target_info { char name[IFNAMSIZ]; int8_t interval; u_int8_t ewma_log; + + /* Used internally by the kernel */ struct xt_rateest *est __attribute__((aligned(8))); }; diff --git a/include/linux/netfilter/xt_connlimit.h b/include/linux/netfilter/xt_connlimit.h index 315d2dce9da6..7e3284bcbd2b 100644 --- a/include/linux/netfilter/xt_connlimit.h +++ b/include/linux/netfilter/xt_connlimit.h @@ -15,7 +15,7 @@ struct xt_connlimit_info { }; unsigned int limit, inverse; - /* this needs to be at the end */ + /* Used internally by the kernel */ struct xt_connlimit_data *data __attribute__((aligned(8))); }; diff --git a/include/linux/netfilter/xt_hashlimit.h b/include/linux/netfilter/xt_hashlimit.h index b4556b8edbfd..c19972e4564d 100644 --- a/include/linux/netfilter/xt_hashlimit.h +++ b/include/linux/netfilter/xt_hashlimit.h @@ -29,9 +29,9 @@ struct hashlimit_cfg { struct xt_hashlimit_info { char name [IFNAMSIZ]; /* name */ struct hashlimit_cfg cfg; - struct xt_hashlimit_htable *hinfo; /* Used internally by the kernel */ + struct xt_hashlimit_htable *hinfo; union { void *ptr; struct xt_hashlimit_info *master; diff --git a/include/linux/netfilter/xt_quota.h b/include/linux/netfilter/xt_quota.h index acd7fd77bbee..4c8368d781e5 100644 --- a/include/linux/netfilter/xt_quota.h +++ b/include/linux/netfilter/xt_quota.h @@ -9,6 +9,8 @@ enum xt_quota_flags { struct xt_quota_info { u_int32_t flags; u_int32_t pad; + + /* Used internally by the kernel */ aligned_u64 quota; struct xt_quota_info *master; }; diff --git a/include/linux/netfilter/xt_rateest.h b/include/linux/netfilter/xt_rateest.h index 51948e15aea2..2010cb74250f 100644 --- a/include/linux/netfilter/xt_rateest.h +++ b/include/linux/netfilter/xt_rateest.h @@ -26,6 +26,8 @@ struct xt_rateest_match_info { u_int32_t pps1; u_int32_t bps2; u_int32_t pps2; + + /* Used internally by the kernel */ struct xt_rateest *est1 __attribute__((aligned(8))); struct xt_rateest *est2 __attribute__((aligned(8))); }; diff --git a/include/linux/netfilter/xt_statistic.h b/include/linux/netfilter/xt_statistic.h index c344e9916e23..3d38bc975048 100644 --- a/include/linux/netfilter/xt_statistic.h +++ b/include/linux/netfilter/xt_statistic.h @@ -23,6 +23,7 @@ struct xt_statistic_info { struct { u_int32_t every; u_int32_t packet; + /* Used internally by the kernel */ u_int32_t count; } nth; } u; diff --git a/include/linux/netfilter/xt_string.h b/include/linux/netfilter/xt_string.h index 3b3419f2637d..bb21dd1aee2d 100644 --- a/include/linux/netfilter/xt_string.h +++ b/include/linux/netfilter/xt_string.h @@ -12,6 +12,8 @@ struct xt_string_info char pattern[XT_STRING_MAX_PATTERN_SIZE]; u_int8_t patlen; u_int8_t invert; + + /* Used internally by the kernel */ struct ts_config __attribute__((aligned(8))) *config; }; diff --git a/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h b/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h index daf50be22c9d..e5a3687c8a72 100644 --- a/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h +++ b/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h @@ -27,6 +27,7 @@ struct ipt_clusterip_tgt_info { u_int32_t hash_mode; u_int32_t hash_initval; + /* Used internally by the kernel */ struct clusterip_config *config; }; -- cgit v1.2.3 From 0dc8c76029f4675c2345eefd947f123e64de1aae Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Mon, 14 Jan 2008 23:38:34 -0800 Subject: [NETFILTER]: xt_CONNMARK target, revision 1 Introduces the xt_CONNMARK target revision 1. It uses fixed types, and also uses the more expressive XOR logic. Futhermore, it allows to selectively pick bits from both the ctmark and the nfmark in the SAVE and RESTORE operations. Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/xt_CONNMARK.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_CONNMARK.h b/include/linux/netfilter/xt_CONNMARK.h index 9f744689fffc..4e58ba43c289 100644 --- a/include/linux/netfilter/xt_CONNMARK.h +++ b/include/linux/netfilter/xt_CONNMARK.h @@ -22,4 +22,9 @@ struct xt_connmark_target_info { u_int8_t mode; }; +struct xt_connmark_tginfo1 { + u_int32_t ctmark, ctmask, nfmask; + u_int8_t mode; +}; + #endif /*_XT_CONNMARK_H_target*/ -- cgit v1.2.3 From e0a812aea5cbf2085f7645bf2bfd9cba91c8a672 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Mon, 14 Jan 2008 23:38:52 -0800 Subject: [NETFILTER]: xt_MARK target, revision 2 Introduces the xt_MARK target revision 2. It uses fixed types, and also uses the more expressive XOR logic. Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/xt_MARK.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_MARK.h b/include/linux/netfilter/xt_MARK.h index b021e93ee5d6..778b278fd9f2 100644 --- a/include/linux/netfilter/xt_MARK.h +++ b/include/linux/netfilter/xt_MARK.h @@ -18,4 +18,8 @@ struct xt_mark_target_info_v1 { u_int8_t mode; }; +struct xt_mark_tginfo2 { + u_int32_t mark, mask; +}; + #endif /*_XT_MARK_H_target */ -- cgit v1.2.3 From 96e3227265852ffad332f911887c9cf26c85e40a Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Mon, 14 Jan 2008 23:39:13 -0800 Subject: [NETFILTER]: xt_connmark match, revision 1 Introduces the xt_connmark match revision 1. It uses fixed types, eventually obsoleting revision 0 some day (uses nonfixed types). (Unfixed types like "unsigned long" do not play well with mixed user-/kernelspace "bitness", e.g. 32/64, as is common on SPARC64, and need extra compat code.) Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/xt_connmark.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_connmark.h b/include/linux/netfilter/xt_connmark.h index c592f6ae0883..359ef86918dc 100644 --- a/include/linux/netfilter/xt_connmark.h +++ b/include/linux/netfilter/xt_connmark.h @@ -15,4 +15,9 @@ struct xt_connmark_info { u_int8_t invert; }; +struct xt_connmark_mtinfo1 { + u_int32_t mark, mask; + u_int8_t invert; +}; + #endif /*_XT_CONNMARK_H*/ -- cgit v1.2.3 From 2e3075a2c4364c0e8726ac2a0f3b1708da781bac Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Mon, 14 Jan 2008 23:40:34 -0800 Subject: [NETFILTER]: Extend nf_inet_addr with in{,6}_addr Extend union nf_inet_addr with struct in_addr and in6_addr. Useful because a lot of in-kernel IPv4 and IPv6 functions use in_addr/in6_addr. Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index c41f6438095d..d74e79bacd2d 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -7,6 +7,8 @@ #include #include #include +#include +#include #include #include #endif @@ -52,6 +54,8 @@ union nf_inet_addr { u_int32_t all[4]; __be32 ip; __be32 ip6[4]; + struct in_addr in; + struct in6_addr in6; }; #ifdef __KERNEL__ -- cgit v1.2.3 From 64eb12f9972d45f3b9b0f0a33a966e311c3d5275 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Mon, 14 Jan 2008 23:40:53 -0800 Subject: [NETFILTER]: xt_conntrack match, revision 1 Introduces the xt_conntrack match revision 1. It uses fixed types, the new nf_inet_addr and comes with IPv6 support, thereby completely superseding xt_state. Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/xt_conntrack.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_conntrack.h b/include/linux/netfilter/xt_conntrack.h index 70b6f718cf4c..d2492a3329be 100644 --- a/include/linux/netfilter/xt_conntrack.h +++ b/include/linux/netfilter/xt_conntrack.h @@ -6,7 +6,9 @@ #define _XT_CONNTRACK_H #include -#include +#ifdef __KERNEL__ +# include +#endif #define XT_CONNTRACK_STATE_BIT(ctinfo) (1 << ((ctinfo)%IP_CT_IS_REPLY+1)) #define XT_CONNTRACK_STATE_INVALID (1 << 0) @@ -60,4 +62,16 @@ struct xt_conntrack_info /* Inverse flags */ u_int8_t invflags; }; + +struct xt_conntrack_mtinfo1 { + union nf_inet_addr origsrc_addr, origsrc_mask; + union nf_inet_addr origdst_addr, origdst_mask; + union nf_inet_addr replsrc_addr, replsrc_mask; + union nf_inet_addr repldst_addr, repldst_mask; + u_int32_t expires_min, expires_max; + u_int16_t l4proto; + u_int8_t state_mask, status_mask; + u_int8_t match_flags, invert_flags; +}; + #endif /*_XT_CONNTRACK_H*/ -- cgit v1.2.3 From 17b0d7ef658583842da75eebf8001dc617f0b52e Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Mon, 14 Jan 2008 23:41:11 -0800 Subject: [NETFILTER]: xt_mark match, revision 1 Introduces the xt_mark match revision 1. It uses fixed types, eventually obsoleting revision 0 some day (uses nonfixed types). Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/xt_mark.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_mark.h b/include/linux/netfilter/xt_mark.h index 802dd4842caf..fae74bc3f34e 100644 --- a/include/linux/netfilter/xt_mark.h +++ b/include/linux/netfilter/xt_mark.h @@ -6,4 +6,9 @@ struct xt_mark_info { u_int8_t invert; }; +struct xt_mark_mtinfo1 { + u_int32_t mark, mask; + u_int8_t invert; +}; + #endif /*_XT_MARK_H*/ -- cgit v1.2.3 From 917b6fbd6e8dd952c64d1d7468897160467d2cc0 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Mon, 14 Jan 2008 23:42:06 -0800 Subject: [NETFILTER]: xt_policy: use the new union nf_inet_addr Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/xt_policy.h | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_policy.h b/include/linux/netfilter/xt_policy.h index 45654d359a68..053d8cc65464 100644 --- a/include/linux/netfilter/xt_policy.h +++ b/include/linux/netfilter/xt_policy.h @@ -27,18 +27,33 @@ struct xt_policy_spec reqid:1; }; +#ifndef __KERNEL__ union xt_policy_addr { struct in_addr a4; struct in6_addr a6; }; +#endif struct xt_policy_elem { - union xt_policy_addr saddr; - union xt_policy_addr smask; - union xt_policy_addr daddr; - union xt_policy_addr dmask; + union { +#ifdef __KERNEL__ + struct { + union nf_inet_addr saddr; + union nf_inet_addr smask; + union nf_inet_addr daddr; + union nf_inet_addr dmask; + }; +#else + struct { + union xt_policy_addr saddr; + union xt_policy_addr smask; + union xt_policy_addr daddr; + union xt_policy_addr dmask; + }; +#endif + }; __be32 spi; u_int32_t reqid; u_int8_t proto; -- cgit v1.2.3 From f72e25a897c7edda03a0e1f767925d98772684da Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Mon, 14 Jan 2008 23:42:47 -0800 Subject: [NETFILTER]: Rename ipt_iprange to xt_iprange This patch moves ipt_iprange to xt_iprange, in preparation for adding IPv6 support to xt_iprange. Signed-off-by: Jan Engelhardt Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/Kbuild | 1 + include/linux/netfilter/xt_iprange.h | 17 +++++++++++++++++ include/linux/netfilter_ipv4/ipt_iprange.h | 6 +----- 3 files changed, 19 insertions(+), 5 deletions(-) create mode 100644 include/linux/netfilter/xt_iprange.h (limited to 'include/linux') diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild index ac9e6429f747..91fef0cae42f 100644 --- a/include/linux/netfilter/Kbuild +++ b/include/linux/netfilter/Kbuild @@ -21,6 +21,7 @@ header-y += xt_dccp.h header-y += xt_dscp.h header-y += xt_esp.h header-y += xt_hashlimit.h +header-y += xt_iprange.h header-y += xt_helper.h header-y += xt_length.h header-y += xt_limit.h diff --git a/include/linux/netfilter/xt_iprange.h b/include/linux/netfilter/xt_iprange.h new file mode 100644 index 000000000000..a4299c7d3680 --- /dev/null +++ b/include/linux/netfilter/xt_iprange.h @@ -0,0 +1,17 @@ +#ifndef _LINUX_NETFILTER_XT_IPRANGE_H +#define _LINUX_NETFILTER_XT_IPRANGE_H 1 + +enum { + IPRANGE_SRC = 1 << 0, /* match source IP address */ + IPRANGE_DST = 1 << 1, /* match destination IP address */ + IPRANGE_SRC_INV = 1 << 4, /* negate the condition */ + IPRANGE_DST_INV = 1 << 5, /* -"- */ +}; + +struct xt_iprange_mtinfo { + union nf_inet_addr src_min, src_max; + union nf_inet_addr dst_min, dst_max; + u_int8_t flags; +}; + +#endif /* _LINUX_NETFILTER_XT_IPRANGE_H */ diff --git a/include/linux/netfilter_ipv4/ipt_iprange.h b/include/linux/netfilter_ipv4/ipt_iprange.h index a92fefc3c7ec..5f1aebde4d2f 100644 --- a/include/linux/netfilter_ipv4/ipt_iprange.h +++ b/include/linux/netfilter_ipv4/ipt_iprange.h @@ -2,11 +2,7 @@ #define _IPT_IPRANGE_H #include - -#define IPRANGE_SRC 0x01 /* Match source IP address */ -#define IPRANGE_DST 0x02 /* Match destination IP address */ -#define IPRANGE_SRC_INV 0x10 /* Negate the condition */ -#define IPRANGE_DST_INV 0x20 /* Negate the condition */ +#include struct ipt_iprange { /* Inclusive: network order. */ -- cgit v1.2.3 From e37b386c95fff34eb0eebeaf257c4f5a8b69b81f Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 14 Jan 2008 23:47:44 -0800 Subject: [NETFILTER]: nf_conntrack_sctp: remove unused ttag field from conntrack data Spotted by Pablo Neira Ayuso . Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nf_conntrack_sctp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_sctp.h b/include/linux/netfilter/nf_conntrack_sctp.h index 5cf2c115cce4..768f78c4ac53 100644 --- a/include/linux/netfilter/nf_conntrack_sctp.h +++ b/include/linux/netfilter/nf_conntrack_sctp.h @@ -21,7 +21,6 @@ struct ip_ct_sctp enum sctp_conntrack state; __be32 vtag[IP_CT_DIR_MAX]; - u_int32_t ttag[IP_CT_DIR_MAX]; }; #endif /* _NF_CONNTRACK_SCTP_H */ -- cgit v1.2.3 From a2fbb9ea235467b0be6db3cec0132b6c83c0b9fb Mon Sep 17 00:00:00 2001 From: Eliezer Tamir Date: Thu, 15 Nov 2007 20:09:02 +0200 Subject: add bnx2x driver for BCM57710 Signed-off-by: Eliezer Tamir Signed-off-by: David S. Miller --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 1fbd0256e86b..f162d9c1226c 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1943,6 +1943,7 @@ #define PCI_DEVICE_ID_NX2_5706 0x164a #define PCI_DEVICE_ID_NX2_5708 0x164c #define PCI_DEVICE_ID_TIGON3_5702FE 0x164d +#define PCI_DEVICE_ID_NX2_57710 0x164e #define PCI_DEVICE_ID_TIGON3_5705 0x1653 #define PCI_DEVICE_ID_TIGON3_5705_2 0x1654 #define PCI_DEVICE_ID_TIGON3_5720 0x1658 -- cgit v1.2.3 From 092427be8cef341c957a93ec2469890501a09bff Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Fri, 23 Nov 2007 21:49:27 -0500 Subject: drivers/net/r6040: fix obvious problems (but more remain) - checkpatch fixes - fix bogus and uninitialized return codes in r6040_start_xmit() - netdev_get_settings() fix obvious locking bug flagged by compiler warning - set DMA consistent mask - remove unnecessary setting of dev->base_addr Signed-off-by: Jeff Garzik --- include/linux/pci_ids.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index f162d9c1226c..1280b0c726ea 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2110,6 +2110,9 @@ #define PCI_DEVICE_ID_HERC_WIN 0x5732 #define PCI_DEVICE_ID_HERC_UNI 0x5832 +#define PCI_VENDOR_ID_RDC 0x17f3 +#define PCI_DEVICE_ID_RDC_R6040 0x6040 + #define PCI_VENDOR_ID_SITECOM 0x182d #define PCI_DEVICE_ID_SITECOM_DC105V2 0x3069 -- cgit v1.2.3 From 5ac5d616327bdbdf632bdf4dc9ae09477f79b6b3 Mon Sep 17 00:00:00 2001 From: Francois Romieu Date: Wed, 28 Nov 2007 23:02:33 +0100 Subject: r6040: cleanups - whitespaces vs tabs - use 80 cols - use if_mii - use netdev_priv - remove useless cast to void * - PCI device id does not need to be globally available Signed-off-by: Francois Romieu --- include/linux/pci_ids.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 1280b0c726ea..6b4a132bf861 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2111,7 +2111,6 @@ #define PCI_DEVICE_ID_HERC_UNI 0x5832 #define PCI_VENDOR_ID_RDC 0x17f3 -#define PCI_DEVICE_ID_RDC_R6040 0x6040 #define PCI_VENDOR_ID_SITECOM 0x182d #define PCI_DEVICE_ID_SITECOM_DC105V2 0x3069 -- cgit v1.2.3 From ac82fab44f6b981e3f6b53784e2f23838f4908e1 Mon Sep 17 00:00:00 2001 From: Larry Finger Date: Fri, 9 Nov 2007 16:54:45 -0600 Subject: ssb: Add new SPROM structure while keeping the old The SPROM's for various devices utilizing the Sonics Silicon Backplane come with various revisions. The Revision 2 SPROM inherited the data layout of 1, and Revision 3 inherited the layout of 2. The first instance of Revision 4 has now been found in a BCM4328 wireless LAN card. This device does not inherit any layout from previous versions. Although it was possible to create a data structure that kept all the old layouts, we decided to start fresh, keep only those SPROM variables that are used by the drivers that utilize ssb, and to do the conversion in such a manner that neither compilation or execution will be affected if a bisection lands in the middle of these changes, while keeping the patches as small as possible. In this patch, the sprom structures are changed while maintaining the old ones. Signed-off-by: Larry Finger Signed-off-by: John W. Linville --- include/linux/ssb/ssb.h | 32 ++++++++++++++++++++++++++------ include/linux/ssb/ssb_regs.h | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 58 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 2b5c312c4960..cdd8a2fd4a69 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -78,13 +78,34 @@ struct ssb_sprom_r3 { u32 ofdmgpo; /* G-PHY OFDM Power Offset */ }; -struct ssb_sprom_r4 { - /* TODO */ -}; - struct ssb_sprom { u8 revision; - u8 crc; + u8 temp_fill[2 * sizeof(struct ssb_sprom_r1)]; + u8 il0mac[6]; /* MAC address for 802.11b/g */ + u8 et0mac[6]; /* MAC address for Ethernet */ + u8 et1mac[6]; /* MAC address for 802.11a */ + u8 et0phyaddr; /* MII address for enet0 */ + u8 et1phyaddr; /* MII address for enet1 */ + u8 country_code; /* Country Code */ + u16 pa0b0; + u16 pa0b1; + u16 pa0b2; + u16 pa1b0; + u16 pa1b1; + u16 pa1b2; + u8 gpio0; /* GPIO pin 0 */ + u8 gpio1; /* GPIO pin 1 */ + u8 gpio2; /* GPIO pin 2 */ + u8 gpio3; /* GPIO pin 3 */ + u16 maxpwr_a; /* A-PHY Amplifier Max Power (in dBm Q5.2) */ + u16 maxpwr_bg; /* B/G-PHY Amplifier Max Power (in dBm Q5.2) */ + u8 itssi_a; /* Idle TSSI Target for A-PHY */ + u8 itssi_bg; /* Idle TSSI Target for B/G-PHY */ + u16 boardflags_lo; /* Boardflags (low 16 bits) */ + u8 antenna_gain_a; /* A-PHY Antenna gain (in dBm Q5.2) */ + u8 antenna_gain_bg; /* B/G-PHY Antenna gain (in dBm Q5.2) */ + + /* TODO - add any parameters needed from rev 2, 3, or 4 SPROMs */ /* The valid r# fields are selected by the "revision". * Revision 3 and lower inherit from lower revisions. */ @@ -94,7 +115,6 @@ struct ssb_sprom { struct ssb_sprom_r2 r2; struct ssb_sprom_r3 r3; }; - struct ssb_sprom_r4 r4; }; }; diff --git a/include/linux/ssb/ssb_regs.h b/include/linux/ssb/ssb_regs.h index 47c7c71a5acf..bcebcffd448b 100644 --- a/include/linux/ssb/ssb_regs.h +++ b/include/linux/ssb/ssb_regs.h @@ -250,6 +250,38 @@ #define SSB_SPROM3_CCKPO_11M 0xF000 /* 11M Rate PO */ #define SSB_SPROM3_CCKPO_11M_SHIFT 12 #define SSB_SPROM3_OFDMGPO 0x107A /* G-PHY OFDM Power Offset (4 bytes, BigEndian) */ +/* SPROM Revision 4 */ +#define SSB_SPROM4_IL0MAC 0x104C /* 6 byte MAC address for b/g */ +#define SSB_SPROM4_ETHPHY 0x105A /* Ethernet PHY settings */ +#define SSB_SPROM4_ETHPHY_ET0A 0x001F /* MII Address for enet0 */ +#define SSB_SPROM4_ETHPHY_ET1A 0x03E0 /* MII Address for enet1 */ +#define SSB_SPROM4_ETHPHY_ET1A_SHIFT 5 +#define SSB_SPROM4_ETHPHY_ET0M (1<<14) /* MDIO for enet0 */ +#define SSB_SPROM4_ETHPHY_ET1M (1<<15) /* MDIO for enet1 */ +#define SSB_SPROM4_CCODE 0x1052 /* Country Code (2 bytes) */ +#define SSB_SPROM4_ANT_A 0x105D /* A Antennas */ +#define SSB_SPROM4_ANT_BG 0x105C /* B/G Antennas */ +#define SSB_SPROM4_BFLLO 0x1044 /* Boardflags (low 16 bits) */ +#define SSB_SPROM4_AGAIN 0x105E /* Antenna Gain (in dBm Q5.2) */ +#define SSB_SPROM4_BFLHI 0x1046 /* Board Flags Hi */ +#define SSB_SPROM4_MAXP_A 0x1000 /* Max Power A */ +#define SSB_SPROM4_MAXP_A_HI 0x00FF /* Mask for Hi */ +#define SSB_SPROM4_MAXP_A_LO 0xFF00 /* Mask for Lo */ +#define SSB_SPROM4_MAXP_A_LO_SHIFT 16 /* Shift for Lo */ +#define SSB_SPROM4_PA1LOB0 0x1000 +#define SSB_SPROM4_PA1LOB1 0x1000 +#define SSB_SPROM4_PA1LOB2 0x1000 +#define SSB_SPROM4_PA1HIB0 0x1000 +#define SSB_SPROM4_PA1HIB1 0x1000 +#define SSB_SPROM4_PA1HIB2 0x1000 +#define SSB_SPROM4_OPO 0x1000 +#define SSB_SPROM4_OPO_VALUE 0x0000 +#define SSB_SPROM4_GPIOLDC 0x105A /* LED Powersave Duty Cycle */ +#define SSB_SPROM4_GPIOLDC_OFF 0x0000FF00 /* Off Count */ +#define SSB_SPROM4_GPIOLDC_OFF_SHIFT 8 +#define SSB_SPROM4_GPIOLDC_ON 0x00FF0000 /* On Count */ +#define SSB_SPROM4_GPIOLDC_ON_SHIFT 16 + /* Values for SSB_SPROM1_BINF_CCODE */ enum { -- cgit v1.2.3 From c272ef4403c271799a7f09a4ab7a236c86643843 Mon Sep 17 00:00:00 2001 From: Larry Finger Date: Fri, 9 Nov 2007 16:56:25 -0600 Subject: ssb: Convert to use of the new SPROM structure In disagreement with the SPROM specs, revision 3 devices appear to have moved the MAC address. Change ssb to handle the revision 4 SPROM, which is a different size. This change in size is handled by adding a new variable to the ssb_sprom struct and using it whenever possible. For those routines that do not have access to this structure, a 'u16 size' argument is added. The new PCI_ID for the BCM4328 is also added. Testing of the Revision 4 SPROM, which is used on the BCM4328, was done by Michael Gerdau . Signed-off-by: Larry Finger Signed-off-by: John W. Linville --- include/linux/ssb/ssb.h | 1 + include/linux/ssb/ssb_regs.h | 38 +++++++++++++++++++++++++++----------- 2 files changed, 28 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index cdd8a2fd4a69..745de2aac85f 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -308,6 +308,7 @@ struct ssb_bus { /* ID information about the Chip. */ u16 chip_id; u16 chip_rev; + u16 sprom_size; /* number of words in sprom */ u8 chip_package; /* List of devices (cores) on the backplane. */ diff --git a/include/linux/ssb/ssb_regs.h b/include/linux/ssb/ssb_regs.h index bcebcffd448b..96bba69b1271 100644 --- a/include/linux/ssb/ssb_regs.h +++ b/include/linux/ssb/ssb_regs.h @@ -147,6 +147,10 @@ #define SSB_IDLOW_SSBREV 0xF0000000 /* Sonics Backplane Revision code */ #define SSB_IDLOW_SSBREV_22 0x00000000 /* <= 2.2 */ #define SSB_IDLOW_SSBREV_23 0x10000000 /* 2.3 */ +#define SSB_IDLOW_SSBREV_24 0x40000000 /* ?? Found in BCM4328 */ +#define SSB_IDLOW_SSBREV_25 0x50000000 /* ?? Not Found yet */ +#define SSB_IDLOW_SSBREV_26 0x60000000 /* ?? Found in some BCM4311/2 */ +#define SSB_IDLOW_SSBREV_27 0x70000000 /* ?? Found in some BCM4311/2 */ #define SSB_IDHIGH 0x0FFC /* SB Identification High */ #define SSB_IDHIGH_RCLO 0x0000000F /* Revision Code (low part) */ #define SSB_IDHIGH_CC 0x00008FF0 /* Core Code */ @@ -162,6 +166,10 @@ */ #define SSB_SPROMSIZE_WORDS 64 #define SSB_SPROMSIZE_BYTES (SSB_SPROMSIZE_WORDS * sizeof(u16)) +#define SSB_SPROMSIZE_WORDS_R123 64 +#define SSB_SPROMSIZE_WORDS_R4 220 +#define SSB_SPROMSIZE_BYTES_R123 (SSB_SPROMSIZE_WORDS_R123 * sizeof(u16)) +#define SSB_SPROMSIZE_BYTES_R4 (SSB_SPROMSIZE_WORDS_R4 * sizeof(u16)) #define SSB_SPROM_BASE 0x1000 #define SSB_SPROM_REVISION 0x107E #define SSB_SPROM_REVISION_REV 0x00FF /* SPROM Revision number */ @@ -232,7 +240,10 @@ #define SSB_SPROM2_OPO_VALUE 0x00FF #define SSB_SPROM2_OPO_UNUSED 0xFF00 #define SSB_SPROM2_CCODE 0x107C /* Two char Country Code */ -/* SPROM Revision 3 (inherits from rev 2) */ +/* SPROM Revision 3 (inherits most data from rev 2) */ +#define SSB_SPROM3_IL0MAC 0x104A /* 6 bytes MAC address for 802.11b/g */ +#define SSB_SPROM3_ET0MAC 0x1050 /* 6 bytes MAC address for Ethernet ?? */ +#define SSB_SPROM3_ET1MAC 0x1050 /* 6 bytes MAC address for 802.11a ?? */ #define SSB_SPROM3_OFDMAPO 0x102C /* A-PHY OFDM Mid Power Offset (4 bytes, BigEndian) */ #define SSB_SPROM3_OFDMALPO 0x1030 /* A-PHY OFDM Low Power Offset (4 bytes, BigEndian) */ #define SSB_SPROM3_OFDMAHPO 0x1034 /* A-PHY OFDM High Power Offset (4 bytes, BigEndian) */ @@ -250,8 +261,10 @@ #define SSB_SPROM3_CCKPO_11M 0xF000 /* 11M Rate PO */ #define SSB_SPROM3_CCKPO_11M_SHIFT 12 #define SSB_SPROM3_OFDMGPO 0x107A /* G-PHY OFDM Power Offset (4 bytes, BigEndian) */ -/* SPROM Revision 4 */ +/* SPROM Revision 4 entries with ?? in comment are unknown */ #define SSB_SPROM4_IL0MAC 0x104C /* 6 byte MAC address for b/g */ +#define SSB_SPROM4_ET0MAC 0x1018 /* 6 bytes MAC address for Ethernet ?? */ +#define SSB_SPROM4_ET1MAC 0x1018 /* 6 bytes MAC address for 802.11a ?? */ #define SSB_SPROM4_ETHPHY 0x105A /* Ethernet PHY settings */ #define SSB_SPROM4_ETHPHY_ET0A 0x001F /* MII Address for enet0 */ #define SSB_SPROM4_ETHPHY_ET1A 0x03E0 /* MII Address for enet1 */ @@ -263,19 +276,22 @@ #define SSB_SPROM4_ANT_BG 0x105C /* B/G Antennas */ #define SSB_SPROM4_BFLLO 0x1044 /* Boardflags (low 16 bits) */ #define SSB_SPROM4_AGAIN 0x105E /* Antenna Gain (in dBm Q5.2) */ +#define SSB_SPROM4_AGAIN_0 0x00FF /* Antenna 0 */ +#define SSB_SPROM4_AGAIN_1 0xFF00 /* Antenna 1 */ +#define SSB_SPROM4_AGAIN_1_SHIFT 8 #define SSB_SPROM4_BFLHI 0x1046 /* Board Flags Hi */ -#define SSB_SPROM4_MAXP_A 0x1000 /* Max Power A */ +#define SSB_SPROM4_MAXP_A 0x1000 /* Max Power A ?? */ #define SSB_SPROM4_MAXP_A_HI 0x00FF /* Mask for Hi */ #define SSB_SPROM4_MAXP_A_LO 0xFF00 /* Mask for Lo */ #define SSB_SPROM4_MAXP_A_LO_SHIFT 16 /* Shift for Lo */ -#define SSB_SPROM4_PA1LOB0 0x1000 -#define SSB_SPROM4_PA1LOB1 0x1000 -#define SSB_SPROM4_PA1LOB2 0x1000 -#define SSB_SPROM4_PA1HIB0 0x1000 -#define SSB_SPROM4_PA1HIB1 0x1000 -#define SSB_SPROM4_PA1HIB2 0x1000 -#define SSB_SPROM4_OPO 0x1000 -#define SSB_SPROM4_OPO_VALUE 0x0000 +#define SSB_SPROM4_PA1LOB0 0x1000 /* ?? */ +#define SSB_SPROM4_PA1LOB1 0x1000 /* ?? */ +#define SSB_SPROM4_PA1LOB2 0x1000 /* ?? */ +#define SSB_SPROM4_PA1HIB0 0x1000 /* ?? */ +#define SSB_SPROM4_PA1HIB1 0x1000 /* ?? */ +#define SSB_SPROM4_PA1HIB2 0x1000 /* ?? */ +#define SSB_SPROM4_OPO 0x1000 /* ?? */ +#define SSB_SPROM4_OPO_VALUE 0x0000 /* ?? */ #define SSB_SPROM4_GPIOLDC 0x105A /* LED Powersave Duty Cycle */ #define SSB_SPROM4_GPIOLDC_OFF 0x0000FF00 /* Off Count */ #define SSB_SPROM4_GPIOLDC_OFF_SHIFT 8 -- cgit v1.2.3 From d3c319f9c8d9ee2c042c60b8a1bbd909dcc42782 Mon Sep 17 00:00:00 2001 From: Larry Finger Date: Fri, 9 Nov 2007 16:58:20 -0600 Subject: ssb: Remove the old, now unused, data structures The old, now unused, data structures and SPROM extraction routines are removed. Signed-off-by: Larry Finger Signed-off-by: John W. Linville --- include/linux/ssb/ssb.h | 74 -------------------------------------------- include/linux/ssb/ssb_regs.h | 49 ++++++++++++++++------------- 2 files changed, 28 insertions(+), 95 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 745de2aac85f..a21ab29ff363 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -15,72 +15,8 @@ struct pcmcia_device; struct ssb_bus; struct ssb_driver; - -struct ssb_sprom_r1 { - u16 pci_spid; /* Subsystem Product ID for PCI */ - u16 pci_svid; /* Subsystem Vendor ID for PCI */ - u16 pci_pid; /* Product ID for PCI */ - u8 il0mac[6]; /* MAC address for 802.11b/g */ - u8 et0mac[6]; /* MAC address for Ethernet */ - u8 et1mac[6]; /* MAC address for 802.11a */ - u8 et0phyaddr:5; /* MII address for enet0 */ - u8 et1phyaddr:5; /* MII address for enet1 */ - u8 et0mdcport:1; /* MDIO for enet0 */ - u8 et1mdcport:1; /* MDIO for enet1 */ - u8 board_rev; /* Board revision */ - u8 country_code:4; /* Country Code */ - u8 antenna_a:2; /* Antenna 0/1 available for A-PHY */ - u8 antenna_bg:2; /* Antenna 0/1 available for B-PHY and G-PHY */ - u16 pa0b0; - u16 pa0b1; - u16 pa0b2; - u16 pa1b0; - u16 pa1b1; - u16 pa1b2; - u8 gpio0; /* GPIO pin 0 */ - u8 gpio1; /* GPIO pin 1 */ - u8 gpio2; /* GPIO pin 2 */ - u8 gpio3; /* GPIO pin 3 */ - u16 maxpwr_a; /* A-PHY Power Amplifier Max Power (in dBm Q5.2) */ - u16 maxpwr_bg; /* B/G-PHY Power Amplifier Max Power (in dBm Q5.2) */ - u8 itssi_a; /* Idle TSSI Target for A-PHY */ - u8 itssi_bg; /* Idle TSSI Target for B/G-PHY */ - u16 boardflags_lo; /* Boardflags (low 16 bits) */ - u8 antenna_gain_a; /* A-PHY Antenna gain (in dBm Q5.2) */ - u8 antenna_gain_bg; /* B/G-PHY Antenna gain (in dBm Q5.2) */ - u8 oem[8]; /* OEM string (rev 1 only) */ -}; - -struct ssb_sprom_r2 { - u16 boardflags_hi; /* Boardflags (high 16 bits) */ - u8 maxpwr_a_lo; /* A-PHY Max Power Low */ - u8 maxpwr_a_hi; /* A-PHY Max Power High */ - u16 pa1lob0; /* A-PHY PA Low Settings */ - u16 pa1lob1; /* A-PHY PA Low Settings */ - u16 pa1lob2; /* A-PHY PA Low Settings */ - u16 pa1hib0; /* A-PHY PA High Settings */ - u16 pa1hib1; /* A-PHY PA High Settings */ - u16 pa1hib2; /* A-PHY PA High Settings */ - u8 ofdm_pwr_off; /* OFDM Power Offset from CCK Level */ - u8 country_str[2]; /* Two char Country Code */ -}; - -struct ssb_sprom_r3 { - u32 ofdmapo; /* A-PHY OFDM Mid Power Offset */ - u32 ofdmalpo; /* A-PHY OFDM Low Power Offset */ - u32 ofdmahpo; /* A-PHY OFDM High Power Offset */ - u8 gpioldc_on_cnt; /* GPIO LED Powersave Duty Cycle ON count */ - u8 gpioldc_off_cnt; /* GPIO LED Powersave Duty Cycle OFF count */ - u8 cckpo_1M:4; /* CCK Power Offset for Rate 1M */ - u8 cckpo_2M:4; /* CCK Power Offset for Rate 2M */ - u8 cckpo_55M:4; /* CCK Power Offset for Rate 5.5M */ - u8 cckpo_11M:4; /* CCK Power Offset for Rate 11M */ - u32 ofdmgpo; /* G-PHY OFDM Power Offset */ -}; - struct ssb_sprom { u8 revision; - u8 temp_fill[2 * sizeof(struct ssb_sprom_r1)]; u8 il0mac[6]; /* MAC address for 802.11b/g */ u8 et0mac[6]; /* MAC address for Ethernet */ u8 et1mac[6]; /* MAC address for 802.11a */ @@ -106,16 +42,6 @@ struct ssb_sprom { u8 antenna_gain_bg; /* B/G-PHY Antenna gain (in dBm Q5.2) */ /* TODO - add any parameters needed from rev 2, 3, or 4 SPROMs */ - /* The valid r# fields are selected by the "revision". - * Revision 3 and lower inherit from lower revisions. - */ - union { - struct { - struct ssb_sprom_r1 r1; - struct ssb_sprom_r2 r2; - struct ssb_sprom_r3 r3; - }; - }; }; /* Information about the PCB the circuitry is soldered on. */ diff --git a/include/linux/ssb/ssb_regs.h b/include/linux/ssb/ssb_regs.h index 96bba69b1271..30222e89ad16 100644 --- a/include/linux/ssb/ssb_regs.h +++ b/include/linux/ssb/ssb_regs.h @@ -175,6 +175,7 @@ #define SSB_SPROM_REVISION_REV 0x00FF /* SPROM Revision number */ #define SSB_SPROM_REVISION_CRC 0xFF00 /* SPROM CRC8 value */ #define SSB_SPROM_REVISION_CRC_SHIFT 8 + /* SPROM Revision 1 */ #define SSB_SPROM1_SPID 0x1004 /* Subsystem Product ID for PCI */ #define SSB_SPROM1_SVID 0x1006 /* Subsystem Vendor ID for PCI */ @@ -223,7 +224,7 @@ #define SSB_SPROM1_AGAIN_A 0x00FF /* A-PHY */ #define SSB_SPROM1_AGAIN_BG 0xFF00 /* B-PHY and G-PHY */ #define SSB_SPROM1_AGAIN_BG_SHIFT 8 -#define SSB_SPROM1_OEM 0x1076 /* 8 bytes OEM string (rev 1 only) */ + /* SPROM Revision 2 (inherits from rev 1) */ #define SSB_SPROM2_BFLHI 0x1038 /* Boardflags (high 16 bits) */ #define SSB_SPROM2_MAXP_A 0x103A /* A-PHY Max Power */ @@ -240,6 +241,7 @@ #define SSB_SPROM2_OPO_VALUE 0x00FF #define SSB_SPROM2_OPO_UNUSED 0xFF00 #define SSB_SPROM2_CCODE 0x107C /* Two char Country Code */ + /* SPROM Revision 3 (inherits most data from rev 2) */ #define SSB_SPROM3_IL0MAC 0x104A /* 6 bytes MAC address for 802.11b/g */ #define SSB_SPROM3_ET0MAC 0x1050 /* 6 bytes MAC address for Ethernet ?? */ @@ -261,11 +263,12 @@ #define SSB_SPROM3_CCKPO_11M 0xF000 /* 11M Rate PO */ #define SSB_SPROM3_CCKPO_11M_SHIFT 12 #define SSB_SPROM3_OFDMGPO 0x107A /* G-PHY OFDM Power Offset (4 bytes, BigEndian) */ + /* SPROM Revision 4 entries with ?? in comment are unknown */ -#define SSB_SPROM4_IL0MAC 0x104C /* 6 byte MAC address for b/g */ +#define SSB_SPROM4_IL0MAC 0x104C /* 6 byte MAC address for a/b/g/n */ #define SSB_SPROM4_ET0MAC 0x1018 /* 6 bytes MAC address for Ethernet ?? */ #define SSB_SPROM4_ET1MAC 0x1018 /* 6 bytes MAC address for 802.11a ?? */ -#define SSB_SPROM4_ETHPHY 0x105A /* Ethernet PHY settings */ +#define SSB_SPROM4_ETHPHY 0x105A /* Ethernet PHY settings ?? */ #define SSB_SPROM4_ETHPHY_ET0A 0x001F /* MII Address for enet0 */ #define SSB_SPROM4_ETHPHY_ET1A 0x03E0 /* MII Address for enet1 */ #define SSB_SPROM4_ETHPHY_ET1A_SHIFT 5 @@ -280,24 +283,28 @@ #define SSB_SPROM4_AGAIN_1 0xFF00 /* Antenna 1 */ #define SSB_SPROM4_AGAIN_1_SHIFT 8 #define SSB_SPROM4_BFLHI 0x1046 /* Board Flags Hi */ -#define SSB_SPROM4_MAXP_A 0x1000 /* Max Power A ?? */ -#define SSB_SPROM4_MAXP_A_HI 0x00FF /* Mask for Hi */ -#define SSB_SPROM4_MAXP_A_LO 0xFF00 /* Mask for Lo */ -#define SSB_SPROM4_MAXP_A_LO_SHIFT 16 /* Shift for Lo */ -#define SSB_SPROM4_PA1LOB0 0x1000 /* ?? */ -#define SSB_SPROM4_PA1LOB1 0x1000 /* ?? */ -#define SSB_SPROM4_PA1LOB2 0x1000 /* ?? */ -#define SSB_SPROM4_PA1HIB0 0x1000 /* ?? */ -#define SSB_SPROM4_PA1HIB1 0x1000 /* ?? */ -#define SSB_SPROM4_PA1HIB2 0x1000 /* ?? */ -#define SSB_SPROM4_OPO 0x1000 /* ?? */ -#define SSB_SPROM4_OPO_VALUE 0x0000 /* ?? */ -#define SSB_SPROM4_GPIOLDC 0x105A /* LED Powersave Duty Cycle */ -#define SSB_SPROM4_GPIOLDC_OFF 0x0000FF00 /* Off Count */ -#define SSB_SPROM4_GPIOLDC_OFF_SHIFT 8 -#define SSB_SPROM4_GPIOLDC_ON 0x00FF0000 /* On Count */ -#define SSB_SPROM4_GPIOLDC_ON_SHIFT 16 - +#define SSB_SPROM4_MAXP_BG 0x1080 /* Max Power BG in path 1 */ +#define SSB_SPROM4_MAXP_BG_MASK 0x00FF /* Mask for Max Power BG */ +#define SSB_SPROM4_ITSSI_BG 0xFF00 /* Mask for path 1 itssi_bg */ +#define SSB_SPROM4_ITSSI_BG_SHIFT 8 +#define SSB_SPROM4_MAXP_A 0x108A /* Max Power A in path 1 */ +#define SSB_SPROM4_MAXP_A_MASK 0x00FF /* Mask for Max Power A */ +#define SSB_SPROM4_ITSSI_A 0xFF00 /* Mask for path 1 itssi_a */ +#define SSB_SPROM4_ITSSI_A_SHIFT 8 +#define SSB_SPROM4_GPIOA 0x1056 /* Gen. Purpose IO # 0 and 1 */ +#define SSB_SPROM4_GPIOA_P0 0x00FF /* Pin 0 */ +#define SSB_SPROM4_GPIOA_P1 0xFF00 /* Pin 1 */ +#define SSB_SPROM4_GPIOA_P1_SHIFT 8 +#define SSB_SPROM4_GPIOB 0x1058 /* Gen. Purpose IO # 2 and 3 */ +#define SSB_SPROM4_GPIOB_P2 0x00FF /* Pin 2 */ +#define SSB_SPROM4_GPIOB_P3 0xFF00 /* Pin 3 */ +#define SSB_SPROM4_GPIOB_P3_SHIFT 8 +#define SSB_SPROM4_PA0B0 0x1082 /* The paXbY locations are */ +#define SSB_SPROM4_PA0B1 0x1084 /* only guesses */ +#define SSB_SPROM4_PA0B2 0x1086 +#define SSB_SPROM4_PA1B0 0x108E +#define SSB_SPROM4_PA1B1 0x1090 +#define SSB_SPROM4_PA1B2 0x1092 /* Values for SSB_SPROM1_BINF_CCODE */ enum { -- cgit v1.2.3 From a3edb08311fc559652ffc959e93eb5be9294443f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 22 Dec 2007 17:52:42 +0000 Subject: annotate tun Signed-off-by: Al Viro Signed-off-by: Jeff Garzik --- include/linux/if_tun.