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 --- Documentation/crypto/async-tx-api.txt | 9 ++++----- crypto/async_tx/async_memcpy.c | 2 +- crypto/async_tx/async_memset.c | 2 +- crypto/async_tx/async_tx.c | 4 ++-- crypto/async_tx/async_xor.c | 6 ++---- drivers/md/raid5.c | 25 +++++++++++-------------- include/linux/async_tx.h | 4 +--- 7 files changed, 22 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/Documentation/crypto/async-tx-api.txt b/Documentation/crypto/async-tx-api.txt index 4af12180d191..76feda8541dc 100644 --- a/Documentation/crypto/async-tx-api.txt +++ b/Documentation/crypto/async-tx-api.txt @@ -80,8 +80,8 @@ acknowledged by the application before the offload engine driver is allowed to recycle (or free) the descriptor. A descriptor can be acked by one of the following methods: 1/ setting the ASYNC_TX_ACK flag if no child operations are to be submitted -2/ setting the ASYNC_TX_DEP_ACK flag to acknowledge the parent - descriptor of a new operation. +2/ submitting an unacknowledged descriptor as a dependency to another + async_tx call will implicitly set the acknowledged state. 3/ calling async_tx_ack() on the descriptor. 3.4 When does the operation execute? @@ -136,10 +136,9 @@ int run_xor_copy_xor(struct page **xor_srcs, tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len, ASYNC_TX_XOR_DROP_DST, NULL, NULL, NULL); - tx = async_memcpy(copy_dest, copy_src, 0, 0, copy_len, - ASYNC_TX_DEP_ACK, tx, NULL, NULL); + tx = async_memcpy(copy_dest, copy_src, 0, 0, copy_len, tx, NULL, NULL); tx = async_xor(xor_dest, xor_srcs, 0, xor_src_cnt, xor_len, - ASYNC_TX_XOR_DROP_DST | ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, + ASYNC_TX_XOR_DROP_DST | ASYNC_TX_ACK, tx, complete_xor_copy_xor, NULL); async_tx_issue_pending_all(); diff --git a/crypto/async_tx/async_memcpy.c b/crypto/async_tx/async_memcpy.c index ddccfb01c416..7117ec6f1b74 100644 --- a/crypto/async_tx/async_memcpy.c +++ b/crypto/async_tx/async_memcpy.c @@ -35,7 +35,7 @@ * @src: src page * @offset: offset in pages to start transaction * @len: length in bytes - * @flags: ASYNC_TX_ACK, ASYNC_TX_DEP_ACK, + * @flags: ASYNC_TX_ACK * @depend_tx: memcpy depends on the result of this transaction * @cb_fn: function to call when the memcpy completes * @cb_param: parameter to pass to the callback routine diff --git a/crypto/async_tx/async_memset.c b/crypto/async_tx/async_memset.c index 5b5eb99bb244..b2f133885b7f 100644 --- a/crypto/async_tx/async_memset.c +++ b/crypto/async_tx/async_memset.c @@ -35,7 +35,7 @@ * @val: fill value * @offset: offset in pages to start transaction * @len: length in bytes - * @flags: ASYNC_TX_ACK, ASYNC_TX_DEP_ACK + * @flags: ASYNC_TX_ACK * @depend_tx: memset depends on the result of this transaction * @cb_fn: function to call when the memcpy completes * @cb_param: parameter to pass to the callback routine diff --git a/crypto/async_tx/async_tx.c b/crypto/async_tx/async_tx.c index 06eb6cc09fef..3766bc3d7d89 100644 --- a/crypto/async_tx/async_tx.c +++ b/crypto/async_tx/async_tx.c @@ -223,7 +223,7 @@ async_tx_submit(struct dma_chan *chan, struct dma_async_tx_descriptor *tx, if (flags & ASYNC_TX_ACK) async_tx_ack(tx); - if (depend_tx && (flags & ASYNC_TX_DEP_ACK)) + if (depend_tx) async_tx_ack(depend_tx); } EXPORT_SYMBOL_GPL(async_tx_submit); @@ -231,7 +231,7 @@ EXPORT_SYMBOL_GPL(async_tx_submit); /** * async_trigger_callback - schedules the callback function to be run after * any dependent operations have been completed. - * @flags: ASYNC_TX_ACK, ASYNC_TX_DEP_ACK + * @flags: ASYNC_TX_ACK * @depend_tx: 'callback' requires the completion of this transaction * @cb_fn: function to call after depend_tx completes * @cb_param: parameter to pass to the callback routine diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c index e0580b0ea533..3cc5dc763b54 100644 --- a/crypto/async_tx/async_xor.c +++ b/crypto/async_tx/async_xor.c @@ -105,7 +105,6 @@ do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list, _cb_param); depend_tx = tx; - flags |= ASYNC_TX_DEP_ACK; if (src_cnt > xor_src_cnt) { /* drop completed sources */ @@ -168,8 +167,7 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset, * @offset: offset in pages to start transaction * @src_cnt: number of source pages * @len: length in bytes - * @flags: ASYNC_TX_XOR_ZERO_DST, ASYNC_TX_XOR_DROP_DEST, - * ASYNC_TX_ACK, ASYNC_TX_DEP_ACK + * @flags: ASYNC_TX_XOR_ZERO_DST, ASYNC_TX_XOR_DROP_DEST, ASYNC_TX_ACK * @depend_tx: xor depends on the result of this transaction. * @cb_fn: function to call when the xor completes * @cb_param: parameter to pass to the callback routine @@ -230,7 +228,7 @@ static int page_is_zero(struct page *p, unsigned int offset, size_t len) * @src_cnt: number of source pages * @len: length in bytes * @result: 0 if sum == 0 else non-zero - * @flags: ASYNC_TX_ACK, ASYNC_TX_DEP_ACK + * @flags: ASYNC_TX_ACK * @depend_tx: xor depends on the result of this transaction. * @cb_fn: function to call when the xor completes * @cb_param: parameter to pass to the callback routine diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index f8d2d35ed298..0ef5362c8d02 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -525,14 +525,12 @@ async_copy_data(int frombio, struct bio *bio, struct page *page, bio_page = bio_iovec_idx(bio, i)->bv_page; if (frombio) tx = async_memcpy(page, bio_page, page_offset, - b_offset, clen, - ASYNC_TX_DEP_ACK, - tx, NULL, NULL); + b_offset, clen, 0, + tx, NULL, NULL); else tx = async_memcpy(bio_page, page, b_offset, - page_offset, clen, - ASYNC_TX_DEP_ACK, - tx, NULL, NULL); + page_offset, clen, 0, + tx, NULL, NULL); } if (clen < len) /* hit end of page */ break; @@ -615,8 +613,7 @@ static void ops_run_biofill(struct stripe_head *sh) } atomic_inc(&sh->count); - async_trigger_callback(ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, tx, - ops_complete_biofill, sh); + async_trigger_callback(ASYNC_TX_ACK, tx, ops_complete_biofill, sh); } static void ops_complete_compute5(void *stripe_head_ref) @@ -701,8 +698,8 @@ ops_run_prexor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx) } tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, - ASYNC_TX_DEP_ACK | ASYNC_TX_XOR_DROP_DST, tx, - ops_complete_prexor, sh); + ASYNC_TX_XOR_DROP_DST, tx, + ops_complete_prexor, sh); return tx; } @@ -809,7 +806,7 @@ ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx) * set ASYNC_TX_XOR_DROP_DST and ASYNC_TX_XOR_ZERO_DST * for the synchronous xor case */ - flags = ASYNC_TX_DEP_ACK | ASYNC_TX_ACK | + flags = ASYNC_TX_ACK | (prexor ? ASYNC_TX_XOR_DROP_DST : ASYNC_TX_XOR_ZERO_DST); atomic_inc(&sh->count); @@ -858,7 +855,7 @@ static void ops_run_check(struct stripe_head *sh) &sh->ops.zero_sum_result, 0, NULL, NULL, NULL); atomic_inc(&sh->count); - tx = async_trigger_callback(ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, tx, + tx = async_trigger_callback(ASYNC_TX_ACK, tx, ops_complete_check, sh); } @@ -2687,8 +2684,8 @@ static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh, /* place all the copies on one channel */ tx = async_memcpy(sh2->dev[dd_idx].page, - sh->dev[i].page, 0, 0, STRIPE_SIZE, - ASYNC_TX_DEP_ACK, tx, NULL, NULL); + sh->dev[i].page, 0, 0, STRIPE_SIZE, + 0, tx, NULL, NULL); set_bit(R5_Expanded, &sh2->dev[dd_idx].flags); set_bit(R5_UPTODATE, &sh2->dev[dd_idx].flags); 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 --- Documentation/crypto/async-tx-api.txt | 6 +- crypto/async_tx/async_memcpy.c | 26 +++---- crypto/async_tx/async_memset.c | 25 +++---- crypto/async_tx/async_tx.c | 51 +++++++------- crypto/async_tx/async_xor.c | 123 +++++++++++++++++----------------- drivers/md/raid5.c | 59 +++++++++------- include/linux/async_tx.h | 84 ++++++++++++++--------- 7 files changed, 200 insertions(+), 174 deletions(-) (limited to 'include/linux') diff --git a/Documentation/crypto/async-tx-api.txt b/Documentation/crypto/async-tx-api.txt index 76feda8541dc..dfe0475f7919 100644 --- a/Documentation/crypto/async-tx-api.txt +++ b/Documentation/crypto/async-tx-api.txt @@ -54,11 +54,7 @@ features surfaced as a result: 3.1 General format of the API: struct dma_async_tx_descriptor * -async_(, - enum async_tx_flags flags, - struct dma_async_tx_descriptor *dependency, - dma_async_tx_callback callback_routine, - void *callback_parameter); +async_(, struct async_submit ctl *submit) 3.2 Supported operations: memcpy - memory copy between a source and a destination buffer diff --git a/crypto/async_tx/async_memcpy.c b/crypto/async_tx/async_memcpy.c index 7117ec6f1b74..89e05556f3df 100644 --- a/crypto/async_tx/async_memcpy.c +++ b/crypto/async_tx/async_memcpy.c @@ -33,28 +33,28 @@ * async_memcpy - attempt to copy memory with a dma engine. * @dest: destination page * @src: src page - * @offset: offset in pages to start transaction + * @dest_offset: offset into 'dest' to start transaction + * @src_offset: offset into 'src' to start transaction * @len: length in bytes - * @flags: ASYNC_TX_ACK - * @depend_tx: memcpy depends on the result of this transaction - * @cb_fn: function to call when the memcpy completes - * @cb_param: parameter to pass to the callback routine + * @submit: submission / completion modifiers + * + * honored flags: ASYNC_TX_ACK */ 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_param) + unsigned int src_offset, size_t len, + struct async_submit_ctl *submit) { - struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_MEMCPY, + struct dma_chan *chan = async_tx_find_channel(submit, DMA_MEMCPY, &dest, 1, &src, 1, len); struct dma_device *device = chan ? chan->device : NULL; struct dma_async_tx_descriptor *tx = NULL; if (device) { dma_addr_t dma_dest, dma_src; - unsigned long dma_prep_flags = cb_fn ? DMA_PREP_INTERRUPT : 0; + unsigned long dma_prep_flags; + dma_prep_flags = submit->cb_fn ? DMA_PREP_INTERRUPT : 0; dma_dest = dma_map_page(device->dev, dest, dest_offset, len, DMA_FROM_DEVICE); @@ -67,13 +67,13 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset, if (tx) { pr_debug("%s: (async) len: %zu\n", __func__, len); - async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param); + async_tx_submit(chan, tx, submit); } else { void *dest_buf, *src_buf; pr_debug("%s: (sync) len: %zu\n", __func__, len); /* wait for any prerequisite operations */ - async_tx_quiesce(&depend_tx); + async_tx_quiesce(&submit->depend_tx); dest_buf = kmap_atomic(dest, KM_USER0) + dest_offset; src_buf = kmap_atomic(src, KM_USER1) + src_offset; @@ -83,7 +83,7 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset, kunmap_atomic(dest_buf, KM_USER0); kunmap_atomic(src_buf, KM_USER1); - async_tx_sync_epilog(cb_fn, cb_param); + async_tx_sync_epilog(submit); } return tx; diff --git a/crypto/async_tx/async_memset.c b/crypto/async_tx/async_memset.c index b2f133885b7f..c14437238f4c 100644 --- a/crypto/async_tx/async_memset.c +++ b/crypto/async_tx/async_memset.c @@ -35,26 +35,23 @@ * @val: fill value * @offset: offset in pages to start transaction * @len: length in bytes - * @flags: ASYNC_TX_ACK - * @depend_tx: memset depends on the result of this transaction - * @cb_fn: function to call when the memcpy completes - * @cb_param: parameter to pass to the callback routine + * + * honored flags: ASYNC_TX_ACK */ 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_param) +async_memset(struct page *dest, int val, unsigned int offset, size_t len, + struct async_submit_ctl *submit) { - struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_MEMSET, + struct dma_chan *chan = async_tx_find_channel(submit, DMA_MEMSET, &dest, 1, NULL, 0, len); struct dma_device *device = chan ? chan->device : NULL; struct dma_async_tx_descriptor *tx = NULL; if (device) { dma_addr_t dma_dest; - unsigned long dma_prep_flags = cb_fn ? DMA_PREP_INTERRUPT : 0; + unsigned long dma_prep_flags; + dma_prep_flags = submit->cb_fn ? DMA_PREP_INTERRUPT : 0; dma_dest = dma_map_page(device->dev, dest, offset, len, DMA_FROM_DEVICE); @@ -64,19 +61,19 @@ async_memset(struct page *dest, int val, unsigned int offset, if (tx) { pr_debug("%s: (async) len: %zu\n", __func__, len); - async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param); + async_tx_submit(chan, tx, submit); } else { /* run the memset synchronously */ void *dest_buf; pr_debug("%s: (sync) len: %zu\n", __func__, len); - dest_buf = (void *) (((char *) page_address(dest)) + offset); + dest_buf = page_address(dest) + offset; /* wait for any prerequisite operations */ - async_tx_quiesce(&depend_tx); + async_tx_quiesce(&submit->depend_tx); memset(dest_buf, val, len); - async_tx_sync_epilog(cb_fn, cb_param); + async_tx_sync_epilog(submit); } return tx; diff --git a/crypto/async_tx/async_tx.c b/crypto/async_tx/async_tx.c index 3766bc3d7d89..802a5ce437d9 100644 --- a/crypto/async_tx/async_tx.c +++ b/crypto/async_tx/async_tx.c @@ -45,13 +45,15 @@ static void __exit async_tx_exit(void) /** * __async_tx_find_channel - find a channel to carry out the operation or let * the transaction execute synchronously - * @depend_tx: transaction dependency + * @submit: transaction dependency and submission modifiers * @tx_type: transaction 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) { + struct dma_async_tx_descriptor *depend_tx = submit->depend_tx; + /* see if we can keep the chain on one channel */ if (depend_tx && dma_has_cap(tx_type, depend_tx->chan->device->cap_mask)) @@ -144,13 +146,14 @@ async_tx_channel_switch(struct dma_async_tx_descriptor *depend_tx, /** - * submit_disposition - while holding depend_tx->lock we must avoid submitting - * new operations to prevent a circular locking dependency with - * drivers that already hold a channel lock when calling - * async_tx_run_dependencies. + * submit_disposition - flags for routing an incoming operation * @ASYNC_TX_SUBMITTED: we were able to append the new operation under the lock * @ASYNC_TX_CHANNEL_SWITCH: when the lock is dropped schedule a channel switch * @ASYNC_TX_DIRECT_SUBMIT: when the lock is dropped submit directly + * + * while holding depend_tx->lock we must avoid submitting new operations + * to prevent a circular locking dependency with drivers that already + * hold a channel lock when calling async_tx_run_dependencies. */ enum submit_disposition { ASYNC_TX_SUBMITTED, @@ -160,11 +163,12 @@ enum submit_disposition { 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_param) + struct async_submit_ctl *submit) { - tx->callback = cb_fn; - tx->callback_param = cb_param; + struct dma_async_tx_descriptor *depend_tx = submit->depend_tx; + + tx->callback = submit->cb_fn; + tx->callback_param = submit->cb_param; if (depend_tx) { enum submit_disposition s; @@ -220,7 +224,7 @@ async_tx_submit(struct dma_chan *chan, struct dma_async_tx_descriptor *tx, tx->tx_submit(tx); } - if (flags & ASYNC_TX_ACK) + if (submit->flags & ASYNC_TX_ACK) async_tx_ack(tx); if (depend_tx) @@ -229,21 +233,20 @@ async_tx_submit(struct dma_chan *chan, struct dma_async_tx_descriptor *tx, EXPORT_SYMBOL_GPL(async_tx_submit); /** - * async_trigger_callback - schedules the callback function to be run after - * any dependent operations have been completed. - * @flags: ASYNC_TX_ACK - * @depend_tx: 'callback' requires the completion of this transaction - * @cb_fn: function to call after depend_tx completes - * @cb_param: parameter to pass to the callback routine + * async_trigger_callback - schedules the callback function to be run + * @submit: submission and completion parameters + * + * honored flags: ASYNC_TX_ACK + * + * The callback is run after any dependent operations have completed. */ 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_param) +async_trigger_callback(struct async_submit_ctl *submit) { struct dma_chan *chan; struct dma_device *device; struct dma_async_tx_descriptor *tx; + struct dma_async_tx_descriptor *depend_tx = submit->depend_tx; if (depend_tx) { chan = depend_tx->chan; @@ -262,14 +265,14 @@ async_trigger_callback(enum async_tx_flags flags, if (tx) { pr_debug("%s: (async)\n", __func__); - async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param); + async_tx_submit(chan, tx, submit); } else { pr_debug("%s: (sync)\n", __func__); /* wait for any prerequisite operations */ - async_tx_quiesce(&depend_tx); + async_tx_quiesce(&submit->depend_tx); - async_tx_sync_epilog(cb_fn, cb_param); + async_tx_sync_epilog(submit); } return tx; diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c index 3cc5dc763b54..691fa98a18c4 100644 --- a/crypto/async_tx/async_xor.c +++ b/crypto/async_tx/async_xor.c @@ -34,18 +34,16 @@ static __async_inline struct dma_async_tx_descriptor * do_async_xor(struct dma_chan *chan, 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_param) + struct async_submit_ctl *submit) { struct dma_device *dma = chan->device; dma_addr_t *dma_src = (dma_addr_t *) src_list; struct dma_async_tx_descriptor *tx = NULL; int src_off = 0; int i; - dma_async_tx_callback _cb_fn; - void *_cb_param; - enum async_tx_flags async_flags; + dma_async_tx_callback cb_fn_orig = submit->cb_fn; + void *cb_param_orig = submit->cb_param; + enum async_tx_flags flags_orig = submit->flags; enum dma_ctrl_flags dma_flags; int xor_src_cnt; dma_addr_t dma_dest; @@ -63,7 +61,7 @@ do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list, } while (src_cnt) { - async_flags = flags; + submit->flags = flags_orig; dma_flags = 0; xor_src_cnt = min(src_cnt, dma->max_xor); /* if we are submitting additional xors, leave the chain open, @@ -71,15 +69,15 @@ do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list, * buffer mapped */ if (src_cnt > xor_src_cnt) { - async_flags &= ~ASYNC_TX_ACK; + submit->flags &= ~ASYNC_TX_ACK; dma_flags = DMA_COMPL_SKIP_DEST_UNMAP; - _cb_fn = NULL; - _cb_param = NULL; + submit->cb_fn = NULL; + submit->cb_param = NULL; } else { - _cb_fn = cb_fn; - _cb_param = cb_param; + submit->cb_fn = cb_fn_orig; + submit->cb_param = cb_param_orig; } - if (_cb_fn) + if (submit->cb_fn) dma_flags |= DMA_PREP_INTERRUPT; /* Since we have clobbered the src_list we are committed @@ -90,7 +88,7 @@ do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list, xor_src_cnt, len, dma_flags); if (unlikely(!tx)) - async_tx_quiesce(&depend_tx); + async_tx_quiesce(&submit->depend_tx); /* spin wait for the preceeding transactions to complete */ while (unlikely(!tx)) { @@ -101,10 +99,8 @@ do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list, dma_flags); } - async_tx_submit(chan, tx, async_flags, depend_tx, _cb_fn, - _cb_param); - - depend_tx = tx; + async_tx_submit(chan, tx, submit); + submit->depend_tx = tx; if (src_cnt > xor_src_cnt) { /* drop completed sources */ @@ -123,8 +119,7 @@ do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list, static void do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset, - int src_cnt, size_t len, enum async_tx_flags flags, - dma_async_tx_callback cb_fn, void *cb_param) + int src_cnt, size_t len, struct async_submit_ctl *submit) { int i; int xor_src_cnt; @@ -139,7 +134,7 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset, /* set destination address */ dest_buf = page_address(dest) + offset; - if (flags & ASYNC_TX_XOR_ZERO_DST) + if (submit->flags & ASYNC_TX_XOR_ZERO_DST) memset(dest_buf, 0, len); while (src_cnt > 0) { @@ -152,33 +147,35 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset, src_off += xor_src_cnt; } - async_tx_sync_epilog(cb_fn, cb_param); + async_tx_sync_epilog(submit); } /** * async_xor - attempt to xor a set of blocks with a dma engine. - * xor_blocks always uses the dest as a source so the ASYNC_TX_XOR_ZERO_DST - * flag must be set to not include dest data in the calculation. The - * assumption with dma eninges is that they only use the destination - * buffer as a source when it is explicity specified in the source list. * @dest: destination page - * @src_list: array of source pages (if the dest is also a source it must be - * at index zero). The contents of this array may be overwritten. - * @offset: offset in pages to start transaction + * @src_list: array of source pages + * @offset: common src/dst offset to start transaction * @src_cnt: number of source pages * @len: length in bytes - * @flags: ASYNC_TX_XOR_ZERO_DST, ASYNC_TX_XOR_DROP_DEST, ASYNC_TX_ACK - * @depend_tx: xor depends on the result of this transaction. - * @cb_fn: function to call when the xor completes - * @cb_param: parameter to pass to the callback routine + * @submit: submission / completion modifiers + * + * honored flags: ASYNC_TX_ACK, ASYNC_TX_XOR_ZERO_DST, ASYNC_TX_XOR_DROP_DST + * + * xor_blocks always uses the dest as a source so the + * ASYNC_TX_XOR_ZERO_DST flag must be set to not include dest data in + * the calculation. The assumption with dma eninges is that they only + * use the destination buffer as a source when it is explicity specified + * in the source list. + * + * src_list note: if the dest is also a source it must be at index zero. + * The contents of this array will be overwritten if a scribble region + * is not specified. */ 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_param) + int src_cnt, size_t len, struct async_submit_ctl *submit) { - struct dma_chan *chan = async_tx_find_channel(depend_tx, DMA_XOR, + struct dma_chan *chan = async_tx_find_channel(submit, DMA_XOR, &dest, 1, src_list, src_cnt, len); BUG_ON(src_cnt <= 1); @@ -188,7 +185,7 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset, pr_debug("%s (async): len: %zu\n", __func__, len); return do_async_xor(chan, dest, src_list, offset, src_cnt, len, - flags, depend_tx, cb_fn, cb_param); + submit); } else { /* run the xor synchronously */ pr_debug("%s (sync): len: %zu\n", __func__, len); @@ -196,16 +193,15 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset, /* in the sync case the dest is an implied source * (assumes the dest is the first source) */ - if (flags & ASYNC_TX_XOR_DROP_DST) { + if (submit->flags & ASYNC_TX_XOR_DROP_DST) { src_cnt--; src_list++; } /* wait for any prerequisite operations */ - async_tx_quiesce(&depend_tx); + async_tx_quiesce(&submit->depend_tx); - do_sync_xor(dest, src_list, offset, src_cnt, len, - flags, cb_fn, cb_param); + do_sync_xor(dest, src_list, offset, src_cnt, len, submit); return NULL; } @@ -222,25 +218,25 @@ static int page_is_zero(struct page *p, unsigned int offset, size_t len) /** * async_xor_val - attempt a xor parity check with a dma engine. * @dest: destination page used if the xor is performed synchronously - * @src_list: array of source pages. The dest page must be listed as a source - * at index zero. The contents of this array may be overwritten. + * @src_list: array of source pages * @offset: offset in pages to start transaction * @src_cnt: number of source pages * @len: length in bytes * @result: 0 if sum == 0 else non-zero - * @flags: ASYNC_TX_ACK - * @depend_tx: xor depends on the result of this transaction. - * @cb_fn: function to call when the xor completes - * @cb_param: parameter to pass to the callback routine + * @submit: submission / completion modifiers + * + * honored flags: ASYNC_TX_ACK + * + * src_list note: if the dest is also a source it must be at index zero. + * The contents of this array will be overwritten if a scribble region + * is not specified. */ 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_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_chan *chan = async_tx_find_channel(depend_tx, DMA_XOR_VAL, + struct dma_chan *chan = async_tx_find_channel(submit, DMA_XOR_VAL, &dest, 1, src_list, src_cnt, len); struct dma_device *device = chan ? chan->device : NULL; @@ -250,11 +246,12 @@ async_xor_val(struct page *dest, struct page **src_list, if (device && src_cnt <= device->max_xor) { dma_addr_t *dma_src = (dma_addr_t *) src_list; - unsigned long dma_prep_flags = cb_fn ? DMA_PREP_INTERRUPT : 0; + unsigned long dma_prep_flags; int i; pr_debug("%s: (async) len: %zu\n", __func__, len); + dma_prep_flags = submit->cb_fn ? DMA_PREP_INTERRUPT : 0; for (i = 0; i < src_cnt; i++) dma_src[i] = dma_map_page(device->dev, src_list[i], offset, len, DMA_TO_DEVICE); @@ -263,7 +260,7 @@ async_xor_val(struct page *dest, struct page **src_list, len, result, dma_prep_flags); if (unlikely(!tx)) { - async_tx_quiesce(&depend_tx); + async_tx_quiesce(&submit->depend_tx); while (!tx) { dma_async_issue_pending(chan); @@ -273,23 +270,23 @@ async_xor_val(struct page *dest, struct page **src_list, } } - async_tx_submit(chan, tx, flags, depend_tx, cb_fn, cb_param); + async_tx_submit(chan, tx, submit); } else { - unsigned long xor_flags = flags; + enum async_tx_flags flags_orig = submit->flags; pr_debug("%s: (sync) len: %zu\n", __func__, len); - xor_flags |= ASYNC_TX_XOR_DROP_DST; - xor_flags &= ~ASYNC_TX_ACK; + submit->flags |= ASYNC_TX_XOR_DROP_DST; + submit->flags &= ~ASYNC_TX_ACK; - tx = async_xor(dest, src_list, offset, src_cnt, len, xor_flags, - depend_tx, NULL, NULL); + tx = async_xor(dest, src_list, offset, src_cnt, len, submit); async_tx_quiesce(&tx); *result = page_is_zero(dest, offset, len) ? 0 : 1; - async_tx_sync_epilog(cb_fn, cb_param); + async_tx_sync_epilog(submit); + submit->flags = flags_orig; } return tx; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 0ef5362c8d02..e1920f23579f 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -499,11 +499,14 @@ async_copy_data(int frombio, struct bio *bio, struct page *page, struct page *bio_page; int i; int page_offset; + struct async_submit_ctl submit; if (bio->bi_sector >= sector) page_offset = (signed)(bio->bi_sector - sector) * 512; else page_offset = (signed)(sector - bio->bi_sector) * -512; + + init_async_submit(&submit, 0, tx, NULL, NULL, NULL); bio_for_each_segment(bvl, bio, i) { int len = bio_iovec_idx(bio, i)->bv_len; int clen; @@ -525,13 +528,14 @@ async_copy_data(int frombio, struct bio *bio, struct page *page, bio_page = bio_iovec_idx(bio, i)->bv_page; if (frombio) tx = async_memcpy(page, bio_page, page_offset, - b_offset, clen, 0, - tx, NULL, NULL); + b_offset, clen, &submit); else tx = async_memcpy(bio_page, page, b_offset, - page_offset, clen, 0, - tx, NULL, NULL); + page_offset, clen, &submit); } + /* chain the operations */ + submit.depend_tx = tx; + if (clen < len) /* hit end of page */ break; page_offset += len; @@ -590,6 +594,7 @@ static void ops_run_biofill(struct stripe_head *sh) { struct dma_async_tx_descriptor *tx = NULL; raid5_conf_t *conf = sh->raid_conf; + struct async_submit_ctl submit; int i; pr_debug("%s: stripe %llu\n", __func__, @@ -613,7 +618,8 @@ static void ops_run_biofill(struct stripe_head *sh) } atomic_inc(&sh->count); - async_trigger_callback(ASYNC_TX_ACK, tx, ops_complete_biofill, sh); + init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_biofill, sh, NULL); + async_trigger_callback(&submit); } static void ops_complete_compute5(void *stripe_head_ref) @@ -645,6 +651,7 @@ static struct dma_async_tx_descriptor *ops_run_compute5(struct stripe_head *sh) struct page *xor_dest = tgt->page; int count = 0; struct dma_async_tx_descriptor *tx; + struct async_submit_ctl submit; int i; pr_debug("%s: stripe %llu block: %d\n", @@ -657,13 +664,12 @@ static struct dma_async_tx_descriptor *ops_run_compute5(struct stripe_head *sh) atomic_inc(&sh->count); + init_async_submit(&submit, ASYNC_TX_XOR_ZERO_DST, NULL, + ops_complete_compute5, sh, NULL); if (unlikely(count == 1)) - tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, - 0, NULL, ops_complete_compute5, sh); + tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit); else - tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, - ASYNC_TX_XOR_ZERO_DST, NULL, - ops_complete_compute5, sh); + tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit); return tx; } @@ -683,6 +689,7 @@ ops_run_prexor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx) int disks = sh->disks; struct page *xor_srcs[disks]; int count = 0, pd_idx = sh->pd_idx, i; + struct async_submit_ctl submit; /* existing parity data subtracted */ struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page; @@ -697,9 +704,9 @@ ops_run_prexor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx) xor_srcs[count++] = dev->page; } - tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, - ASYNC_TX_XOR_DROP_DST, tx, - ops_complete_prexor, sh); + init_async_submit(&submit, ASYNC_TX_XOR_DROP_DST, tx, + ops_complete_prexor, sh, NULL); + tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit); return tx; } @@ -772,7 +779,7 @@ ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx) /* kernel stack size limits the total number of disks */ int disks = sh->disks; struct page *xor_srcs[disks]; - + struct async_submit_ctl submit; int count = 0, pd_idx = sh->pd_idx, i; struct page *xor_dest; int prexor = 0; @@ -811,13 +818,11 @@ ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx) atomic_inc(&sh->count); - if (unlikely(count == 1)) { - flags &= ~(ASYNC_TX_XOR_DROP_DST | ASYNC_TX_XOR_ZERO_DST); - tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, - flags, tx, ops_complete_postxor, sh); - } else - tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, - flags, tx, ops_complete_postxor, sh); + init_async_submit(&submit, flags, tx, ops_complete_postxor, sh, NULL); + if (unlikely(count == 1)) + tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit); + else + tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit); } static void ops_complete_check(void *stripe_head_ref) @@ -838,6 +843,7 @@ static void ops_run_check(struct stripe_head *sh) int disks = sh->disks; struct page *xor_srcs[disks]; struct dma_async_tx_descriptor *tx; + struct async_submit_ctl submit; int count = 0, pd_idx = sh->pd_idx, i; struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page; @@ -851,12 +857,13 @@ static void ops_run_check(struct stripe_head *sh) xor_srcs[count++] = dev->page; } + init_async_submit(&submit, 0, NULL, NULL, NULL, NULL); tx = async_xor_val(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, - &sh->ops.zero_sum_result, 0, NULL, NULL, NULL); + &sh->ops.zero_sum_result, &submit); atomic_inc(&sh->count); - tx = async_trigger_callback(ASYNC_TX_ACK, tx, - ops_complete_check, sh); + init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_check, sh, NULL); + tx = async_trigger_callback(&submit); } static void raid5_run_ops(struct stripe_head *sh, unsigned long ops_request) @@ -2664,6 +2671,7 @@ static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh, if (i != sh->pd_idx && i != sh->qd_idx) { int dd_idx, j; struct stripe_head *sh2; + struct async_submit_ctl submit; sector_t bn = compute_blocknr(sh, i, 1); sector_t s = raid5_compute_sector(conf, bn, 0, @@ -2683,9 +2691,10 @@ static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh, } /* place all the copies on one channel */ + init_async_submit(&submit, 0, tx, NULL, NULL, NULL); tx = async_memcpy(sh2->dev[dd_idx].page, sh->dev[i].page, 0, 0, STRIPE_SIZE, - 0, tx, NULL, NULL); + &submit); set_bit(R5_Expanded, &sh2->dev[dd_idx].flags); set_bit(R5_UPTODATE, &sh2->dev[dd_idx].flags); 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 --- arch/arm/include/asm/hardware/iop3xx-adma.h | 5 +++-- arch/arm/mach-iop13xx/include/mach/adma.h | 12 +++++++----- crypto/async_tx/async_xor.c | 4 ++-- drivers/md/raid5.c | 2 +- drivers/md/raid5.h | 5 +++-- include/linux/async_tx.h | 2 +- include/linux/dmaengine.h | 21 ++++++++++++++++++++- 7 files changed, 37 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/include/asm/hardware/iop3xx-adma.h b/arch/arm/include/asm/hardware/iop3xx-adma.h index 83e6ba338e2c..26eefea02314 100644 --- a/arch/arm/include/asm/hardware/iop3xx-adma.h +++ b/arch/arm/include/asm/hardware/iop3xx-adma.h @@ -756,13 +756,14 @@ static inline void iop_desc_set_block_fill_val(struct iop_adma_desc_slot *desc, hw_desc->src[0] = val; } -static inline int iop_desc_get_zero_result(struct iop_adma_desc_slot *desc) +static inline enum sum_check_flags +iop_desc_get_zero_result(struct iop_adma_desc_slot *desc) { struct iop3xx_desc_aau *hw_desc = desc->hw_desc; struct iop3xx_aau_desc_ctrl desc_ctrl = hw_desc->desc_ctrl_field; iop_paranoia(!