From 099f53cb50e45ef617a9f1d63ceec799e489418b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 8 Apr 2009 14:28:37 -0700 Subject: async_tx: rename zero_sum to val 'zero_sum' does not properly describe the operation of generating parity and checking that it validates against an existing buffer. Change the name of the operation to 'val' (for 'validate'). This is in anticipation of the p+q case where it is a requirement to identify the target parity buffers separately from the source buffers, because the target parity buffers will not have corresponding pq coefficients. Reviewed-by: Andre Noll Acked-by: Maciej Sosnowski Signed-off-by: Dan Williams --- include/linux/async_tx.h | 2 +- include/linux/dmaengine.h | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h index 5fc2ef8d97fa..513150d8c25b 100644 --- a/include/linux/async_tx.h +++ b/include/linux/async_tx.h @@ -117,7 +117,7 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset, dma_async_tx_callback cb_fn, void *cb_fn_param); struct dma_async_tx_descriptor * -async_xor_zero_sum(struct page *dest, struct page **src_list, +async_xor_val(struct page *dest, struct page **src_list, unsigned int offset, int src_cnt, size_t len, u32 *result, enum async_tx_flags flags, struct dma_async_tx_descriptor *depend_tx, diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 2e2aa3df170c..6768727d00d7 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -55,8 +55,8 @@ enum dma_transaction_type { DMA_PQ_XOR, DMA_DUAL_XOR, DMA_PQ_UPDATE, - DMA_ZERO_SUM, - DMA_PQ_ZERO_SUM, + DMA_XOR_VAL, + DMA_PQ_VAL, DMA_MEMSET, DMA_MEMCPY_CRC32C, DMA_INTERRUPT, @@ -214,7 +214,7 @@ struct dma_async_tx_descriptor { * @device_free_chan_resources: release DMA channel's resources * @device_prep_dma_memcpy: prepares a memcpy operation * @device_prep_dma_xor: prepares a xor operation - * @device_prep_dma_zero_sum: prepares a zero_sum operation + * @device_prep_dma_xor_val: prepares a xor validation operation * @device_prep_dma_memset: prepares a memset operation * @device_prep_dma_interrupt: prepares an end of chain interrupt operation * @device_prep_slave_sg: prepares a slave dma operation @@ -243,7 +243,7 @@ struct dma_device { struct dma_async_tx_descriptor *(*device_prep_dma_xor)( struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src, unsigned int src_cnt, size_t len, unsigned long flags); - struct dma_async_tx_descriptor *(*device_prep_dma_zero_sum)( + struct dma_async_tx_descriptor *(*device_prep_dma_xor_val)( struct dma_chan *chan, dma_addr_t *src, unsigned int src_cnt, size_t len, u32 *result, unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_dma_memset)( -- cgit v1.2.3 From 88ba2aa586c874681c072101287e15d40de7e6e2 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 9 Apr 2009 16:16:18 -0700 Subject: async_tx: kill ASYNC_TX_DEP_ACK flag In support of inter-channel chaining async_tx utilizes an ack flag to gate whether a dependent operation can be chained to another. While the flag is not set the chain can be considered open for appending. Setting the ack flag closes the chain and flags the descriptor for garbage collection. The ASYNC_TX_DEP_ACK flag essentially means "close the chain after adding this dependency". Since each operation can only have one child the api now implicitly sets the ack flag at dependency submission time. This removes an unnecessary management burden from clients of the api. [ Impact: clean up and enforce one dependency per operation ] Reviewed-by: Andre Noll Acked-by: Maciej Sosnowski Signed-off-by: Dan Williams --- include/linux/async_tx.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h index 513150d8c25b..9f14cd540cd2 100644 --- a/include/linux/async_tx.h +++ b/include/linux/async_tx.h @@ -58,13 +58,11 @@ struct dma_chan_ref { * array. * @ASYNC_TX_ACK: immediately ack the descriptor, precludes setting up a * dependency chain - * @ASYNC_TX_DEP_ACK: ack the dependency descriptor. Useful for chaining. */ enum async_tx_flags { ASYNC_TX_XOR_ZERO_DST = (1 << 0), ASYNC_TX_XOR_DROP_DST = (1 << 1), - ASYNC_TX_ACK = (1 << 3), - ASYNC_TX_DEP_ACK = (1 << 4), + ASYNC_TX_ACK = (1 << 2), }; #ifdef CONFIG_DMA_ENGINE -- cgit v1.2.3 From a08abd8ca890a377521d65d493d174bebcaf694b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 3 Jun 2009 11:43:59 -0700 Subject: async_tx: structify submission arguments, add scribble Prepare the api for the arrival of a new parameter, 'scribble'. This will allow callers to identify scratchpad memory for dma address or page address conversions. As this adds yet another parameter, take this opportunity to convert the common submission parameters (flags, dependency, callback, and callback argument) into an object that is passed by reference. Also, take this opportunity to fix up the kerneldoc and add notes about the relevant ASYNC_TX_* flags for each routine. [ Impact: moves api pass-by-value parameters to a pass-by-reference struct ] Signed-off-by: Andre Noll Acked-by: Maciej Sosnowski Signed-off-by: Dan Williams --- include/linux/async_tx.h | 84 +++++++++++++++++++++++++++++++----------------- 1 file changed, 54 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h index 9f14cd540cd2..00cfb637ddf2 100644 --- a/include/linux/async_tx.h +++ b/include/linux/async_tx.h @@ -65,6 +65,22 @@ enum async_tx_flags { ASYNC_TX_ACK = (1 << 2), }; +/** + * struct async_submit_ctl - async_tx submission/completion modifiers + * @flags: submission modifiers + * @depend_tx: parent dependency of the current operation being submitted + * @cb_fn: callback routine to run at operation completion + * @cb_param: parameter for the callback routine + * @scribble: caller provided space for dma/page address conversions + */ +struct async_submit_ctl { + enum async_tx_flags flags; + struct dma_async_tx_descriptor *depend_tx; + dma_async_tx_callback cb_fn; + void *cb_param; + void *scribble; +}; + #ifdef CONFIG_DMA_ENGINE #define async_tx_issue_pending_all dma_issue_pending_all #ifdef CONFIG_ARCH_HAS_ASYNC_TX_FIND_CHANNEL @@ -73,8 +89,8 @@ enum async_tx_flags { #define async_tx_find_channel(dep, type, dst, dst_count, src, src_count, len) \ __async_tx_find_channel(dep, type) struct dma_chan * -__async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx, - enum dma_transaction_type tx_type); +__async_tx_find_channel(struct async_submit_ctl *submit, + enum dma_transaction_type tx_type); #endif /* CONFIG_ARCH_HAS_ASYNC_TX_FIND_CHANNEL */ #else static inline void async_tx_issue_pending_all(void) @@ -83,9 +99,10 @@ static inline void async_tx_issue_pending_all(void) } static inline struct dma_chan * -async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx, - enum dma_transaction_type tx_type, struct page **dst, int dst_count, - struct page **src, int src_count, size_t len) +async_tx_find_channel(struct async_submit_ctl *submit, + enum dma_transaction_type tx_type, struct page **dst, + int dst_count, struct page **src, int src_count, + size_t len) { return NULL; } @@ -97,46 +114,53 @@ async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx, * @cb_fn_param: parameter to pass to the callback routine */ static inline void -async_tx_sync_epilog(dma_async_tx_callback cb_fn, void *cb_fn_param) +async_tx_sync_epilog(struct async_submit_ctl *submit) +{ + if (submit->cb_fn) + submit->cb_fn(submit->cb_param); +} + +typedef union { + unsigned long addr; + struct page *page; + dma_addr_t dma; +} addr_conv_t; + +static inline void +init_async_submit(struct async_submit_ctl *args, enum async_tx_flags flags, + struct dma_async_tx_descriptor *tx, + dma_async_tx_callback cb_fn, void *cb_param, + addr_conv_t *scribble) { - if (cb_fn) - cb_fn(cb_fn_param); + args->flags = flags; + args->depend_tx = tx; + args->cb_fn = cb_fn; + args->cb_param = cb_param; + args->scribble = scribble; } -void -async_tx_submit(struct dma_chan *chan, struct dma_async_tx_descriptor *tx, - enum async_tx_flags flags, struct dma_async_tx_descriptor *depend_tx, - dma_async_tx_callback cb_fn, void *cb_fn_param); +void async_tx_submit(struct dma_chan *chan, struct dma_async_tx_descriptor *tx, + struct async_submit_ctl *submit); struct dma_async_tx_descriptor * async_xor(struct page *dest, struct page **src_list, unsigned int offset, - int src_cnt, size_t len, enum async_tx_flags flags, - struct dma_async_tx_descriptor *depend_tx, - dma_async_tx_callback cb_fn, void *cb_fn_param); + int src_cnt, size_t len, struct async_submit_ctl *submit); struct dma_async_tx_descriptor * -async_xor_val(struct page *dest, struct page **src_list, - unsigned int offset, int src_cnt, size_t len, - u32 *result, enum async_tx_flags flags, - struct dma_async_tx_descriptor *depend_tx, - dma_async_tx_callback cb_fn, void *cb_fn_param); +async_xor_val(struct page *dest, struct page **src_list, unsigned int offset, + int src_cnt, size_t len, u32 *result, + struct async_submit_ctl *submit); struct dma_async_tx_descriptor * async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset, - unsigned int src_offset, size_t len, enum async_tx_flags flags, - struct dma_async_tx_descriptor *depend_tx, - dma_async_tx_callback cb_fn, void *cb_fn_param); + unsigned int src_offset, size_t len, + struct async_submit_ctl *submit); struct dma_async_tx_descriptor * async_memset(struct page *dest, int val, unsigned int offset, - size_t len, enum async_tx_flags flags, - struct dma_async_tx_descriptor *depend_tx, - dma_async_tx_callback cb_fn, void *cb_fn_param); + size_t len, struct async_submit_ctl *submit); -struct dma_async_tx_descriptor * -async_trigger_callback(enum async_tx_flags flags, - struct dma_async_tx_descriptor *depend_tx, - dma_async_tx_callback cb_fn, void *cb_fn_param); +struct dma_async_tx_descriptor *async_trigger_callback(struct async_submit_ctl *submit); void async_tx_quiesce(struct dma_async_tx_descriptor **tx); #endif /* _ASYNC_TX_H_ */ -- cgit v1.2.3 From ad283ea4a3ce82cda2efe33163748a397b31b1eb Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sat, 29 Aug 2009 19:09:26 -0700 Subject: async_tx: add sum check flags Replace the flat zero_sum_result with a collection of flags to contain the P (xor) zero-sum result, and the soon to be utilized Q (raid6 reed solomon syndrome) zero-sum result. Use the SUM_CHECK_ namespace instead of DMA_ since these flags will be used on non-dma-zero-sum enabled platforms. Reviewed-by: Andre Noll Acked-by: Maciej Sosnowski Signed-off-by: Dan Williams --- include/linux/async_tx.h | 2 +- include/linux/dmaengine.h | 21 ++++++++++++++++++++- 2 files changed, 21 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h index 00cfb637ddf2..3d21a2517518 100644 --- a/include/linux/async_tx.h +++ b/include/linux/async_tx.h @@ -148,7 +148,7 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset, struct dma_async_tx_descriptor * async_xor_val(struct page *dest, struct page **src_list, unsigned int offset, - int src_cnt, size_t len, u32 *result, + int src_cnt, size_t len, enum sum_check_flags *result, struct async_submit_ctl *submit); struct dma_async_tx_descriptor * diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 6768727d00d7..02447afcebad 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -86,6 +86,25 @@ enum dma_ctrl_flags { DMA_COMPL_SKIP_DEST_UNMAP = (1 << 3), }; +/** + * enum sum_check_bits - bit position of pq_check_flags + */ +enum sum_check_bits { + SUM_CHECK_P = 0, + SUM_CHECK_Q = 1, +}; + +/** + * enum pq_check_flags - result of async_{xor,pq}_zero_sum operations + * @SUM_CHECK_P_RESULT - 1 if xor zero sum error, 0 otherwise + * @SUM_CHECK_Q_RESULT - 1 if reed-solomon zero sum error, 0 otherwise + */ +enum sum_check_flags { + SUM_CHECK_P_RESULT = (1 << SUM_CHECK_P), + SUM_CHECK_Q_RESULT = (1 << SUM_CHECK_Q), +}; + + /** * dma_cap_mask_t - capabilities bitmap modeled after cpumask_t. * See linux/cpumask.h @@ -245,7 +264,7 @@ struct dma_device { unsigned int src_cnt, size_t len, unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_dma_xor_val)( struct dma_chan *chan, dma_addr_t *src, unsigned int src_cnt, - size_t len, u32 *result, unsigned long flags); + size_t len, enum sum_check_flags *result, unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_dma_memset)( struct dma_chan *chan, dma_addr_t dest, int value, size_t len, unsigned long flags); -- cgit v1.2.3 From 95475e57113c66aac7583925736ed2e2d58c990d Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 14 Jul 2009 12:19:02 -0700 Subject: async_tx: remove walk of tx->parent chain in dma_wait_for_async_tx We currently walk the parent chain when waiting for a given tx to complete however this walk may race with the driver cleanup routine. The routines in async_raid6_recov.c may fall back to the synchronous path at any point so we need to be prepared to call async_tx_quiesce() (which calls dma_wait_for_async_tx). To remove the ->parent walk we guarantee that every time a dependency is attached ->issue_pending() is invoked, then we can simply poll the initial descriptor until completion. This also allows for a lighter weight 'issue pending' implementation as there is no longer a requirement to iterate through all the channels' ->issue_pending() routines as long as operations have been submitted in an ordered chain. async_tx_issue_pending() is added for this case. Signed-off-by: Dan Williams --- include/linux/async_tx.