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 33e489d5bb33..72f1c5f47be3 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -21,6 +21,8 @@ /* Uncomment to enable debugging */ /* #define TUN_DEBUG 1 */ +#include + #ifdef __KERNEL__ #ifdef TUN_DEBUG @@ -88,7 +90,7 @@ struct tun_struct { struct tun_pi { unsigned short flags; - unsigned short proto; + __be16 proto; }; #define TUN_PKT_STRIP 0x0001 -- cgit v1.2.3 From 904584018e9ba30a3e562d86ee7dfb6239105664 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 22 Dec 2007 17:52:52 +0000 Subject: annotate the rest of drivers/net/wan Signed-off-by: Al Viro Signed-off-by: Jeff Garzik --- include/linux/if_frad.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_frad.h b/include/linux/if_frad.h index f272a80caa3e..5c34240de746 100644 --- a/include/linux/if_frad.h +++ b/include/linux/if_frad.h @@ -137,7 +137,7 @@ struct frhdr unsigned char NLPID; unsigned char OUI[3]; - unsigned short PID; + __be16 PID; #define IP_NLPID pad } __attribute__((packed)); -- cgit v1.2.3 From b7c6ba6eb1234e35a74fb8ba8123232a7b1ba9e4 Mon Sep 17 00:00:00 2001 From: "Denis V. Lunev" Date: Mon, 28 Jan 2008 14:41:19 -0800 Subject: [NETNS]: Consolidate kernel netlink socket destruction. Create a specific helper for netlink kernel socket disposal. This just let the code look better and provides a ground for proper disposal inside a namespace. Signed-off-by: Denis V. Lunev Tested-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 2aee0f510876..bd13b6f4a98e 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -178,6 +178,7 @@ extern struct sock *netlink_kernel_create(struct net *net, void (*input)(struct sk_buff *skb), struct mutex *cb_mutex, struct module *module); +extern void netlink_kernel_release(struct sock *sk); extern int netlink_change_ngroups(struct sock *sk, unsigned int groups); extern void netlink_clear_multicast_users(struct sock *sk, unsigned int group); extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err); -- cgit v1.2.3 From 476bcea67f9a1ca6f2c0028e75fb2129272c8398 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 21 Jan 2008 00:18:26 -0800 Subject: [VLAN]: Remove unnecessary structure declarations - struct packet_type is not used - struct vlan_group is declared later in the file before the first use - struct net_device is not needed since netdevice.h is included - struct vlan_collection does not exist - struct vlan_dev_info is declared later in the file before the first use Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 4562105fdb2b..a26805198b14 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -16,11 +16,6 @@ #ifdef __KERNEL__ /* externally defined structs */ -struct vlan_group; -struct net_device; -struct packet_type; -struct vlan_collection; -struct vlan_dev_info; struct hlist_node; #include -- cgit v1.2.3 From 740c15d0dd281c0cbe1a9ab1abc4f332e0df29bc Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 21 Jan 2008 00:18:53 -0800 Subject: [VLAN]: Clean up vlan_hdr/vlan_ethhdr structs Fix 3 space indentation and some overly long lines by moving the comments to a kdoc structure description. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 33 +++++++++++++++++++++++---------- 1 file changed, 23 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index a26805198b14..a1b0066ec0d9 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -34,12 +34,30 @@ struct hlist_node; #define VLAN_ETH_DATA_LEN 1500 /* Max. octets in payload */ #define VLAN_ETH_FRAME_LEN 1518 /* Max. octets in frame sans FCS */ +/* + * struct vlan_hdr - vlan header + * @h_vlan_TCI: priority and VLAN ID + * @h_vlan_encapsulated_proto: packet type ID or len + */ +struct vlan_hdr { + __be16 h_vlan_TCI; + __be16 h_vlan_encapsulated_proto; +}; + +/** + * struct vlan_ethhdr - vlan ethernet header (ethhdr + vlan_hdr) + * @h_dest: destination ethernet address + * @h_source: source ethernet address + * @h_vlan_proto: ethernet protocol (always 0x8100) + * @h_vlan_TCI: priority and VLAN ID + * @h_vlan_encapsulated_proto: packet type ID or len + */ struct vlan_ethhdr { - unsigned char h_dest[ETH_ALEN]; /* destination eth addr */ - unsigned char h_source[ETH_ALEN]; /* source ether addr */ - __be16 h_vlan_proto; /* Should always be 0x8100 */ - __be16 h_vlan_TCI; /* Encapsulates priority and VLAN ID */ - __be16 h_vlan_encapsulated_proto; /* packet type ID field (or len) */ + unsigned char h_dest[ETH_ALEN]; + unsigned char h_source[ETH_ALEN]; + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + __be16 h_vlan_encapsulated_proto; }; #include @@ -49,11 +67,6 @@ static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb) return (struct vlan_ethhdr *)skb_mac_header(skb); } -struct vlan_hdr { - __be16 h_vlan_TCI; /* Encapsulates priority and VLAN ID */ - __be16 h_vlan_encapsulated_proto; /* packet type ID field (or len) */ -}; - #define VLAN_VID_MASK 0xfff /* found in socket.c */ -- cgit v1.2.3 From b7a4a83629c1ddde8c2e6a872618c66577cb20f0 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 21 Jan 2008 00:19:16 -0800 Subject: [VLAN]: Kill useless VLAN_NAME define The only user already includes __FUNCTION__ (vlan_proto_init) in the output, which is enough to identify what the message is about. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index a1b0066ec0d9..0325d6b17e07 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -72,8 +72,6 @@ static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb) /* found in socket.c */ extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *)); -#define VLAN_NAME "vlan" - /* if this changes, algorithm will have to be reworked because this * depends on completely exhausting the VLAN identifier space. Thus * it gives constant time look-up, but in many cases it wastes memory. -- cgit v1.2.3 From 7bd38d778e3f2250e96fc277040879d66c30ecb4 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 21 Jan 2008 00:19:31 -0800 Subject: [VLAN]: Use dev->stats Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 0325d6b17e07..07db4169463e 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -140,18 +140,11 @@ struct vlan_dev_info { struct proc_dir_entry *dent; /* Holds the proc data */ unsigned long cnt_inc_headroom_on_tx; /* How many times did we have to grow the skb on TX. */ unsigned long cnt_encap_on_xmit; /* How many times did we have to encapsulate the skb on TX. */ - struct net_device_stats dev_stats; /* Device stats (rx-bytes, tx-pkts, etc...) */ }; #define VLAN_DEV_INFO(x) ((struct vlan_dev_info *)(x->priv)) /* inline functions */ - -static inline struct net_device_stats *vlan_dev_get_stats(struct net_device *dev) -{ - return &(VLAN_DEV_INFO(dev)->dev_stats); -} - static inline __u32 vlan_get_ingress_priority(struct net_device *dev, unsigned short vlan_tag) { @@ -196,7 +189,7 @@ static inline int __vlan_hwaccel_rx(struct sk_buff *skb, skb->dev->last_rx = jiffies; - stats = vlan_dev_get_stats(skb->dev); + stats = &skb->dev->stats; stats->rx_packets++; stats->rx_bytes += skb->len; -- cgit v1.2.3 From a5250a36954c6658e28cc2e7e07e314e0c79e8bb Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 21 Jan 2008 00:24:13 -0800 Subject: [ETHER]: Bring back MAC_FMT The print_mac function is not very suitable for debugging printks in performance critical paths since without ifdefs it will always get called. MAC_FMT can be used with pr_debug without any overhead when debugging is disabled. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_ether.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index 7a1e011b8a2c..e157c1399b61 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -130,6 +130,7 @@ extern ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len); * Display a 6 byte device address (MAC) in a readable format. */ extern char *print_mac(char *buf, const unsigned char *addr); +#define MAC_FMT "%02x:%02x:%02x:%02x:%02x:%02x" #define MAC_BUF_SIZE 18 #define DECLARE_MAC_BUF(var) char var[MAC_BUF_SIZE] __maybe_unused -- cgit v1.2.3 From af30151709bcace1ca844d4bb8b7e2e392ff81eb Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 21 Jan 2008 00:25:50 -0800 Subject: [VLAN]: Simplify vlan unregistration Keep track of the number of VLAN devices in a vlan group. This allows to have the caller sense when the group is going to be destroyed and stop using it, which in turn allows to remove the wrapper around unregister_vlan_dev for the NETDEV_UNREGISTER notifier and avoid iterating over all possible VLAN ids whenever a device in unregistered. Also fix what looks like a use-after-free (but is actually safe since we're holding the RTNL), the real_dev reference should not be dropped while we still use it. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 07db4169463e..129fa876dbe4 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -82,6 +82,7 @@ extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *)); struct vlan_group { int real_dev_ifindex; /* The ifindex of the ethernet(like) device the vlan is attached to. */ + unsigned int nr_vlans; struct hlist_node hlist; /* linked list */ struct net_device **vlan_devices_arrays[VLAN_GROUP_ARRAY_SPLIT_PARTS]; struct rcu_head rcu; -- cgit v1.2.3 From 9dfebcc6479c55c001e4bb5fe7cc16b6799c43a7 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 21 Jan 2008 00:26:07 -0800 Subject: [VLAN]: Turn VLAN_DEV_INFO into inline function Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 129fa876dbe4..82c23522a46d 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -143,13 +143,16 @@ struct vlan_dev_info { unsigned long cnt_encap_on_xmit; /* How many times did we have to encapsulate the skb on TX. */ }; -#define VLAN_DEV_INFO(x) ((struct vlan_dev_info *)(x->priv)) +static inline struct vlan_dev_info *vlan_dev_info(const struct net_device *dev) +{ + return netdev_priv(dev); +} /* inline functions */ static inline __u32 vlan_get_ingress_priority(struct net_device *dev, unsigned short vlan_tag) { - struct vlan_dev_info *vip = VLAN_DEV_INFO(dev); + struct vlan_dev_info *vip = vlan_dev_info(dev); return vip->ingress_priority_map[(vlan_tag >> 13) & 0x7]; } -- cgit v1.2.3 From 57d3ae847d4403c5e4a35ae5f38665fff1a94c02 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 21 Jan 2008 00:26:25 -0800 Subject: [VLAN]: Turn __constant_htons into htons where possible Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 82c23522a46d..34f40efc7607 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -271,12 +271,12 @@ static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb, unsigned short memmove(skb->data, skb->data + VLAN_HLEN, 2 * VLAN_ETH_ALEN); /* first, the ethernet type */ - veth->h_vlan_proto = __constant_htons(ETH_P_8021Q); + veth->h_vlan_proto = htons(ETH_P_8021Q); /* now, the tag */ veth->h_vlan_TCI = htons(tag); - skb->protocol = __constant_htons(ETH_P_8021Q); + skb->protocol = htons(ETH_P_8021Q); skb->mac_header -= VLAN_HLEN; skb->network_header -= VLAN_HLEN; @@ -331,7 +331,7 @@ static inline int __vlan_get_tag(struct sk_buff *skb, unsigned short *tag) { struct vlan_ethhdr *veth = (struct vlan_ethhdr *)skb->data; - if (veth->h_vlan_proto != __constant_htons(ETH_P_8021Q)) { + if (veth->h_vlan_proto != htons(ETH_P_8021Q)) { return -EINVAL; } -- cgit v1.2.3 From 1e637c74b0f84eaca02b914c0b8c6f67276e9697 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Mon, 21 Jan 2008 03:18:08 -0800 Subject: [IPV4]: Enable use of 240/4 address space. This short patch modifies the IPv4 networking to enable use of the 240.0.0.0/4 (aka "class-E") address space as propsed in the internet draft draft-fuller-240space-00.txt. Signed-off-by: Jan Engelhardt Acked-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/in.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/in.h b/include/linux/in.h index 27d8a5ae9f75..70c6df882694 100644 --- a/include/linux/in.h +++ b/include/linux/in.h @@ -262,9 +262,10 @@ static inline bool ipv4_is_local_multicast(__be32 addr) return (addr & htonl(0xffffff00)) == htonl(0xe0000000); } -static inline bool ipv4_is_badclass(__be32 addr) +static inline bool ipv4_is_lbcast(__be32 addr) { - return (addr & htonl(0xf0000000)) == htonl(0xf0000000); + /* limited broadcast */ + return addr == INADDR_BROADCAST; } static inline bool ipv4_is_zeronet(__be32 addr) -- cgit v1.2.3 From e861b98d5e1be769ca6483b6df97149b956ea834 Mon Sep 17 00:00:00 2001 From: Michael Buesch Date: Sat, 22 Dec 2007 21:51:30 +0100 Subject: ssb: Fix extraction of values from SPROM This fixes extraction of some values from the SPROM. It mainly fixes extraction of antenna related values, which is needed for another b43 fix sent later. Signed-off-by: Michael Buesch Signed-off-by: John W. Linville --- include/linux/ssb/ssb.h | 19 +++++++++++++++++-- include/linux/ssb/ssb_regs.h | 38 ++++++++++++++++++++++++-------------- 2 files changed, 41 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index a21ab29ff363..0eaa98424f0a 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -22,7 +22,12 @@ struct ssb_sprom { u8 et1mac[6]; /* MAC address for 802.11a */ u8 et0phyaddr; /* MII address for enet0 */ u8 et1phyaddr; /* MII address for enet1 */ + u8 et0mdcport; /* MDIO for enet0 */ + u8 et1mdcport; /* MDIO for enet1 */ + u8 board_rev; /* Board revision number from SPROM. */ u8 country_code; /* Country Code */ + u8 ant_available_a; /* A-PHY antenna available bits (up to 4) */ + u8 ant_available_bg; /* B/G-PHY antenna available bits (up to 4) */ u16 pa0b0; u16 pa0b1; u16 pa0b2; @@ -38,8 +43,18 @@ struct ssb_sprom { u8 itssi_a; /* Idle TSSI Target for A-PHY */ u8 itssi_bg; /* Idle TSSI Target for B/G-PHY */ u16 boardflags_lo; /* Boardflags (low 16 bits) */ - u8 antenna_gain_a; /* A-PHY Antenna gain (in dBm Q5.2) */ - u8 antenna_gain_bg; /* B/G-PHY Antenna gain (in dBm Q5.2) */ + + /* Antenna gain values for up to 4 antennas + * on each band. Values in dBm/4 (Q5.2). Negative gain means the + * loss in the connectors is bigger than the gain. */ + struct { + struct { + s8 a0, a1, a2, a3; + } ghz24; /* 2.4GHz band */ + struct { + s8 a0, a1, a2, a3; + } ghz5; /* 5GHz band */ + } antenna_gain; /* TODO - add any parameters needed from rev 2, 3, or 4 SPROMs */ }; diff --git a/include/linux/ssb/ssb_regs.h b/include/linux/ssb/ssb_regs.h index 30222e89ad16..ebad0bac9801 100644 --- a/include/linux/ssb/ssb_regs.h +++ b/include/linux/ssb/ssb_regs.h @@ -193,10 +193,10 @@ #define SSB_SPROM1_BINF_BREV 0x00FF /* Board Revision */ #define SSB_SPROM1_BINF_CCODE 0x0F00 /* Country Code */ #define SSB_SPROM1_BINF_CCODE_SHIFT 8 -#define SSB_SPROM1_BINF_ANTA 0x3000 /* Available A-PHY antennas */ -#define SSB_SPROM1_BINF_ANTA_SHIFT 12 -#define SSB_SPROM1_BINF_ANTBG 0xC000 /* Available B-PHY antennas */ -#define SSB_SPROM1_BINF_ANTBG_SHIFT 14 +#define SSB_SPROM1_BINF_ANTBG 0x3000 /* Available B-PHY and G-PHY antennas */ +#define SSB_SPROM1_BINF_ANTBG_SHIFT 12 +#define SSB_SPROM1_BINF_ANTA 0xC000 /* Available A-PHY antennas */ +#define SSB_SPROM1_BINF_ANTA_SHIFT 14 #define SSB_SPROM1_PA0B0 0x105E #define SSB_SPROM1_PA0B1 0x1060 #define SSB_SPROM1_PA0B2 0x1062 @@ -221,9 +221,10 @@ #define SSB_SPROM1_ITSSI_A_SHIFT 8 #define SSB_SPROM1_BFLLO 0x1072 /* Boardflags (low 16 bits) */ #define SSB_SPROM1_AGAIN 0x1074 /* Antenna Gain (in dBm Q5.2) */ -#define SSB_SPROM1_AGAIN_A 0x00FF /* A-PHY */ -#define SSB_SPROM1_AGAIN_BG 0xFF00 /* B-PHY and G-PHY */ -#define SSB_SPROM1_AGAIN_BG_SHIFT 8 +#define SSB_SPROM1_AGAIN_BG 0x00FF /* B-PHY and G-PHY */ +#define SSB_SPROM1_AGAIN_BG_SHIFT 0 +#define SSB_SPROM1_AGAIN_A 0xFF00 /* A-PHY */ +#define SSB_SPROM1_AGAIN_A_SHIFT 8 /* SPROM Revision 2 (inherits from rev 1) */ #define SSB_SPROM2_BFLHI 0x1038 /* Boardflags (high 16 bits) */ @@ -264,7 +265,7 @@ #define SSB_SPROM3_CCKPO_11M_SHIFT 12 #define SSB_SPROM3_OFDMGPO 0x107A /* G-PHY OFDM Power Offset (4 bytes, BigEndian) */ -/* SPROM Revision 4 entries with ?? in comment are unknown */ +/* SPROM Revision 4 */ #define SSB_SPROM4_IL0MAC 0x104C /* 6 byte MAC address for a/b/g/n */ #define SSB_SPROM4_ET0MAC 0x1018 /* 6 bytes MAC address for Ethernet ?? */ #define SSB_SPROM4_ET1MAC 0x1018 /* 6 bytes MAC address for 802.11a ?? */ @@ -275,13 +276,22 @@ #define SSB_SPROM4_ETHPHY_ET0M (1<<14) /* MDIO for enet0 */ #define SSB_SPROM4_ETHPHY_ET1M (1<<15) /* MDIO for enet1 */ #define SSB_SPROM4_CCODE 0x1052 /* Country Code (2 bytes) */ -#define SSB_SPROM4_ANT_A 0x105D /* A Antennas */ -#define SSB_SPROM4_ANT_BG 0x105C /* B/G Antennas */ +#define SSB_SPROM4_ANTAVAIL 0x105D /* Antenna available bitfields */ +#define SSB_SPROM4_ANTAVAIL_A 0x00FF /* A-PHY bitfield */ +#define SSB_SPROM4_ANTAVAIL_A_SHIFT 0 +#define SSB_SPROM4_ANTAVAIL_BG 0xFF00 /* B-PHY and G-PHY bitfield */ +#define SSB_SPROM4_ANTAVAIL_BG_SHIFT 8 #define SSB_SPROM4_BFLLO 0x1044 /* Boardflags (low 16 bits) */ -#define SSB_SPROM4_AGAIN 0x105E /* Antenna Gain (in dBm Q5.2) */ -#define SSB_SPROM4_AGAIN_0 0x00FF /* Antenna 0 */ -#define SSB_SPROM4_AGAIN_1 0xFF00 /* Antenna 1 */ -#define SSB_SPROM4_AGAIN_1_SHIFT 8 +#define SSB_SPROM4_AGAIN01 0x105E /* Antenna Gain (in dBm Q5.2) */ +#define SSB_SPROM4_AGAIN0 0x00FF /* Antenna 0 */ +#define SSB_SPROM4_AGAIN0_SHIFT 0 +#define SSB_SPROM4_AGAIN1 0xFF00 /* Antenna 1 */ +#define SSB_SPROM4_AGAIN1_SHIFT 8 +#define SSB_SPROM4_AGAIN23 0x1060 +#define SSB_SPROM4_AGAIN2 0x00FF /* Antenna 2 */ +#define SSB_SPROM4_AGAIN2_SHIFT 0 +#define SSB_SPROM4_AGAIN3 0xFF00 /* Antenna 3 */ +#define SSB_SPROM4_AGAIN3_SHIFT 8 #define SSB_SPROM4_BFLHI 0x1046 /* Board Flags Hi */ #define SSB_SPROM4_MAXP_BG 0x1080 /* Max Power BG in path 1 */ #define SSB_SPROM4_MAXP_BG_MASK 0x00FF /* Mask for Max Power BG */ -- cgit v1.2.3 From 993e1c780b323736a2cdc24564f35e80ce8d3337 Mon Sep 17 00:00:00 2001 From: Michael Buesch Date: Sat, 22 Dec 2007 22:01:36 +0100 Subject: ssb: Fix PCMCIA lowlevel register access This fixes lowlevel register access for PCMCIA based devices. The patch also adds a temporary workaround for the device mac address. It simply adds generation of a random address. The real SPROM extraction will follow in another patch. The temporary workaround will be removed then, but for now it's OK. Signed-off-by: Michael Buesch Signed-off-by: John W. Linville --- include/linux/ssb/ssb.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 0eaa98424f0a..cacbae531945 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -231,7 +231,8 @@ struct ssb_bus { struct ssb_device *mapped_device; /* Currently mapped PCMCIA segment. (bustype == SSB_BUSTYPE_PCMCIA only) */ u8 mapped_pcmcia_seg; - /* Lock for core and segment switching. */ + /* Lock for core and segment switching. + * On PCMCIA-host busses this is used to protect the whole MMIO access. */ spinlock_t bar_lock; /* The bus this backplane is running on. */ -- cgit v1.2.3 From 961d57c883198831503c7be5c088a26101dfb16c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Miguel=20Bot=C3=B3n?= Date: Tue, 1 Jan 2008 01:16:46 +0100 Subject: ssb: add 'ssb_pcihost_set_power_state' function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds the 'ssb_pcihost_set_power_state' function. This function allows us to set the power state of a PCI device (for example b44 ethernet device). Signed-off-by: Miguel Botón Signed-off-by: John W. Linville --- include/linux/ssb/ssb.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index cacbae531945..1ab4688c678b 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -365,6 +365,13 @@ static inline void ssb_pcihost_unregister(struct pci_driver *driver) { pci_unregister_driver(driver); } + +static inline +void ssb_pcihost_set_power_state(struct ssb_device *sdev, pci_power_t state) +{ + if (sdev->bus->bustype == SSB_BUSTYPE_PCI) + pci_set_power_state(sdev->bus->host_pci, state); +} #endif /* CONFIG_SSB_PCIHOST */ -- cgit v1.2.3 From f653211197f3841f383fa9757ef8ce182c6cf627 Mon Sep 17 00:00:00 2001 From: Michael Wu Date: Sun, 14 Oct 2007 14:43:16 -0400 Subject: Add rtl8180 wireless driver This patch adds a mac80211 based wireless driver for the rtl8180 and rtl8185 PCI wireless cards. Also included are some rtl8187 changes required due to the relationship between that driver and this one. Michael Wu is primarily responsible for the initial driver and rtl8185 support. Andreas Merello provided the additional rtl8180 support. Thanks to Jukka Ruohonen for the donating a rtl8185 card! It was very helpful for the rtl8225z2 code. The Signed-off-by information below is collected from the individual patches submitted to wireless-2.6 before merging this driver upstream. Signed-off-by: Andrea Merello Signed-off-by: Johannes Berg Signed-off-by: Pavel Roskin Signed-off-by: Michael Wu Signed-off-by: John W. Linville --- include/linux/pci_ids.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 6b4a132bf861..c69531348363 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2082,6 +2082,9 @@ #define PCI_DEVICE_ID_ALTIMA_AC9100 0x03ea #define PCI_DEVICE_ID_ALTIMA_AC1003 0x03eb +#define PCI_VENDOR_ID_BELKIN 0x1799 +#define PCI_DEVICE_ID_BELKIN_F5D7010V7 0x701f + #define PCI_VENDOR_ID_LENOVO 0x17aa #define PCI_VENDOR_ID_ARECA 0x17d3 -- cgit v1.2.3 From af4b7450788426a113057ce2d85c25b4f4e440d1 Mon Sep 17 00:00:00 2001 From: Michael Buesch Date: Sun, 13 Jan 2008 21:08:24 +0100 Subject: ssb: Add boardflags_hi field to the sprom data structure Add boardflags-high. Signed-off-by: Michael Buesch Signed-off-by: John W. Linville --- include/linux/ssb/ssb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 1ab4688c678b..e18f5c23b930 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -43,6 +43,7 @@ struct ssb_sprom { u8 itssi_a; /* Idle TSSI Target for A-PHY */ u8 itssi_bg; /* Idle TSSI Target for B/G-PHY */ u16 boardflags_lo; /* Boardflags (low 16 bits) */ + u16 boardflags_hi; /* Boardflags (high 16 bits) */ /* Antenna gain values for up to 4 antennas * on each band. Values in dBm/4 (Q5.2). Negative gain means the -- cgit v1.2.3 From 7fee0ca23711ce1a6b13d3ab78915809a72a59ec Mon Sep 17 00:00:00 2001 From: "Denis V. Lunev" Date: Mon, 21 Jan 2008 17:32:38 -0800 Subject: [NETNS]: Add netns parameter to inetdev_by_index. Signed-off-by: Denis V. Lunev Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 45f373107530..e74a2ee8ee2a 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -133,7 +133,7 @@ extern struct net_device *ip_dev_find(__be32 addr); extern int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b); extern int devinet_ioctl(unsigned int cmd, void __user *); extern void devinet_init(void); -extern struct in_device *inetdev_by_index(int); +extern struct in_device *inetdev_by_index(struct net *, int); extern __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope); extern __be32 inet_confirm_addr(struct in_device *in_dev, __be32 dst, __be32 local, int scope); extern struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); -- cgit v1.2.3 From a8b47ea3c583645977a916ab3e2d323c7504aa7b Mon Sep 17 00:00:00 2001 From: Ron Rindjunsky Date: Mon, 21 Jan 2008 12:39:11 +0200 Subject: mac80211: fixing ieee80211_bar types This patch changes ieee80211_bar control and start_seq_num to match the proper bitwise attribute expected from ieee 802.11 frame Signed-off-by: Ron Rindjunsky Signed-off-by: Tomas Winkler Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 4d5a4c9dcba7..5de6d911cdf7 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -237,8 +237,8 @@ struct ieee80211_bar { __le16 duration; __u8 ra[6]; __u8 ta[6]; - __u16 control; - __u16 start_seq_num; + __le16 control; + __le16 start_seq_num; } __attribute__((packed)); /** -- cgit v1.2.3 From 1ab352768fc73838b062776ca5d1add3876a019f Mon Sep 17 00:00:00 2001 From: "Denis V. Lunev" Date: Tue, 22 Jan 2008 22:04:30 -0800 Subject: [NETNS]: Add namespace parameter to ip_dev_find. in_dev_find() need a namespace to pass it to fib_get_table(), so add an argument. Signed-off-by: Denis V. Lunev Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index e74a2ee8ee2a..8d9eaaebded7 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -129,7 +129,7 @@ struct in_ifaddr extern int register_inetaddr_notifier(struct notifier_block *nb); extern int unregister_inetaddr_notifier(struct notifier_block *nb); -extern struct net_device *ip_dev_find(__be32 addr); +extern struct net_device *ip_dev_find(struct net *net, __be32 addr); extern int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b); extern int devinet_ioctl(unsigned int cmd, void __user *); extern void devinet_init(void); -- cgit v1.2.3 From 5feb5e1aaa887f6427b8290bce48bfb6b7010fc6 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 23 Jan 2008 20:35:19 -0800 Subject: [NET_SCHED]: sch_api: introduce constant for rate table size Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/pkt_sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pkt_sched.h b/include/linux/pkt_sched.h index 919af93b7059..32761352e858 100644 --- a/include/linux/pkt_sched.h +++ b/include/linux/pkt_sched.h @@ -83,6 +83,8 @@ struct tc_ratespec __u32 rate; }; +#define TC_RTAB_SIZE 1024 + /* FIFO section */ struct tc_fifo_qopt -- cgit v1.2.3 From afc7cbca5bfd556c3e12d3acefbee5ab0cbd4670 Mon Sep 17 00:00:00 2001 From: Takashi Sato Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: ext4: Support large blocksize up to PAGESIZE This patch set supports large block size(>4k, <=64k) in ext4, just enlarging the block size limit. But it is NOT possible to have 64kB blocksize on ext4 without some changes to the directory handling code. The reason is that an empty 64kB directory block would have a rec_len == (__u16)2^16 == 0, and this would cause an error to be hit in the filesystem. The proposed solution is treat 64k rec_len with a an impossible value like rec_len = 0xffff to handle this. The Patch-set consists of the following 2 patches. [1/2] ext4: enlarge blocksize - Allow blocksize up to pagesize [2/2] ext4: fix rec_len overflow - prevent rec_len from overflow with 64KB blocksize Now on 64k page ppc64 box runs with this patch set we could create a 64k block size ext4dev, and able to handle empty directory block. Signed-off-by: Takashi Sato Signed-off-by: Mingming Cao --- include/linux/ext4_fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index 97dd409d5f4a..dfe4487fc739 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -73,8 +73,8 @@ * Macro-instructions used to manage several block sizes */ #define EXT4_MIN_BLOCK_SIZE 1024 -#define EXT4_MAX_BLOCK_SIZE 4096 -#define EXT4_MIN_BLOCK_LOG_SIZE 10 +#define EXT4_MAX_BLOCK_SIZE 65536 +#define EXT4_MIN_BLOCK_LOG_SIZE 10 #ifdef __KERNEL__ # define EXT4_BLOCK_SIZE(s) ((s)->s_blocksize) #else -- cgit v1.2.3 From a72d7f834e1afa08421938d7eb06bd8e56b0e58c Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: ext4: Avoid rec_len overflow with 64KB block size With 64KB blocksize, a directory entry can have size 64KB which does not fit into 16 bits we have for entry lenght. So we store 0xffff instead and convert value when read from / written to disk. The patch also converts some places to use ext4_next_entry() when we are changing them anyway. Signed-off-by: Jan Kara Signed-off-by: Mingming Cao --- include/linux/ext4_fs.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index dfe4487fc739..fb31c1aba989 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -767,6 +767,26 @@ struct ext4_dir_entry_2 { #define EXT4_DIR_ROUND (EXT4_DIR_PAD - 1) #define EXT4_DIR_REC_LEN(name_len) (((name_len) + 8 + EXT4_DIR_ROUND) & \ ~EXT4_DIR_ROUND) +#define EXT4_MAX_REC_LEN ((1<<16)-1) + +static inline unsigned ext4_rec_len_from_disk(__le16 dlen) +{ + unsigned len = le16_to_cpu(dlen); + + if (len == EXT4_MAX_REC_LEN) + return 1 << 16; + return len; +} + +static inline __le16 ext4_rec_len_to_disk(unsigned len) +{ + if (len == (1 << 16)) + return cpu_to_le16(EXT4_MAX_REC_LEN); + else if (len > (1 << 16)) + BUG(); + return cpu_to_le16(len); +} + /* * Hash Tree Directory indexing * (c) Daniel Phillips, 2001 -- cgit v1.2.3 From 725d26d3f09ccb5bac4b4293096b985a312a0d67 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: ext4: Introduce ext4_lblk_t This patch adds a new data type ext4_lblk_t to represent the logical file blocks. This is the preparatory patch to support large files in ext4 The follow up patch with convert the ext4_inode i_blocks to represent the number of blocks in file system block size. This changes makes it possible to have a block number 2**32 -1 which will result in overflow if the block number is represented by signed long. This patch convert all the block number to type ext4_lblk_t which is typedef to __u32 Also remove dead code ext4_ext_walk_space Signed-off-by: Aneesh Kumar K.V Signed-off-by: Mingming Cao Signed-off-by: Eric Sandeen --- include/linux/ext4_fs.h | 29 +++++++++++++++++++---------- include/linux/ext4_fs_extents.h | 19 ++----------------- include/linux/ext4_fs_i.h | 9 ++++++--- 3 files changed, 27 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index fb31c1aba989..5e2da0974d16 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -935,11 +935,14 @@ extern unsigned long ext4_count_free (struct buffer_head *, unsigned); /* inode.c */ int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t blocknr); -struct buffer_head * ext4_getblk (handle_t *, struct inode *, long, int, int *); -struct buffer_head * ext4_bread (handle_t *, struct inode *, int, int, int *); +struct buffer_head *ext4_getblk(handle_t *, struct inode *, + ext4_lblk_t, int, int *); +struct buffer_head *ext4_bread(handle_t *, struct inode *, + ext4_lblk_t, int, int *); int ext4_get_blocks_handle(handle_t *handle, struct inode *inode, - sector_t iblock, unsigned long maxblocks, struct buffer_head *bh_result, - int create, int extend_disksize); + ext4_lblk_t iblock, unsigned long maxblocks, + struct buffer_head *bh_result, + int create, int extend_disksize); extern void ext4_read_inode (struct inode *); extern int ext4_write_inode (struct inode *, int); @@ -1068,7 +1071,7 @@ extern const struct inode_operations ext4_fast_symlink_inode_operations; extern int ext4_ext_tree_init(handle_t *handle, struct inode *); extern int ext4_ext_writepage_trans_blocks(struct inode *, int); extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, - ext4_fsblk_t iblock, + ext4_lblk_t iblock, unsigned long max_blocks, struct buffer_head *bh_result, int create, int extend_disksize); extern void ext4_ext_truncate(struct inode *, struct page *); @@ -1081,11 +1084,17 @@ ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, unsigned long max_blocks, struct buffer_head *bh, int create, int extend_disksize) { - if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) - return ext4_ext_get_blocks(handle, inode, block, max_blocks, - bh, create, extend_disksize); - return ext4_get_blocks_handle(handle, inode, block, max_blocks, bh, - create, extend_disksize); + int retval; + if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) { + retval = ext4_ext_get_blocks(handle, inode, + (ext4_lblk_t)block, max_blocks, + bh, create, extend_disksize); + } else { + retval = ext4_get_blocks_handle(handle, inode, + (ext4_lblk_t)block, max_blocks, + bh, create, extend_disksize); + } + return retval; } diff --git a/include/linux/ext4_fs_extents.h b/include/linux/ext4_fs_extents.h index d2045a26195d..023683b9d883 100644 --- a/include/linux/ext4_fs_extents.h +++ b/include/linux/ext4_fs_extents.h @@ -124,20 +124,6 @@ struct ext4_ext_path { #define EXT4_EXT_CACHE_GAP 1 #define EXT4_EXT_CACHE_EXTENT 2 -/* - * to be called by ext4_ext_walk_space() - * negative retcode - error - * positive retcode - signal for ext4_ext_walk_space(), see below - * callback must return valid extent (passed or newly created) - */ -typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *, - struct ext4_ext_cache *, - void *); - -#define EXT_CONTINUE 0 -#define EXT_BREAK 1 -#define EXT_REPEAT 2 - #define EXT_MAX_BLOCK 0xffffffff @@ -233,8 +219,7 @@ extern int ext4_ext_try_to_merge(struct inode *inode, struct ext4_extent *); extern unsigned int ext4_ext_check_overlap(struct inode *, struct ext4_extent *, struct ext4_ext_path *); extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *); -extern int ext4_ext_walk_space(struct inode *, unsigned long, unsigned long, ext_prepare_callback, void *); -extern struct ext4_ext_path * ext4_ext_find_extent(struct inode *, int, struct ext4_ext_path *); - +extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t, + struct ext4_ext_path *); #endif /* _LINUX_EXT4_EXTENTS */ diff --git a/include/linux/ext4_fs_i.h b/include/linux/ext4_fs_i.h index 86ddfe2089f3..6c610b67b047 100644 --- a/include/linux/ext4_fs_i.h +++ b/include/linux/ext4_fs_i.h @@ -27,6 +27,9 @@ typedef int ext4_grpblk_t; /* data type for filesystem-wide blocks number */ typedef unsigned long long ext4_fsblk_t; +/* data type for file logical block number */ +typedef __u32 ext4_lblk_t; + struct ext4_reserve_window { ext4_fsblk_t _rsv_start; /* First byte reserved */ ext4_fsblk_t _rsv_end; /* Last byte reserved or 0 */ @@ -48,7 +51,7 @@ struct ext4_block_alloc_info { * most-recently-allocated block in this file. * We use this for detecting linearly ascending allocation requests. */ - __u32 last_alloc_logical_block; + ext4_lblk_t last_alloc_logical_block; /* * Was i_next_alloc_goal in ext4_inode_info * is the *physical* companion to i_next_alloc_block. @@ -67,7 +70,7 @@ struct ext4_block_alloc_info { */ struct ext4_ext_cache { ext4_fsblk_t ec_start; - __u32 ec_block; + ext4_lblk_t ec_block; __u32 ec_len; /* must be 32bit to return holes */ __u32 ec_type; }; @@ -95,7 +98,7 @@ struct ext4_inode_info { /* block reservation info */ struct ext4_block_alloc_info *i_block_alloc_info; - __u32 i_dir_start_lookup; + ext4_lblk_t i_dir_start_lookup; #ifdef CONFIG_EXT4DEV_FS_XATTR /* * Extended attributes can be read independently of the main file -- cgit v1.2.3 From fd2d42912f9f09e5250cb3b024ee0625704e9cb7 Mon Sep 17 00:00:00 2001 From: Avantika Mathur Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: ext4: add ext4_group_t, and change all group variables to this type. In many places variables for block group are of type int, which limits the maximum number of block groups to 2^31. Each block group can have up to 2^15 blocks, with a 4K block size, and the max filesystem size is limited to 2^31 * (2^15 * 2^12) = 2^58 -- or 256 PB This patch introduces a new type ext4_group_t, of type unsigned long, to represent block group numbers in ext4. All