(desc_ctrl.tx_complete && desc_ctrl.zero_result_en)); - return desc_ctrl.zero_result_err; + return desc_ctrl.zero_result_err << SUM_CHECK_P; } static inline void iop_chan_append(struct iop_adma_chan *chan) diff --git a/arch/arm/mach-iop13xx/include/mach/adma.h b/arch/arm/mach-iop13xx/include/mach/adma.h index 5722e86f2174..1cd31df8924d 100644 --- a/arch/arm/mach-iop13xx/include/mach/adma.h +++ b/arch/arm/mach-iop13xx/include/mach/adma.h @@ -428,18 +428,20 @@ static inline void iop_desc_set_block_fill_val(struct iop_adma_desc_slot *desc, hw_desc->block_fill_data = val; } -static inline int iop_desc_get_zero_result(struct iop_adma_desc_slot *desc) +static inline enum sum_check_flags +iop_desc_get_zero_result(struct iop_adma_desc_slot *desc) { struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc; struct iop13xx_adma_desc_ctrl desc_ctrl = hw_desc->desc_ctrl_field; struct iop13xx_adma_byte_count byte_count = hw_desc->byte_count_field; + enum sum_check_flags flags; BUG_ON(!(byte_count.tx_complete && desc_ctrl.zero_result)); - if (desc_ctrl.pq_xfer_en) - return byte_count.zero_result_err_q; - else - return byte_count.zero_result_err; + flags = byte_count.zero_result_err_q << SUM_CHECK_Q; + flags |= byte_count.zero_result_err << SUM_CHECK_P; + + return flags; } static inline void iop_chan_append(struct iop_adma_chan *chan) diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c index 1e96c4df7061..78fb7780272a 100644 --- a/crypto/async_tx/async_xor.c +++ b/crypto/async_tx/async_xor.c @@ -246,7 +246,7 @@ static int page_is_zero(struct page *p, unsigned int offset, size_t len) */ 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_chan *chan = async_tx_find_channel(submit, DMA_XOR_VAL, @@ -304,7 +304,7 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset, async_tx_quiesce(&tx); - *result = page_is_zero(dest, offset, len) ? 0 : 1; + *result = !page_is_zero(dest, offset, len) << SUM_CHECK_P; async_tx_sync_epilog(submit); submit->flags = flags_orig; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 7727954cf726..1f2a266f3cf7 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2590,7 +2590,7 @@ static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh, * we are done. Otherwise update the mismatch count and repair * parity if !MD_RECOVERY_CHECK */ - if (sh->ops.zero_sum_result == 0) + if ((sh->ops.zero_sum_result & SUM_CHECK_P_RESULT) == 0) /* parity is correct (on disc, * not in buffer any more) */ diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index e7baabffee86..75f2c6c4cf90 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -2,6 +2,7 @@ #define _RAID5_H #include +#include /* * @@ -215,8 +216,8 @@ struct stripe_head { * @target - STRIPE_OP_COMPUTE_BLK target */ struct stripe_operations { - int target; - u32 zero_sum_result; + int target; + enum sum_check_flags zero_sum_result; } ops; struct r5dev { struct bio req; 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 --- crypto/async_tx/async_tx.c | 13 +++++++------ drivers/dma/dmaengine.c | 45 ++++++++++----------------------------------- include/linux/async_tx.h | 23 +++++++++++++++++++++++ 3 files changed, 40 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/crypto/async_tx/async_tx.c b/crypto/async_tx/async_tx.c index 6e37ad3f4417..60615fedcf5e 100644 --- a/crypto/async_tx/async_tx.c +++ b/crypto/async_tx/async_tx.c @@ -77,8 +77,8 @@ static void async_tx_channel_switch(struct dma_async_tx_descriptor *depend_tx, struct dma_async_tx_descriptor *tx) { - struct dma_chan *chan; - struct dma_device *device; + struct dma_chan *chan = depend_tx->chan; + struct dma_device *device = chan->device; struct dma_async_tx_descriptor *intr_tx = (void *) ~0; /* first check to see if we can still append to depend_tx */ @@ -90,11 +90,11 @@ async_tx_channel_switch(struct dma_async_tx_descriptor *depend_tx, } spin_unlock_bh(&depend_tx->lock); - if (!intr_tx) + /* attached dependency, flush the parent channel */ + if (!intr_tx) { + device->device_issue_pending(chan); return; - - chan = depend_tx->chan; - device = chan->device; + } /* see if we can schedule an interrupt * otherwise poll for completion @@ -128,6 +128,7 @@ async_tx_channel_switch(struct dma_async_tx_descriptor *depend_tx, intr_tx->tx_submit(intr_tx); async_tx_ack(intr_tx); } + device->device_issue_pending(chan); } else { if (dma_wait_for_async_tx(depend_tx) == DMA_ERROR) panic("%s: DMA_ERROR waiting for depend_tx\n", diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 6781e8f3c064..e002e0e0d055 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -934,49 +934,24 @@ EXPORT_SYMBOL(dma_async_tx_descriptor_init); /* dma_wait_for_async_tx - spin wait for a transaction to complete * @tx: in-flight transaction to wait on - * - * This routine assumes that tx was obtained from a call to async_memcpy, - * async_xor, async_memset, etc which ensures that tx is "in-flight" (prepped - * and submitted). Walking the parent chain is only meant to cover for DMA - * drivers that do not implement the DMA_INTERRUPT capability and may race with - * the driver's descriptor cleanup routine. */ enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx) { - enum dma_status status; - struct dma_async_tx_descriptor *iter; - struct dma_async_tx_descriptor *parent; + unsigned long dma_sync_wait_timeout = jiffies + msecs_to_jiffies(5000); if (!tx) return DMA_SUCCESS; - WARN_ONCE(tx->parent, "%s: speculatively walking dependency chain for" - " %s\n", __func__, dma_chan_name(tx->chan)); - - /* poll through the dependency chain, return when tx is complete */ - do { - iter = tx; - - /* find the root of the unsubmitted dependency chain */ - do { - parent = iter->parent; - if (!parent) - break; - else - iter = parent; - } while (parent); - - /* there is a small window for ->parent == NULL and - * ->cookie == -EBUSY - */ - while (iter->cookie == -EBUSY) - cpu_relax(); - - status = dma_sync_wait(iter->chan, iter->cookie); - } while (status == DMA_IN_PROGRESS || (iter != tx)); - - return status; + while (tx->cookie == -EBUSY) { + if (time_after_eq(jiffies, dma_sync_wait_timeout)) { + pr_err("%s timeout waiting for descriptor submission\n", + __func__); + return DMA_ERROR; + } + cpu_relax(); + } + return dma_sync_wait(tx->chan, tx->cookie); } EXPORT_SYMBOL_GPL(dma_wait_for_async_tx); 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 --- Documentation/crypto/async-tx-api.txt | 3 + arch/arm/mach-iop13xx/setup.c | 2 +- crypto/async_tx/Kconfig | 4 + crypto/async_tx/Makefile | 1 + crypto/async_tx/async_pq.c | 388 ++++++++++++++++++++++++++++++++++ crypto/async_tx/async_xor.c | 2 +- drivers/dma/dmaengine.c | 4 + drivers/dma/iop-adma.c | 2 +- include/linux/async_tx.h | 9 + include/linux/dmaengine.h | 87 +++++++- 10 files changed, 493 insertions(+), 9 deletions(-) create mode 100644 crypto/async_tx/async_pq.c (limited to 'include/linux') diff --git a/Documentation/crypto/async-tx-api.txt b/Documentation/crypto/async-tx-api.txt index 6b15e488c0e7..0e48e054d69a 100644 --- a/Documentation/crypto/async-tx-api.txt +++ b/Documentation/crypto/async-tx-api.txt @@ -64,6 +64,9 @@ xor - xor a series of source buffers and write the result to a xor_val - xor a series of source buffers and set a flag if the result is zero. The implementation attempts to prevent writes to memory +pq - generate the p+q (raid6 syndrome) from a series of source buffers +pq_val - validate that a p and or q buffer are in sync with a given series of + sources 3.3 Descriptor management: The return value is non-NULL and points to a 'descriptor' when the operation diff --git a/arch/arm/mach-iop13xx/setup.c b/arch/arm/mach-iop13xx/setup.c index 9800228b71d3..2e7ca0d75f8a 100644 --- a/arch/arm/mach-iop13xx/setup.c +++ b/arch/arm/mach-iop13xx/setup.c @@ -506,7 +506,7 @@ void __init iop13xx_platform_init(void) dma_cap_set(DMA_MEMSET, plat_data->cap_mask); dma_cap_set(DMA_MEMCPY_CRC32C, plat_data->cap_mask); dma_cap_set(DMA_INTERRUPT, plat_data->cap_mask); - dma_cap_set(DMA_PQ_XOR, plat_data->cap_mask); + dma_cap_set(DMA_PQ, plat_data->cap_mask); dma_cap_set(DMA_PQ_UPDATE, plat_data->cap_mask); dma_cap_set(DMA_PQ_VAL, plat_data->cap_mask); break; diff --git a/crypto/async_tx/Kconfig b/crypto/async_tx/Kconfig index d8fb39145986..cb6d7314f198 100644 --- a/crypto/async_tx/Kconfig +++ b/crypto/async_tx/Kconfig @@ -14,3 +14,7 @@ config ASYNC_MEMSET tristate select ASYNC_CORE +config ASYNC_PQ + tristate + select ASYNC_CORE + diff --git a/crypto/async_tx/Makefile b/crypto/async_tx/Makefile index 27baa7d52fbc..1b9926588259 100644 --- a/crypto/async_tx/Makefile +++ b/crypto/async_tx/Makefile @@ -2,3 +2,4 @@ obj-$(CONFIG_ASYNC_CORE) += async_tx.o obj-$(CONFIG_ASYNC_MEMCPY) += async_memcpy.o obj-$(CONFIG_ASYNC_MEMSET) += async_memset.o obj-$(CONFIG_ASYNC_XOR) += async_xor.o +obj-$(CONFIG_ASYNC_PQ) += async_pq.o diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c new file mode 100644 index 000000000000..108b21efb499 --- /dev/null +++ b/crypto/async_tx/async_pq.c @@ -0,0 +1,388 @@ +/* + * Copyright(c) 2007 Yuri Tikhonov + * Copyright(c) 2009 Intel Corporation + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 + * Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * The full GNU General Public License is included in this distribution in the + * file called COPYING. + */ +#include +#include +#include +#include +#include + +/** + * scribble - space to hold throwaway P buffer for synchronous gen_syndrome + */ +static struct page *scribble; + +static bool is_raid6_zero_block(struct page *p) +{ + return p == (void *) raid6_empty_zero_page; +} + +/* the struct page *blocks[] parameter passed to async_gen_syndrome() + * and async_syndrome_val() contains the 'P' destination address at + * blocks[disks-2] and the 'Q' destination address at blocks[disks-1] + * + * note: these are macros as they are used as lvalues + */ +#define P(b, d) (b[d-2]) +#define Q(b, d) (b[d-1]) + +/** + * do_async_gen_syndrome - asynchronously calculate P and/or Q + */ +static __async_inline struct dma_async_tx_descriptor * +do_async_gen_syndrome(struct dma_chan *chan, struct page **blocks, + const unsigned char *scfs, unsigned int offset, int disks, + size_t len, dma_addr_t *dma_src, + struct async_submit_ctl *submit) +{ + struct dma_async_tx_descriptor *tx = NULL; + struct dma_device *dma = chan->device; + enum dma_ctrl_flags dma_flags = 0; + enum async_tx_flags flags_orig = submit->flags; + dma_async_tx_callback cb_fn_orig = submit->cb_fn; + dma_async_tx_callback cb_param_orig = submit->cb_param; + int src_cnt = disks - 2; + unsigned char coefs[src_cnt]; + unsigned short pq_src_cnt; + dma_addr_t dma_dest[2]; + int src_off = 0; + int idx; + int i; + + /* DMAs use destinations as sources, so use BIDIRECTIONAL mapping */ + if (P(blocks, disks)) + dma_dest[0] = dma_map_page(dma->dev, P(blocks, disks), offset, + len, DMA_BIDIRECTIONAL); + else + dma_flags |= DMA_PREP_PQ_DISABLE_P; + if (Q(blocks, disks)) + dma_dest[1] = dma_map_page(dma->dev, Q(blocks, disks), offset, + len, DMA_BIDIRECTIONAL); + else + dma_flags |= DMA_PREP_PQ_DISABLE_Q; + + /* convert source addresses being careful to collapse 'empty' + * sources and update the coefficients accordingly + */ + for (i = 0, idx = 0; i < src_cnt; i++) { + if (is_raid6_zero_block(blocks[i])) + continue; + dma_src[idx] = dma_map_page(dma->dev, blocks[i], offset, len, + DMA_TO_DEVICE); + coefs[idx] = scfs[i]; + idx++; + } + src_cnt = idx; + + while (src_cnt > 0) { + submit->flags = flags_orig; + pq_src_cnt = min(src_cnt, dma_maxpq(dma, dma_flags)); + /* if we are submitting additional pqs, leave the chain open, + * clear the callback parameters, and leave the destination + * buffers mapped + */ + if (src_cnt > pq_src_cnt) { + submit->flags &= ~ASYNC_TX_ACK; + dma_flags |= DMA_COMPL_SKIP_DEST_UNMAP; + submit->cb_fn = NULL; + submit->cb_param = NULL; + } else { + dma_flags &= ~DMA_COMPL_SKIP_DEST_UNMAP; + submit->cb_fn = cb_fn_orig; + submit->cb_param = cb_param_orig; + if (cb_fn_orig) + dma_flags |= DMA_PREP_INTERRUPT; + } + + /* Since we have clobbered the src_list we are committed + * to doing this asynchronously. Drivers force forward + * progress in case they can not provide a descriptor + */ + for (;;) { + tx = dma->device_prep_dma_pq(chan, dma_dest, + &dma_src[src_off], + pq_src_cnt, + &coefs[src_off], len, + dma_flags); + if (likely(tx)) + break; + async_tx_quiesce(&submit->depend_tx); + dma_async_issue_pending(chan); + } + + async_tx_submit(chan, tx, submit); + submit->depend_tx = tx; + + /* drop completed sources */ + src_cnt -= pq_src_cnt; + src_off += pq_src_cnt; + + dma_flags |= DMA_PREP_CONTINUE; + } + + return tx; +} + +/** + * do_sync_gen_syndrome - synchronously calculate a raid6 syndrome + */ +static void +do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks, + size_t len, struct async_submit_ctl *submit) +{ + void **srcs; + int i; + + if (submit->scribble) + srcs = submit->scribble; + else + srcs = (void **) blocks; + + for (i = 0; i < disks; i++) { + if (is_raid6_zero_block(blocks[i])) { + BUG_ON(i > disks - 3); /* P or Q can't be zero */ + srcs[i] = blocks[i]; + } else + srcs[i] = page_address(blocks[i]) + offset; + } + raid6_call.gen_syndrome(disks, len, srcs); + async_tx_sync_epilog(submit); +} + +/** + * async_gen_syndrome - asynchronously calculate a raid6 syndrome + * @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1 + * @offset: common offset into each block (src and dest) to start transaction + * @disks: number of blocks (including missing P or Q, see below) + * @len: length of operation in bytes + * @submit: submission/completion modifiers + * + * General note: This routine assumes a field of GF(2^8) with a + * primitive polynomial of 0x11d and a generator of {02}. + * + * 'disks' note: callers can optionally omit either P or Q (but not + * both) from the calculation by setting blocks[disks-2] or + * blocks[disks-1] to NULL. When P or Q is omitted 'len' must be <= + * PAGE_SIZE as a temporary buffer of this size is used in the + * synchronous path. 'disks' always accounts for both destination + * buffers. + * + * 'blocks' note: if submit->scribble is NULL then the contents of + * 'blocks' may be overridden + */ +struct dma_async_tx_descriptor * +async_gen_syndrome(struct page **blocks, unsigned int offset, int disks, + size_t len, struct async_submit_ctl *submit) +{ + int src_cnt = disks - 2; + struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ, + &P(blocks, disks), 2, + blocks, src_cnt, len); + struct dma_device *device = chan ? chan->device : NULL; + dma_addr_t *dma_src = NULL; + + BUG_ON(disks > 255 || !(P(blocks, disks) || Q(blocks, disks))); + + if (submit->scribble) + dma_src = submit->scribble; + else if (sizeof(dma_addr_t) <= sizeof(struct page *)) + dma_src = (dma_addr_t *) blocks; + + if (dma_src && device && + (src_cnt <= dma_maxpq(device, 0) || + dma_maxpq(device, DMA_PREP_CONTINUE) > 0)) { + /* run the p+q asynchronously */ + pr_debug("%s: (async) disks: %d len: %zu\n", + __func__, disks, len); + return do_async_gen_syndrome(chan, blocks, raid6_gfexp, offset, + disks, len, dma_src, submit); + } + + /* run the pq synchronously */ + pr_debug("%s: (sync) disks: %d len: %zu\n", __func__, disks, len); + + /* wait for any prerequisite operations */ + async_tx_quiesce(&submit->depend_tx); + + if (!P(blocks, disks)) { + P(blocks, disks) = scribble; + BUG_ON(len + offset > PAGE_SIZE); + } + if (!Q(blocks, disks)) { + Q(blocks, disks) = scribble; + BUG_ON(len + offset > PAGE_SIZE); + } + do_sync_gen_syndrome(blocks, offset, disks, len, submit); + + return NULL; +} +EXPORT_SYMBOL_GPL(async_gen_syndrome); + +/** + * async_syndrome_val - asynchronously validate a raid6 syndrome + * @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1 + * @offset: common offset into each block (src and dest) to start transaction + * @disks: number of blocks (including missing P or Q, see below) + * @len: length of operation in bytes + * @pqres: on val failure SUM_CHECK_P_RESULT and/or SUM_CHECK_Q_RESULT are set + * @spare: temporary result buffer for the synchronous case + * @submit: submission / completion modifiers + * + * The same notes from async_gen_syndrome apply to the 'blocks', + * and 'disks' parameters of this routine. The synchronous path + * requires a temporary result buffer and submit->scribble to be + * specified. + */ +struct dma_async_tx_descriptor * +async_syndrome_val(struct page **blocks, unsigned int offset, int disks, + size_t len, enum sum_check_flags *pqres, struct page *spare, + struct async_submit_ctl *submit) +{ + struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ_VAL, + NULL, 0, blocks, disks, + len); + struct dma_device *device = chan ? chan->device : NULL; + struct dma_async_tx_descriptor *tx; + enum dma_ctrl_flags dma_flags = submit->cb_fn ? DMA_PREP_INTERRUPT : 0; + dma_addr_t *dma_src = NULL; + + BUG_ON(disks < 4); + + if (submit->scribble) + dma_src = submit->scribble; + else if (sizeof(dma_addr_t) <= sizeof(struct page *)) + dma_src = (dma_addr_t *) blocks; + + if (dma_src && device && disks <= dma_maxpq(device, 0)) { + struct device *dev = device->dev; + dma_addr_t *pq = &dma_src[disks-2]; + int i; + + pr_debug("%s: (async) disks: %d len: %zu\n", + __func__, disks, len); + if (!P(blocks, disks)) + dma_flags |= DMA_PREP_PQ_DISABLE_P; + if (!Q(blocks, disks)) + dma_flags |= DMA_PREP_PQ_DISABLE_Q; + for (i = 0; i < disks; i++) + if (likely(blocks[i])) { + BUG_ON(is_raid6_zero_block(blocks[i])); + dma_src[i] = dma_map_page(dev, blocks[i], + offset, len, + DMA_TO_DEVICE); + } + + for (;;) { + tx = device->device_prep_dma_pq_val(chan, pq, dma_src, + disks - 2, + raid6_gfexp, + len, pqres, + dma_flags); + if (likely(tx)) + break; + async_tx_quiesce(&submit->depend_tx); + dma_async_issue_pending(chan); + } + async_tx_submit(chan, tx, submit); + + return tx; + } else { + struct page *p_src = P(blocks, disks); + struct page *q_src = Q(blocks, disks); + enum async_tx_flags flags_orig = submit->flags; + dma_async_tx_callback cb_fn_orig = submit->cb_fn; + void *scribble = submit->scribble; + void *cb_param_orig = submit->cb_param; + void *p, *q, *s; + + pr_debug("%s: (sync) disks: %d len: %zu\n", + __func__, disks, len); + + /* caller must provide a temporary result buffer and + * allow the input parameters to be preserved + */ + BUG_ON(!spare || !scribble); + + /* wait for any prerequisite operations */ + async_tx_quiesce(&submit->depend_tx); + + /* recompute p and/or q into the temporary buffer and then + * check to see the result matches the current value + */ + tx = NULL; + *pqres = 0; + if (p_src) { + init_async_submit(submit, ASYNC_TX_XOR_ZERO_DST, NULL, + NULL, NULL, scribble); + tx = async_xor(spare, blocks, offset, disks-2, len, submit); + async_tx_quiesce(&tx); + p = page_address(p_src) + offset; + s = page_address(spare) + offset; + *pqres |= !!memcmp(p, s, len) << SUM_CHECK_P; + } + + if (q_src) { + P(blocks, disks) = NULL; + Q(blocks, disks) = spare; + init_async_submit(submit, 0, NULL, NULL, NULL, scribble); + tx = async_gen_syndrome(blocks, offset, disks, len, submit); + async_tx_quiesce(&tx); + q = page_address(q_src) + offset; + s = page_address(spare) + offset; + *pqres |= !!memcmp(q, s, len) << SUM_CHECK_Q; + } + + /* restore P, Q and submit */ + P(blocks, disks) = p_src; + Q(blocks, disks) = q_src; + + submit->cb_fn = cb_fn_orig; + submit->cb_param = cb_param_orig; + submit->flags = flags_orig; + async_tx_sync_epilog(submit); + + return NULL; + } +} +EXPORT_SYMBOL_GPL(async_syndrome_val); + +static int __init async_pq_init(void) +{ + scribble = alloc_page(GFP_KERNEL); + + if (scribble) + return 0; + + pr_err("%s: failed to allocate required spare page\n", __func__); + + return -ENOMEM; +} + +static void __exit async_pq_exit(void) +{ + put_page(scribble); +} + +module_init(async_pq_init); +module_exit(async_pq_exit); + +MODULE_DESCRIPTION("asynchronous raid6 syndrome generation/validation"); +MODULE_LICENSE("GPL"); diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c index 78fb7780272a..56b5f98da463 100644 --- a/crypto/async_tx/async_xor.c +++ b/crypto/async_tx/async_xor.c @@ -62,7 +62,7 @@ do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list, while (src_cnt) { submit->flags = flags_orig; dma_flags = 0; - xor_src_cnt = min(src_cnt, dma->max_xor); + xor_src_cnt = min(src_cnt, (int)dma->max_xor); /* if we are submitting additional xors, leave the chain open, * clear the callback parameters, and leave the destination * buffer mapped diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index e002e0e0d055..cd5673d3043b 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -646,6 +646,10 @@ int dma_async_device_register(struct dma_device *device) !device->device_prep_dma_xor); BUG_ON(dma_has_cap(DMA_XOR_VAL, device->cap_mask) && !device->device_prep_dma_xor_val); + BUG_ON(dma_has_cap(DMA_PQ, device->cap_mask) && + !device->device_prep_dma_pq); + BUG_ON(dma_has_cap(DMA_PQ_VAL, device->cap_mask) && + !device->device_prep_dma_pq_val); BUG_ON(dma_has_cap(DMA_MEMSET, device->cap_mask) && !device->device_prep_dma_memset); BUG_ON(dma_has_cap(DMA_INTERRUPT, device->cap_mask) && diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c index 6ff79a672699..4496bc606662 100644 --- a/drivers/dma/iop-adma.c +++ b/drivers/dma/iop-adma.c @@ -1257,7 +1257,7 @@ static int __devinit iop_adma_probe(struct platform_device *pdev) dev_printk(KERN_INFO, &pdev->dev, "Intel(R) IOP: " "( %s%s%s%s%s%s%s%s%s%s)\n", - dma_has_cap(DMA_PQ_XOR, dma_dev->cap_mask) ? "pq_xor " : "", + dma_has_cap(DMA_PQ, dma_dev->cap_mask) ? "pq " : "", dma_has_cap(DMA_PQ_UPDATE, dma_dev->cap_mask) ? "pq_update " : "", dma_has_cap(DMA_PQ_VAL, dma_dev->cap_mask) ? "pq_val " : "", dma_has_cap(DMA_XOR, dma_dev->cap_mask) ? "xor " : "", 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 --- Documentation/crypto/async-tx-api.txt | 4 + crypto/async_tx/Kconfig | 5 + crypto/async_tx/Makefile | 1 + crypto/async_tx/async_raid6_recov.c | 448 ++++++++++++++++++++++++++++++++++ include/linux/async_tx.h | 8 + 5 files changed, 466 insertions(+) create mode 100644 crypto/async_tx/async_raid6_recov.c (limited to 'include/linux') diff --git a/Documentation/crypto/async-tx-api.txt b/Documentation/crypto/async-tx-api.txt index 0e48e054d69a..ba046b8fa92f 100644 --- a/Documentation/crypto/async-tx-api.txt +++ b/Documentation/crypto/async-tx-api.txt @@ -67,6 +67,10 @@ xor_val - xor a series of source buffers and set a flag if the pq - generate the p+q (raid6 syndrome) from a series of source buffers pq_val - validate that a p and or q buffer are in sync with a given series of sources +datap - (raid6_datap_recov) recover a raid6 data block and the p block + from the given sources +2data - (raid6_2data_recov) recover 2 raid6 data blocks from the given + sources 3.3 Descriptor management: The return value is non-NULL and points to a 'descriptor' when the operation diff --git a/crypto/async_tx/Kconfig b/crypto/async_tx/Kconfig index cb6d7314f198..e5aeb2b79e6f 100644 --- a/crypto/async_tx/Kconfig +++ b/crypto/async_tx/Kconfig @@ -18,3 +18,8 @@ config ASYNC_PQ tristate select ASYNC_CORE +config ASYNC_RAID6_RECOV + tristate + select ASYNC_CORE + select ASYNC_PQ + diff --git a/crypto/async_tx/Makefile b/crypto/async_tx/Makefile index 1b9926588259..9a1a76811b80 100644 --- a/crypto/async_tx/Makefile +++ b/crypto/async_tx/Makefile @@ -3,3 +3,4 @@ obj-$(CONFIG_ASYNC_MEMCPY) += async_memcpy.o obj-$(CONFIG_ASYNC_MEMSET) += async_memset.o obj-$(CONFIG_ASYNC_XOR) += async_xor.o obj-$(CONFIG_ASYNC_PQ) += async_pq.o +obj-$(CONFIG_ASYNC_RAID6_RECOV) += async_raid6_recov.o diff --git a/crypto/async_tx/async_raid6_recov.c b/crypto/async_tx/async_raid6_recov.c new file mode 100644 index 000000000000..0c14d48c9896 --- /dev/null +++ b/crypto/async_tx/async_raid6_recov.c @@ -0,0 +1,448 @@ +/* + * Asynchronous RAID-6 recovery calculations ASYNC_TX API. + * Copyright(c) 2009 Intel Corporation + * + * based on raid6recov.c: + * Copyright 2002 H. Peter Anvin + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 51 + * Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * + */ +#include +#include +#include +#include +#include + +static struct dma_async_tx_descriptor * +async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef, + size_t len, struct async_submit_ctl *submit) +{ + struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ, + &dest, 1, srcs, 2, len); + struct dma_device *dma = chan ? chan->device : NULL; + const u8 *amul, *bmul; + u8 ax, bx; + u8 *a, *b, *c; + + if (dma) { + dma_addr_t dma_dest[2]; + dma_addr_t dma_src[2]; + struct device *dev = dma->dev; + struct dma_async_tx_descriptor *tx; + enum dma_ctrl_flags dma_flags = DMA_PREP_PQ_DISABLE_P; + + dma_dest[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL); + dma_src[0] = dma_map_page(dev, srcs[0], 0, len, DMA_TO_DEVICE); + dma_src[1] = dma_map_page(dev, srcs[1], 0, len, DMA_TO_DEVICE); + tx = dma->device_prep_dma_pq(chan, dma_dest, dma_src, 2, coef, + len, dma_flags); + if (tx) { + async_tx_submit(chan, tx, submit); + return tx; + } + } + + /* run the operation synchronously */ + async_tx_quiesce(&submit->depend_tx); + amul = raid6_gfmul[coef[0]]; + bmul = raid6_gfmul[coef[1]]; + a = page_address(srcs[0]); + b = page_address(srcs[1]); + c = page_address(dest); + + while (len--) { + ax = amul[*a++]; + bx = bmul[*b++]; + *c++ = ax ^ bx; + } + + return NULL; +} + +static struct dma_async_tx_descriptor * +async_mult(struct page *dest, struct page *src, u8 coef, size_t len, + struct async_submit_ctl *submit) +{ + struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ, + &dest, 1, &src, 1, len); + struct dma_device *dma = chan ? chan->device : NULL; + const u8 *qmul; /* Q multiplier table */ + u8 *d, *s; + + if (dma) { + dma_addr_t dma_dest[2]; + dma_addr_t dma_src[1]; + struct device *dev = dma->dev; + struct dma_async_tx_descriptor *tx; + enum dma_ctrl_flags dma_flags = DMA_PREP_PQ_DISABLE_P; + + dma_dest[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL); + dma_src[0] = dma_map_page(dev, src, 0, len, DMA_TO_DEVICE); + tx = dma->device_prep_dma_pq(chan, dma_dest, dma_src, 1, &coef, + len, dma_flags); + if (tx) { + async_tx_submit(chan, tx, submit); + return tx; + } + } + + /* no channel available, or failed to allocate a descriptor, so + * perform the operation synchronously + */ + async_tx_quiesce(&submit->depend_tx); + qmul = raid6_gfmul[coef]; + d = page_address(dest); + s = page_address(src); + + while (len--) + *d++ = qmul[*s++]; + + return NULL; +} + +static struct dma_async_tx_descriptor * +__2data_recov_4(size_t bytes, int faila, int failb, struct page **blocks, + struct async_submit_ctl *submit) +{ + struct dma_async_tx_descriptor *tx = NULL; + struct page *p, *q, *a, *b; + struct page *srcs[2]; + unsigned char coef[2]; + enum async_tx_flags flags = submit->flags; + dma_async_tx_callback cb_fn = submit->cb_fn; + void *cb_param = submit->cb_param; + void *scribble = submit->scribble; + + p = blocks[4-2]; + q = blocks[4-1]; + + a = blocks[faila]; + b = blocks[failb]; + + /* in the 4 disk case P + Pxy == P and Q + Qxy == Q */ + /* Dx = A*(P+Pxy) + B*(Q+Qxy) */ + srcs[0] = p; + srcs[1] = q; + coef[0] = raid6_gfexi[failb-faila]; + coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]]; + init_async_submit(submit, 0, tx, NULL, NULL, scribble); + tx = async_sum_product(b, srcs, coef, bytes, submit); + + /* Dy = P+Pxy+Dx */ + srcs[0] = p; + srcs[1] = b; + init_async_submit(submit, flags | ASYNC_TX_XOR_ZERO_DST, tx, cb_fn, + cb_param, scribble); + tx = async_xor(a, srcs, 0, 2, bytes, submit); + + return tx; + +} + +static struct dma_async_tx_descriptor * +__2data_recov_5(size_t bytes, int faila, int failb, struct page **blocks, + struct async_submit_ctl *submit) +{ + struct dma_async_tx_descriptor *tx = NULL; + struct page *p, *q, *g, *dp, *dq; + struct page *srcs[2]; + unsigned char coef[2]; + enum async_tx_flags flags = submit->flags; + dma_async_tx_callback cb_fn = submit->cb_fn; + void *cb_param = submit->cb_param; + void *scribble = submit->scribble; + int uninitialized_var(good); + int i; + + for (i = 0; i < 3; i++) { + if (i == faila || i == failb) + continue; + else { + good = i; + break; + } + } + BUG_ON(i >= 3); + + p = blocks[5-2]; + q = blocks[5-1]; + g = blocks[good]; + + /* Compute syndrome with zero for the missing data pages + * Use the dead data pages as temporary storage for delta p and + * delta q + */ + dp = blocks[faila]; + dq = blocks[failb]; + + init_async_submit(submit, 0, tx, NULL, NULL, scribble); + tx = async_memcpy(dp, g, 0, 0, bytes, submit); + init_async_submit(submit, 0, tx, NULL, NULL, scribble); + tx = async_mult(dq, g, raid6_gfexp[good], bytes, submit); + + /* compute P + Pxy */ + srcs[0] = dp; + srcs[1] = p; + init_async_submit(submit, ASYNC_TX_XOR_DROP_DST, tx, NULL, NULL, + scribble); + tx = async_xor(dp, srcs, 0, 2, bytes, submit); + + /* compute Q + Qxy */ + srcs[0] = dq; + srcs[1] = q; + init_async_submit(submit, ASYNC_TX_XOR_DROP_DST, tx, NULL, NULL, + scribble); + tx = async_xor(dq, srcs, 0, 2, bytes, submit); + + /* Dx = A*(P+Pxy) + B*(Q+Qxy) */ + srcs[0] = dp; + srcs[1] = dq; + coef[0] = raid6_gfexi[failb-faila]; + coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]]; + init_async_submit(submit, 0, tx, NULL, NULL, scribble); + tx = async_sum_product(dq, srcs, coef, bytes, submit); + + /* Dy = P+Pxy+Dx */ + srcs[0] = dp; + srcs[1] = dq; + init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn, + cb_param, scribble); + tx = async_xor(dp, srcs, 0, 2, bytes, submit); + + return tx; +} + +static struct dma_async_tx_descriptor * +__2data_recov_n(int disks, size_t bytes, int faila, int failb, + struct page **blocks, struct async_submit_ctl *submit) +{ + struct dma_async_tx_descriptor *tx = NULL; + struct page *p, *q, *dp, *dq; + struct page *srcs[2]; + unsigned char coef[2]; + enum async_tx_flags flags = submit->flags; + dma_async_tx_callback cb_fn = submit->cb_fn; + void *cb_param = submit->cb_param; + void *scribble = submit->scribble; + + p = blocks[disks-2]; + q = blocks[disks-1]; + + /* Compute syndrome with zero for the missing data pages + * Use the dead data pages as temporary storage for + * delta p and delta q + */ + dp = blocks[faila]; + blocks[faila] = (void *)raid6_empty_zero_page; + blocks[disks-2] = dp; + dq = blocks[failb]; + blocks[failb] = (void *)raid6_empty_zero_page; + blocks[disks-1] = dq; + + init_async_submit(submit, 0, tx, NULL, NULL, scribble); + tx = async_gen_syndrome(blocks, 0, disks, bytes, submit); + + /* Restore pointer table */ + blocks[faila] = dp; + blocks[failb] = dq; + blocks[disks-2] = p; + blocks[disks-1] = q; + + /* compute P + Pxy */ + srcs[0] = dp; + srcs[1] = p; + init_async_submit(submit, ASYNC_TX_XOR_DROP_DST, tx, NULL, NULL, + scribble); + tx = async_xor(dp, srcs, 0, 2, bytes, submit); + + /* compute Q + Qxy */ + srcs[0] = dq; + srcs[1] = q; + init_async_submit(submit, ASYNC_TX_XOR_DROP_DST, tx, NULL, NULL, + scribble); + tx = async_xor(dq, srcs, 0, 2, bytes, submit); + + /* Dx = A*(P+Pxy) + B*(Q+Qxy) */ + srcs[0] = dp; + srcs[1] = dq; + coef[0] = raid6_gfexi[failb-faila]; + coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]]; + init_async_submit(submit, 0, tx, NULL, NULL, scribble); + tx = async_sum_product(dq, srcs, coef, bytes, submit); + + /* Dy = P+Pxy+Dx */ + srcs[0] = dp; + srcs[1] = dq; + init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn, + cb_param, scribble); + tx = async_xor(dp, srcs, 0, 2, bytes, submit); + + return tx; +} + +/** + * async_raid6_2data_recov - asynchronously calculate two missing data blocks + * @disks: number of disks in the RAID-6 array + * @bytes: block size + * @faila: first failed drive index + * @failb: second failed drive index + * @blocks: array of source pointers where the last two entries are p and q + * @submit: submission/completion modifiers + */ +struct dma_async_tx_descriptor * +async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb, + struct page **blocks, struct async_submit_ctl *submit) +{ + BUG_ON(faila == failb); + if (failb < faila) + swap(faila, failb); + + pr_debug("%s: disks: %d len: %zu\n", __func__, disks, bytes); + + /* we need to preserve the contents of 'blocks' for the async + * case, so punt to synchronous if a scribble buffer is not available + */ + if (!submit->scribble) { + void **ptrs = (void **) blocks; + int i; + + async_tx_quiesce(&submit->depend_tx); + for (i = 0; i < disks; i++) + ptrs[i] = page_address(blocks[i]); + + raid6_2data_recov(disks, bytes, faila, failb, ptrs); + + async_tx_sync_epilog(submit); + + return NULL; + } + + switch (disks) { + case 4: + /* dma devices do not uniformly understand a zero source pq + * operation (in contrast to the synchronous case), so + * explicitly handle the 4 disk special case + */ + return __2data_recov_4(bytes, faila, failb, blocks, submit); + case 5: + /* dma devices do not uniformly understand a single + * source pq operation (in contrast to the synchronous + * case), so explicitly handle the 5 disk special case + */ + return __2data_recov_5(bytes, faila, failb, blocks, submit); + default: + return __2data_recov_n(disks, bytes, faila, failb, blocks, submit); + } +} +EXPORT_SYMBOL_GPL(async_raid6_2data_recov); + +/** + * async_raid6_datap_recov - asynchronously calculate a data and the 'p' block + * @disks: number of disks in the RAID-6 array + * @bytes: block size + * @faila: failed drive index + * @blocks: array of source pointers where the last two entries are p and q + * @submit: submission/completion modifiers + */ +struct dma_async_tx_descriptor * +async_raid6_datap_recov(int disks, size_t bytes, int faila, + struct page **blocks, struct async_submit_ctl *submit) +{ + struct dma_async_tx_descriptor *tx = NULL; + struct page *p, *q, *dq; + u8 coef; + enum async_tx_flags flags = submit->flags; + dma_async_tx_callback cb_fn = submit->cb_fn; + void *cb_param = submit->cb_param; + void *scribble = submit->scribble; + struct page *srcs[2]; + + pr_debug("%s: disks: %d len: %zu\n", __func__, disks, bytes); + + /* we need to preserve the contents of 'blocks' for the async + * case, so punt to synchronous if a scribble buffer is not available + */ + if (!scribble) { + void **ptrs = (void **) blocks; + int i; + + async_tx_quiesce(&submit->depend_tx); + for (i = 0; i < disks; i++) + ptrs[i] = page_address(blocks[i]); + + raid6_datap_recov(disks, bytes, faila, ptrs); + + async_tx_sync_epilog(submit); + + return NULL; + } + + p = blocks[disks-2]; + q = blocks[disks-1]; + + /* Compute syndrome with zero for the missing data page + * Use the dead data page as temporary storage for delta q + */ + dq = blocks[faila]; + blocks[faila] = (void *)raid6_empty_zero_page; + blocks[disks-1] = dq; + + /* in the 4 disk case we only need to perform a single source + * multiplication + */ + if (disks == 4) { + int good = faila == 0 ? 