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h index 3d21a2517518..12a2efcbd565 100644 --- a/include/linux/async_tx.h +++ b/include/linux/async_tx.h @@ -83,6 +83,24 @@ struct async_submit_ctl { #ifdef CONFIG_DMA_ENGINE #define async_tx_issue_pending_all dma_issue_pending_all + +/** + * async_tx_issue_pending - send pending descriptor to the hardware channel + * @tx: descriptor handle to retrieve hardware context + * + * Note: any dependent operations will have already been issued by + * async_tx_channel_switch, or (in the case of no channel switch) will + * be already pending on this channel. + */ +static inline void async_tx_issue_pending(struct dma_async_tx_descriptor *tx) +{ + if (likely(tx)) { + struct dma_chan *chan = tx->chan; + struct dma_device *dma = chan->device; + + dma->device_issue_pending(chan); + } +} #ifdef CONFIG_ARCH_HAS_ASYNC_TX_FIND_CHANNEL #include #else @@ -98,6 +116,11 @@ static inline void async_tx_issue_pending_all(void) do { } while (0); } +static inline void async_tx_issue_pending(struct dma_async_tx_descriptor *tx) +{ + do { } while (0); +} + static inline struct dma_chan * async_tx_find_channel(struct async_submit_ctl *submit, enum dma_transaction_type tx_type, struct page **dst, -- cgit v1.2.3 From b2f46fd8ef3dff2ab30f31126833f78b7480283a Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 14 Jul 2009 12:20:36 -0700 Subject: async_tx: add support for asynchronous GF multiplication [ Based on an original patch by Yuri Tikhonov ] This adds support for doing asynchronous GF multiplication by adding two additional functions to the async_tx API: async_gen_syndrome() does simultaneous XOR and Galois field multiplication of sources. async_syndrome_val() validates the given source buffers against known P and Q values. When a request is made to run async_pq against more than the hardware maximum number of supported sources we need to reuse the previous generated P and Q values as sources into the next operation. Care must be taken to remove Q from P' and P from Q'. For example to perform a 5 source pq op with hardware that only supports 4 sources at a time the following approach is taken: p, q = PQ(src0, src1, src2, src3, COEF({01}, {02}, {04}, {08})) p', q' = PQ(p, q, q, src4, COEF({00}, {01}, {00}, {10})) p' = p + q + q + src4 = p + src4 q' = {00}*p + {01}*q + {00}*q + {10}*src4 = q + {10}*src4 Note: 4 is the minimum acceptable maxpq otherwise we punt to synchronous-software path. The DMA_PREP_CONTINUE flag indicates to the driver to reuse p and q as sources (in the above manner) and fill the remaining slots up to maxpq with the new sources/coefficients. Note1: Some devices have native support for P+Q continuation and can skip this extra work. Devices with this capability can advertise it with dma_set_maxpq. It is up to each driver how to handle the DMA_PREP_CONTINUE flag. Note2: The api supports disabling the generation of P when generating Q, this is ignored by the synchronous path but is implemented by some dma devices to save unnecessary writes. In this case the continuation algorithm is simplified to only reuse Q as a source. Cc: H. Peter Anvin Cc: David Woodhouse Signed-off-by: Yuri Tikhonov Signed-off-by: Ilya Yanok Reviewed-by: Andre Noll Acked-by: Maciej Sosnowski Signed-off-by: Dan Williams --- include/linux/async_tx.h | 9 +++++ include/linux/dmaengine.h | 87 +++++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 90 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h index 12a2efcbd565..e6ce5f004f98 100644 --- a/include/linux/async_tx.h +++ b/include/linux/async_tx.h @@ -185,5 +185,14 @@ async_memset(struct page *dest, int val, unsigned int offset, struct dma_async_tx_descriptor *async_trigger_callback(struct async_submit_ctl *submit); +struct dma_async_tx_descriptor * +async_gen_syndrome(struct page **blocks, unsigned int offset, int src_cnt, + size_t len, struct async_submit_ctl *submit); + +struct dma_async_tx_descriptor * +async_syndrome_val(struct page **blocks, unsigned int offset, int src_cnt, + size_t len, enum sum_check_flags *pqres, struct page *spare, + struct async_submit_ctl *submit); + void async_tx_quiesce(struct dma_async_tx_descriptor **tx); #endif /* _ASYNC_TX_H_ */ diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 02447afcebad..ce010cd991d2 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -52,7 +52,7 @@ enum dma_status { enum dma_transaction_type { DMA_MEMCPY, DMA_XOR, - DMA_PQ_XOR, + DMA_PQ, DMA_DUAL_XOR, DMA_PQ_UPDATE, DMA_XOR_VAL, @@ -70,20 +70,28 @@ enum dma_transaction_type { /** * enum dma_ctrl_flags - DMA flags to augment operation preparation, - * control completion, and communicate status. + * control completion, and communicate status. * @DMA_PREP_INTERRUPT - trigger an interrupt (callback) upon completion of - * this transaction + * this transaction * @DMA_CTRL_ACK - the descriptor cannot be reused until the client - * acknowledges receipt, i.e. has has a chance to establish any - * dependency chains + * acknowledges receipt, i.e. has has a chance to establish any dependency + * chains * @DMA_COMPL_SKIP_SRC_UNMAP - set to disable dma-unmapping the source buffer(s) * @DMA_COMPL_SKIP_DEST_UNMAP - set to disable dma-unmapping the destination(s) + * @DMA_PREP_PQ_DISABLE_P - prevent generation of P while generating Q + * @DMA_PREP_PQ_DISABLE_Q - prevent generation of Q while generating P + * @DMA_PREP_CONTINUE - indicate to a driver that it is reusing buffers as + * sources that were the result of a previous operation, in the case of a PQ + * operation it continues the calculation with new sources */ enum dma_ctrl_flags { DMA_PREP_INTERRUPT = (1 << 0), DMA_CTRL_ACK = (1 << 1), DMA_COMPL_SKIP_SRC_UNMAP = (1 << 2), DMA_COMPL_SKIP_DEST_UNMAP = (1 << 3), + DMA_PREP_PQ_DISABLE_P = (1 << 4), + DMA_PREP_PQ_DISABLE_Q = (1 << 5), + DMA_PREP_CONTINUE = (1 << 6), }; /** @@ -226,6 +234,7 @@ struct dma_async_tx_descriptor { * @global_node: list_head for global dma_device_list * @cap_mask: one or more dma_capability flags * @max_xor: maximum number of xor sources, 0 if no capability + * @max_pq: maximum number of PQ sources and PQ-continue capability * @dev_id: unique device ID * @dev: struct device reference for dma mapping api * @device_alloc_chan_resources: allocate resources and return the @@ -234,6 +243,8 @@ struct dma_async_tx_descriptor { * @device_prep_dma_memcpy: prepares a memcpy operation * @device_prep_dma_xor: prepares a xor operation * @device_prep_dma_xor_val: prepares a xor validation operation + * @device_prep_dma_pq: prepares a pq operation + * @device_prep_dma_pq_val: prepares a pqzero_sum operation * @device_prep_dma_memset: prepares a memset operation * @device_prep_dma_interrupt: prepares an end of chain interrupt operation * @device_prep_slave_sg: prepares a slave dma operation @@ -248,7 +259,9 @@ struct dma_device { struct list_head channels; struct list_head global_node; dma_cap_mask_t cap_mask; - int max_xor; + unsigned short max_xor; + unsigned short max_pq; + #define DMA_HAS_PQ_CONTINUE (1 << 15) int dev_id; struct device *dev; @@ -265,6 +278,14 @@ struct dma_device { struct dma_async_tx_descriptor *(*device_prep_dma_xor_val)( struct dma_chan *chan, dma_addr_t *src, unsigned int src_cnt, size_t len, enum sum_check_flags *result, unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_dma_pq)( + struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src, + unsigned int src_cnt, const unsigned char *scf, + size_t len, unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_dma_pq_val)( + struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src, + unsigned int src_cnt, const unsigned char *scf, size_t len, + enum sum_check_flags *pqres, unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_dma_memset)( struct dma_chan *chan, dma_addr_t dest, int value, size_t len, unsigned long flags); @@ -283,6 +304,60 @@ struct dma_device { void (*device_issue_pending)(struct dma_chan *chan); }; +static inline void +dma_set_maxpq(struct dma_device *dma, int maxpq, int has_pq_continue) +{ + dma->max_pq = maxpq; + if (has_pq_continue) + dma->max_pq |= DMA_HAS_PQ_CONTINUE; +} + +static inline bool dmaf_continue(enum dma_ctrl_flags flags) +{ + return (flags & DMA_PREP_CONTINUE) == DMA_PREP_CONTINUE; +} + +static inline bool dmaf_p_disabled_continue(enum dma_ctrl_flags flags) +{ + enum dma_ctrl_flags mask = DMA_PREP_CONTINUE | DMA_PREP_PQ_DISABLE_P; + + return (flags & mask) == mask; +} + +static inline bool dma_dev_has_pq_continue(struct dma_device *dma) +{ + return (dma->max_pq & DMA_HAS_PQ_CONTINUE) == DMA_HAS_PQ_CONTINUE; +} + +static unsigned short dma_dev_to_maxpq(struct dma_device *dma) +{ + return dma->max_pq & ~DMA_HAS_PQ_CONTINUE; +} + +/* dma_maxpq - reduce maxpq in the face of continued operations + * @dma - dma device with PQ capability + * @flags - to check if DMA_PREP_CONTINUE and DMA_PREP_PQ_DISABLE_P are set + * + * When an engine does not support native continuation we need 3 extra + * source slots to reuse P and Q with the following coefficients: + * 1/ {00} * P : remove P from Q', but use it as a source for P' + * 2/ {01} * Q : use Q to continue Q' calculation + * 3/ {00} * Q : subtract Q from P' to cancel (2) + * + * In the case where P is disabled we only need 1 extra source: + * 1/ {01} * Q : use Q to continue Q' calculation + */ +static inline int dma_maxpq(struct dma_device *dma, enum dma_ctrl_flags flags) +{ + if (dma_dev_has_pq_continue(dma) || !dmaf_continue(flags)) + return dma_dev_to_maxpq(dma); + else if (dmaf_p_disabled_continue(flags)) + return dma_dev_to_maxpq(dma) - 1; + else if (dmaf_continue(flags)) + return dma_dev_to_maxpq(dma) - 3; + BUG(); +} + /* --- public DMA engine API --- */ #ifdef CONFIG_DMA_ENGINE -- cgit v1.2.3 From 0a82a6239beecc95db6e05fe43ee62d16b381d38 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 14 Jul 2009 12:20:37 -0700 Subject: async_tx: add support for asynchronous RAID6 recovery operations async_raid6_2data_recov() recovers two data disk failures async_raid6_datap_recov() recovers a data disk and the P disk These routines are a port of the synchronous versions found in drivers/md/raid6recov.c. The primary difference is breaking out the xor operations into separate calls to async_xor. Two helper routines are introduced to perform scalar multiplication where needed. async_sum_product() multiplies two sources by scalar coefficients and then sums (xor) the result. async_mult() simply multiplies a single source by a scalar. This implemention also includes, in contrast to the original synchronous-only code, special case handling for the 4-disk and 5-disk array cases. In these situations the default N-disk algorithm will present 0-source or 1-source operations to dma devices. To cover for dma devices where the minimum source count is 2 we implement 4-disk and 5-disk handling in the recovery code. [ Impact: asynchronous raid6 recovery routines for 2data and datap cases ] Cc: Yuri Tikhonov Cc: Ilya Yanok Cc: H. Peter Anvin Cc: David Woodhouse Reviewed-by: Andre Noll Acked-by: Maciej Sosnowski Signed-off-by: Dan Williams --- include/linux/async_tx.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h index e6ce5f004f98..866e61c4e2e0 100644 --- a/include/linux/async_tx.h +++ b/include/linux/async_tx.h @@ -194,5 +194,13 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int src_cnt, size_t len, enum sum_check_flags *pqres, struct page *spare, struct async_submit_ctl *submit); +struct dma_async_tx_descriptor * +async_raid6_2data_recov(int src_num, size_t bytes, int faila, int failb, + struct page **ptrs, struct async_submit_ctl *submit); + +struct dma_async_tx_descriptor * +async_raid6_datap_recov(int src_num, size_t bytes, int faila, + struct page **ptrs, struct async_submit_ctl *submit); + void async_tx_quiesce(struct dma_async_tx_descriptor **tx); #endif /* _ASYNC_TX_H_ */ -- cgit v1.2.3 From 0403e3827788d878163f9ef0541b748b0f88ca5d Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 8 Sep 2009 17:42:50 -0700 Subject: dmaengine: add fence support Some engines optimize operation by reading ahead in the descriptor chain such that descriptor2 may start execution before descriptor1 completes. If descriptor2 depends on the result from descriptor1 then a fence is required (on descriptor2) to disable this optimization. The async_tx api could implicitly identify dependencies via the 'depend_tx' parameter, but that would constrain cases where the dependency chain only specifies a completion order rather than a data dependency. So, provide an ASYNC_TX_FENCE to explicitly identify data dependencies. Signed-off-by: Dan Williams --- include/linux/async_tx.h | 3 +++ include/linux/dmaengine.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h index 866e61c4e2e0..a1c486a88e88 100644 --- a/include/linux/async_tx.h +++ b/include/linux/async_tx.h @@ -58,11 +58,14 @@ struct dma_chan_ref { * array. * @ASYNC_TX_ACK: immediately ack the descriptor, precludes setting up a * dependency chain + * @ASYNC_TX_FENCE: specify that the next operation in the dependency + * chain uses this operation's result as an input */ enum async_tx_flags { ASYNC_TX_XOR_ZERO_DST = (1 << 0), ASYNC_TX_XOR_DROP_DST = (1 << 1), ASYNC_TX_ACK = (1 << 2), + ASYNC_TX_FENCE = (1 << 3), }; /** diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 1012f1abcb54..4d6c1c925fd4 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -87,6 +87,8 @@ enum dma_transaction_type { * @DMA_PREP_CONTINUE - indicate to a driver that it is reusing buffers as * sources that were the result of a previous operation, in the case of a PQ * operation it continues the calculation with new sources + * @DMA_PREP_FENCE - tell the driver that subsequent operations depend + * on the result of this operation */ enum dma_ctrl_flags { DMA_PREP_INTERRUPT = (1 << 0), @@ -98,6 +100,7 @@ enum dma_ctrl_flags { DMA_PREP_PQ_DISABLE_P = (1 << 6), DMA_PREP_PQ_DISABLE_Q = (1 << 7), DMA_PREP_CONTINUE = (1 << 8), + DMA_PREP_FENCE = (1 << 9), }; /** -- cgit v1.2.3 From 138f4c359d23d2ec38d18bd70dd9613ae515fe93 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 8 Sep 2009 17:42:51 -0700 Subject: dmaengine, async_tx: add a "no channel switch" allocator Channel switching is problematic for some dmaengine drivers as the architecture precludes separating the ->prep from ->submit. In these cases the driver can select ASYNC_TX_DISABLE_CHANNEL_SWITCH to modify the async_tx allocator to only return channels that support all of the required asynchronous operations. For example MD_RAID456=y selects support for asynchronous xor, xor validate, pq, pq validate, and memcpy. When ASYNC_TX_DISABLE_CHANNEL_SWITCH=y any channel with all these capabilities is marked DMA_ASYNC_TX allowing async_tx_find_channel() to quickly locate compatible channels with the guarantee that dependency chains will remain on one channel. When ASYNC_TX_DISABLE_CHANNEL_SWITCH=n async_tx_find_channel() may select channels that lead to operation chains that need to cross channel boundaries using the async_tx channel switch capability. Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 4d6c1c925fd4..86853ed7970b 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -48,6 +48,9 @@ enum dma_status { /** * enum dma_transaction_type - DMA transaction types/indexes + * + * Note: The DMA_ASYNC_TX capability is not to be set by drivers. It is + * automatically set as dma devices are registered. */ enum dma_transaction_type { DMA_MEMCPY, @@ -61,6 +64,7 @@ enum dma_transaction_type { DMA_MEMCPY_CRC32C, DMA_INTERRUPT, DMA_PRIVATE, + DMA_ASYNC_TX, DMA_SLAVE, }; @@ -396,7 +400,11 @@ static inline void net_dmaengine_put(void) #ifdef CONFIG_ASYNC_TX_DMA #define async_dmaengine_get() dmaengine_get() #define async_dmaengine_put() dmaengine_put() +#ifdef CONFIG_ASYNC_TX_DISABLE_CHANNEL_SWITCH +#define async_dma_find_channel(type) dma_find_channel(DMA_ASYNC_TX) +#else #define async_dma_find_channel(type) dma_find_channel(type) +#endif /* CONFIG_ASYNC_TX_DISABLE_CHANNEL_SWITCH */ #else static inline void async_dmaengine_get(void) { @@ -409,7 +417,7 @@ async_dma_find_channel(enum dma_transaction_type type) { return NULL; } -#endif +#endif /* CONFIG_ASYNC_TX_DMA */ dma_cookie_t dma_async_memcpy_buf_to_buf(struct dma_chan *chan, void *dest, void *src, size_t len); -- cgit v1.2.3 From 9308add6ea4fedeba37b0d7c4630a542bd34f214 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 8 Sep 2009 17:42:52 -0700 Subject: dmaengine: cleanup unused transaction types No drivers currently implement these operation types, so they can be deleted. Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 86853ed7970b..db23fd583f98 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -56,12 +56,9 @@ enum dma_transaction_type { DMA_MEMCPY, DMA_XOR, DMA_PQ, - DMA_DUAL_XOR, - DMA_PQ_UPDATE, DMA_XOR_VAL, DMA_PQ_VAL, DMA_MEMSET, - DMA_MEMCPY_CRC32C, DMA_INTERRUPT, DMA_PRIVATE, DMA_ASYNC_TX, -- cgit v1.2.3 From 83544ae9f3991bfc7d5e0fe9a3008cd05a8d57b7 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 8 Sep 2009 17:42:53 -0700 Subject: dmaengine, async_tx: support alignment checks Some engines have transfer size and address alignment restrictions. Add a per-operation alignment property to struct dma_device that the async routines and dmatest can use to check alignment capabilities. Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index db23fd583f98..835b9c7bf1c2 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -245,6 +245,10 @@ struct dma_async_tx_descriptor { * @cap_mask: one or more dma_capability flags * @max_xor: maximum number of xor sources, 0 if no capability * @max_pq: maximum number of PQ sources and PQ-continue capability + * @copy_align: alignment shift for memcpy operations + * @xor_align: alignment shift for xor operations + * @pq_align: alignment shift for pq operations + * @fill_align: alignment shift for memset operations * @dev_id: unique device ID * @dev: struct device reference for dma mapping api * @device_alloc_chan_resources: allocate resources and return the @@ -271,6 +275,10 @@ struct dma_device { dma_cap_mask_t cap_mask; unsigned short max_xor; unsigned short max_pq; + u8 copy_align; + u8 xor_align; + u8 pq_align; + u8 fill_align; #define DMA_HAS_PQ_CONTINUE (1 << 15) int dev_id; @@ -314,6 +322,42 @@ struct dma_device { void (*device_issue_pending)(struct dma_chan *chan); }; +static inline bool dmaengine_check_align(u8 align, size_t off1, size_t off2, size_t len) +{ + size_t mask; + + if (!align) + return true; + mask = (1 << align) - 1; + if (mask & (off1 | off2 | len)) + return false; + return true; +} + +static inline bool is_dma_copy_aligned(struct dma_device *dev, size_t off1, + size_t off2, size_t len) +{ + return dmaengine_check_align(dev->copy_align, off1, off2, len); +} + +static inline bool is_dma_xor_aligned(struct dma_device *dev, size_t off1, + size_t off2, size_t len) +{ + return dmaengine_check_align(dev->xor_align, off1, off2, len); +} + +static inline bool is_dma_pq_aligned(struct dma_device *dev, size_t off1, + size_t off2, size_t len) +{ + return dmaengine_check_align(dev->pq_align, off1, off2, len); +} + +static inline bool is_dma_fill_aligned(struct dma_device *dev, size_t off1, + size_t off2, size_t len) +{ + return dmaengine_check_align(dev->fill_align, off1, off2, len); +} + static inline void dma_set_maxpq(struct dma_device *dma, int maxpq, int has_pq_continue) { -- cgit v1.2.3 From b265b11fc1a0bd6ae5a7fde12e374583a52ab326 Mon Sep 17 00:00:00 2001 From: Tom Picard Date: Tue, 8 Sep 2009 17:43:01 -0700 Subject: ioat3: ioat3.2 pci ids for Jasper Forest Jasper Forest introduces raid offload support via ioat3.2 support. When raid offload is enabled two (out of 8 channels) will report raid5/raid6 offload capabilities. The remaining channels will only report ioat3.0 capabilities (memcpy). Signed-off-by: Tom Picard Signed-off-by: Dan Williams --- include/linux/pci_ids.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 0f71812d67d3..2b4b8ce53256 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2529,6 +2529,16 @@ #define PCI_DEVICE_ID_INTEL_E7525_MCH 0x359e #define PCI_DEVICE_ID_INTEL_IOAT_CNB 0x360b #define PCI_DEVICE_ID_INTEL_FBD_CNB 0x360c +#define PCI_DEVICE_ID_INTEL_IOAT_JSF0 0x3710 +#define PCI_DEVICE_ID_INTEL_IOAT_JSF1 0x3711 +#define PCI_DEVICE_ID_INTEL_IOAT_JSF2 0x3712 +#define PCI_DEVICE_ID_INTEL_IOAT_JSF3 0x3713 +#define PCI_DEVICE_ID_INTEL_IOAT_JSF4 0x3714 +#define PCI_DEVICE_ID_INTEL_IOAT_JSF5 0x3715 +#define PCI_DEVICE_ID_INTEL_IOAT_JSF6 0x3716 +#define PCI_DEVICE_ID_INTEL_IOAT_JSF7 0x3717 +#define PCI_DEVICE_ID_INTEL_IOAT_JSF8 0x3718 +#define PCI_DEVICE_ID_INTEL_IOAT_JSF9 0x3719 #define PCI_DEVICE_ID_INTEL_ICH10_0 0x3a14 #define PCI_DEVICE_ID_INTEL_ICH10_1 0x3a16 #define PCI_DEVICE_ID_INTEL_ICH10_2 0x3a18 -- cgit v1.2.3 From 0803172778901e24a75ab074798d98c2b7411559 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 8 Sep 2009 17:53:04 -0700 Subject: dmaengine: kill tx_list The tx_list attribute of struct dma_async_tx_descriptor is common to most, but not all dma driver implementations. None of the upper level code (dmaengine/async_tx) uses it, so allow drivers to implement it locally if they need it. This saves sizeof(struct list_head) bytes for drivers that do not manage descriptors with a linked list (e.g.: ioatdma v2,3). Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index ffefba81c818..f114bc7790bc 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -180,8 +180,6 @@ typedef void (*dma_async_tx_callback)(void *dma_async_param); * @flags: flags to augment operation preparation, control completion, and * communicate status * @phys: physical address of the descriptor - * @tx_list: driver common field for operations that require multiple - * descriptors * @chan: target channel for this operation * @tx_submit: set the prepared descriptor(s) to be executed by the engine * @callback: routine to call after this operation is complete @@ -195,7 +193,6 @@ struct dma_async_tx_descriptor { dma_cookie_t cookie; enum dma_ctrl_flags flags; /* not a 'long' to pack with cookie */ dma_addr_t phys; - struct list_head tx_list; struct dma_chan *chan; dma_cookie_t (*tx_submit)(struct dma_async_tx_descriptor *tx); dma_async_tx_callback callback; -- cgit v1.2.3 From 1a5aeeecd550ee4344cfba1791f1134739b16dc6 Mon Sep 17 00:00:00 2001 From: Maciej Sosnowski Date: Thu, 10 Sep 2009 15:05:58 +0200 Subject: dca: registering requesters in multiple dca domains This patch enables DCA support on multiple-IOH/multiple-IIO architectures. It modifies dca module by replacing single dca_providers list with dca_domains list, each domain containing separate list of providers. This approach lets dca driver manage multiple domains, i.e. sets of providers and requesters mapped back to the same PCI root complex device. The driver takes care to register each requester to a provider from the same domain. Signed-off-by: Dan Williams Signed-off-by: Maciej Sosnowski --- include/linux/dca.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dca.h b/include/linux/dca.h index 9c20c7e87d0a..d27a7a05718d 100644 --- a/include/linux/dca.h +++ b/include/linux/dca.h @@ -20,6 +20,9 @@ */ #ifndef DCA_H #define DCA_H + +#include + /* DCA Provider API */ /* DCA Notifier Interface */ @@ -36,6 +39,12 @@ struct dca_provider { int id; }; +struct dca_domain { + struct list_head node; + struct list_head dca_providers; + struct pci_bus *pci_rc; +}; + struct dca_ops { int (*add_requester) (struct dca_provider *, struct device *); int (*remove_requester) (struct dca_provider *, struct device *); @@ -47,7 +56,7 @@ struct dca_ops { struct dca_provider *alloc_dca_provider(struct dca_ops *ops, int priv_size); void free_dca_provider(struct dca_provider *dca); int register_dca_provider(struct dca_provider *dca, struct device *dev); -void unregister_dca_provider(struct dca_provider *dca); +void unregister_dca_provider(struct dca_provider *dca, struct device *dev); static inline void *dca_priv(struct dca_provider *dca) { -- cgit v1.2.3 From 52a7a1cec88acdaf3f8b36a6b1fe904f6eca7ee5 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Thu, 10 Sep 2009 15:26:30 +0200 Subject: [ARM] pxafb: add accelerator ID for PXA3xx GCU Add ID 99 for PXA3xx frame buffers and report it in the pxa frame buffer conditionally, depending on a new flag in struct pxafb_mach_info. Signed-off-by: Daniel Mack Cc: linux-fbdev-devel@lists.sourceforge.net Cc: Dennis Oliver Kropp Cc: Sven Neumann Cc: Guennadi Liakhovetski Signed-off-by: Eric Miao --- include/linux/fb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index f847df9e99b6..a34bdf5a9d23 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -133,6 +133,7 @@ struct dentry; #define FB_ACCEL_NEOMAGIC_NM2230 96 /* NeoMagic NM2230 */ #define FB_ACCEL_NEOMAGIC_NM2360 97 /* NeoMagic NM2360 */ #define FB_ACCEL_NEOMAGIC_NM2380 98 /* NeoMagic NM2380 */ +#define FB_ACCEL_PXA3XX 99 /* PXA3xx */ #define FB_ACCEL_SAVAGE4 0x80 /* S3 Savage4 */ #define FB_ACCEL_SAVAGE3D 0x81 /* S3 Savage3D */ -- cgit v1.2.3 From d466f2fcb32cd97fd586bfa33f5dba3ac78aadb0 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 16 Sep 2009 11:50:03 +0200 Subject: HWPOISON: Add page flag for poisoned pages Hardware poisoned pages need special handling in the VM and shouldn't be touched again. This requires a new page flag. Define it here. The page flags wars seem to be over, so it shouldn't be a problem to get a new one. v2: Add TestSetHWPoison (suggested by Johannes Weiner) Acked-by: Christoph Lameter Signed-off-by: Andi Kleen --- include/linux/page-flags.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 2b87acfc5f87..9bc5fd9fdbf6 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -51,6 +51,9 @@ * PG_buddy is set to indicate that the page is free and in the buddy system * (see mm/page_alloc.c). * + * PG_hwpoison indicates that a page got corrupted in hardware and contains + * data with incorrect ECC bits that triggered a machine check. Accessing is + * not safe since it may cause another machine check. Don't touch! */ /* @@ -101,6 +104,9 @@ enum pageflags { #endif #ifdef CONFIG_ARCH_USES_PG_UNCACHED PG_uncached, /* Page has been mapped as uncached */ +#endif +#ifdef CONFIG_MEMORY_FAILURE + PG_hwpoison, /* hardware poisoned page. Don't touch */ #endif __NR_PAGEFLAGS, @@ -263,6 +269,15 @@ PAGEFLAG(Uncached, uncached) PAGEFLAG_FALSE(Uncached) #endif +#ifdef CONFIG_MEMORY_FAILURE +PAGEFLAG(HWPoison, hwpoison) +TESTSETFLAG(HWPoison, hwpoison) +#define __PG_HWPOISON (1UL << PG_hwpoison) +#else +PAGEFLAG_FALSE(HWPoison) +#define __PG_HWPOISON 0 +#endif + static inline int PageUptodate(struct page *page) { int ret = test_bit(PG_uptodate, &(page)->flags); @@ -387,7 +402,7 @@ static inline void __ClearPageTail(struct page *page) 1 << PG_private | 1 << PG_private_2 | \ 1 << PG_buddy | 1 << PG_writeback | 1 << PG_reserved | \ 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ - 1 << PG_unevictable | __PG_MLOCKED) + 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON) /* * Flags checked when a page is prepped for return by the page allocator. -- cgit v1.2.3 From 10be22dfe1e6ad978269dc275147e0ed049187bb Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 16 Sep 2009 11:50:04 +0200 Subject: HWPOISON: Export some rmap vma locking to outside world Needed for later patch that walks rmap entries on its own. This used to be very frowned upon, but memory-failure.c does some rather specialized rmap walking and rmap has been stable for quite some time, so I think it's ok now to export it. Signed-off-by: Andi Kleen --- include/linux/rmap.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index bf116d0dbf23..8dff2ffab82c 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -112,6 +112,12 @@ int page_mkclean(struct page *); */ int try_to_munlock(struct page *); +/* + * Called by memory-failure.c to kill processes. + */ +struct anon_vma *page_lock_anon_vma(struct page *page); +void page_unlock_anon_vma(struct anon_vma *anon_vma); + #else /* !CONFIG_MMU */ #define anon_vma_init() do {} while (0) -- cgit v1.2.3 From a7420aa54dbf699a5a05feba3c859b6baaa3938c Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 16 Sep 2009 11:50:05 +0200 Subject: HWPOISON: Add support for poison swap entries v2 Memory migration uses special swap entry types to trigger special actions on page faults. Extend this mechanism to also support poisoned swap entries, to trigger poison handling on page faults. This allows follow-on patches to prevent processes from faulting in poisoned pages again. v2: Fix overflow in MAX_SWAPFILES (Fengguang Wu) v3: Better overflow fix (Hidehiro Kawai) Signed-off-by: Andi Kleen --- include/linux/swap.h | 34 ++++++++++++++++++++++++++++------ include/linux/swapops.h | 38 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 66 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 7c15334f3ff2..f077e454c659 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -34,15 +34,37 @@ static inline int current_is_kswapd(void) * the type/offset into the pte as 5/27 as well. */ #define MAX_SWAPFILES_SHIFT 5 -#ifndef CONFIG_MIGRATION -#define MAX_SWAPFILES (1 << MAX_SWAPFILES_SHIFT) + +/* + * Use some of the swap files numbers for other purposes. This + * is a convenient way to hook into the VM to trigger special + * actions on faults. + */ + +/* + * NUMA node memory migration support + */ +#ifdef CONFIG_MIGRATION +#define SWP_MIGRATION_NUM 2 +#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) +#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) #else -/* Use last two entries for page migration swap entries */ -#define MAX_SWAPFILES ((1 << MAX_SWAPFILES_SHIFT)-2) -#define SWP_MIGRATION_READ MAX_SWAPFILES -#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + 1) +#define SWP_MIGRATION_NUM 0 #endif +/* + * Handling of hardware poisoned pages with memory corruption. + */ +#ifdef CONFIG_MEMORY_FAILURE +#define SWP_HWPOISON_NUM 1 +#define SWP_HWPOISON MAX_SWAPFILES +#else +#define SWP_HWPOISON_NUM 0 +#endif + +#define MAX_SWAPFILES \ + ((1 << MAX_SWAPFILES_SHIFT) - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM) + /* * Magic header for a swap area. The first part of the union is * what the swap magic looks like for the old (limited to 128MB) diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 6ec39ab27b4b..cd42e30b7c6e 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -131,3 +131,41 @@ static inline int is_write_migration_entry(swp_entry_t entry) #endif +#ifdef CONFIG_MEMORY_FAILURE +/* + * Support for hardware poisoned pages + */ +static inline swp_entry_t make_hwpoison_entry(struct page *page) +{ + BUG_ON(!PageLocked(page)); + return swp_entry(SWP_HWPOISON, page_to_pfn(page)); +} + +static inline int is_hwpoison_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_HWPOISON; +} +#else + +static inline swp_entry_t make_hwpoison_entry(struct page *page) +{ + return swp_entry(0, 0); +} + +static inline int is_hwpoison_entry(swp_entry_t swp) +{ + return 0; +} +#endif + +#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) +static inline int non_swap_entry(swp_entry_t entry) +{ + return swp_type(entry) >= MAX_SWAPFILES; +} +#else +static inline int non_swap_entry(swp_entry_t entry) +{ + return 0; +} +#endif -- cgit v1.2.3 From d1737fdbec7f90edc52dd0c5c3767457f28e78d8 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 16 Sep 2009 11:50:06 +0200 Subject: HWPOISON: Add basic support for poisoned pages in fault handler v3 - Add a new VM_FAULT_HWPOISON error code to handle_mm_fault. Right now architectures have to explicitely enable poison page support, so this is forward compatible to all architectures. They only need to add it when they enable poison page support. - Add poison page handling in swap in fault code v2: Add missing delayacct_clear_flag (Hidehiro Kawai) v3: Really use delayacct_clear_flag (Hidehiro Kawai) Signed-off-by: Andi Kleen --- 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 9a72cc78e6b8..082b68cb5ffe 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -685,11 +685,12 @@ static inline int page_mapped(struct page *page) #define VM_FAULT_SIGBUS 0x0002 #define VM_FAULT_MAJOR 0x0004 #define VM_FAULT_WRITE 0x0008 /* Special case for get_user_pages */ +#define VM_FAULT_HWPOISON 0x0010 /* Hit poisoned page */ #define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */ #define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */ -#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS) +#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON) /* * Can be called by the pagefault handler when it gets a VM_FAULT_OOM. -- cgit v1.2.3 From 14fa31b89c5ae79e4131da41761378a6df674352 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 16 Sep 2009 11:50:10 +0200 Subject: HWPOISON: Use bitmask/action code for try_to_unmap behaviour try_to_unmap currently has multiple modi (migration, munlock, normal unmap) which are selected by magic flag variables. The logic is not very straight forward, because each of these flag change multiple behaviours (e.g. migration turns off aging, not only sets up migration ptes etc.) Also the different flags interact in magic ways. A later patch in this series adds another mode to try_to_unmap, so this becomes quickly unmanageable. Replace the different flags with a action code (migration, munlock, munmap) and some additional flags as modifiers (ignore mlock, ignore aging). This makes the logic more straight forward and allows easier extension to new behaviours. Change all the caller to declare what they want to do. This patch is supposed to be a nop in behaviour. If anyone can prove it is not that would be a bug. Cc: Lee.Schermerhorn@hp.com Cc: npiggin@suse.de Signed-off-by: Andi Kleen --- include/linux/rmap.