occurrences of block group variables are converted to type ext4_group_t. Signed-off-by: Avantika Mathur --- include/linux/ext4_fs.h | 11 ++++++----- include/linux/ext4_fs_i.h | 5 ++++- include/linux/ext4_fs_sb.h | 2 +- 3 files changed, 11 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index 5e2da0974d16..e1103c2a0d42 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -830,7 +830,7 @@ struct ext4_iloc { struct buffer_head *bh; unsigned long offset; - unsigned long block_group; + ext4_group_t block_group; }; static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc) @@ -855,7 +855,7 @@ struct dir_private_info { /* calculate the first block number of the group */ static inline ext4_fsblk_t -ext4_group_first_block_no(struct super_block *sb, unsigned long group_no) +ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no) { return group_no * (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); @@ -886,8 +886,9 @@ extern unsigned int ext4_block_group(struct super_block *sb, ext4_fsblk_t blocknr); extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb, ext4_fsblk_t blocknr); -extern int ext4_bg_has_super(struct super_block *sb, int group); -extern unsigned long ext4_bg_num_gdb(struct super_block *sb, int group); +extern int ext4_bg_has_super(struct super_block *sb, ext4_group_t group); +extern unsigned long ext4_bg_num_gdb(struct super_block *sb, + ext4_group_t group); extern ext4_fsblk_t ext4_new_block (handle_t *handle, struct inode *inode, ext4_fsblk_t goal, int *errp); extern ext4_fsblk_t ext4_new_blocks (handle_t *handle, struct inode *inode, @@ -900,7 +901,7 @@ extern void ext4_free_blocks_sb (handle_t *handle, struct super_block *sb, extern ext4_fsblk_t ext4_count_free_blocks (struct super_block *); extern void ext4_check_blocks_bitmap (struct super_block *); extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, - unsigned int block_group, + ext4_group_t block_group, struct buffer_head ** bh); extern int ext4_should_retry_alloc(struct super_block *sb, int *retries); extern void ext4_init_block_alloc_info(struct inode *); diff --git a/include/linux/ext4_fs_i.h b/include/linux/ext4_fs_i.h index 6c610b67b047..2b4e3700c725 100644 --- a/include/linux/ext4_fs_i.h +++ b/include/linux/ext4_fs_i.h @@ -30,6 +30,9 @@ typedef unsigned long long ext4_fsblk_t; /* data type for file logical block number */ typedef __u32 ext4_lblk_t; +/* data type for block group number */ +typedef unsigned long ext4_group_t; + struct ext4_reserve_window { ext4_fsblk_t _rsv_start; /* First byte reserved */ ext4_fsblk_t _rsv_end; /* Last byte reserved or 0 */ @@ -92,7 +95,7 @@ struct ext4_inode_info { * place a file's data blocks near its inode block, and new inodes * near to their parent directory's inode. */ - __u32 i_block_group; + ext4_group_t i_block_group; __u32 i_state; /* Dynamic state flags for ext4 */ /* block reservation info */ diff --git a/include/linux/ext4_fs_sb.h b/include/linux/ext4_fs_sb.h index b40e827cd495..f15821c5e4c4 100644 --- a/include/linux/ext4_fs_sb.h +++ b/include/linux/ext4_fs_sb.h @@ -35,7 +35,7 @@ struct ext4_sb_info { unsigned long s_itb_per_group; /* Number of inode table blocks per group */ unsigned long s_gdb_count; /* Number of group descriptor blocks */ unsigned long s_desc_per_block; /* Number of group descriptors per block */ - unsigned long s_groups_count; /* Number of groups in the fs */ + ext4_group_t s_groups_count; /* Number of groups in the fs */ unsigned long s_overhead_last; /* Last calculated overhead */ unsigned long s_blocks_last; /* Last seen block count */ struct buffer_head * s_sbh; /* Buffer containing the super block */ -- cgit v1.2.3 From 99e6f829a854daa6d56006cad51156e98863e73a Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: ext4: Introduce ext4_update_*_feature Introduce ext4_update_*_feature and use them instead of opencoding. Signed-off-by: Aneesh Kumar K.V --- include/linux/ext4_fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index e1103c2a0d42..429dbfc851ea 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -989,6 +989,12 @@ extern void ext4_abort (struct super_block *, const char *, const char *, ...) extern void ext4_warning (struct super_block *, const char *, const char *, ...) __attribute__ ((format (printf, 3, 4))); extern void ext4_update_dynamic_rev (struct super_block *sb); +extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb, + __u32 compat); +extern int ext4_update_rocompat_feature(handle_t *handle, + struct super_block *sb, __u32 rocompat); +extern int ext4_update_incompat_feature(handle_t *handle, + struct super_block *sb, __u32 incompat); extern ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, struct ext4_group_desc *bg); extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, -- cgit v1.2.3 From 1d03ec984ca41ba184822d1101babb3fa3e26c77 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: ext4: Fix sparse warnings. Fix sparse warnings related to static functions and local variables. Signed-off-by: Aneesh Kumar K.V --- include/linux/ext4_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index 429dbfc851ea..1a27433b159a 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -893,6 +893,8 @@ extern ext4_fsblk_t ext4_new_block (handle_t *handle, struct inode *inode, ext4_fsblk_t goal, int *errp); extern ext4_fsblk_t ext4_new_blocks (handle_t *handle, struct inode *inode, ext4_fsblk_t goal, unsigned long *count, int *errp); +extern ext4_fsblk_t ext4_new_blocks_old(handle_t *handle, struct inode *inode, + ext4_fsblk_t goal, unsigned long *count, int *errp); extern void ext4_free_blocks (handle_t *handle, struct inode *inode, ext4_fsblk_t block, unsigned long count); extern void ext4_free_blocks_sb (handle_t *handle, struct super_block *sb, -- cgit v1.2.3 From 7973c0c19ecba92f113488045005f8e7ce1cd7c8 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: ext4: Rename i_file_acl to i_file_acl_lo Rename i_file_acl to i_file_acl_lo. This helps in finding bugs where we use i_file_acl instead of the combined i_file_acl_lo and i_file_acl_high Signed-off-by: Aneesh Kumar K.V --- include/linux/ext4_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index 1a27433b159a..6894f361d01d 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -297,7 +297,7 @@ struct ext4_inode { } osd1; /* OS dependent 1 */ __le32 i_block[EXT4_N_BLOCKS];/* Pointers to blocks */ __le32 i_generation; /* File version (for NFS) */ - __le32 i_file_acl; /* File ACL */ + __le32 i_file_acl_lo; /* File ACL */ __le32 i_dir_acl; /* Directory ACL */ __le32 i_obso_faddr; /* Obsoleted fragment address */ union { -- cgit v1.2.3 From a48380f769dfed6163fb82a68b13bd562ea1e027 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: ext4: Rename i_dir_acl to i_size_high Rename ext4_inode.i_dir_acl to i_size_high drop ext4_inode_info.i_dir_acl as it is not used Rename ext4_inode.i_size to ext4_inode.i_size_lo Add helper function for accessing the ext4_inode combined i_size. Signed-off-by: Aneesh Kumar K.V --- include/linux/ext4_fs.h | 15 ++++++++++++--- include/linux/ext4_fs_i.h | 1 - 2 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index 6894f361d01d..a8f3faea8eff 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -275,7 +275,7 @@ struct ext4_mount_options { struct ext4_inode { __le16 i_mode; /* File mode */ __le16 i_uid; /* Low 16 bits of Owner Uid */ - __le32 i_size; /* Size in bytes */ + __le32 i_size_lo; /* Size in bytes */ __le32 i_atime; /* Access time */ __le32 i_ctime; /* Inode Change time */ __le32 i_mtime; /* Modification time */ @@ -298,7 +298,7 @@ struct ext4_inode { __le32 i_block[EXT4_N_BLOCKS];/* Pointers to blocks */ __le32 i_generation; /* File version (for NFS) */ __le32 i_file_acl_lo; /* File ACL */ - __le32 i_dir_acl; /* Directory ACL */ + __le32 i_size_high; __le32 i_obso_faddr; /* Obsoleted fragment address */ union { struct { @@ -330,7 +330,6 @@ struct ext4_inode { __le32 i_crtime_extra; /* extra FileCreationtime (nsec << 2 | epoch) */ }; -#define i_size_high i_dir_acl #define EXT4_EPOCH_BITS 2 #define EXT4_EPOCH_MASK ((1 << EXT4_EPOCH_BITS) - 1) @@ -1049,7 +1048,17 @@ static inline void ext4_r_blocks_count_set(struct ext4_super_block *es, es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32); } +static inline loff_t ext4_isize(struct ext4_inode *raw_inode) +{ + return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) | + le32_to_cpu(raw_inode->i_size_lo); +} +static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size) +{ + raw_inode->i_size_lo = cpu_to_le32(i_size); + raw_inode->i_size_high = cpu_to_le32(i_size >> 32); +} #define ext4_std_error(sb, errno) \ do { \ diff --git a/include/linux/ext4_fs_i.h b/include/linux/ext4_fs_i.h index 2b4e3700c725..f1cd4934e46f 100644 --- a/include/linux/ext4_fs_i.h +++ b/include/linux/ext4_fs_i.h @@ -85,7 +85,6 @@ struct ext4_inode_info { __le32 i_data[15]; /* unconverted */ __u32 i_flags; ext4_fsblk_t i_file_acl; - __u32 i_dir_acl; __u32 i_dtime; /* -- cgit v1.2.3 From 0fc1b451471dfc3cabd6e99ef441df9804616e63 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 28 Jan 2008 23:58:26 -0500 Subject: ext4: Add support for 48 bit inode i_blocks. Use the __le16 l_i_reserved1 field of the linux2 struct of ext4_inode to represet the higher 16 bits for i_blocks. With this change max_file size becomes (2**48 -1 )* 512 bytes. We add a RO_COMPAT feature to the super block to indicate that inode have i_blocks represented as a split 48 bits. Super block with this feature set cannot be mounted read write on a kernel with CONFIG_LSF disabled. Super block flag EXT4_FEATURE_RO_COMPAT_HUGE_FILE Signed-off-by: Aneesh Kumar K.V --- include/linux/ext4_fs.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index a8f3faea8eff..be25eca9c040 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -282,7 +282,7 @@ struct ext4_inode { __le32 i_dtime; /* Deletion Time */ __le16 i_gid; /* Low 16 bits of Group Id */ __le16 i_links_count; /* Links count */ - __le32 i_blocks; /* Blocks count */ + __le32 i_blocks_lo; /* Blocks count */ __le32 i_flags; /* File flags */ union { struct { @@ -302,7 +302,7 @@ struct ext4_inode { __le32 i_obso_faddr; /* Obsoleted fragment address */ union { struct { - __le16 l_i_reserved1; /* Obsoleted fragment number/size which are removed in ext4 */ + __le16 l_i_blocks_high; /* were l_i_reserved1 */ __le16 l_i_file_acl_high; __le16 l_i_uid_high; /* these 2 fields */ __le16 l_i_gid_high; /* were reserved2[0] */ @@ -404,6 +404,7 @@ do { \ #if defined(__KERNEL__) || defined(__linux__) #define i_reserved1 osd1.linux1.l_i_reserved1 #define i_file_acl_high osd2.linux2.l_i_file_acl_high +#define i_blocks_high osd2.linux2.l_i_blocks_high #define i_uid_low i_uid #define i_gid_low i_gid #define i_uid_high osd2.linux2.l_i_uid_high @@ -670,6 +671,7 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) #define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001 #define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002 #define EXT4_FEATURE_RO_COMPAT_BTREE_DIR 0x0004 +#define EXT4_FEATURE_RO_COMPAT_HUGE_FILE 0x0008 #define EXT4_FEATURE_RO_COMPAT_GDT_CSUM 0x0010 #define EXT4_FEATURE_RO_COMPAT_DIR_NLINK 0x0020 #define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE 0x0040 @@ -681,6 +683,7 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) #define EXT4_FEATURE_INCOMPAT_META_BG 0x0010 #define EXT4_FEATURE_INCOMPAT_EXTENTS 0x0040 /* extents support */ #define EXT4_FEATURE_INCOMPAT_64BIT 0x0080 +#define EXT4_FEATURE_INCOMPAT_MMP 0x0100 #define EXT4_FEATURE_INCOMPAT_FLEX_BG 0x0200 #define EXT4_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR @@ -695,7 +698,8 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \ EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \ EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \ - EXT4_FEATURE_RO_COMPAT_BTREE_DIR) + EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\ + EXT4_FEATURE_RO_COMPAT_HUGE_FILE) /* * Default values for user and/or group using reserved blocks -- cgit v1.2.3 From 8180a5627d126362c2f64e4fa886d6f608d9632a Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: ext4: Support large files This patch converts ext4_inode i_blocks to represent total blocks occupied by the inode in file system block size. Earlier the variable used to represent this in 512 byte block size. This actually limited the total size of the file. The feature is enabled transparently when we write an inode whose i_blocks cannot be represnted as 512 byte units in a 48 bit variable. inode flag EXT4_HUGE_FILE_FL Signed-off-by: Aneesh Kumar K.V --- include/linux/ext4_fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index be25eca9c040..6ae91f40aaa2 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -178,8 +178,9 @@ struct ext4_group_desc #define EXT4_NOTAIL_FL 0x00008000 /* file tail should not be merged */ #define EXT4_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ #define EXT4_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ -#define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ +#define EXT4_HUGE_FILE_FL 0x00040000 /* Set to each huge file */ #define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */ +#define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ #define EXT4_FL_USER_VISIBLE 0x000BDFFF /* User visible flags */ #define EXT4_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */ -- cgit v1.2.3 From e2b4657453c0d5571bd3c7256585c486ed42d364 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: ext4: store maxbytes for bitmapped files and return EFBIG as appropriate Calculate & store the max offset for bitmapped files, and catch too-large seeks, truncates, and writes in ext4, shortening or rejecting as appropriate. Signed-off-by: Eric Sandeen --- include/linux/ext4_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ext4_fs_sb.h b/include/linux/ext4_fs_sb.h index f15821c5e4c4..38a47ec06df9 100644 --- a/include/linux/ext4_fs_sb.h +++ b/include/linux/ext4_fs_sb.h @@ -38,6 +38,7 @@ struct ext4_sb_info { ext4_group_t s_groups_count; /* Number of groups in the fs */ unsigned long s_overhead_last; /* Last calculated overhead */ unsigned long s_blocks_last; /* Last seen block count */ + loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */ struct buffer_head * s_sbh; /* Buffer containing the super block */ struct ext4_super_block * s_es; /* Pointer to the super block in the buffer */ struct buffer_head ** s_group_desc; -- cgit v1.2.3 From 91b51a018d7711b20e9e0bb14c3d790de4e310d4 Mon Sep 17 00:00:00 2001 From: Coly Li Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: ext4: sync up block group descriptor with e2fsprogs. This patch extends bg_itable_unused of ext4 group descriptor from 16bit into 32bit. In order to add bg_itable_unused_hi into struct ext4_group_desc, some extra fields which are already introduced into e2fsprogs are also added in for consistency. Signed-off-by: Coly Li Cc: Andreas Dilger Signed-off-by: Mingming Cao --- include/linux/ext4_fs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index 6ae91f40aaa2..55a376e7bca0 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -118,6 +118,11 @@ struct ext4_group_desc __le32 bg_block_bitmap_hi; /* Blocks bitmap block MSB */ __le32 bg_inode_bitmap_hi; /* Inodes bitmap block MSB */ __le32 bg_inode_table_hi; /* Inodes table block MSB */ + __le16 bg_free_blocks_count_hi;/* Free blocks count MSB */ + __le16 bg_free_inodes_count_hi;/* Free inodes count MSB */ + __le16 bg_used_dirs_count_hi; /* Directories count MSB */ + __le16 bg_itable_unused_hi; /* Unused inodes count MSB */ + __u32 bg_reserved2[3]; }; #define EXT4_BG_INODE_UNINIT 0x0001 /* Inode table/bitmap not in use */ -- cgit v1.2.3 From 389d1b083c767a360ec84b27a95da06244becec8 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 28 Jan 2008 23:58:26 -0500 Subject: Add buffer head related helper functions Add buffer head related helper function bh_uptodate_or_lock and bh_submit_read which can be used by file system Signed-off-by: Aneesh Kumar K.V --- include/linux/buffer_head.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index da0d83fbadc0..e98801f06dcc 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -192,6 +192,8 @@ int sync_dirty_buffer(struct buffer_head *bh); int submit_bh(int, struct buffer_head *); void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize); +int bh_uptodate_or_lock(struct buffer_head *bh); +int bh_submit_read(struct buffer_head *bh); extern int buffer_heads_over_limit; -- cgit v1.2.3 From 36df53f4a3e445175fc1e9d7f433599482ec6d7f Mon Sep 17 00:00:00 2001 From: Chris Snook Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: jbd2: Remove printk from J_ASSERT to preserve registers during BUG Signed-off-by: Chris Snook Cc: "Stephen C. Tweedie" Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: "Theodore Ts'o" --- include/linux/jbd2.h | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 06ef11457051..d5f7cff4cb28 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -256,17 +256,7 @@ typedef struct journal_superblock_s #include #include -#define JBD2_ASSERTIONS -#ifdef JBD2_ASSERTIONS -#define J_ASSERT(assert) \ -do { \ - if (!(assert)) { \ - printk (KERN_EMERG \ - "Assertion failure in %s() at %s:%d: \"%s\"\n", \ - __FUNCTION__, __FILE__, __LINE__, # assert); \ - BUG(); \ - } \ -} while (0) +#define J_ASSERT(assert) BUG_ON(!(assert)) #if defined(CONFIG_BUFFER_DEBUG) void buffer_assertion_failure(struct buffer_head *bh); @@ -282,10 +272,6 @@ void buffer_assertion_failure(struct buffer_head *bh); #define J_ASSERT_JH(jh, expr) J_ASSERT(expr) #endif -#else -#define J_ASSERT(assert) do { } while (0) -#endif /* JBD2_ASSERTIONS */ - #if defined(JBD2_PARANOID_IOFAIL) #define J_EXPECT(expr, why...) J_ASSERT(expr) #define J_EXPECT_BH(bh, expr, why...) J_ASSERT_BH(bh, expr) -- cgit v1.2.3 From f5a7a6b0d9b6af7d46124ed3f6b3995225cb62d0 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: jbd2: Fix assertion failure in fs/jbd2/checkpoint.c Before we start committing a transaction, we call __journal_clean_checkpoint_list() to cleanup transaction's written-back buffers. If this call happens to remove all of them (and there were already some buffers), __journal_remove_checkpoint() will decide to free the transaction because it isn't (yet) a committing transaction and soon we fail some assertion - the transaction really isn't ready to be freed :). We change the check in __journal_remove_checkpoint() to free only a transaction in T_FINISHED state. The locking there is subtle though (as everywhere in JBD ;(). We use j_list_lock to protect the check and a subsequent call to __journal_drop_transaction() and do the same in the end of journal_commit_transaction() which is the only place where a transaction can get to T_FINISHED state. Probably I'm too paranoid here and such locking is not really necessary - checkpoint lists are processed only from log_do_checkpoint() where a transaction must be already committed to be processed or from __journal_clean_checkpoint_list() where kjournald itself calls it and thus transaction cannot change state either. Better be safe if something changes in future... Signed-off-by: Jan Kara Cc: Signed-off-by: Andrew Morton --- include/linux/jbd2.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d5f7cff4cb28..d861ffd49821 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -442,6 +442,8 @@ struct transaction_s /* * Transaction's current state * [no locking - only kjournald2 alters this] + * [j_list_lock] guards transition of a transaction into T_FINISHED + * state and subsequent call of __jbd2_journal_drop_transaction() * FIXME: needs barriers * KLUDGE: [use j_state_lock] */ -- cgit v1.2.3 From c278bfecebfb1ed67c326ef472660878baa745cd Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: ext4: Make ext4_get_blocks_wrap take the truncate_mutex early. When doing a migrate from ext3 to ext4 inode we need to make sure the test for inode type and walking inode data happens inside lock. To make this happen move truncate_mutex early before checking the i_flags. This actually should enable us to remove the verify_chain(). Signed-off-by: Aneesh Kumar K.V --- include/linux/ext4_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index 55a376e7bca0..583049c1d366 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -1113,6 +1113,7 @@ ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, int create, int extend_disksize) { int retval; + mutex_lock(&EXT4_I(inode)->truncate_mutex); if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) { retval = ext4_ext_get_blocks(handle, inode, (ext4_lblk_t)block, max_blocks, @@ -1122,6 +1123,7 @@ ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, (ext4_lblk_t)block, max_blocks, bh, create, extend_disksize); } + mutex_unlock(&EXT4_I(inode)->truncate_mutex); return retval; } -- cgit v1.2.3 From 0e855ac8b103ef579052936b59fe7c599ac422a4 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 28 Jan 2008 23:58:26 -0500 Subject: ext4: Convert truncate_mutex to read write semaphore. We are currently taking the truncate_mutex for every read. This would have performance impact on large CPU configuration. Convert the lock to read write semaphore and take read lock when we are trying to read the file. Signed-off-by: Aneesh Kumar K.V --- include/linux/ext4_fs.h | 25 ++++--------------------- include/linux/ext4_fs_i.h | 6 +++--- 2 files changed, 7 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index 583049c1d366..300cc5a5adb9 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -1107,27 +1107,10 @@ extern void ext4_ext_init(struct super_block *); extern void ext4_ext_release(struct super_block *); extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len); -static inline int -ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, - unsigned long max_blocks, struct buffer_head *bh, - int create, int extend_disksize) -{ - int retval; - mutex_lock(&EXT4_I(inode)->truncate_mutex); - if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) { - retval = ext4_ext_get_blocks(handle, inode, - (ext4_lblk_t)block, max_blocks, - bh, create, extend_disksize); - } else { - retval = ext4_get_blocks_handle(handle, inode, - (ext4_lblk_t)block, max_blocks, - bh, create, extend_disksize); - } - mutex_unlock(&EXT4_I(inode)->truncate_mutex); - return retval; -} - - +extern int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, + sector_t block, unsigned long max_blocks, + struct buffer_head *bh, int create, + int extend_disksize); #endif /* __KERNEL__ */ #endif /* _LINUX_EXT4_FS_H */ diff --git a/include/linux/ext4_fs_i.h b/include/linux/ext4_fs_i.h index f1cd4934e46f..4377d249d378 100644 --- a/include/linux/ext4_fs_i.h +++ b/include/linux/ext4_fs_i.h @@ -139,16 +139,16 @@ struct ext4_inode_info { __u16 i_extra_isize; /* - * truncate_mutex is for serialising ext4_truncate() against + * i_data_sem is for serialising ext4_truncate() against * ext4_getblock(). In the 2.4 ext2 design, great chunks of inode's * data tree are chopped off during truncate. We can't do that in * ext4 because whenever we perform intermediate commits during * truncate, the inode and all the metadata blocks *must* be in a * consistent state which allows truncation of the orphans to restart * during recovery. Hence we must fix the get_block-vs-truncate race - * by other means, so we have truncate_mutex. + * by other means, so we have i_data_sem. */ - struct mutex truncate_mutex; + struct rw_semaphore i_data_sem; struct inode vfs_inode; unsigned long i_ext_generation; -- cgit v1.2.3 From 8e85fb3f305b24b79c6d9cb7a56d22b062335ad3 Mon Sep 17 00:00:00 2001 From: Johann Lombardi Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: jbd2: jbd2 stats through procfs The patch below updates the jbd stats patch to 2.6.20/jbd2. The initial patch was posted by Alex Tomas in December 2005 (http://marc.info/?l=linux-ext4&m=113538565128617&w=2). It provides statistics via procfs such as transaction lifetime and size. Sometimes, investigating performance problems, i find useful to have stats from jbd about transaction's lifetime, size, etc. here is a patch for review and inclusion probably. for example, stats after creation of 3M files in htree directory: [root@bob ~]# cat /proc/fs/jbd/sda/history R/C tid wait run lock flush log hndls block inlog ctime write drop close R 261 8260 2720 0 0 750 9892 8170 8187 C 259 750 0 4885 1 R 262 20 2200 10 0 770 9836 8170 8187 R 263 30 2200 10 0 3070 9812 8170 8187 R 264 0 5000 10 0 1340 0 0 0 C 261 8240 3212 4957 0 R 265 8260 1470 0 0 4640 9854 8170 8187 R 266 0 5000 10 0 1460 0 0 0 C 262 8210 2989 4868 0 R 267 8230 1490 10 0 4440 9875 8171 8188 R 268 0 5000 10 0 1260 0 0 0 C 263 7710 2937 4908 0 R 269 7730 1470 10 0 3330 9841 8170 8187 R 270 0 5000 10 0 830 0 0 0 C 265 8140 3234 4898 0 C 267 720 0 4849 1 R 271 8630 2740 20 0 740 9819 8170 8187 C 269 800 0 4214 1 R 272 40 2170 10 0 830 9716 8170 8187 R 273 40 2280 0 0 3530 9799 8170 8187 R 274 0 5000 10 0 990 0 0 0 where, R - line for transaction's life from T_RUNNING to T_FINISHED C - line for transaction's checkpointing tid - transaction's id wait - for how long we were waiting for new transaction to start (the longest period journal_start() took in this transaction) run - real transaction's lifetime (from T_RUNNING to T_LOCKED lock - how long we were waiting for all handles to close (time the transaction was in T_LOCKED) flush - how long it took to flush all data (data=ordered) log - how long it took to write the transaction to the log hndls - how many handles got to the transaction block - how many blocks got to the transaction inlog - how many blocks are written to the log (block + descriptors) ctime - how long it took to checkpoint the transaction write - how many blocks have been written during checkpointing drop - how many blocks have been dropped during checkpointing close - how many running transactions have been closed to checkpoint this one all times are in msec. [root@bob ~]# cat /proc/fs/jbd/sda/info 280 transaction, each upto 8192 blocks average: 1633ms waiting for transaction 3616ms running transaction 5ms transaction was being locked 1ms flushing data (in ordered mode) 1799ms logging transaction 11781 handles per transaction 5629 blocks per transaction 5641 logged blocks per transaction Signed-off-by: Johann Lombardi Signed-off-by: Mariusz Kozlowski Signed-off-by: Mingming Cao Signed-off-by: Eric Sandeen --- include/linux/jbd2.h | 77 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 77 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d861ffd49821..685640036e81 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -395,6 +395,16 @@ struct handle_s }; +/* + * Some stats for checkpoint phase + */ +struct transaction_chp_stats_s { + unsigned long cs_chp_time; + unsigned long cs_forced_to_close; + unsigned long cs_written; + unsigned long cs_dropped; +}; + /* The transaction_t type is the guts of the journaling mechanism. It * tracks a compound transaction through its various states: * @@ -531,6 +541,21 @@ struct transaction_s */ spinlock_t t_handle_lock; + /* + * Longest time some handle had to wait for running transaction + */ + unsigned long t_max_wait; + + /* + * When transaction started + */ + unsigned long t_start; + + /* + * Checkpointing stats [j_checkpoint_sem] + */ + struct transaction_chp_stats_s t_chp_stats; + /* * Number of outstanding updates running on this transaction * [t_handle_lock] @@ -562,6 +587,39 @@ struct transaction_s }; +struct transaction_run_stats_s { + unsigned long rs_wait; + unsigned long rs_running; + unsigned long rs_locked; + unsigned long rs_flushing; + unsigned long rs_logging; + + unsigned long rs_handle_count; + unsigned long rs_blocks; + unsigned long rs_blocks_logged; +}; + +struct transaction_stats_s { + int ts_type; + unsigned long ts_tid; + union { + struct transaction_run_stats_s run; + struct transaction_chp_stats_s chp; + } u; +}; + +#define JBD2_STATS_RUN 1 +#define JBD2_STATS_CHECKPOINT 2 + +static inline unsigned long +jbd2_time_diff(unsigned long start, unsigned long end) +{ + if (end >= start) + return end - start; + + return end + (MAX_JIFFY_OFFSET - start); +} + /** * struct journal_s - The journal_s type is the concrete type associated with * journal_t. @@ -623,6 +681,12 @@ struct transaction_s * @j_wbufsize: maximum number of buffer_heads allowed in j_wbuf, the * number that will fit in j_blocksize * @j_last_sync_writer: most recent pid which did a synchronous write + * @j_history: Buffer storing the transactions statistics history + * @j_history_max: Maximum number of transactions in the statistics history + * @j_history_cur: Current number of transactions in the statistics history + * @j_history_lock: Protect the transactions statistics history + * @j_proc_entry: procfs entry for the jbd statistics directory + * @j_stats: Overall statistics * @j_private: An opaque pointer to fs-private information. */ @@ -814,6 +878,19 @@ struct journal_s pid_t j_last_sync_writer; + /* + * Journal statistics + */ + struct transaction_stats_s *j_history; + int j_history_max; + int j_history_cur; + /* + * Protect the transactions statistics history + */ + spinlock_t j_history_lock; + struct proc_dir_entry *j_proc_entry; + struct transaction_stats_s j_stats; + /* * An opaque pointer to fs-private information. ext3 puts its * superblock pointer here -- cgit v1.2.3 From 818d276ceb83aa9fdebb5e0a53188290312de987 Mon Sep 17 00:00:00 2001 From: Girish Shilamkar Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: ext4: Add the journal checksum feature The journal checksum feature adds two new flags i.e JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT and JBD2_FEATURE_COMPAT_CHECKSUM. JBD2_FEATURE_CHECKSUM flag indicates that the commit block contains the checksum for the blocks described by the descriptor blocks. Due to checksums, writing of the commit record no longer needs to be synchronous. Now commit record can be sent to disk without waiting for descriptor blocks to be written to disk. This behavior is controlled using JBD2_FEATURE_ASYNC_COMMIT flag. Older kernels/e2fsck should not be able to recover the journal with _ASYNC_COMMIT hence it is made incompat. The commit header has been extended to hold the checksum along with the type of the checksum. For recovery in pass scan checksums are verified to ensure the sanity and completeness(in case of _ASYNC_COMMIT) of every transaction. Signed-off-by: Andreas Dilger Signed-off-by: Girish Shilamkar Signed-off-by: Dave Kleikamp Signed-off-by: Mingming Cao --- include/linux/ext4_fs.h | 3 ++- include/linux/jbd2.h | 36 ++++++++++++++++++++++++++++++++---- 2 files changed, 34 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index 300cc5a5adb9..cd406dba0e64 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -467,7 +467,8 @@ do { \ #define EXT4_MOUNT_USRQUOTA 0x100000 /* "old" user quota */ #define EXT4_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */ #define EXT4_MOUNT_EXTENTS 0x400000 /* Extents support */ - +#define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */ +#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */ /* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */ #ifndef _LINUX_EXT2_FS_H #define clear_opt(o, opt) o &= ~EXT4_MOUNT_##opt diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 685640036e81..98a2bc5d3e3f 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -149,6 +149,28 @@ typedef struct journal_header_s __be32 h_sequence; } journal_header_t; +/* + * Checksum types. + */ +#define JBD2_CRC32_CHKSUM 1 +#define JBD2_MD5_CHKSUM 2 +#define JBD2_SHA1_CHKSUM 3 + +#define JBD2_CRC32_CHKSUM_SIZE 4 + +#define JBD2_CHECKSUM_BYTES (32 / sizeof(u32)) +/* + * Commit block header for storing transactional checksums: + */ +struct commit_header { + __be32 h_magic; + __be32 h_blocktype; + __be32 h_sequence; + unsigned char h_chksum_type; + unsigned char h_chksum_size; + unsigned char h_padding[2]; + __be32 h_chksum[JBD2_CHECKSUM_BYTES]; +}; /* * The block tag: used to describe a single buffer in the journal. @@ -242,14 +264,18 @@ typedef struct journal_superblock_s ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_incompat & cpu_to_be32((mask)))) -#define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001 -#define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 +#define JBD2_FEATURE_COMPAT_CHECKSUM 0x00000001 + +#define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001 +#define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 +#define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004 /* Features known to this kernel version: */ -#define JBD2_KNOWN_COMPAT_FEATURES 0 +#define JBD2_KNOWN_COMPAT_FEATURES JBD2_FEATURE_COMPAT_CHECKSUM #define JBD2_KNOWN_ROCOMPAT_FEATURES 0 #define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \ - JBD2_FEATURE_INCOMPAT_64BIT) + JBD2_FEATURE_INCOMPAT_64BIT | \ + JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT) #ifdef __KERNEL__ @@ -997,6 +1023,8 @@ extern int jbd2_journal_check_available_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_set_features (journal_t *, unsigned long, unsigned long, unsigned long); +extern void jbd2_journal_clear_features + (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_create (journal_t *); extern int jbd2_journal_load (journal_t *journal); extern void jbd2_journal_destroy (journal_t *); -- cgit v1.2.3 From 7a224228ed79d587ece2304869000aad1b8e97dd Mon Sep 17 00:00:00 2001 From: Jean Noel Cordenner Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: vfs: Add 64 bit i_version support The i_version field of the inode is changed to be a 64-bit counter that is set on every inode creation and that is incremented every time the inode data is modified (similarly to the "ctime" time-stamp). The aim is to fulfill a NFSv4 requirement for rfc3530. This first part concerns the vfs, it converts the 32-bit i_version in the generic inode to a 64-bit, a flag is added in the super block in order to check if the feature is enabled and the i_version is incremented in the vfs. Signed-off-by: Mingming Cao Signed-off-by: Jean Noel Cordenner Signed-off-by: Kalpak Shah --- include/linux/fs.