1 : 0; + struct page *g = blocks[good]; + + init_async_submit(submit, 0, tx, NULL, NULL, scribble); + tx = async_memcpy(p, g, 0, 0, bytes, submit); + + init_async_submit(submit, 0, tx, NULL, NULL, scribble); + tx = async_mult(dq, g, raid6_gfexp[good], bytes, submit); + } else { + init_async_submit(submit, 0, tx, NULL, NULL, scribble); + tx = async_gen_syndrome(blocks, 0, disks, bytes, submit); + } + + /* Restore pointer table */ + blocks[faila] = dq; + blocks[disks-1] = q; + + /* calculate g^{-faila} */ + coef = raid6_gfinv[raid6_gfexp[faila]]; + + srcs[0] = dq; + srcs[1] = q; + init_async_submit(submit, ASYNC_TX_XOR_DROP_DST, tx, NULL, NULL, + scribble); + tx = async_xor(dq, srcs, 0, 2, bytes, submit); + + init_async_submit(submit, 0, tx, NULL, NULL, scribble); + tx = async_mult(dq, dq, coef, bytes, submit); + + srcs[0] = p; + srcs[1] = dq; + init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn, + cb_param, scribble); + tx = async_xor(p, srcs, 0, 2, bytes, submit); + + return tx; +} +EXPORT_SYMBOL_GPL(async_raid6_datap_recov); + +MODULE_AUTHOR("Dan Williams "); +MODULE_DESCRIPTION("asynchronous RAID-6 recovery api"); +MODULE_LICENSE("GPL"); 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 c746b5519a88b8803d43946ad06326ece4829116 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Sat, 5 Sep 2009 14:09:21 +0100 Subject: leds: Add WM831x status LED driver The WM831x devices feature two software controlled status LEDs with hardware assisted blinking. The device can also autonomously control the LEDs based on a selection of sources. This can be configured at boot time using either platform data or the chip OTP. A sysfs file in the style of that for triggers allowing the control source to be configured at run time. Triggers can't be used here since they can't depend on the implementation details of a specific LED type. Signed-off-by: Mark Brown Signed-off-by: Richard Purdie --- drivers/leds/Kconfig | 7 + drivers/leds/Makefile | 1 + drivers/leds/leds-wm831x-status.c | 341 ++++++++++++++++++++++++++++++++++++++ include/linux/mfd/wm831x/status.h | 34 ++++ 4 files changed, 383 insertions(+) create mode 100644 drivers/leds/leds-wm831x-status.c create mode 100644 include/linux/mfd/wm831x/status.h (limited to 'include/linux') diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index 7c8e7122aaa9..edfd4e302be7 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -195,6 +195,13 @@ config LEDS_PCA955X LED driver chips accessed via the I2C bus. Supported devices include PCA9550, PCA9551, PCA9552, and PCA9553. +config LEDS_WM831X_STATUS + tristate "LED support for status LEDs on WM831x PMICs" + depends on LEDS_CLASS && MFD_WM831X + help + This option enables support for the status LEDs of the WM831x + series of PMICs. + config LEDS_WM8350 tristate "LED Support for WM8350 AudioPlus PMIC" depends on LEDS_CLASS && MFD_WM8350 diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile index e8cdcf77a4c3..46d72704d606 100644 --- a/drivers/leds/Makefile +++ b/drivers/leds/Makefile @@ -26,6 +26,7 @@ obj-$(CONFIG_LEDS_HP6XX) += leds-hp6xx.o obj-$(CONFIG_LEDS_FSG) += leds-fsg.o obj-$(CONFIG_LEDS_PCA955X) += leds-pca955x.o obj-$(CONFIG_LEDS_DA903X) += leds-da903x.o +obj-$(CONFIG_LEDS_WM831X_STATUS) += leds-wm831x-status.o obj-$(CONFIG_LEDS_WM8350) += leds-wm8350.o obj-$(CONFIG_LEDS_PWM) += leds-pwm.o diff --git a/drivers/leds/leds-wm831x-status.c b/drivers/leds/leds-wm831x-status.c new file mode 100644 index 000000000000..c586d05e336a --- /dev/null +++ b/drivers/leds/leds-wm831x-status.c @@ -0,0 +1,341 @@ +/* + * LED driver for WM831x status LEDs + * + * Copyright(C) 2009 Wolfson Microelectronics PLC. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include + + +struct wm831x_status { + struct led_classdev cdev; + struct wm831x *wm831x; + struct work_struct work; + struct mutex mutex; + + spinlock_t value_lock; + int reg; /* Control register */ + int reg_val; /* Control register value */ + + int blink; + int blink_time; + int blink_cyc; + int src; + enum led_brightness brightness; +}; + +#define to_wm831x_status(led_cdev) \ + container_of(led_cdev, struct wm831x_status, cdev) + +static void wm831x_status_work(struct work_struct *work) +{ + struct wm831x_status *led = container_of(work, struct wm831x_status, + work); + unsigned long flags; + + mutex_lock(&led->mutex); + + led->reg_val &= ~(WM831X_LED_SRC_MASK | WM831X_LED_MODE_MASK | + WM831X_LED_DUTY_CYC_MASK | WM831X_LED_DUR_MASK); + + spin_lock_irqsave(&led->value_lock, flags); + + led->reg_val |= led->src << WM831X_LED_SRC_SHIFT; + if (led->blink) { + led->reg_val |= 2 << WM831X_LED_MODE_SHIFT; + led->reg_val |= led->blink_time << WM831X_LED_DUR_SHIFT; + led->reg_val |= led->blink_cyc; + } else { + if (led->brightness != LED_OFF) + led->reg_val |= 1 << WM831X_LED_MODE_SHIFT; + } + + spin_unlock_irqrestore(&led->value_lock, flags); + + wm831x_reg_write(led->wm831x, led->reg, led->reg_val); + + mutex_unlock(&led->mutex); +} + +static void wm831x_status_set(struct led_classdev *led_cdev, + enum led_brightness value) +{ + struct wm831x_status *led = to_wm831x_status(led_cdev); + unsigned long flags; + + spin_lock_irqsave(&led->value_lock, flags); + led->brightness = value; + if (value == LED_OFF) + led->blink = 0; + schedule_work(&led->work); + spin_unlock_irqrestore(&led->value_lock, flags); +} + +static int wm831x_status_blink_set(struct led_classdev *led_cdev, + unsigned long *delay_on, + unsigned long *delay_off) +{ + struct wm831x_status *led = to_wm831x_status(led_cdev); + unsigned long flags; + int ret = 0; + + /* Pick some defaults if we've not been given times */ + if (*delay_on == 0 && *delay_off == 0) { + *delay_on = 250; + *delay_off = 250; + } + + spin_lock_irqsave(&led->value_lock, flags); + + /* We only have a limited selection of settings, see if we can + * support the configuration we're being given */ + switch (*delay_on) { + case 1000: + led->blink_time = 0; + break; + case 250: + led->blink_time = 1; + break; + case 125: + led->blink_time = 2; + break; + case 62: + case 63: + /* Actually 62.5ms */ + led->blink_time = 3; + break; + default: + ret = -EINVAL; + break; + } + + if (ret == 0) { + switch (*delay_off / *delay_on) { + case 1: + led->blink_cyc = 0; + break; + case 3: + led->blink_cyc = 1; + break; + case 4: + led->blink_cyc = 2; + break; + case 8: + led->blink_cyc = 3; + break; + default: + ret = -EINVAL; + break; + } + } + + if (ret == 0) + led->blink = 1; + else + led->blink = 0; + + /* Always update; if we fail turn off blinking since we expect + * a software fallback. */ + schedule_work(&led->work); + + spin_unlock_irqrestore(&led->value_lock, flags); + + return ret; +} + +static const char *led_src_texts[] = { + "otp", + "power", + "charger", + "soft", +}; + +static ssize_t wm831x_status_src_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct led_classdev *led_cdev = dev_get_drvdata(dev); + struct wm831x_status *led = to_wm831x_status(led_cdev); + int i; + ssize_t ret = 0; + + mutex_lock(&led->mutex); + + for (i = 0; i < ARRAY_SIZE(led_src_texts); i++) + if (i == led->src) + ret += sprintf(&buf[ret], "[%s] ", led_src_texts[i]); + else + ret += sprintf(&buf[ret], "%s ", led_src_texts[i]); + + mutex_unlock(&led->mutex); + + ret += sprintf(&buf[ret], "\n"); + + return ret; +} + +static ssize_t wm831x_status_src_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + struct led_classdev *led_cdev = dev_get_drvdata(dev); + struct wm831x_status *led = to_wm831x_status(led_cdev); + char name[20]; + int i; + size_t len; + + name[sizeof(name) - 1] = '\0'; + strncpy(name, buf, sizeof(name) - 1); + len = strlen(name); + + if (len && name[len - 1] == '\n') + name[len - 1] = '\0'; + + for (i = 0; i < ARRAY_SIZE(led_src_texts); i++) { + if (!strcmp(name, led_src_texts[i])) { + mutex_lock(&led->mutex); + + led->src = i; + schedule_work(&led->work); + + mutex_unlock(&led->mutex); + } + } + + return size; +} + +static DEVICE_ATTR(src, 0644, wm831x_status_src_show, wm831x_status_src_store); + +static int wm831x_status_probe(struct platform_device *pdev) +{ + struct wm831x *wm831x = dev_get_drvdata(pdev->dev.parent); + struct wm831x_pdata *chip_pdata; + struct wm831x_status_pdata pdata; + struct wm831x_status *drvdata; + struct resource *res; + int id = pdev->id % ARRAY_SIZE(chip_pdata->status); + int ret; + + res = platform_get_resource(pdev, IORESOURCE_IO, 0); + if (res == NULL) { + dev_err(&pdev->dev, "No I/O resource\n"); + ret = -EINVAL; + goto err; + } + + drvdata = kzalloc(sizeof(struct wm831x_status), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + dev_set_drvdata(&pdev->dev, drvdata); + + drvdata->wm831x = wm831x; + drvdata->reg = res->start; + + if (wm831x->dev->platform_data) + chip_pdata = wm831x->dev->platform_data; + else + chip_pdata = NULL; + + memset(&pdata, 0, sizeof(pdata)); + if (chip_pdata && chip_pdata->status[id]) + memcpy(&pdata, chip_pdata->status[id], sizeof(pdata)); + else + pdata.name = dev_name(&pdev->dev); + + mutex_init(&drvdata->mutex); + INIT_WORK(&drvdata->work, wm831x_status_work); + spin_lock_init(&drvdata->value_lock); + + /* We cache the configuration register and read startup values + * from it. */ + drvdata->reg_val = wm831x_reg_read(wm831x, drvdata->reg); + + if (drvdata->reg_val & WM831X_LED_MODE_MASK) + drvdata->brightness = LED_FULL; + else + drvdata->brightness = LED_OFF; + + /* Set a default source if configured, otherwise leave the + * current hardware setting. + */ + if (pdata.default_src == WM831X_STATUS_PRESERVE) { + drvdata->src = drvdata->reg_val; + drvdata->src &= WM831X_LED_SRC_MASK; + drvdata->src >>= WM831X_LED_SRC_SHIFT; + } else { + drvdata->src = pdata.default_src - 1; + } + + drvdata->cdev.name = pdata.name; + drvdata->cdev.default_trigger = pdata.default_trigger; + drvdata->cdev.brightness_set = wm831x_status_set; + drvdata->cdev.blink_set = wm831x_status_blink_set; + + ret = led_classdev_register(wm831x->dev, &drvdata->cdev); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to register LED: %d\n", ret); + goto err_led; + } + + ret = device_create_file(drvdata->cdev.dev, &dev_attr_src); + if (ret != 0) + dev_err(&pdev->dev, + "No source control for LED: %d\n", ret); + + return 0; + +err_led: + led_classdev_unregister(&drvdata->cdev); + kfree(drvdata); +err: + return ret; +} + +static int wm831x_status_remove(struct platform_device *pdev) +{ + struct wm831x_status *drvdata = platform_get_drvdata(pdev); + + device_remove_file(drvdata->cdev.dev, &dev_attr_src); + led_classdev_unregister(&drvdata->cdev); + kfree(drvdata); + + return 0; +} + +static struct platform_driver wm831x_status_driver = { + .driver = { + .name = "wm831x-status", + .owner = THIS_MODULE, + }, + .probe = wm831x_status_probe, + .remove = wm831x_status_remove, +}; + +static int __devinit wm831x_status_init(void) +{ + return platform_driver_register(&wm831x_status_driver); +} +module_init(wm831x_status_init); + +static void wm831x_status_exit(void) +{ + platform_driver_unregister(&wm831x_status_driver); +} +module_exit(wm831x_status_exit); + +MODULE_AUTHOR("Mark Brown "); +MODULE_DESCRIPTION("WM831x status LED driver"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:wm831x-status"); diff --git a/include/linux/mfd/wm831x/status.h b/include/linux/mfd/wm831x/status.h new file mode 100644 index 000000000000..6bc090d0e3ac --- /dev/null +++ b/include/linux/mfd/wm831x/status.h @@ -0,0 +1,34 @@ +/* + * include/linux/mfd/wm831x/status.h -- Status LEDs for WM831x + * + * Copyright 2009 Wolfson Microelectronics PLC. + * + * Author: Mark Brown + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + */ + +#ifndef __MFD_WM831X_STATUS_H__ +#define __MFD_WM831X_STATUS_H__ + +#define WM831X_LED_SRC_MASK 0xC000 /* LED_SRC - [15:14] */ +#define WM831X_LED_SRC_SHIFT 14 /* LED_SRC - [15:14] */ +#define WM831X_LED_SRC_WIDTH 2 /* LED_SRC - [15:14] */ +#define WM831X_LED_MODE_MASK 0x0300 /* LED_MODE - [9:8] */ +#define WM831X_LED_MODE_SHIFT 8 /* LED_MODE - [9:8] */ +#define WM831X_LED_MODE_WIDTH 2 /* LED_MODE - [9:8] */ +#define WM831X_LED_SEQ_LEN_MASK 0x0030 /* LED_SEQ_LEN - [5:4] */ +#define WM831X_LED_SEQ_LEN_SHIFT 4 /* LED_SEQ_LEN - [5:4] */ +#define WM831X_LED_SEQ_LEN_WIDTH 2 /* LED_SEQ_LEN - [5:4] */ +#define WM831X_LED_DUR_MASK 0x000C /* LED_DUR - [3:2] */ +#define WM831X_LED_DUR_SHIFT 2 /* LED_DUR - [3:2] */ +#define WM831X_LED_DUR_WIDTH 2 /* LED_DUR - [3:2] */ +#define WM831X_LED_DUTY_CYC_MASK 0x0003 /* LED_DUTY_CYC - [1:0] */ +#define WM831X_LED_DUTY_CYC_SHIFT 0 /* LED_DUTY_CYC - [1:0] */ +#define WM831X_LED_DUTY_CYC_WIDTH 2 /* LED_DUTY_CYC - [1:0] */ + +#endif -- cgit v1.2.3 From 5036cc41e07d6614350e329666ee8a79cea6f793 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 6 Aug 2009 16:07:10 -0700 Subject: backlight: spi driver for LMS283GF05 LCD ADd support for the SPI part of LMS283GF05 LCD. The LCD uses SPI for initialization and powerdown sequences. No further defails are specified in the datasheet about the initialization/powerdown sequence, just the magic numbers that have to be sent over SPI bus. This LCD can be found in the Aeronix Zipit Z2 handheld. Signed-off-by: Marek Vasut Signed-off-by: Andrew Morton Signed-off-by: Richard Purdie --- drivers/video/backlight/Kconfig | 7 + drivers/video/backlight/Makefile | 1 + drivers/video/backlight/lms283gf05.c | 242 +++++++++++++++++++++++++++++++++++ include/linux/spi/lms283gf05.h | 28 ++++ 4 files changed, 278 insertions(+) create mode 100644 drivers/video/backlight/lms283gf05.c create mode 100644 include/linux/spi/lms283gf05.h (limited to 'include/linux') diff --git a/drivers/video/backlight/Kconfig b/drivers/video/backlight/Kconfig index f86dbfd209ad..c0d4a536ea87 100644 --- a/drivers/video/backlight/Kconfig +++ b/drivers/video/backlight/Kconfig @@ -31,6 +31,13 @@ config LCD_CORGI Say y here to support the LCD panels usually found on SHARP corgi (C7x0) and spitz (Cxx00) models. +config LCD_LMS283GF05 + tristate "Samsung LMS283GF05 LCD" + depends on LCD_CLASS_DEVICE && SPI_MASTER && GENERIC_GPIO + help + SPI driver for Samsung LMS283GF05. This provides basic support + for powering the LCD up/down through a sysfs interface. + config LCD_LTV350QV tristate "Samsung LTV350QV LCD Panel" depends on LCD_CLASS_DEVICE && SPI_MASTER diff --git a/drivers/video/backlight/Makefile b/drivers/video/backlight/Makefile index df0b67ce88b6..0abc014215ba 100644 --- a/drivers/video/backlight/Makefile +++ b/drivers/video/backlight/Makefile @@ -3,6 +3,7 @@ obj-$(CONFIG_LCD_CLASS_DEVICE) += lcd.o obj-$(CONFIG_LCD_CORGI) += corgi_lcd.o obj-$(CONFIG_LCD_HP700) += jornada720_lcd.o +obj-$(CONFIG_LCD_LMS283GF05) += lms283gf05.o obj-$(CONFIG_LCD_LTV350QV) += ltv350qv.o obj-$(CONFIG_LCD_ILI9320) += ili9320.o obj-$(CONFIG_LCD_PLATFORM) += platform_lcd.o diff --git a/drivers/video/backlight/lms283gf05.c b/drivers/video/backlight/lms283gf05.c new file mode 100644 index 000000000000..447b542a20ca --- /dev/null +++ b/drivers/video/backlight/lms283gf05.c @@ -0,0 +1,242 @@ +/* + * lms283gf05.c -- support for Samsung LMS283GF05 LCD + * + * Copyright (c) 2009 Marek Vasut + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include + +#include +#include + +struct lms283gf05_state { + struct spi_device *spi; + struct lcd_device *ld; +}; + +struct lms283gf05_seq { + unsigned char reg; + unsigned short value; + unsigned char delay; +}; + +/* Magic sequences supplied by manufacturer, for details refer to datasheet */ +static struct lms283gf05_seq disp_initseq[] = { + /* REG, VALUE, DELAY */ + { 0x07, 0x0000, 0 }, + { 0x13, 0x0000, 10 }, + + { 0x11, 0x3004, 0 }, + { 0x14, 0x200F, 0 }, + { 0x10, 0x1a20, 0 }, + { 0x13, 0x0040, 50 }, + + { 0x13, 0x0060, 0 }, + { 0x13, 0x0070, 200 }, + + { 0x01, 0x0127, 0 }, + { 0x02, 0x0700, 0 }, + { 0x03, 0x1030, 0 }, + { 0x08, 0x0208, 0 }, + { 0x0B, 0x0620, 0 }, + { 0x0C, 0x0110, 0 }, + { 0x30, 0x0120, 0 }, + { 0x31, 0x0127, 0 }, + { 0x32, 0x0000, 0 }, + { 0x33, 0x0503, 0 }, + { 0x34, 0x0727, 0 }, + { 0x35, 0x0124, 0 }, + { 0x36, 0x0706, 0 }, + { 0x37, 0x0701, 0 }, + { 0x38, 0x0F00, 0 }, + { 0x39, 0x0F00, 0 }, + { 0x40, 0x0000, 0 }, + { 0x41, 0x0000, 0 }, + { 0x42, 0x013f, 0 }, + { 0x43, 0x0000, 0 }, + { 0x44, 0x013f, 0 }, + { 0x45, 0x0000, 0 }, + { 0x46, 0xef00, 0 }, + { 0x47, 0x013f, 0 }, + { 0x48, 0x0000, 0 }, + { 0x07, 0x0015, 30 }, + + { 0x07, 0x0017, 0 }, + + { 0x20, 0x0000, 0 }, + { 0x21, 0x0000, 0 }, + { 0x22, 0x0000, 0 } +}; + +static struct lms283gf05_seq disp_pdwnseq[] = { + { 0x07, 0x0016, 30 }, + + { 0x07, 0x0004, 0 }, + { 0x10, 0x0220, 20 }, + + { 0x13, 0x0060, 50 }, + + { 0x13, 0x0040, 50 }, + + { 0x13, 0x0000, 0 }, + { 0x10, 0x0000, 0 } +}; + + +static void lms283gf05_reset(unsigned long gpio, bool inverted) +{ + gpio_set_value(gpio, !inverted); + mdelay(100); + gpio_set_value(gpio, inverted); + mdelay(20); + gpio_set_value(gpio, !inverted); + mdelay(20); +} + +static void lms283gf05_toggle(struct spi_device *spi, + struct lms283gf05_seq *seq, int sz) +{ + char buf[3]; + int i; + + for (i = 0; i < sz; i++) { + buf[0] = 0x74; + buf[1] = 0x00; + buf[2] = seq[i].reg; + spi_write(spi, buf, 3); + + buf[0] = 0x76; + buf[1] = seq[i].value >> 8; + buf[2] = seq[i].value & 0xff; + spi_write(spi, buf, 3); + + mdelay(seq[i].delay); + } +} + +static int lms283gf05_power_set(struct lcd_device *ld, int power) +{ + struct lms283gf05_state *st = lcd_get_data(ld); + struct spi_device *spi = st->spi; + struct lms283gf05_pdata *pdata = spi->dev.platform_data; + + if (power) { + if (pdata) + lms283gf05_reset(pdata->reset_gpio, + pdata->reset_inverted); + lms283gf05_toggle(spi, disp_initseq, ARRAY_SIZE(disp_initseq)); + } else { + lms283gf05_toggle(spi, disp_pdwnseq, ARRAY_SIZE(disp_pdwnseq)); + if (pdata) + gpio_set_value(pdata->reset_gpio, + pdata->reset_inverted); + } + + return 0; +} + +static struct lcd_ops lms_ops = { + .set_power = lms283gf05_power_set, + .get_power = NULL, +}; + +static int __devinit lms283gf05_probe(struct spi_device *spi) +{ + struct lms283gf05_state *st; + struct lms283gf05_pdata *pdata = spi->dev.platform_data; + struct lcd_device *ld; + int ret = 0; + + if (pdata != NULL) { + ret = gpio_request(pdata->reset_gpio, "LMS285GF05 RESET"); + if (ret) + return ret; + + ret = gpio_direction_output(pdata->reset_gpio, + !pdata->reset_inverted); + if (ret) + goto err; + } + + st = kzalloc(sizeof(struct lms283gf05_state), GFP_KERNEL); + if (st == NULL) { + dev_err(&spi->dev, "No memory for device state\n"); + ret = -ENOMEM; + goto err; + } + + ld = lcd_device_register("lms283gf05", &spi->dev, st, &lms_ops); + if (IS_ERR(ld)) { + ret = PTR_ERR(ld); + goto err2; + } + + st->spi = spi; + st->ld = ld; + + dev_set_drvdata(&spi->dev, st); + + /* kick in the LCD */ + if (pdata) + lms283gf05_reset(pdata->reset_gpio, pdata->reset_inverted); + lms283gf05_toggle(spi, disp_initseq, ARRAY_SIZE(disp_initseq)); + + return 0; + +err2: + kfree(st); +err: + if (pdata != NULL) + gpio_free(pdata->reset_gpio); + + return ret; +} + +static int __devexit lms283gf05_remove(struct spi_device *spi) +{ + struct lms283gf05_state *st = dev_get_drvdata(&spi->dev); + struct lms283gf05_pdata *pdata = st->spi->dev.platform_data; + + lcd_device_unregister(st->ld); + + if (pdata != NULL) + gpio_free(pdata->reset_gpio); + + kfree(st); + + return 0; +} + +static struct spi_driver lms283gf05_driver = { + .driver = { + .name = "lms283gf05", + .owner = THIS_MODULE, + }, + .probe = lms283gf05_probe, + .remove = __devexit_p(lms283gf05_remove), +}; + +static __init int lms283gf05_init(void) +{ + return spi_register_driver(&lms283gf05_driver); +} + +static __exit void lms283gf05_exit(void) +{ + spi_unregister_driver(&lms283gf05_driver); +} + +module_init(lms283gf05_init); +module_exit(lms283gf05_exit); + +MODULE_AUTHOR("Marek Vasut "); +MODULE_DESCRIPTION("LCD283GF05 LCD"); +MODULE_LICENSE("GPL v2"); diff --git a/include/linux/spi/lms283gf05.h b/include/linux/spi/lms283gf05.h new file mode 100644 index 000000000000..555d254e6606 --- /dev/null +++ b/include/linux/spi/lms283gf05.h @@ -0,0 +1,28 @@ +/* + * lms283gf05.h - Platform glue for Samsung LMS283GF05 LCD + * + * Copyright (C) 2009 Marek Vasut + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +*/ + +#ifndef _INCLUDE_LINUX_SPI_LMS283GF05_H_ +#define _INCLUDE_LINUX_SPI_LMS283GF05_H_ + +struct lms283gf05_pdata { + unsigned long reset_gpio; + bool reset_inverted; +}; + +#endif /* _INCLUDE_LINUX_SPI_LMS283GF05_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 --- crypto/async_tx/async_memcpy.c | 7 ++++-- crypto/async_tx/async_memset.c | 7 ++++-- crypto/async_tx/async_pq.c | 5 ++++ crypto/async_tx/async_raid6_recov.c | 47 +++++++++++++++++++++---------------- crypto/async_tx/async_xor.c | 11 ++++++--- drivers/md/raid5.c | 37 ++++++++++++++++++----------- include/linux/async_tx.h | 3 +++ include/linux/dmaengine.h | 3 +++ 8 files changed, 79 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/crypto/async_tx/async_memcpy.c b/crypto/async_tx/async_memcpy.c index 98e15bd0dcb5..b38cbb3fd527 100644 --- a/crypto/async_tx/async_memcpy.c +++ b/crypto/async_tx/async_memcpy.c @@ -52,9 +52,12 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset, if (device) { dma_addr_t dma_dest, dma_src; - unsigned long dma_prep_flags; + unsigned long dma_prep_flags = 0; - dma_prep_flags = submit->cb_fn ? DMA_PREP_INTERRUPT : 0; + if (submit->cb_fn) + dma_prep_flags |= DMA_PREP_INTERRUPT; + if (submit->flags & ASYNC_TX_FENCE) + dma_prep_flags |= DMA_PREP_FENCE; dma_dest = dma_map_page(device->dev, dest, dest_offset, len, DMA_FROM_DEVICE); diff --git a/crypto/async_tx/async_memset.c b/crypto/async_tx/async_memset.c index b896a6e5f673..a374784e3329 100644 --- a/crypto/async_tx/async_memset.c +++ b/crypto/async_tx/async_memset.c @@ -49,9 +49,12 @@ async_memset(struct page *dest, int val, unsigned int offset, size_t len, if (device) { dma_addr_t dma_dest; - unsigned long dma_prep_flags; + unsigned long dma_prep_flags = 0; - dma_prep_flags = submit->cb_fn ? DMA_PREP_INTERRUPT : 0; + if (submit->cb_fn) + dma_prep_flags |= DMA_PREP_INTERRUPT; + if (submit->flags & ASYNC_TX_FENCE) + dma_prep_flags |= DMA_PREP_FENCE; dma_dest = dma_map_page(device->dev, dest, offset, len, DMA_FROM_DEVICE); diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c index 108b21efb499..a25e290c39fb 100644 --- a/crypto/async_tx/async_pq.c +++ b/crypto/async_tx/async_pq.c @@ -101,6 +101,7 @@ do_async_gen_syndrome(struct dma_chan *chan, struct page **blocks, */ if (src_cnt > pq_src_cnt) { submit->flags &= ~ASYNC_TX_ACK; + submit->flags |= ASYNC_TX_FENCE; dma_flags |= DMA_COMPL_SKIP_DEST_UNMAP; submit->cb_fn = NULL; submit->cb_param = NULL; @@ -111,6 +112,8 @@ do_async_gen_syndrome(struct dma_chan *chan, struct page **blocks, if (cb_fn_orig) dma_flags |= DMA_PREP_INTERRUPT; } + if (submit->flags & ASYNC_TX_FENCE) + dma_flags |= DMA_PREP_FENCE; /* Since we have clobbered the src_list we are committed * to doing this asynchronously. Drivers force forward @@ -282,6 +285,8 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks, dma_flags |= DMA_PREP_PQ_DISABLE_P; if (!Q(blocks, disks)) dma_flags |= DMA_PREP_PQ_DISABLE_Q; + if (submit->flags & ASYNC_TX_FENCE) + dma_flags |= DMA_PREP_FENCE; for (i = 0; i < disks; i++) if (likely(blocks[i])) { BUG_ON(is_raid6_zero_block(blocks[i])); diff --git a/crypto/async_tx/async_raid6_recov.c b/crypto/async_tx/async_raid6_recov.c index 0c14d48c9896..822a42d10061 100644 --- a/crypto/async_tx/async_raid6_recov.c +++ b/crypto/async_tx/async_raid6_recov.c @@ -44,6 +44,8 @@ async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef, struct dma_async_tx_descriptor *tx; enum dma_ctrl_flags dma_flags = DMA_PREP_PQ_DISABLE_P; + if (submit->flags & ASYNC_TX_FENCE) + dma_flags |= DMA_PREP_FENCE; dma_dest[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL); dma_src[0] = dma_map_page(dev, srcs[0], 0, len, DMA_TO_DEVICE); dma_src[1] = dma_map_page(dev, srcs[1], 0, len, DMA_TO_DEVICE); @@ -89,6 +91,8 @@ async_mult(struct page *dest, struct page *src, u8 coef, size_t len, struct dma_async_tx_descriptor *tx; enum dma_ctrl_flags dma_flags = DMA_PREP_PQ_DISABLE_P; + if (submit->flags & ASYNC_TX_FENCE) + dma_flags |= DMA_PREP_FENCE; dma_dest[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL); dma_src[0] = dma_map_page(dev, src, 0, len, DMA_TO_DEVICE); tx = dma->device_prep_dma_pq(chan, dma_dest, dma_src, 1, &coef, @@ -138,7 +142,7 @@ __2data_recov_4(size_t bytes, int faila, int failb, struct page **blocks, srcs[1] = q; coef[0] = raid6_gfexi[failb-faila]; coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]]; - init_async_submit(submit, 0, tx, NULL, NULL, scribble); + init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble); tx = async_sum_product(b, srcs, coef, bytes, submit); /* Dy = P+Pxy+Dx */ @@ -188,23 +192,23 @@ __2data_recov_5(size_t bytes, int faila, int failb, struct page **blocks, dp = blocks[faila]; dq = blocks[failb]; - init_async_submit(submit, 0, tx, NULL, NULL, scribble); + init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble); tx = async_memcpy(dp, g, 0, 0, bytes, submit); - init_async_submit(submit, 0, tx, NULL, NULL, scribble); + init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble); tx = async_mult(dq, g, raid6_gfexp[good], bytes, submit); /* compute P + Pxy */ srcs[0] = dp; srcs[1] = p; - init_async_submit(submit, ASYNC_TX_XOR_DROP_DST, tx, NULL, NULL, - scribble); + init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx, + NULL, NULL, scribble); tx = async_xor(dp, srcs, 0, 2, bytes, submit); /* compute Q + Qxy */ srcs[0] = dq; srcs[1] = q; - init_async_submit(submit, ASYNC_TX_XOR_DROP_DST, tx, NULL, NULL, - scribble); + init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx, + NULL, NULL, scribble); tx = async_xor(dq, srcs, 0, 2, bytes, submit); /* Dx = A*(P+Pxy) + B*(Q+Qxy) */ @@ -212,7 +216,7 @@ __2data_recov_5(size_t bytes, int faila, int failb, struct page **blocks, srcs[1] = dq; coef[0] = raid6_gfexi[failb-faila]; coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]]; - init_async_submit(submit, 0, tx, NULL, NULL, scribble); + init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble); tx = async_sum_product(dq, srcs, coef, bytes, submit); /* Dy = P+Pxy+Dx */ @@ -252,7 +256,7 @@ __2data_recov_n(int disks, size_t bytes, int faila, int failb, blocks[failb] = (void *)raid6_empty_zero_page; blocks[disks-1] = dq; - init_async_submit(submit, 0, tx, NULL, NULL, scribble); + init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble); tx = async_gen_syndrome(blocks, 0, disks, bytes, submit); /* Restore pointer table */ @@ -264,15 +268,15 @@ __2data_recov_n(int disks, size_t bytes, int faila, int failb, /* compute P + Pxy */ srcs[0] = dp; srcs[1] = p; - init_async_submit(submit, ASYNC_TX_XOR_DROP_DST, tx, NULL, NULL, - scribble); + init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx, + NULL, NULL, scribble); tx = async_xor(dp, srcs, 0, 2, bytes, submit); /* compute Q + Qxy */ srcs[0] = dq; srcs[1] = q; - init_async_submit(submit, ASYNC_TX_XOR_DROP_DST, tx, NULL, NULL, - scribble); + init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx, + NULL, NULL, scribble); tx = async_xor(dq, srcs, 0, 2, bytes, submit); /* Dx = A*(P+Pxy) + B*(Q+Qxy) */ @@ -280,7 +284,7 @@ __2data_recov_n(int disks, size_t bytes, int faila, int failb, srcs[1] = dq; coef[0] = raid6_gfexi[failb-faila]; coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]]; - init_async_submit(submit, 0, tx, NULL, NULL, scribble); + init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble); tx = async_sum_product(dq, srcs, coef, bytes, submit); /* Dy = P+Pxy+Dx */ @@ -407,13 +411,16 @@ async_raid6_datap_recov(int disks, size_t bytes, int faila, int good = faila == 0 ? 