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 8dff2ffab82c..4c4a2d4d289e 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -85,7 +85,18 @@ static inline void page_dup_rmap(struct page *page, struct vm_area_struct *vma, */ int page_referenced(struct page *, int is_locked, struct mem_cgroup *cnt, unsigned long *vm_flags); -int try_to_unmap(struct page *, int ignore_refs); +enum ttu_flags { + TTU_UNMAP = 0, /* unmap mode */ + TTU_MIGRATION = 1, /* migration mode */ + TTU_MUNLOCK = 2, /* munlock mode */ + TTU_ACTION_MASK = 0xff, + + TTU_IGNORE_MLOCK = (1 << 8), /* ignore mlock */ + TTU_IGNORE_ACCESS = (1 << 9), /* don't age */ +}; +#define TTU_ACTION(x) ((x) & TTU_ACTION_MASK) + +int try_to_unmap(struct page *, enum ttu_flags flags); /* * Called from mm/filemap_xip.c to unmap empty zero page -- cgit v1.2.3 From 888b9f7c58ebe8303bad817cd554df887a683957 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 16 Sep 2009 11:50:11 +0200 Subject: HWPOISON: Handle hardware poisoned pages in try_to_unmap When a page has the poison bit set replace the PTE with a poison entry. This causes the right error handling to be done later when a process runs into it. v2: add a new flag to not do that (needed for the memory-failure handler later) (Fengguang) v3: remove unnecessary is_migration_entry() test (Fengguang, Minchan) Reviewed-by: Minchan Kim Reviewed-by: Wu Fengguang Signed-off-by: Andi Kleen --- include/linux/rmap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 4c4a2d4d289e..ce989f1fc2ed 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -93,6 +93,7 @@ enum ttu_flags { TTU_IGNORE_MLOCK = (1 << 8), /* ignore mlock */ TTU_IGNORE_ACCESS = (1 << 9), /* don't age */ + TTU_IGNORE_HWPOISON = (1 << 10),/* corrupted page is recoverable */ }; #define TTU_ACTION(x) ((x) & TTU_ACTION_MASK) -- cgit v1.2.3 From 750b4987b0cd4d408e54cb83a80a067cbe690feb Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 16 Sep 2009 11:50:12 +0200 Subject: HWPOISON: Refactor truncate to allow direct truncating of page v2 Extract out truncate_inode_page() out of the truncate path so that it can be used by memory-failure.c [AK: description, headers, fix typos] v2: Some white space changes from Fengguang Wu Signed-off-by: Andi Kleen --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 082b68cb5ffe..8cbc0aafd5bd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -794,6 +794,8 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping, extern int vmtruncate(struct inode * inode, loff_t offset); extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end); +int truncate_inode_page(struct address_space *mapping, struct page *page); + #ifdef CONFIG_MMU extern int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); -- cgit v1.2.3 From 83f786680aec8d030184f7ced1a0a3dd8ac81764 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Wed, 16 Sep 2009 11:50:13 +0200 Subject: HWPOISON: Add invalidate_inode_page Add a simple way to invalidate a single page This is just a refactoring of the truncate.c code. Originally from Fengguang, modified by Andi Kleen. Signed-off-by: Andi Kleen --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8cbc0aafd5bd..b05bbde0296d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -796,6 +796,8 @@ extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end); int truncate_inode_page(struct address_space *mapping, struct page *page); +int invalidate_inode_page(struct page *page); + #ifdef CONFIG_MMU extern int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); -- cgit v1.2.3 From 257187362123f15d9d1e09918cf87cebbea4e786 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 16 Sep 2009 11:50:13 +0200 Subject: HWPOISON: Define a new error_remove_page address space op for async truncation Truncating metadata pages is not safe right now before we haven't audited all file systems. To enable truncation only for data address space define a new address_space callback error_remove_page. This is used for memory_failure.c memory error handling. This can be then set to truncate_inode_page() This patch just defines the new operation and adds documentation. Callers and users come in followon patches. Signed-off-by: Andi Kleen --- include/linux/fs.h | 1 + include/linux/mm.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index b21cf6b9c80b..4f47afd37647 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -595,6 +595,7 @@ struct address_space_operations { int (*launder_page) (struct page *); int (*is_partially_uptodate) (struct page *, read_descriptor_t *, unsigned long); + int (*error_remove_page)(struct address_space *, struct page *); }; /* diff --git a/include/linux/mm.h b/include/linux/mm.h index b05bbde0296d..a16018f7d61c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -795,6 +795,7 @@ extern int vmtruncate(struct inode * inode, loff_t offset); extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end); int truncate_inode_page(struct address_space *mapping, struct page *page); +int generic_error_remove_page(struct address_space *mapping, struct page *page); int invalidate_inode_page(struct page *page); -- cgit v1.2.3 From 4db96cf077aa938b11fe7ac79ecc9b29ec00fbab Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 16 Sep 2009 11:50:14 +0200 Subject: HWPOISON: Add PR_MCE_KILL prctl to control early kill behaviour per process This allows processes to override their early/late kill behaviour on hardware memory errors. Typically applications which are memory error aware is better of with early kill (see the error as soon as possible), all others with late kill (only see the error when the error is really impacting execution) There's a global sysctl, but this way an application can set its specific policy. We're using two bits, one to signify that the process stated its intention and that I also made the prctl future proof by enforcing the unused arguments are 0. The state is inherited to children. Note this makes us officially run out of process flags on 32bit, but the next patch can easily add another field. Manpage patch will be supplied separately. Signed-off-by: Andi Kleen --- include/linux/prctl.h | 2 ++ include/linux/sched.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/prctl.h b/include/linux/prctl.h index b00df4c79c63..3dc303197e67 100644 --- a/include/linux/prctl.h +++ b/include/linux/prctl.h @@ -88,4 +88,6 @@ #define PR_TASK_PERF_COUNTERS_DISABLE 31 #define PR_TASK_PERF_COUNTERS_ENABLE 32 +#define PR_MCE_KILL 33 + #endif /* _LINUX_PRCTL_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index f3d74bd04d18..29eae73c951d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1687,6 +1687,7 @@ extern cputime_t task_gtime(struct task_struct *p); #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ #define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */ +#define PF_MCE_PROCESS 0x00000080 /* process policy on mce errors */ #define PF_SUPERPRIV 0x00000100 /* used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* dumped core */ #define PF_SIGNALED 0x00000400 /* killed by a signal */ @@ -1706,6 +1707,7 @@ extern cputime_t task_gtime(struct task_struct *p); #define PF_SPREAD_PAGE 0x01000000 /* Spread page cache over cpuset */ #define PF_SPREAD_SLAB 0x02000000 /* Spread some slab caches over cpuset */ #define PF_THREAD_BOUND 0x04000000 /* Thread bound to specific cpu */ +#define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMPOLICY 0x10000000 /* Non-default NUMA mempolicy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezeable */ -- cgit v1.2.3 From 6a46079cf57a7f7758e8b926980a4f852f89b34d Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 16 Sep 2009 11:50:15 +0200 Subject: HWPOISON: The high level memory error handler in the VM v7 Add the high level memory handler that poisons pages that got corrupted by hardware (typically by a two bit flip in a DIMM or a cache) on the Linux level. The goal is to prevent everyone from accessing these pages in the future. This done at the VM level by marking a page hwpoisoned and doing the appropriate action based on the type of page it is. The code that does this is portable and lives in mm/memory-failure.c To quote the overview comment: High level machine check handler. Handles pages reported by the hardware as being corrupted usually due to a 2bit ECC memory or cache failure. This focuses on pages detected as corrupted in the background. When the current CPU tries to consume corruption the currently running process can just be killed directly instead. This implies that if the error cannot be handled for some reason it's safe to just ignore it because no corruption has been consumed yet. Instead when that happens another machine check will happen. Handles page cache pages in various states. The tricky part here is that we can access any page asynchronous to other VM users, because memory failures could happen anytime and anywhere, possibly violating some of their assumptions. This is why this code has to be extremely careful. Generally it tries to use normal locking rules, as in get the standard locks, even if that means the error handling takes potentially a long time. Some of the operations here are somewhat inefficient and have non linear algorithmic complexity, because the data structures have not been optimized for this case. This is in particular the case for the mapping from a vma to a process. Since this case is expected to be rare we hope we can get away with this. There are in principle two strategies to kill processes on poison: - just unmap the data and wait for an actual reference before killing - kill as soon as corruption is detected. Both have advantages and disadvantages and should be used in different situations. Right now both are implemented and can be switched with a new sysctl vm.memory_failure_early_kill The default is early kill. The patch does some rmap data structure walking on its own to collect processes to kill. This is unusual because normally all rmap data structure knowledge is in rmap.c only. I put it here for now to keep everything together and rmap knowledge has been seeping out anyways Includes contributions from Johannes Weiner, Chris Mason, Fengguang Wu, Nick Piggin (who did a lot of great work) and others. Cc: npiggin@suse.de Cc: riel@redhat.com Signed-off-by: Andi Kleen Acked-by: Rik van Riel Reviewed-by: Hidehiro Kawai --- include/linux/mm.h | 7 +++++++ include/linux/rmap.h | 1 + 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index a16018f7d61c..1ffca03f34b7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1309,5 +1309,12 @@ void vmemmap_populate_print_last(void); extern int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim, size_t size); extern void refund_locked_memory(struct mm_struct *mm, size_t size); + +extern void memory_failure(unsigned long pfn, int trapno); +extern int __memory_failure(unsigned long pfn, int trapno, int ref); +extern int sysctl_memory_failure_early_kill; +extern int sysctl_memory_failure_recovery; +extern atomic_long_t mce_bad_pages; + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/include/linux/rmap.h b/include/linux/rmap.h index ce989f1fc2ed..3c1004e50747 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -129,6 +129,7 @@ int try_to_munlock(struct page *); */ struct anon_vma *page_lock_anon_vma(struct page *page); void page_unlock_anon_vma(struct anon_vma *anon_vma); +int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); #else /* !CONFIG_MMU */ -- cgit v1.2.3 From e2d4304b7d2b85c45de89ec420037d6b9261a12d Mon Sep 17 00:00:00 2001 From: Jesse Barnes Date: Thu, 17 Sep 2009 09:40:31 -0700 Subject: PCI: fix VGA arbiter header file Remove reference to vgaarb.c and replace it with a comment about the arbiter itself. Reported-by: Tiago Vignatti Signed-off-by: Jesse Barnes --- include/linux/vgaarb.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h index e81c64af80c1..a1fa1da8dc1a 100644 --- a/include/linux/vgaarb.h +++ b/include/linux/vgaarb.h @@ -1,5 +1,6 @@ /* - * vgaarb.c + * The VGA aribiter manages VGA space routing and VGA resource decode to + * allow multiple VGA devices to be used in a system in a safe way. * * (C) Copyright 2005 Benjamin Herrenschmidt * (C) Copyright 2007 Paulo R. Zanoni -- cgit v1.2.3 From ee2b805c8eb6459cf541ef141ff70dae17af59ca Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 15 Aug 2009 15:12:05 +0100 Subject: ARM: 5678/1: SSP/SPI PL022 polarity terminology fix The definition of the SPI clock phase for the Motorola mode of the PL022 driver was incorrect: the spec had been interpreted as data being recieved on rising or falling edge of the clocks while the correct interpretation is that data can be recieved on the first or second edge transition, falling or rising depending on the polarity setting. Signed-off-by: Linus Walleij Signed-off-by: Russell King --- include/linux/amba/pl022.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/amba/pl022.h b/include/linux/amba/pl022.h index dcad0ffd1755..e4836c6b3dd7 100644 --- a/include/linux/amba/pl022.h +++ b/include/linux/amba/pl022.h @@ -136,12 +136,12 @@ enum ssp_tx_level_trig { /** * enum SPI Clock Phase - clock phase (Motorola SPI interface only) - * @SSP_CLK_RISING_EDGE: Receive data on rising edge - * @SSP_CLK_FALLING_EDGE: Receive data on falling edge + * @SSP_CLK_FIRST_EDGE: Receive data on first edge transition (actual direction depends on polarity) + * @SSP_CLK_SECOND_EDGE: Receive data on second edge transition (actual direction depends on polarity) */ enum ssp_spi_clk_phase { - SSP_CLK_RISING_EDGE, - SSP_CLK_FALLING_EDGE + SSP_CLK_FIRST_EDGE, + SSP_CLK_SECOND_EDGE }; /** -- cgit v1.2.3 From 6ef297f86b62f187c59475784208f75c2ed8ccd8 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 22 Sep 2009 14:29:36 +0100 Subject: ARM: 5720/1: Move MMCI header to amba include dir This moves the mmci platform data definition struct away from arch/arm/include/asm/mach/mmc.h into the more proper place among the other primecells in include/linux/amba/mmci.h and at the same time renames it to "mmci.h", and also the struct in this file confusingly named mmc_platform_data has been renamed mmci_platform_data for clarity. Cc: Catalin Marinas Signed-off-by: Linus Walleij Signed-off-by: Russell King --- include/linux/amba/mmci.