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 21398a5d688d..9608839552b3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -124,6 +124,7 @@ extern int dir_notify_enable; #define MS_SHARED (1<<20) /* change to shared */ #define MS_RELATIME (1<<21) /* Update atime relative to mtime/ctime. */ #define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */ +#define MS_I_VERSION (1<<23) /* Update inode I_version field */ #define MS_ACTIVE (1<<30) #define MS_NOUSER (1<<31) @@ -173,6 +174,7 @@ extern int dir_notify_enable; ((inode)->i_flags & (S_SYNC|S_DIRSYNC))) #define IS_MANDLOCK(inode) __IS_FLG(inode, MS_MANDLOCK) #define IS_NOATIME(inode) __IS_FLG(inode, MS_RDONLY|MS_NOATIME) +#define IS_I_VERSION(inode) __IS_FLG(inode, MS_I_VERSION) #define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA) #define IS_APPEND(inode) ((inode)->i_flags & S_APPEND) @@ -599,7 +601,7 @@ struct inode { uid_t i_uid; gid_t i_gid; dev_t i_rdev; - unsigned long i_version; + u64 i_version; loff_t i_size; #ifdef __NEED_I_SIZE_ORDERED seqcount_t i_size_seqcount; @@ -1394,6 +1396,7 @@ static inline void inode_dec_link_count(struct inode *inode) mark_inode_dirty(inode); } +extern void inode_inc_iversion(struct inode *inode); extern void touch_atime(struct vfsmount *mnt, struct dentry *dentry); static inline void file_accessed(struct file *file) { -- cgit v1.2.3 From 25ec56b518257a56d2ff41a941d288e4b5ff9488 Mon Sep 17 00:00:00 2001 From: Jean Noel Cordenner Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: ext4: Add inode version support in ext4 This patch adds 64-bit inode version support to ext4. The lower 32 bits are stored in the osd1.linux1.l_i_version field while the high 32 bits are stored in the i_version_hi field newly created in the ext4_inode. This field is incremented in case the ext4_inode is large enough. A i_version mount option has been added to enable the feature. Signed-off-by: Mingming Cao Signed-off-by: Andreas Dilger Signed-off-by: Kalpak Shah Signed-off-by: Aneesh Kumar K.V Signed-off-by: Jean Noel Cordenner --- include/linux/ext4_fs.h | 6 +++++- include/linux/fs.h | 16 +++++++++++++++- 2 files changed, 20 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index cd406dba0e64..b6092940c8b8 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -292,7 +292,7 @@ struct ext4_inode { __le32 i_flags; /* File flags */ union { struct { - __u32 l_i_reserved1; + __le32 l_i_version; } linux1; struct { __u32 h_i_translator; @@ -334,6 +334,7 @@ struct ext4_inode { __le32 i_atime_extra; /* extra Access time (nsec << 2 | epoch) */ __le32 i_crtime; /* File Creation time */ __le32 i_crtime_extra; /* extra FileCreationtime (nsec << 2 | epoch) */ + __le32 i_version_hi; /* high 32 bits for 64-bit version */ }; @@ -407,6 +408,8 @@ do { \ raw_inode->xtime ## _extra); \ } while (0) +#define i_disk_version osd1.linux1.l_i_version + #if defined(__KERNEL__) || defined(__linux__) #define i_reserved1 osd1.linux1.l_i_reserved1 #define i_file_acl_high osd2.linux2.l_i_file_acl_high @@ -469,6 +472,7 @@ do { \ #define EXT4_MOUNT_EXTENTS 0x400000 /* Extents support */ #define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */ #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */ +#define EXT4_MOUNT_I_VERSION 0x2000000 /* i_version support */ /* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */ #ifndef _LINUX_EXT2_FS_H #define clear_opt(o, opt) o &= ~EXT4_MOUNT_##opt diff --git a/include/linux/fs.h b/include/linux/fs.h index 9608839552b3..a516b6716870 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1396,7 +1396,21 @@ static inline void inode_dec_link_count(struct inode *inode) mark_inode_dirty(inode); } -extern void inode_inc_iversion(struct inode *inode); +/** + * inode_inc_iversion - increments i_version + * @inode: inode that need to be updated + * + * Every time the inode is modified, the i_version field will be incremented. + * The filesystem has to be mounted with i_version flag + */ + +static inline void inode_inc_iversion(struct inode *inode) +{ + spin_lock(&inode->i_lock); + inode->i_version++; + spin_unlock(&inode->i_lock); +} + extern void touch_atime(struct vfsmount *mnt, struct dentry *dentry); static inline void file_accessed(struct file *file) { -- cgit v1.2.3 From c14c6fd5c56a0d0495d8a7c0f2bc330be658663e Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 28 Jan 2008 23:58:26 -0500 Subject: ext4: Add EXT4_IOC_MIGRATE ioctl The below patch add ioctl for migrating ext3 indirect block mapped inode to ext4 extent mapped inode. Signed-off-by: Aneesh Kumar K.V --- include/linux/ext4_fs.h | 4 ++++ include/linux/ext4_fs_extents.h | 2 ++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index b6092940c8b8..213974f7c5d8 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -243,6 +243,7 @@ struct ext4_new_group_data { #endif #define EXT4_IOC_GETRSVSZ _IOR('f', 5, long) #define EXT4_IOC_SETRSVSZ _IOW('f', 6, long) +#define EXT4_IOC_MIGRATE _IO('f', 7) /* * ioctl commands in 32 bit emulation @@ -983,6 +984,9 @@ extern int ext4_ioctl (struct inode *, struct file *, unsigned int, unsigned long); extern long ext4_compat_ioctl (struct file *, unsigned int, unsigned long); +/* migrate.c */ +extern int ext4_ext_migrate(struct inode *, struct file *, unsigned int, + unsigned long); /* namei.c */ extern int ext4_orphan_add(handle_t *, struct inode *); extern int ext4_orphan_del(handle_t *, struct inode *); diff --git a/include/linux/ext4_fs_extents.h b/include/linux/ext4_fs_extents.h index 023683b9d883..1cfb4854c964 100644 --- a/include/linux/ext4_fs_extents.h +++ b/include/linux/ext4_fs_extents.h @@ -212,6 +212,8 @@ static inline int ext4_ext_get_actual_len(struct ext4_extent *ext) (le16_to_cpu(ext->ee_len) - EXT_INIT_MAX_LEN)); } +extern ext4_fsblk_t idx_pblock(struct ext4_extent_idx *); +extern void ext4_ext_store_pblock(struct ext4_extent *, ext4_fsblk_t); extern int ext4_extent_tree_init(handle_t *, struct inode *); extern int ext4_ext_calc_credits_for_insert(struct inode *, struct ext4_ext_path *); extern int ext4_ext_try_to_merge(struct inode *inode, -- cgit v1.2.3 From aa02ad67d9b308290fde390682cd039b29f7ab85 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: ext4: Add ext4_find_next_bit() This function is used by the ext4 multi block allocator patches. Also add generic_find_next_le_bit Signed-off-by: Aneesh Kumar K.V Cc: Signed-off-by: Andrew Morton --- include/linux/ext4_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index 213974f7c5d8..d0b7ca99b91f 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -493,6 +493,7 @@ do { \ #define ext4_test_bit ext2_test_bit #define ext4_find_first_zero_bit ext2_find_first_zero_bit #define ext4_find_next_zero_bit ext2_find_next_zero_bit +#define ext4_find_next_bit ext2_find_next_bit /* * Maximal mount counts between two filesystem checks -- cgit v1.2.3 From 1988b51e476bd097d910c9245b53f2e38aedaf0d Mon Sep 17 00:00:00 2001 From: Alex Tomas Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: ext4: Add new functions for searching extent tree Add the functions ext4_ext_search_left() and ext4_ext_search_right(), which are used by mballoc during ext4_ext_get_blocks to decided whether to merge extent information. Signed-off-by: Alex Tomas Signed-off-by: Andreas Dilger Signed-off-by: Johann Lombardi Signed-off-by: Aneesh Kumar K.V Signed-off-by: "Theodore Ts'o" --- include/linux/ext4_fs_extents.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ext4_fs_extents.h b/include/linux/ext4_fs_extents.h index 1cfb4854c964..697da4bce6c5 100644 --- a/include/linux/ext4_fs_extents.h +++ b/include/linux/ext4_fs_extents.h @@ -223,5 +223,9 @@ extern unsigned int ext4_ext_check_overlap(struct inode *, struct ext4_extent *, extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *); extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t, struct ext4_ext_path *); +extern int ext4_ext_search_left(struct inode *, struct ext4_ext_path *, + ext4_lblk_t *, ext4_fsblk_t *); +extern int ext4_ext_search_right(struct inode *, struct ext4_ext_path *, + ext4_lblk_t *, ext4_fsblk_t *); #endif /* _LINUX_EXT4_EXTENTS */ -- cgit v1.2.3 From c9de560ded61faa5b754137b7753da252391c55a Mon Sep 17 00:00:00 2001 From: Alex Tomas Date: Tue, 29 Jan 2008 00:19:52 -0500 Subject: ext4: Add multi block allocator for ext4 Signed-off-by: Alex Tomas Signed-off-by: Andreas Dilger Signed-off-by: Aneesh Kumar K.V Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- include/linux/ext4_fs.h | 76 +++++++++++++++++++++++++++++++++++++++++++++- include/linux/ext4_fs_i.h | 4 +++ include/linux/ext4_fs_sb.h | 52 +++++++++++++++++++++++++++++++ 3 files changed, 131 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h index d0b7ca99b91f..1852313fc7c7 100644 --- a/include/linux/ext4_fs.h +++ b/include/linux/ext4_fs.h @@ -20,6 +20,8 @@ #include #include +#include + /* * The second extended filesystem constants/structures */ @@ -51,6 +53,50 @@ #define ext4_debug(f, a...) do {} while (0) #endif +#define EXT4_MULTIBLOCK_ALLOCATOR 1 + +/* prefer goal again. length */ +#define EXT4_MB_HINT_MERGE 1 +/* blocks already reserved */ +#define EXT4_MB_HINT_RESERVED 2 +/* metadata is being allocated */ +#define EXT4_MB_HINT_METADATA 4 +/* first blocks in the file */ +#define EXT4_MB_HINT_FIRST 8 +/* search for the best chunk */ +#define EXT4_MB_HINT_BEST 16 +/* data is being allocated */ +#define EXT4_MB_HINT_DATA 32 +/* don't preallocate (for tails) */ +#define EXT4_MB_HINT_NOPREALLOC 64 +/* allocate for locality group */ +#define EXT4_MB_HINT_GROUP_ALLOC 128 +/* allocate goal blocks or none */ +#define EXT4_MB_HINT_GOAL_ONLY 256 +/* goal is meaningful */ +#define EXT4_MB_HINT_TRY_GOAL 512 + +struct ext4_allocation_request { + /* target inode for block we're allocating */ + struct inode *inode; + /* logical block in target inode */ + ext4_lblk_t logical; + /* phys. target (a hint) */ + ext4_fsblk_t goal; + /* the closest logical allocated block to the left */ + ext4_lblk_t lleft; + /* phys. block for ^^^ */ + ext4_fsblk_t pleft; + /* the closest logical allocated block to the right */ + ext4_lblk_t lright; + /* phys. block for ^^^ */ + ext4_fsblk_t pright; + /* how many blocks we want to allocate */ + unsigned long len; + /* flags. see above EXT4_MB_HINT_* */ + unsigned long flags; +}; + /* * Special inodes numbers */ @@ -474,6 +520,7 @@ do { \ #define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */ #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */ #define EXT4_MOUNT_I_VERSION 0x2000000 /* i_version support */ +#define EXT4_MOUNT_MBALLOC 0x4000000 /* Buddy allocation support */ /* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */ #ifndef _LINUX_EXT2_FS_H #define clear_opt(o, opt) o &= ~EXT4_MOUNT_##opt @@ -912,7 +959,7 @@ extern ext4_fsblk_t ext4_new_blocks (handle_t *handle, struct inode *inode, extern ext4_fsblk_t ext4_new_blocks_old(handle_t *handle, struct inode *inode, ext4_fsblk_t goal, unsigned long *count, int *errp); extern void ext4_free_blocks (handle_t *handle, struct inode *inode, - ext4_fsblk_t block, unsigned long count); + ext4_fsblk_t block, unsigned long count, int metadata); extern void ext4_free_blocks_sb (handle_t *handle, struct super_block *sb, ext4_fsblk_t block, unsigned long count, unsigned long *pdquot_freed_blocks); @@ -950,6 +997,20 @@ extern unsigned long ext4_count_dirs (struct super_block *); extern void ext4_check_inodes_bitmap (struct super_block *); extern unsigned long ext4_count_free (struct buffer_head *, unsigned); +/* mballoc.c */ +extern long ext4_mb_stats; +extern long ext4_mb_max_to_scan; +extern int ext4_mb_init(struct super_block *, int); +extern int ext4_mb_release(struct super_block *); +extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *, + struct ext4_allocation_request *, int *); +extern int ext4_mb_reserve_blocks(struct super_block *, int); +extern void ext4_mb_discard_inode_preallocations(struct inode *); +extern int __init init_ext4_mballoc(void); +extern void exit_ext4_mballoc(void); +extern void ext4_mb_free_blocks(handle_t *, struct inode *, + unsigned long, unsigned long, int, unsigned long *); + /* inode.c */ int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode, @@ -1080,6 +1141,19 @@ static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size) raw_inode->i_size_high = cpu_to_le32(i_size >> 32); } +static inline +struct ext4_group_info *ext4_get_group_info(struct super_block *sb, + ext4_group_t group) +{ + struct ext4_group_info ***grp_info; + long indexv, indexh; + grp_info = EXT4_SB(sb)->s_group_info; + indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb)); + indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1); + return grp_info[indexv][indexh]; +} + + #define ext4_std_error(sb, errno) \ do { \ if ((errno)) \ diff --git a/include/linux/ext4_fs_i.h b/include/linux/ext4_fs_i.h index 4377d249d378..d5508d3cf290 100644 --- a/include/linux/ext4_fs_i.h +++ b/include/linux/ext4_fs_i.h @@ -158,6 +158,10 @@ struct ext4_inode_info { * struct timespec i_{a,c,m}time in the generic inode. */ struct timespec i_crtime; + + /* mballoc */ + struct list_head i_prealloc_list; + spinlock_t i_prealloc_lock; }; #endif /* _LINUX_EXT4_FS_I */ diff --git a/include/linux/ext4_fs_sb.h b/include/linux/ext4_fs_sb.h index 38a47ec06df9..abaae2c8cccf 100644 --- a/include/linux/ext4_fs_sb.h +++ b/include/linux/ext4_fs_sb.h @@ -91,6 +91,58 @@ struct ext4_sb_info { unsigned long s_ext_blocks; unsigned long s_ext_extents; #endif + + /* for buddy allocator */ + struct ext4_group_info ***s_group_info; + struct inode *s_buddy_cache; + long s_blocks_reserved; + spinlock_t s_reserve_lock; + struct list_head s_active_transaction; + struct list_head s_closed_transaction; + struct list_head s_committed_transaction; + spinlock_t s_md_lock; + tid_t s_last_transaction; + unsigned short *s_mb_offsets, *s_mb_maxs; + + /* tunables */ + unsigned long s_stripe; + unsigned long s_mb_stream_request; + unsigned long s_mb_max_to_scan; + unsigned long s_mb_min_to_scan; + unsigned long s_mb_stats; + unsigned long s_mb_order2_reqs; + unsigned long s_mb_group_prealloc; + /* where last allocation was done - for stream allocation */ + unsigned long s_mb_last_group; + unsigned long s_mb_last_start; + + /* history to debug policy */ + struct ext4_mb_history *s_mb_history; + int s_mb_history_cur; + int s_mb_history_max; + int s_mb_history_num; + struct proc_dir_entry *s_mb_proc; + spinlock_t s_mb_history_lock; + int s_mb_history_filter; + + /* stats for buddy allocator */ + spinlock_t s_mb_pa_lock; + atomic_t s_bal_reqs; /* number of reqs with len > 1 */ + atomic_t s_bal_success; /* we found long enough chunks */ + atomic_t s_bal_allocated; /* in blocks */ + atomic_t s_bal_ex_scanned; /* total extents scanned */ + atomic_t s_bal_goals; /* goal hits */ + atomic_t s_bal_breaks; /* too long searches */ + atomic_t s_bal_2orders; /* 2^order hits */ + spinlock_t s_bal_lock; + unsigned long s_mb_buddies_generated; + unsigned long long s_mb_generation_time; + atomic_t s_mb_lost_chunks; + atomic_t s_mb_preallocated; + atomic_t s_mb_discarded; + + /* locality groups */ + struct ext4_locality_group *s_locality_groups; }; #endif /* _LINUX_EXT4_FS_SB */ -- cgit v1.2.3 From 7b7510662f4d05ddcc45d435769860e73e6aa20e Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Mon, 28 Jan 2008 23:58:27 -0500 Subject: jbd2: add lockdep support Ported from similar patch for the jbd layer. Signed-off-by: Mingming Cao Signed-off-by: "Theodore Ts'o" --- include/linux/jbd2.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 98a2bc5d3e3f..2cbf6fdb1799 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -418,6 +418,10 @@ struct handle_s unsigned int h_sync: 1; /* sync-on-close */ unsigned int h_jdata: 1; /* force data journaling */ unsigned int h_aborted: 1; /* fatal error on handle */ + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map h_lockdep_map; +#endif }; -- cgit v1.2.3 From 6dd06c9fbe025f542bce4cdb91790c0f91962722 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 29 Jan 2008 17:13:22 -0500 Subject: module: make module_address_lookup safe module_address_lookup releases preemption then returns a pointer into the module space. The only user (kallsyms) copies the result, so just do that under the preempt disable. Signed-off-by: Rusty Russell --- include/linux/module.h | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index c97bdb7eb957..aedc06be1de8 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -446,11 +446,14 @@ static inline void __module_get(struct module *module) __mod ? __mod->name : "kernel"; \ }) -/* For kallsyms to ask for address resolution. NULL means not found. */ -const char *module_address_lookup(unsigned long addr, - unsigned long *symbolsize, - unsigned long *offset, - char **modname); +/* For kallsyms to ask for address resolution. namebuf should be at + * least KSYM_NAME_LEN long: a pointer to namebuf is returned if + * found, otherwise NULL. */ +char *module_address_lookup(unsigned long addr, + unsigned long *symbolsize, + unsigned long *offset, + char **modname, + char *namebuf); int lookup_module_symbol_name(unsigned long addr, char *symname); int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name); @@ -516,10 +519,11 @@ static inline void module_put(struct module *module) #define module_name(mod) "kernel" /* For kallsyms to ask for address resolution. NULL means not found. */ -static inline const char *module_address_lookup(unsigned long addr, - unsigned long *symbolsize, - unsigned long *offset, - char **modname) +static inline char *module_address_lookup(unsigned long addr, + unsigned long *symbolsize, + unsigned long *offset, + char **modname, + char *namebuf) { return NULL; } -- cgit v1.2.3 From 023ccde109b995bb99862bf9c87efd006b1d1885 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 29 Jan 2008 14:08:06 +0100 Subject: block: fix warning on compile with CONFIG_BLOCK struct io_context was not defined, just add an empty forward decl. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 71e7a847dffc..e18d4192f6e8 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -825,6 +825,7 @@ static inline void exit_io_context(void) { } +struct io_context; static inline int put_io_context(struct io_context *ioc) { return 1; -- cgit v1.2.3 From 7da975a231ae8c11593fd79d1083215321be213a Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Tue, 29 Jan 2008 19:12:06 +0100 Subject: Fix blktrace compile warning request_queue_t is deprecated Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 06dadba349ac..cfc3147e5cf9 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -282,10 +282,10 @@ static inline void blk_add_trace_remap(struct request_queue *q, struct bio *bio, __blk_add_trace(bt, from, bio->bi_size, bio->bi_rw, BLK_TA_REMAP, !bio_flagged(bio, BIO_UPTODATE), sizeof(r), &r); } -extern int blk_trace_setup(request_queue_t *q, char *name, dev_t dev, +extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, char __user *arg); -extern int blk_trace_startstop(request_queue_t *q, int start); -extern int blk_trace_remove(request_queue_t *q); +extern int blk_trace_startstop(struct request_queue *q, int start); +extern int blk_trace_remove(struct request_queue *q); #else /* !CONFIG_BLK_DEV_IO_TRACE */ #define blk_trace_ioctl(bdev, cmd, arg) (-ENOTTY) -- cgit v1.2.3 From d621d35e576aa20a0ddae8022c3810f38357c8ff Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Tue, 29 Jan 2008 08:43:36 -0500 Subject: SELinux: Enable dynamic enable/disable of the network access checks This patch introduces a mechanism for checking when labeled IPsec or SECMARK are in use by keeping introducing a configuration reference counter for each subsystem. In the case of labeled IPsec, whenever a labeled SA or SPD entry is created the labeled IPsec/XFRM reference count is increased and when the entry is removed it is decreased. In the case of SECMARK, when a SECMARK target is created the reference count is increased and later decreased when the target is removed. These reference counters allow SELinux to quickly determine if either of these subsystems are enabled. NetLabel already has a similar mechanism which provides the netlbl_enabled() function. This patch also renames the selinux_relabel_packet_permission() function to selinux_secmark_relabel_packet_permission() as the original name and description were misleading in that they referenced a single packet label which is not the case. Signed-off-by: Paul Moore Signed-off-by: James Morris --- include/linux/selinux.h | 45 +++++++++++++++++++++++++++++++++++++-------- 1 file changed, 37 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/selinux.h b/include/linux/selinux.h index 6080f73fc85f..8c2cc4c02526 100644 --- a/include/linux/selinux.h +++ b/include/linux/selinux.h @@ -120,16 +120,35 @@ void selinux_get_task_sid(struct task_struct *tsk, u32 *sid); int selinux_string_to_sid(char *str, u32 *sid); /** - * selinux_relabel_packet_permission - check permission to relabel a packet - * @sid: ID value to be applied to network packet (via SECMARK, most likely) + * selinux_secmark_relabel_packet_permission - secmark permission check + * @sid: SECMARK ID value to be applied to network packet * - * Returns 0 if the current task is allowed to label packets with the - * supplied security ID. Note that it is implicit that the packet is always - * being relabeled from the default unlabled value, and that the access - * control decision is made in the AVC. + * Returns 0 if the current task is allowed to set the SECMARK label of + * packets with the supplied security ID. Note that it is implicit that + * the packet is always being relabeled from the default unlabeled value, + * and that the access control decision is made in the AVC. */ -int selinux_relabel_packet_permission(u32 sid); +int selinux_secmark_relabel_packet_permission(u32 sid); +/** + * selinux_secmark_refcount_inc - increments the secmark use counter + * + * SELinux keeps track of the current SECMARK targets in use so it knows + * when to apply SECMARK label access checks to network packets. This + * function incements this reference count to indicate that a new SECMARK + * target has been configured. + */ +void selinux_secmark_refcount_inc(void); + +/** + * selinux_secmark_refcount_dec - decrements the secmark use counter + * + * SELinux keeps track of the current SECMARK targets in use so it knows + * when to apply SECMARK label access checks to network packets. This + * function decements this reference count to indicate that one of the + * existing SECMARK targets has been removed/flushed. + */ +void selinux_secmark_refcount_dec(void); #else static inline int selinux_audit_rule_init(u32 field, u32 op, @@ -184,11 +203,21 @@ static inline int selinux_string_to_sid(const char *str, u32 *sid) return 0; } -static inline int selinux_relabel_packet_permission(u32 sid) +static inline int selinux_secmark_relabel_packet_permission(u32 sid) { return 0; } +static inline void selinux_secmark_refcount_inc(void) +{ + return; +} + +static inline void selinux_secmark_refcount_dec(void) +{ + return; +} + #endif /* CONFIG_SECURITY_SELINUX */ #endif /* _LINUX_SELINUX_H */ -- cgit v1.2.3 From 13541b3adad2dc2f56761c5193c2b88db3597f0e Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Tue, 29 Jan 2008 08:44:23 -0500 Subject: NetLabel: Add auditing to the static labeling mechanism This patch adds auditing support to the NetLabel static labeling mechanism. Signed-off-by: Paul Moore Signed-off-by: James Morris --- 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 c68781692838..bdd6f5de5fc4 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -115,6 +115,8 @@ #define AUDIT_MAC_IPSEC_ADDSPD 1413 /* Not used */ #define AUDIT_MAC_IPSEC_DELSPD 1414 /* Not used */ #define AUDIT_MAC_IPSEC_EVENT 1415 /* Audit an IPSec event */ +#define AUDIT_MAC_UNLBL_STCADD 1416 /* NetLabel: add a static label */ +#define AUDIT_MAC_UNLBL_STCDEL 1417 /* NetLabel: del a static label */ #define AUDIT_FIRST_KERN_ANOM_MSG 1700 #define AUDIT_LAST_KERN_ANOM_MSG 1799 -- cgit v1.2.3 From acee478afc6ff7e1b8852d9a4dca1ff36021414d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 22 Jan 2008 17:13:07 -0500 Subject: NFS: Clean up the write request locking. Ensure that we set/clear NFS_PAGE_TAG_LOCKED when the nfs_page is hashed. Signed-off-by: Trond Myklebust --- include/linux/nfs_page.h | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 30dbcc185e69..a1676e19e491 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -83,6 +83,7 @@ extern void nfs_pageio_complete(struct nfs_pageio_descriptor *desc); extern void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *, pgoff_t); extern int nfs_wait_on_request(struct nfs_page *); extern void nfs_unlock_request(struct nfs_page *req); +extern int nfs_set_page_tag_locked(struct nfs_page *req); extern void nfs_clear_page_tag_locked(struct nfs_page *req); @@ -95,18 +96,6 @@ nfs_lock_request_dontget(struct nfs_page *req) return !test_and_set_bit(PG_BUSY, &req->wb_flags); } -/* - * Lock the page of an asynchronous request and take a reference - */ -static inline int -nfs_lock_request(struct nfs_page *req) -{ - if (test_and_set_bit(PG_BUSY, &req->wb_flags)) - return 0; - kref_get(&req->wb_kref); - return 1; -} - /** * nfs_list_add_request - Insert a request into a list * @req: request -- cgit v1.2.3 From ef818a28fac9bd214e676986d8301db0582b92a9 Mon Sep 17 00:00:00 2001 From: Steve Dickson Date: Thu, 8 Nov 2007 04:05:04 -0500 Subject: NFS: Stop sillyname renames and unmounts from racing Added an active/deactive mechanism to the nfs_server structure allowing async operations to hold off umount until the operations are done. Signed-off-by: Steve Dickson Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 0cac49bc0955..9f949b587684 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -3,6 +3,9 @@ #include #include +#include + +#include struct nfs_iostats; @@ -110,6 +113,9 @@ struct nfs_server { filesystem */ #endif void (*destroy)(struct nfs_server *); + + atomic_t active; /* Keep trace of any activity to this server */ + wait_queue_head_t active_wq; /* Wait for any activity to stop */ }; /* Server capabilities */ -- cgit v1.2.3 From 66af1e558538137080615e7ad6d1f2f80862de01 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 6 Nov 2007 10:18:36 -0500 Subject: SUNRPC: Fix a race in xs_tcp_state_change() When scheduling the autoclose RPC call, we want to ensure that we don't race against the test_bit() call in xprt_clear_locked(). Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 30b17b3bc1a9..6f524a9e7fd0 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -246,6 +246,7 @@ struct rpc_rqst * xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid); void xprt_complete_rqst(struct rpc_task *task, int copied); void xprt_release_rqst_cong(struct rpc_task *task); void xprt_disconnect(struct rpc_xprt *xprt); +void xprt_force_disconnect(struct rpc_xprt *xprt); /* * Reserved bit positions in xprt->state -- cgit v1.2.3 From 3b948ae5be5e22532584113e2e02029519bbad8f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 5 Nov 2007 17:42:39 -0500 Subject: SUNRPC: Allow the client to detect if the TCP connection is closed Add an xprt->state bit to enable the TCP ->state_change() method to signal whether or not the TCP connection is in the process of closing down. This will to be used by the reconnection logic in a separate patch. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 6f524a9e7fd0..afb9e6ad7fe0 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -257,6 +257,7 @@ void xprt_force_disconnect(struct rpc_xprt *xprt); #define XPRT_CLOSE_WAIT (3) #define XPRT_BOUND (4) #define XPRT_BINDING (5) +#define XPRT_CLOSING (6) static inline void xprt_set_connected(struct rpc_xprt *xprt) { -- cgit v1.2.3 From 62da3b24880bccd4ffc32cf8d9a7e23fab475bdd Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 6 Nov 2007 18:44:20 -0500 Subject: SUNRPC: Rename xprt_disconnect() xprt_disconnect() should really only be called when the transport shutdown is completed, and it is time to wake up any pending tasks. Rename it to xprt_disconnect_done() in order to reflect the semantical change. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index afb9e6ad7fe0..2554cd2b016f 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -245,7 +245,7 @@ void xprt_adjust_cwnd(struct rpc_task *task, int result); struct rpc_rqst * xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid); void xprt_complete_rqst(struct rpc_task *task, int copied); void xprt_release_rqst_cong(struct rpc_task *task); -void xprt_disconnect(struct rpc_xprt *xprt); +void xprt_disconnect_done(struct rpc_xprt *xprt); void xprt_force_disconnect(struct rpc_xprt *xprt); /* -- cgit v1.2.3 From 84115e1cd4a3614c4e566d4cce31381dce3dbef9 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 14 Jul 2007 15:39:59 -0400 Subject: SUNRPC: Cleanup of rpc_task initialisation Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 2 +- include/linux/sunrpc/sched.h | 14 +++++++++----- 2 files changed, 10 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index d9d5c5ad826c..ec9704181f94 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -126,7 +126,7 @@ int rpcb_register(u32, u32, int, unsigned short, int *); int rpcb_getport_sync(struct sockaddr_in *, __u32, __u32, int); void rpcb_getport_async(struct rpc_task *); -void rpc_call_setup(struct rpc_task *, struct rpc_message *, int); +void rpc_call_setup(struct rpc_task *, const struct rpc_message *, int); int rpc_call_async(struct rpc_clnt *clnt, struct rpc_message *msg, int flags, const struct rpc_call_ops *tk_ops, diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 8ea077db0099..9efe045fc376 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -117,6 +117,13 @@ struct rpc_call_ops { void (*rpc_release)(void *); }; +struct rpc_task_setup { + struct rpc_clnt *rpc_client; + const struct rpc_message *rpc_message; + const struct rpc_call_ops *callback_ops; + void *callback_data; + unsigned short flags; +}; /* * RPC task flags @@ -236,13 +243,10 @@ struct rpc_wait_queue { /* * Function prototypes */ -struct rpc_task *rpc_new_task(struct rpc_clnt *, int flags, - const struct rpc_call_ops *ops, void *data); +struct rpc_task *rpc_new_task(const struct rpc_task_setup *); struct rpc_task *rpc_run_task(struct rpc_clnt *clnt, int flags, const struct rpc_call_ops *ops, void *data); -void rpc_init_task(struct rpc_task *task, struct rpc_clnt *clnt, - int flags, const struct rpc_call_ops *ops, - void *data); +void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *); void rpc_put_task(struct rpc_task *); void rpc_exit_task(struct rpc_task *); void rpc_release_calldata(const struct rpc_call_ops *, void *); -- cgit v1.2.3 From c970aa85e71bd581726c42df843f6f129db275ac Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 14 Jul 2007 15:39:59 -0400 Subject: SUNRPC: Clean up rpc_run_task Make it use the new task initialiser structure instead of acting as a wrapper. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 9efe045fc376..d974421d7647 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -244,8 +244,7 @@ struct rpc_wait_queue { * Function prototypes */ struct rpc_task *rpc_new_task(const struct rpc_task_setup *); -struct rpc_task *rpc_run_task(struct rpc_clnt *clnt, int flags, - const struct rpc_call_ops *ops, void *data); +struct rpc_task *rpc_run_task(const struct rpc_task_setup *); void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *); void rpc_put_task(struct rpc_task *); void rpc_exit_task(struct rpc_task *); -- cgit v1.2.3 From 3ff7576ddac06c3d07089e241b40826d24bbf1ac Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 14 Jul 2007 15:40:00 -0400 Subject: SUNRPC: Clean up the initialisation of priority queue scheduling info. We want the default scheduling priority (priority == 0) to remain RPC_PRIORITY_NORMAL. Also ensure that the priority wait queue scheduling is per process id instead of sometimes being per thread, and sometimes being per inode. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index d974421d7647..c9444fdc23ac 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -56,8 +56,6 @@ struct rpc_task { __u8 tk_garb_retry; __u8 tk_cred_retry; - unsigned long tk_cookie; /* Cookie for batching tasks */ - /* * timeout_fn to be executed by timer bottom half * callback to be executed after waking up @@ -78,7 +76,6 @@ struct rpc_task { struct timer_list tk_timer; /* kernel timer */ unsigned long tk_timeout; /* timeout for rpc_sleep() */ unsigned short tk_flags; /* misc flags */ - unsigned char tk_priority : 2;/* Task priority */ unsigned long tk_runstate; /* Task run status */ struct workqueue_struct *tk_workqueue; /* Normally rpciod, but could * be any workqueue @@ -94,6 +91,9 @@ struct rpc_task { unsigned long tk_start; /* RPC task init timestamp */ long tk_rtt; /* round-trip time (jiffies) */ + pid_t tk_owner; /* Process id for batching tasks */ + unsigned char tk_priority : 2;/* Task priority */ + #ifdef RPC_DEBUG unsigned short tk_pid; /* debugging aid */ #endif @@ -123,6 +123,7 @@ struct rpc_task_setup { const struct rpc_call_ops *callback_ops; void *callback_data; unsigned short flags; + signed char priority; }; /* @@ -187,10 +188,10 @@ struct rpc_task_setup { * Note: if you change these, you must also change * the task initialization definitions below. */ -#define RPC_PRIORITY_LOW 0 -#define RPC_PRIORITY_NORMAL 1 -#define RPC_PRIORITY_HIGH 2 -#define RPC_NR_PRIORITY (RPC_PRIORITY_HIGH+1) +#define RPC_PRIORITY_LOW (-1) +#define RPC_PRIORITY_NORMAL (0) +#define RPC_PRIORITY_HIGH (1) +#define RPC_NR_PRIORITY (1 + RPC_PRIORITY_HIGH - RPC_PRIORITY_LOW) /* * RPC synchronization objects @@ -198,7 +199,7 @@ struct rpc_task_setup { struct rpc_wait_queue { spinlock_t lock; struct list_head tasks[RPC_NR_PRIORITY]; /* task queue for each priority level */ - unsigned long cookie; /* cookie of last task serviced */ + pid_t owner; /* process id of last task serviced */ unsigned char maxpriority; /* maximum priority (0 if queue is not a priority queue) */ unsigned char priority; /* current priority */ unsigned char count; /* # task groups remaining serviced so far */ -- cgit v1.2.3 From 77de2c590ec72828156d85fa13a96db87301cc68 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 25 Oct 2007 18:40:21 -0400 Subject: SUNRPC: Add a helper rpc_call_start() that initialises task->tk_action Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index ec9704181f94..c79f2edf0323 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -127,7 +127,7 @@ int rpcb_getport_sync(struct sockaddr_in *, __u32, __u32, int); void rpcb_getport_async(struct rpc_task *); void rpc_call_setup(struct rpc_task *, const struct rpc_message *, int); - +void rpc_call_start(struct rpc_task *); int rpc_call_async(struct rpc_clnt *clnt, struct rpc_message *msg, int flags, const struct rpc_call_ops *tk_ops, void *calldata); -- cgit v1.2.3 From bdc7f021f3a1fade77adf3c2d7f65690566fddfe Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 14 Jul 2007 15:40:00 -0400 Subject: NFS: Clean up the (commit|read|write)_setup() callback routines Move the common code for setting up the nfs_write_data and nfs_read_data structures into fs/nfs/read.c, fs/nfs/write.c and fs/nfs/direct.c. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index daab252f2e5c..6b213a64b15f 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -816,11 +816,11 @@ struct nfs_rpc_ops { struct nfs_pathconf *); int (*set_capabilities)(struct nfs_server *, struct nfs_fh *); __be32 *(*decode_dirent)(__be32 *, struct nfs_entry *, int plus); - void (*read_setup) (struct nfs_read_data *); + void (*read_setup) (struct nfs_read_data *, struct rpc_message *); int (*read_done) (struct rpc_task *, struct nfs_read_data *); - void (*write_setup) (struct nfs_write_data *, int how); + void (*write_setup) (struct nfs_write_data *, struct rpc_message *); int (*write_done) (struct rpc_task *, struct nfs_write_data *); - void (*commit_setup) (struct nfs_write_data *, int how); + void (*commit_setup) (struct nfs_write_data *, struct rpc_message *); int (*commit_done) (struct rpc_task *, struct nfs_write_data *); int (*file_open) (struct inode *, struct file *); int (*file_release) (struct inode *, struct file *); -- cgit v1.2.3 From b5627943ab6fabbc13a45d92683363a3d08a249f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 25 Oct 2007 18:42:21 -0400 Subject: SUNRPC: Remove the now unused function rpc_call_setup() Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index c79f2edf0323..4fc268ab6f3e 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -126,7 +126,6 @@ int rpcb_register(u32, u32, int, unsigned short, int *); int rpcb_getport_sync(struct sockaddr_in *, __u32, __u32, int); void rpcb_getport_async(struct rpc_task *); -void rpc_call_setup(struct rpc_task *, const struct rpc_message *, int); void rpc_call_start(struct rpc_task *); int rpc_call_async(struct rpc_clnt *clnt, struct rpc_message *msg, int flags, const struct rpc_call_ops *tk_ops, -- cgit v1.2.3 From e8f5d77c8029ff8f5dcd1dfc133aac0bbbffd92b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 25 Oct 2007 18:42:53 -0400 Subject: SUNRPC: allow the caller of rpc_run_task to preallocate the struct rpc_task Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index c9444fdc23ac..60a05c71637e 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -118,6 +118,7 @@ struct rpc_call_ops { }; struct rpc_task_setup { + struct rpc_task *task; struct rpc_clnt *rpc_client; const struct rpc_message *rpc_message; const struct rpc_call_ops *callback_ops; -- cgit v1.2.3 From 47fe064831a2a949f6c1e0086f61a105e99ea867 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 25 Oct 2007 18:42:55 -0400 Subject: SUNRPC: Unexport rpc_init_task() and rpc_execute() Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 60a05c71637e..23481a5e1f53 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -247,7 +247,6 @@ struct rpc_wait_queue { */ struct rpc_task *rpc_new_task(const struct rpc_task_setup *); struct rpc_task *rpc_run_task(const struct rpc_task_setup *); -void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *); void rpc_put_task(struct rpc_task *); void rpc_exit_task(struct rpc_task *); void rpc_release_calldata(const struct rpc_call_ops *, void *); -- cgit v1.2.3 From c087567d3ffb2c7c61e091982e6ca45478394f1a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 18 Jul 2007 18:32:38 -0400 Subject: SUNRPC: Remove the obsolete RPC_WAITQ macro Now that we've killed off all the users. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 23481a5e1f53..ce3d1b132729 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -217,29 +217,6 @@ struct rpc_wait_queue { * performance of NFS operations such as read/write. */ #define RPC_BATCH_COUNT 16 - -#ifndef RPC_DEBUG -# define RPC_WAITQ_INIT(var,qname) { \ - .lock = __SPIN_LOCK_UNLOCKED(var.lock), \ - .tasks = { \ - [0] = LIST_HEAD_INIT(var.tasks[0]), \ - [1] = LIST_HEAD_INIT(var.tasks[1]), \ - [2] = LIST_HEAD_INIT(var.tasks[2]), \ - }, \ - } -#else -# define RPC_WAITQ_INIT(var,qname) { \ - .lock = __SPIN_LOCK_UNLOCKED(var.lock), \ - .tasks = { \ - [0] = LIST_HEAD_INIT(var.tasks[0]), \ - [1] = LIST_HEAD_INIT(var.tasks[1]), \ - [2] = LIST_HEAD_INIT(var.tasks[2]), \ - }, \ - .name = qname, \ - } -#endif -# define RPC_WAITQ(var,qname) struct rpc_wait_queue var = RPC_WAITQ_INIT(var,qname) - #define RPC_IS_PRIORITY(q) ((q)->maxpriority > 0) /* -- cgit v1.2.3 From bfc69a456642a51c89dfd8e5184468857cb44f32 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 15 Oct 2007 18:18:29 -0400 Subject: NFS: define a function to update nfsi->cache_change_attribute Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 2d15d4aac094..7095aaa087d8 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -366,6 +366,7 @@ extern const struct inode_operations nfs3_dir_inode_operations; extern const struct file_operations nfs_dir_operations; extern struct dentry_operations nfs_dentry_operations; +extern void nfs_force_lookup_revalidate(struct inode *dir); extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr); extern int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags); extern void nfs_access_zap_cache(struct inode *inode); -- cgit v1.2.3 From 40c553193df41920de659f0446e5d214c862e827 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 14 Dec 2007 14:56:07 -0500 Subject: NFS: Remove the redundant nfs_client->cl_nfsversion We can get the same information from the rpc_ops structure instead. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 9f949b587684..97b325756667 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -17,7 +17,6 @@ struct nfs_client { int cl_cons_state; /* current construction state (-ve: init error) */ #define NFS_CS_READY 0 /* ready to be used */ #define NFS_CS_INITING 1 /* busy initialising */ - int cl_nfsversion; /* NFS protocol version */ unsigned long cl_res_state; /* NFS resources state */ #define NFS_CS_CALLBACK 1 /* - callback started */ #define NFS_CS_IDMAP 2 /* - idmap started */ -- cgit v1.2.3 From 0fb2b7e945f55a8317e5f58db7c068aab5b825a1 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 10 Dec 2007 14:56:46 -0500 Subject: SUNRPC: Move universal address definitions to global header Universal addresses are defined in RFC 1833 and clarified in RFC 3530. We need to use them in several places in the NFS and RPC clients, so move the relevant definition and block comment to an appropriate global include file. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/msg_prot.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h index c4beb5775111..70df4f1d8847 100644 --- a/include/linux/sunrpc/msg_prot.h +++ b/include/linux/sunrpc/msg_prot.h @@ -152,5 +152,44 @@ typedef __be32 rpc_fraghdr; */ #define RPCBIND_MAXNETIDLEN (4u) +/* + * Universal addresses are introduced in RFC 1833 and further spelled + * out in RFC 3530. RPCBIND_MAXUADDRLEN defines a maximum byte length + * of a universal address for use in allocating buffers and character + * arrays. + * + * Quoting RFC 3530, section 2.2: + * + * For TCP over IPv4 and for UDP over IPv4, the format of r_addr is the + * US-ASCII string: + * + * h1.h2.h3.h4.p1.p2 + * + * The prefix, "h1.h2.h3.h4", is the standard textual form for + * representing an IPv4 address, which is always four octets long. + * Assuming big-endian ordering, h1, h2, h3, and h4, are respectively, + * the first through fourth octets each converted to ASCII-decimal. + * Assuming big-endian ordering, p1 and p2 are, respectively, the first + * and second octets each converted to ASCII-decimal. For example, if a + * host, in big-endian order, has an address of 0x0A010307 and there is + * a service listening on, in big endian order, port 0x020F (decimal + * 527), then the complete universal address is "10.1.3.7.2.15". + * + * ... + * + * For TCP over IPv6 and for UDP over IPv6, the format of r_addr is the + * US-ASCII string: + * + * x1:x2:x3:x4:x5:x6:x7:x8.p1.p2 + * + * The suffix "p1.p2" is the service port, and is computed the same way + * as with universal addresses for TCP and UDP over IPv4. The prefix, + * "x1:x2:x3:x4:x5:x6:x7:x8", is the standard textual form for + * representing an IPv6 address as defined in Section 2.2 of [RFC2373]. + * Additionally, the two alternative forms specified in Section 2.2 of + * [RFC2373] are also acceptable. + */ +#define RPCBIND_MAXUADDRLEN (56u) + #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_MSGPROT_H_ */ -- cgit v1.2.3 From cc38bac3a0093b3b7928efc6ff8e9faf9e75f41d Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 10 Dec 2007 14:56:54 -0500 Subject: NFS: Ensure NFSv4 SETCLIENTID send buffer is large enough Ensure that the RPC buffer size specified for NFSv4 SETCLIENTID procedures matches what we are encoding into the buffer. See the definition of struct nfs4_setclientid {} and the encode_setclientid() function. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 6b213a64b15f..d8e395d0c7c9 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -666,16 +666,17 @@ struct nfs4_rename_res { struct nfs_fattr * new_fattr; }; +#define NFS4_SETCLIENTID_NAMELEN (48) struct nfs4_setclientid { - const nfs4_verifier * sc_verifier; /* request */ + const nfs4_verifier * sc_verifier; unsigned int sc_name_len; - char sc_name[48]; /* request */ - u32 sc_prog; /* request */ + char sc_name[NFS4_SETCLIENTID_NAMELEN]; + u32 sc_prog; unsigned int sc_netid_len; - char sc_netid[4]; /* request */ + char sc_netid[RPCBIND_MAXNETIDLEN]; unsigned int sc_uaddr_len; - char sc_uaddr[24]; /* request */ - u32 sc_cb_ident; /* request */ + char sc_uaddr[RPCBIND_MAXUADDRLEN]; + u32 sc_cb_ident; }; struct nfs4_statfs_arg { -- cgit v1.2.3 From 4392f2592297876967191238a341667a6d4fc456 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 10 Dec 2007 14:57:01 -0500 Subject: NFS: Increase size of cl_ipaddr field to hold IPv6 addresses The nfs_client's cl_ipaddr field needs to be larger to hold strings that represent IPv6 addresses. Signed-off-by: Chuck Lever Cc: Aurelien Charbon Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 97b325756667..0b3dcba3d97d 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -64,7 +64,7 @@ struct nfs_client { /* Our own IP address, as a null-terminated string. * This is used to generate the clientid, and the callback address. */ - char cl_ipaddr[16]; + char cl_ipaddr[48]; unsigned char cl_id_uniquifier; #endif }; -- cgit v1.2.3 From 6e4cffd7b2cf86022dcf9cceeb63f16ff852caa1 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 10 Dec 2007 14:58:15 -0500 Subject: NFS: Expand server address storage in nfs_client struct Prepare for managing larger addresses in the NFS client by widening the nfs_client struct's cl_addr field. Signed-off-by: Chuck Lever Cc: Aurelien Charbon (Modified to work with the new parameters for nfs_alloc_client) Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 0b3dcba3d97d..912cfe84ea86 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -21,7 +21,8 @@ struct nfs_client { #define NFS_CS_CALLBACK 1 /* - callback started */ #define NFS_CS_IDMAP 2 /* - idmap started */ #define NFS_CS_RENEWD 3 /* - renewd started */ - struct sockaddr_in cl_addr; /* server identifier */ + struct sockaddr_storage cl_addr; /* server identifier */ + size_t cl_addrlen; char * cl_hostname; /* hostname of server */ struct list_head cl_share_link; /* link in global client list */ struct list_head cl_superblocks; /* List of nfs_server structs */ -- cgit v1.2.3 From 69dd716c5ffd89f5ba14ffb871d633ecea74d13a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 14 Dec 2007 14:56:07 -0500 Subject: NFSv4: Add socket proto argument to setclientid Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index d8e395d0c7c9..d342ae5c76ab 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -666,7 +666,7 @@ struct nfs4_rename_res { struct nfs_fattr * new_fattr; }; -#define NFS4_SETCLIENTID_NAMELEN (48) +#define NFS4_SETCLIENTID_NAMELEN (56) struct nfs4_setclientid { const nfs4_verifier * sc_verifier; unsigned int sc_name_len; -- cgit v1.2.3 From 2881ae74e68ecfe3b32a90936e5d93a9ba598c3a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 20 Dec 2007 16:03:54 -0500 Subject: SUNRPC: Clean up the transport timeout initialisation Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 2554cd2b016f..a00d4a4ba6ee 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -202,11 +202,6 @@ struct xprt_class { char name[32]; }; -/* - * Transport operations used by ULPs - */ -void xprt_set_timeout(struct rpc_timeout *to, unsigned int retr, unsigned long incr); - /* * Generic internal transport functions */ -- cgit v1.2.3 From ba7392bb37cb12781890f45d7ddee1618e33a036 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 20 Dec 2007 16:03:55 -0500 Subject: SUNRPC: Add support for per-client timeout values In order to be able to support setting the timeo and retrans parameters on a per-mountpoint basis, we move the rpc_timeout structure into the rpc_clnt. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 4 +++- include/linux/sunrpc/xprt.h | 3 +-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 4fc268ab6f3e..51a338189a23 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -46,6 +46,7 @@ struct rpc_clnt { cl_autobind : 1;/* use getport() */ struct rpc_rtt * cl_rtt; /* RTO estimator data */ + const struct rpc_timeout *cl_timeout; /* Timeout strategy */ int cl_nodelen; /* nodename length */ char cl_nodename[UNX_MAXNODENAME]; @@ -54,6 +55,7 @@ struct rpc_clnt { struct dentry * cl_dentry; /* inode */ struct rpc_clnt * cl_parent; /* Points to parent of clones */ struct rpc_rtt cl_rtt_default; + struct rpc_timeout cl_timeout_default; struct rpc_program * cl_program; char cl_inline_name[32]; }; @@ -99,7 +101,7 @@ struct rpc_create_args { struct sockaddr *address; size_t addrsize; struct sockaddr *saddress; - struct rpc_timeout *timeout; + const struct rpc_timeout *timeout; char *servername; struct rpc_program *program; u32 version; diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index a00d4a4ba6ee..c3364d88d83e 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -120,7 +120,7 @@ struct rpc_xprt { struct kref kref; /* Reference count */ struct rpc_xprt_ops * ops; /* transport methods */ - struct rpc_timeout timeout; /* timeout parms */ + const struct rpc_timeout *timeout; /* timeout parms */ struct sockaddr_storage addr; /* server address */ size_t addrlen; /* size of server address */ int prot; /* IP protocol */ @@ -191,7 +191,6 @@ struct xprt_create { struct sockaddr * srcaddr; /* optional local address */ struct sockaddr * dstaddr; /* remote peer address */ size_t addrlen; - struct rpc_timeout * timeout; /* optional timeout parameters */ }; struct xprt_class { -- cgit v1.2.3 From 331702337f2b2e7cef40366ee207a25604df4671 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 20 Dec 2007 16:03:59 -0500 Subject: NFS: Support per-mountpoint timeout parameters. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 912cfe84ea86..d15c9487b8f1 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -29,8 +29,6 @@ struct nfs_client { struct rpc_clnt * cl_rpcclient; const struct nfs_rpc_ops *rpc_ops; /* NFS protocol vector */ - unsigned long retrans_timeo; /* retransmit timeout */ - unsigned int retrans_count; /* number of retransmit tries */ #ifdef CONFIG_NFS_V4 u64 cl_clientid; /* constant */ -- cgit v1.2.3 From 59dca3b28cb915745019d4f4c27d97b6b6ab12c6 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 3 Jan 2008 16:29:06 -0500 Subject: NFS: Fix the 'proto=' mount option Currently, if you have a server mounted using networking protocol, you cannot specify a different value using the 'proto=' option on another mountpoint. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index d15c9487b8f1..b5ba5f79485d 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -29,6 +29,7 @@ struct nfs_client { struct rpc_clnt * cl_rpcclient; const struct nfs_rpc_ops *rpc_ops; /* NFS protocol vector */ + int cl_proto; /* Network transport protocol */ #ifdef CONFIG_NFS_V4 u64 cl_clientid; /* constant */ -- cgit v1.2.3 From b454ae906085cf7774fb4756746680c9b03b6f84 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 7 Jan 2008 18:34:48 -0500 Subject: SUNRPC: fewer conditionals in the format_ip_address routines Clean up: have the set up routines explicitly pass the strings to be used for the transport name and NETID. This removes a number of conditionals and dependencies on rpc_xprt.prot, which is overloaded. Tighten up type checking on the address_strings array while we're at it. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 2 +- include/linux/sunrpc/xprt.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 51a338189a23..5a13da2573b0 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -143,7 +143,7 @@ void rpc_setbufsize(struct rpc_clnt *, unsigned int, unsigned int); size_t rpc_max_payload(struct rpc_clnt *); void rpc_force_rebind(struct rpc_clnt *); size_t rpc_peeraddr(struct rpc_clnt *, struct sockaddr *, size_t); -char * rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t); +const char *rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t); #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_CLNT_H */ diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index c3364d88d83e..b3ff9a815e6f 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -183,7 +183,7 @@ struct rpc_xprt { bklog_u; /* backlog queue utilization */ } stat; - char * address_strings[RPC_DISPLAY_MAX]; + const char *address_strings[RPC_DISPLAY_MAX]; }; struct xprt_create { -- cgit v1.2.3 From 52c4044d00fe703eb3fb18e0d8dfd1c196eb28be Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 11 Jan 2008 17:09:44 -0500 Subject: NLM: Introduce external nlm_host set-up and tear-down functions We would like to remove the per-lock-operation nlm_lookup_host() call from nlmclnt_proc(). The new architecture pins an nlm_host structure to each NFS client superblock that has the "lock" mount option set. The NFS client passes in the pinned nlm_host structure during each call to nlmclnt_proc(). NFS client unmount processing "puts" the nlm_host so it can be garbage- collected later. This patch introduces externally callable NLM functions that handle mount-time nlm_host set up and tear-down. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/lockd/bind.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockd/bind.h b/include/linux/lockd/bind.h index 6f1637c61e10..ad5402f5456b 100644 --- a/include/linux/lockd/bind.h +++ b/include/linux/lockd/bind.h @@ -35,6 +35,13 @@ extern struct nlmsvc_binding * nlmsvc_ops; /* * Functions exported by the lockd module */ +extern struct nlm_host *nlmclnt_init(const char *server_name, + const struct sockaddr *server_address, + size_t server_addrlen, + unsigned short protocol, + u32 nfs_version); +extern void nlmclnt_done(struct nlm_host *host); + extern int nlmclnt_proc(struct inode *, int, struct file_lock *); extern int lockd_up(int proto); extern void lockd_down(void); -- cgit v1.2.3 From 9289e7f91add1c09c3ec8571a2080f7507730b8d Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 11 Jan 2008 17:09:52 -0500 Subject: NFS: Invoke nlmclnt_init during NFS mount processing Cache an appropriate nlm_host structure in the NFS client's mount point metadata for later use. Note that there is no need to set NFS_MOUNT_NONLM in the error case -- if nfs_start_lockd() returns a non-zero value, its callers ensure that the mount request fails outright. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index b5ba5f79485d..3423c6761bf7 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -8,6 +8,7 @@ #include struct nfs_iostats; +struct nlm_host; /* * The nfs_client identifies our client state to the server. @@ -80,6 +81,7 @@ struct nfs_server { struct list_head master_link; /* link in master servers list */ struct rpc_clnt * client; /* RPC client handle */ struct rpc_clnt * client_acl; /* ACL RPC client handle */ + struct nlm_host *nlm_host; /* NLM client handle */ struct nfs_iostats * io_stats; /* I/O statistics */ struct backing_dev_info backing_dev_info; atomic_long_t writeback; /* number of writeback pages */ -- cgit v1.2.3 From 1093a60ef34bb12010fe7ea4b780bee1c57cfbbe Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 11 Jan 2008 17:09:59 -0500 Subject: NLM/NFS: Use cached nlm_host when calling nlmclnt_proc() Now that each NFS mount point caches its own nlm_host structure, it can be passed to nlmclnt_proc() for each lock request. By pinning an nlm_host for each mount point, we trade the overhead of looking up or creating a fresh nlm_host struct during every NLM procedure call for a little extra memory. We also restrict the nlmclnt_proc symbol to limit the use of this call to in-tree modules. Note that nlm_lookup_host() (just removed from the client's per-request NLM processing) could also trigger an nlm_host garbage collection. Now client-side nlm_host garbage collection occurs only during NFS mount processing. Since the NFS client now holds a reference on these nlm_host structures, they wouldn't have been affected by garbage collection anyway. Given that nlm_lookup_host() reorders the global nlm_host chain after every successful lookup, and that a garbage collection could be triggered during the call, we've removed a significant amount of per-NLM-request CPU processing overhead. Sidebar: there are only a few remaining references to the internals of NFS inodes in the client-side NLM code. The only references I found are related to extracting or comparing the inode's file handle via NFS_FH(). One is in nlmclnt_grant(); the other is in nlmclnt_setlockargs(). Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/lockd/bind.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockd/bind.h b/include/linux/lockd/bind.h index ad5402f5456b..73368075af03 100644 --- a/include/linux/lockd/bind.h +++ b/include/linux/lockd/bind.h @@ -42,7 +42,8 @@ extern struct nlm_host *nlmclnt_init(const char *server_name, u32 nfs_version); extern void nlmclnt_done(struct nlm_host *host); -extern int nlmclnt_proc(struct inode *, int, struct file_lock *); +extern int nlmclnt_proc(struct nlm_host *host, int cmd, + struct file_lock *fl); extern int lockd_up(int proto); extern void lockd_down(void); -- cgit v1.2.3 From 883bb163f84e0a54b29846c61621f52db3f27393 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 15 Jan 2008 16:04:20 -0500 Subject: NLM: Introduce an arguments structure for nlmclnt_init() Clean up: pass 5 arguments to nlmclnt_init() in a structure similar to the new nfs_client_initdata structure. Signed-off-by: Chuck Lever --- include/linux/lockd/bind.h | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/bind.h b/include/linux/lockd/bind.h index 73368075af03..3d25bcd139d1 100644 --- a/include/linux/lockd/bind.h +++ b/include/linux/lockd/bind.h @@ -32,14 +32,23 @@ struct nlmsvc_binding { extern struct nlmsvc_binding * nlmsvc_ops; +/* + * Similar to nfs_client_initdata, but without the NFS-specific + * rpc_ops field. + */ +struct nlmclnt_initdata { + const char *hostname; + const struct sockaddr *address; + size_t addrlen; + unsigned short protocol; + u32 nfs_version; +}; + /* * Functions exported by the lockd module */ -extern struct nlm_host *nlmclnt_init(const char *server_name, - const struct sockaddr *server_address, - size_t server_addrlen, - unsigned short protocol, - u32 nfs_version); + +extern struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init); extern void nlmclnt_done(struct nlm_host *host); extern int nlmclnt_proc(struct nlm_host *host, int cmd, -- cgit v1.2.3 From c0e07cb68db353c0ffbb0f82401cf6d79c253aed Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 14 Jan 2008 12:32:05 -0500 Subject: NFS: NFS version number is unsigned RPC protocol version numbers are unsigned. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index d342ae5c76ab..f301d0b8babc 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -774,7 +774,7 @@ struct nfs_access_entry; * RPC procedure vector for NFSv2/NFSv3 demuxing */ struct nfs_rpc_ops { - int version; /* Protocol version */ + u32 version; /* Protocol version */ struct dentry_operations *dentry_ops; const struct inode_operations *dir_inode_ops; const struct inode_operations *file_inode_ops; -- cgit v1.2.3 From f1ec08cb9492cab579f85f9d937c79788b1dfde3 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 14 Jan 2008 15:11:53 -0500 Subject: SUNRPC: Use appropriate argument types in rpcb client Clean up: Follow recommendations of Chapter 5 of Documentation/CodingStyle and use "u32" instead of "__u32" for types in definitions that are not shared with user space. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 5a13da2573b0..3e9addc741c1 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -125,7 +125,7 @@ void rpc_shutdown_client(struct rpc_clnt *); void rpc_release_client(struct rpc_clnt *); int rpcb_register(u32, u32, int, unsigned short, int *); -int rpcb_getport_sync(struct sockaddr_in *, __u32, __u32, int); +int rpcb_getport_sync(struct sockaddr_in *, u32, u32, int); void rpcb_getport_async(struct rpc_task *); void rpc_call_start(struct rpc_task *); -- cgit v1.2.3 From 3a10c30acc4821ca000b52ed0edafd0d3bf26a52 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Wed, 23 Jan 2008 08:58:59 +0200 Subject: nfs: obliterate NFS_FLAGS macro use NFS_I(inode)->flags instead Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 7095aaa087d8..9e7c24a2aca9 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -214,8 +214,7 @@ static inline struct nfs_inode *NFS_I(struct inode *inode) (S_ISDIR(inode->i_mode)? NFS_SERVER(inode)->acdirmax \ : NFS_SERVER(inode)->acregmax) -#define NFS_FLAGS(inode) (NFS_I(inode)->flags) -#define NFS_STALE(inode) (test_bit(NFS_INO_STALE, &NFS_FLAGS(inode))) +#define NFS_STALE(inode) (test_bit(NFS_INO_STALE, &NFS_I(inode)->flags)) #define NFS_FILEID(inode) (NFS_I(inode)->fileid) @@ -237,7 +236,7 @@ static inline int nfs_server_capable(struct inode *inode, int cap) static inline int NFS_USE_READDIRPLUS(struct inode *inode) { - return test_bit(NFS_INO_ADVISE_RDPLUS, &NFS_FLAGS(inode)); + return test_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); } static inline void nfs_set_verifier(struct dentry * dentry, unsigned long verf) -- cgit v1.2.3 From 99fadcd76465842c014c88b8c9c19b457e9debc0 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Wed, 23 Jan 2008 08:59:08 +0200 Subject: nfs: convert NFS_*(inode) helpers to static inline Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 76 ++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 58 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 9e7c24a2aca9..099ddb4481c0 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -196,27 +196,67 @@ struct nfs_inode { #define NFS_INO_STALE (2) /* possible stale inode */ #define NFS_INO_ACL_LRU_SET (3) /* Inode is on the LRU list */ -static inline struct nfs_inode *NFS_I(struct inode *inode) +static inline struct nfs_inode *NFS_I(const struct inode *inode) { return container_of(inode, struct nfs_inode, vfs_inode); } -#define NFS_SB(s) ((struct nfs_server *)(s->s_fs_info)) - -#define NFS_FH(inode) (&NFS_I(inode)->fh) -#define NFS_SERVER(inode) (NFS_SB(inode->i_sb)) -#define NFS_CLIENT(inode) (NFS_SERVER(inode)->client) -#define NFS_PROTO(inode) (NFS_SERVER(inode)->nfs_client->rpc_ops) -#define NFS_COOKIEVERF(inode) (NFS_I(inode)->cookieverf) -#define NFS_MINATTRTIMEO(inode) \ - (S_ISDIR(inode->i_mode)? NFS_SERVER(inode)->acdirmin \ - : NFS_SERVER(inode)->acregmin) -#define NFS_MAXATTRTIMEO(inode) \ - (S_ISDIR(inode->i_mode)? NFS_SERVER(inode)->acdirmax \ - : NFS_SERVER(inode)->acregmax) - -#define NFS_STALE(inode) (test_bit(NFS_INO_STALE, &NFS_I(inode)->flags)) - -#define NFS_FILEID(inode) (NFS_I(inode)->fileid) + +static inline struct nfs_server *NFS_SB(const struct super_block *s) +{ + return (struct nfs_server *)(s->s_fs_info); +} + +static inline struct nfs_fh *NFS_FH(const struct inode *inode) +{ + return &NFS_I(inode)->fh; +} + +static inline struct nfs_server *NFS_SERVER(const struct inode *inode) +{ + return NFS_SB(inode->i_sb); +} + +static inline struct rpc_clnt *NFS_CLIENT(const struct inode *inode) +{ + return NFS_SERVER(inode)->client; +} + +static inline const struct nfs_rpc_ops *NFS_PROTO(const struct inode *inode) +{ + return NFS_SERVER(inode)->nfs_client->rpc_ops; +} + +static inline __be32 *NFS_COOKIEVERF(const struct inode *inode) +{ + return NFS_I(inode)->cookieverf; +} + +static inline unsigned NFS_MINATTRTIMEO(const struct inode *inode) +{ + struct nfs_server *nfss = NFS_SERVER(inode); + return S_ISDIR(inode->i_mode) ? nfss->acdirmin : nfss->acregmin; +} + +static inline unsigned NFS_MAXATTRTIMEO(const struct inode *inode) +{ + struct nfs_server *nfss = NFS_SERVER(inode); + return S_ISDIR(inode->i_mode) ? nfss->acdirmax : nfss->acregmax; +} + +static inline int NFS_STALE(const struct inode *inode) +{ + return test_bit(NFS_INO_STALE, &NFS_I(inode)->flags); +} + +static inline __u64 NFS_FILEID(const struct inode *inode) +{ + return NFS_I(inode)->fileid; +} + +static inline void set_nfs_fileid(struct inode *inode, __u64 fileid) +{ + NFS_I(inode)->fileid = fileid; +} static inline void nfs_mark_for_revalidate(struct inode *inode) { -- cgit v1.2.3 From a6fa8e5a6172a5a5bc06ed04f34e50b36c978127 Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Wed, 30 Jan 2008 13:30:00 +0100 Subject: time: clean hungarian notation from timers Clean up hungarian notation from timer code. Signed-off-by: Pavel Machek Cc: john stultz Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/timer.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timer.h b/include/linux/timer.h index 78cf899b4409..de0e71359ede 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -5,7 +5,7 @@ #include #include -struct tvec_t_base_s; +struct tvec_base; struct timer_list { struct list_head entry; @@ -14,7 +14,7 @@ struct timer_list { void (*function)(unsigned long); unsigned long data; - struct tvec_t_base_s *base; + struct tvec_base *base; #ifdef CONFIG_TIMER_STATS void *start_site; char start_comm[16]; @@ -22,7 +22,7 @@ struct timer_list { #endif }; -extern struct tvec_t_base_s boot_tvec_bases; +extern struct tvec_base boot_tvec_bases; #define TIMER_INITIALIZER(_function, _expires, _data) { \ .function = (_function), \ -- cgit v1.2.3 From 1d76c2622813fbc692b0d323028cfef9ee36051a Mon Sep 17 00:00:00 2001 From: Atsushi Nemoto Date: Wed, 30 Jan 2008 13:30:01 +0100 Subject: clocksource: make CLOCKSOURCE_MASK bullet-proof Signed-off-by: Atsushi Nemoto Cc: john stultz Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/clocksource.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 107787aacb64..07b42153de24 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -103,7 +103,7 @@ struct clocksource { #define CLOCK_SOURCE_VALID_FOR_HRES 0x20 /* simplify initialization of mask field */ -#define CLOCKSOURCE_MASK(bits) (cycle_t)(bits<64 ? ((1ULL< Date: Wed, 30 Jan 2008 13:30:02 +0100 Subject: clocksource: add unregister function to disable unusable clocksources On x86 the PIT might become an unusable clocksource. Add an unregister function to provide a possibilty to remove the PIT from the list of available clock sources. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/clocksource.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 07b42153de24..85778a4b1209 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -215,6 +215,7 @@ static inline void clocksource_calculate_interval(struct clocksource *c, /* used to install a new clocksource */ extern int clocksource_register(struct clocksource*); +extern void clocksource_unregister(struct clocksource*); extern struct clocksource* clocksource_get_next(void); extern void clocksource_change_rating(struct clocksource *cs, int rating); extern void clocksource_resume(void); -- cgit v1.2.3 From e3f37a54f690d3e64995ea7ecea08c5ab3070faf Mon Sep 17 00:00:00 2001 From: Balaji Rao Date: Wed, 30 Jan 2008 13:30:03 +0100 Subject: x86: assign IRQs to HPET timers The userspace API for the HPET (see Documentation/hpet.txt) did not work. The HPET_IE_ON ioctl was failing as there was no IRQ assigned to the timer device. This patch fixes it by allocating IRQs to timer blocks in the HPET. arch/x86/kernel/hpet.c | 13 +++++-------- drivers/char/hpet.c | 45 ++++++++++++++++++++++++++++++++++++++------- include/linux/hpet.h | 2 +- 3 files changed, 44 insertions(+), 16 deletions(-) Signed-off-by: Balaji Rao Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/hpet.