1 : 0; struct page *g = blocks[good]; - init_async_submit(submit, 0, tx, NULL, NULL, scribble); + init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, + scribble); tx = async_memcpy(p, g, 0, 0, bytes, submit); - init_async_submit(submit, 0, tx, NULL, NULL, scribble); + init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, + scribble); tx = async_mult(dq, g, raid6_gfexp[good], bytes, submit); } else { - init_async_submit(submit, 0, tx, NULL, NULL, scribble); + init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, + scribble); tx = async_gen_syndrome(blocks, 0, disks, bytes, submit); } @@ -426,11 +433,11 @@ async_raid6_datap_recov(int disks, size_t bytes, int faila, srcs[0] = dq; srcs[1] = q; - init_async_submit(submit, ASYNC_TX_XOR_DROP_DST, tx, NULL, NULL, - scribble); + init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx, + NULL, NULL, scribble); tx = async_xor(dq, srcs, 0, 2, bytes, submit); - init_async_submit(submit, 0, tx, NULL, NULL, scribble); + init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble); tx = async_mult(dq, dq, coef, bytes, submit); srcs[0] = p; diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c index 56b5f98da463..db279872ef3d 100644 --- a/crypto/async_tx/async_xor.c +++ b/crypto/async_tx/async_xor.c @@ -69,6 +69,7 @@ do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list, */ if (src_cnt > xor_src_cnt) { submit->flags &= ~ASYNC_TX_ACK; + submit->flags |= ASYNC_TX_FENCE; dma_flags = DMA_COMPL_SKIP_DEST_UNMAP; submit->cb_fn = NULL; submit->cb_param = NULL; @@ -78,7 +79,8 @@ do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list, } if (submit->cb_fn) dma_flags |= DMA_PREP_INTERRUPT; - + if (submit->flags & ASYNC_TX_FENCE) + dma_flags |= DMA_PREP_FENCE; /* Since we have clobbered the src_list we are committed * to doing this asynchronously. Drivers force forward progress * in case they can not provide a descriptor @@ -264,12 +266,15 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset, dma_src = (dma_addr_t *) src_list; if (dma_src && device && src_cnt <= device->max_xor) { - unsigned long dma_prep_flags; + unsigned long dma_prep_flags = 0; int i; pr_debug("%s: (async) len: %zu\n", __func__, len); - dma_prep_flags = submit->cb_fn ? DMA_PREP_INTERRUPT : 0; + if (submit->cb_fn) + dma_prep_flags |= DMA_PREP_INTERRUPT; + if (submit->flags & ASYNC_TX_FENCE) + dma_prep_flags |= DMA_PREP_FENCE; for (i = 0; i < src_cnt; i++) dma_src[i] = dma_map_page(device->dev, src_list[i], offset, len, DMA_TO_DEVICE); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 0a5cf2171214..54ef8d75541d 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -502,13 +502,17 @@ async_copy_data(int frombio, struct bio *bio, struct page *page, int i; int page_offset; struct async_submit_ctl submit; + enum async_tx_flags flags = 0; if (bio->bi_sector >= sector) page_offset = (signed)(bio->bi_sector - sector) * 512; else page_offset = (signed)(sector - bio->bi_sector) * -512; - init_async_submit(&submit, 0, tx, NULL, NULL, NULL); + if (frombio) + flags |= ASYNC_TX_FENCE; + init_async_submit(&submit, flags, tx, NULL, NULL, NULL); + bio_for_each_segment(bvl, bio, i) { int len = bio_iovec_idx(bio, i)->bv_len; int clen; @@ -685,7 +689,7 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu) atomic_inc(&sh->count); - init_async_submit(&submit, ASYNC_TX_XOR_ZERO_DST, NULL, + init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, NULL, ops_complete_compute, sh, to_addr_conv(sh, percpu)); if (unlikely(count == 1)) tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit); @@ -763,7 +767,8 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu) count = set_syndrome_sources(blocks, sh); blocks[count] = NULL; /* regenerating p is not necessary */ BUG_ON(blocks[count+1] != dest); /* q should already be set */ - init_async_submit(&submit, 0, NULL, ops_complete_compute, sh, + init_async_submit(&submit, ASYNC_TX_FENCE, NULL, + ops_complete_compute, sh, to_addr_conv(sh, percpu)); tx = async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit); } else { @@ -775,8 +780,8 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu) blocks[count++] = sh->dev[i].page; } - init_async_submit(&submit, ASYNC_TX_XOR_ZERO_DST, NULL, - ops_complete_compute, sh, + init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, + NULL, ops_complete_compute, sh, to_addr_conv(sh, percpu)); tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE, &submit); } @@ -837,8 +842,9 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu) /* Q disk is one of the missing disks */ if (faila == syndrome_disks) { /* Missing P+Q, just recompute */ - init_async_submit(&submit, 0, NULL, ops_complete_compute, - sh, to_addr_conv(sh, percpu)); + init_async_submit(&submit, ASYNC_TX_FENCE, NULL, + ops_complete_compute, sh, + to_addr_conv(sh, percpu)); return async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit); } else { @@ -859,21 +865,24 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu) blocks[count++] = sh->dev[i].page; } dest = sh->dev[data_target].page; - init_async_submit(&submit, ASYNC_TX_XOR_ZERO_DST, NULL, - NULL, NULL, to_addr_conv(sh, percpu)); + init_async_submit(&submit, + ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, + NULL, NULL, NULL, + to_addr_conv(sh, percpu)); tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE, &submit); count = set_syndrome_sources(blocks, sh); - init_async_submit(&submit, 0, tx, ops_complete_compute, - sh, to_addr_conv(sh, percpu)); + init_async_submit(&submit, ASYNC_TX_FENCE, tx, + ops_complete_compute, sh, + to_addr_conv(sh, percpu)); return async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit); } } - init_async_submit(&submit, 0, NULL, ops_complete_compute, sh, - to_addr_conv(sh, percpu)); + init_async_submit(&submit, ASYNC_TX_FENCE, NULL, ops_complete_compute, + sh, to_addr_conv(sh, percpu)); if (failb == syndrome_disks) { /* We're missing D+P. */ return async_raid6_datap_recov(syndrome_disks+2, STRIPE_SIZE, @@ -916,7 +925,7 @@ ops_run_prexor(struct stripe_head *sh, struct raid5_percpu *percpu, xor_srcs[count++] = dev->page; } - init_async_submit(&submit, ASYNC_TX_XOR_DROP_DST, tx, + init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx, ops_complete_prexor, sh, to_addr_conv(sh, percpu)); tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit); 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 --- crypto/async_tx/async_tx.c | 4 ++++ drivers/dma/Kconfig | 4 ++++ drivers/dma/dmaengine.c | 40 ++++++++++++++++++++++++++++++++++++++++ include/linux/dmaengine.h | 10 +++++++++- 4 files changed, 57 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/crypto/async_tx/async_tx.c b/crypto/async_tx/async_tx.c index 60615fedcf5e..f9cdf04fe7c0 100644 --- a/crypto/async_tx/async_tx.c +++ b/crypto/async_tx/async_tx.c @@ -81,6 +81,10 @@ async_tx_channel_switch(struct dma_async_tx_descriptor *depend_tx, struct dma_device *device = chan->device; struct dma_async_tx_descriptor *intr_tx = (void *) ~0; + #ifdef CONFIG_ASYNC_TX_DISABLE_CHANNEL_SWITCH + BUG(); + #endif + /* first check to see if we can still append to depend_tx */ spin_lock_bh(&depend_tx->lock); if (depend_tx->parent && depend_tx->chan == tx->chan) { diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 912a51b5cbd3..ddcd9793b25c 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -17,11 +17,15 @@ if DMADEVICES comment "DMA Devices" +config ASYNC_TX_DISABLE_CHANNEL_SWITCH + bool + config INTEL_IOATDMA tristate "Intel I/OAT DMA support" depends on PCI && X86 select DMA_ENGINE select DCA + select ASYNC_TX_DISABLE_CHANNEL_SWITCH help Enable support for the Intel(R) I/OAT DMA engine present in recent Intel Xeon chipsets. diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 96598479eece..d5bc628d207c 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -608,6 +608,40 @@ void dmaengine_put(void) } EXPORT_SYMBOL(dmaengine_put); +static bool device_has_all_tx_types(struct dma_device *device) +{ + /* A device that satisfies this test has channels that will never cause + * an async_tx channel switch event as all possible operation types can + * be handled. + */ + #ifdef CONFIG_ASYNC_TX_DMA + if (!dma_has_cap(DMA_INTERRUPT, device->cap_mask)) + return false; + #endif + + #if defined(CONFIG_ASYNC_MEMCPY) || defined(CONFIG_ASYNC_MEMCPY_MODULE) + if (!dma_has_cap(DMA_MEMCPY, device->cap_mask)) + return false; + #endif + + #if defined(CONFIG_ASYNC_MEMSET) || defined(CONFIG_ASYNC_MEMSET_MODULE) + if (!dma_has_cap(DMA_MEMSET, device->cap_mask)) + return false; + #endif + + #if defined(CONFIG_ASYNC_XOR) || defined(CONFIG_ASYNC_XOR_MODULE) + if (!dma_has_cap(DMA_XOR, device->cap_mask)) + return false; + #endif + + #if defined(CONFIG_ASYNC_PQ) || defined(CONFIG_ASYNC_PQ_MODULE) + if (!dma_has_cap(DMA_PQ, device->cap_mask)) + return false; + #endif + + return true; +} + static int get_dma_id(struct dma_device *device) { int rc; @@ -665,6 +699,12 @@ int dma_async_device_register(struct dma_device *device) BUG_ON(!device->device_issue_pending); BUG_ON(!device->dev); + /* note: this only matters in the + * CONFIG_ASYNC_TX_DISABLE_CHANNEL_SWITCH=y case + */ + if (device_has_all_tx_types(device)) + dma_cap_set(DMA_ASYNC_TX, device->cap_mask); + idr_ref = kmalloc(sizeof(*idr_ref), GFP_KERNEL); if (!idr_ref) return -ENOMEM; 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 --- arch/arm/mach-iop13xx/setup.c | 7 ------- arch/arm/plat-iop/adma.c | 2 -- drivers/dma/iop-adma.c | 5 +---- include/linux/dmaengine.h | 3 --- 4 files changed, 1 insertion(+), 16 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-iop13xx/setup.c b/arch/arm/mach-iop13xx/setup.c index faaef95342b6..5c147fb66a01 100644 --- a/arch/arm/mach-iop13xx/setup.c +++ b/arch/arm/mach-iop13xx/setup.c @@ -477,10 +477,8 @@ void __init iop13xx_platform_init(void) plat_data = &iop13xx_adma_0_data; dma_cap_set(DMA_MEMCPY, plat_data->cap_mask); dma_cap_set(DMA_XOR, plat_data->cap_mask); - dma_cap_set(DMA_DUAL_XOR, plat_data->cap_mask); dma_cap_set(DMA_XOR_VAL, plat_data->cap_mask); dma_cap_set(DMA_MEMSET, plat_data->cap_mask); - dma_cap_set(DMA_MEMCPY_CRC32C, plat_data->cap_mask); dma_cap_set(DMA_INTERRUPT, plat_data->cap_mask); break; case IOP13XX_INIT_ADMA_1: @@ -489,10 +487,8 @@ void __init iop13xx_platform_init(void) plat_data = &iop13xx_adma_1_data; dma_cap_set(DMA_MEMCPY, plat_data->cap_mask); dma_cap_set(DMA_XOR, plat_data->cap_mask); - dma_cap_set(DMA_DUAL_XOR, plat_data->cap_mask); dma_cap_set(DMA_XOR_VAL, plat_data->cap_mask); dma_cap_set(DMA_MEMSET, plat_data->cap_mask); - dma_cap_set(DMA_MEMCPY_CRC32C, plat_data->cap_mask); dma_cap_set(DMA_INTERRUPT, plat_data->cap_mask); break; case IOP13XX_INIT_ADMA_2: @@ -501,13 +497,10 @@ void __init iop13xx_platform_init(void) plat_data = &iop13xx_adma_2_data; dma_cap_set(DMA_MEMCPY, plat_data->cap_mask); dma_cap_set(DMA_XOR, plat_data->cap_mask); - dma_cap_set(DMA_DUAL_XOR, plat_data->cap_mask); dma_cap_set(DMA_XOR_VAL, plat_data->cap_mask); dma_cap_set(DMA_MEMSET, plat_data->cap_mask); - dma_cap_set(DMA_MEMCPY_CRC32C, plat_data->cap_mask); dma_cap_set(DMA_INTERRUPT, plat_data->cap_mask); dma_cap_set(DMA_PQ, plat_data->cap_mask); - dma_cap_set(DMA_PQ_UPDATE, plat_data->cap_mask); dma_cap_set(DMA_PQ_VAL, plat_data->cap_mask); break; } diff --git a/arch/arm/plat-iop/adma.c b/arch/arm/plat-iop/adma.c index da1dd0dab07c..1ff6a37e893c 100644 --- a/arch/arm/plat-iop/adma.c +++ b/arch/arm/plat-iop/adma.c @@ -179,7 +179,6 @@ static int __init iop3xx_adma_cap_init(void) dma_cap_set(DMA_INTERRUPT, iop3xx_dma_0_data.cap_mask); #else dma_cap_set(DMA_MEMCPY, iop3xx_dma_0_data.cap_mask); - dma_cap_set(DMA_MEMCPY_CRC32C, iop3xx_dma_0_data.cap_mask); dma_cap_set(DMA_INTERRUPT, iop3xx_dma_0_data.cap_mask); #endif @@ -188,7 +187,6 @@ static int __init iop3xx_adma_cap_init(void) dma_cap_set(DMA_INTERRUPT, iop3xx_dma_1_data.cap_mask); #else dma_cap_set(DMA_MEMCPY, iop3xx_dma_1_data.cap_mask); - dma_cap_set(DMA_MEMCPY_CRC32C, iop3xx_dma_1_data.cap_mask); dma_cap_set(DMA_INTERRUPT, iop3xx_dma_1_data.cap_mask); #endif diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c index 4496bc606662..cecb6d657d55 100644 --- a/drivers/dma/iop-adma.c +++ b/drivers/dma/iop-adma.c @@ -1256,15 +1256,12 @@ static int __devinit iop_adma_probe(struct platform_device *pdev) } dev_printk(KERN_INFO, &pdev->dev, "Intel(R) IOP: " - "( %s%s%s%s%s%s%s%s%s%s)\n", + "( %s%s%s%s%s%s%s)\n", dma_has_cap(DMA_PQ, dma_dev->cap_mask) ? "pq " : "", - dma_has_cap(DMA_PQ_UPDATE, dma_dev->cap_mask) ? "pq_update " : "", dma_has_cap(DMA_PQ_VAL, dma_dev->cap_mask) ? "pq_val " : "", dma_has_cap(DMA_XOR, dma_dev->cap_mask) ? "xor " : "", - dma_has_cap(DMA_DUAL_XOR, dma_dev->cap_mask) ? "dual_xor " : "", dma_has_cap(DMA_XOR_VAL, dma_dev->cap_mask) ? "xor_val " : "", dma_has_cap(DMA_MEMSET, dma_dev->cap_mask) ? "fill " : "", - dma_has_cap(DMA_MEMCPY_CRC32C, dma_dev->cap_mask) ? "cpy+crc " : "", dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask) ? "cpy " : "", dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask) ? "intr " : ""); 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 --- crypto/async_tx/async_memcpy.c | 2 +- crypto/async_tx/async_memset.c | 2 +- crypto/async_tx/async_pq.c | 6 ++++-- crypto/async_tx/async_xor.c | 5 +++-- drivers/dma/dmatest.c | 14 ++++++++++++++ include/linux/dmaengine.h | 44 ++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 67 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/crypto/async_tx/async_memcpy.c b/crypto/async_tx/async_memcpy.c index b38cbb3fd527..0ec1fb69d4ea 100644 --- a/crypto/async_tx/async_memcpy.c +++ b/crypto/async_tx/async_memcpy.c @@ -50,7 +50,7 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset, struct dma_device *device = chan ? chan->device : NULL; struct dma_async_tx_descriptor *tx = NULL; - if (device) { + if (device && is_dma_copy_aligned(device, src_offset, dest_offset, len)) { dma_addr_t dma_dest, dma_src; unsigned long dma_prep_flags = 0; diff --git a/crypto/async_tx/async_memset.c b/crypto/async_tx/async_memset.c index a374784e3329..58e4a8752aee 100644 --- a/crypto/async_tx/async_memset.c +++ b/crypto/async_tx/async_memset.c @@ -47,7 +47,7 @@ async_memset(struct page *dest, int val, unsigned int offset, size_t len, struct dma_device *device = chan ? chan->device : NULL; struct dma_async_tx_descriptor *tx = NULL; - if (device) { + if (device && is_dma_fill_aligned(device, offset, 0, len)) { dma_addr_t dma_dest; unsigned long dma_prep_flags = 0; diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c index a25e290c39fb..b88db6d1dc65 100644 --- a/crypto/async_tx/async_pq.c +++ b/crypto/async_tx/async_pq.c @@ -211,7 +211,8 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks, if (dma_src && device && (src_cnt <= dma_maxpq(device, 0) || - dma_maxpq(device, DMA_PREP_CONTINUE) > 0)) { + dma_maxpq(device, DMA_PREP_CONTINUE) > 0) && + is_dma_pq_aligned(device, offset, 0, len)) { /* run the p+q asynchronously */ pr_debug("%s: (async) disks: %d len: %zu\n", __func__, disks, len); @@ -274,7 +275,8 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks, else if (sizeof(dma_addr_t) <= sizeof(struct page *)) dma_src = (dma_addr_t *) blocks; - if (dma_src && device && disks <= dma_maxpq(device, 0)) { + if (dma_src && device && disks <= dma_maxpq(device, 0) && + is_dma_pq_aligned(device, offset, 0, len)) { struct device *dev = device->dev; dma_addr_t *pq = &dma_src[disks-2]; int i; diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c index db279872ef3d..b459a9034aac 100644 --- a/crypto/async_tx/async_xor.c +++ b/crypto/async_tx/async_xor.c @@ -193,7 +193,7 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset, else if (sizeof(dma_addr_t) <= sizeof(struct page *)) dma_src = (dma_addr_t *) src_list; - if (dma_src && chan) { + if (dma_src && chan && is_dma_xor_aligned(chan->device, offset, 0, len)) { /* run the xor asynchronously */ pr_debug("%s (async): len: %zu\n", __func__, len); @@ -265,7 +265,8 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset, else if (sizeof(dma_addr_t) <= sizeof(struct page *)) dma_src = (dma_addr_t *) src_list; - if (dma_src && device && src_cnt <= device->max_xor) { + if (dma_src && device && src_cnt <= device->max_xor && + is_dma_xor_aligned(device, offset, 0, len)) { unsigned long dma_prep_flags = 0; int i; diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index 58e49e41c7a3..a3722a7384b5 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -288,6 +288,7 @@ static int dmatest_func(void *data) dma_addr_t dma_dsts[dst_cnt]; struct completion cmp; unsigned long tmo = msecs_to_jiffies(3000); + u8 align = 0; total_tests++; @@ -295,6 +296,18 @@ static int dmatest_func(void *data) src_off = dmatest_random() % (test_buf_size - len + 1); dst_off = dmatest_random() % (test_buf_size - len + 1); + /* honor alignment restrictions */ + if (thread->type == DMA_MEMCPY) + align = dev->copy_align; + else if (thread->type == DMA_XOR) + align = dev->xor_align; + else if (thread->type == DMA_PQ) + align = dev->pq_align; + + len = (len >> align) << align; + src_off = (src_off >> align) << align; + dst_off = (dst_off >> align) << align; + dmatest_init_srcs(thread->srcs, src_off, len); dmatest_init_dsts(thread->dsts, dst_off, len); @@ -311,6 +324,7 @@ static int dmatest_func(void *data) DMA_BIDIRECTIONAL); } + if (thread->type == DMA_MEMCPY) tx = dev->device_prep_dma_memcpy(chan, dma_dsts[0] + dst_off, 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 --- drivers/dma/ioat/pci.c | 13 +++++++++++++ include/linux/pci_ids.h | 10 ++++++++++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/drivers/dma/ioat/pci.c b/drivers/dma/ioat/pci.c index 626a508a4f8b..6c1aac5b3598 100644 --- a/drivers/dma/ioat/pci.c +++ b/drivers/dma/ioat/pci.c @@ -58,6 +58,19 @@ static struct pci_device_id ioat_pci_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG5) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG6) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_TBG7) }, + + /* I/OAT v3.2 platforms */ + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF0) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF1) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF2) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF3) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF4) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF5) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF6) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF7) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF8) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_JSF9) }, + { 0, } }; 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 --- drivers/dma/dmaengine.c | 1 - include/linux/dmaengine.h | 3 --- 2 files changed, 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 5a87384ea4ff..562d182eae66 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -933,7 +933,6 @@ void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx, { tx->chan = chan; spin_lock_init(&tx->lock); - INIT_LIST_HEAD(&tx->tx_list); } EXPORT_SYMBOL(dma_async_tx_descriptor_init); 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 --- drivers/dca/dca-core.c | 122 +++++++++++++++++++++++++++++++++++++++++++------ drivers/dma/ioat/pci.c | 2 +- include/linux/dca.h | 11 ++++- 3 files changed, 120 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/dca/dca-core.c b/drivers/dca/dca-core.c index 25b743abfb59..7e318de0904b 100644 --- a/drivers/dca/dca-core.c +++ b/drivers/dca/dca-core.c @@ -28,7 +28,7 @@ #include #include -#define DCA_VERSION "1.8" +#define DCA_VERSION "1.12.1" MODULE_VERSION(DCA_VERSION); MODULE_LICENSE("GPL"); @@ -36,20 +36,92 @@ MODULE_AUTHOR("Intel Corporation"); static DEFINE_SPINLOCK(dca_lock); -static LIST_HEAD(dca_providers); +static LIST_HEAD(dca_domains); -static struct dca_provider *dca_find_provider_by_dev(struct device *dev) +static struct pci_bus *dca_pci_rc_from_dev(struct device *dev) { - struct dca_provider *dca, *ret = NULL; + struct pci_dev *pdev = to_pci_dev(dev); + struct pci_bus *bus = pdev->bus; - list_for_each_entry(dca, &dca_providers, node) { - if ((!dev) || (dca->ops->dev_managed(dca, dev))) { - ret = dca; - break; - } + while (bus->parent) + bus = bus->parent; + + return bus; +} + +static struct dca_domain *dca_allocate_domain(struct pci_bus *rc) +{ + struct dca_domain *domain; + + domain = kzalloc(sizeof(*domain), GFP_NOWAIT); + if (!domain) + return NULL; + + INIT_LIST_HEAD(&domain->dca_providers); + domain->pci_rc = rc; + + return domain; +} + +static void dca_free_domain(struct dca_domain *domain) +{ + list_del(&domain->node); + kfree(domain); +} + +static struct dca_domain *dca_find_domain(struct pci_bus *rc) +{ + struct dca_domain *domain; + + list_for_each_entry(domain, &dca_domains, node) + if (domain->pci_rc == rc) + return domain; + + return NULL; +} + +static struct dca_domain *dca_get_domain(struct device *dev) +{ + struct pci_bus *rc; + struct dca_domain *domain; + + rc = dca_pci_rc_from_dev(dev); + domain = dca_find_domain(rc); + + if (!domain) { + domain = dca_allocate_domain(rc); + if (domain) + list_add(&domain->node, &dca_domains); + } + + return domain; +} + +static struct dca_provider *dca_find_provider_by_dev(struct device *dev) +{ + struct dca_provider *dca; + struct pci_bus *rc; + struct dca_domain *domain; + + if (dev) { + rc = dca_pci_rc_from_dev(dev); + domain = dca_find_domain(rc); + if (!domain) + return NULL; + } else { + if (!list_empty(&dca_domains)) + domain = list_first_entry(&dca_domains, + struct dca_domain, + node); + else + return NULL; } - return ret; + list_for_each_entry(dca, &domain->dca_providers, node) + if ((!dev) || (dca->ops->dev_managed(dca, dev))) + return dca; + + return NULL; } /** @@ -61,6 +133,8 @@ int dca_add_requester(struct device *dev) struct dca_provider *dca; int err, slot = -ENODEV; unsigned long flags; + struct pci_bus *pci_rc; + struct dca_domain *domain; if (!dev) return -EFAULT; @@ -74,7 +148,14 @@ int dca_add_requester(struct device *dev) return -EEXIST; } - list_for_each_entry(dca, &dca_providers, node) { + pci_rc = dca_pci_rc_from_dev(dev); + domain = dca_find_domain(pci_rc); + if (!domain) { + spin_unlock_irqrestore(&dca_lock, flags); + return -ENODEV; + } + + list_for_each_entry(dca, &domain->dca_providers, node) { slot = dca->ops->add_requester(dca, dev); if (slot >= 0) break; @@ -222,13 +303,19 @@ int register_dca_provider(struct dca_provider *dca, struct device *dev) { int err; unsigned long flags; + struct dca_domain *domain; err = dca_sysfs_add_provider(dca, dev); if (err) return err; spin_lock_irqsave(&dca_lock, flags); - list_add(&dca->node, &dca_providers); + domain = dca_get_domain(dev); + if (!domain) { + spin_unlock_irqrestore(&dca_lock, flags); + return -ENODEV; + } + list_add(&dca->node, &domain->dca_providers); spin_unlock_irqrestore(&dca_lock, flags); blocking_notifier_call_chain(&dca_provider_chain, @@ -241,15 +328,24 @@ EXPORT_SYMBOL_GPL(register_dca_provider); * unregister_dca_provider - remove a dca provider * @dca - struct created by alloc_dca_provider() */ -void unregister_dca_provider(struct dca_provider *dca) +void unregister_dca_provider(struct dca_provider *dca, struct device *dev) { unsigned long flags; + struct pci_bus *pci_rc; + struct dca_domain *domain; blocking_notifier_call_chain(&dca_provider_chain, DCA_PROVIDER_REMOVE, NULL); spin_lock_irqsave(&dca_lock, flags); + list_del(&dca->node); + + pci_rc = dca_pci_rc_from_dev(dev); + domain = dca_find_domain(pci_rc); + if (list_empty(&domain->dca_providers)) + dca_free_domain(domain); + spin_unlock_irqrestore(&dca_lock, flags); dca_sysfs_remove_provider(dca); diff --git a/drivers/dma/ioat/pci.c b/drivers/dma/ioat/pci.c index c788fa266470..d545fae30f37 100644 --- a/drivers/dma/ioat/pci.c +++ b/drivers/dma/ioat/pci.c @@ -175,7 +175,7 @@ static void __devexit ioat_remove(struct pci_dev *pdev) dev_err(&pdev->dev, "Removing dma and dca services\n"); if (device->dca) { - unregister_dca_provider(device->dca); + unregister_dca_provider(device->dca, &pdev->dev); free_dca_provider(device->dca); device->dca = NULL; } 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 --- arch/arm/mach-pxa/include/mach/pxafb.h | 3 ++- drivers/video/pxafb.c | 3 +++ include/linux/fb.h | 1 + 3 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/arm/mach-pxa/include/mach/pxafb.h b/arch/arm/mach-pxa/include/mach/pxafb.h index 6932720ba04e..f73061c90b5e 100644 --- a/arch/arm/mach-pxa/include/mach/pxafb.h +++ b/arch/arm/mach-pxa/include/mach/pxafb.h @@ -118,7 +118,8 @@ struct pxafb_mach_info { u_int fixed_modes:1, cmap_inverse:1, cmap_static:1, - unused:29; + acceleration_enabled:1, + unused:28; /* The following should be defined in LCCR0 * LCCR0_Act or LCCR0_Pas Active or Passive diff --git a/drivers/video/pxafb.c b/drivers/video/pxafb.c index 3a002a634ecf..1820c4a24434 100644 --- a/drivers/video/pxafb.c +++ b/drivers/video/pxafb.c @@ -2083,6 +2083,9 @@ static int __devinit pxafb_probe(struct platform_device *dev) goto failed; } + if (cpu_is_pxa3xx() && inf->acceleration_enabled) + fbi->fb.fix.accel = FB_ACCEL_PXA3XX; + fbi->backlight_power = inf->pxafb_backlight_power; fbi->lcd_power = inf->pxafb_lcd_power; 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 ++++++ mm/rmap.c | 4 ++-- 2 files changed, 8 insertions(+), 2 deletions(-) (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) diff --git a/mm/rmap.c b/mm/rmap.c index 0895b5c7cbff..5a35c030e779 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -191,7 +191,7 @@ void __init anon_vma_init(void) * Getting a lock on a stable anon_vma from a page off the LRU is * tricky: page_lock_anon_vma rely on RCU to guard against the races. */ -static struct anon_vma *page_lock_anon_vma(struct page *page) +struct anon_vma *page_lock_anon_vma(struct page *page) { struct anon_vma *anon_vma; unsigned long anon_mapping; @@ -211,7 +211,7 @@ out: return NULL; } -static void page_unlock_anon_vma(struct anon_vma *anon_vma) +void page_unlock_anon_vma(struct anon_vma *anon_vma) { spin_unlock(&anon_vma->lock); rcu_read_unlock(); -- 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 ++++++++++++++++++++++++++++++++++++++ mm/swapfile.c | 4 ++-- 3 files changed, 68 insertions(+), 8 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 diff --git a/mm/swapfile.c b/mm/swapfile.c index 74f1102e8749..ce5dda6d604b 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -699,7 +699,7 @@ int free_swap_and_cache(swp_entry_t entry) struct swap_info_struct *p; struct page *page = NULL; - if (is_migration_entry(entry)) + if (non_swap_entry(entry)) return 1; p = swap_info_get(entry); @@ -2085,7 +2085,7 @@ static int __swap_duplicate(swp_entry_t entry, bool cache) int count; bool has_cache; - if (is_migration_entry(entry)) + if (non_swap_entry(entry)) return -EINVAL; type = swp_type(entry); -- 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 ++- mm/memory.c | 18 +++++++++++++++--- 2 files changed, 17 insertions(+), 4 deletions(-) (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. diff --git a/mm/memory.c b/mm/memory.c index aede2ce3aba4..02bae2d540d4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1319,7 +1319,8 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, if (ret & VM_FAULT_ERROR) { if (ret & VM_FAULT_OOM) return i ? i : -ENOMEM; - else if (ret & VM_FAULT_SIGBUS) + if (ret & + (VM_FAULT_HWPOISON|VM_FAULT_SIGBUS)) return i ? i : -EFAULT; BUG(); } @@ -2511,8 +2512,15 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, goto out; entry = pte_to_swp_entry(orig_pte); - if (is_migration_entry(entry)) { - migration_entry_wait(mm, pmd, address); + if (unlikely(non_swap_entry(entry))) { + if (is_migration_entry(entry)) { + migration_entry_wait(mm, pmd, address); + } else if (is_hwpoison_entry(entry)) { + ret = VM_FAULT_HWPOISON; + } else { + print_bad_pte(vma, address, orig_pte, NULL); + ret = VM_FAULT_OOM; + } goto out; } delayacct_set_flag(DELAYACCT_PF_SWAPIN); @@ -2536,6 +2544,10 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Had to read the page from swap area: Major fault */ ret = VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); + } else if (PageHWPoison(page)) { + ret = VM_FAULT_HWPOISON; + delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + goto out; } lock_page(page); -- 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 ++++++++++++- mm/migrate.c | 2 +- mm/rmap.c | 40 ++++++++++++++++++++++------------------ mm/vmscan.c | 2 +- 4 files changed, 36 insertions(+), 21 deletions(-) (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 diff --git a/mm/migrate.c b/mm/migrate.c index 939888f9ddab..e3a0cd3859a9 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -669,7 +669,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, } /* Establish migration ptes or remove ptes */ - try_to_unmap(page, 1); + try_to_unmap(page, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS); if (!page_mapped(page)) rc = move_to_new_page(newpage, page); diff --git a/mm/rmap.c b/mm/rmap.c index 5a35c030e779..08c112a776a7 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -774,7 +774,7 @@ void page_remove_rmap(struct page *page) * repeatedly from either try_to_unmap_anon or try_to_unmap_file. */ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, - int migration) + enum ttu_flags flags) { struct mm_struct *mm = vma->vm_mm; unsigned long address; @@ -796,11 +796,13 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * If it's recently referenced (perhaps page_referenced * skipped over this mm) then we should reactivate it. */ - if (!migration) { + if (!(flags & TTU_IGNORE_MLOCK)) { if (vma->vm_flags & VM_LOCKED) { ret = SWAP_MLOCK; goto out_unmap; } + } + if (!(flags & TTU_IGNORE_ACCESS)) { if (ptep_clear_flush_young_notify(vma, address, pte)) { ret = SWAP_FAIL; goto out_unmap; @@ -840,12 +842,12 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ - BUG_ON(!migration); + BUG_ON(TTU_ACTION(flags) != TTU_MIGRATION); entry = make_migration_entry(page, pte_write(pteval)); } set_pte_at(mm, address, pte, swp_entry_to_pte(entry)); BUG_ON(pte_file(*pte)); - } else if (PAGE_MIGRATION && migration) { + } else if (PAGE_MIGRATION && (TTU_ACTION(flags) == TTU_MIGRATION)) { /* Establish migration entry for a file page */ swp_entry_t entry; entry = make_migration_entry(page, pte_write(pteval)); @@ -1014,12 +1016,13 @@ static int try_to_mlock_page(struct page *page, struct vm_area_struct *vma) * vm_flags for that VMA. That should be OK, because that vma shouldn't be * 'LOCKED. */ -static int try_to_unmap_anon(struct page *page, int unlock, int migration) +static int try_to_unmap_anon(struct page *page, enum ttu_flags flags) { struct anon_vma *anon_vma; struct vm_area_struct *vma; unsigned int mlocked = 0; int ret = SWAP_AGAIN; + int unlock = TTU_ACTION(flags) == TTU_MUNLOCK; if (MLOCK_PAGES && unlikely(unlock)) ret = SWAP_SUCCESS; /* default for try_to_munlock() */ @@ -1035,7 +1038,7 @@ static int try_to_unmap_anon(struct page *page, int unlock, int migration) continue; /* must visit all unlocked vmas */ ret = SWAP_MLOCK; /* saw at least one mlocked vma */ } else { - ret = try_to_unmap_one(page, vma, migration); + ret = try_to_unmap_one(page, vma, flags); if (ret == SWAP_FAIL || !page_mapped(page)) break; } @@ -1059,8 +1062,7 @@ static int try_to_unmap_anon(struct page *page, int unlock, int migration) /** * try_to_unmap_file - unmap/unlock file page using the object-based rmap method * @page: the page to unmap/unlock - * @unlock: request for unlock rather than unmap [unlikely] - * @migration: unmapping for migration - ignored if @unlock + * @flags: action and flags * * Find all the mappings of a page using the mapping pointer and the vma chains * contained in the address_space struct it points to. @@ -1072,7 +1074,7 @@ static int try_to_unmap_anon(struct page *page, int unlock, int migration) * vm_flags for that VMA. That should be OK, because that vma shouldn't be * 'LOCKED. */ -static int try_to_unmap_file(struct page *page, int unlock, int migration) +static int try_to_unmap_file(struct page *page, enum ttu_flags flags) { struct address_space *mapping = page->mapping; pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); @@ -1084,6 +1086,7 @@ static int try_to_unmap_file(struct page *page, int unlock, int migration) unsigned long max_nl_size = 0; unsigned int mapcount; unsigned int mlocked = 0; + int unlock = TTU_ACTION(flags) == TTU_MUNLOCK; if (MLOCK_PAGES && unlikely(unlock)) ret = SWAP_SUCCESS; /* default for try_to_munlock() */ @@ -1096,7 +1099,7 @@ static int try_to_unmap_file(struct page *page, int unlock, int migration) continue; /* must visit all vmas */ ret = SWAP_MLOCK; } else { - ret = try_to_unmap_one(page, vma, migration); + ret = try_to_unmap_one(page, vma, flags); if (ret == SWAP_FAIL || !page_mapped(page)) goto out; } @@ -1121,7 +1124,8 @@ static int try_to_unmap_file(struct page *page, int unlock, int migration) ret = SWAP_MLOCK; /* leave mlocked == 0 */ goto out; /* no need to look further */ } - if (!MLOCK_PAGES && !migration && (vma->vm_flags & VM_LOCKED)) + if (!MLOCK_PAGES && !