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 include/linux/amba/mmci.h (limited to 'include/linux') diff --git a/include/linux/amba/mmci.h b/include/linux/amba/mmci.h new file mode 100644 index 000000000000..6b4241748dda --- /dev/null +++ b/include/linux/amba/mmci.h @@ -0,0 +1,18 @@ +/* + * include/linux/amba/mmci.h + */ +#ifndef AMBA_MMCI_H +#define AMBA_MMCI_H + +#include + +struct mmci_platform_data { + unsigned int ocr_mask; /* available voltages */ + u32 (*translate_vdd)(struct device *, unsigned int); + unsigned int (*status)(struct device *); + int gpio_wp; + int gpio_cd; + unsigned long capabilities; +}; + +#endif -- cgit v1.2.3 From 22fe404218156328a27e66349b1175cd0baa4990 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 18 Sep 2009 13:05:44 -0700 Subject: vfs: split generic_forget_inode() so that hugetlbfs does not have to copy it Hugetlbfs needs to do special things instead of truncate_inode_pages(). Currently, it copied generic_forget_inode() except for truncate_inode_pages() call which is asking for trouble (the code there isn't trivial). So create a separate function generic_detach_inode() which does all the list magic done in generic_forget_inode() and call it from hugetlbfs_forget_inode(). Signed-off-by: Jan Kara Cc: Al Viro Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 51803528b095..955e34615cb7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2156,6 +2156,7 @@ extern ino_t iunique(struct super_block *, ino_t); extern int inode_needs_sync(struct inode *inode); extern void generic_delete_inode(struct inode *inode); extern void generic_drop_inode(struct inode *inode); +extern int generic_detach_inode(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), -- cgit v1.2.3 From 42cb56ae2ab67390da34906b27bedc3f2ff1393b Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 18 Sep 2009 13:05:53 -0700 Subject: vfs: change sb->s_maxbytes to a loff_t sb->s_maxbytes is supposed to indicate the maximum size of a file that can exist on the filesystem. It's declared as an unsigned long long. Even if a filesystem has no inherent limit that prevents it from using every bit in that unsigned long long, it's still problematic to set it to anything larger than MAX_LFS_FILESIZE. There are places in the kernel that cast s_maxbytes to a signed value. If it's set too large then this cast makes it a negative number and generally breaks the comparison. Change s_maxbytes to be loff_t instead. That should help eliminate the temptation to set it too large by making it a signed value. Also, add a warning for couple of releases to help catch filesystems that set s_maxbytes too large. Eventually we can either convert this to a BUG() or just remove it and in the hope that no one will get it wrong now that it's a signed value. Signed-off-by: Jeff Layton Cc: Johannes Weiner Cc: Christoph Hellwig Cc: Al Viro Cc: Robert Love Cc: Mandeep Singh Baines Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- 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 955e34615cb7..cbb7724c11d3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1315,7 +1315,7 @@ struct super_block { unsigned long s_blocksize; unsigned char s_blocksize_bits; unsigned char s_dirt; - unsigned long long s_maxbytes; /* Max file size */ + loff_t s_maxbytes; /* Max file size */ struct file_system_type *s_type; const struct super_operations *s_op; const struct dquot_operations *dq_op; -- cgit v1.2.3 From f84398068d9c2babe41500504ef247ae07081857 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 21 Sep 2009 14:48:36 +0200 Subject: vfs: seq_file: add helpers for data filling Add two helpers that allow access to the seq_file's own buffer, but hide the internal details of seq_files. This allows easier implementation of special purpose filling functions. It also cleans up some existing functions which duplicated the seq_file logic. Make these inline functions in seq_file.h, as suggested by Al. Signed-off-by: Miklos Szeredi Acked-by: Hugh Dickins Signed-off-by: Al Viro --- include/linux/seq_file.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) (limited to 'include/linux') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 0c6a86b79596..8366d8f12e53 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -35,6 +35,44 @@ struct seq_operations { #define SEQ_SKIP 1 +/** + * seq_get_buf - get buffer to write arbitrary data to + * @m: the seq_file handle + * @bufp: the beginning of the buffer is stored here + * + * Return the number of bytes available in the buffer, or zero if + * there's no space. + */ +static inline size_t seq_get_buf(struct seq_file *m, char **bufp) +{ + BUG_ON(m->count > m->size); + if (m->count < m->size) + *bufp = m->buf + m->count; + else + *bufp = NULL; + + return m->size - m->count; +} + +/** + * seq_commit - commit data to the buffer + * @m: the seq_file handle + * @num: the number of bytes to commit + * + * Commit @num bytes of data written to a buffer previously acquired + * by seq_buf_get. To signal an error condition, or that the data + * didn't fit in the available space, pass a negative @num value. + */ +static inline void seq_commit(struct seq_file *m, int num) +{ + if (num < 0) { + m->count = m->size; + } else { + BUG_ON(m->count + num > m->size); + m->count += num; + } +} + char *mangle_path(char *s, char *p, char *esc); int seq_open(struct file *, const struct seq_operations *); ssize_t seq_read(struct file *, char __user *, size_t, loff_t *); -- cgit v1.2.3 From 4fadd7bb20a1e7c774ed88dc703d8fbcd00ff917 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 3 Aug 2009 23:28:06 +0200 Subject: freeze_bdev: kill bd_mount_sem Now that we have the freeze count there is not much reason for bd_mount_sem anymore. The actual freeze/thaw operations are serialized using the bd_fsfreeze_mutex, and the only other place we take bd_mount_sem is get_sb_bdev which tries to prevent mounting a filesystem while the block device is frozen. Instead of add a check for bd_fsfreeze_count and return -EBUSY if a filesystem is frozen. While that is a change in user visible behaviour a failing mount is much better for this case rather than having the mount process stuck uninterruptible for a long time. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index cbb7724c11d3..72dfbd423974 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -640,7 +640,6 @@ struct block_device { struct super_block * bd_super; int bd_openers; struct mutex bd_mutex; /* open/close mutex */ - struct semaphore bd_mount_sem; struct list_head bd_inodes; void * bd_holder; int bd_holders; -- cgit v1.2.3 From 4504230a71566785a05d3e6b53fa1ee071b864eb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 3 Aug 2009 23:28:35 +0200 Subject: freeze_bdev: grab active reference to frozen superblocks Currently we held s_umount while a filesystem is frozen, despite that we might return to userspace and unlock it from a different process. Instead grab an active reference to keep the file system busy and add an explicit check for frozen filesystems in remount and reject the remount instead of blocking on s_umount. Add a new get_active_super helper to super.c for use by freeze_bdev that grabs an active reference to a superblock from a given block device. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 72dfbd423974..502d96ef345d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2334,6 +2334,7 @@ extern void get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern struct super_block *get_super(struct block_device *); +extern struct super_block *get_active_super(struct block_device *bdev); extern struct super_block *user_get_super(dev_t); extern void drop_super(struct super_block *sb); -- cgit v1.2.3 From 25d9e2d15286281ec834b829a4aaf8969011f1cd Mon Sep 17 00:00:00 2001 From: "npiggin@suse.de" Date: Fri, 21 Aug 2009 02:35:05 +1000 Subject: truncate: new helpers Introduce new truncate helpers truncate_pagecache and inode_newsize_ok. vmtruncate is also consolidated from mm/memory.c and mm/nommu.c and into mm/truncate.c. Reviewed-by: Christoph Hellwig Signed-off-by: Nick Piggin Signed-off-by: Al Viro --- include/linux/fs.h | 3 ++- include/linux/mm.h | 5 +++-- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 502d96ef345d..2b08b5ce09b6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2382,7 +2382,8 @@ extern int buffer_migrate_page(struct address_space *, #define buffer_migrate_page NULL #endif -extern int inode_change_ok(struct inode *, struct iattr *); +extern int inode_change_ok(const struct inode *, struct iattr *); +extern int inode_newsize_ok(const struct inode *, loff_t offset); extern int __must_check inode_setattr(struct inode *, struct iattr *); extern void file_update_time(struct file *file); diff --git a/include/linux/mm.h b/include/linux/mm.h index b6eae5e3144b..8347e938fb2f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -791,8 +791,9 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping, unmap_mapping_range(mapping, holebegin, holelen, 0); } -extern int vmtruncate(struct inode * inode, loff_t offset); -extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end); +extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new); +extern int vmtruncate(struct inode *inode, loff_t offset); +extern int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end); #ifdef CONFIG_MMU extern int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, -- cgit v1.2.3 From 57f1f0874f426a9bdfc5cd3f886113dd5cd17834 Mon Sep 17 00:00:00 2001 From: Zhaolei Date: Wed, 23 Sep 2009 15:56:10 -0700 Subject: time: add function to convert between calendar time and broken-down time for universal use There are many similar code in kernel for one object: convert time between calendar time and broken-down time. Here is some source I found: fs/ncpfs/dir.c fs/smbfs/proc.c fs/fat/misc.c fs/udf/udftime.c fs/cifs/netmisc.c net/netfilter/xt_time.c drivers/scsi/ips.c drivers/input/misc/hp_sdc_rtc.c drivers/rtc/rtc-lib.c arch/ia64/hp/sim/boot/fw-emu.c arch/m68k/mac/misc.c arch/powerpc/kernel/time.c arch/parisc/include/asm/rtc.h ... We can make a common function for this type of conversion, At least we can get following benefit: 1: Make kernel simple and unify 2: Easy to fix bug in converting code 3: Reduce clone of code in future For example, I'm trying to make ftrace display walltime, this patch will make me easy. This code is based on code from glibc-2.6 Signed-off-by: Zhao Lei Cc: OGAWA Hirofumi Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Pavel Machek Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/time.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index 56787c093345..fe04e5ef6a59 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -155,6 +155,34 @@ extern void timekeeping_leap_insert(int leapsecond); struct tms; extern void do_sys_times(struct tms *); +/* + * Similar to the struct tm in userspace , but it needs to be here so + * that the kernel source is self contained. + */ +struct tm { + /* + * the number of seconds after the minute, normally in the range + * 0 to 59, but can be up to 60 to allow for leap seconds + */ + int tm_sec; + /* the number of minutes after the hour, in the range 0 to 59*/ + int tm_min; + /* the number of hours past midnight, in the range 0 to 23 */ + int tm_hour; + /* the day of the month, in the range 1 to 31 */ + int tm_mday; + /* the number of months since January, in the range 0 to 11 */ + int tm_mon; + /* the number of years since 1900 */ + long tm_year; + /* the number of days since Sunday, in the range 0 to 6 */ + int tm_wday; + /* the number of days since January 1, in the range 0 to 365 */ + int tm_yday; +}; + +void time_to_tm(time_t totalsecs, int offset, struct tm *result); + /** * timespec_to_ns - Convert timespec to nanoseconds * @ts: pointer to the timespec variable to be converted -- cgit v1.2.3 From 55dff4954ebdeba2be59e19398a607d799c5fa9f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 23 Sep 2009 15:56:17 -0700 Subject: docs: fix various Documentation/ paths in header files Fix various Documentation/ paths in include/linux/. Signed-off-by: Randy Dunlap Reviewed-by: Jesper Juhl Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/configfs.h | 4 ++-- include/linux/debugfs.h | 2 +- include/linux/relay.h | 2 +- include/linux/tracepoint.h | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/configfs.h b/include/linux/configfs.h index 7f627775c947..ddb7a97c78c2 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -27,8 +27,8 @@ * * configfs Copyright (C) 2005 Oracle. All rights reserved. * - * Please read Documentation/filesystems/configfs.txt before using the - * configfs interface, ESPECIALLY the parts about reference counts and + * Please read Documentation/filesystems/configfs/configfs.txt before using + * the configfs interface, ESPECIALLY the parts about reference counts and * item destructors. */ diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index eb5c2ba2f81a..fc1b930f246c 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -9,7 +9,7 @@ * 2 as published by the Free Software Foundation. * * debugfs is for people to use instead of /proc or /sys. - * See Documentation/DocBook/kernel-api for more details. + * See Documentation/DocBook/filesystems for more details. */ #ifndef _DEBUGFS_H_ diff --git a/include/linux/relay.h b/include/linux/relay.h index 953fc055e875..14a86bc7102b 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -140,7 +140,7 @@ struct rchan_callbacks * cause relay_open() to create a single global buffer rather * than the default set of per-cpu buffers. * - * See Documentation/filesystems/relayfs.txt for more info. + * See Documentation/filesystems/relay.txt for more info. */ struct dentry *(*create_buf_file)(const char *filename, struct dentry *parent, diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 63a3f7a80580..660a9de96f81 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -4,7 +4,7 @@ /* * Kernel Tracepoint API. * - * See Documentation/tracepoint.txt. + * See Documentation/trace/tracepoints.txt. * * (C) Copyright 2008 Mathieu Desnoyers * -- cgit v1.2.3 From 8f3ff20862cfcb85500a2bb55ee64622bd59fd0c Mon Sep 17 00:00:00 2001 From: Paul Menage Date: Wed, 23 Sep 2009 15:56:25 -0700 Subject: cgroups: revert "cgroups: fix pid namespace bug" The following series adds a "cgroup.procs" file to each cgroup that reports unique tgids rather than pids, and allows all threads in a threadgroup to be atomically moved to a new cgroup. The subsystem "attach" interface is modified to support attaching whole threadgroups at a time, which could introduce potential problems if any subsystem were to need to access the old cgroup of every thread being moved. The attach interface may need to be revised if this becomes the case. Also added is functionality for read/write locking all CLONE_THREAD fork()ing within a threadgroup, by means of an rwsem that lives in the sighand_struct, for per-threadgroup-ness and also for sharing a cacheline with the sighand's atomic count. This scheme should introduce no extra overhead in the fork path when there's no contention. The final patch reveals potential for a race when forking before a subsystem's attach function is called - one potential solution in case any subsystem has this problem is to hang on to the group's fork mutex through the attach() calls, though no subsystem yet demonstrates need for an extended critical section. This patch: Revert commit 096b7fe012d66ed55e98bc8022405ede0cc80e96 Author: Li Zefan AuthorDate: Wed Jul 29 15:04:04 2009 -0700 Commit: Linus Torvalds CommitDate: Wed Jul 29 19:10:35 2009 -0700 cgroups: fix pid namespace bug This is in preparation for some clashing cgroups changes that subsume the original commit's functionaliy. The original commit fixed a pid namespace bug which Ben Blum fixed independently (in the same way, but with different code) as part of a series of patches. I played around with trying to reconcile Ben's patch series with Li's patch, but concluded that it was simpler to just revert Li's, given that Ben's patch series contained essentially the same fix. Signed-off-by: Paul Menage Cc: Li Zefan Cc: Matt Helsley Cc: "Eric W. Biederman" Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 90bba9e62286..c833d6f23672 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -179,11 +179,14 @@ struct cgroup { */ struct list_head release_list; - /* pids_mutex protects pids_list and cached pid arrays. */ + /* pids_mutex