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hpet.h b/include/linux/hpet.h index 707f7cb9e795..e3c0b2aa944c 100644 --- a/include/linux/hpet.h +++ b/include/linux/hpet.h @@ -64,7 +64,7 @@ struct hpet { */ #define Tn_INT_ROUTE_CAP_MASK (0xffffffff00000000ULL) -#define Tn_INI_ROUTE_CAP_SHIFT (32UL) +#define Tn_INT_ROUTE_CAP_SHIFT (32UL) #define Tn_FSB_INT_DELCAP_MASK (0x8000UL) #define Tn_FSB_INT_DELCAP_SHIFT (15) #define Tn_FSB_EN_CNF_MASK (0x4000UL) -- cgit v1.2.3 From 6378ddb592158db4b42197f1bc8666228800e379 Mon Sep 17 00:00:00 2001 From: Venki Pallipadi Date: Wed, 30 Jan 2008 13:30:04 +0100 Subject: time: track accurate idle time with tick_sched.idle_sleeptime Current idle time in kstat is based on jiffies and is coarse grained. tick_sched.idle_sleeptime is making some attempt to keep track of idle time in a fine grained manner. But, it is not handling the time spent in interrupts fully. Make tick_sched.idle_sleeptime accurate with respect to time spent on handling interrupts and also add tick_sched.idle_lastupdate, which keeps track of last time when idle_sleeptime was updated. This statistics will be crucial for cpufreq-ondemand governor, which can shed some conservative gaurd band that is uses today while setting the frequency. The ondemand changes that uses the exact idle time is coming soon. Signed-off-by: Venkatesh Pallipadi Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/tick.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index f4a1395e05ff..0fadf95debe1 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -51,8 +51,10 @@ struct tick_sched { unsigned long idle_jiffies; unsigned long idle_calls; unsigned long idle_sleeps; + int idle_active; ktime_t idle_entrytime; ktime_t idle_sleeptime; + ktime_t idle_lastupdate; ktime_t sleep_length; unsigned long last_jiffies; unsigned long next_jiffies; @@ -103,6 +105,8 @@ extern void tick_nohz_stop_sched_tick(void); extern void tick_nohz_restart_sched_tick(void); extern void tick_nohz_update_jiffies(void); extern ktime_t tick_nohz_get_sleep_length(void); +extern void tick_nohz_stop_idle(int cpu); +extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); # else static inline void tick_nohz_stop_sched_tick(void) { } static inline void tick_nohz_restart_sched_tick(void) { } @@ -113,6 +117,8 @@ static inline ktime_t tick_nohz_get_sleep_length(void) return len; } +static inline void tick_nohz_stop_idle(int cpu) { } +static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return 0; } # endif /* !NO_HZ */ #endif -- cgit v1.2.3 From c202f298de59c17c0a9799dc0e1b9e0629347935 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 30 Jan 2008 13:30:08 +0100 Subject: x86: clean up arch/x86/ia32/sys_ia32.c White space and coding style clenaup. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/compat.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 0e69d2cf14aa..ba29d4c59643 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -191,6 +191,10 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct compat_timeval __user *tvp); +asmlinkage long compat_sys_wait4(compat_pid_t pid, + compat_uint_t *stat_addr, int options, + struct compat_rusage *ru); + #define BITS_PER_COMPAT_LONG (8*sizeof(compat_long_t)) #define BITS_TO_COMPAT_LONGS(bits) \ -- cgit v1.2.3 From 70a20025632ca320316b5068326784d07c8ff351 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 30 Jan 2008 13:30:18 +0100 Subject: x86: move pmtmr related declarations Move more stuff out of proto.h Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/acpi_pmtmr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi_pmtmr.h b/include/linux/acpi_pmtmr.h index 1d0ef1ae8036..7e3d2859be50 100644 --- a/include/linux/acpi_pmtmr.h +++ b/include/linux/acpi_pmtmr.h @@ -25,6 +25,8 @@ static inline u32 acpi_pm_read_early(void) return acpi_pm_read_verified() & ACPI_PM_MASK; } +extern void pmtimer_wait(unsigned); + #else static inline u32 acpi_pm_read_early(void) -- cgit v1.2.3 From 02456c708eab4515121e5e581422fa3be14368d1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 30 Jan 2008 13:30:27 +0100 Subject: x86: nuke a ton of dead hpet code No users, just ballast Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/hpet.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hpet.h b/include/linux/hpet.h index e3c0b2aa944c..9cd94bfd07e5 100644 --- a/include/linux/hpet.h +++ b/include/linux/hpet.h @@ -115,9 +115,6 @@ static inline void hpet_reserve_timer(struct hpet_data *hd, int timer) } int hpet_alloc(struct hpet_data *); -int hpet_register(struct hpet_task *, int); -int hpet_unregister(struct hpet_task *); -int hpet_control(struct hpet_task *, unsigned int, unsigned long); #endif /* __KERNEL__ */ -- cgit v1.2.3 From c9cce83dd1d59f52e2c8f8c7d265ba4854c40785 Mon Sep 17 00:00:00 2001 From: Bernhard Walle Date: Wed, 30 Jan 2008 13:30:32 +0100 Subject: x86: remove extern declarations for code, data, bss resources This patch removes the extern struct resource declarations for data_resource, code_resource and bss_resource on x86 and declares that three structures as static as done on other architectures like IA64. On i386, these structures are moved to setup_32.c (from e820_32.c) because that's code that is not specific to e820 and also required on EFI systems. That makes the "extern" reference superfluous. On x86_64, data_resource, code_resource and bss_resource are passed to e820_reserve_resources() as arguments just as done on i386 and IA64. That also avoids the "extern" reference and it's possible to make it static. Signed-off-by: Bernhard Walle Cc: "Luck, Tony" Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ioport.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 6187a8567bc7..605d237364d2 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -8,6 +8,7 @@ #ifndef _LINUX_IOPORT_H #define _LINUX_IOPORT_H +#ifndef __ASSEMBLY__ #include #include /* @@ -153,4 +154,5 @@ extern struct resource * __devm_request_region(struct device *dev, extern void __devm_release_region(struct device *dev, struct resource *parent, resource_size_t start, resource_size_t n); +#endif /* __ASSEMBLY__ */ #endif /* _LINUX_IOPORT_H */ -- cgit v1.2.3 From fb7fa8f1741c91f6c6e958762155abe9339476ca Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Wed, 30 Jan 2008 13:30:47 +0100 Subject: ptrace: arch_has_single_step This defines the new macro arch_has_single_step() in linux/ptrace.h, a default for when asm/ptrace.h does not define it. It declares the new user_enable_single_step and user_disable_single_step functions. This is not used yet, but paves the way to harmonize on this interface for the arch-specific calls on all machines. Signed-off-by: Roland McGrath Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ptrace.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 3ea5750a0f7e..8f06c6fb22a5 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -129,6 +129,52 @@ int generic_ptrace_pokedata(struct task_struct *tsk, long addr, long data); #define force_successful_syscall_return() do { } while (0) #endif +/* + * should define the following things inside #ifdef __KERNEL__. + * + * These do-nothing inlines are used when the arch does not + * implement single-step. The kerneldoc comments are here + * to document the interface for all arch definitions. + */ + +#ifndef arch_has_single_step +/** + * arch_has_single_step - does this CPU support user-mode single-step? + * + * If this is defined, then there must be function declarations or + * inlines for user_enable_single_step() and user_disable_single_step(). + * arch_has_single_step() should evaluate to nonzero iff the machine + * supports instruction single-step for user mode. + * It can be a constant or it can test a CPU feature bit. + */ +#define arch_has_single_step() (0) + +/** + * user_enable_single_step - single-step in user-mode task + * @task: either current or a task stopped in %TASK_TRACED + * + * This can only be called when arch_has_single_step() has returned nonzero. + * Set @task so that when it returns to user mode, it will trap after the + * next single instruction executes. + */ +static inline void user_enable_single_step(struct task_struct *task) +{ + BUG(); /* This can never be called. */ +} + +/** + * user_disable_single_step - cancel user-mode single-step + * @task: either current or a task stopped in %TASK_TRACED + * + * Clear @task of the effects of user_enable_single_step(). This can + * be called whether or not user_enable_single_step() was ever called + * on @task, and even if arch_has_single_step() returned zero. + */ +static inline void user_disable_single_step(struct task_struct *task) +{ +} +#endif /* arch_has_single_step */ + #endif #endif -- cgit v1.2.3 From dc802c2d2e66e2d1544e023bfd4be6cdee48d57b Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Wed, 30 Jan 2008 13:30:53 +0100 Subject: ptrace: arch_has_block_step This defines the new macro arch_has_block_step() in linux/ptrace.h, a default for when asm/ptrace.h does not define it. This is the analog of arch_has_single_step() for step-until-branch on machines that have it. It declares the new user_enable_block_step function, which goes with the existing user_enable_single_step and user_disable_single_step. This is not used yet, but paves the way to harmonize on this interface for the arch-specific calls on all machines. Signed-off-by: Roland McGrath Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ptrace.h | 37 +++++++++++++++++++++++++++++++++---- 1 file changed, 33 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 8f06c6fb22a5..1febc541dda5 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -155,7 +155,8 @@ int generic_ptrace_pokedata(struct task_struct *tsk, long addr, long data); * * This can only be called when arch_has_single_step() has returned nonzero. * Set @task so that when it returns to user mode, it will trap after the - * next single instruction executes. + * next single instruction executes. If arch_has_block_step() is defined, + * this must clear the effects of user_enable_block_step() too. */ static inline void user_enable_single_step(struct task_struct *task) { @@ -166,15 +167,43 @@ static inline void user_enable_single_step(struct task_struct *task) * user_disable_single_step - cancel user-mode single-step * @task: either current or a task stopped in %TASK_TRACED * - * Clear @task of the effects of user_enable_single_step(). This can - * be called whether or not user_enable_single_step() was ever called - * on @task, and even if arch_has_single_step() returned zero. + * Clear @task of the effects of user_enable_single_step() and + * user_enable_block_step(). This can be called whether or not either + * of those was ever called on @task, and even if arch_has_single_step() + * returned zero. */ static inline void user_disable_single_step(struct task_struct *task) { } #endif /* arch_has_single_step */ +#ifndef arch_has_block_step +/** + * arch_has_block_step - does this CPU support user-mode block-step? + * + * If this is defined, then there must be a function declaration or inline + * for user_enable_block_step(), and arch_has_single_step() must be defined + * too. arch_has_block_step() should evaluate to nonzero iff the machine + * supports step-until-branch for user mode. It can be a constant or it + * can test a CPU feature bit. + */ +#define arch_has_single_step() (0) + +/** + * user_enable_block_step - step until branch in user-mode task + * @task: either current or a task stopped in %TASK_TRACED + * + * This can only be called when arch_has_block_step() has returned nonzero, + * and will never be called when single-instruction stepping is being used. + * Set @task so that when it returns to user mode, it will trap after the + * next branch or trap taken. + */ +static inline void user_enable_block_step(struct task_struct *task) +{ + BUG(); /* This can never be called. */ +} +#endif /* arch_has_block_step */ + #endif #endif -- cgit v1.2.3 From 5b88abbf770a0e1975c668743100f42934f385e8 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Wed, 30 Jan 2008 13:30:53 +0100 Subject: ptrace: generic PTRACE_SINGLEBLOCK This makes ptrace_request handle PTRACE_SINGLEBLOCK along with PTRACE_CONT et al. The new generic code makes use of the arch_has_block_step macro and generic entry points on machines that define them. [ mingo@elte.hu: bugfix ] Signed-off-by: Roland McGrath Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ptrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 1febc541dda5..515bff053de8 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -187,7 +187,7 @@ static inline void user_disable_single_step(struct task_struct *task) * supports step-until-branch for user mode. It can be a constant or it * can test a CPU feature bit. */ -#define arch_has_single_step() (0) +#define arch_has_block_step() (0) /** * user_enable_block_step - step until branch in user-mode task -- cgit v1.2.3 From 5548fecdff5617ba3a2f09f0e585e1ac6e1bd25c Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Wed, 30 Jan 2008 13:30:55 +0100 Subject: x86: clean up bitops-related warnings Add casts to appropriate places to silence spurious bitops warnings. Signed-off-by: Jeremy Fitzhardinge Cc: Andi Kleen Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/thread_info.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 9c4ad755d7e5..dfbdfb9836f4 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -42,27 +42,27 @@ extern long do_no_restart_syscall(struct restart_block *parm); static inline void set_ti_thread_flag(struct thread_info *ti, int flag) { - set_bit(flag,&ti->flags); + set_bit(flag, (unsigned long *)&ti->flags); } static inline void clear_ti_thread_flag(struct thread_info *ti, int flag) { - clear_bit(flag,&ti->flags); + clear_bit(flag, (unsigned long *)&ti->flags); } static inline int test_and_set_ti_thread_flag(struct thread_info *ti, int flag) { - return test_and_set_bit(flag,&ti->flags); + return test_and_set_bit(flag, (unsigned long *)&ti->flags); } static inline int test_and_clear_ti_thread_flag(struct thread_info *ti, int flag) { - return test_and_clear_bit(flag,&ti->flags); + return test_and_clear_bit(flag, (unsigned long *)&ti->flags); } static inline int test_ti_thread_flag(struct thread_info *ti, int flag) { - return test_bit(flag,&ti->flags); + return test_bit(flag, (unsigned long *)&ti->flags); } #define set_thread_flag(flag) \ -- cgit v1.2.3 From 2355188570790930718fb72444cddc2959039d9d Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 30 Jan 2008 13:31:10 +0100 Subject: x86: avoid build warning fix this build warning: include/asm/topology_32.h: In function 'node_to_first_cpu': include/asm/topology_32.h:66: warning: unused variable 'mask' Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/cpumask.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 85bd790c201e..7047f58306a7 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -218,8 +218,8 @@ int __first_cpu(const cpumask_t *srcp); int __next_cpu(int n, const cpumask_t *srcp); #define next_cpu(n, src) __next_cpu((n), &(src)) #else -#define first_cpu(src) 0 -#define next_cpu(n, src) 1 +#define first_cpu(src) ({ (void)(src); 0; }) +#define next_cpu(n, src) ({ (void)(src); 1; }) #endif #define cpumask_of_cpu(cpu) \ -- cgit v1.2.3 From 95c354fe9f7d6decc08a92aa26eb233ecc2155bf Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 30 Jan 2008 13:31:20 +0100 Subject: spinlock: lockbreak cleanup The break_lock data structure and code for spinlocks is quite nasty. Not only does it double the size of a spinlock but it changes locking to a potentially less optimal trylock. Put all of that under CONFIG_GENERIC_LOCKBREAK, and introduce a __raw_spin_is_contended that uses the lock data itself to determine whether there are waiters on the lock, to be used if CONFIG_GENERIC_LOCKBREAK is not set. Rename need_lockbreak to spin_needbreak, make it use spin_is_contended to decouple it from the spinlock implementation, and make it typesafe (rwlocks do not have any need_lockbreak sites -- why do they even get bloated up with that break_lock then?). Signed-off-by: Nick Piggin Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 21 +++++++-------------- include/linux/spinlock.h | 6 ++++++ include/linux/spinlock_types.h | 4 ++-- include/linux/spinlock_up.h | 2 ++ 4 files changed, 17 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2d0546e884ea..9d4797609aa5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1922,23 +1922,16 @@ extern int cond_resched_softirq(void); /* * Does a critical section need to be broken due to another - * task waiting?: + * task waiting?: (technically does not depend on CONFIG_PREEMPT, + * but a general need for low latency) */ -#if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP) -# define need_lockbreak(lock) ((lock)->break_lock) -#else -# define need_lockbreak(lock) 0 -#endif - -/* - * Does a critical section need to be broken due to another - * task waiting or preemption being signalled: - */ -static inline int lock_need_resched(spinlock_t *lock) +static inline int spin_needbreak(spinlock_t *lock) { - if (need_lockbreak(lock) || need_resched()) - return 1; +#ifdef CONFIG_PREEMPT + return spin_is_contended(lock); +#else return 0; +#endif } /* diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index c376f3b36c89..124449733c55 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -120,6 +120,12 @@ do { \ #define spin_is_locked(lock) __raw_spin_is_locked(&(lock)->raw_lock) +#ifdef CONFIG_GENERIC_LOCKBREAK +#define spin_is_contended(lock) ((lock)->break_lock) +#else +#define spin_is_contended(lock) __raw_spin_is_contended(&(lock)->raw_lock) +#endif + /** * spin_unlock_wait - wait until the spinlock gets unlocked * @lock: the spinlock in question. diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h index f6a3a951b79e..68d88f71f1a2 100644 --- a/include/linux/spinlock_types.h +++ b/include/linux/spinlock_types.h @@ -19,7 +19,7 @@ typedef struct { raw_spinlock_t raw_lock; -#if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP) +#ifdef CONFIG_GENERIC_LOCKBREAK unsigned int break_lock; #endif #ifdef CONFIG_DEBUG_SPINLOCK @@ -35,7 +35,7 @@ typedef struct { typedef struct { raw_rwlock_t raw_lock; -#if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP) +#ifdef CONFIG_GENERIC_LOCKBREAK unsigned int break_lock; #endif #ifdef CONFIG_DEBUG_SPINLOCK diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h index ea54c4c9a4ec..938234c4a996 100644 --- a/include/linux/spinlock_up.h +++ b/include/linux/spinlock_up.h @@ -64,6 +64,8 @@ static inline void __raw_spin_unlock(raw_spinlock_t *lock) # define __raw_spin_trylock(lock) ({ (void)(lock); 1; }) #endif /* DEBUG_SPINLOCK */ +#define __raw_spin_is_contended(lock) (((void)(lock), 0)) + #define __raw_read_can_lock(lock) (((void)(lock), 1)) #define __raw_write_can_lock(lock) (((void)(lock), 1)) -- cgit v1.2.3 From cae4595764cb3b08f6517e99bac1e3862854b1a1 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Wed, 30 Jan 2008 13:31:23 +0100 Subject: x86: make __{save,restore}_processor_state static .. allowing to remove their declarations from a global include file (the symbols don't exist for anything but x86). Likewise for 64-bits' fix_processor_context(), just that that one was properly declared in an arch-specific header. Signed-off-by: Jan Beulich Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/suspend.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 4360e0816956..40280df2a3db 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -211,9 +211,6 @@ static inline int hibernate(void) { return -ENOSYS; } #ifdef CONFIG_PM_SLEEP void save_processor_state(void); void restore_processor_state(void); -struct saved_context; -void __save_processor_state(struct saved_context *ctxt); -void __restore_processor_state(struct saved_context *ctxt); /* kernel/power/main.c */ extern struct blocking_notifier_head pm_chain_head; -- cgit v1.2.3 From bdf88217b70dbb18c4ee27a6c497286e040a6705 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Wed, 30 Jan 2008 13:31:44 +0100 Subject: x86: user_regset header The new header defines the types struct user_regset and struct user_regset_view, with some associated declarations. This new set of interfaces will become the standard way for arch code to expose user-mode machine-specific state. A single set of entry points into arch code can do all the low-level work in one place to fill the needs of core dumps, ptrace, and any other user-mode debugging facilities that might come along in the future. For existing arch code to adapt to the user_regset interfaces, each arch can work from the code it already has to support core files and ptrace. The formats you want for user_regset are the core file formats. The only wrinkle in adapting old ptrace implementation code as user_regset get and set functions is that these functions can be called on current as well as on another task_struct that is stopped and switched out as for ptrace. For some kinds of machine state, you may have to load it directly from CPU registers or otherwise differently for current than for another thread. (Your core dump support already handles this in elf_core_copy_regs for current and elf_core_copy_task_regs for other tasks, so just check there.) The set function should also be made to work on current in case that entails some special cases, though this was never required before for ptrace. Adding this flexibility covers the arch needs to open the door to more sophisticated new debugging facilities that don't always need to context-switch to do every little thing. The copyin/copyout helper functions (in a later patch) relieve the arch code of most of the cumbersome details of the flexible get/set interfaces. Signed-off-by: Roland McGrath Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/regset.h | 206 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 206 insertions(+) create mode 100644 include/linux/regset.h (limited to 'include/linux') diff --git a/include/linux/regset.h b/include/linux/regset.h new file mode 100644 index 000000000000..85d0fb0a014d --- /dev/null +++ b/include/linux/regset.h @@ -0,0 +1,206 @@ +/* + * User-mode machine state access + * + * Copyright (C) 2007 Red Hat, Inc. All rights reserved. + * + * This copyrighted material is made available to anyone wishing to use, + * modify, copy, or redistribute it subject to the terms and conditions + * of the GNU General Public License v.2. + * + * Red Hat Author: Roland McGrath. + */ + +#ifndef _LINUX_REGSET_H +#define _LINUX_REGSET_H 1 + +#include +#include +struct task_struct; +struct user_regset; + + +/** + * user_regset_active_fn - type of @active function in &struct user_regset + * @target: thread being examined + * @regset: regset being examined + * + * Return -%ENODEV if not available on the hardware found. + * Return %0 if no interesting state in this thread. + * Return >%0 number of @size units of interesting state. + * Any get call fetching state beyond that number will + * see the default initialization state for this data, + * so a caller that knows what the default state is need + * not copy it all out. + * This call is optional; the pointer is %NULL if there + * is no inexpensive check to yield a value < @n. + */ +typedef int user_regset_active_fn(struct task_struct *target, + const struct user_regset *regset); + +/** + * user_regset_get_fn - type of @get function in &struct user_regset + * @target: thread being examined + * @regset: regset being examined + * @pos: offset into the regset data to access, in bytes + * @count: amount of data to copy, in bytes + * @kbuf: if not %NULL, a kernel-space pointer to copy into + * @ubuf: if @kbuf is %NULL, a user-space pointer to copy into + * + * Fetch register values. Return %0 on success; -%EIO or -%ENODEV + * are usual failure returns. The @pos and @count values are in + * bytes, but must be properly aligned. If @kbuf is non-null, that + * buffer is used and @ubuf is ignored. If @kbuf is %NULL, then + * ubuf gives a userland pointer to access directly, and an -%EFAULT + * return value is possible. + */ +typedef int user_regset_get_fn(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf); + +/** + * user_regset_set_fn - type of @set function in &struct user_regset + * @target: thread being examined + * @regset: regset being examined + * @pos: offset into the regset data to access, in bytes + * @count: amount of data to copy, in bytes + * @kbuf: if not %NULL, a kernel-space pointer to copy from + * @ubuf: if @kbuf is %NULL, a user-space pointer to copy from + * + * Store register values. Return %0 on success; -%EIO or -%ENODEV + * are usual failure returns. The @pos and @count values are in + * bytes, but must be properly aligned. If @kbuf is non-null, that + * buffer is used and @ubuf is ignored. If @kbuf is %NULL, then + * ubuf gives a userland pointer to access directly, and an -%EFAULT + * return value is possible. + */ +typedef int user_regset_set_fn(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf); + +/** + * user_regset_writeback_fn - type of @writeback function in &struct user_regset + * @target: thread being examined + * @regset: regset being examined + * @immediate: zero if writeback at completion of next context switch is OK + * + * This call is optional; usually the pointer is %NULL. When + * provided, there is some user memory associated with this regset's + * hardware, such as memory backing cached register data on register + * window machines; the regset's data controls what user memory is + * used (e.g. via the stack pointer value). + * + * Write register data back to user memory. If the @immediate flag + * is nonzero, it must be written to the user memory so uaccess or + * access_process_vm() can see it when this call returns; if zero, + * then it must be written back by the time the task completes a + * context switch (as synchronized with wait_task_inactive()). + * Return %0 on success or if there was nothing to do, -%EFAULT for + * a memory problem (bad stack pointer or whatever), or -%EIO for a + * hardware problem. + */ +typedef int user_regset_writeback_fn(struct task_struct *target, + const struct user_regset *regset, + int immediate); + +/** + * struct user_regset - accessible thread CPU state + * @n: Number of slots (registers). + * @size: Size in bytes of a slot (register). + * @align: Required alignment, in bytes. + * @bias: Bias from natural indexing. + * @core_note_type: ELF note @n_type value used in core dumps. + * @get: Function to fetch values. + * @set: Function to store values. + * @active: Function to report if regset is active, or %NULL. + * @writeback: Function to write data back to user memory, or %NULL. + * + * This data structure describes a machine resource we call a register set. + * This is part of the state of an individual thread, not necessarily + * actual CPU registers per se. A register set consists of a number of + * similar slots, given by @n. Each slot is @size bytes, and aligned to + * @align bytes (which is at least @size). + * + * These functions must be called only on the current thread or on a + * thread that is in %TASK_STOPPED or %TASK_TRACED state, that we are + * guaranteed will not be woken up and return to user mode, and that we + * have called wait_task_inactive() on. (The target thread always might + * wake up for SIGKILL while these functions are working, in which case + * that thread's user_regset state might be scrambled.) + * + * The @pos argument must be aligned according to @align; the @count + * argument must be a multiple of @size. These functions are not + * responsible for checking for invalid arguments. + * + * When there is a natural value to use as an index, @bias gives the + * difference between the natural index and the slot index for the + * register set. For example, x86 GDT segment descriptors form a regset; + * the segment selector produces a natural index, but only a subset of + * that index space is available as a regset (the TLS slots); subtracting + * @bias from a segment selector index value computes the regset slot. + * + * If nonzero, @core_note_type gives the n_type field (NT_* value) + * of the core file note in which this regset's data appears. + * NT_PRSTATUS is a special case in that the regset data starts at + * offsetof(struct elf_prstatus, pr_reg) into the note data; that is + * part of the per-machine ELF formats userland knows about. In + * other cases, the core file note contains exactly the whole regset + * (@n * @size) and nothing else. The core file note is normally + * omitted when there is an @active function and it returns zero. + */ +struct user_regset { + user_regset_get_fn *get; + user_regset_set_fn *set; + user_regset_active_fn *active; + user_regset_writeback_fn *writeback; + unsigned int n; + unsigned int size; + unsigned int align; + unsigned int bias; + unsigned int core_note_type; +}; + +/** + * struct user_regset_view - available regsets + * @name: Identifier, e.g. UTS_MACHINE string. + * @regsets: Array of @n regsets available in this view. + * @n: Number of elements in @regsets. + * @e_machine: ELF header @e_machine %EM_* value written in core dumps. + * @e_flags: ELF header @e_flags value written in core dumps. + * @ei_osabi: ELF header @e_ident[%EI_OSABI] value written in core dumps. + * + * A regset view is a collection of regsets (&struct user_regset, + * above). This describes all the state of a thread that can be seen + * from a given architecture/ABI environment. More than one view might + * refer to the same &struct user_regset, or more than one regset + * might refer to the same machine-specific state in the thread. For + * example, a 32-bit thread's state could be examined from the 32-bit + * view or from the 64-bit view. Either method reaches the same thread + * register state, doing appropriate widening or truncation. + */ +struct user_regset_view { + const char *name; + const struct user_regset *regsets; + unsigned int n; + u32 e_flags; + u16 e_machine; + u8 ei_osabi; +}; + +/* + * This is documented here rather than at the definition sites because its + * implementation is machine-dependent but its interface is universal. + */ +/** + * task_user_regset_view - Return the process's native regset view. + * @tsk: a thread of the process in question + * + * Return the &struct user_regset_view that is native for the given process. + * For example, what it would access when it called ptrace(). + * Throughout the life of the process, this only changes at exec. + */ +const struct user_regset_view *task_user_regset_view(struct task_struct *tsk); + + +#endif /* */ -- cgit v1.2.3 From bae3f7c39dee5951bcbedeaedb6744f882a00173 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Wed, 30 Jan 2008 13:31:45 +0100 Subject: x86: user_regset helpers This adds some inlines to linux/regset.h intended for arch code to use in its user_regset get and set functions. These make it pretty easy to deal with the interface's optional kernel-space or user-space pointers and its generalized access to a part of the register data at a time. In simple cases where the internal data structure matches the exported layout (core dump format), a get function can be nothing but a call to user_regset_copyout, and a set function a call to user_regset_copyin. In other cases the exported layout is usually made up of a few pieces each stored contiguously in a different internal data structure. These helpers make it straightforward to write a get or set function by processing each contiguous chunk of the data in order. The start_pos and end_pos arguments are always constants, so these inlines collapse to a small amount of code. Signed-off-by: Roland McGrath Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/regset.h | 116 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 116 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regset.h b/include/linux/regset.h index 85d0fb0a014d..761c931af975 100644 --- a/include/linux/regset.h +++ b/include/linux/regset.h @@ -15,6 +15,7 @@ #include #include +#include struct task_struct; struct user_regset; @@ -203,4 +204,119 @@ struct user_regset_view { const struct user_regset_view *task_user_regset_view(struct task_struct *tsk); +/* + * These are helpers for writing regset get/set functions in arch code. + * Because @start_pos and @end_pos are always compile-time constants, + * these are inlined into very little code though they look large. + * + * Use one or more calls sequentially for each chunk of regset data stored + * contiguously in memory. Call with constants for @start_pos and @end_pos, + * giving the range of byte positions in the regset that data corresponds + * to; @end_pos can be -1 if this chunk is at the end of the regset layout. + * Each call updates the arguments to point past its chunk. + */ + +static inline int user_regset_copyout(unsigned int *pos, unsigned int *count, + void **kbuf, + void __user **ubuf, const void *data, + const int start_pos, const int end_pos) +{ + if (*count == 0) + return 0; + BUG_ON(*pos < start_pos); + if (end_pos < 0 || *pos < end_pos) { + unsigned int copy = (end_pos < 0 ? *count + : min(*count, end_pos - *pos)); + data += *pos - start_pos; + if (*kbuf) { + memcpy(*kbuf, data, copy); + *kbuf += copy; + } else if (__copy_to_user(*ubuf, data, copy)) + return -EFAULT; + else + *ubuf += copy; + *pos += copy; + *count -= copy; + } + return 0; +} + +static inline int user_regset_copyin(unsigned int *pos, unsigned int *count, + const void **kbuf, + const void __user **ubuf, void *data, + const int start_pos, const int end_pos) +{ + if (*count == 0) + return 0; + BUG_ON(*pos < start_pos); + if (end_pos < 0 || *pos < end_pos) { + unsigned int copy = (end_pos < 0 ? *count + : min(*count, end_pos - *pos)); + data += *pos - start_pos; + if (*kbuf) { + memcpy(data, *kbuf, copy); + *kbuf += copy; + } else if (__copy_from_user(data, *ubuf, copy)) + return -EFAULT; + else + *ubuf += copy; + *pos += copy; + *count -= copy; + } + return 0; +} + +/* + * These two parallel the two above, but for portions of a regset layout + * that always read as all-zero or for which writes are ignored. + */ +static inline int user_regset_copyout_zero(unsigned int *pos, + unsigned int *count, + void **kbuf, void __user **ubuf, + const int start_pos, + const int end_pos) +{ + if (*count == 0) + return 0; + BUG_ON(*pos < start_pos); + if (end_pos < 0 || *pos < end_pos) { + unsigned int copy = (end_pos < 0 ? *count + : min(*count, end_pos - *pos)); + if (*kbuf) { + memset(*kbuf, 0, copy); + *kbuf += copy; + } else if (__clear_user(*ubuf, copy)) + return -EFAULT; + else + *ubuf += copy; + *pos += copy; + *count -= copy; + } + return 0; +} + +static inline int user_regset_copyin_ignore(unsigned int *pos, + unsigned int *count, + const void **kbuf, + const void __user **ubuf, + const int start_pos, + const int end_pos) +{ + if (*count == 0) + return 0; + BUG_ON(*pos < start_pos); + if (end_pos < 0 || *pos < end_pos) { + unsigned int copy = (end_pos < 0 ? *count + : min(*count, end_pos - *pos)); + if (*kbuf) + *kbuf += copy; + else + *ubuf += copy; + *pos += copy; + *count -= copy; + } + return 0; +} + + #endif /* */ -- cgit v1.2.3 From 5bde4d181793be84351bc21c256d8c71cfcd313a Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Wed, 30 Jan 2008 13:31:47 +0100 Subject: x86: user_regset user-copy helpers This defines two new inlines in linux/regset.h, for use in arch_ptrace implementations and the like. These provide simplified wrappers for using the user_regset interfaces to copy thread regset data into the caller's user-space memory. The inlines are trivial, but make the common uses in places such as ptrace implementation much more concise, easier to read, and less prone to code-copying errors. Signed-off-by: Roland McGrath Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/regset.