(flags & TTU_IGNORE_MLOCK) && + (vma->vm_flags & VM_LOCKED)) continue; cursor = (unsigned long) vma->vm_private_data; if (cursor > max_nl_cursor) @@ -1155,7 +1159,7 @@ static int try_to_unmap_file(struct page *page, int unlock, int migration) do { list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list) { - if (!MLOCK_PAGES && !migration && + if (!MLOCK_PAGES && !(flags & TTU_IGNORE_MLOCK) && (vma->vm_flags & VM_LOCKED)) continue; cursor = (unsigned long) vma->vm_private_data; @@ -1195,7 +1199,7 @@ out: /** * try_to_unmap - try to remove all page table mappings to a page * @page: the page to get unmapped - * @migration: migration flag + * @flags: action and flags * * Tries to remove all the page table entries which are mapping this * page, used in the pageout path. Caller must hold the page lock. @@ -1206,16 +1210,16 @@ out: * SWAP_FAIL - the page is unswappable * SWAP_MLOCK - page is mlocked. */ -int try_to_unmap(struct page *page, int migration) +int try_to_unmap(struct page *page, enum ttu_flags flags) { int ret; BUG_ON(!PageLocked(page)); if (PageAnon(page)) - ret = try_to_unmap_anon(page, 0, migration); + ret = try_to_unmap_anon(page, flags); else - ret = try_to_unmap_file(page, 0, migration); + ret = try_to_unmap_file(page, flags); if (ret != SWAP_MLOCK && !page_mapped(page)) ret = SWAP_SUCCESS; return ret; @@ -1240,8 +1244,8 @@ int try_to_munlock(struct page *page) VM_BUG_ON(!PageLocked(page) || PageLRU(page)); if (PageAnon(page)) - return try_to_unmap_anon(page, 1, 0); + return try_to_unmap_anon(page, TTU_MUNLOCK); else - return try_to_unmap_file(page, 1, 0); + return try_to_unmap_file(page, TTU_MUNLOCK); } diff --git a/mm/vmscan.c b/mm/vmscan.c index ba8228e0a806..ab3b0ad3ce52 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -659,7 +659,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, * processes. Try to unmap it here. */ if (page_mapped(page) && mapping) { - switch (try_to_unmap(page, 0)) { + switch (try_to_unmap(page, TTU_UNMAP)) { case SWAP_FAIL: goto activate_locked; case SWAP_AGAIN: -- 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 + mm/rmap.c | 9 ++++++++- 2 files changed, 9 insertions(+), 1 deletion(-) (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) diff --git a/mm/rmap.c b/mm/rmap.c index 08c112a776a7..7e72ca19d68b 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -820,7 +820,14 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, /* Update high watermark before we lower rss */ update_hiwater_rss(mm); - if (PageAnon(page)) { + if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) { + if (PageAnon(page)) + dec_mm_counter(mm, anon_rss); + else + dec_mm_counter(mm, file_rss); + set_pte_at(mm, address, pte, + swp_entry_to_pte(make_hwpoison_entry(page))); + } else if (PageAnon(page)) { swp_entry_t entry = { .val = page_private(page) }; if (PageSwapCache(page)) { -- 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 ++ mm/truncate.c | 29 +++++++++++++++-------------- 2 files changed, 17 insertions(+), 14 deletions(-) (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); diff --git a/mm/truncate.c b/mm/truncate.c index ccc3ecf7cb98..2519a7c92873 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -93,11 +93,11 @@ EXPORT_SYMBOL(cancel_dirty_page); * its lock, b) when a concurrent invalidate_mapping_pages got there first and * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space. */ -static void +static int truncate_complete_page(struct address_space *mapping, struct page *page) { if (page->mapping != mapping) - return; + return -EIO; if (page_has_private(page)) do_invalidatepage(page, 0); @@ -108,6 +108,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page) remove_from_page_cache(page); ClearPageMappedToDisk(page); page_cache_release(page); /* pagecache ref */ + return 0; } /* @@ -135,6 +136,16 @@ invalidate_complete_page(struct address_space *mapping, struct page *page) return ret; } +int truncate_inode_page(struct address_space *mapping, struct page *page) +{ + if (page_mapped(page)) { + unmap_mapping_range(mapping, + (loff_t)page->index << PAGE_CACHE_SHIFT, + PAGE_CACHE_SIZE, 0); + } + return truncate_complete_page(mapping, page); +} + /** * truncate_inode_pages - truncate range of pages specified by start & end byte offsets * @mapping: mapping to truncate @@ -196,12 +207,7 @@ void truncate_inode_pages_range(struct address_space *mapping, unlock_page(page); continue; } - if (page_mapped(page)) { - unmap_mapping_range(mapping, - (loff_t)page_index<index<index > next) next = page->index; next++; - truncate_complete_page(mapping, page); unlock_page(page); } pagevec_release(&pvec); -- 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 ++ mm/truncate.c | 26 ++++++++++++++++++++------ 2 files changed, 22 insertions(+), 6 deletions(-) (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); diff --git a/mm/truncate.c b/mm/truncate.c index 2519a7c92873..ea132f7ea2d2 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -146,6 +146,24 @@ int truncate_inode_page(struct address_space *mapping, struct page *page) return truncate_complete_page(mapping, page); } +/* + * Safely invalidate one page from its pagecache mapping. + * It only drops clean, unused pages. The page must be locked. + * + * Returns 1 if the page is successfully invalidated, otherwise 0. + */ +int invalidate_inode_page(struct page *page) +{ + struct address_space *mapping = page_mapping(page); + if (!mapping) + return 0; + if (PageDirty(page) || PageWriteback(page)) + return 0; + if (page_mapped(page)) + return 0; + return invalidate_complete_page(mapping, page); +} + /** * truncate_inode_pages - truncate range of pages specified by start & end byte offsets * @mapping: mapping to truncate @@ -312,12 +330,8 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, if (lock_failed) continue; - if (PageDirty(page) || PageWriteback(page)) - goto unlock; - if (page_mapped(page)) - goto unlock; - ret += invalidate_complete_page(mapping, page); -unlock: + ret += invalidate_inode_page(page); + unlock_page(page); if (next > end) break; -- 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 --- Documentation/filesystems/vfs.txt | 7 +++++++ include/linux/fs.h | 1 + include/linux/mm.h | 1 + mm/truncate.c | 17 +++++++++++++++++ 4 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index f49eecf2e573..623f094c9d8d 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -536,6 +536,7 @@ struct address_space_operations { /* migrate the contents of a page to the specified target */ int (*migratepage) (struct page *, struct page *); int (*launder_page) (struct page *); + int (*error_remove_page) (struct mapping *mapping, struct page *page); }; writepage: called by the VM to write a dirty page to backing store. @@ -694,6 +695,12 @@ struct address_space_operations { prevent redirtying the page, it is kept locked during the whole operation. + error_remove_page: normally set to generic_error_remove_page if truncation + is ok for this address space. Used for memory failure handling. + Setting this implies you deal with pages going away under you, + unless you have them locked or reference counts increased. + + The File Object =============== 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); diff --git a/mm/truncate.c b/mm/truncate.c index ea132f7ea2d2..a17b3977cfdf 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -146,6 +146,23 @@ int truncate_inode_page(struct address_space *mapping, struct page *page) return truncate_complete_page(mapping, page); } +/* + * Used to get rid of pages on hardware memory corruption. + */ +int generic_error_remove_page(struct address_space *mapping, struct page *page) +{ + if (!mapping) + return -EINVAL; + /* + * Only punch for normal data pages for now. + * Handling other types like directories would need more auditing. + */ + if (!S_ISREG(mapping->host->i_mode)) + return -EIO; + return truncate_inode_page(mapping, page); +} +EXPORT_SYMBOL(generic_error_remove_page); + /* * Safely invalidate one page from its pagecache mapping. * It only drops clean, unused pages. The page must be locked. -- 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 ++ kernel/sys.c | 22 ++++++++++++++++++++++ 3 files changed, 26 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 */ diff --git a/kernel/sys.c b/kernel/sys.c index b3f1097c76fa..41e02eff3398 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1528,6 +1528,28 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, current->timer_slack_ns = arg2; error = 0; break; + case PR_MCE_KILL: + if (arg4 | arg5) + return -EINVAL; + switch (arg2) { + case 0: + if (arg3 != 0) + return -EINVAL; + current->flags &= ~PF_MCE_PROCESS; + break; + case 1: + current->flags |= PF_MCE_PROCESS; + if (arg3 != 0) + current->flags |= PF_MCE_EARLY; + else + current->flags &= ~PF_MCE_EARLY; + break; + default: + return -EINVAL; + } + error = 0; + break; + default: error = -EINVAL; break; -- 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 --- Documentation/sysctl/vm.txt | 41 ++- fs/proc/meminfo.c | 9 +- include/linux/mm.h | 7 + include/linux/rmap.h | 1 + kernel/sysctl.c | 25 ++ mm/Kconfig | 10 + mm/Makefile | 1 + mm/filemap.c | 4 + mm/memory-failure.c | 832 ++++++++++++++++++++++++++++++++++++++++++++ mm/rmap.c | 7 +- 10 files changed, 934 insertions(+), 3 deletions(-) create mode 100644 mm/memory-failure.c (limited to 'include/linux') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index c4de6359d440..faf62740aa2c 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -32,6 +32,8 @@ Currently, these files are in /proc/sys/vm: - legacy_va_layout - lowmem_reserve_ratio - max_map_count +- memory_failure_early_kill +- memory_failure_recovery - min_free_kbytes - min_slab_ratio - min_unmapped_ratio @@ -53,7 +55,6 @@ Currently, these files are in /proc/sys/vm: - vfs_cache_pressure - zone_reclaim_mode - ============================================================== block_dump @@ -275,6 +276,44 @@ e.g., up to one or two maps per allocation. The default value is 65536. +============================================================= + +memory_failure_early_kill: + +Control how to kill processes when uncorrected memory error (typically +a 2bit error in a memory module) is detected in the background by hardware +that cannot be handled by the kernel. In some cases (like the page +still having a valid copy on disk) the kernel will handle the failure +transparently without affecting any applications. But if there is +no other uptodate copy of the data it will kill to prevent any data +corruptions from propagating. + +1: Kill all processes that have the corrupted and not reloadable page mapped +as soon as the corruption is detected. Note this is not supported +for a few types of pages, like kernel internally allocated data or +the swap cache, but works for the majority of user pages. + +0: Only unmap the corrupted page from all processes and only kill a process +who tries to access it. + +The kill is done using a catchable SIGBUS with BUS_MCEERR_AO, so processes can +handle this if they want to. + +This is only active on architectures/platforms with advanced machine +check handling and depends on the hardware capabilities. + +Applications can override this setting individually with the PR_MCE_KILL prctl + +============================================================== + +memory_failure_recovery + +Enable memory failure recovery (when supported by the platform) + +1: Attempt recovery. + +0: Always panic on a memory failure. + ============================================================== min_free_kbytes: diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index d5c410d47fae..78faedcb0a8d 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -95,7 +95,11 @@ static int meminfo_proc_show(struct seq_file *m, void *v) "Committed_AS: %8lu kB\n" "VmallocTotal: %8lu kB\n" "VmallocUsed: %8lu kB\n" - "VmallocChunk: %8lu kB\n", + "VmallocChunk: %8lu kB\n" +#ifdef CONFIG_MEMORY_FAILURE + "HardwareCorrupted: %8lu kB\n" +#endif + , K(i.totalram), K(i.freeram), K(i.bufferram), @@ -140,6 +144,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v) (unsigned long)VMALLOC_TOTAL >> 10, vmi.used >> 10, vmi.largest_chunk >> 10 +#ifdef CONFIG_MEMORY_FAILURE + ,atomic_long_read(&mce_bad_pages) << (PAGE_SHIFT - 10) +#endif ); hugetlb_report_meminfo(m); 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 */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6bb59f707402..eacae77ac9fc 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1372,6 +1372,31 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = &scan_unevictable_handler, }, +#ifdef CONFIG_MEMORY_FAILURE + { + .ctl_name = CTL_UNNUMBERED, + .procname = "memory_failure_early_kill", + .data = &sysctl_memory_failure_early_kill, + .maxlen = sizeof(sysctl_memory_failure_early_kill), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &zero, + .extra2 = &one, + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "memory_failure_recovery", + .data = &sysctl_memory_failure_recovery, + .maxlen = sizeof(sysctl_memory_failure_recovery), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &zero, + .extra2 = &one, + }, +#endif + /* * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt diff --git a/mm/Kconfig b/mm/Kconfig index 3aa519f52e18..ea2d8b61c631 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -233,6 +233,16 @@ config DEFAULT_MMAP_MIN_ADDR /proc/sys/vm/mmap_min_addr tunable. +config MEMORY_FAILURE + depends on MMU + depends on X86_MCE + bool "Enable recovery from hardware memory errors" + help + Enables code to recover from some memory failures on systems + with MCA recovery. This allows a system to continue running + even when some of its memory has uncorrected errors. This requires + special hardware support and typically ECC memory. + config NOMMU_INITIAL_TRIM_EXCESS int "Turn on mmap() excess space trimming before booting" depends on !MMU diff --git a/mm/Makefile b/mm/Makefile index ea4b18bd3960..dc2551e7d006 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -40,5 +40,6 @@ obj-$(CONFIG_SMP) += allocpercpu.o endif obj-$(CONFIG_QUICKLIST) += quicklist.o obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o +obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o diff --git a/mm/filemap.c b/mm/filemap.c index dd51c68e2b86..75575c392167 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -104,6 +104,10 @@ * * ->task->proc_lock * ->dcache_lock (proc_pid_lookup) + * + * (code doesn't rely on that order, so you could switch it around) + * ->tasklist_lock (memory_failure, collect_procs_ao) + * ->i_mmap_lock */ /* diff --git a/mm/memory-failure.c b/mm/memory-failure.c new file mode 100644 index 000000000000..729d4b15b645 --- /dev/null +++ b/mm/memory-failure.c @@ -0,0 +1,832 @@ +/* + * Copyright (C) 2008, 2009 Intel Corporation + * Authors: Andi Kleen, Fengguang Wu + * + * This software may be redistributed and/or modified under the terms of + * the GNU General Public License ("GPL") version 2 only as published by the + * Free Software Foundation. + * + * High level machine check handler. Handles pages reported by the + * hardware as being corrupted usually due to a 2bit ECC memory or cache + * failure. + * + * 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. + * + * The operation to map back from RMAP chains to processes has to walk + * the complete process list and has non linear complexity with the number + * mappings. In short it can be quite slow. But since memory corruptions + * are rare we hope to get away with this. + */ + +/* + * Notebook: + * - hugetlb needs more code + * - kcore/oldmem/vmcore/mem/kmem check for hwpoison pages + * - pass bad pages to kdump next kernel + */ +#define DEBUG 1 /* remove me in 2.6.34 */ +#include +#include +#include +#include +#include +#include +#include +#include +#include "internal.h" + +int sysctl_memory_failure_early_kill __read_mostly = 0; + +int sysctl_memory_failure_recovery __read_mostly = 1; + +atomic_long_t mce_bad_pages __read_mostly = ATOMIC_LONG_INIT(0); + +/* + * Send all the processes who have the page mapped an ``action optional'' + * signal. + */ +static int kill_proc_ao(struct task_struct *t, unsigned long addr, int trapno, + unsigned long pfn) +{ + struct siginfo si; + int ret; + + printk(KERN_ERR + "MCE %#lx: Killing %s:%d early due to hardware memory corruption\n", + pfn, t->comm, t->pid); + si.si_signo = SIGBUS; + si.si_errno = 0; + si.si_code = BUS_MCEERR_AO; + si.si_addr = (void *)addr; +#ifdef __ARCH_SI_TRAPNO + si.si_trapno = trapno; +#endif + si.si_addr_lsb = PAGE_SHIFT; + /* + * Don't use force here, it's convenient if the signal + * can be temporarily blocked. + * This could cause a loop when the user sets SIGBUS + * to SIG_IGN, but hopefully noone will do that? + */ + ret = send_sig_info(SIGBUS, &si, t); /* synchronous? */ + if (ret < 0) + printk(KERN_INFO "MCE: Error sending signal to %s:%d: %d\n", + t->comm, t->pid, ret); + return ret; +} + +/* + * Kill all processes that have a poisoned page mapped and then isolate + * the page. + * + * General strategy: + * Find all processes having the page mapped and kill them. + * But we keep a page reference around so that the page is not + * actually freed yet. + * Then stash the page away + * + * There's no convenient way to get back to mapped processes + * from the VMAs. So do a brute-force search over all + * running processes. + * + * Remember that machine checks are not common (or rather + * if they are common you have other problems), so this shouldn't + * be a performance issue. + * + * Also there are some races possible while we get from the + * error detection to actually handle it. + */ + +struct to_kill { + struct list_head nd; + struct task_struct *tsk; + unsigned long addr; + unsigned addr_valid:1; +}; + +/* + * Failure handling: if we can't find or can't kill a process there's + * not much we can do. We just print a message and ignore otherwise. + */ + +/* + * Schedule a process for later kill. + * Uses GFP_ATOMIC allocations to avoid potential recursions in the VM. + * TBD would GFP_NOIO be enough? + */ +static void add_to_kill(struct task_struct *tsk, struct page *p, + struct vm_area_struct *vma, + struct list_head *to_kill, + struct to_kill **tkc) +{ + struct to_kill *tk; + + if (*tkc) { + tk = *tkc; + *tkc = NULL; + } else { + tk = kmalloc(sizeof(struct to_kill), GFP_ATOMIC); + if (!tk) { + printk(KERN_ERR + "MCE: Out of memory while machine check handling\n"); + return; + } + } + tk->addr = page_address_in_vma(p, vma); + tk->addr_valid = 1; + + /* + * In theory we don't have to kill when the page was + * munmaped. But it could be also a mremap. Since that's + * likely very rare kill anyways just out of paranoia, but use + * a SIGKILL because the error is not contained anymore. + */ + if (tk->addr == -EFAULT) { + pr_debug("MCE: Unable to find user space address %lx in %s\n", + page_to_pfn(p), tsk->comm); + tk->addr_valid = 0; + } + get_task_struct(tsk); + tk->tsk = tsk; + list_add_tail(&tk->nd, to_kill); +} + +/* + * Kill the processes that have been collected earlier. + * + * Only do anything when DOIT is set, otherwise just free the list + * (this is used for clean pages which do not need killing) + * Also when FAIL is set do a force kill because something went + * wrong earlier. + */ +static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno, + int fail, unsigned long pfn) +{ + struct to_kill *tk, *next; + + list_for_each_entry_safe (tk, next, to_kill, nd) { + if (doit) { + /* + * In case something went wrong with munmaping + * make sure the process doesn't catch the + * signal and then access the memory. Just kill it. + * the signal handlers + */ + if (fail || tk->addr_valid == 0) { + printk(KERN_ERR + "MCE %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", + pfn, tk->tsk->comm, tk->tsk->pid); + force_sig(SIGKILL, tk->tsk); + } + + /* + * In theory the process could have mapped + * something else on the address in-between. We could + * check for that, but we need to tell the + * process anyways. + */ + else if (kill_proc_ao(tk->tsk, tk->addr, trapno, + pfn) < 0) + printk(KERN_ERR + "MCE %#lx: Cannot send advisory machine check signal to %s:%d\n", + pfn, tk->tsk->comm, tk->tsk->pid); + } + put_task_struct(tk->tsk); + kfree(tk); + } +} + +static int task_early_kill(struct task_struct *tsk) +{ + if (!tsk->mm) + return 0; + if (tsk->flags & PF_MCE_PROCESS) + return !!(tsk->flags & PF_MCE_EARLY); + return sysctl_memory_failure_early_kill; +} + +/* + * Collect processes when the error hit an anonymous page. + */ +static void collect_procs_anon(struct page *page, struct list_head *to_kill, + struct to_kill **tkc) +{ + struct vm_area_struct *vma; + struct task_struct *tsk; + struct anon_vma *av; + + read_lock(&tasklist_lock); + av = page_lock_anon_vma(page); + if (av == NULL) /* Not actually mapped anymore */ + goto out; + for_each_process (tsk) { + if (!task_early_kill(tsk)) + continue; + list_for_each_entry (vma, &av->head, anon_vma_node) { + if (!page_mapped_in_vma(page, vma)) + continue; + if (vma->vm_mm == tsk->mm) + add_to_kill(tsk, page, vma, to_kill, tkc); + } + } + page_unlock_anon_vma(av); +out: + read_unlock(&tasklist_lock); +} + +/* + * Collect processes when the error hit a file mapped page. + */ +static void collect_procs_file(struct page *page, struct list_head *to_kill, + struct to_kill **tkc) +{ + struct vm_area_struct *vma; + struct task_struct *tsk; + struct prio_tree_iter iter; + struct address_space *mapping = page->mapping; + + /* + * A note on the locking order between the two locks. + * We don't rely on this particular order. + * If you have some other code that needs a different order + * feel free to switch them around. Or add a reverse link + * from mm_struct to task_struct, then this could be all + * done without taking tasklist_lock and looping over all tasks. + */ + + read_lock(&tasklist_lock); + spin_lock(&mapping->i_mmap_lock); + for_each_process(tsk) { + pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + + if (!task_early_kill(tsk)) + continue; + + vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, + pgoff) { + /* + * Send early kill signal to tasks where a vma covers + * the page but the corrupted page is not necessarily + * mapped it in its pte. + * Assume applications who requested early kill want + * to be informed of all such data corruptions. + */ + if (vma->vm_mm == tsk->mm) + add_to_kill(tsk, page, vma, to_kill, tkc); + } + } + spin_unlock(&mapping->i_mmap_lock); + read_unlock(&tasklist_lock); +} + +/* + * Collect the processes who have the corrupted page mapped to kill. + * This is done in two steps for locking reasons. + * First preallocate one tokill structure outside the spin locks, + * so that we can kill at least one process reasonably reliable. + */ +static void collect_procs(struct page *page, struct list_head *tokill) +{ + struct to_kill *tk; + + if (!page->mapping) + return; + + tk = kmalloc(sizeof(struct to_kill), GFP_NOIO); + if (!tk) + return; + if (PageAnon(page)) + collect_procs_anon(page, tokill, &tk); + else + collect_procs_file(page, tokill, &tk); + kfree(tk); +} + +/* + * Error handlers for various types of pages. + */ + +enum outcome { + FAILED, /* Error handling failed */ + DELAYED, /* Will be handled later */ + IGNORED, /* Error safely ignored */ + RECOVERED, /* Successfully recovered */ +}; + +static const char *action_name[] = { + [FAILED] = "Failed", + [DELAYED] = "Delayed", + [IGNORED] = "Ignored", + [RECOVERED] = "Recovered", +}; + +/* + * Error hit kernel page. + * Do nothing, try to be lucky and not touch this instead. For a few cases we + * could be more sophisticated. + */ +static int me_kernel(struct page *p, unsigned long pfn) +{ + return DELAYED; +} + +/* + * Already poisoned page. + */ +static int me_ignore(struct page *p, unsigned long pfn) +{ + return IGNORED; +} + +/* + * Page in unknown state. Do nothing. + */ +static int me_unknown(struct page *p, unsigned long pfn) +{ + printk(KERN_ERR "MCE %#lx: Unknown page state\n", pfn); + return FAILED; +} + +/* + * Free memory + */ +static int me_free(struct page *p, unsigned long pfn) +{ + return DELAYED; +} + +/* + * Clean (or cleaned) page cache page. + */ +static int me_pagecache_clean(struct page *p, unsigned long pfn) +{ + int err; + int ret = FAILED; + struct address_space *mapping; + + if (!isolate_lru_page(p)) + page_cache_release(p); + + /* + * For anonymous pages we're done the only reference left + * should be the one m_f() holds. + */ + if (PageAnon(p)) + return RECOVERED; + + /* + * Now truncate the page in the page cache. This is really + * more like a "temporary hole punch" + * Don't do this for block devices when someone else + * has a reference, because it could be file system metadata + * and that's not safe to truncate. + */ + mapping = page_mapping(p); + if (!mapping) { + /* + * Page has been teared down in the meanwhile + */ + return FAILED; + } + + /* + * Truncation is a bit tricky. Enable it per file system for now. + * + * Open: to take i_mutex or not for this? Right now we don't. + */ + if (mapping->a_ops->error_remove_page) { + err = mapping->a_ops->error_remove_page(mapping, p); + if (err != 0) { + printk(KERN_INFO "MCE %#lx: Failed to punch page: %d\n", + pfn, err); + } else if (page_has_private(p) && + !try_to_release_page(p, GFP_NOIO)) { + pr_debug("MCE %#lx: failed to release buffers\n", pfn); + } else { + ret = RECOVERED; + } + } else { + /* + * If the file system doesn't support it just invalidate + * This fails on dirty or anything with private pages + */ + if (invalidate_inode_page(p)) + ret = RECOVERED; + else + printk(KERN_INFO "MCE %#lx: Failed to invalidate\n", + pfn); + } + return ret; +} + +/* + * Dirty cache page page + * Issues: when the error hit a hole page the error is not properly + * propagated. + */ +static int me_pagecache_dirty(struct page *p, unsigned long pfn) +{ + struct address_space *mapping = page_mapping(p); + + SetPageError(p); + /* TBD: print more information about the file. */ + if (mapping) { + /* + * IO error will be reported by write(), fsync(), etc. + * who check the mapping. + * This way the application knows that something went + * wrong with its dirty file data. + * + * There's one open issue: + * + * The EIO will be only reported on the next IO + * operation and then cleared through the IO map. + * Normally Linux has two mechanisms to pass IO error + * first through the AS_EIO flag in the address space + * and then through the PageError flag in the page. + * Since we drop pages on memory failure handling the + * only mechanism open to use is through AS_AIO. + * + * This has the disadvantage that it gets cleared on + * the first operation that returns an error, while + * the PageError bit is more sticky and only cleared + * when the page is reread or dropped. If an + * application assumes it will always get error on + * fsync, but does other operations on the fd before + * and the page is dropped inbetween then the error + * will not be properly reported. + * + * This can already happen even without hwpoisoned + * pages: first on metadata IO errors (which only + * report through AS_EIO) or when the page is dropped + * at the wrong time. + * + * So right now we assume that the application DTRT on + * the first EIO, but we're not worse than other parts + * of the kernel. + */ + mapping_set_error(mapping, EIO); + } + + return me_pagecache_clean(p, pfn); +} + +/* + * Clean and dirty swap cache. + * + * Dirty swap cache page is tricky to handle. The page could live both in page + * cache and swap cache(ie. page is freshly swapped in). So it could be + * referenced concurrently by 2 types of PTEs: + * normal PTEs and swap PTEs. We try to handle them consistently by calling + * try_to_unmap(TTU_IGNORE_HWPOISON) to convert the normal PTEs to swap PTEs, + * and then + * - clear dirty bit to prevent IO + * - remove from LRU + * - but keep in the swap cache, so that when we return to it on + * a later page fault, we know the application is accessing + * corrupted data and shall be killed (we installed simple + * interception code in do_swap_page to catch it). + * + * Clean swap cache pages can be directly isolated. A later page fault will + * bring in the known good data from disk. + */ +static int me_swapcache_dirty(struct page *p, unsigned long pfn) +{ + int ret = FAILED; + + ClearPageDirty(p); + /* Trigger EIO in shmem: */ + ClearPageUptodate(p); + + if (!isolate_lru_page(p)) { + page_cache_release(p); + ret = DELAYED; + } + + return ret; +} + +static int me_swapcache_clean(struct page *p, unsigned long pfn) +{ + int ret = FAILED; + + if (!isolate_lru_page(p)) { + page_cache_release(p); + ret = RECOVERED; + } + delete_from_swap_cache(p); + return ret; +} + +/* + * Huge pages. Needs work. + * Issues: + * No rmap support so we cannot find the original mapper. In theory could walk + * all MMs and look for the mappings, but that would be non atomic and racy. + * Need rmap for hugepages for this. Alternatively we could employ a heuristic, + * like just walking the current process and hoping it has it mapped (that + * should be usually true for the common "shared database cache" case) + * Should handle free huge pages and dequeue them too, but this needs to + * handle huge page accounting correctly. + */ +static int me_huge_page(struct page *p, unsigned long pfn) +{ + return FAILED; +} + +/* + * Various page states we can handle. + * + * A page state is defined by its current page->flags bits. + * The table matches them in order and calls the right handler. + * + * This is quite tricky because we can access page at any time + * in its live cycle, so all accesses have to be extremly careful. + * + * This is not complete. More states could be added. + * For any missing state don't attempt recovery. + */ + +#define dirty (1UL << PG_dirty) +#define sc (1UL << PG_swapcache) +#define unevict (1UL << PG_unevictable) +#define mlock (1UL << PG_mlocked) +#define writeback (1UL << PG_writeback) +#define lru (1UL << PG_lru) +#define swapbacked (1UL << PG_swapbacked) +#define head (1UL << PG_head) +#define tail (1UL << PG_tail) +#define compound (1UL << PG_compound) +#define slab (1UL << PG_slab) +#define buddy (1UL << PG_buddy) +#define reserved (1UL << PG_reserved) + +static struct page_state { + unsigned long mask; + unsigned long res; + char *msg; + int (*action)(struct page *p, unsigned long pfn); +} error_states[] = { + { reserved, reserved, "reserved kernel", me_ignore }, + { buddy, buddy, "free kernel", me_free }, + + /* + * Could in theory check if slab page is free or if we can drop + * currently unused objects without touching them. But just + * treat it as standard kernel for now. + */ + { slab, slab, "kernel slab", me_kernel }, + +#ifdef CONFIG_PAGEFLAGS_EXTENDED + { head, head, "huge", me_huge_page }, + { tail, tail, "huge", me_huge_page }, +#else + { compound, compound, "huge", me_huge_page }, +#endif + + { sc|dirty, sc|dirty, "swapcache", me_swapcache_dirty }, + { sc|dirty, sc, "swapcache", me_swapcache_clean }, + + { unevict|dirty, unevict|dirty, "unevictable LRU", me_pagecache_dirty}, + { unevict, unevict, "unevictable LRU", me_pagecache_clean}, + +#ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT + { mlock|dirty, mlock|dirty, "mlocked LRU", me_pagecache_dirty }, + { mlock, mlock, "mlocked LRU", me_pagecache_clean }, +#endif + + { lru|dirty, lru|dirty, "LRU", me_pagecache_dirty }, + { lru|dirty, lru, "clean LRU", me_pagecache_clean }, + { swapbacked, swapbacked, "anonymous", me_pagecache_clean }, + + /* + * Catchall entry: must be at end. + */ + { 0, 0, "unknown page state", me_unknown }, +}; + +#undef lru + +static void action_result(unsigned long pfn, char *msg, int result) +{ + struct page *page = NULL; + if (pfn_valid(pfn)) + page = pfn_to_page(pfn); + + printk(KERN_ERR "MCE %#lx: %s%s page recovery: %s\n", + pfn, + page && PageDirty(page) ? "dirty " : "", + msg, action_name[result]); +} + +static int page_action(struct page_state *ps, struct page *p, + unsigned long pfn, int ref) +{ + int result; + + result = ps->action(p, pfn); + action_result(pfn, ps->msg, result); + if (page_count(p) != 1 + ref) + printk(KERN_ERR + "MCE %#lx: %s page still referenced by %d users\n", + pfn, ps->msg, page_count(p) - 1); + + /* Could do more checks here if page looks ok */ + /* + * Could adjust zone counters here to correct for the missing page. + */ + + return result == RECOVERED ? 