protects the fields below */ struct rw_semaphore pids_mutex; - - /* Linked list of struct cgroup_pids */ - struct list_head pids_list; + /* Array of process ids in the cgroup */ + pid_t *tasks_pids; + /* How many files are using the current tasks_pids array */ + int pids_use_count; + /* Length of the current tasks_pids array */ + int pids_length; /* For RCU-protected deletion */ struct rcu_head rcu_head; -- cgit v1.2.3 From 102a775e3647628727ae83a9a6abf0564c3ca7cb Mon Sep 17 00:00:00 2001 From: Ben Blum Date: Wed, 23 Sep 2009 15:56:26 -0700 Subject: cgroups: add a read-only "procs" file similar to "tasks" that shows only unique tgids struct cgroup used to have a bunch of fields for keeping track of the pidlist for the tasks file. Those are now separated into a new struct cgroup_pidlist, of which two are had, one for procs and one for tasks. The way the seq_file operations are set up is changed so that just the pidlist struct gets passed around as the private data. Interface example: Suppose a multithreaded process has pid 1000 and other threads with ids 1001, 1002, 1003: $ cat tasks 1000 1001 1002 1003 $ cat cgroup.procs 1000 $ Signed-off-by: Ben Blum Signed-off-by: Paul Menage Acked-by: Li Zefan Cc: Matt Helsley Cc: "Eric W. Biederman" Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c833d6f23672..2357733a0a80 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -141,6 +141,17 @@ enum { CGRP_WAIT_ON_RMDIR, }; +struct cgroup_pidlist { + /* protects the other fields */ + struct rw_semaphore mutex; + /* array of xids */ + pid_t *list; + /* how many elements the above list has */ + int length; + /* how many files are using the current array */ + int use_count; +}; + struct cgroup { unsigned long flags; /* "unsigned long" so bitops work */ @@ -179,14 +190,9 @@ struct cgroup { */ struct list_head release_list; - /* pids_mutex protects the fields below */ - struct rw_semaphore pids_mutex; - /* Array of process ids in the cgroup */ - pid_t *tasks_pids; - /* How many files are using the current tasks_pids array */ - int pids_use_count; - /* Length of the current tasks_pids array */ - int pids_length; + /* we will have two separate pidlists, one for pids (the tasks file) + * and one for tgids (the procs file). */ + struct cgroup_pidlist tasks, procs; /* For RCU-protected deletion */ struct rcu_head rcu_head; -- cgit v1.2.3 From 72a8cb30d10d4041c455a7054607a7d519167c87 Mon Sep 17 00:00:00 2001 From: Ben Blum Date: Wed, 23 Sep 2009 15:56:27 -0700 Subject: cgroups: ensure correct concurrent opening/reading of pidlists across pid namespaces Previously there was the problem in which two processes from different pid namespaces reading the tasks or procs file could result in one process seeing results from the other's namespace. Rather than one pidlist for each file in a cgroup, we now keep a list of pidlists keyed by namespace and file type (tasks versus procs) in which entries are placed on demand. Each pidlist has its own lock, and that the pidlists themselves are passed around in the seq_file's private pointer means we don't have to touch the cgroup or its master list except when creating and destroying entries. Signed-off-by: Ben Blum Signed-off-by: Paul Menage Cc: Li Zefan Cc: Matt Helsley Cc: "Eric W. Biederman" Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 34 +++++++++++++++++++++++++++++----- 1 file changed, 29 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 2357733a0a80..88e863460726 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -141,15 +141,36 @@ enum { CGRP_WAIT_ON_RMDIR, }; +/* which pidlist file are we talking about? */ +enum cgroup_filetype { + CGROUP_FILE_PROCS, + CGROUP_FILE_TASKS, +}; + +/* + * A pidlist is a list of pids that virtually represents the contents of one + * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists, + * a pair (one each for procs, tasks) for each pid namespace that's relevant + * to the cgroup. + */ struct cgroup_pidlist { - /* protects the other fields */ - struct rw_semaphore mutex; + /* + * used to find which pidlist is wanted. doesn't change as long as + * this particular list stays in the list. + */ + struct { enum cgroup_filetype type; struct pid_namespace *ns; } key; /* array of xids */ pid_t *list; /* how many elements the above list has */ int length; /* how many files are using the current array */ int use_count; + /* each of these stored in a list by its cgroup */ + struct list_head links; + /* pointer to the cgroup we belong to, for list removal purposes */ + struct cgroup *owner; + /* protects the other fields */ + struct rw_semaphore mutex; }; struct cgroup { @@ -190,9 +211,12 @@ struct cgroup { */ struct list_head release_list; - /* we will have two separate pidlists, one for pids (the tasks file) - * and one for tgids (the procs file). */ - struct cgroup_pidlist tasks, procs; + /* + * list of pidlists, up to two for each namespace (one for procs, one + * for tasks); created on demand. + */ + struct list_head pidlists; + struct mutex pidlist_mutex; /* For RCU-protected deletion */ struct rcu_head rcu_head; -- cgit v1.2.3 From c378369d8b4fa516ff2b1e79c3eded4e0e955ebb Mon Sep 17 00:00:00 2001 From: Ben Blum Date: Wed, 23 Sep 2009 15:56:29 -0700 Subject: cgroups: change css_set freeing mechanism to be under RCU Changes css_set freeing mechanism to be under RCU This is a prepatch for making the procs file writable. In order to free the old css_sets for each task to be moved as they're being moved, the freeing mechanism must be RCU-protected, or else we would have to have a call to synchronize_rcu() for each task before freeing its old css_set. Signed-off-by: Ben Blum Signed-off-by: Paul Menage Cc: "Paul E. McKenney" Acked-by: Li Zefan Cc: Matt Helsley Cc: "Eric W. Biederman" Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 88e863460726..3ac78a2f4b5a 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -260,6 +260,9 @@ struct css_set { * during subsystem registration (at boot time). */ struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; + + /* For RCU-protected deletion */ + struct rcu_head rcu_head; }; /* -- cgit v1.2.3 From be367d09927023d081f9199665c8500f69f14d22 Mon Sep 17 00:00:00 2001 From: Ben Blum Date: Wed, 23 Sep 2009 15:56:31 -0700 Subject: cgroups: let ss->can_attach and ss->attach do whole threadgroups at a time Alter the ss->can_attach and ss->attach functions to be able to deal with a whole threadgroup at a time, for use in cgroup_attach_proc. (This is a pre-patch to cgroup-procs-writable.patch.) Currently, new mode of the attach function can only tell the subsystem about the old cgroup of the threadgroup leader. No subsystem currently needs that information for each thread that's being moved, but if one were to be added (for example, one that counts tasks within a group) this bit would need to be reworked a bit to tell the subsystem the right information. [hidave.darkstar@gmail.com: fix build] Signed-off-by: Ben Blum Signed-off-by: Paul Menage Acked-by: Li Zefan Reviewed-by: Matt Helsley Cc: "Eric W. Biederman" Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Dave Young Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 3ac78a2f4b5a..b62bb9294d0c 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -425,10 +425,11 @@ struct cgroup_subsys { struct cgroup *cgrp); int (*pre_destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp); void (*destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp); - int (*can_attach)(struct cgroup_subsys *ss, - struct cgroup *cgrp, struct task_struct *tsk); + int (*can_attach)(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct task_struct *tsk, bool threadgroup); void (*attach)(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup *old_cgrp, struct task_struct *tsk); + struct cgroup *old_cgrp, struct task_struct *tsk, + bool threadgroup); void (*fork)(struct cgroup_subsys *ss, struct task_struct *task); void (*exit)(struct cgroup_subsys *ss, struct task_struct *task); int (*populate)(struct cgroup_subsys *ss, -- cgit v1.2.3 From 4b3bde4c983de36c59e6c1a24701f6fe816f9f55 Mon Sep 17 00:00:00 2001 From: Balbir Singh Date: Wed, 23 Sep 2009 15:56:32 -0700 Subject: memcg: remove the overhead associated with the root cgroup Change the memory cgroup to remove the overhead associated with accounting all pages in the root cgroup. As a side-effect, we can no longer set a memory hard limit in the root cgroup. A new flag to track whether the page has been accounted or not has been added as well. Flags are now set atomically for page_cgroup, pcg_default_flags is now obsolete and removed. [akpm@linux-foundation.org: fix a few documentation glitches] Signed-off-by: Balbir Singh Signed-off-by: Daisuke Nishimura Reviewed-by: KAMEZAWA Hiroyuki Cc: Daisuke Nishimura Cc: Li Zefan Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_cgroup.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index ada779f24178..4b938d4f3ac2 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -38,6 +38,7 @@ enum { PCG_LOCK, /* page cgroup is locked */ PCG_CACHE, /* charged as cache */ PCG_USED, /* this object is in use. */ + PCG_ACCT_LRU, /* page has been accounted for */ }; #define TESTPCGFLAG(uname, lname) \ @@ -52,11 +53,23 @@ static inline void SetPageCgroup##uname(struct page_cgroup *pc)\ static inline void ClearPageCgroup##uname(struct page_cgroup *pc) \ { clear_bit(PCG_##lname, &pc->flags); } +#define TESTCLEARPCGFLAG(uname, lname) \ +static inline int TestClearPageCgroup##uname(struct page_cgroup *pc) \ + { return test_and_clear_bit(PCG_##lname, &pc->flags); } + /* Cache flag is set only once (at allocation) */ TESTPCGFLAG(Cache, CACHE) +CLEARPCGFLAG(Cache, CACHE) +SETPCGFLAG(Cache, CACHE) TESTPCGFLAG(Used, USED) CLEARPCGFLAG(Used, USED) +SETPCGFLAG(Used, USED) + +SETPCGFLAG(AcctLRU, ACCT_LRU) +CLEARPCGFLAG(AcctLRU, ACCT_LRU) +TESTPCGFLAG(AcctLRU, ACCT_LRU) +TESTCLEARPCGFLAG(AcctLRU, ACCT_LRU) static inline int page_cgroup_nid(struct page_cgroup *pc) { -- cgit v1.2.3 From 296c81d89f4f14269f7346f81442910158c0a83a Mon Sep 17 00:00:00 2001 From: Balbir Singh Date: Wed, 23 Sep 2009 15:56:36 -0700 Subject: memory controller: soft limit interface Add an interface to allow get/set of soft limits. Soft limits for memory plus swap controller (memsw) is currently not supported. Resource counters have been enhanced to support soft limits and new type RES_SOFT_LIMIT has been added. Unlike hard limits, soft limits can be directly set and do not need any reclaim or checks before setting them to a newer value. Kamezawa-San raised a question as to whether soft limit should belong to res_counter. Since all resources understand the basic concepts of hard and soft limits, it is justified to add soft limits here. Soft limits are a generic resource usage feature, even file system quotas support soft limits. Signed-off-by: Balbir Singh Cc: KAMEZAWA Hiroyuki Cc: Li Zefan Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/res_counter.h | 58 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) (limited to 'include/linux') diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index 511f42fc6816..fcb9884df618 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -34,6 +34,10 @@ struct res_counter { * the limit that usage cannot exceed */ unsigned long long limit; + /* + * the limit that usage can be exceed + */ + unsigned long long soft_limit; /* * the number of unsuccessful attempts to consume the resource */ @@ -87,6 +91,7 @@ enum { RES_MAX_USAGE, RES_LIMIT, RES_FAILCNT, + RES_SOFT_LIMIT, }; /* @@ -132,6 +137,36 @@ static inline bool res_counter_limit_check_locked(struct res_counter *cnt) return false; } +static inline bool res_counter_soft_limit_check_locked(struct res_counter *cnt) +{ + if (cnt->usage < cnt->soft_limit) + return true; + + return false; +} + +/** + * Get the difference between the usage and the soft limit + * @cnt: The counter + * + * Returns 0 if usage is less than or equal to soft limit + * The difference between usage and soft limit, otherwise. + */ +static inline unsigned long long +res_counter_soft_limit_excess(struct res_counter *cnt) +{ + unsigned long long excess; + unsigned long flags; + + spin_lock_irqsave(&cnt->lock, flags); + if (cnt->usage <= cnt->soft_limit) + excess = 0; + else + excess = cnt->usage - cnt->soft_limit; + spin_unlock_irqrestore(&cnt->lock, flags); + return excess; +} + /* * Helper function to detect if the cgroup is within it's limit or * not. It's currently called from cgroup_rss_prepare() @@ -147,6 +182,17 @@ static inline bool res_counter_check_under_limit(struct res_counter *cnt) return ret; } +static inline bool res_counter_check_under_soft_limit(struct res_counter *cnt) +{ + bool ret; + unsigned long flags; + + spin_lock_irqsave(&cnt->lock, flags); + ret = res_counter_soft_limit_check_locked(cnt); + spin_unlock_irqrestore(&cnt->lock, flags); + return ret; +} + static inline void res_counter_reset_max(struct res_counter *cnt) { unsigned long flags; @@ -180,4 +226,16 @@ static inline int res_counter_set_limit(struct res_counter *cnt, return ret; } +static inline int +res_counter_set_soft_limit(struct res_counter *cnt, + unsigned long long soft_limit) +{ + unsigned long flags; + + spin_lock_irqsave(&cnt->lock, flags); + cnt->soft_limit = soft_limit; + spin_unlock_irqrestore(&cnt->lock, flags); + return 0; +} + #endif -- cgit v1.2.3 From f64c3f54940d6929a2b6dcffaab942bd62be2e66 Mon Sep 17 00:00:00 2001 From: Balbir Singh Date: Wed, 23 Sep 2009 15:56:37 -0700 Subject: memory controller: soft limit organize cgroups Organize cgroups over soft limit in a RB-Tree Introduce an RB-Tree for storing memory cgroups that are over their soft limit. The overall goal is to 1. Add a memory cgroup to the RB-Tree when the soft limit is exceeded. We are careful about updates, updates take place only after a particular time interval has passed 2. We remove the node from the RB-Tree when the usage goes below the soft limit The next set of patches will exploit the RB-Tree to get the group that is over its soft limit by the largest amount and reclaim from it, when we face memory contention. [hugh.dickins@tiscali.co.uk: CONFIG_CGROUP_MEM_RES_CTLR=y CONFIG_PREEMPT=y fails to boot] Signed-off-by: Balbir Singh Signed-off-by: KAMEZAWA Hiroyuki Cc: Li Zefan Cc: KOSAKI Motohiro Signed-off-by: Hugh Dickins Cc: Jiri Slaby Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/res_counter.