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regset.h b/include/linux/regset.h index 761c931af975..8abee6556223 100644 --- a/include/linux/regset.h +++ b/include/linux/regset.h @@ -318,5 +318,51 @@ static inline int user_regset_copyin_ignore(unsigned int *pos, return 0; } +/** + * copy_regset_to_user - fetch a thread's user_regset data into user memory + * @target: thread to be examined + * @view: &struct user_regset_view describing user thread machine state + * @setno: index in @view->regsets + * @offset: offset into the regset data, in bytes + * @size: amount of data to copy, in bytes + * @data: user-mode pointer to copy into + */ +static inline int copy_regset_to_user(struct task_struct *target, + const struct user_regset_view *view, + unsigned int setno, + unsigned int offset, unsigned int size, + void __user *data) +{ + const struct user_regset *regset = &view->regsets[setno]; + + if (!access_ok(VERIFY_WRITE, data, size)) + return -EIO; + + return regset->get(target, regset, offset, size, NULL, data); +} + +/** + * copy_regset_from_user - store into thread's user_regset data from user memory + * @target: thread to be examined + * @view: &struct user_regset_view describing user thread machine state + * @setno: index in @view->regsets + * @offset: offset into the regset data, in bytes + * @size: amount of data to copy, in bytes + * @data: user-mode pointer to copy from + */ +static inline int copy_regset_from_user(struct task_struct *target, + const struct user_regset_view *view, + unsigned int setno, + unsigned int offset, unsigned int size, + const void __user *data) +{ + const struct user_regset *regset = &view->regsets[setno]; + + if (!access_ok(VERIFY_READ, data, size)) + return -EIO; + + return regset->set(target, regset, offset, size, NULL, data); +} + #endif /* */ -- cgit v1.2.3 From 032d82d9065dec0e26718eca376c2029e4bd0595 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Wed, 30 Jan 2008 13:31:47 +0100 Subject: x86: compat_ptrace_request This adds a compat_ptrace_request that is the analogue of ptrace_request for the things that 32-on-64 ptrace implementations can share in common. So far there are just a couple of requests handled generically. Signed-off-by: Roland McGrath Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/compat.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index ba29d4c59643..a907fbede6c3 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -243,6 +243,10 @@ asmlinkage long compat_sys_migrate_pages(compat_pid_t pid, compat_ulong_t maxnode, const compat_ulong_t __user *old_nodes, const compat_ulong_t __user *new_nodes); +extern int compat_ptrace_request(struct task_struct *child, + compat_long_t request, + compat_ulong_t addr, compat_ulong_t data); + /* * epoll (fs/eventpoll.c) compat bits follow ... */ -- cgit v1.2.3 From c269f19617f508cc5c29c0b064c1a437d7011a46 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Wed, 30 Jan 2008 13:31:48 +0100 Subject: x86: compat_sys_ptrace This adds a generic definition of compat_sys_ptrace that calls compat_arch_ptrace, parallel to sys_ptrace/arch_ptrace. Some machines needing this already define a function by that name. The new generic function is defined only on machines that put #define __ARCH_WANT_COMPAT_SYS_PTRACE into asm/ptrace.h. Signed-off-by: Roland McGrath Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/compat.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index a907fbede6c3..d38655f2be70 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -247,6 +247,13 @@ extern int compat_ptrace_request(struct task_struct *child, compat_long_t request, compat_ulong_t addr, compat_ulong_t data); +#ifdef __ARCH_WANT_COMPAT_SYS_PTRACE +extern long compat_arch_ptrace(struct task_struct *child, compat_long_t request, + compat_ulong_t addr, compat_ulong_t data); +asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, + compat_long_t addr, compat_long_t data); +#endif /* __ARCH_WANT_COMPAT_SYS_PTRACE */ + /* * epoll (fs/eventpoll.c) compat bits follow ... */ -- cgit v1.2.3 From bb61682b3f31dec7d058cae2f6edd2275248a704 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Wed, 30 Jan 2008 13:31:56 +0100 Subject: x86: x86 core dump TLS This makes ELF core dumps of 32-bit processes include a new note type NT_386_TLS (0x200) giving the contents of the TLS slots in struct user_desc format. This lets post mortem examination figure out what the segment registers mean like the debugger does with get_thread_area on a live process. Signed-off-by: Roland McGrath Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/elf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/elf.h b/include/linux/elf.h index 576e83bd6d88..7ceb24d87c1a 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -355,6 +355,7 @@ typedef struct elf64_shdr { #define NT_AUXV 6 #define NT_PRXFPREG 0x46e62b7f /* copied from gdb5.1/include/elf/common.h */ #define NT_PPC_VMX 0x100 /* PowerPC Altivec/VMX registers */ +#define NT_386_TLS 0x200 /* i386 TLS slots (struct user_desc) */ /* Note header in a PT_NOTE section */ -- cgit v1.2.3 From 74ef649fe847fdfbd3e1732d21b923f59ca04e8c Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Wed, 30 Jan 2008 13:32:42 +0100 Subject: x86: add _AT() macro to conditionally cast # HG changeset patch # User Jeremy Fitzhardinge # Date 1199317452 28800 # Node ID f7e7db3facd9406545103164f9be8f9ba1a2b549 # Parent 4d9a413a0f4c1d98dbea704f0366457b5117045d x86: add _AT() macro to conditionally cast Define _AT(type, value) to conditionally cast a value when compiling C code, but not when used in assembler. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/const.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/const.h b/include/linux/const.h index 07b300bfe34b..c22c707c455d 100644 --- a/include/linux/const.h +++ b/include/linux/const.h @@ -7,13 +7,18 @@ * C code. Therefore we cannot annotate them always with * 'UL' and other type specifiers unilaterally. We * use the following macros to deal with this. + * + * Similarly, _AT() will cast an expression with a type in C, but + * leave it unchanged in asm. */ #ifdef __ASSEMBLY__ #define _AC(X,Y) X +#define _AT(T,X) X #else #define __AC(X,Y) (X##Y) #define _AC(X,Y) __AC(X,Y) +#define _AT(T,X) ((T)(X)) #endif #endif /* !(_LINUX_CONST_H) */ -- cgit v1.2.3 From 5280e004fc22314122c84978c0b6a741cf96dc0f Mon Sep 17 00:00:00 2001 From: "travis@sgi.com" Date: Wed, 30 Jan 2008 13:32:52 +0100 Subject: percpu: move arch XX_PER_CPU_XX definitions into linux/percpu.h - Special consideration for IA64: Add the ability to specify arch specific per cpu flags - remove .data.percpu attribute from DEFINE_PER_CPU for non-smp case. The arch definitions are all the same. So move them into linux/percpu.h. We cannot move DECLARE_PER_CPU since some include files just include asm/percpu.h to avoid include recursion problems. Cc: Rusty Russell Cc: Andi Kleen Signed-off-by: Christoph Lameter Signed-off-by: Mike Travis Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/percpu.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 926adaae0f96..00412bb494c4 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -9,6 +9,30 @@ #include +#ifndef PER_CPU_ATTRIBUTES +#define PER_CPU_ATTRIBUTES +#endif + +#ifdef CONFIG_SMP +#define DEFINE_PER_CPU(type, name) \ + __attribute__((__section__(".data.percpu"))) \ + PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name + +#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ + __attribute__((__section__(".data.percpu.shared_aligned"))) \ + PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name \ + ____cacheline_aligned_in_smp +#else +#define DEFINE_PER_CPU(type, name) \ + PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name + +#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ + DEFINE_PER_CPU(type, name) +#endif + +#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var) +#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var) + /* Enough to cover all DEFINE_PER_CPUs in kernel, including modules. */ #ifndef PERCPU_ENOUGH_ROOM #ifdef CONFIG_MODULES -- cgit v1.2.3 From 8c1c9356429741a82ff176d0f3400fb9e06b2a30 Mon Sep 17 00:00:00 2001 From: Ananth N Mavinakayanahalli Date: Wed, 30 Jan 2008 13:32:53 +0100 Subject: x86: kprobes: add kprobes smoke tests that run on boot Here is a quick and naive smoke test for kprobes. This is intended to just verify if some unrelated change broke the *probes subsystem. It is self contained, architecture agnostic and isn't of any great use by itself. This needs to be built in the kernel and runs a basic set of tests to verify if kprobes, jprobes and kretprobes run fine on the kernel. In case of an error, it'll print out a message with a "BUG" prefix. This is a start; we intend to add more tests to this bucket over time. Thanks to Jim Keniston and Masami Hiramatsu for comments and suggestions. Tested on x86 (32/64) and powerpc. Signed-off-by: Ananth N Mavinakayanahalli Acked-by: Masami Hiramatsu Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/kprobes.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 81891581e89b..6168c0a44172 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -182,6 +182,15 @@ static inline void kretprobe_assert(struct kretprobe_instance *ri, } } +#ifdef CONFIG_KPROBES_SANITY_TEST +extern int init_test_probes(void); +#else +static inline int init_test_probes(void) +{ + return 0; +} +#endif /* CONFIG_KPROBES_SANITY_TEST */ + extern spinlock_t kretprobe_lock; extern struct mutex kprobe_mutex; extern int arch_prepare_kprobe(struct kprobe *p); @@ -227,6 +236,7 @@ void unregister_kretprobe(struct kretprobe *rp); void kprobe_flush_task(struct task_struct *tk); void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head); + #else /* CONFIG_KPROBES */ #define __kprobes /**/ -- cgit v1.2.3 From d50efc6c40620b2e11648cac64ebf4a824e40382 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 30 Jan 2008 13:33:00 +0100 Subject: x86: fix UML and -regparm=3 introduce the "asmregparm" calling convention: for functions implemented in assembly with a fixed regparm input parameters calling convention. mark the semaphore and rwsem slowpath functions with that. Signed-off-by: Ingo Molnar Signed-off-by: Miklos Szeredi Signed-off-by: Thomas Gleixner --- include/linux/linkage.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index ff203dd02919..ceeeb5ea5b15 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -13,6 +13,10 @@ #define asmlinkage CPP_ASMLINKAGE #endif +#ifndef asmregparm +# define asmregparm +#endif + #ifndef prevent_tail_call # define prevent_tail_call(ret) do { } while (0) #endif -- cgit v1.2.3 From 076f9776f5d8d131b36955db8641aba3893c2c1b Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 30 Jan 2008 13:33:06 +0100 Subject: x86: make early printk selectable on 64-bit as well Enable CONFIG_EMBEDDED to select CONFIG_EARLY_PRINTK on 64-bit as well. saves ~2K: text data bss dec hex filename 7290283 3672091 1907848 12870222 c4624e vmlinux.before 7288373 3671795 1907848 12868016 c459b0 vmlinux.after Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/kernel.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index a7283c9beadf..ff356b2ee478 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -194,6 +194,9 @@ static inline int log_buf_read(int idx) { return 0; } static inline int log_buf_copy(char *dest, int idx, int len) { return 0; } #endif +extern void __attribute__((format(printf, 1, 2))) + early_printk(const char *fmt, ...); + unsigned long int_sqrt(unsigned long); extern int printk_ratelimit(void); -- cgit v1.2.3 From 6b8be6df7f971919622d152d144c8798ad7fd160 Mon Sep 17 00:00:00 2001 From: John Reiser Date: Wed, 30 Jan 2008 13:33:13 +0100 Subject: x86: add ENDPROC() markers The ENDPROCs() were not used everywhere. Some code used just END() instead, while other code used nothing. um/sys-i386/checksum.S didn't #include . I also got confused because gcc puts the .type near the ENTRY, while ENDPROC puts it on the opposite end. Signed off by: John Reiser Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/linkage.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index ceeeb5ea5b15..3faf599ea58e 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -57,6 +57,10 @@ .size name, .-name #endif +/* If symbol 'name' is treated as a subroutine (gets called, and returns) + * then please use ENDPROC to mark 'name' as STT_FUNC for the benefit of + * static analysis tools such as stack depth analyzer. + */ #ifndef ENDPROC #define ENDPROC(name) \ .type name, @function; \ -- cgit v1.2.3 From ca74a6f84e68b44867022f4a4f3ec17c087c864e Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 30 Jan 2008 13:33:17 +0100 Subject: x86: optimize lock prefix switching to run less frequently On VMs implemented using JITs that cache translated code changing the lock prefixes is a quite costly operation that forces the JIT to throw away and retranslate a lot of code. Previously a SMP kernel would rewrite the locks once for each CPU which is quite unnecessary. This patch changes the code to never switch at boot in the normal case (SMP kernel booting with >1 CPU) or only once for SMP kernel on UP. This makes a significant difference in boot up performance on AMD SimNow! Also I expect it to be a little faster on native systems too because a smp switch does a lot of text_poke()s which each synchronize the pipeline. v1->v2: Rename max_cpus v1->v2: Fix off by one in UP check (Thomas Gleixner) Signed-off-by: Andi Kleen Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/smp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index c25e66bcecf3..55232ccf9cfd 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -78,6 +78,8 @@ int on_each_cpu(void (*func) (void *info), void *info, int retry, int wait); */ void smp_prepare_boot_cpu(void); +extern unsigned int setup_max_cpus; + #else /* !SMP */ /* -- cgit v1.2.3 From 03252919b79891063cf99145612360efbdf9500b Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 30 Jan 2008 13:33:18 +0100 Subject: x86: print which shared library/executable faulted in segfault etc. messages v3 They now look like: hal-resmgr[13791]: segfault at 3c rip 2b9c8caec182 rsp 7fff1e825d30 error 4 in libacl.so.1.1.0[2b9c8caea000+6000] This makes it easier to pinpoint bugs to specific libraries. And printing the offset into a mapping also always allows to find the correct fault point in a library even with randomized mappings. Previously there was no way to actually find the correct code address inside the randomized mapping. Relies on earlier patch to shorten the printk formats. They are often now longer than 80 characters, but I think that's worth it. [includes fix from Eric Dumazet to check d_path error value] Signed-off-by: Andi Kleen Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1897ca223eca..3c22d971afa7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1146,6 +1146,7 @@ extern int randomize_va_space; #endif const char * arch_vma_name(struct vm_area_struct *vma); +void print_vma_addr(char *prefix, unsigned long rip); struct page *sparse_mem_map_populate(unsigned long pnum, int nid); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); -- cgit v1.2.3 From 0acf8e3447b893ff921863c2a4258e210d584452 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 30 Jan 2008 13:33:36 +0100 Subject: pci: add PCI identifiers for the RDC devices This patch defines the PCI identifiers found in the RDC R-321x System-on-Chip. Signed-off-by: Florian Fainelli Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/pci_ids.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index c69531348363..41f6f28690f6 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2085,6 +2085,13 @@ #define PCI_VENDOR_ID_BELKIN 0x1799 #define PCI_DEVICE_ID_BELKIN_F5D7010V7 0x701f +#define PCI_VENDOR_ID_RDC 0x17f3 +#define PCI_DEVICE_ID_RDC_R6020 0x6020 +#define PCI_DEVICE_ID_RDC_R6030 0x6030 +#define PCI_DEVICE_ID_RDC_R6040 0x6040 +#define PCI_DEVICE_ID_RDC_R6060 0x6060 +#define PCI_DEVICE_ID_RDC_R6061 0x6061 + #define PCI_VENDOR_ID_LENOVO 0x17aa #define PCI_VENDOR_ID_ARECA 0x17d3 -- cgit v1.2.3 From a5a19c63f4e55e32dc0bc3d936d7f94793d8b380 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Wed, 30 Jan 2008 13:33:39 +0100 Subject: x86: demacro asm-x86/pgalloc_32.h Convert macros into inline functions, for better type-checking. This patch required a little bit of fiddling with headers in order to make __(pte|pmd)_free_tlb inline rather than macros. asm-generic/tlb.h includes asm/pgalloc.h, though it doesn't directly use any pgalloc definitions. I removed this include to avoid an include cycle, but it may cause secondary compile failures by things depending on the indirect inclusion; arch/x86/mm/hugetlbpage.c was one such place; there may be others. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/swap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 4f3838adbb30..2c3ce4c69b25 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -6,6 +6,7 @@ #include #include #include +#include #include #include -- cgit v1.2.3 From 12d6f21eacc21d84a809829543f2fe45c7e37319 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 30 Jan 2008 13:33:58 +0100 Subject: x86: do not PSE on CONFIG_DEBUG_PAGEALLOC=y get more testing of the c_p_a() code done by not turning off PSE on DEBUG_PAGEALLOC. this simplifies the early pagetable setup code, and tests the largepage-splitup code quite heavily. In the end, all the largepages will be split up pretty quickly, so there's no difference to how DEBUG_PAGEALLOC worked before. Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/mm.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3c22d971afa7..1bba6789a50a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1118,9 +1118,21 @@ static inline void vm_stat_account(struct mm_struct *mm, } #endif /* CONFIG_PROC_FS */ -#ifndef CONFIG_DEBUG_PAGEALLOC +#ifdef CONFIG_DEBUG_PAGEALLOC +extern int debug_pagealloc_enabled; + +extern void kernel_map_pages(struct page *page, int numpages, int enable); + +static inline void enable_debug_pagealloc(void) +{ + debug_pagealloc_enabled = 1; +} +#else static inline void kernel_map_pages(struct page *page, int numpages, int enable) {} +static inline void enable_debug_pagealloc(void) +{ +} #endif extern struct vm_area_struct *get_gate_vma(struct task_struct *tsk); -- cgit v1.2.3 From f212ec4b7b4d84290f12c9c0416cdea283bf5f40 Mon Sep 17 00:00:00 2001 From: Bernhard Kaindl Date: Wed, 30 Jan 2008 13:34:11 +0100 Subject: x86: early boot debugging via FireWire (ohci1394_dma=early) This patch adds a new configuration option, which adds support for a new early_param which gets checked in arch/x86/kernel/setup_{32,64}.c:setup_arch() to decide wether OHCI-1394 FireWire controllers should be initialized and enabled for physical DMA access to allow remote debugging of early problems like issues ACPI or other subsystems which are executed very early. If the config option is not enabled, no code is changed, and if the boot paramenter is not given, no new code is executed, and independent of that, all new code is freed after boot, so the config option can be even enabled in standard, non-debug kernels. With specialized tools, it is then possible to get debugging information from machines which have no serial ports (notebooks) such as the printk buffer contents, or any data which can be referenced from global pointers, if it is stored below the 4GB limit and even memory dumps of of the physical RAM region below the 4GB limit can be taken without any cooperation from the CPU of the host, so the machine can be crashed early, it does not matter. In the extreme, even kernel debuggers can be accessed in this way. I wrote a small kgdb module and an accompanying gdb stub for FireWire which allows to gdb to talk to kgdb using remote remory reads and writes over FireWire. An version of the gdb stub fore FireWire is able to read all global data from a system which is running a a normal kernel without any kernel debugger, without any interruption or support of the system's CPU. That way, e.g. the task struct and so on can be read and even manipulated when the physical DMA access is granted. A HOWTO is included in this patch, in Documentation/debugging-via-ohci1394.txt and I've put a copy online at ftp://ftp.suse.de/private/bk/firewire/docs/debugging-via-ohci1394.txt It also has links to all the tools which are available to make use of it another copy of it is online at: ftp://ftp.suse.de/private/bk/firewire/kernel/ohci1394_dma_early-v2.diff Signed-Off-By: Bernhard Kaindl Tested-By: Thomas Renninger Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/init_ohci1394_dma.h | 4 ++++ 1 file changed, 4 insertions(+) create mode 100644 include/linux/init_ohci1394_dma.h (limited to 'include/linux') diff --git a/include/linux/init_ohci1394_dma.h b/include/linux/init_ohci1394_dma.h new file mode 100644 index 000000000000..3c03a4bba5e4 --- /dev/null +++ b/include/linux/init_ohci1394_dma.h @@ -0,0 +1,4 @@ +#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT +extern int __initdata init_ohci1394_dma_early; +extern void __init init_ohci1394_dma_on_all_controllers(void); +#endif -- cgit v1.2.3 From 7aa81cc04781b5b99a0647ec04533599d78cd219 Mon Sep 17 00:00:00 2001 From: Anthony Liguori Date: Mon, 17 Sep 2007 14:57:50 -0500 Subject: KVM: Refactor hypercall infrastructure (v3) This patch refactors the current hypercall infrastructure to better support live migration and SMP. It eliminates the hypercall page by trapping the UD exception that would occur if you used the wrong hypercall instruction for the underlying architecture and replacing it with the right one lazily. A fall-out of this patch is that the unhandled hypercalls no longer trap to userspace. There is very little reason though to use a hypercall to communicate with userspace as PIO or MMIO can be used. There is no code in tree that uses userspace hypercalls. [avi: fix #ud injection on vmx] Signed-off-by: Anthony Liguori Signed-off-by: Avi Kivity --- include/linux/kvm_para.h | 159 +++++++++++++++++++++++++++++------------------ 1 file changed, 98 insertions(+), 61 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_para.h b/include/linux/kvm_para.h index 3b292565a693..cc5dfb433706 100644 --- a/include/linux/kvm_para.h +++ b/include/linux/kvm_para.h @@ -1,73 +1,110 @@ #ifndef __LINUX_KVM_PARA_H #define __LINUX_KVM_PARA_H -/* - * Guest OS interface for KVM paravirtualization - * - * Note: this interface is totally experimental, and is certain to change - * as we make progress. +/* This CPUID returns the signature 'KVMKVMKVM' in ebx, ecx, and edx. It + * should be used to determine that a VM is running under KVM. */ +#define KVM_CPUID_SIGNATURE 0x40000000 -/* - * Per-VCPU descriptor area shared between guest and host. Writable to - * both guest and host. Registered with the host by the guest when - * a guest acknowledges paravirtual mode. - * - * NOTE: all addresses are guest-physical addresses (gpa), to make it - * easier for the hypervisor to map between the various addresses. - */ -struct kvm_vcpu_para_state { - /* - * API version information for compatibility. If there's any support - * mismatch (too old host trying to execute too new guest) then - * the host will deny entry into paravirtual mode. Any other - * combination (new host + old guest and new host + new guest) - * is supposed to work - new host versions will support all old - * guest API versions. - */ - u32 guest_version; - u32 host_version; - u32 size; - u32 ret; - - /* - * The address of the vm exit instruction (VMCALL or VMMCALL), - * which the host will patch according to the CPU model the - * VM runs on: - */ - u64 hypercall_gpa; - -} __attribute__ ((aligned(PAGE_SIZE))); - -#define KVM_PARA_API_VERSION 1 - -/* - * This is used for an RDMSR's ECX parameter to probe for a KVM host. - * Hopefully no CPU vendor will use up this number. This is placed well - * out of way of the typical space occupied by CPU vendors' MSR indices, - * and we think (or at least hope) it wont be occupied in the future - * either. +/* This CPUID returns a feature bitmap in eax. Before enabling a particular + * paravirtualization, the appropriate feature bit should be checked. */ -#define MSR_KVM_API_MAGIC 0x87655678 +#define KVM_CPUID_FEATURES 0x40000001 -#define KVM_EINVAL 1 +/* Return values for hypercalls */ +#define KVM_ENOSYS 1000 -/* - * Hypercall calling convention: - * - * Each hypercall may have 0-6 parameters. - * - * 64-bit hypercall index is in RAX, goes from 0 to __NR_hypercalls-1 - * - * 64-bit parameters 1-6 are in the standard gcc x86_64 calling convention - * order: RDI, RSI, RDX, RCX, R8, R9. - * - * 32-bit index is EBX, parameters are: EAX, ECX, EDX, ESI, EDI, EBP. - * (the first 3 are according to the gcc regparm calling convention) +#ifdef __KERNEL__ +#include + +/* This instruction is vmcall. On non-VT architectures, it will generate a + * trap that we will then rewrite to the appropriate instruction. + */ +#define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1" + +/* For KVM hypercalls, a three-byte sequence of either the vmrun or the vmmrun + * instruction. The hypervisor may replace it with something else but only the + * instructions are guaranteed to be supported. * - * No registers are clobbered by the hypercall, except that the - * return value is in RAX. + * Up to four arguments may be passed in rbx, rcx, rdx, and rsi respectively. + * The hypercall number should be placed in rax and the return value will be + * placed in rax. No other registers will be clobbered unless explicited + * noted by the particular hypercall. */ -#define __NR_hypercalls 0 + +static inline long kvm_hypercall0(unsigned int nr) +{ + long ret; + asm volatile(KVM_HYPERCALL + : "=a"(ret) + : "a"(nr)); + return ret; +} + +static inline long kvm_hypercall1(unsigned int nr, unsigned long p1) +{ + long ret; + asm volatile(KVM_HYPERCALL + : "=a"(ret) + : "a"(nr), "b"(p1)); + return ret; +} + +static inline long kvm_hypercall2(unsigned int nr, unsigned long p1, + unsigned long p2) +{ + long ret; + asm volatile(KVM_HYPERCALL + : "=a"(ret) + : "a"(nr), "b"(p1), "c"(p2)); + return ret; +} + +static inline long kvm_hypercall3(unsigned int nr, unsigned long p1, + unsigned long p2, unsigned long p3) +{ + long ret; + asm volatile(KVM_HYPERCALL + : "=a"(ret) + : "a"(nr), "b"(p1), "c"(p2), "d"(p3)); + return ret; +} + +static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, + unsigned long p2, unsigned long p3, + unsigned long p4) +{ + long ret; + asm volatile(KVM_HYPERCALL + : "=a"(ret) + : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4)); + return ret; +} + +static inline int kvm_para_available(void) +{ + unsigned int eax, ebx, ecx, edx; + char signature[13]; + + cpuid(KVM_CPUID_SIGNATURE, &eax, &ebx, &ecx, &edx); + memcpy(signature + 0, &ebx, 4); + memcpy(signature + 4, &ecx, 4); + memcpy(signature + 8, &edx, 4); + signature[12] = 0; + + if (strcmp(signature, "KVMKVMKVM") == 0) + return 1; + + return 0; +} + +static inline int kvm_para_has_feature(unsigned int feature) +{ + if (cpuid_eax(KVM_CPUID_FEATURES) & (1UL << feature)) + return 1; + return 0; +} + +#endif #endif -- cgit v1.2.3 From 82ce2c96831f049a37118733ced5c8f7c8848102 Mon Sep 17 00:00:00 2001 From: Izik Eidus Date: Tue, 2 Oct 2007 18:52:55 +0200 Subject: KVM: Allow dynamic allocation of the mmu shadow cache size The user is now able to set how many mmu pages will be allocated to the guest. Signed-off-by: Izik Eidus Signed-off-by: Avi Kivity --- include/linux/kvm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 057a7f34ee36..d2fd973d81fe 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -347,11 +347,14 @@ struct kvm_signal_mask { */ #define KVM_CAP_IRQCHIP 0 #define KVM_CAP_HLT 1 +#define KVM_CAP_MMU_SHADOW_CACHE_CONTROL 2 /* * ioctls for VM fds */ #define KVM_SET_MEMORY_REGION _IOW(KVMIO, 0x40, struct kvm_memory_region) +#define KVM_SET_NR_MMU_PAGES _IO(KVMIO, 0x44) +#define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) /* * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns * a vcpu fd. -- cgit v1.2.3 From 6fc138d2278078990f597cb1f62fde9e5b458f96 Mon Sep 17 00:00:00 2001 From: Izik Eidus Date: Tue, 9 Oct 2007 19:20:39 +0200 Subject: KVM: Support assigning userspace memory to the guest Instead of having the kernel allocate memory to the guest, let userspace allocate it and pass the address to the kernel. This is required for s390 support, but also enables features like memory sharing and using hugetlbfs backed memory. Signed-off-by: Izik Eidus Signed-off-by: Avi Kivity --- include/linux/kvm.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index d2fd973d81fe..971f465e26fa 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -23,6 +23,15 @@ struct kvm_memory_region { __u64 memory_size; /* bytes */ }; +/* for KVM_SET_USER_MEMORY_REGION */ +struct kvm_userspace_memory_region { + __u32 slot; + __u32 flags; + __u64 guest_phys_addr; + __u64 memory_size; /* bytes */ + __u64 userspace_addr; /* start of the userspace allocated memory */ +}; + /* for kvm_memory_region::flags */ #define KVM_MEM_LOG_DIRTY_PAGES 1UL @@ -348,6 +357,7 @@ struct kvm_signal_mask { #define KVM_CAP_IRQCHIP 0 #define KVM_CAP_HLT 1 #define KVM_CAP_MMU_SHADOW_CACHE_CONTROL 2 +#define KVM_CAP_USER_MEMORY 3 /* * ioctls for VM fds @@ -355,6 +365,8 @@ struct kvm_signal_mask { #define KVM_SET_MEMORY_REGION _IOW(KVMIO, 0x40, struct kvm_memory_region) #define KVM_SET_NR_MMU_PAGES _IO(KVMIO, 0x44) #define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) +#define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46,\ + struct kvm_userspace_memory_region) /* * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns * a vcpu fd. -- cgit v1.2.3 From 5f43238d036fb30e73563e81e42d9c6f1de5551a Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 11 Oct 2007 15:34:17 +0200 Subject: KVM: Per-architecture hypercall definitions Currently kvm provides hypercalls only for x86* architectures. To provide hypercall infrastructure for other kvm architectures I split kvm_para.h into a generic header file and architecture specific definitions. Signed-off-by: Christian Borntraeger Signed-off-by: Avi Kivity --- include/linux/kvm_para.h | 105 ++++++----------------------------------------- 1 file changed, 12 insertions(+), 93 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_para.h b/include/linux/kvm_para.h index cc5dfb433706..e4db25ffdb52 100644 --- a/include/linux/kvm_para.h +++ b/include/linux/kvm_para.h @@ -1,110 +1,29 @@ #ifndef __LINUX_KVM_PARA_H #define __LINUX_KVM_PARA_H -/* This CPUID returns the signature 'KVMKVMKVM' in ebx, ecx, and edx. It - * should be used to determine that a VM is running under KVM. +/* + * This header file provides a method for making a hypercall to the host + * Architectures should define: + * - kvm_hypercall0, kvm_hypercall1... + * - kvm_arch_para_features + * - kvm_para_available */ -#define KVM_CPUID_SIGNATURE 0x40000000 - -/* This CPUID returns a feature bitmap in eax. Before enabling a particular - * paravirtualization, the appropriate feature bit should be checked. - */ -#define KVM_CPUID_FEATURES 0x40000001 /* Return values for hypercalls */ #define KVM_ENOSYS 1000 #ifdef __KERNEL__ -#include - -/* This instruction is vmcall. On non-VT architectures, it will generate a - * trap that we will then rewrite to the appropriate instruction. - */ -#define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1" - -/* For KVM hypercalls, a three-byte sequence of either the vmrun or the vmmrun - * instruction. The hypervisor may replace it with something else but only the - * instructions are guaranteed to be supported. - * - * Up to four arguments may be passed in rbx, rcx, rdx, and rsi respectively. - * The hypercall number should be placed in rax and the return value will be - * placed in rax. No other registers will be clobbered unless explicited - * noted by the particular hypercall. +/* + * hypercalls use architecture specific */ - -static inline long kvm_hypercall0(unsigned int nr) -{ - long ret; - asm volatile(KVM_HYPERCALL - : "=a"(ret) - : "a"(nr)); - return ret; -} - -static inline long kvm_hypercall1(unsigned int nr, unsigned long p1) -{ - long ret; - asm volatile(KVM_HYPERCALL - : "=a"(ret) - : "a"(nr), "b"(p1)); - return ret; -} - -static inline long kvm_hypercall2(unsigned int nr, unsigned long p1, - unsigned long p2) -{ - long ret; - asm volatile(KVM_HYPERCALL - : "=a"(ret) - : "a"(nr), "b"(p1), "c"(p2)); - return ret; -} - -static inline long kvm_hypercall3(unsigned int nr, unsigned long p1, - unsigned long p2, unsigned long p3) -{ - long ret; - asm volatile(KVM_HYPERCALL - : "=a"(ret) - : "a"(nr), "b"(p1), "c"(p2), "d"(p3)); - return ret; -} - -static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, - unsigned long p2, unsigned long p3, - unsigned long p4) -{ - long ret; - asm volatile(KVM_HYPERCALL - : "=a"(ret) - : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4)); - return ret; -} - -static inline int kvm_para_available(void) -{ - unsigned int eax, ebx, ecx, edx; - char signature[13]; - - cpuid(KVM_CPUID_SIGNATURE, &eax, &ebx, &ecx, &edx); - memcpy(signature + 0, &ebx, 4); - memcpy(signature + 4, &ecx, 4); - memcpy(signature + 8, &edx, 4); - signature[12] = 0; - - if (strcmp(signature, "KVMKVMKVM") == 0) - return 1; - - return 0; -} +#include static inline int kvm_para_has_feature(unsigned int feature) { - if (cpuid_eax(KVM_CPUID_FEATURES) & (1UL << feature)) + if (kvm_arch_para_features() & (1UL << feature)) return 1; return 0; } +#endif /* __KERNEL__ */ +#endif /* __LINUX_KVM_PARA_H */ -#endif - -#endif -- cgit v1.2.3 From cbc9402297b9a233981f74587786364cda21c771 Mon Sep 17 00:00:00 2001 From: Izik Eidus Date: Thu, 25 Oct 2007 00:29:55 +0200 Subject: KVM: Add ioctl to tss address from userspace, Currently kvm has a wart in that it requires three extra pages for use as a tss when emulating real mode on Intel. This patch moves the allocation internally, only requiring userspace to tell us where in the physical address space we can place the tss. Signed-off-by: Izik Eidus Signed-off-by: Avi Kivity --- include/linux/kvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 971f465e26fa..71d33d62944f 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -358,6 +358,7 @@ struct kvm_signal_mask { #define KVM_CAP_HLT 1 #define KVM_CAP_MMU_SHADOW_CACHE_CONTROL 2 #define KVM_CAP_USER_MEMORY 3 +#define KVM_CAP_SET_TSS_ADDR 4 /* * ioctls for VM fds @@ -367,6 +368,7 @@ struct kvm_signal_mask { #define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) #define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46,\ struct kvm_userspace_memory_region) +#define KVM_SET_TSS_ADDR _IO(KVMIO, 0x47) /* * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns * a vcpu fd. -- cgit v1.2.3 From f6a40e3bdf5fe0a7d7d7f2dbc5b10158fbdad968 Mon Sep 17 00:00:00 2001 From: Jerone Young Date: Mon, 19 Nov 2007 17:06:31 -0600 Subject: KVM: Portability: Move kvm_memory_alias to asm/kvm.h This patch moves sturct kvm_memory_alias from include/linux/kvm.h to include/asm-x86/kvm.h. Also have include/linux/kvm.h include include/asm/kvm.h. Signed-off-by: Jerone Young Signed-off-by: Avi Kivity --- include/linux/kvm.