0 : -EBUSY; +} + +#define N_UNMAP_TRIES 5 + +/* + * Do all that is necessary to remove user space mappings. Unmap + * the pages and send SIGBUS to the processes if the data was dirty. + */ +static void hwpoison_user_mappings(struct page *p, unsigned long pfn, + int trapno) +{ + enum ttu_flags ttu = TTU_UNMAP | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS; + struct address_space *mapping; + LIST_HEAD(tokill); + int ret; + int i; + int kill = 1; + + if (PageReserved(p) || PageCompound(p) || PageSlab(p)) + return; + + if (!PageLRU(p)) + lru_add_drain_all(); + + /* + * This check implies we don't kill processes if their pages + * are in the swap cache early. Those are always late kills. + */ + if (!page_mapped(p)) + return; + + if (PageSwapCache(p)) { + printk(KERN_ERR + "MCE %#lx: keeping poisoned page in swap cache\n", pfn); + ttu |= TTU_IGNORE_HWPOISON; + } + + /* + * Propagate the dirty bit from PTEs to struct page first, because we + * need this to decide if we should kill or just drop the page. + */ + mapping = page_mapping(p); + if (!PageDirty(p) && mapping && mapping_cap_writeback_dirty(mapping)) { + if (page_mkclean(p)) { + SetPageDirty(p); + } else { + kill = 0; + ttu |= TTU_IGNORE_HWPOISON; + printk(KERN_INFO + "MCE %#lx: corrupted page was clean: dropped without side effects\n", + pfn); + } + } + + /* + * First collect all the processes that have the page + * mapped in dirty form. This has to be done before try_to_unmap, + * because ttu takes the rmap data structures down. + * + * Error handling: We ignore errors here because + * there's nothing that can be done. + */ + if (kill) + collect_procs(p, &tokill); + + /* + * try_to_unmap can fail temporarily due to races. + * Try a few times (RED-PEN better strategy?) + */ + for (i = 0; i < N_UNMAP_TRIES; i++) { + ret = try_to_unmap(p, ttu); + if (ret == SWAP_SUCCESS) + break; + pr_debug("MCE %#lx: try_to_unmap retry needed %d\n", pfn, ret); + } + + if (ret != SWAP_SUCCESS) + printk(KERN_ERR "MCE %#lx: failed to unmap page (mapcount=%d)\n", + pfn, page_mapcount(p)); + + /* + * Now that the dirty bit has been propagated to the + * struct page and all unmaps done we can decide if + * killing is needed or not. Only kill when the page + * was dirty, otherwise the tokill list is merely + * freed. When there was a problem unmapping earlier + * use a more force-full uncatchable kill to prevent + * any accesses to the poisoned memory. + */ + kill_procs_ao(&tokill, !!PageDirty(p), trapno, + ret != SWAP_SUCCESS, pfn); +} + +int __memory_failure(unsigned long pfn, int trapno, int ref) +{ + struct page_state *ps; + struct page *p; + int res; + + if (!sysctl_memory_failure_recovery) + panic("Memory failure from trap %d on page %lx", trapno, pfn); + + if (!pfn_valid(pfn)) { + action_result(pfn, "memory outside kernel control", IGNORED); + return -EIO; + } + + p = pfn_to_page(pfn); + if (TestSetPageHWPoison(p)) { + action_result(pfn, "already hardware poisoned", IGNORED); + return 0; + } + + atomic_long_add(1, &mce_bad_pages); + + /* + * We need/can do nothing about count=0 pages. + * 1) it's a free page, and therefore in safe hand: + * prep_new_page() will be the gate keeper. + * 2) it's part of a non-compound high order page. + * Implies some kernel user: cannot stop them from + * R/W the page; let's pray that the page has been + * used and will be freed some time later. + * In fact it's dangerous to directly bump up page count from 0, + * that may make page_freeze_refs()/page_unfreeze_refs() mismatch. + */ + if (!get_page_unless_zero(compound_head(p))) { + action_result(pfn, "free or high order kernel", IGNORED); + return PageBuddy(compound_head(p)) ? 0 : -EBUSY; + } + + /* + * Lock the page and wait for writeback to finish. + * It's very difficult to mess with pages currently under IO + * and in many cases impossible, so we just avoid it here. + */ + lock_page_nosync(p); + wait_on_page_writeback(p); + + /* + * Now take care of user space mappings. + */ + hwpoison_user_mappings(p, pfn, trapno); + + /* + * Torn down by someone else? + */ + if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) { + action_result(pfn, "already truncated LRU", IGNORED); + res = 0; + goto out; + } + + res = -EBUSY; + for (ps = error_states;; ps++) { + if ((p->flags & ps->mask) == ps->res) { + res = page_action(ps, p, pfn, ref); + break; + } + } +out: + unlock_page(p); + return res; +} +EXPORT_SYMBOL_GPL(__memory_failure); + +/** + * memory_failure - Handle memory failure of a page. + * @pfn: Page Number of the corrupted page + * @trapno: Trap number reported in the signal to user space. + * + * This function is called by the low level machine check code + * of an architecture when it detects hardware memory corruption + * of a page. It tries its best to recover, which includes + * dropping pages, killing processes etc. + * + * The function is primarily of use for corruptions that + * happen outside the current execution context (e.g. when + * detected by a background scrubber) + * + * Must run in process context (e.g. a work queue) with interrupts + * enabled and no spinlocks hold. + */ +void memory_failure(unsigned long pfn, int trapno) +{ + __memory_failure(pfn, trapno, 0); +} diff --git a/mm/rmap.c b/mm/rmap.c index 7e72ca19d68b..09c3d0b96116 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -36,6 +36,11 @@ * mapping->tree_lock (widely used, in set_page_dirty, * in arch-dependent flush_dcache_mmap_lock, * within inode_lock in __sync_single_inode) + * + * (code doesn't rely on that order so it could be switched around) + * ->tasklist_lock + * anon_vma->lock (memory_failure, collect_procs_anon) + * pte map lock */ #include @@ -311,7 +316,7 @@ pte_t *page_check_address(struct page *page, struct mm_struct *mm, * if the page is not mapped into the page tables of this VMA. Only * valid for normal file or anonymous VMAs. */ -static int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) +int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) { unsigned long address; pte_t *pte; -- 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 181d683d752c432635eda0f182ee71548c1f1820 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 16 Sep 2009 01:06:43 -0700 Subject: Input: libps2 - additional locking for i8042 ports The serio ports on i8042 are not completely isolated; while we provide enough locking to ensure proper serialization when accessing control and data registers AUX and KBD ports can still have an effect on each other on PS/2 protocol level. The most prominent effect is that issuing a command for the device connected to one port may cause abort of the command currently executing by the device connected to another port. Since i8042 nor serio subsystem are not aware of the details of the PS/2 protocol (length of the commands and their replies and so on) the locking should be done on libps2 level by adding special handling when we see that we are dealing with serio port on i8042. Signed-off-by: Dmitry Torokhov --- drivers/input/mouse/sentelic.c | 18 ++++++++++-------- drivers/input/serio/i8042.c | 41 +++++++++++++++++++++++++++++++++++++++++ drivers/input/serio/libps2.c | 28 ++++++++++++++++++++++++---- drivers/leds/leds-clevo-mail.c | 8 ++++++++ drivers/platform/x86/acer-wmi.c | 2 ++ include/linux/i8042.h | 30 ++++++++++++++++++++++++++++++ include/linux/libps2.h | 2 ++ 7 files changed, 117 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/input/mouse/sentelic.c b/drivers/input/mouse/sentelic.c index 84e2fc04d11b..f84cbd97c884 100644 --- a/drivers/input/mouse/sentelic.c +++ b/drivers/input/mouse/sentelic.c @@ -92,7 +92,8 @@ static int fsp_reg_read(struct psmouse *psmouse, int reg_addr, int *reg_val) */ ps2_command(ps2dev, NULL, PSMOUSE_CMD_DISABLE); psmouse_set_state(psmouse, PSMOUSE_CMD_MODE); - mutex_lock(&ps2dev->cmd_mutex); + + ps2_begin_command(ps2dev); if (ps2_sendbyte(ps2dev, 0xf3, FSP_CMD_TIMEOUT) < 0) goto out; @@ -126,7 +127,7 @@ static int fsp_reg_read(struct psmouse *psmouse, int reg_addr, int *reg_val) rc = 0; out: - mutex_unlock(&ps2dev->cmd_mutex); + ps2_end_command(ps2dev); ps2_command(ps2dev, NULL, PSMOUSE_CMD_ENABLE); psmouse_set_state(psmouse, PSMOUSE_ACTIVATED); dev_dbg(&ps2dev->serio->dev, "READ REG: 0x%02x is 0x%02x (rc = %d)\n", @@ -140,7 +141,7 @@ static int fsp_reg_write(struct psmouse *psmouse, int reg_addr, int reg_val) unsigned char v; int rc = -1; - mutex_lock(&ps2dev->cmd_mutex); + ps2_begin_command(ps2dev); if (ps2_sendbyte(ps2dev, 0xf3, FSP_CMD_TIMEOUT) < 0) goto out; @@ -179,7 +180,7 @@ static int fsp_reg_write(struct psmouse *psmouse, int reg_addr, int reg_val) rc = 0; out: - mutex_unlock(&ps2dev->cmd_mutex); + ps2_end_command(ps2dev); dev_dbg(&ps2dev->serio->dev, "WRITE REG: 0x%02x to 0x%02x (rc = %d)\n", reg_addr, reg_val, rc); return rc; @@ -214,7 +215,8 @@ static int fsp_page_reg_read(struct psmouse *psmouse, int *reg_val) ps2_command(ps2dev, NULL, PSMOUSE_CMD_DISABLE); psmouse_set_state(psmouse, PSMOUSE_CMD_MODE); - mutex_lock(&ps2dev->cmd_mutex); + + ps2_begin_command(ps2dev); if (ps2_sendbyte(ps2dev, 0xf3, FSP_CMD_TIMEOUT) < 0) goto out; @@ -236,7 +238,7 @@ static int fsp_page_reg_read(struct psmouse *psmouse, int *reg_val) rc = 0; out: - mutex_unlock(&ps2dev->cmd_mutex); + ps2_end_command(ps2dev); ps2_command(ps2dev, NULL, PSMOUSE_CMD_ENABLE); psmouse_set_state(psmouse, PSMOUSE_ACTIVATED); dev_dbg(&ps2dev->serio->dev, "READ PAGE REG: 0x%02x (rc = %d)\n", @@ -250,7 +252,7 @@ static int fsp_page_reg_write(struct psmouse *psmouse, int reg_val) unsigned char v; int rc = -1; - mutex_lock(&ps2dev->cmd_mutex); + ps2_begin_command(ps2dev); if (ps2_sendbyte(ps2dev, 0xf3, FSP_CMD_TIMEOUT) < 0) goto out; @@ -275,7 +277,7 @@ static int fsp_page_reg_write(struct psmouse *psmouse, int reg_val) rc = 0; out: - mutex_unlock(&ps2dev->cmd_mutex); + ps2_end_command(ps2dev); dev_dbg(&ps2dev->serio->dev, "WRITE PAGE REG: to 0x%02x (rc = %d)\n", reg_val, rc); return rc; diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index eb3ff94af58c..bc56e52b945f 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -87,8 +87,22 @@ static bool i8042_bypass_aux_irq_test; #include "i8042.h" +/* + * i8042_lock protects serialization between i8042_command and + * the interrupt handler. + */ static DEFINE_SPINLOCK(i8042_lock); +/* + * Writers to AUX and KBD ports as well as users issuing i8042_command + * directly should acquire i8042_mutex (by means of calling + * i8042_lock_chip() and i8042_unlock_ship() helpers) to ensure that + * they do not disturb each other (unfortunately in many i8042 + * implementations write to one of the ports will immediately abort + * command that is being processed by another port). + */ +static DEFINE_MUTEX(i8042_mutex); + struct i8042_port { struct serio *serio; int irq; @@ -113,6 +127,18 @@ static struct platform_device *i8042_platform_device; static irqreturn_t i8042_interrupt(int irq, void *dev_id); +void i8042_lock_chip(void) +{ + mutex_lock(&i8042_mutex); +} +EXPORT_SYMBOL(i8042_lock_chip); + +void i8042_unlock_chip(void) +{ + mutex_unlock(&i8042_mutex); +} +EXPORT_SYMBOL(i8042_unlock_chip); + /* * The i8042_wait_read() and i8042_wait_write functions wait for the i8042 to * be ready for reading values from it / writing values to it. @@ -1161,6 +1187,21 @@ static void __devexit i8042_unregister_ports(void) } } +/* + * Checks whether port belongs to i8042 controller. + */ +bool i8042_check_port_owner(const struct serio *port) +{ + int i; + + for (i = 0; i < I8042_NUM_PORTS; i++) + if (i8042_ports[i].serio == port) + return true; + + return false; +} +EXPORT_SYMBOL(i8042_check_port_owner); + static void i8042_free_irqs(void) { if (i8042_aux_irq_registered) diff --git a/drivers/input/serio/libps2.c b/drivers/input/serio/libps2.c index 3a95b508bf27..769ba65a585a 100644 --- a/drivers/input/serio/libps2.c +++ b/drivers/input/serio/libps2.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -54,6 +55,24 @@ int ps2_sendbyte(struct ps2dev *ps2dev, unsigned char byte, int timeout) } EXPORT_SYMBOL(ps2_sendbyte); +void ps2_begin_command(struct ps2dev *ps2dev) +{ + mutex_lock(&ps2dev->cmd_mutex); + + if (i8042_check_port_owner(ps2dev->serio)) + i8042_lock_chip(); +} +EXPORT_SYMBOL(ps2_begin_command); + +void ps2_end_command(struct ps2dev *ps2dev) +{ + if (i8042_check_port_owner(ps2dev->serio)) + i8042_unlock_chip(); + + mutex_unlock(&ps2dev->cmd_mutex); +} +EXPORT_SYMBOL(ps2_end_command); + /* * ps2_drain() waits for device to transmit requested number of bytes * and discards them. @@ -66,7 +85,7 @@ void ps2_drain(struct ps2dev *ps2dev, int maxbytes, int timeout) maxbytes = sizeof(ps2dev->cmdbuf); } - mutex_lock(&ps2dev->cmd_mutex); + ps2_begin_command(ps2dev); serio_pause_rx(ps2dev->serio); ps2dev->flags = PS2_FLAG_CMD; @@ -76,7 +95,8 @@ void ps2_drain(struct ps2dev *ps2dev, int maxbytes, int timeout) wait_event_timeout(ps2dev->wait, !(ps2dev->flags & PS2_FLAG_CMD), msecs_to_jiffies(timeout)); - mutex_unlock(&ps2dev->cmd_mutex); + + ps2_end_command(ps2dev); } EXPORT_SYMBOL(ps2_drain); @@ -237,9 +257,9 @@ int ps2_command(struct ps2dev *ps2dev, unsigned char *param, int command) { int rc; - mutex_lock(&ps2dev->cmd_mutex); + ps2_begin_command(ps2dev); rc = __ps2_command(ps2dev, param, command); - mutex_unlock(&ps2dev->cmd_mutex); + ps2_end_command(ps2dev); return rc; } diff --git a/drivers/leds/leds-clevo-mail.c b/drivers/leds/leds-clevo-mail.c index 1813c84ea5fc..f2242db54016 100644 --- a/drivers/leds/leds-clevo-mail.c +++ b/drivers/leds/leds-clevo-mail.c @@ -93,6 +93,8 @@ static struct dmi_system_id __initdata mail_led_whitelist[] = { static void clevo_mail_led_set(struct led_classdev *led_cdev, enum led_brightness value) { + i8042_lock_chip(); + if (value == LED_OFF) i8042_command(NULL, CLEVO_MAIL_LED_OFF); else if (value <= LED_HALF) @@ -100,6 +102,8 @@ static void clevo_mail_led_set(struct led_classdev *led_cdev, else i8042_command(NULL, CLEVO_MAIL_LED_BLINK_1HZ); + i8042_unlock_chip(); + } static int clevo_mail_led_blink(struct led_classdev *led_cdev, @@ -108,6 +112,8 @@ static int clevo_mail_led_blink(struct led_classdev *led_cdev, { int status = -EINVAL; + i8042_lock_chip(); + if (*delay_on == 0 /* ms */ && *delay_off == 0 /* ms */) { /* Special case: the leds subsystem requested us to * chose one user friendly blinking of the LED, and @@ -135,6 +141,8 @@ static int clevo_mail_led_blink(struct led_classdev *led_cdev, *delay_on, *delay_off); } + i8042_unlock_chip(); + return status; } diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index fb45f5ee8df1..454970d2d701 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -746,7 +746,9 @@ static acpi_status WMID_set_u32(u32 value, u32 cap, struct wmi_interface *iface) return AE_BAD_PARAMETER; if (quirks->mailled == 1) { param = value ? 0x92 : 0x93; + i8042_lock_chip(); i8042_command(¶m, 0x1059); + i8042_unlock_chip(); return 0; } break; diff --git a/include/linux/i8042.h b/include/linux/i8042.h index 7907a72403ee..60c3360ef6ad 100644 --- a/include/linux/i8042.h +++ b/include/linux/i8042.h @@ -7,6 +7,7 @@ * the Free Software Foundation. */ +#include /* * Standard commands. @@ -30,6 +31,35 @@ #define I8042_CMD_MUX_PFX 0x0090 #define I8042_CMD_MUX_SEND 0x1090 +struct serio; + +#if defined(CONFIG_SERIO_I8042) || defined(CONFIG_SERIO_I8042_MODULE) + +void i8042_lock_chip(void); +void i8042_unlock_chip(void); int i8042_command(unsigned char *param, int command); +bool i8042_check_port_owner(const struct serio *); + +#else + +void i8042_lock_chip(void) +{ +} + +void i8042_unlock_chip(void) +{ +} + +int i8042_command(unsigned char *param, int command) +{ + return -ENOSYS; +} + +bool i8042_check_port_owner(const struct serio *serio) +{ + return false; +} + +#endif #endif diff --git a/include/linux/libps2.h b/include/linux/libps2.h index fcf5fbe6a50c..79603a6c356f 100644 --- a/include/linux/libps2.h +++ b/include/linux/libps2.h @@ -44,6 +44,8 @@ struct ps2dev { void ps2_init(struct ps2dev *ps2dev, struct serio *serio); int ps2_sendbyte(struct ps2dev *ps2dev, unsigned char byte, int timeout); void ps2_drain(struct ps2dev *ps2dev, int maxbytes, int timeout); +void ps2_begin_command(struct ps2dev *ps2dev); +void ps2_end_command(struct ps2dev *ps2dev); int __ps2_command(struct ps2dev *ps2dev, unsigned char *param, int command); int ps2_command(struct ps2dev *ps2dev, unsigned char *param, int command); int ps2_handle_ack(struct ps2dev *ps2dev, unsigned char data); -- cgit v1.2.3 From ffd0db97196c1057f09c2ab42dd5b30e94e511d9 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 16 Sep 2009 01:06:43 -0700 Subject: Input: add generic suspend and resume for input devices Automatically turn off leds and sound effects as part of suspend process and restore led state, sounds and repeat rate at resume. Signed-off-by: Dmitry Torokhov --- drivers/input/input.c | 64 ++++++++++++++++++++++++++++++++++++++++++++++++++- include/linux/input.h | 2 +- 2 files changed, 64 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/input/input.c b/drivers/input/input.c index 7c237e6ac711..b8ed4294fccd 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -11,6 +11,7 @@ */ #include +#include #include #include #include @@ -514,7 +515,7 @@ static void input_disconnect_device(struct input_dev *dev) * that there are no threads in the middle of input_open_device() */ mutex_lock(&dev->mutex); - dev->going_away = 1; + dev->going_away = true; mutex_unlock(&dev->mutex); spin_lock_irq(&dev->event_lock); @@ -1259,10 +1260,71 @@ static int input_dev_uevent(struct device *device, struct kobj_uevent_env *env) return 0; } +#define INPUT_DO_TOGGLE(dev, type, bits, on) \ + do { \ + int i; \ + if (!test_bit(EV_##type, dev->evbit)) \ + break; \ + for (i = 0; i < type##_MAX; i++) { \ + if (!test_bit(i, dev->bits##bit) || \ + !test_bit(i, dev->bits)) \ + continue; \ + dev->event(dev, EV_##type, i, on); \ + } \ + } while (0) + +static void input_dev_reset(struct input_dev *dev, bool activate) +{ + if (!dev->event) + return; + + INPUT_DO_TOGGLE(dev, LED, led, activate); + INPUT_DO_TOGGLE(dev, SND, snd, activate); + + if (activate && test_bit(EV_REP, dev->evbit)) { + dev->event(dev, EV_REP, REP_PERIOD, dev->rep[REP_PERIOD]); + dev->event(dev, EV_REP, REP_DELAY, dev->rep[REP_DELAY]); + } +} + +#ifdef CONFIG_PM +static int input_dev_suspend(struct device *dev) +{ + struct input_dev *input_dev = to_input_dev(dev); + + mutex_lock(&input_dev->mutex); + input_dev_reset(input_dev, false); + mutex_unlock(&input_dev->mutex); + + return 0; +} + +static int input_dev_resume(struct device *dev) +{ + struct input_dev *input_dev = to_input_dev(dev); + + mutex_lock(&input_dev->mutex); + input_dev_reset(input_dev, true); + mutex_unlock(&input_dev->mutex); + + return 0; +} + +static const struct dev_pm_ops input_dev_pm_ops = { + .suspend = input_dev_suspend, + .resume = input_dev_resume, + .poweroff = input_dev_suspend, + .restore = input_dev_resume, +}; +#endif /* CONFIG_PM */ + static struct device_type input_dev_type = { .groups = input_dev_attr_groups, .release = input_dev_release, .uevent = input_dev_uevent, +#ifdef CONFIG_PM + .pm = &input_dev_pm_ops, +#endif }; static char *input_nodename(struct device *dev) diff --git a/include/linux/input.h b/include/linux/input.h index 8b3bc3e0d146..0ccfc30cd40f 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -1123,7 +1123,7 @@ struct input_dev { struct mutex mutex; unsigned int users; - int going_away; + bool going_away; struct device dev; -- cgit v1.2.3 From 38e783b38148531c0840ac130b97eb8158f84b48 Mon Sep 17 00:00:00 2001 From: Joonyoung Shim Date: Thu, 17 Sep 2009 22:35:45 -0700 Subject: Input: add touchscreen driver for MELFAS MCS-5000 controller The MELPAS MCS-5000 is the touchscreen controller. The overview of this controller can see at the following website: http://www.melfas.com/product/product01.asp?k_r=eng_ This driver is tested on s3c6410 NCP board and supports only the i2c interface. Signed-off-by: Joonyoung Shim Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/Kconfig | 11 ++ drivers/input/touchscreen/Makefile | 1 + drivers/input/touchscreen/mcs5000_ts.c | 318 +++++++++++++++++++++++++++++++++ include/linux/i2c/mcs5000_ts.h | 24 +++ 4 files changed, 354 insertions(+) create mode 100644 drivers/input/touchscreen/mcs5000_ts.c create mode 100644 include/linux/i2c/mcs5000_ts.h (limited to 'include/linux') diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig index 5a252d449e55..6dfb0a2b0a7d 100644 --- a/drivers/input/touchscreen/Kconfig +++ b/drivers/input/touchscreen/Kconfig @@ -169,6 +169,17 @@ config TOUCHSCREEN_WACOM_W8001 To compile this driver as a module, choose M here: the module will be called wacom_w8001. +config TOUCHSCREEN_MCS5000 + tristate "MELFAS MCS-5000 touchscreen" + depends on I2C + help + Say Y here if you have the MELFAS MCS-5000 touchscreen controller + chip in your system. + + If unsure, say N. + + To compile this driver as a module, choose M here: the + module will be called mcs5000_ts. config TOUCHSCREEN_MTOUCH tristate "MicroTouch serial touchscreens" diff --git a/drivers/input/touchscreen/Makefile b/drivers/input/touchscreen/Makefile index 3e1c5e0b952f..a882ca16506b 100644 --- a/drivers/input/touchscreen/Makefile +++ b/drivers/input/touchscreen/Makefile @@ -17,6 +17,7 @@ obj-$(CONFIG_TOUCHSCREEN_EETI) += eeti_ts.o obj-$(CONFIG_TOUCHSCREEN_ELO) += elo.o obj-$(CONFIG_TOUCHSCREEN_FUJITSU) += fujitsu_ts.o obj-$(CONFIG_TOUCHSCREEN_INEXIO) += inexio.o +obj-$(CONFIG_TOUCHSCREEN_MCS5000) += mcs5000_ts.o obj-$(CONFIG_TOUCHSCREEN_MIGOR) += migor_ts.o obj-$(CONFIG_TOUCHSCREEN_MTOUCH) += mtouch.o obj-$(CONFIG_TOUCHSCREEN_MK712) += mk712.o diff --git a/drivers/input/touchscreen/mcs5000_ts.c b/drivers/input/touchscreen/mcs5000_ts.c new file mode 100644 index 000000000000..4c28b89757f9 --- /dev/null +++ b/drivers/input/touchscreen/mcs5000_ts.c @@ -0,0 +1,318 @@ +/* + * mcs5000_ts.c - Touchscreen driver for MELFAS MCS-5000 controller + * + * Copyright (C) 2009 Samsung Electronics Co.Ltd + * Author: Joonyoung Shim + * + * Based on wm97xx-core.c + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + */ + +#include +#include +#include +#include +#include +#include +#include + +/* Registers */ +#define MCS5000_TS_STATUS 0x00 +#define STATUS_OFFSET 0 +#define STATUS_NO (0 << STATUS_OFFSET) +#define STATUS_INIT (1 << STATUS_OFFSET) +#define STATUS_SENSING (2 << STATUS_OFFSET) +#define STATUS_COORD (3 << STATUS_OFFSET) +#define STATUS_GESTURE (4 << STATUS_OFFSET) +#define ERROR_OFFSET 4 +#define ERROR_NO (0 << ERROR_OFFSET) +#define ERROR_POWER_ON_RESET (1 << ERROR_OFFSET) +#define ERROR_INT_RESET (2 << ERROR_OFFSET) +#define ERROR_EXT_RESET (3 << ERROR_OFFSET) +#define ERROR_INVALID_REG_ADDRESS (8 << ERROR_OFFSET) +#define ERROR_INVALID_REG_VALUE (9 << ERROR_OFFSET) + +#define MCS5000_TS_OP_MODE 0x01 +#define RESET_OFFSET 0 +#define RESET_NO (0 << RESET_OFFSET) +#define RESET_EXT_SOFT (1 << RESET_OFFSET) +#define OP_MODE_OFFSET 1 +#define OP_MODE_SLEEP (0 << OP_MODE_OFFSET) +#define OP_MODE_ACTIVE (1 << OP_MODE_OFFSET) +#define GESTURE_OFFSET 4 +#define GESTURE_DISABLE (0 << GESTURE_OFFSET) +#define GESTURE_ENABLE (1 << GESTURE_OFFSET) +#define PROXIMITY_OFFSET 5 +#define PROXIMITY_DISABLE (0 << PROXIMITY_OFFSET) +#define PROXIMITY_ENABLE (1 << PROXIMITY_OFFSET) +#define SCAN_MODE_OFFSET 6 +#define SCAN_MODE_INTERRUPT (0 << SCAN_MODE_OFFSET) +#define SCAN_MODE_POLLING (1 << SCAN_MODE_OFFSET) +#define REPORT_RATE_OFFSET 7 +#define REPORT_RATE_40 (0 << REPORT_RATE_OFFSET) +#define REPORT_RATE_80 (1 << REPORT_RATE_OFFSET) + +#define MCS5000_TS_SENS_CTL 0x02 +#define MCS5000_TS_FILTER_CTL 0x03 +#define PRI_FILTER_OFFSET 0 +#define SEC_FILTER_OFFSET 4 + +#define MCS5000_TS_X_SIZE_UPPER 0x08 +#define MCS5000_TS_X_SIZE_LOWER 0x09 +#define MCS5000_TS_Y_SIZE_UPPER 0x0A +#define MCS5000_TS_Y_SIZE_LOWER 0x0B + +#define MCS5000_TS_INPUT_INFO 0x10 +#define INPUT_TYPE_OFFSET 0 +#define INPUT_TYPE_NONTOUCH (0 << INPUT_TYPE_OFFSET) +#define INPUT_TYPE_SINGLE (1 << INPUT_TYPE_OFFSET) +#define INPUT_TYPE_DUAL (2 << INPUT_TYPE_OFFSET) +#define INPUT_TYPE_PALM (3 << INPUT_TYPE_OFFSET) +#define INPUT_TYPE_PROXIMITY (7 << INPUT_TYPE_OFFSET) +#define GESTURE_CODE_OFFSET 3 +#define GESTURE_CODE_NO (0 << GESTURE_CODE_OFFSET) + +#define MCS5000_TS_X_POS_UPPER 0x11 +#define MCS5000_TS_X_POS_LOWER 0x12 +#define MCS5000_TS_Y_POS_UPPER 0x13 +#define MCS5000_TS_Y_POS_LOWER 0x14 +#define MCS5000_TS_Z_POS 0x15 +#define MCS5000_TS_WIDTH 0x16 +#define MCS5000_TS_GESTURE_VAL 0x17 +#define MCS5000_TS_MODULE_REV 0x20 +#define MCS5000_TS_FIRMWARE_VER 0x21 + +/* Touchscreen absolute values */ +#define MCS5000_MAX_XC 0x3ff +#define MCS5000_MAX_YC 0x3ff + +enum mcs5000_ts_read_offset { + READ_INPUT_INFO, + READ_X_POS_UPPER, + READ_X_POS_LOWER, + READ_Y_POS_UPPER, + READ_Y_POS_LOWER, + READ_BLOCK_SIZE, +}; + +/* Each client has this additional data */ +struct mcs5000_ts_data { + struct i2c_client *client; + struct input_dev *input_dev; + const struct mcs5000_ts_platform_data *platform_data; +}; + +static irqreturn_t mcs5000_ts_interrupt(int irq, void *dev_id) +{ + struct mcs5000_ts_data *data = dev_id; + struct i2c_client *client = data->client; + u8 buffer[READ_BLOCK_SIZE]; + int err; + int x; + int y; + + err = i2c_smbus_read_i2c_block_data(client, MCS5000_TS_INPUT_INFO, + READ_BLOCK_SIZE, buffer); + if (err < 0) { + dev_err(&client->dev, "%s, err[%d]\n", __func__, err); + goto out; + } + + switch (buffer[READ_INPUT_INFO]) { + case INPUT_TYPE_NONTOUCH: + input_report_key(data->input_dev, BTN_TOUCH, 0); + input_sync(data->input_dev); + break; + + case INPUT_TYPE_SINGLE: + x = (buffer[READ_X_POS_UPPER] << 8) | buffer[READ_X_POS_LOWER]; + y = (buffer[READ_Y_POS_UPPER] << 8) | buffer[READ_Y_POS_LOWER]; + + input_report_key(data->input_dev, BTN_TOUCH, 1); + input_report_abs(data->input_dev, ABS_X, x); + input_report_abs(data->input_dev, ABS_Y, y); + input_sync(data->input_dev); + break; + + case INPUT_TYPE_DUAL: + /* TODO */ + break; + + case INPUT_TYPE_PALM: + /* TODO */ + break; + + case INPUT_TYPE_PROXIMITY: + /* TODO */ + break; + + default: + dev_err(&client->dev, "Unknown ts input type %d\n", + buffer[READ_INPUT_INFO]); + break; + } + + out: + return IRQ_HANDLED; +} + +static void mcs5000_ts_phys_init(struct mcs5000_ts_data *data) +{ + const struct mcs5000_ts_platform_data *platform_data = + data->platform_data; + struct i2c_client *client = data->client; + + /* Touch reset & sleep mode */ + i2c_smbus_write_byte_data(client, MCS5000_TS_OP_MODE, + RESET_EXT_SOFT | OP_MODE_SLEEP); + + /* Touch size */ + i2c_smbus_write_byte_data(client, MCS5000_TS_X_SIZE_UPPER, + platform_data->x_size >> 8); + i2c_smbus_write_byte_data(client, MCS5000_TS_X_SIZE_LOWER, + platform_data->x_size & 0xff); + i2c_smbus_write_byte_data(client, MCS5000_TS_Y_SIZE_UPPER, + platform_data->y_size >> 8); + i2c_smbus_write_byte_data(client, MCS5000_TS_Y_SIZE_LOWER, + platform_data->y_size & 0xff); + + /* Touch active mode & 80 report rate */ + i2c_smbus_write_byte_data(data->client, MCS5000_TS_OP_MODE, + OP_MODE_ACTIVE | REPORT_RATE_80); +} + +static int __devinit mcs5000_ts_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct mcs5000_ts_data *data; + struct input_dev *input_dev; + int ret; + + if (!client->dev.platform_data) + return -EINVAL; + + data = kzalloc(sizeof(struct mcs5000_ts_data), GFP_KERNEL); + input_dev = input_allocate_device(); + if (!data || !input_dev) { + dev_err(&client->dev, "Failed to allocate memory\n"); + ret = -ENOMEM; + goto err_free_mem; + } + + data->client = client; + data->input_dev = input_dev; + data->platform_data = client->dev.platform_data; + + input_dev->name = "MELPAS MCS-5000 Touchscreen"; + input_dev->id.bustype = BUS_I2C; + input_dev->dev.parent = &client->dev; + + __set_bit(EV_ABS, input_dev->evbit); + __set_bit(EV_KEY, input_dev->evbit); + __set_bit(BTN_TOUCH, input_dev->keybit); + input_set_abs_params(input_dev, ABS_X, 0, MCS5000_MAX_XC, 0, 0); + input_set_abs_params(input_dev, ABS_Y, 0, MCS5000_MAX_YC, 0, 0); + + input_set_drvdata(input_dev, data); + + if (data->platform_data->cfg_pin) + data->platform_data->cfg_pin(); + + ret = request_threaded_irq(client->irq, NULL, mcs5000_ts_interrupt, + IRQF_TRIGGER_LOW | IRQF_ONESHOT, "mcs5000_ts", data); + + if (ret < 0) { + dev_err(&client->dev, "Failed to register interrupt\n"); + goto err_free_mem; + } + + ret = input_register_device(data->input_dev); + if (ret < 0) + goto err_free_irq; + + mcs5000_ts_phys_init(data); + i2c_set_clientdata(client, data); + + return 0; + +err_free_irq: + free_irq(client->irq, data); +err_free_mem: + input_free_device(input_dev); + kfree(data); + return ret; +} + +static int __devexit mcs5000_ts_remove(struct i2c_client *client) +{ + struct mcs5000_ts_data *data = i2c_get_clientdata(client); + + free_irq(client->irq, data); + input_unregister_device(data->input_dev); + kfree(data); + i2c_set_clientdata(client, NULL); + + return 0; +} + +#ifdef CONFIG_PM +static int mcs5000_ts_suspend(struct i2c_client *client, pm_message_t mesg) +{ + /* Touch sleep mode */ + i2c_smbus_write_byte_data(client, MCS5000_TS_OP_MODE, OP_MODE_SLEEP); + + return 0; +} + +static int mcs5000_ts_resume(struct i2c_client *client) +{ + struct mcs5000_ts_data *data = i2c_get_clientdata(client); + + mcs5000_ts_phys_init(data); + + return 0; +} +#else +#define mcs5000_ts_suspend NULL +#define mcs5000_ts_resume NULL +#endif + +static const struct i2c_device_id mcs5000_ts_id[] = { + { "mcs5000_ts", 0 }, + { } +}; +MODULE_DEVICE_TABLE(i2c, mcs5000_ts_id); + +static struct i2c_driver mcs5000_ts_driver = { + .probe = mcs5000_ts_probe, + .remove = __devexit_p(mcs5000_ts_remove), + .suspend = mcs5000_ts_suspend, + .resume = mcs5000_ts_resume, + .driver = { + .name = "mcs5000_ts", + }, + .id_table = mcs5000_ts_id, +}; + +static int __init mcs5000_ts_init(void) +{ + return i2c_add_driver(&mcs5000_ts_driver); +} + +static void __exit mcs5000_ts_exit(void) +{ + i2c_del_driver(&mcs5000_ts_driver); +} + +module_init(mcs5000_ts_init); +module_exit(mcs5000_ts_exit); + +/* Module information */ +MODULE_AUTHOR("Joonyoung Shim "); +MODULE_DESCRIPTION("Touchscreen driver for MELFAS MCS-5000 controller"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/i2c/mcs5000_ts.h b/include/linux/i2c/mcs5000_ts.h new file mode 100644 index 000000000000..5a117b5ca15e --- /dev/null +++ b/include/linux/i2c/mcs5000_ts.h @@ -0,0 +1,24 @@ +/* + * mcs5000_ts.h + * + * Copyright (C) 2009 Samsung Electronics Co.Ltd + * Author: Joonyoung Shim + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + */ + +#ifndef __LINUX_MCS5000_TS_H +#define __LINUX_MCS5000_TS_H + +/* platform data for the MELFAS MCS-5000 touchscreen driver */ +struct mcs5000_ts_platform_data { + void (*cfg_pin)(void); + int x_size; + int y_size; +}; + +#endif /* __LINUX_MCS5000_TS_H */ -- cgit v1.2.3 From 88751dd6ce1fb0627c36c4ab08a40730e5a50d3e Mon Sep 17 00:00:00 2001 From: Michael Hennerich Date: Thu, 17 Sep 2009 22:39:38 -0700 Subject: Input: add driver for ADP5588 QWERTY I2C Keypad Signed-off-by: Michael Hennerich Signed-off-by: Bryan Wu Signed-off-by: Mike Frysinger Signed-off-by: Dmitry Torokhov --- drivers/input/keyboard/Kconfig | 10 + drivers/input/keyboard/Makefile | 1 + drivers/input/keyboard/adp5588-keys.c | 361 ++++++++++++++++++++++++++++++++++ include/linux/i2c/adp5588.h | 92 +++++++++ 4 files changed, 464 insertions(+) create mode 100644 drivers/input/keyboard/adp5588-keys.c create mode 100644 include/linux/i2c/adp5588.h (limited to 'include/linux') diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig index b14bd3a07140..d615c09a83c6 100644 --- a/drivers/input/keyboard/Kconfig +++ b/drivers/input/keyboard/Kconfig @@ -24,6 +24,16 @@ config KEYBOARD_AAED2000 To compile this driver as a module, choose M here: the module will be called aaed2000_kbd. +config KEYBOARD_ADP5588 + tristate "ADP5588 I2C QWERTY Keypad and IO Expander" + depends on I2C + help + Say Y here if you want to use a ADP5588 attached to your + system I2C bus. + + To compile this driver as a module, choose M here: the + module will be called adp5588-keys. + config KEYBOARD_AMIGA tristate "Amiga keyboard" depends on AMIGA diff --git a/drivers/input/keyboard/Makefile b/drivers/input/keyboard/Makefile index ab35ac36111e..a5c08cdf8083 100644 --- a/drivers/input/keyboard/Makefile +++ b/drivers/input/keyboard/Makefile @@ -5,6 +5,7 @@ # Each configuration option enables a list of files. obj-$(CONFIG_KEYBOARD_AAED2000) += aaed2000_kbd.o +obj-$(CONFIG_KEYBOARD_ADP5588) += adp5588-keys.o obj-$(CONFIG_KEYBOARD_AMIGA) += amikbd.o obj-$(CONFIG_KEYBOARD_ATARI) += atakbd.o obj-$(CONFIG_KEYBOARD_ATKBD) += atkbd.o diff --git a/drivers/input/keyboard/adp5588-keys.c b/drivers/input/keyboard/adp5588-keys.c new file mode 100644 index 000000000000..d48c808d5928 --- /dev/null +++ b/drivers/input/keyboard/adp5588-keys.c @@ -0,0 +1,361 @@ +/* + * File: drivers/input/keyboard/adp5588_keys.c + * Description: keypad driver for ADP5588 I2C QWERTY Keypad and IO Expander + * Bugs: Enter bugs at http://blackfin.uclinux.org/ + * + * Copyright (C) 2008-2009 Analog Devices Inc. + * Licensed under the GPL-2 or later. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + + /* Configuration Register1 */ +#define AUTO_INC (1 << 7) +#define GPIEM_CFG (1 << 6) +#define OVR_FLOW_M (1 << 5) +#define INT_CFG (1 << 4) +#define OVR_FLOW_IEN (1 << 3) +#define K_LCK_IM (1 << 2) +#define GPI_IEN (1 << 1) +#define KE_IEN (1 << 0) + +/* Interrupt Status Register */ +#define CMP2_INT (1 << 5) +#define CMP1_INT (1 << 4) +#define OVR_FLOW_INT (1 << 3) +#define K_LCK_INT (1 << 2) +#define GPI_INT (1 << 1) +#define KE_INT (1 << 0) + +/* Key Lock and Event Counter Register */ +#define K_LCK_EN (1 << 6) +#define LCK21 0x30 +#define KEC 0xF + +/* Key Event Register xy */ +#define KEY_EV_PRESSED (1 << 7) +#define KEY_EV_MASK (0x7F) + +#define KP_SEL(x) (0xFFFF >> (16 - x)) /* 2^x-1 */ + +#define KEYP_MAX_EVENT 10 + +/* + * Early pre 4.0 Silicon required to delay readout by at least 25ms, + * since the Event Counter Register updated 25ms after the interrupt + * asserted. + */ +#define WA_DELAYED_READOUT_REVID(rev) ((rev) < 4) + +struct adp5588_kpad { + struct i2c_client *client; + struct input_dev *input; + struct delayed_work work; + unsigned long delay; + unsigned short keycode[ADP5588_KEYMAPSIZE]; +}; + +static int adp5588_read(struct i2c_client *client, u8 reg) +{ + int ret = i2c_smbus_read_byte_data(client, reg); + + if (ret < 0) + dev_err(&client->dev, "Read Error\n"); + + return ret; +} + +static int adp5588_write(struct i2c_client *client, u8 reg, u8 val) +{ + return i2c_smbus_write_byte_data(client, reg, val); +} + +static void adp5588_work(struct work_struct *work) +{ + struct adp5588_kpad *kpad = container_of(work, + struct adp5588_kpad, work.work); + struct i2c_client *client = kpad->client; + int i, key, status, ev_cnt; + + status = adp5588_read(client, INT_STAT); + + if (status & OVR_FLOW_INT) /* Unlikely and should never happen */ + dev_err(&client->dev, "Event Overflow Error\n"); + + if (status & KE_INT) { + ev_cnt = adp5588_read(client, KEY_LCK_EC_STAT) & KEC; + if (ev_cnt) { + for (i = 0; i < ev_cnt; i++) { + key = adp5588_read(client, Key_EVENTA + i); + input_report_key(kpad->input, + kpad->keycode[(key & KEY_EV_MASK) - 1], + key & KEY_EV_PRESSED); + } + input_sync(kpad->input); + } + } + adp5588_write(client, INT_STAT, status); /* Status is W1C */ +} + +static irqreturn_t adp5588_irq(int irq, void *handle) +{ + struct adp5588_kpad *kpad = handle; + + /* + * use keventd context to read the event fifo registers + * Schedule readout at least 25ms after notification for + * REVID < 4 + */ + + schedule_delayed_work(&kpad->work, kpad->delay); + + return IRQ_HANDLED; +} + +static int __devinit adp5588_setup(struct i2c_client *client) +{ + struct adp5588_kpad_platform_data *pdata = client->dev.platform_data; + int i, ret; + + ret = adp5588_write(client, KP_GPIO1, KP_SEL(pdata->rows)); + ret |= adp5588_write(client, KP_GPIO2, KP_SEL(pdata->cols) & 0xFF); + ret |= adp5588_write(client, KP_GPIO3, KP_SEL(pdata->cols) >> 8); + + if (pdata->en_keylock) { + ret |= adp5588_write(client, UNLOCK1, pdata->unlock_key1); + ret |= adp5588_write(client, UNLOCK2, pdata->unlock_key2); + ret |= adp5588_write(client, KEY_LCK_EC_STAT, K_LCK_EN); + } + + for (i = 0; i < KEYP_MAX_EVENT; i++) + ret |= adp5588_read(client, Key_EVENTA); + + ret |= adp5588_write(client, INT_STAT, CMP2_INT | CMP1_INT | + OVR_FLOW_INT | K_LCK_INT | + GPI_INT | KE_INT); /* Status is W1C */ + + ret |= adp5588_write(client, CFG, INT_CFG | OVR_FLOW_IEN | KE_IEN); + + if (ret < 0) { + dev_err(&client->dev, "Write Error\n"); + return ret; + } + + return 0; +} + +static int __devinit adp5588_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct adp5588_kpad *kpad; + struct adp5588_kpad_platform_data *pdata = client->dev.platform_data; + struct input_dev *input; + unsigned int revid; + int ret, i; + int error; + + if (!i2c_check_functionality(client->adapter, + I2C_FUNC_SMBUS_BYTE_DATA)) { + dev_err(&client->dev, "SMBUS Byte Data not Supported\n"); + return -EIO; + } + + if (!pdata) { + dev_err(&client->dev, "no platform data?\n"); + return -EINVAL; + } + + if (!pdata->rows || !pdata->cols || !pdata->keymap) { + dev_err(&client->dev, "no rows, cols or keymap from pdata\n"); + return -EINVAL; + } + + if (pdata->keymapsize != ADP5588_KEYMAPSIZE) { + dev_err(&client->dev, "invalid keymapsize\n"); + return -EINVAL; + } + + if (!client->irq) { + dev_err(&client->dev, "no IRQ?\n"); + return -EINVAL; + } + + kpad = kzalloc(sizeof(*kpad), GFP_KERNEL); + input = input_allocate_device(); + if (!kpad || !input) { + error = -ENOMEM; + goto err_free_mem; + } + + kpad->client = client; + kpad->input = input; + INIT_DELAYED_WORK(&kpad->work, adp5588_work); + + ret = adp5588_read(client, DEV_ID); + if (ret < 0) { + error = ret; + goto err_free_mem; + } + + revid = (u8) ret & ADP5588_DEVICE_ID_MASK; + if (WA_DELAYED_READOUT_REVID(revid)) + kpad->delay = msecs_to_jiffies(30); + + input->name = client->name; + input->phys = "adp5588-keys/input0"; + input->dev.parent = &client->dev; + + input_set_drvdata(input, kpad); + + input->id.bustype = BUS_I2C; + input->id.vendor = 0x0001; + input->id.product = 0x0001; + input->id.version = revid; + + input->keycodesize = sizeof(kpad->keycode[0]); + input->keycodemax = pdata->keymapsize; + input->keycode = kpad->keycode; + + memcpy(kpad->keycode, pdata->keymap, + pdata->keymapsize * input->keycodesize); + + /* setup input device */ + __set_bit(EV_KEY, input->evbit); + + if (pdata->repeat) + __set_bit(EV_REP, input->evbit); + + for (i = 0; i < input->keycodemax; i++) + __set_bit(kpad->keycode[i] & KEY_MAX, input->keybit); + __clear_bit(KEY_RESERVED, input->keybit); + + error = input_register_device(input); + if (error) { + dev_err(&client->dev, "unable to register input device\n"); + goto err_free_mem; + } + + error = request_irq(client->irq, adp5588_irq, + IRQF_TRIGGER_FALLING | IRQF_DISABLED, + client->dev.driver->name, kpad); + if (error) { + dev_err(&client->dev, "irq %d busy?\n", client->irq); + goto err_unreg_dev; + } + + error = adp5588_setup(client); + if (error) + goto err_free_irq; + + device_init_wakeup(&client->dev, 1); + i2c_set_clientdata(client, kpad); + + dev_info(&client->dev, "Rev.%d keypad, irq %d\n", revid, client->irq); + return 0; + + err_free_irq: + free_irq(client->irq, kpad); + err_unreg_dev: + input_unregister_device(input); + input = NULL; + err_free_mem: + input_free_device(input); + kfree(kpad); + + return error; +} + +static int __devexit adp5588_remove(struct i2c_client *client) +{ + struct adp5588_kpad *kpad = i2c_get_clientdata(client); + + adp5588_write(client, CFG, 0); + free_irq(client->irq, kpad); + cancel_delayed_work_sync(&kpad->work); + input_unregister_device(kpad->input); + i2c_set_clientdata(client, NULL); + kfree(kpad); + + return 0; +} + +#ifdef CONFIG_PM +static int adp5588_suspend(struct device *dev) +{ + struct adp5588_kpad *kpad = dev_get_drvdata(dev); + struct i2c_client *client = kpad->client; + + disable_irq(client->irq); + cancel_delayed_work_sync(&kpad->work); + + if (device_may_wakeup(&client->dev)) + enable_irq_wake(client->irq); + + return 0; +} + +static int adp5588_resume(struct device *dev) +{ + struct adp5588_kpad *kpad = dev_get_drvdata(dev); + struct i2c_client *client = kpad->client; + + if (device_may_wakeup(&client->dev)) + disable_irq_wake(client->irq); + + enable_irq(client->irq); + + return 0; +} + +static struct dev_pm_ops adp5588_dev_pm_ops = { + .suspend = adp5588_suspend, + .resume = adp5588_resume, +}; +#endif + +static const struct i2c_device_id adp5588_id[] = { + { KBUILD_MODNAME, 0 }, + { } +}; +MODULE_DEVICE_TABLE(i2c, adp5588_id); + +static struct i2c_driver adp5588_driver = { + .driver = { + .name = KBUILD_MODNAME, +#ifdef CONFIG_PM + .pm = &adp5588_dev_pm_ops, +#endif + }, + .probe = adp5588_probe, + .remove = __devexit_p(adp5588_remove), + .id_table = adp5588_id, +}; + +static int __init adp5588_init(void) +{ + return i2c_add_driver(&adp5588_driver); +} +module_init(adp5588_init); + +static void __exit adp5588_exit(void) +{ + i2c_del_driver(&adp5588_driver); +} +module_exit(adp5588_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Michael Hennerich "); +MODULE_DESCRIPTION("ADP5588 Keypad driver"); +MODULE_ALIAS("platform:adp5588-keys"); diff --git a/include/linux/i2c/adp5588.h b/include/linux/i2c/adp5588.h new file mode 100644 index 000000000000..fc5db826b48e --- /dev/null +++ b/include/linux/i2c/adp5588.h @@ -0,0 +1,92 @@ +/* + * Analog Devices ADP5588 I/O Expander and QWERTY Keypad Controller + * + * Copyright 2009 Analog Devices Inc. + * + * Licensed under the GPL-2 or later. + */ + +#ifndef _ADP5588_H +#define _ADP5588_H + +#define DEV_ID 0x00 /* Device ID */ +#define CFG 0x01 /* Configuration Register1 */ +#define INT_STAT 0x02 /* Interrupt Status Register */ +#define KEY_LCK_EC_STAT 0x03 /* Key Lock and Event Counter Register */ +#define Key_EVENTA 0x04 /* Key Event Register A */ +#define Key_EVENTB 0x05 /* Key Event Register B */ +#define Key_EVENTC 0x06 /* Key Event Register C */ +#define Key_EVENTD 0x07 /* Key Event Register D */ +#define Key_EVENTE 0x08 /* Key Event Register E */ +#define Key_EVENTF 0x09 /* Key Event Register F */ +#define Key_EVENTG 0x0A /* Key Event Register G */ +#define Key_EVENTH 0x0B /* Key Event Register H */ +#define Key_EVENTI 0x0C /* Key Event Register I */ +#define Key_EVENTJ 0x0D /* Key Event Register J */ +#define KP_LCK_TMR 0x0E /* Keypad Lock1 to Lock2 Timer */ +#define UNLOCK1 0x0F /* Unlock Key1 */ +#define UNLOCK2 0x10 /* Unlock Key2 */ +#define GPIO_INT_STAT1 0x11 /* GPIO Interrupt Status */ +#define GPIO_INT_STAT2 0x12 /* GPIO Interrupt Status */ +#define GPIO_INT_STAT3 0x13 /* GPIO Interrupt Status */ +#define GPIO_DAT_STAT1 0x14 /* GPIO Data Status, Read twice to clear */ +#define GPIO_DAT_STAT2 0x15 /* GPIO Data Status, Read twice to clear */ +#define GPIO_DAT_STAT3 0x16 /* GPIO Data Status, Read twice to clear */ +#define GPIO_DAT_OUT1 0x17 /* GPIO DATA OUT */ +#define GPIO_DAT_OUT2 0x18 /* GPIO DATA OUT */ +#define GPIO_DAT_OUT3 0x19 /* GPIO DATA OUT */ +#define GPIO_INT_EN1 0x1A /* GPIO Interrupt Enable */ +#define GPIO_INT_EN2 0x1B /* GPIO Interrupt Enable */ +#define GPIO_INT_EN3 0x1C /* GPIO Interrupt Enable */ +#define KP_GPIO1 0x1D /* Keypad or GPIO Selection */ +#define KP_GPIO2 0x1E /* Keypad or GPIO Selection */ +#define KP_GPIO3 0x1F /* Keypad or GPIO Selection */ +#define GPI_EM1 0x20 /* GPI Event Mode 1 */ +#define GPI_EM2 0x21 /* GPI Event Mode 2 */ +#define GPI_EM3 0x22 /* GPI Event Mode 3 */ +#define GPIO_DIR1 0x23 /* GPIO Data Direction */ +#define GPIO_DIR2 0x24 /* GPIO Data Direction */ +#define GPIO_DIR3 0x25 /* GPIO Data Direction */ +#define GPIO_INT_LVL1 0x26 /* GPIO Edge/Level Detect */ +#define GPIO_INT_LVL2 0x27 /* GPIO Edge/Level Detect */ +#define GPIO_INT_LVL3 0x28 /* GPIO Edge/Level Detect */ +#define Debounce_DIS1 0x29 /* Debounce Disable */ +#define Debounce_DIS2 0x2A /* Debounce Disable */ +#define Debounce_DIS3 0x2B /* Debounce Disable */ +#define GPIO_PULL1 0x2C /* GPIO Pull Disable */ +#define GPIO_PULL2 0x2D /* GPIO Pull Disable */ +#define GPIO_PULL3 0x2E /* GPIO Pull Disable */ +#define CMP_CFG_STAT 0x30 /* Comparator Configuration and Status Register */ +#define CMP_CONFG_SENS1 0x31 /* Sensor1 Comparator Configuration Register */ +#define CMP_CONFG_SENS2 0x32 /* L2 Light Sensor Reference Level, Output Falling for Sensor 1 */ +#define CMP1_LVL2_TRIP 0x33 /* L2 Light Sensor Hysteresis (Active when Output Rising) for Sensor 1 */ +#define CMP1_LVL2_HYS 0x34 /* L3 Light Sensor Reference Level, Output Falling For Sensor 1 */ +#define CMP1_LVL3_TRIP 0x35 /* L3 Light Sensor Hysteresis (Active when Output Rising) For Sensor 1 */ +#define CMP1_LVL3_HYS 0x36 /* Sensor 2 Comparator Configuration Register */ +#define CMP2_LVL2_TRIP 0x37 /* L2 Light Sensor Reference Level, Output Falling for Sensor 2 */ +#define CMP2_LVL2_HYS 0x38 /* L2 Light Sensor Hysteresis (Active when Output Rising) for Sensor 2 */ +#define CMP2_LVL3_TRIP 0x39 /* L3 Light Sensor Reference Level, Output Falling For Sensor 2 */ +#define CMP2_LVL3_HYS 0x3A /* L3 Light Sensor Hysteresis (Active when Output Rising) For Sensor 2 */ +#define CMP1_ADC_DAT_R1 0x3B /* Comparator 1 ADC data Register1 */ +#define CMP1_ADC_DAT_R2 0x3C /* Comparator 1 ADC data Register2 */ +#define CMP2_ADC_DAT_R1 0x3D /* Comparator 2 ADC data Register1 */ +#define CMP2_ADC_DAT_R2 0x3E /* Comparator 2 ADC data Register2 */ + +#define ADP5588_DEVICE_ID_MASK 0xF + +/* Put one of these structures in i2c_board_info platform_data */ + +#define ADP5588_KEYMAPSIZE 80 + +struct adp5588_kpad_platform_data { + int rows; /* Number of rows */ + int cols; /* Number of columns */ + const unsigned short *keymap; /* Pointer to keymap */ + unsigned short keymapsize; /* Keymap size */ + unsigned repeat:1; /* Enable key repeat */ + unsigned en_keylock:1; /* Enable Key Lock feature */ + unsigned short unlock_key1; /* Unlock Key 1 */ + unsigned short unlock_key2; /* Unlock Key 2 */ +}; + +#endif -- 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 --- arch/arm/mach-u300/spi.c | 2 +- drivers/spi/amba-pl022.c | 8 ++++---- include/linux/amba/pl022.h | 8 ++++---- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-u300/spi.c b/arch/arm/mach-u300/spi.c index 307d007ea7f3..f0e887bea30e 100644 --- a/arch/arm/mach-u300/spi.c +++ b/arch/arm/mach-u300/spi.c @@ -48,7 +48,7 @@ struct pl022_config_chip dummy_chip_info = { .data_size = SSP_DATA_BITS_8, /* used to be 12 in some default */ .rx_lev_trig = SSP_RX_1_OR_MORE_ELEM, .tx_lev_trig = SSP_TX_1_OR_MORE_EMPTY_LOC, - .clk_phase = SSP_CLK_FALLING_EDGE, + .clk_phase = SSP_CLK_SECOND_EDGE, .clk_pol = SSP_CLK_POL_IDLE_LOW, .ctrl_len = SSP_BITS_12, .wait_state = SSP_MWIRE_WAIT_ZERO, diff --git a/drivers/spi/amba-pl022.c b/drivers/spi/amba-pl022.c index da76797ce8b9..35521af0d0d7 100644 --- a/drivers/spi/amba-pl022.c +++ b/drivers/spi/amba-pl022.c @@ -534,7 +534,7 @@ static void restore_state(struct pl022 *pl022) GEN_MASK_BITS(SSP_DATA_BITS_12, SSP_CR0_MASK_DSS, 0) | \ GEN_MASK_BITS(SSP_MICROWIRE_CHANNEL_FULL_DUPLEX, SSP_CR0_MASK_HALFDUP, 5) | \ GEN_MASK_BITS(SSP_CLK_POL_IDLE_LOW, SSP_CR0_MASK_SPO, 6) | \ - GEN_MASK_BITS(SSP_CLK_FALLING_EDGE, SSP_CR0_MASK_SPH, 7) | \ + GEN_MASK_BITS(SSP_CLK_SECOND_EDGE, SSP_CR0_MASK_SPH, 7) | \ GEN_MASK_BITS(NMDK_SSP_DEFAULT_CLKRATE, SSP_CR0_MASK_SCR, 8) | \ GEN_MASK_BITS(SSP_BITS_8, SSP_CR0_MASK_CSS, 16) | \ GEN_MASK_BITS(SSP_INTERFACE_MOTOROLA_SPI, SSP_CR0_MASK_FRF, 21) \ @@ -1249,8 +1249,8 @@ static int verify_controller_parameters(struct pl022 *pl022, return -EINVAL; } if (chip_info->iface == SSP_INTERFACE_MOTOROLA_SPI) { - if ((chip_info->clk_phase != SSP_CLK_RISING_EDGE) - && (chip_info->clk_phase != SSP_CLK_FALLING_EDGE)) { + if ((chip_info->clk_phase != SSP_CLK_FIRST_EDGE) + && (chip_info->clk_phase != SSP_CLK_SECOND_EDGE)) { dev_err(chip_info->dev, "Clock Phase is configured incorrectly\n"); return -EINVAL; @@ -1487,7 +1487,7 @@ static int pl022_setup(struct spi_device *spi) chip_info->data_size = SSP_DATA_BITS_12; chip_info->rx_lev_trig = SSP_RX_1_OR_MORE_ELEM; chip_info->tx_lev_trig = SSP_TX_1_OR_MORE_EMPTY_LOC; - chip_info->clk_phase = SSP_CLK_FALLING_EDGE; + chip_info->clk_phase = SSP_CLK_SECOND_EDGE; chip_info->clk_pol = SSP_CLK_POL_IDLE_LOW; chip_info->ctrl_len = SSP_BITS_8; chip_info->wait_state = SSP_MWIRE_WAIT_ZERO; 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 42f29a25207dc7b3051d299cc028d4b395d1328d Mon Sep 17 00:00:00 2001 From: Tim Abbott Date: Sun, 20 Sep 2009 18:14:12 -0400 Subject: kbuild: Don't define ALIGN and ENTRY when preprocessing linker scripts. Adding a reference to to x86's causes the x86 linker script to have syntax errors, because the ALIGN and ENTRY keywords get redefined to the assembly implementations of those. One could fix this by adjusting the include structure, but I think any solution based on that approach would be fragile. Currently, it is impossible when writing a header to do something different for assembly files and linker scripts, even though there are clearly cases where one wants them to define macros differently for the two (ENTRY being an excellent example). So I think the right solution here is to introduce a new preprocessor definition, called LINKER_SCRIPT that is set along with __ASSEMBLY__ for linker scripts, and to use that to not define ALIGN and ENTRY in linker scripts. I suspect we'll find other uses for this mechanism in the future. Signed-off-by: Tim Abbott Signed-off-by: Sam Ravnborg --- include/linux/linkage.h | 2 ++ scripts/Makefile.build | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index 691f59171c6c..5126cceb6ae9 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -57,6 +57,7 @@ #ifdef __ASSEMBLY__ +#ifndef LINKER_SCRIPT #define ALIGN __ALIGN #define ALIGN_STR __ALIGN_STR @@ -66,6 +67,7 @@ ALIGN; \ name: #endif +#endif /* LINKER_SCRIPT */ #ifndef WEAK #define WEAK(name) \ diff --git a/scripts/Makefile.build b/scripts/Makefile.build index d5425660a3df..341b58902ffc 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -271,7 +271,7 @@ targets += $(extra-y) $(MAKECMDGOALS) $(always) # --------------------------------------------------------------------------- quiet_cmd_cpp_lds_S = LDS $@ cmd_cpp_lds_S = $(CPP) $(cpp_flags) -P -C -U$(ARCH) \ - -D__ASSEMBLY__ -o $@ $< + -D__ASSEMBLY__ -DLINKER_SCRIPT -o $@ $< $(obj)/%.lds: $(src)/%.lds.S FORCE $(call if_changed_dep,cpp_lds_S) -- cgit v1.2.3 From 325253a6b2de4bdfa9ef0e28b5df8a4a4fe2b677 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Tue, 14 Jul 2009 17:06:02 +0100 Subject: backlight: Allow drivers to update the core, and generate events on changes Certain hardware will send us events when the backlight brightness changes. Add a function to update the value in the core, and additionally send a uevent so that userspace can pop up appropriate UI. The uevents are flagged depending on whether the update originated in the kernel or from userspace, making it easier to only display UI at the appropriate time. Signed-off-by: Matthew Garrett Signed-off-by: Richard Purdie --- drivers/video/backlight/backlight.c | 41 +++++++++++++++++++++++++++++++++++++ include/linux/backlight.h | 7 +++++++ 2 files changed, 48 insertions(+) (limited to 'include/linux') diff --git a/drivers/video/backlight/backlight.c b/drivers/video/backlight/backlight.c index 157057c79ca3..6e1446ae7f52 100644 --- a/drivers/video/backlight/backlight.c +++ b/drivers/video/backlight/backlight.c @@ -73,6 +73,26 @@ static inline void backlight_unregister_fb(struct backlight_device *bd) } #endif /* CONFIG_FB */ +static void backlight_generate_event(struct backlight_device *bd, + enum backlight_update_reason reason) +{ + char *envp[2]; + + switch (reason) { + case BACKLIGHT_UPDATE_SYSFS: + envp[0] = "SOURCE=sysfs"; + break; + case BACKLIGHT_UPDATE_HOTKEY: + envp[0] = "SOURCE=hotkey"; + break; + default: + envp[0] = "SOURCE=unknown"; + break; + } + envp[1] = NULL; + kobject_uevent_env(&bd->dev.kobj, KOBJ_CHANGE, envp); +} + static ssize_t backlight_show_power(struct device *dev, struct device_attribute *attr,char *buf) { @@ -142,6 +162,8 @@ static ssize_t backlight_store_brightness(struct device *dev, } mutex_unlock(&bd->ops_lock); + backlight_generate_event(bd, BACKLIGHT_UPDATE_SYSFS); + return rc; } @@ -213,6 +235,25 @@ static struct device_attribute bl_device_attributes[] = { __ATTR_NULL, }; +/** + * backlight_force_update - tell the backlight subsystem that hardware state + * has changed + * @bd: the backlight device to update + * + * Updates the internal state of the backlight in response to a hardware event, + * and generate a uevent to notify userspace + */ +void backlight_force_update(struct backlight_device *bd, + enum backlight_update_reason reason) +{ + mutex_lock(&bd->ops_lock); + if (bd->ops && bd->ops->get_brightness) + bd->props.brightness = bd->ops->get_brightness(bd); + mutex_unlock(&bd->ops_lock); + backlight_generate_event(bd, reason); +} +EXPORT_SYMBOL(backlight_force_update); + /** * backlight_device_register - create and register a new object of * backlight_device class. diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 79ca2da81c87..0f5f57858a23 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -27,6 +27,11 @@ * Any other use of the locks below is probably wrong. */ +enum backlight_update_reason { + BACKLIGHT_UPDATE_HOTKEY, + BACKLIGHT_UPDATE_SYSFS, +}; + struct backlight_device; struct fb_info; @@ -100,6 +105,8 @@ static inline void backlight_update_status(struct backlight_device *bd) extern struct backlight_device *backlight_device_register(const char *name, struct device *dev, void *devdata, struct backlight_ops *ops); extern void backlight_device_unregister(struct backlight_device *bd); +extern void backlight_force_update(struct backlight_device *bd, + enum backlight_update_reason reason); #define to_backlight_device(obj) container_of(obj, struct backlight_device, dev) -- cgit v1.2.3 From a6f10a2f5d8c2738b3ac05974bdbea3b68a2aecd Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 22 Sep 2009 22:34:24 +1000 Subject: perf_event: Update PERF_EVENT_FORK header definition PERF_EVENT_FORK always outputs the time field, so update the header to reflect this. Signed-off-by: Anton Blanchard Cc: Arjan van de Ven Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Frederic Weisbecker LKML-Reference: <20090922123424.GD19453@kryten> Signed-off-by: Ingo Molnar --- include/linux/perf_counter.h | 2 +- include/linux/perf_event.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h index 368bd70f1d2d..7b7fbf433cff 100644 --- a/include/linux/perf_counter.h +++ b/include/linux/perf_counter.h @@ -361,7 +361,7 @@ enum perf_event_type { * struct perf_event_header header; * u32 pid, ppid; * u32 tid, ptid; - * { u64 time; } && PERF_SAMPLE_TIME + * u64 time; * }; */ PERF_EVENT_FORK = 7, diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index acefaf71e6dd..3a9d36d1e92a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -357,7 +357,7 @@ enum perf_event_type { * struct perf_event_header header; * u32 pid, ppid; * u32 tid, ptid; - * { u64 time; } && PERF_SAMPLE_TIME + * u64 time; * }; */ PERF_RECORD_FORK = 7, -- 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 --- arch/arm/include/asm/mach/mmc.h | 18 ------------------ arch/arm/mach-integrator/integrator_cp.c | 4 ++-- arch/arm/mach-realview/core.c | 6 +++--- arch/arm/mach-realview/core.h | 4 ++-- arch/arm/mach-realview/realview_eb.c | 2 +- arch/arm/mach-realview/realview_pb1176.c | 2 +- arch/arm/mach-realview/realview_pb11mp.c | 2 +- arch/arm/mach-realview/realview_pba8.c | 2 +- arch/arm/mach-realview/realview_pbx.c | 2 +- arch/arm/mach-u300/mmc.c | 4 ++-- arch/arm/mach-versatile/core.c | 4 ++-- arch/arm/mach-versatile/versatile_pb.c | 4 ++-- drivers/mmc/host/mmci.c | 4 ++-- drivers/mmc/host/mmci.h | 2 +- include/linux/amba/mmci.h | 18 ++++++++++++++++++ 15 files changed, 39 insertions(+), 39 deletions(-) delete mode 100644 arch/arm/include/asm/mach/mmc.h create mode 100644 include/linux/amba/mmci.h (limited to 'include/linux') diff --git a/arch/arm/include/asm/mach/mmc.h b/arch/arm/include/asm/mach/mmc.h deleted file mode 100644 index 27bec555ee16..000000000000 --- a/arch/arm/include/asm/mach/mmc.h +++ /dev/null @@ -1,18 +0,0 @@ -/* - * arch/arm/include/asm/mach/mmc.h - */ -#ifndef ASMARM_MACH_MMC_H -#define ASMARM_MACH_MMC_H - -#include - -struct mmc_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 diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c index 2a318eba1b07..3f35293d457a 100644 --- a/arch/arm/mach-integrator/integrator_cp.c +++ b/arch/arm/mach-integrator/integrator_cp.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -35,7 +36,6 @@ #include #include #include -#include #include #include @@ -400,7 +400,7 @@ static unsigned int mmc_status(struct device *dev) return status & 8; } -static struct mmc_platform_data mmc_data = { +static struct mmci_platform_data mmc_data = { .ocr_mask = MMC_VDD_32_33|MMC_VDD_33_34, .status = mmc_status, .gpio_wp = -1, diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c index 5a5e1f72461e..a2083b60e3fb 100644 --- a/arch/arm/mach-realview/core.c +++ b/arch/arm/mach-realview/core.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include @@ -44,7 +45,6 @@ #include #include #include -#include #include @@ -237,14 +237,14 @@ static unsigned int realview_mmc_status(struct device *dev) return readl(REALVIEW_SYSMCI) & mask; } -struct mmc_platform_data realview_mmc0_plat_data = { +struct mmci_platform_data realview_mmc0_plat_data = { .ocr_mask = MMC_VDD_32_33|MMC_VDD_33_34, .status = realview_mmc_status, .gpio_wp = 17, .gpio_cd = 16, }; -struct mmc_platform_data realview_mmc1_plat_data = { +struct mmci_platform_data realview_mmc1_plat_data = { .ocr_mask = MMC_VDD_32_33|MMC_VDD_33_34, .status = realview_mmc_status, .gpio_wp = 19, diff --git a/arch/arm/mach-realview/core.h b/arch/arm/mach-realview/core.h index 59a337ba4be7..46cd6acb4d40 100644 --- a/arch/arm/mach-realview/core.h +++ b/arch/arm/mach-realview/core.h @@ -47,8 +47,8 @@ static struct amba_device name##_device = { \ extern struct platform_device realview_flash_device; extern struct platform_device realview_cf_device; extern struct platform_device realview_i2c_device; -extern struct mmc_platform_data realview_mmc0_plat_data; -extern struct mmc_platform_data realview_mmc1_plat_data; +extern struct mmci_platform_data realview_mmc0_plat_data; +extern struct mmci_platform_data realview_mmc1_plat_data; extern struct clcd_board clcd_plat_data; extern void __iomem *gic_cpu_base_addr; extern void __iomem *timer0_va_base; diff --git a/arch/arm/mach-realview/realview_eb.c b/arch/arm/mach-realview/realview_eb.c index c0795ea3b3a7..1d65e64ae571 100644 --- a/arch/arm/mach-realview/realview_eb.c +++ b/arch/arm/mach-realview/realview_eb.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -37,7 +38,6 @@ #include #include -#include #include #include diff --git a/arch/arm/mach-realview/realview_pb1176.c b/arch/arm/mach-realview/realview_pb1176.c index 395dc18070b4..2817fe099319 100644 --- a/arch/arm/mach-realview/realview_pb1176.c +++ b/arch/arm/mach-realview/realview_pb1176.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -37,7 +38,6 @@ #include #include #include -#include #include #include diff --git a/arch/arm/mach-realview/realview_pb11mp.c b/arch/arm/mach-realview/realview_pb11mp.c index c0c9e35e6e38..94680fcf726d 100644 --- a/arch/arm/mach-realview/realview_pb11mp.c +++ b/arch/arm/mach-realview/realview_pb11mp.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -38,7 +39,6 @@ #include #include #include -#include #include #include diff --git a/arch/arm/mach-realview/realview_pba8.c b/arch/arm/mach-realview/realview_pba8.c index 4fc64e146c32..941beb2b9709 100644 --- a/arch/arm/mach-realview/realview_pba8.c +++ b/arch/arm/mach-realview/realview_pba8.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -34,7 +35,6 @@ #include #include -#include #include #include diff --git a/arch/arm/mach-realview/realview_pbx.c b/arch/arm/mach-realview/realview_pbx.c index cf68b5426061..7e4bc6cdca52 100644 --- a/arch/arm/mach-realview/realview_pbx.c +++ b/arch/arm/mach-realview/realview_pbx.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -34,7 +35,6 @@ #include #include -#include #include #include diff --git a/arch/arm/mach-u300/mmc.c b/arch/arm/mach-u300/mmc.c index 82af247760e6..7b6b016786bb 100644 --- a/arch/arm/mach-u300/mmc.c +++ b/arch/arm/mach-u300/mmc.c @@ -19,8 +19,8 @@ #include #include #include +#include -#include #include "mmc.h" #include "padmux.h" @@ -28,7 +28,7 @@ struct mmci_card_event { struct input_dev *mmc_input; int mmc_inserted; struct work_struct workq; - struct mmc_platform_data mmc0_plat_data; + struct mmci_platform_data mmc0_plat_data; }; static unsigned int mmc_status(struct device *dev) diff --git a/arch/arm/mach-versatile/core.c b/arch/arm/mach-versatile/core.c index 975eae41ee66..e13be7c444ca 100644 --- a/arch/arm/mach-versatile/core.c +++ b/arch/arm/mach-versatile/core.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -47,7 +48,6 @@ #include #include #include -#include #include "core.h" #include "clock.h" @@ -369,7 +369,7 @@ unsigned int mmc_status(struct device *dev) return readl(VERSATILE_SYSMCI) & mask; } -static struct mmc_platform_data mmc0_plat_data = { +static struct mmci_platform_data mmc0_plat_data = { .ocr_mask = MMC_VDD_32_33|MMC_VDD_33_34, .status = mmc_status, .gpio_wp = -1, diff --git a/arch/arm/mach-versatile/versatile_pb.c b/arch/arm/mach-versatile/versatile_pb.c index 9af8d8154df5..239cd30fc4f5 100644 --- a/arch/arm/mach-versatile/versatile_pb.c +++ b/arch/arm/mach-versatile/versatile_pb.