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index fcb9884df618..731af71cddc9 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -114,7 +114,8 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent); int __must_check res_counter_charge_locked(struct res_counter *counter, unsigned long val); int __must_check res_counter_charge(struct res_counter *counter, - unsigned long val, struct res_counter **limit_fail_at); + unsigned long val, struct res_counter **limit_fail_at, + struct res_counter **soft_limit_at); /* * uncharge - tell that some portion of the resource is released @@ -127,7 +128,8 @@ int __must_check res_counter_charge(struct res_counter *counter, */ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val); -void res_counter_uncharge(struct res_counter *counter, unsigned long val); +void res_counter_uncharge(struct res_counter *counter, unsigned long val, + bool *was_soft_limit_excess); static inline bool res_counter_limit_check_locked(struct res_counter *cnt) { -- cgit v1.2.3 From 4e41695356fb4e0b153be1440ad027e46e0a7ea2 Mon Sep 17 00:00:00 2001 From: Balbir Singh Date: Wed, 23 Sep 2009 15:56:39 -0700 Subject: memory controller: soft limit reclaim on contention Implement reclaim from groups over their soft limit Permit reclaim from memory cgroups on contention (via the direct reclaim path). memory cgroup soft limit reclaim finds the group that exceeds its soft limit by the largest number of pages and reclaims pages from it and then reinserts the cgroup into its correct place in the rbtree. Add additional checks to mem_cgroup_hierarchical_reclaim() to detect long loops in case all swap is turned off. The code has been refactored and the loop check (loop < 2) has been enhanced for soft limits. For soft limits, we try to do more targetted reclaim. Instead of bailing out after two loops, the routine now reclaims memory proportional to the size by which the soft limit is exceeded. The proportion has been empirically determined. [akpm@linux-foundation.org: build fix] [kamezawa.hiroyu@jp.fujitsu.com: fix softlimit css refcnt handling] [nishimura@mxp.nes.nec.co.jp: refcount of the "victim" should be decremented before exiting the loop] Signed-off-by: Balbir Singh Cc: KAMEZAWA Hiroyuki Cc: Li Zefan Acked-by: KOSAKI Motohiro Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Daisuke Nishimura Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 10 ++++++++++ include/linux/swap.h | 5 +++++ 2 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e46a0734ab6e..bf9213b2db8f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -118,6 +118,9 @@ static inline bool mem_cgroup_disabled(void) extern bool mem_cgroup_oom_called(struct task_struct *task); void mem_cgroup_update_mapped_file_stat(struct page *page, int val); +unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, + gfp_t gfp_mask, int nid, + int zid); #else /* CONFIG_CGROUP_MEM_RES_CTLR */ struct mem_cgroup; @@ -276,6 +279,13 @@ static inline void mem_cgroup_update_mapped_file_stat(struct page *page, { } +static inline +unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, + gfp_t gfp_mask, int nid, int zid) +{ + return 0; +} + #endif /* CONFIG_CGROUP_MEM_CONT */ #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 6c990e658f4e..4c78fea989b9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -217,6 +217,11 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, unsigned int swappiness); +extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, + gfp_t gfp_mask, bool noswap, + unsigned int swappiness, + struct zone *zone, + int nid); extern int __isolate_lru_page(struct page *page, int mode, int file); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; -- cgit v1.2.3 From a7f0765edfd53aed09cb7b0e15863688b39447de Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 23 Sep 2009 15:56:44 -0700 Subject: ptrace: __ptrace_detach: do __wake_up_parent() if we reap the tracee The bug is old, it wasn't cause by recent changes. Test case: static void *tfunc(void *arg) { int pid = (long)arg; assert(ptrace(PTRACE_ATTACH, pid, NULL, NULL) == 0); kill(pid, SIGKILL); sleep(1); return NULL; } int main(void) { pthread_t th; long pid = fork(); if (!pid) pause(); signal(SIGCHLD, SIG_IGN); assert(pthread_create(&th, NULL, tfunc, (void*)pid) == 0); int r = waitpid(-1, NULL, __WNOTHREAD); printf("waitpid: %d %m\n", r); return 0; } Before the patch this program hangs, after this patch waitpid() correctly fails with errno == -ECHILD. The problem is, __ptrace_detach() reaps the EXIT_ZOMBIE tracee if its ->real_parent is our sub-thread and we ignore SIGCHLD. But in this case we should wake up other threads which can sleep in do_wait(). Signed-off-by: Oleg Nesterov Cc: Roland McGrath Cc: Vitaly Mayatskikh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 848d1f20086e..9e5a88afe6be 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2059,6 +2059,7 @@ extern int kill_pgrp(struct pid *pid, int sig, int priv); extern int kill_pid(struct pid *pid, int sig, int priv); extern int kill_proc_info(int, struct siginfo *, pid_t); extern int do_notify_parent(struct task_struct *, int); +extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); extern void force_sig(int, struct task_struct *); extern void force_sig_specific(int, struct task_struct *); extern int send_sig(int, struct task_struct *, int); -- cgit v1.2.3 From ae6d2ed7bb3877ff35b9569402025f40ea2e1803 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Wed, 23 Sep 2009 15:56:53 -0700 Subject: signals: tracehook_notify_jctl change This changes tracehook_notify_jctl() so it's called with the siglock held, and changes its argument and return value definition. These clean-ups make it a better fit for what new tracing hooks need to check. Tracing needs the siglock here, held from the time TASK_STOPPED was set, to avoid potential SIGCONT races if it wants to allow any blocking in its tracing hooks. This also folds the finish_stop() function into its caller do_signal_stop(). The function is short, called only once and only unconditionally. It aids readability to fold it in. [oleg@redhat.com: do not call tracehook_notify_jctl() in TASK_STOPPED state] [oleg@redhat.com: introduce tracehook_finish_jctl() helper] Signed-off-by: Roland McGrath Signed-off-by: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 34 +++++++++++++++++++++++++--------- 1 file changed, 25 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 17ba82efa483..1eb44a924e56 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -1,7 +1,7 @@ /* * Tracing hooks * - * Copyright (C) 2008 Red Hat, Inc. All rights reserved. + * Copyright (C) 2008-2009 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 @@ -463,22 +463,38 @@ static inline int tracehook_get_signal(struct task_struct *task, /** * tracehook_notify_jctl - report about job control stop/continue - * @notify: nonzero if this is the last thread in the group to stop + * @notify: zero, %CLD_STOPPED or %CLD_CONTINUED * @why: %CLD_STOPPED or %CLD_CONTINUED * * This is called when we might call do_notify_parent_cldstop(). - * It's called when about to stop for job control; we are already in - * %TASK_STOPPED state, about to call schedule(). It's also called when - * a delayed %CLD_STOPPED or %CLD_CONTINUED report is ready to be made. * - * Return nonzero to generate a %SIGCHLD with @why, which is - * normal if @notify is nonzero. + * @notify is zero if we would not ordinarily send a %SIGCHLD, + * or is the %CLD_STOPPED or %CLD_CONTINUED .si_code for %SIGCHLD. * - * Called with no locks held. + * @why is %CLD_STOPPED when about to stop for job control; + * we are already in %TASK_STOPPED state, about to call schedule(). + * It might also be that we have just exited (check %PF_EXITING), + * but need to report that a group-wide stop is complete. + * + * @why is %CLD_CONTINUED when waking up after job control stop and + * ready to make a delayed @notify report. + * + * Return the %CLD_* value for %SIGCHLD, or zero to generate no signal. + * + * Called with the siglock held. */ static inline int tracehook_notify_jctl(int notify, int why) { - return notify || (current->ptrace & PT_PTRACED); + return notify ?: (current->ptrace & PT_PTRACED) ? why : 0; +} + +/** + * tracehook_finish_jctl - report about return from job control stop + * + * This is called by do_signal_stop() after wakeup. + */ +static inline void tracehook_finish_jctl(void) +{ } #define DEATH_REAP -1 -- cgit v1.2.3 From 964ee7df90d799e38fb1556c57cd5c45fc736436 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 23 Sep 2009 15:56:59 -0700 Subject: exec: fix set_binfmt() vs sys_delete_module() race sys_delete_module() can set MODULE_STATE_GOING after search_binary_handler() does try_module_get(). In this case set_binfmt()->try_module_get() fails but since none of the callers check the returned error, the task will run with the wrong old ->binfmt. The proper fix should change all ->load_binary() methods, but we can rely on fact that the caller must hold a reference to binfmt->module and use __module_get() which never fails. Signed-off-by: Oleg Nesterov Acked-by: Rusty Russell Cc: Hiroshi Shimamoto Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/binfmts.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 2046b5b8af48..aece486ac734 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -120,7 +120,7 @@ extern int copy_strings_kernel(int argc,char ** argv,struct linux_binprm *bprm); extern int prepare_bprm_creds(struct linux_binprm *bprm); extern void install_exec_creds(struct linux_binprm *bprm); extern void do_coredump(long signr, int exit_code, struct pt_regs *regs); -extern int set_binfmt(struct linux_binfmt *new); +extern void set_binfmt(struct linux_binfmt *new); extern void free_bprm(struct linux_binprm *); #endif /* __KERNEL__ */ -- cgit v1.2.3 From 4a30debfb778240a4b1767d4b0c5a5b25ab97160 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 23 Sep 2009 15:57:00 -0700 Subject: signals: introduce do_send_sig_info() helper Introduce do_send_sig_info() and convert group_send_sig_info(), send_sig_info(), do_send_specific() to use this helper. Hopefully it will have more users soon, it allows to specify specific/group behaviour via "bool group" argument. Shaves 80 bytes from .text. Signed-off-by: Oleg Nesterov Cc: Peter Zijlstra Cc: stephane eranian Cc: Ingo Molnar Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/signal.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index c7552836bd95..ab9272cc270c 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -233,6 +233,8 @@ static inline int valid_signal(unsigned long sig) } extern int next_signal(struct sigpending *pending, sigset_t *mask); +extern int do_send_sig_info(int sig, struct siginfo *info, + struct task_struct *p, bool group); extern int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p); extern int __group_send_sig_info(int, struct siginfo *, struct task_struct *); extern long do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, -- cgit v1.2.3 From d9588725e52650e82989707f8fd2feb67ad2dc8e Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Wed, 23 Sep 2009 15:57:04 -0700 Subject: signals: inline __fatal_signal_pending __fatal_signal_pending inlines to one instruction on x86, probably two instructions on other machines. It takes two longer x86 instructions just to call it and test its return value, not to mention the function itself. On my random x86_64 config, this saved 70 bytes of text (59 of those being __fatal_signal_pending itself). Signed-off-by: Roland McGrath Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 9e5a88afe6be..e951bd2eb9fc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2337,7 +2337,10 @@ static inline int signal_pending(struct task_struct *p) return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING)); } -extern int __fatal_signal_pending(struct task_struct *p); +static inline int __fatal_signal_pending(struct task_struct *p) +{ + return unlikely(sigismember(&p->pending.signal, SIGKILL)); +} static inline int fatal_signal_pending(struct task_struct *p) { -- cgit v1.2.3 From 8d65af789f3e2cf4cfbdbf71a0f7a61ebcd41d38 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 23 Sep 2009 15:57:19 -0700 Subject: sysctl: remove "struct file *" argument of ->proc_handler It's unused. It isn't needed -- read or write flag is already passed and sysctl shouldn't care about the rest. It _was_ used in two places at arch/frv for some reason. Signed-off-by: Alexey Dobriyan Cc: David Howells Cc: "Eric W. Biederman" Cc: Al Viro Cc: Ralf Baechle Cc: Martin Schwidefsky Cc: Ingo Molnar Cc: "David S. Miller" Cc: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- include/linux/ftrace.h | 4 ++-- include/linux/hugetlb.h | 6 +++--- include/linux/mm.h | 2 +- include/linux/mmzone.h | 13 ++++++------- include/linux/sched.h | 8 ++++---- include/linux/security.h | 2 +- include/linux/swap.h | 2 +- include/linux/sysctl.h | 19 +++++++++---------- include/linux/writeback.h | 11 +++++------ 10 files changed, 33 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 51803528b095..33ed6644abd0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2467,7 +2467,7 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); struct ctl_table; -int proc_nr_files(struct ctl_table *table, int write, struct file *filp, +int proc_nr_files(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); int __init get_filesystem_list(char *buf); diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 3c0924a18daf..cd3d2abaf30a 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -19,7 +19,7 @@ extern int ftrace_enabled; extern int ftrace_enable_sysctl(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip); @@ -94,7 +94,7 @@ static inline void ftrace_start(void) { } extern int stack_tracer_enabled; int stack_trace_sysctl(struct ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); #endif diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 176e7ee73eff..11ab19ac6b3d 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -20,9 +20,9 @@ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) } void reset_vma_resv_huge_pages(struct vm_area_struct *vma); -int hugetlb_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); -int hugetlb_overcommit_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); -int hugetlb_treat_movable_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); +int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); +int hugetlb_overcommit_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); +int hugetlb_treat_movable_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, diff --git a/include/linux/mm.h b/include/linux/mm.h index b6eae5e3144b..87218ae84e36 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1279,7 +1279,7 @@ int in_gate_area_no_task(unsigned long addr); #define in_gate_area(task, addr) ({(void)task; in_gate_area_no_task(addr);}) #endif /* __HAVE_ARCH_GATE_AREA */ -int drop_caches_sysctl_handler(struct ctl_table *, int, struct file *, +int drop_caches_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask, unsigned long lru_pages); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 652ef01be582..6f7561730d88 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -755,21 +755,20 @@ static inline int is_dma(struct zone *zone) /* These two functions are used to setup the per zone pages min values */ struct ctl_table; -struct file; -int min_free_kbytes_sysctl_handler(struct ctl_table *, int, struct file *, +int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1]; -int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, struct file *, +int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); -int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, struct file *, +int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int, - struct file *, void __user *, size_t *, loff_t *); + void __user *, size_t *, loff_t *); int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, - struct file *, void __user *, size_t *, loff_t *); + void __user *, size_t *, loff_t *); extern int numa_zonelist_order_handler(struct ctl_table *, int, - struct file *, void __user *, size_t *, loff_t *); + void __user *, size_t *, loff_t *); extern char numa_zonelist_order[]; #define NUMA_ZONELIST_ORDER_LEN 16 /* string buffer size */ diff --git a/include/linux/sched.h b/include/linux/sched.h index e951bd2eb9fc..811cd96524d7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -309,7 +309,7 @@ extern void softlockup_tick(void); extern void touch_softlockup_watchdog(void); extern void touch_all_softlockup_watchdogs(void); extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos); extern unsigned int