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 71d33d62944f..d09dd5dd5493 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -9,6 +9,7 @@ #include #include +#include #define KVM_API_VERSION 12 @@ -35,13 +36,6 @@ struct kvm_userspace_memory_region { /* for kvm_memory_region::flags */ #define KVM_MEM_LOG_DIRTY_PAGES 1UL -struct kvm_memory_alias { - __u32 slot; /* this has a different namespace than memory slots */ - __u32 flags; - __u64 guest_phys_addr; - __u64 memory_size; - __u64 target_phys_addr; -}; /* for KVM_IRQ_LINE */ struct kvm_irq_level { -- cgit v1.2.3 From da1386a5bc43fa0faf17089a68c2991cf1d526c8 Mon Sep 17 00:00:00 2001 From: Jerone Young Date: Mon, 19 Nov 2007 17:06:32 -0600 Subject: KVM: Portability: Move x86 pic strutctures This patch moves structures: kvm_pic_state kvm_ioapic_state to inclue/asm-x86/kvm.h. Signed-off-by: Jerone Young Signed-off-by: Avi Kivity --- include/linux/kvm.h | 48 ------------------------------------------------ 1 file changed, 48 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index d09dd5dd5493..1779c3d3bdc9 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -48,54 +48,6 @@ struct kvm_irq_level { __u32 level; }; -/* for KVM_GET_IRQCHIP and KVM_SET_IRQCHIP */ -struct kvm_pic_state { - __u8 last_irr; /* edge detection */ - __u8 irr; /* interrupt request register */ - __u8 imr; /* interrupt mask register */ - __u8 isr; /* interrupt service register */ - __u8 priority_add; /* highest irq priority */ - __u8 irq_base; - __u8 read_reg_select; - __u8 poll; - __u8 special_mask; - __u8 init_state; - __u8 auto_eoi; - __u8 rotate_on_auto_eoi; - __u8 special_fully_nested_mode; - __u8 init4; /* true if 4 byte init */ - __u8 elcr; /* PIIX edge/trigger selection */ - __u8 elcr_mask; -}; - -#define KVM_IOAPIC_NUM_PINS 24 -struct kvm_ioapic_state { - __u64 base_address; - __u32 ioregsel; - __u32 id; - __u32 irr; - __u32 pad; - union { - __u64 bits; - struct { - __u8 vector; - __u8 delivery_mode:3; - __u8 dest_mode:1; - __u8 delivery_status:1; - __u8 polarity:1; - __u8 remote_irr:1; - __u8 trig_mode:1; - __u8 mask:1; - __u8 reserve:7; - __u8 reserved[4]; - __u8 dest_id; - } fields; - } redirtbl[KVM_IOAPIC_NUM_PINS]; -}; - -#define KVM_IRQCHIP_PIC_MASTER 0 -#define KVM_IRQCHIP_PIC_SLAVE 1 -#define KVM_IRQCHIP_IOAPIC 2 struct kvm_irqchip { __u32 chip_id; -- cgit v1.2.3 From 19d30b164417e7580d7f8c495a03137e1a45d4a7 Mon Sep 17 00:00:00 2001 From: Jerone Young Date: Mon, 19 Nov 2007 17:06:33 -0600 Subject: KVM: Portability: Move kvm_regs to This patch moves structure kvm_regs to include/asm-x86/kvm.h. Each architecture will need to create there own version of this structure. Signed-off-by: Jerone Young Signed-off-by: Avi Kivity --- include/linux/kvm.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 1779c3d3bdc9..0d83efc9462e 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -134,15 +134,6 @@ struct kvm_run { }; }; -/* for KVM_GET_REGS and KVM_SET_REGS */ -struct kvm_regs { - /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */ - __u64 rax, rbx, rcx, rdx; - __u64 rsi, rdi, rsp, rbp; - __u64 r8, r9, r10, r11; - __u64 r12, r13, r14, r15; - __u64 rip, rflags; -}; /* for KVM_GET_FPU and KVM_SET_FPU */ struct kvm_fpu { -- cgit v1.2.3 From d9ecf9281069c4c8dd429e1eb61cb7e0f3dda6b4 Mon Sep 17 00:00:00 2001 From: Jerone Young Date: Mon, 19 Nov 2007 17:06:34 -0600 Subject: KVM: Portability: Move structure lapic_state to This patch moves structure lapic_state from include/linux/kvm.h to include/asm-x86/kvm.h Signed-off-by: Jerone Young Signed-off-by: Avi Kivity --- include/linux/kvm.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 0d83efc9462e..280ec0d85b4c 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -150,11 +150,6 @@ struct kvm_fpu { __u32 pad2; }; -/* for KVM_GET_LAPIC and KVM_SET_LAPIC */ -#define KVM_APIC_REG_SIZE 0x400 -struct kvm_lapic_state { - char regs[KVM_APIC_REG_SIZE]; -}; struct kvm_segment { __u64 base; -- cgit v1.2.3 From 3a56b20104f51bd6caf07e49fa1e3c09bee222e5 Mon Sep 17 00:00:00 2001 From: Jerone Young Date: Mon, 19 Nov 2007 17:06:35 -0600 Subject: KVM: Portability: Move kvm_segment & kvm_dtable structure to This patch moves structures: kvm_segment kvm_dtable from include/linux/kvm.h to include/asm-x86/kvm.h Signed-off-by: Jerone Young Signed-off-by: Avi Kivity --- include/linux/kvm.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 280ec0d85b4c..442cb58bb73c 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -151,21 +151,6 @@ struct kvm_fpu { }; -struct kvm_segment { - __u64 base; - __u32 limit; - __u16 selector; - __u8 type; - __u8 present, dpl, db, s, l, g, avl; - __u8 unusable; - __u8 padding; -}; - -struct kvm_dtable { - __u64 base; - __u16 limit; - __u16 padding[3]; -}; /* for KVM_GET_SREGS and KVM_SET_SREGS */ struct kvm_sregs { -- cgit v1.2.3 From 244d57ece94b56692c61f2d507d1251b5844c550 Mon Sep 17 00:00:00 2001 From: Jerone Young Date: Mon, 19 Nov 2007 17:06:36 -0600 Subject: KVM: Portability: Move kvm_sregs and msr structures to Move structures: kvm_sregs kvm_msr_entry kvm_msrs kvm_msr_list from include/linux/kvm.h to include/asm-x86/kvm.h Signed-off-by: Avi Kivity --- include/linux/kvm.h | 36 ------------------------------------ 1 file changed, 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 442cb58bb73c..e6867aa6daf6 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -13,9 +13,6 @@ #define KVM_API_VERSION 12 -/* Architectural interrupt line count. */ -#define KVM_NR_INTERRUPTS 256 - /* for KVM_CREATE_MEMORY_REGION */ struct kvm_memory_region { __u32 slot; @@ -151,39 +148,6 @@ struct kvm_fpu { }; - -/* for KVM_GET_SREGS and KVM_SET_SREGS */ -struct kvm_sregs { - /* out (KVM_GET_SREGS) / in (KVM_SET_SREGS) */ - struct kvm_segment cs, ds, es, fs, gs, ss; - struct kvm_segment tr, ldt; - struct kvm_dtable gdt, idt; - __u64 cr0, cr2, cr3, cr4, cr8; - __u64 efer; - __u64 apic_base; - __u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64]; -}; - -struct kvm_msr_entry { - __u32 index; - __u32 reserved; - __u64 data; -}; - -/* for KVM_GET_MSRS and KVM_SET_MSRS */ -struct kvm_msrs { - __u32 nmsrs; /* number of msrs in entries */ - __u32 pad; - - struct kvm_msr_entry entries[0]; -}; - -/* for KVM_GET_MSR_INDEX_LIST */ -struct kvm_msr_list { - __u32 nmsrs; /* number of msrs in entries */ - __u32 indices[0]; -}; - /* for KVM_TRANSLATE */ struct kvm_translation { /* in */ -- cgit v1.2.3 From a162dd58736d446f52ca45b170508c3a5868807b Mon Sep 17 00:00:00 2001 From: Jerone Young Date: Mon, 19 Nov 2007 17:06:37 -0600 Subject: KVM: Portability: Move cpuid structures to This patch moves structures: kvm_cpuid_entry kvm_cpuid from include/linux/kvm.h to include/asm-x86/kvm.h Signed-off-by: Jerone Young Signed-off-by: Avi Kivity --- include/linux/kvm.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index e6867aa6daf6..fd4f900fcce3 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -192,22 +192,6 @@ struct kvm_dirty_log { }; }; -struct kvm_cpuid_entry { - __u32 function; - __u32 eax; - __u32 ebx; - __u32 ecx; - __u32 edx; - __u32 padding; -}; - -/* for KVM_SET_CPUID */ -struct kvm_cpuid { - __u32 nent; - __u32 padding; - struct kvm_cpuid_entry entries[0]; -}; - /* for KVM_SET_SIGNAL_MASK */ struct kvm_signal_mask { __u32 len; -- cgit v1.2.3 From 0771671749b59a507b6da4efb931c44d9691e248 Mon Sep 17 00:00:00 2001 From: Dan Kenigsberg Date: Wed, 21 Nov 2007 17:10:04 +0200 Subject: KVM: Enhance guest cpuid management The current cpuid management suffers from several problems, which inhibit passing through the host feature set to the guest: - No way to tell which features the host supports While some features can be supported with no changes to kvm, others need explicit support. That means kvm needs to vet the feature set before it is passed to the guest. - No support for indexed or stateful cpuid entries Some cpuid entries depend on ecx as well as on eax, or on internal state in the processor (running cpuid multiple times with the same input returns different output). The current cpuid machinery only supports keying on eax. - No support for save/restore/migrate The internal state above needs to be exposed to userspace so it can be saved or migrated. This patch adds extended cpuid support by means of three new ioctls: - KVM_GET_SUPPORTED_CPUID: get all cpuid entries the host (and kvm) supports - KVM_SET_CPUID2: sets the vcpu's cpuid table - KVM_GET_CPUID2: gets the vcpu's cpuid table, including hidden state [avi: fix original KVM_SET_CPUID not removing nx on non-nx hosts as it did before] Signed-off-by: Dan Kenigsberg Signed-off-by: Avi Kivity --- include/linux/kvm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index fd4f900fcce3..b751552f2e30 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -224,6 +224,7 @@ struct kvm_signal_mask { #define KVM_CAP_MMU_SHADOW_CACHE_CONTROL 2 #define KVM_CAP_USER_MEMORY 3 #define KVM_CAP_SET_TSS_ADDR 4 +#define KVM_CAP_EXT_CPUID 5 /* * ioctls for VM fds @@ -241,6 +242,7 @@ struct kvm_signal_mask { #define KVM_CREATE_VCPU _IO(KVMIO, 0x41) #define KVM_GET_DIRTY_LOG _IOW(KVMIO, 0x42, struct kvm_dirty_log) #define KVM_SET_MEMORY_ALIAS _IOW(KVMIO, 0x43, struct kvm_memory_alias) +#define KVM_GET_SUPPORTED_CPUID _IOWR(KVMIO, 0x48, struct kvm_cpuid2) /* Device model IOC */ #define KVM_CREATE_IRQCHIP _IO(KVMIO, 0x60) #define KVM_IRQ_LINE _IOW(KVMIO, 0x61, struct kvm_irq_level) @@ -266,5 +268,7 @@ struct kvm_signal_mask { #define KVM_SET_FPU _IOW(KVMIO, 0x8d, struct kvm_fpu) #define KVM_GET_LAPIC _IOR(KVMIO, 0x8e, struct kvm_lapic_state) #define KVM_SET_LAPIC _IOW(KVMIO, 0x8f, struct kvm_lapic_state) +#define KVM_SET_CPUID2 _IOW(KVMIO, 0x90, struct kvm_cpuid2) +#define KVM_GET_CPUID2 _IOWR(KVMIO, 0x91, struct kvm_cpuid2) #endif -- cgit v1.2.3 From 51e296258cba41759ff0de5da110d8d52675ee67 Mon Sep 17 00:00:00 2001 From: Jerone Young Date: Mon, 26 Nov 2007 08:33:53 -0600 Subject: KVM: Add ifdef in irqchip struct for x86 only structures This patch fixes a small issue where sturctures: kvm_pic_state kvm_ioapic_state are defined inside x86 specific code and may or may not be defined in anyway for other architectures. The problem caused is one cannot compile userspace apps (ex. libkvm) for other archs since a size cannot be determined for these structures. Signed-off-by: Jerone Young Signed-off-by: Avi Kivity --- include/linux/Kbuild | 2 +- include/linux/kvm.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 27b9350052b4..c263a69b5680 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -100,7 +100,6 @@ header-y += iso_fs.h header-y += ixjuser.h header-y += jffs2.h header-y += keyctl.h -header-y += kvm.h header-y += limits.h header-y += lock_dlm_plock.h header-y += magic.h @@ -256,6 +255,7 @@ unifdef-y += kd.h unifdef-y += kernelcapi.h unifdef-y += kernel.h unifdef-y += keyboard.h +unifdef-y += kvm.h unifdef-y += llc.h unifdef-y += loop.h unifdef-y += lp.h diff --git a/include/linux/kvm.h b/include/linux/kvm.h index b751552f2e30..f0bebd61ff77 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -51,8 +51,10 @@ struct kvm_irqchip { __u32 pad; union { char dummy[512]; /* reserving space */ +#ifdef CONFIG_X86 struct kvm_pic_state pic; struct kvm_ioapic_state ioapic; +#endif } chip; }; -- cgit v1.2.3 From fb56dbb31c4738a3918db81fd24da732ce3b4ae6 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sun, 2 Dec 2007 10:50:06 +0200 Subject: KVM: Export include/linux/kvm.h only if $ARCH actually supports KVM Currently, make headers_check barfs due to , which includes, not existing. Rather than add a zillion s, export kvm.h only if the arch actually supports it. Signed-off-by: Avi Kivity --- include/linux/Kbuild | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index c263a69b5680..85b2482cc736 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -255,7 +255,7 @@ unifdef-y += kd.h unifdef-y += kernelcapi.h unifdef-y += kernel.h unifdef-y += keyboard.h -unifdef-y += kvm.h +unifdef-$(CONFIG_HAVE_KVM) += kvm.h unifdef-y += llc.h unifdef-y += loop.h unifdef-y += lp.h -- cgit v1.2.3 From edf884172e9828c6234b254208af04655855038d Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sun, 16 Dec 2007 11:02:48 +0200 Subject: KVM: Move arch dependent files to new directory arch/x86/kvm/ This paves the way for multiple architecture support. Note that while ioapic.c could potentially be shared with ia64, it is also moved. Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 289 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/kvm_types.h | 54 +++++++++ 2 files changed, 343 insertions(+) create mode 100644 include/linux/kvm_host.h create mode 100644 include/linux/kvm_types.h (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h new file mode 100644 index 000000000000..a85d5b6943de --- /dev/null +++ b/include/linux/kvm_host.h @@ -0,0 +1,289 @@ +#ifndef __KVM_HOST_H +#define __KVM_HOST_H + +/* + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include + +#include + +#define KVM_MAX_VCPUS 4 +#define KVM_MEMORY_SLOTS 8 +/* memory slots that does not exposed to userspace */ +#define KVM_PRIVATE_MEM_SLOTS 4 + +#define KVM_PIO_PAGE_OFFSET 1 + +/* + * vcpu->requests bit members + */ +#define KVM_REQ_TLB_FLUSH 0 + + +struct kvm_vcpu; +extern struct kmem_cache *kvm_vcpu_cache; + +struct kvm_guest_debug { + int enabled; + unsigned long bp[4]; + int singlestep; +}; + +/* + * It would be nice to use something smarter than a linear search, TBD... + * Thankfully we dont expect many devices to register (famous last words :), + * so until then it will suffice. At least its abstracted so we can change + * in one place. + */ +struct kvm_io_bus { + int dev_count; +#define NR_IOBUS_DEVS 6 + struct kvm_io_device *devs[NR_IOBUS_DEVS]; +}; + +void kvm_io_bus_init(struct kvm_io_bus *bus); +void kvm_io_bus_destroy(struct kvm_io_bus *bus); +struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus, gpa_t addr); +void kvm_io_bus_register_dev(struct kvm_io_bus *bus, + struct kvm_io_device *dev); + +struct kvm_vcpu { + struct kvm *kvm; + struct preempt_notifier preempt_notifier; + int vcpu_id; + struct mutex mutex; + int cpu; + struct kvm_run *run; + int guest_mode; + unsigned long requests; + struct kvm_guest_debug guest_debug; + int fpu_active; + int guest_fpu_loaded; + wait_queue_head_t wq; + int sigset_active; + sigset_t sigset; + struct kvm_vcpu_stat stat; + +#ifdef CONFIG_HAS_IOMEM + int mmio_needed; + int mmio_read_completed; + int mmio_is_write; + int mmio_size; + unsigned char mmio_data[8]; + gpa_t mmio_phys_addr; +#endif + + struct kvm_vcpu_arch arch; +}; + +struct kvm_memory_slot { + gfn_t base_gfn; + unsigned long npages; + unsigned long flags; + unsigned long *rmap; + unsigned long *dirty_bitmap; + unsigned long userspace_addr; + int user_alloc; +}; + +struct kvm { + struct mutex lock; /* protects everything except vcpus */ + struct mm_struct *mm; /* userspace tied to this vm */ + int nmemslots; + struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS + + KVM_PRIVATE_MEM_SLOTS]; + struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; + struct list_head vm_list; + struct file *filp; + struct kvm_io_bus mmio_bus; + struct kvm_io_bus pio_bus; + struct kvm_vm_stat stat; + struct kvm_arch arch; +}; + +/* The guest did something we don't support. */ +#define pr_unimpl(vcpu, fmt, ...) \ + do { \ + if (printk_ratelimit()) \ + printk(KERN_ERR "kvm: %i: cpu%i " fmt, \ + current->tgid, (vcpu)->vcpu_id , ## __VA_ARGS__); \ + } while (0) + +#define kvm_printf(kvm, fmt ...) printk(KERN_DEBUG fmt) +#define vcpu_printf(vcpu, fmt...) kvm_printf(vcpu->kvm, fmt) + +int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id); +void kvm_vcpu_uninit(struct kvm_vcpu *vcpu); + +void vcpu_load(struct kvm_vcpu *vcpu); +void vcpu_put(struct kvm_vcpu *vcpu); + +void decache_vcpus_on_cpu(int cpu); + + +int kvm_init(void *opaque, unsigned int vcpu_size, + struct module *module); +void kvm_exit(void); + +#define HPA_MSB ((sizeof(hpa_t) * 8) - 1) +#define HPA_ERR_MASK ((hpa_t)1 << HPA_MSB) +static inline int is_error_hpa(hpa_t hpa) { return hpa >> HPA_MSB; } +struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva); + +extern struct page *bad_page; + +int is_error_page(struct page *page); +int kvm_is_error_hva(unsigned long addr); +int kvm_set_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + int user_alloc); +int __kvm_set_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + int user_alloc); +int kvm_arch_set_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + struct kvm_memory_slot old, + int user_alloc); +gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn); +struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn); +void kvm_release_page_clean(struct page *page); +void kvm_release_page_dirty(struct page *page); +int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, + int len); +int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len); +int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, + int offset, int len); +int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, + unsigned long len); +int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); +int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); +struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); +int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); +void mark_page_dirty(struct kvm *kvm, gfn_t gfn); + +void kvm_vcpu_block(struct kvm_vcpu *vcpu); +void kvm_resched(struct kvm_vcpu *vcpu); +void kvm_load_guest_fpu(struct kvm_vcpu *vcpu); +void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); +void kvm_flush_remote_tlbs(struct kvm *kvm); + +long kvm_arch_dev_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg); +long kvm_arch_vcpu_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg); +void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu); +void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu); + +int kvm_dev_ioctl_check_extension(long ext); + +int kvm_get_dirty_log(struct kvm *kvm, + struct kvm_dirty_log *log, int *is_dirty); +int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, + struct kvm_dirty_log *log); + +int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, + struct + kvm_userspace_memory_region *mem, + int user_alloc); +long kvm_arch_vm_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg); +void kvm_arch_destroy_vm(struct kvm *kvm); + +int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); +int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); + +int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, + struct kvm_translation *tr); + +int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs); +int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs); +int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs); +int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs); +int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, + struct kvm_debug_guest *dbg); +int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run); + +int kvm_arch_init(void *opaque); +void kvm_arch_exit(void); + +int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu); +void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu); + +void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu); +void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu); +void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu); +struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id); +int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu); +void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu); + +int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu); +void kvm_arch_hardware_enable(void *garbage); +void kvm_arch_hardware_disable(void *garbage); +int kvm_arch_hardware_setup(void); +void kvm_arch_hardware_unsetup(void); +void kvm_arch_check_processor_compat(void *rtn); +int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); + +void kvm_free_physmem(struct kvm *kvm); + +struct kvm *kvm_arch_create_vm(void); +void kvm_arch_destroy_vm(struct kvm *kvm); + +int kvm_cpu_get_interrupt(struct kvm_vcpu *v); +int kvm_cpu_has_interrupt(struct kvm_vcpu *v); + +static inline void kvm_guest_enter(void) +{ + account_system_vtime(current); + current->flags |= PF_VCPU; +} + +static inline void kvm_guest_exit(void) +{ + account_system_vtime(current); + current->flags &= ~PF_VCPU; +} + +static inline int memslot_id(struct kvm *kvm, struct kvm_memory_slot *slot) +{ + return slot - kvm->memslots; +} + +static inline gpa_t gfn_to_gpa(gfn_t gfn) +{ + return (gpa_t)gfn << PAGE_SHIFT; +} + +enum kvm_stat_kind { + KVM_STAT_VM, + KVM_STAT_VCPU, +}; + +struct kvm_stats_debugfs_item { + const char *name; + int offset; + enum kvm_stat_kind kind; + struct dentry *dentry; +}; +extern struct kvm_stats_debugfs_item debugfs_entries[]; + +#endif diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h new file mode 100644 index 000000000000..1c4e46decb22 --- /dev/null +++ b/include/linux/kvm_types.h @@ -0,0 +1,54 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + */ + +#ifndef __KVM_TYPES_H__ +#define __KVM_TYPES_H__ + +#include + +/* + * Address types: + * + * gva - guest virtual address + * gpa - guest physical address + * gfn - guest frame number + * hva - host virtual address + * hpa - host physical address + * hfn - host frame number + */ + +typedef unsigned long gva_t; +typedef u64 gpa_t; +typedef unsigned long gfn_t; + +typedef unsigned long hva_t; +typedef u64 hpa_t; +typedef unsigned long hfn_t; + +struct kvm_pio_request { + unsigned long count; + int cur_count; + struct page *guest_pages[2]; + unsigned guest_page_offset; + int in; + int port; + int size; + int string; + int down; + int rep; +}; + +#endif /* __KVM_TYPES_H__ */ -- cgit v1.2.3 From 5736199afba8a8bb60a1ea282ab72857d6b16400 Mon Sep 17 00:00:00 2001 From: Zhang Xiantao Date: Mon, 17 Dec 2007 14:21:40 +0800 Subject: KVM: Move kvm_vcpu_kick() to x86.c Moving kvm_vcpu_kick() to x86.c. Since it should be common for all archs, put its declarations in Signed-off-by: Zhang Xiantao Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a85d5b6943de..953b50aa0e61 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -250,6 +250,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *v); +void kvm_vcpu_kick(struct kvm_vcpu *vcpu); static inline void kvm_guest_enter(void) { -- cgit v1.2.3 From ec10f4750db5e810cafef114a592428f8242b640 Mon Sep 17 00:00:00 2001 From: Zhang Xiantao Date: Mon, 17 Dec 2007 20:27:27 +0800 Subject: KVM: Expose ioapic to ia64 save/restore APIs IA64 also needs to see ioapic structure in irqchip. Signed-off-by: xiantao.zhang@intel.com Signed-off-by: Avi Kivity --- include/linux/kvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index f0bebd61ff77..de9f28d96ced 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -53,6 +53,8 @@ struct kvm_irqchip { char dummy[512]; /* reserving space */ #ifdef CONFIG_X86 struct kvm_pic_state pic; +#endif +#if defined(CONFIG_X86) || defined(CONFIG_IA64) struct kvm_ioapic_state ioapic; #endif } chip; -- cgit v1.2.3 From b209749f528488c4c0d20a42c0fbcbf49e6933b3 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Mon, 22 Oct 2007 16:50:39 +0200 Subject: KVM: local APIC TPR access reporting facility Add a facility to report on accesses to the local apic tpr even if the local apic is emulated in the kernel. This is basically a hack that allows userspace to patch Windows which tends to bang on the tpr a lot. Signed-off-by: Avi Kivity --- include/linux/kvm.h | 17 +++++++++++++++++ include/linux/kvm_host.h | 2 +- 2 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index de9f28d96ced..850f5ef76636 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -72,6 +72,7 @@ struct kvm_irqchip { #define KVM_EXIT_FAIL_ENTRY 9 #define KVM_EXIT_INTR 10 #define KVM_EXIT_SET_TPR 11 +#define KVM_EXIT_TPR_ACCESS 12 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */ struct kvm_run { @@ -130,6 +131,12 @@ struct kvm_run { __u32 longmode; __u32 pad; } hypercall; + /* KVM_EXIT_TPR_ACCESS */ + struct { + __u64 rip; + __u32 is_write; + __u32 pad; + } tpr_access; /* Fix the size of the union. */ char padding[256]; }; @@ -202,6 +209,13 @@ struct kvm_signal_mask { __u8 sigset[0]; }; +/* for KVM_TPR_ACCESS_REPORTING */ +struct kvm_tpr_access_ctl { + __u32 enabled; + __u32 flags; + __u32 reserved[8]; +}; + #define KVMIO 0xAE /* @@ -229,6 +243,7 @@ struct kvm_signal_mask { #define KVM_CAP_USER_MEMORY 3 #define KVM_CAP_SET_TSS_ADDR 4 #define KVM_CAP_EXT_CPUID 5 +#define KVM_CAP_VAPIC 6 /* * ioctls for VM fds @@ -274,5 +289,7 @@ struct kvm_signal_mask { #define KVM_SET_LAPIC _IOW(KVMIO, 0x8f, struct kvm_lapic_state) #define KVM_SET_CPUID2 _IOW(KVMIO, 0x90, struct kvm_cpuid2) #define KVM_GET_CPUID2 _IOWR(KVMIO, 0x91, struct kvm_cpuid2) +/* Available with KVM_CAP_VAPIC */ +#define KVM_TPR_ACCESS_REPORTING _IOWR(KVMIO, 0x92, struct kvm_tpr_access_ctl) #endif diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 953b50aa0e61..9ff5904c5072 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -35,7 +35,7 @@ * vcpu->requests bit members */ #define KVM_REQ_TLB_FLUSH 0 - +#define KVM_REQ_REPORT_TPR_ACCESS 2 struct kvm_vcpu; extern struct kmem_cache *kvm_vcpu_cache; -- cgit v1.2.3 From b93463aa59d67b21b4921e30bd5c5dcc7c35ffbd Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Thu, 25 Oct 2007 16:52:32 +0200 Subject: KVM: Accelerated apic support This adds a mechanism for exposing the virtual apic tpr to the guest, and a protocol for letting the guest update the tpr without causing a vmexit if conditions allow (e.g. there is no interrupt pending with a higher priority than the new tpr). Signed-off-by: Avi Kivity --- include/linux/kvm.h | 7 +++++++ include/linux/kvm_para.h | 2 ++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 850f5ef76636..b27a381db5e8 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -216,6 +216,11 @@ struct kvm_tpr_access_ctl { __u32 reserved[8]; }; +/* for KVM_SET_VAPIC_ADDR */ +struct kvm_vapic_addr { + __u64 vapic_addr; +}; + #define KVMIO 0xAE /* @@ -291,5 +296,7 @@ struct kvm_tpr_access_ctl { #define KVM_GET_CPUID2 _IOWR(KVMIO, 0x91, struct kvm_cpuid2) /* Available with KVM_CAP_VAPIC */ #define KVM_TPR_ACCESS_REPORTING _IOWR(KVMIO, 0x92, struct kvm_tpr_access_ctl) +/* Available with KVM_CAP_VAPIC */ +#define KVM_SET_VAPIC_ADDR _IOW(KVMIO, 0x93, struct kvm_vapic_addr) #endif diff --git a/include/linux/kvm_para.h b/include/linux/kvm_para.h index e4db25ffdb52..6af91a506fbf 100644 --- a/include/linux/kvm_para.h +++ b/include/linux/kvm_para.h @@ -12,6 +12,8 @@ /* Return values for hypercalls */ #define KVM_ENOSYS 1000 +#define KVM_HC_VAPIC_POLL_IRQ 1 + #ifdef __KERNEL__ /* * hypercalls use architecture specific -- cgit v1.2.3 From 7ec54588210df29ea637e6054489bc942c0ef371 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Thu, 20 Dec 2007 19:18:23 -0500 Subject: KVM: Add kvm_read_guest_atomic() In preparation for a mmu spinlock, add kvm_read_guest_atomic() and use it in fetch() and prefetch_page(). Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9ff5904c5072..a020fb280540 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -167,6 +167,8 @@ void kvm_release_page_clean(struct page *page); void kvm_release_page_dirty(struct page *page); int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len); +int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data, + unsigned long len); int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len); int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, int offset, int len); -- cgit v1.2.3 From aaee2c94f7a1f7726e360a6cfb40173bd552bcff Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Thu, 20 Dec 2007 19:18:26 -0500 Subject: KVM: MMU: Switch to mmu spinlock Convert the synchronization of the shadow handling to a separate mmu_lock spinlock. Also guard fetch() by mmap_sem in read-mode to protect against alias and memslot changes. Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a020fb280540..2714068ee8bc 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -104,7 +104,8 @@ struct kvm_memory_slot { }; struct kvm { - struct mutex lock; /* protects everything except vcpus */ + struct mutex lock; /* protects the vcpus array and APIC accesses */ + spinlock_t mmu_lock; struct mm_struct *mm; /* userspace tied to this vm */ int nmemslots; struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS + -- cgit v1.2.3 From 6f723c7911e7827091586ae63f4040874eeb75e5 Mon Sep 17 00:00:00 2001 From: Christian Ehrhardt Date: Tue, 8 Jan 2008 08:04:50 +0100 Subject: KVM: Portability: Move kvm_fpu to asm-x86/kvm.h This patch moves kvm_fpu asm-x86/kvm.h to allow every architecture to define an own representation used for KVM_GET_FPU/KVM_SET_FPU. Signed-off-by: Christian Ehrhardt Acked-by: Carsten Otte Acked-by: Zhang Xiantao Signed-off-by: Avi Kivity --- include/linux/kvm.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index b27a381db5e8..4de4fd2d8607 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -142,23 +142,6 @@ struct kvm_run { }; }; - -/* for KVM_GET_FPU and KVM_SET_FPU */ -struct kvm_fpu { - __u8 fpr[8][16]; - __u16 fcw; - __u16 fsw; - __u8 ftwx; /* in fxsave format */ - __u8 pad1; - __u16 last_opcode; - __u64 last_ip; - __u64 last_dp; - __u8 xmm[16][16]; - __u32 mxcsr; - __u32 pad2; -}; - - /* for KVM_TRANSLATE */ struct kvm_translation { /* in */ -- cgit v1.2.3 From a03d7f4b544f699bbdd3cf14692bd8f476cb9d24 Mon Sep 17 00:00:00 2001 From: Glauber de Oliveira Costa Date: Tue, 15 Jan 2008 13:10:15 -0200 Subject: KVM: Put kvm_para.h include outside __KERNEL__ kvm_para.h potentially contains definitions that are to be used by userspace, so it should not be included inside the __KERNEL__ block. To protect its own data structures, kvm_para.h already includes its own __KERNEL__ block. Signed-off-by: Glauber de Oliveira Costa Acked-by: Amit Shah Signed-off-by: Avi Kivity --- include/linux/kvm_para.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_para.h b/include/linux/kvm_para.h index 6af91a506fbf..5497aac0d2f8 100644 --- a/include/linux/kvm_para.h +++ b/include/linux/kvm_para.h @@ -14,12 +14,12 @@ #define KVM_HC_VAPIC_POLL_IRQ 1 -#ifdef __KERNEL__ /* * hypercalls use architecture specific */ #include +#ifdef __KERNEL__ static inline int kvm_para_has_feature(unsigned int feature) { if (kvm_arch_para_features() & (1UL << feature)) -- cgit v1.2.3 From 2f52d58c92d971bf421f461ad06eb93fb4f34981 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 16 Jan 2008 12:49:30 +0200 Subject: KVM: Move apic timer migration away from critical section Migrating the apic timer in the critical section is not very nice, and is absolutely horrible with the real-time port. Move migration to the regular vcpu execution path, triggered by a new bitflag. Cc: Thomas Gleixner Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2714068ee8bc..ea4764b0a2f4 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -35,6 +35,7 @@ * vcpu->requests bit members */ #define KVM_REQ_TLB_FLUSH 0 +#define KVM_REQ_MIGRATE_TIMER 1 #define KVM_REQ_REPORT_TPR_ACCESS 2 struct kvm_vcpu; @@ -277,6 +278,11 @@ static inline gpa_t gfn_to_gpa(gfn_t gfn) return (gpa_t)gfn << PAGE_SHIFT; } +static inline void kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) +{ + set_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests); +} + enum kvm_stat_kind { KVM_STAT_VM, KVM_STAT_VCPU, -- cgit v1.2.3