softlockup_panic; extern int softlockup_thresh; @@ -331,7 +331,7 @@ extern unsigned long sysctl_hung_task_check_count; extern unsigned long sysctl_hung_task_timeout_secs; extern unsigned long sysctl_hung_task_warnings; extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos); #endif @@ -1906,7 +1906,7 @@ extern unsigned int sysctl_sched_time_avg; extern unsigned int sysctl_timer_migration; int sched_nr_latency_handler(struct ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, + void __user *buffer, size_t *length, loff_t *ppos); #endif #ifdef CONFIG_SCHED_DEBUG @@ -1924,7 +1924,7 @@ extern unsigned int sysctl_sched_rt_period; extern int sysctl_sched_rt_runtime; int sched_rt_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); extern unsigned int sysctl_sched_compat_yield; diff --git a/include/linux/security.h b/include/linux/security.h index d050b66ab9ef..239e40d0450b 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -133,7 +133,7 @@ static inline unsigned long round_hint_to_min(unsigned long hint) return PAGE_ALIGN(mmap_min_addr); return hint; } -extern int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp, +extern int mmap_min_addr_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); #ifdef CONFIG_SECURITY diff --git a/include/linux/swap.h b/include/linux/swap.h index 4c78fea989b9..82232dbea3f7 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -245,7 +245,7 @@ extern int page_evictable(struct page *page, struct vm_area_struct *vma); extern void scan_mapping_unevictable_pages(struct address_space *); extern unsigned long scan_unevictable_pages; -extern int scan_unevictable_handler(struct ctl_table *, int, struct file *, +extern int scan_unevictable_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int scan_unevictable_register_node(struct node *node); extern void scan_unevictable_unregister_node(struct node *node); diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index e76d3b22a466..1e4743ee6831 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -29,7 +29,6 @@ #include #include -struct file; struct completion; #define CTL_MAXNAME 10 /* how many path components do we allow in a @@ -977,25 +976,25 @@ typedef int ctl_handler (struct ctl_table *table, void __user *oldval, size_t __user *oldlenp, void __user *newval, size_t newlen); -typedef int proc_handler (struct ctl_table *ctl, int write, struct file * filp, +typedef int proc_handler (struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -extern int proc_dostring(struct ctl_table *, int, struct file *, +extern int proc_dostring(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int proc_dointvec(struct ctl_table *, int, struct file *, +extern int proc_dointvec(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int proc_dointvec_minmax(struct ctl_table *, int, struct file *, +extern int proc_dointvec_minmax(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int proc_dointvec_jiffies(struct ctl_table *, int, struct file *, +extern int proc_dointvec_jiffies(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int, struct file *, +extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int proc_dointvec_ms_jiffies(struct ctl_table *, int, struct file *, +extern int proc_dointvec_ms_jiffies(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int proc_doulongvec_minmax(struct ctl_table *, int, struct file *, +extern int proc_doulongvec_minmax(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int, - struct file *, void __user *, size_t *, loff_t *); + void __user *, size_t *, loff_t *); extern int do_sysctl (int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp, diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 75cf58666ff9..66ebddcff664 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -110,21 +110,20 @@ extern int laptop_mode; extern unsigned long determine_dirtyable_memory(void); extern int dirty_background_ratio_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); extern int dirty_background_bytes_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); extern int dirty_ratio_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); extern int dirty_bytes_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); struct ctl_table; -struct file; -int dirty_writeback_centisecs_handler(struct ctl_table *, int, struct file *, +int dirty_writeback_centisecs_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); void get_dirty_limits(unsigned long *pbackground, unsigned long *pdirty, -- cgit v1.2.3 From 9064a6787aa1d8ceaf5ba16fe1dfedb0755dc7eb Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Wed, 23 Sep 2009 15:57:23 -0700 Subject: linux/futex.h: place kernel types behind __KERNEL__ The forward decls for some kernel types are only needed by the code behind __KERNEL__, so don't bleed these types to userspace. Signed-off-by: Mike Frysinger Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/futex.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/futex.h b/include/linux/futex.h index 34956c8fdebf..8ec17997d94f 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -4,11 +4,6 @@ #include #include -struct inode; -struct mm_struct; -struct task_struct; -union ktime; - /* Second argument to futex syscall */ @@ -129,6 +124,11 @@ struct robust_list_head { #define FUTEX_BITSET_MATCH_ANY 0xffffffff #ifdef __KERNEL__ +struct inode; +struct mm_struct; +struct task_struct; +union ktime; + long do_futex(u32 __user *uaddr, int op, u32 val, union ktime *timeout, u32 __user *uaddr2, u32 val2, u32 val3); -- cgit v1.2.3 From 858f09930b32c11b40fd0c5c467982ba09b10894 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 23 Sep 2009 15:57:32 -0700 Subject: aio: ifdef fields in mm_struct ->ioctx_lock and ->ioctx_list are used only under CONFIG_AIO. Signed-off-by: Alexey Dobriyan Cc: Zach Brown Cc: Benjamin LaHaise Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 0042090a4d70..6b7029ab9c8e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -259,11 +259,10 @@ struct mm_struct { unsigned long flags; /* Must use atomic bitops to access the bits */ struct core_state *core_state; /* coredumping support */ - - /* aio bits */ +#ifdef CONFIG_AIO spinlock_t ioctx_lock; struct hlist_head ioctx_list; - +#endif #ifdef CONFIG_MM_OWNER /* * "owner" points to a task that is regarded as the canonical -- cgit v1.2.3 From 2fa4341074cd02fb39aa23410740764948755635 Mon Sep 17 00:00:00 2001 From: Albin Tonnerre Date: Wed, 23 Sep 2009 15:57:38 -0700 Subject: include/linux/unaligned/{l,b}e_byteshift.h: fix usage for compressed kernels When unaligned accesses are required for uncompressing a kernel (such as for LZO decompression on ARM in a patch that follows), including causes issues as it brings in a lot of things that are not available in the decompression environment. linux/kernel.h brings at least: extern int console_printk[]; extern const char hex_asc[]; which causes errors at link-time as they are not available when compiling the pre-boot environement. There are also a few others: arch/arm/boot/compressed/misc.o: In function `valid_user_regs': arch/arm/include/asm/ptrace.h:158: undefined reference to `elf_hwcap' arch/arm/boot/compressed/misc.o: In function `console_silent': include/linux/kernel.h:292: undefined reference to `console_printk' arch/arm/boot/compressed/misc.o: In function `console_verbose': include/linux/kernel.h:297: undefined reference to `console_printk' arch/arm/boot/compressed/misc.o: In function `pack_hex_byte': include/linux/kernel.h:360: undefined reference to `hex_asc' arch/arm/boot/compressed/misc.o: In function `hweight_long': include/linux/bitops.h:45: undefined reference to `hweight32' arch/arm/boot/compressed/misc.o: In function `__cmpxchg_local_generic': include/asm-generic/cmpxchg-local.h:21: undefined reference to `wrong_size_cmpxchg' include/asm-generic/cmpxchg-local.h:42: undefined reference to `wrong_size_cmpxchg' arch/arm/boot/compressed/misc.o: In function `__xchg': arch/arm/include/asm/system.h:309: undefined reference to `__bad_xchg' However, those files apparently use nothing from , all they need is the declaration of types such as u32 or u64, so should be enough Signed-off-by: Albin Tonnerre Cc: Sam Ravnborg Cc: Russell King Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Phillip Lougher Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/unaligned/be_byteshift.h | 2 +- include/linux/unaligned/le_byteshift.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/unaligned/be_byteshift.h b/include/linux/unaligned/be_byteshift.h index 46dd12c5709e..9356b24223ac 100644 --- a/include/linux/unaligned/be_byteshift.h +++ b/include/linux/unaligned/be_byteshift.h @@ -1,7 +1,7 @@ #ifndef _LINUX_UNALIGNED_BE_BYTESHIFT_H #define _LINUX_UNALIGNED_BE_BYTESHIFT_H -#include +#include static inline u16 __get_unaligned_be16(const u8 *p) { diff --git a/include/linux/unaligned/le_byteshift.h b/include/linux/unaligned/le_byteshift.h index 59777e951baf..be376fb79b64 100644 --- a/include/linux/unaligned/le_byteshift.h +++ b/include/linux/unaligned/le_byteshift.h @@ -1,7 +1,7 @@ #ifndef _LINUX_UNALIGNED_LE_BYTESHIFT_H #define _LINUX_UNALIGNED_LE_BYTESHIFT_H -#include +#include static inline u16 __get_unaligned_le16(const u8 *p) { -- cgit v1.2.3 From 801460d0cf5c5288153b722565773059b0f44348 Mon Sep 17 00:00:00 2001 From: Hiroshi Shimamoto Date: Wed, 23 Sep 2009 15:57:41 -0700 Subject: task_struct cleanup: move binfmt field to mm_struct Because the binfmt is not different between threads in the same process, it can be moved from task_struct to mm_struct. And binfmt moudle is handled per mm_struct instead of task_struct. Signed-off-by: Hiroshi Shimamoto Acked-by: Oleg Nesterov Cc: Rusty Russell Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 ++ include/linux/sched.h | 1 - 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6b7029ab9c8e..21d6aa45206a 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -240,6 +240,8 @@ struct mm_struct { unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ + struct linux_binfmt *binfmt; + cpumask_t cpu_vm_mask; /* Architecture-specific MM context */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 811cd96524d7..8a16f6d11dcd 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1271,7 +1271,6 @@ struct task_struct { struct mm_struct *mm, *active_mm; /* task state */ - struct linux_binfmt *binfmt; int exit_state; int exit_code, exit_signal; int pdeath_signal; /* The signal sent when the parent dies */ -- cgit v1.2.3 From 4a4962263f07d14660849ec134ee42b63e95ea9a Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 6 Jul 2009 14:50:42 +0100 Subject: module: reduce symbol table for loaded modules (v2) Discard all symbols not interesting for kallsyms use: absolute, section, and in the common case (!KALLSYMS_ALL) data ones. Signed-off-by: Jan Beulich Signed-off-by: Rusty Russell --- include/linux/module.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 1c755b2f937d..1d3ccb173fd6 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -308,9 +308,13 @@ struct module #endif #ifdef CONFIG_KALLSYMS - /* We keep the symbol and string tables for kallsyms. */ - Elf_Sym *symtab; - unsigned int num_symtab; + /* + * We keep the symbol and string tables for kallsyms. + * The core_* fields below are temporary, loader-only (they + * could really be discarded after module init). + */ + Elf_Sym *symtab, *core_symtab; + unsigned int num_symtab, core_num_syms; char *strtab; /* Section attributes */ -- cgit v1.2.3 From 554bdfe5acf3715e87c8d5e25a4f9a896ac9f014 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 6 Jul 2009 14:51:44 +0100 Subject: module: reduce string table for loaded modules (v2) Also remove all parts of the string table (referenced by the symbol table) that are not needed for kallsyms use (i.e. which were only referenced by symbols discarded by the previous patch, or not referenced at all for whatever reason). Signed-off-by: Jan Beulich Signed-off-by: Rusty Russell --- include/linux/module.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 1d3ccb173fd6..aca980365956 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -315,7 +315,7 @@ struct module */ Elf_Sym *symtab, *core_symtab; unsigned int num_symtab, core_num_syms; - char *strtab; + char *strtab, *core_strtab; /* Section attributes */ struct module_sect_attrs *sect_attrs; -- cgit v1.2.3 From 1d7015caa082d465faeae5d6fd1be077ee6dfa87 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 25 Sep 2009 00:32:58 -0600 Subject: module: preferred way to use MODULE_AUTHOR For the longest time now we've been using multiple MODULE_AUTHOR() statements when a module has more than one author, but the comment here disagrees. Signed-off-by: Johannes Berg Cc: Jiri Kosina Cc: Luciano Coelho Signed-off-by: Andrew Morton Signed-off-by: Rusty Russell --- include/linux/module.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index aca980365956..482efc865acf 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -128,7 +128,10 @@ extern struct module __this_module; */ #define MODULE_LICENSE(_license) MODULE_INFO(license, _license) -/* Author, ideally of form NAME[, NAME]*[ and NAME] */ +/* + * Author(s), use "Name " or just "Name", for multiple + * authors use multiple MODULE_AUTHOR() statements/lines. + */ #define MODULE_AUTHOR(_author) MODULE_INFO(author, _author) /* What your module does. */ -- cgit v1.2.3 From e9ea0e2d1d00959b451dfc239df126d3c6a22043 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 24 Sep 2009 14:47:45 -0700 Subject: hugetlb_file_setup(): use C, not cpp Why macros are always wrong: mm/mmap.c: In function 'do_mmap_pgoff': mm/mmap.c:953: warning: unused variable 'user' also, move a couple of struct forward-decls outside `#ifdef CONFIG_HUGETLB_PAGE' - it's pointless and frequently harmful to make these conditional (eg, this patch needed `struct user_struct'). Cc: Lee Schermerhorn Cc: Mel Gorman Cc: Nishanth Aravamudan Cc: David Rientjes Cc: Adam Litke Cc: Andy Whitcroft Cc: Eric Whitney Cc: Eric B Munson Cc: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 11ab19ac6b3d..16937995abd4 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -3,15 +3,15 @@ #include +struct ctl_table; +struct user_struct; + #ifdef CONFIG_HUGETLB_PAGE #include #include #include -struct ctl_table; -struct user_struct; - int PageHuge(struct page *page); static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) @@ -187,7 +187,11 @@ static inline void set_file_hugepages(struct file *file) #define is_file_hugepages(file) 0 #define set_file_hugepages(file) BUG() -#define hugetlb_file_setup(name,size,acct,user,creat) ERR_PTR(-ENOSYS) +static inline struct file *hugetlb_file_setup(const char *name, size_t size, + int acctflag, struct user_struct **user, int creat_flags) +{ + return ERR_PTR(-ENOSYS); +} #endif /* !CONFIG_HUGETLBFS */ -- cgit v1.2.3 From 934831d060ccd5471ecbc562804a8d3ccd6e562c Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 24 Sep 2009 12:33:32 +0100 Subject: NOMMU: Fallback for is_vmalloc_or_module_addr() should be inline The NOMMU fallback for is_vmalloc_or_module_addr() should be static inline, not just static, in linux/mm.h. Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index df08551cb0ad..24c395694f4d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -288,7 +288,7 @@ static inline int is_vmalloc_addr(const void *x) #ifdef CONFIG_MMU extern int is_vmalloc_or_module_addr(const void *x); #else -static int is_vmalloc_or_module_addr(const void *x) +static inline int is_vmalloc_or_module_addr(const void *x) { return 0; } -- cgit v1.2.3