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include @@ -31,7 +32,6 @@ #include #include -#include #include "core.h" @@ -41,7 +41,7 @@ #define IRQ_MMCI1A IRQ_SIC_MMCI1A #endif -static struct mmc_platform_data mmc1_plat_data = { +static struct mmci_platform_data mmc1_plat_data = { .ocr_mask = MMC_VDD_32_33|MMC_VDD_33_34, .status = mmc_status, .gpio_wp = -1, diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index bf7c05b29e2c..79205e565c07 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -22,12 +22,12 @@ #include #include #include +#include #include #include #include #include -#include #include "mmci.h" @@ -537,7 +537,7 @@ static void mmci_check_status(unsigned long data) static int __devinit mmci_probe(struct amba_device *dev, struct amba_id *id) { - struct mmc_platform_data *plat = dev->dev.platform_data; + struct mmci_platform_data *plat = dev->dev.platform_data; struct mmci_host *host; struct mmc_host *mmc; int ret; diff --git a/drivers/mmc/host/mmci.h b/drivers/mmc/host/mmci.h index 839f264c9725..a7f9a51a0a3e 100644 --- a/drivers/mmc/host/mmci.h +++ b/drivers/mmc/host/mmci.h @@ -161,7 +161,7 @@ struct mmci_host { unsigned int mclk; unsigned int cclk; u32 pwr; - struct mmc_platform_data *plat; + struct mmci_platform_data *plat; u8 hw_designer; u8 hw_revision:4; 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 8cd09a5984c08dafade74c9c1ab4311af2bf2d24 Mon Sep 17 00:00:00 2001 From: Li Hong Date: Tue, 22 Sep 2009 18:00:44 +0800 Subject: tracing: Fix a comment and a trivial format issue in tracepoint.h Fix the tracepoint documentation path in tracepoints headers and a misaligned tabulation. Signed-off-by: Li Hong Cc: Steven Rostedt Cc: Ingo Molnar LKML-Reference: <3a3680030909220300h7cf18849q4d4702b9d4feaa67@mail.gmail.com> Signed-off-by: Frederic Weisbecker --- include/linux/tracepoint.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 63a3f7a80580..2aac8a83e89b 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 * @@ -36,7 +36,7 @@ struct tracepoint { #ifndef DECLARE_TRACE #define TP_PROTO(args...) args -#define TP_ARGS(args...) args +#define TP_ARGS(args...) args #ifdef CONFIG_TRACEPOINTS -- cgit v1.2.3 From ec4756238239f1a331d9fb95bad8b281dad56855 Mon Sep 17 00:00:00 2001 From: Steve Glendinning Date: Tue, 22 Sep 2009 04:00:27 +0000 Subject: smsc95xx: fix transmission where ZLP is expected Usbnet framework assumes USB hardware doesn't handle zero length packets, but SMSC LAN95xx requires these to be sent for correct operation. This patch fixes an easily reproducible tx lockup when sending a frame that results in exactly 512 bytes in a USB transmission (e.g. a UDP frame with 458 data bytes, due to IP headers and our USB headers). It adds an extra flag to usbnet for the hardware driver to indicate that it can handle and requires the zero length packets. This patch should not affect other usbnet users, please also consider for -stable. Signed-off-by: Steve Glendinning Signed-off-by: David S. Miller --- drivers/net/usb/smsc95xx.c | 2 +- drivers/net/usb/usbnet.c | 2 +- include/linux/usb/usbnet.h | 1 + 3 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 3aafebdbe7b5..c6c922247d05 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1227,7 +1227,7 @@ static const struct driver_info smsc95xx_info = { .rx_fixup = smsc95xx_rx_fixup, .tx_fixup = smsc95xx_tx_fixup, .status = smsc95xx_status, - .flags = FLAG_ETHER, + .flags = FLAG_ETHER | FLAG_SEND_ZLP, }; static const struct usb_device_id products[] = { diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 24b36f795151..ca5ca5ae061d 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1049,7 +1049,7 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, * NOTE: strictly conforming cdc-ether devices should expect * the ZLP here, but ignore the one-byte packet. */ - if ((length % dev->maxpacket) == 0) { + if (!(info->flags & FLAG_SEND_ZLP) && (length % dev->maxpacket) == 0) { urb->transfer_buffer_length++; if (skb_tailroom(skb)) { skb->data[skb->len] = 0; diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index bb69e256cd16..f81473052059 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -89,6 +89,7 @@ struct driver_info { #define FLAG_FRAMING_AX 0x0040 /* AX88772/178 packets */ #define FLAG_WLAN 0x0080 /* use "wlan%d" names */ #define FLAG_AVOID_UNLINK_URBS 0x0100 /* don't unlink urbs at usbnet_stop() */ +#define FLAG_SEND_ZLP 0x0200 /* hw requires ZLPs are sent */ /* init device ... can sleep, or cause probe() failure */ -- cgit v1.2.3 From fc2219d49ef1606e7fd2c88af2b423b01ff3d319 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 23 Sep 2009 09:50:41 -0700 Subject: rcu: Clean up code based on review feedback from Josh Triplett These issues identified during an old-fashioned face-to-face code review extended over many hours. o Bury various forms of the "rsp->completed == rsp->gpnum" comparison into an rcu_gp_in_progress() function, which has the beneficial side-effect of forcing consistent use of ACCESS_ONCE(). o Replace hand-coded arithmetic with DIV_ROUND_UP(). o Bury several "!list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x01])" instances into an rcu_preempted_readers() function, as this expression indicates that there are no readers blocked within RCU read-side critical sections blocking the current grace period. (Though there might well be similar readers blocking the next grace period.) o Remove a dangling rcu_restart_cpu() declaration that has been dangling for almost 20 minor releases of the kernel. Signed-off-by: Paul E. McKenney Acked-by: Peter Zijlstra Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: akpm@linux-foundation.org Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <12537246442687-git-send-email-> Signed-off-by: Ingo Molnar --- include/linux/rcutree.h | 1 - kernel/rcutree.c | 29 +++++++++++++++++----------- kernel/rcutree.h | 6 +++--- kernel/rcutree_plugin.h | 50 ++++++++++++++++++++++++------------------------- 4 files changed, 46 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 37682770e9d2..88109c87f29c 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -85,7 +85,6 @@ static inline void synchronize_rcu_bh_expedited(void) extern void __rcu_init(void); extern void rcu_check_callbacks(int cpu, int user); -extern void rcu_restart_cpu(int cpu); extern long rcu_batches_completed(void); extern long rcu_batches_completed_bh(void); diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 52b06f6e158c..f85b6842d1e1 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -100,6 +100,16 @@ static void __cpuinit rcu_init_percpu_data(int cpu, struct rcu_state *rsp, #include "rcutree_plugin.h" +/* + * Return true if an RCU grace period is in progress. The ACCESS_ONCE()s + * permit this function to be invoked without holding the root rcu_node + * structure's ->lock, but of course results can be subject to change. + */ +static int rcu_gp_in_progress(struct rcu_state *rsp) +{ + return ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum); +} + /* * Note a quiescent state. Because we do not need to know * how many quiescent states passed, just if there was at least @@ -173,9 +183,7 @@ cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp) static int cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp) { - /* ACCESS_ONCE() because we are accessing outside of lock. */ - return *rdp->nxttail[RCU_DONE_TAIL] && - ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum); + return *rdp->nxttail[RCU_DONE_TAIL] && !rcu_gp_in_progress(rsp); } /* @@ -482,7 +490,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp) spin_lock_irqsave(&rnp->lock, flags); delta = jiffies - rsp->jiffies_stall; - if (delta < RCU_STALL_RAT_DELAY || rsp->gpnum == rsp->completed) { + if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) { spin_unlock_irqrestore(&rnp->lock, flags); return; } @@ -537,8 +545,7 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) /* We haven't checked in, so go dump stack. */ print_cpu_stall(rsp); - } else if (rsp->gpnum != rsp->completed && - delta >= RCU_STALL_RAT_DELAY) { + } else if (rcu_gp_in_progress(rsp) && delta >= RCU_STALL_RAT_DELAY) { /* They had two time units to dump stack, so complain. */ print_other_cpu_stall(rsp); @@ -703,9 +710,9 @@ rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp) * hold rnp->lock, as required by rcu_start_gp(), which will release it. */ static void cpu_quiet_msk_finish(struct rcu_state *rsp, unsigned long flags) - __releases(rnp->lock) + __releases(rcu_get_root(rsp)->lock) { - WARN_ON_ONCE(rsp->completed == rsp->gpnum); + WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); rsp->completed = rsp->gpnum; rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]); rcu_start_gp(rsp, flags); /* releases root node's rnp->lock. */ @@ -1092,7 +1099,7 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed) struct rcu_node *rnp = rcu_get_root(rsp); u8 signaled; - if (ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum)) + if (!rcu_gp_in_progress(rsp)) return; /* No grace period in progress, nothing to force. */ if (!spin_trylock_irqsave(&rsp->fqslock, flags)) { rsp->n_force_qs_lh++; /* Inexact, can lose counts. Tough! */ @@ -1251,7 +1258,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), rdp->nxttail[RCU_NEXT_TAIL] = &head->next; /* Start a new grace period if one not already started. */ - if (ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum)) { + if (!rcu_gp_in_progress(rsp)) { unsigned long nestflag; struct rcu_node *rnp_root = rcu_get_root(rsp); @@ -1331,7 +1338,7 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) } /* Has an RCU GP gone long enough to send resched IPIs &c? */ - if (ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum) && + if (rcu_gp_in_progress(rsp) && ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0)) { rdp->n_rp_need_fqs++; return 1; diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 8e8287a983c2..9aa8c8a160d8 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -48,14 +48,14 @@ #elif NR_CPUS <= RCU_FANOUT_SQ # define NUM_RCU_LVLS 2 # define NUM_RCU_LVL_0 1 -# define NUM_RCU_LVL_1 (((NR_CPUS) + RCU_FANOUT - 1) / RCU_FANOUT) +# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT) # define NUM_RCU_LVL_2 (NR_CPUS) # define NUM_RCU_LVL_3 0 #elif NR_CPUS <= RCU_FANOUT_CUBE # define NUM_RCU_LVLS 3 # define NUM_RCU_LVL_0 1 -# define NUM_RCU_LVL_1 (((NR_CPUS) + RCU_FANOUT_SQ - 1) / RCU_FANOUT_SQ) -# define NUM_RCU_LVL_2 (((NR_CPUS) + (RCU_FANOUT) - 1) / (RCU_FANOUT)) +# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_SQ) +# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT) # define NUM_RCU_LVL_3 NR_CPUS #else # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS" diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 1cee04f627eb..8ff1ba7b3c43 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -150,6 +150,16 @@ void __rcu_read_lock(void) } EXPORT_SYMBOL_GPL(__rcu_read_lock); +/* + * Check for preempted RCU readers blocking the current grace period + * for the specified rcu_node structure. If the caller needs a reliable + * answer, it must hold the rcu_node's ->lock. + */ +static int rcu_preempted_readers(struct rcu_node *rnp) +{ + return !list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]); +} + static void rcu_read_unlock_special(struct task_struct *t) { int empty; @@ -196,7 +206,7 @@ static void rcu_read_unlock_special(struct task_struct *t) break; spin_unlock(&rnp->lock); /* irqs remain disabled. */ } - empty = list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]); + empty = !rcu_preempted_readers(rnp); list_del_init(&t->rcu_node_entry); t->rcu_blocked_node = NULL; @@ -207,7 +217,7 @@ static void rcu_read_unlock_special(struct task_struct *t) * drop rnp->lock and restore irq. */ if (!empty && rnp->qsmask == 0 && - list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1])) { + !rcu_preempted_readers(rnp)) { struct rcu_node *rnp_p; if (rnp->parent == NULL) { @@ -257,12 +267,12 @@ static void rcu_print_task_stall(struct rcu_node *rnp) { unsigned long flags; struct list_head *lp; - int phase = rnp->gpnum & 0x1; + int phase; struct task_struct *t; - if (!list_empty(&rnp->blocked_tasks[phase])) { + if (rcu_preempted_readers(rnp)) { spin_lock_irqsave(&rnp->lock, flags); - phase = rnp->gpnum & 0x1; /* re-read under lock. */ + phase = rnp->gpnum & 0x1; lp = &rnp->blocked_tasks[phase]; list_for_each_entry(t, lp, rcu_node_entry) printk(" P%d", t->pid); @@ -281,20 +291,10 @@ static void rcu_print_task_stall(struct rcu_node *rnp) */ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) { - WARN_ON_ONCE(!list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1])); + WARN_ON_ONCE(rcu_preempted_readers(rnp)); WARN_ON_ONCE(rnp->qsmask); } -/* - * Check for preempted RCU readers for the specified rcu_node structure. - * If the caller needs a reliable answer, it must hold the rcu_node's - * >lock. - */ -static int rcu_preempted_readers(struct rcu_node *rnp) -{ - return !list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]); -} - #ifdef CONFIG_HOTPLUG_CPU /* @@ -461,6 +461,15 @@ static void rcu_preempt_note_context_switch(int cpu) { } +/* + * Because preemptable RCU does not exist, there are never any preempted + * RCU readers. + */ +static int rcu_preempted_readers(struct rcu_node *rnp) +{ + return 0; +} + #ifdef CONFIG_RCU_CPU_STALL_DETECTOR /* @@ -483,15 +492,6 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) WARN_ON_ONCE(rnp->qsmask); } -/* - * Because preemptable RCU does not exist, there are never any preempted - * RCU readers. - */ -static int rcu_preempted_readers(struct rcu_node *rnp) -{ - return 0; -} - #ifdef CONFIG_HOTPLUG_CPU /* -- cgit v1.2.3 From 1eba8f84380bede3c602bd7758dea96925cead01 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 23 Sep 2009 09:50:42 -0700 Subject: rcu: Clean up code based on review feedback from Josh Triplett, part 2 These issues identified during an old-fashioned face-to-face code review extending over many hours. o Add comments for tricky parts of code, and correct comments that have passed their sell-by date. o Get rid of the vestiges of rcu_init_sched(), which is no longer needed now that PREEMPT_RCU is gone. o Move the #include of rcutree_plugin.h to the end of rcutree.c, which means that, rather than having a random collection of forward declarations, the new set of forward declarations document the set of plugins. The new home for this #include also allows __rcu_init_preempt() to move into rcutree_plugin.h. o Fix rcu_preempt_check_callbacks() to be static. Suggested-by: Josh Triplett Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: akpm@linux-foundation.org Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <12537246443924-git-send-email-> Signed-off-by: Ingo Molnar Peter Zijlstra --- include/linux/rcupdate.h | 4 +++ include/linux/rcutree.h | 6 +--- init/main.c | 1 - kernel/rcutree.c | 72 ++++++++++++++++++++++-------------------------- kernel/rcutree.h | 31 +++++++++++++++------ kernel/rcutree_plugin.h | 23 ++++++++++++++-- 6 files changed, 82 insertions(+), 55 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 6fe0363724e9..70331218e4b4 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -196,6 +196,8 @@ static inline void rcu_read_lock_sched(void) __acquire(RCU_SCHED); rcu_read_acquire(); } + +/* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_lock_sched_notrace(void) { preempt_disable_notrace(); @@ -213,6 +215,8 @@ static inline void rcu_read_unlock_sched(void) __release(RCU_SCHED); preempt_enable(); } + +/* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_unlock_sched_notrace(void) { __release(RCU_SCHED); diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 88109c87f29c..19a3b06943e0 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -90,10 +90,6 @@ extern long rcu_batches_completed(void); extern long rcu_batches_completed_bh(void); extern long rcu_batches_completed_sched(void); -static inline void rcu_init_sched(void) -{ -} - #ifdef CONFIG_NO_HZ void rcu_enter_nohz(void); void rcu_exit_nohz(void); @@ -106,7 +102,7 @@ static inline void rcu_exit_nohz(void) } #endif /* CONFIG_NO_HZ */ -/* A context switch is a grace period for rcutree. */ +/* A context switch is a grace period for RCU-sched and RCU-bh. */ static inline int rcu_blocking_is_gp(void) { return num_online_cpus() == 1; diff --git a/init/main.c b/init/main.c index 34971becbd3c..833d675677d1 100644 --- a/init/main.c +++ b/init/main.c @@ -782,7 +782,6 @@ static void __init do_initcalls(void) */ static void __init do_basic_setup(void) { - rcu_init_sched(); /* needed by module_init stage. */ init_workqueues(); cpuset_init_smp(); usermodehelper_init(); diff --git a/kernel/rcutree.c b/kernel/rcutree.c index f85b6842d1e1..53a5ef0ca911 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -81,24 +81,29 @@ DEFINE_PER_CPU(struct rcu_data, rcu_sched_data); struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state); DEFINE_PER_CPU(struct rcu_data, rcu_bh_data); -extern long rcu_batches_completed_sched(void); -static struct rcu_node *rcu_get_root(struct rcu_state *rsp); -static void cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp, - struct rcu_node *rnp, unsigned long flags); -static void cpu_quiet_msk_finish(struct rcu_state *rsp, unsigned long flags); +/* Forward declarations for rcutree_plugin.h */ +static inline void rcu_bootup_announce(void); +long rcu_batches_completed(void); +static void rcu_preempt_note_context_switch(int cpu); +static int rcu_preempted_readers(struct rcu_node *rnp); +#ifdef CONFIG_RCU_CPU_STALL_DETECTOR +static void rcu_print_task_stall(struct rcu_node *rnp); +#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ +static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU -static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp); +static void rcu_preempt_offline_tasks(struct rcu_state *rsp, + struct rcu_node *rnp, + struct rcu_data *rdp); +static void rcu_preempt_offline_cpu(int cpu); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ -static void __rcu_process_callbacks(struct rcu_state *rsp, - struct rcu_data *rdp); -static void __call_rcu(struct rcu_head *head, - void (*func)(struct rcu_head *rcu), - struct rcu_state *rsp); -static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp); -static void __cpuinit rcu_init_percpu_data(int cpu, struct rcu_state *rsp, - int preemptable); +static void rcu_preempt_check_callbacks(int cpu); +static void rcu_preempt_process_callbacks(void); +void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); +static int rcu_preempt_pending(int cpu); +static int rcu_preempt_needs_cpu(int cpu); +static void __cpuinit rcu_preempt_init_percpu_data(int cpu); +static void __init __rcu_init_preempt(void); -#include "rcutree_plugin.h" /* * Return true if an RCU grace period is in progress. The ACCESS_ONCE()s @@ -377,7 +382,7 @@ static long dyntick_recall_completed(struct rcu_state *rsp) /* * Snapshot the specified CPU's dynticks counter so that we can later * credit them with an implicit quiescent state. Return 1 if this CPU - * is already in a quiescent state courtesy of dynticks idle mode. + * is in dynticks idle mode, which is an extended quiescent state. */ static int dyntick_save_progress_counter(struct rcu_data *rdp) { @@ -624,9 +629,15 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) note_new_gpnum(rsp, rdp); /* - * Because we are first, we know that all our callbacks will - * be covered by this upcoming grace period, even the ones - * that were registered arbitrarily recently. + * Because this CPU just now started the new grace period, we know + * that all of its callbacks will be covered by this upcoming grace + * period, even the ones that were registered arbitrarily recently. + * Therefore, advance all outstanding callbacks to RCU_WAIT_TAIL. + * + * Other CPUs cannot be sure exactly when the grace period started. + * Therefore, their recently registered callbacks must pass through + * an additional RCU_NEXT_READY stage, so that they will be handled + * by the next RCU grace period. */ rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; @@ -886,7 +897,7 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) /* * Move callbacks from the outgoing CPU to the running CPU. - * Note that the outgoing CPU is now quiscent, so it is now + * Note that the outgoing CPU is now quiescent, so it is now * (uncharacteristically) safe to access its rcu_data structure. * Note also that we must carefully retain the order of the * outgoing CPU's callbacks in order for rcu_barrier() to work @@ -1577,25 +1588,6 @@ do { \ } \ } while (0) -#ifdef CONFIG_TREE_PREEMPT_RCU - -void __init __rcu_init_preempt(void) -{ - int i; /* All used by RCU_INIT_FLAVOR(). */ - int j; - struct rcu_node *rnp; - - RCU_INIT_FLAVOR(&rcu_preempt_state, rcu_preempt_data); -} - -#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - -void __init __rcu_init_preempt(void) -{ -} - -#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */ - void __init __rcu_init(void) { int i; /* All used by RCU_INIT_FLAVOR(). */ @@ -1612,6 +1604,8 @@ void __init __rcu_init(void) open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); } +#include "rcutree_plugin.h" + module_param(blimit, int, 0); module_param(qhimark, int, 0); module_param(qlowmark, int, 0); diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 9aa8c8a160d8..a48d11f37b4c 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -79,15 +79,21 @@ struct rcu_dynticks { * Definition for node within the RCU grace-period-detection hierarchy. */ struct rcu_node { - spinlock_t lock; + spinlock_t lock; /* Root rcu_node's lock protects some */ + /* rcu_state fields as well as following. */ long gpnum; /* Current grace period for this node. */ /* This will either be equal to or one */ /* behind the root rcu_node's gpnum. */ unsigned long qsmask; /* CPUs or groups that need to switch in */ /* order for current grace period to proceed.*/ + /* In leaf rcu_node, each bit corresponds to */ + /* an rcu_data structure, otherwise, each */ + /* bit corresponds to a child rcu_node */ + /* structure. */ unsigned long qsmaskinit; /* Per-GP initialization for qsmask. */ unsigned long grpmask; /* Mask to apply to parent qsmask. */ + /* Only one bit will be set in this mask. */ int grplo; /* lowest-numbered CPU or group here. */ int grphi; /* highest-numbered CPU or group here. */ u8 grpnum; /* CPU/group number for next level up. */ @@ -95,6 +101,9 @@ struct rcu_node { struct rcu_node *parent; struct list_head blocked_tasks[2]; /* Tasks blocked in RCU read-side critsect. */ + /* Grace period number (->gpnum) x blocked */ + /* by tasks on the (x & 0x1) element of the */ + /* blocked_tasks[] array. */ } ____cacheline_internodealigned_in_smp; /* Index values for nxttail array in struct rcu_data. */ @@ -126,19 +135,22 @@ struct rcu_data { * Any of the partitions might be empty, in which case the * pointer to that partition will be equal to the pointer for * the following partition. When the list is empty, all of - * the nxttail elements point to nxtlist, which is NULL. + * the nxttail elements point to the ->nxtlist pointer itself, + * which in that case is NULL. * - * [*nxttail[RCU_NEXT_READY_TAIL], NULL = *nxttail[RCU_NEXT_TAIL]): - * Entries that might have arrived after current GP ended - * [*nxttail[RCU_WAIT_TAIL], *nxttail[RCU_NEXT_READY_TAIL]): - * Entries known to have arrived before current GP ended - * [*nxttail[RCU_DONE_TAIL], *nxttail[RCU_WAIT_TAIL]): - * Entries that batch # <= ->completed - 1: waiting for current GP * [nxtlist, *nxttail[RCU_DONE_TAIL]): * Entries that batch # <= ->completed * The grace period for these entries has completed, and * the other grace-period-completed entries may be moved * here temporarily in rcu_process_callbacks(). + * [*nxttail[RCU_DONE_TAIL], *nxttail[RCU_WAIT_TAIL]): + * Entries that batch # <= ->completed - 1: waiting for current GP + * [*nxttail[RCU_WAIT_TAIL], *nxttail[RCU_NEXT_READY_TAIL]): + * Entries known to have arrived before current GP ended + * [*nxttail[RCU_NEXT_READY_TAIL], *nxttail[RCU_NEXT_TAIL]): + * Entries that might have arrived after current GP ended + * Note that the value of *nxttail[RCU_NEXT_TAIL] will + * always be NULL, as this is the end of the list. */ struct rcu_head *nxtlist; struct rcu_head **nxttail[RCU_NEXT_SIZE]; @@ -216,6 +228,9 @@ struct rcu_state { /* Force QS state. */ long gpnum; /* Current gp number. */ long completed; /* # of last completed gp. */ + + /* End of fields guarded by root rcu_node's lock. */ + spinlock_t onofflock; /* exclude on/offline and */ /* starting new GP. */ spinlock_t fqslock; /* Only one task forcing */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 8ff1ba7b3c43..65250219ab6d 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -418,6 +418,18 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu) rcu_init_percpu_data(cpu, &rcu_preempt_state, 1); } +/* + * Initialize preemptable RCU's state structures. + */ +static void __init __rcu_init_preempt(void) +{ + int i; /* All used by RCU_INIT_FLAVOR(). */ + int j; + struct rcu_node *rnp; + + RCU_INIT_FLAVOR(&rcu_preempt_state, rcu_preempt_data); +} + /* * Check for a task exiting while in a preemptable-RCU read-side * critical section, clean up if so. No need to issue warnings, @@ -518,7 +530,7 @@ static void rcu_preempt_offline_cpu(int cpu) * Because preemptable RCU does not exist, it never has any callbacks * to check. */ -void rcu_preempt_check_callbacks(int cpu) +static void rcu_preempt_check_callbacks(int cpu) { } @@ -526,7 +538,7 @@ void rcu_preempt_check_callbacks(int cpu) * Because preemptable RCU does not exist, it never has any callbacks * to process. */ -void rcu_preempt_process_callbacks(void) +static void rcu_preempt_process_callbacks(void) { } @@ -563,4 +575,11 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu) { } +/* + * Because preemptable RCU does not exist, it need not be initialized. + */ +static void __init __rcu_init_preempt(void) +{ +} + #endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */ -- cgit v1.2.3 From 9b2619aff0332e95ea5eb7a0d75b0208818d871c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 23 Sep 2009 09:50:43 -0700 Subject: rcu: Clean up code to address Ingo's checkpatch feedback Move declarations and update storage classes to make checkpatch happy. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: akpm@linux-foundation.org Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <12537246441701-git-send-email-> Signed-off-by: Ingo Molnar --- include/linux/rcutree.h | 6 +++++- kernel/rcupdate.c | 3 --- kernel/rcutorture.c | 4 +--- kernel/rcutree.c | 23 ----------------------- kernel/rcutree.h | 26 +++++++++++++++++++++++++- kernel/rcutree_trace.c | 12 ++++++------ 6 files changed, 37 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 19a3b06943e0..46e9ab3ee6e1 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -30,10 +30,14 @@ #ifndef __LINUX_RCUTREE_H #define __LINUX_RCUTREE_H +struct notifier_block; + extern void rcu_sched_qs(int cpu); extern void rcu_bh_qs(int cpu); - +extern int rcu_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu); extern int rcu_needs_cpu(int cpu); +extern int rcu_expedited_torture_stats(char *page); #ifdef CONFIG_TREE_PREEMPT_RCU diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 37ac45483082..8e795133b33d 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -259,9 +259,6 @@ static void rcu_migrate_callback(struct rcu_head *notused) wake_up(&rcu_migrate_wq); } -extern int rcu_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu); - static int __cpuinit rcu_barrier_cpu_hotplug(struct notifier_block *self, unsigned long action, void *hcpu) { diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 233768f21f97..697c0a0229d4 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -606,8 +606,6 @@ static struct rcu_torture_ops sched_ops_sync = { .name = "sched_sync" }; -extern int rcu_expedited_torture_stats(char *page); - static struct rcu_torture_ops sched_expedited_ops = { .init = rcu_sync_torture_init, .cleanup = NULL, @@ -650,7 +648,7 @@ rcu_torture_writer(void *arg) old_rp = rcu_torture_current; rp->rtort_mbtest = 1; rcu_assign_pointer(rcu_torture_current, rp); - smp_wmb(); + smp_wmb(); /* Mods to old_rp must follow rcu_assign_pointer() */ if (old_rp) { i = old_rp->rtort_pipe_count; if (i > RCU_TORTURE_PIPE_LEN) diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 53a5ef0ca911..8e52cde7b8f7 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -81,29 +81,6 @@ DEFINE_PER_CPU(struct rcu_data, rcu_sched_data); struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state); DEFINE_PER_CPU(struct rcu_data, rcu_bh_data); -/* Forward declarations for rcutree_plugin.h */ -static inline void rcu_bootup_announce(void); -long rcu_batches_completed(void); -static void rcu_preempt_note_context_switch(int cpu); -static int rcu_preempted_readers(struct rcu_node *rnp); -#ifdef CONFIG_RCU_CPU_STALL_DETECTOR -static void rcu_print_task_stall(struct rcu_node *rnp); -#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ -static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); -#ifdef CONFIG_HOTPLUG_CPU -static void rcu_preempt_offline_tasks(struct rcu_state *rsp, - struct rcu_node *rnp, - struct rcu_data *rdp); -static void rcu_preempt_offline_cpu(int cpu); -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ -static void rcu_preempt_check_callbacks(int cpu); -static void rcu_preempt_process_callbacks(void); -void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); -static int rcu_preempt_pending(int cpu); -static int rcu_preempt_needs_cpu(int cpu); -static void __cpuinit rcu_preempt_init_percpu_data(int cpu); -static void __init __rcu_init_preempt(void); - /* * Return true if an RCU grace period is in progress. The ACCESS_ONCE()s diff --git a/kernel/rcutree.h b/kernel/rcutree.h index a48d11f37b4c..e6ab31cc28ba 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -270,5 +270,29 @@ extern struct rcu_state rcu_preempt_state; DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data); #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ -#endif /* #ifdef RCU_TREE_NONCORE */ +#else /* #ifdef RCU_TREE_NONCORE */ +/* Forward declarations for rcutree_plugin.h */ +static inline void rcu_bootup_announce(void); +long rcu_batches_completed(void); +static void rcu_preempt_note_context_switch(int cpu); +static int rcu_preempted_readers(struct rcu_node *rnp); +#ifdef CONFIG_RCU_CPU_STALL_DETECTOR +static void rcu_print_task_stall(struct rcu_node *rnp); +#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ +static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); +#ifdef CONFIG_HOTPLUG_CPU +static void rcu_preempt_offline_tasks(struct rcu_state *rsp, + struct rcu_node *rnp, + struct rcu_data *rdp); +static void rcu_preempt_offline_cpu(int cpu); +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ +static void rcu_preempt_check_callbacks(int cpu); +static void rcu_preempt_process_callbacks(void); +void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); +static int rcu_preempt_pending(int cpu); +static int rcu_preempt_needs_cpu(int cpu); +static void __cpuinit rcu_preempt_init_percpu_data(int cpu); +static void __init __rcu_init_preempt(void); + +#endif /* #else #ifdef RCU_TREE_NONCORE */ diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index c89f5e9fd173..f09af28b8262 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -93,7 +93,7 @@ static int rcudata_open(struct inode *inode, struct file *file) return single_open(file, show_rcudata, NULL); } -static struct file_operations rcudata_fops = { +static const struct file_operations rcudata_fops = { .owner = THIS_MODULE, .open = rcudata_open, .read = seq_read, @@ -145,7 +145,7 @@ static int rcudata_csv_open(struct inode *inode, struct file *file) return single_open(file, show_rcudata_csv, NULL); } -static struct file_operations rcudata_csv_fops = { +static const struct file_operations rcudata_csv_fops = { .owner = THIS_MODULE, .open = rcudata_csv_open, .read = seq_read, @@ -159,7 +159,7 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) struct rcu_node *rnp; seq_printf(m, "c=%ld g=%ld s=%d jfq=%ld j=%x " - "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu\n", + "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu\n", rsp->completed, rsp->gpnum, rsp->signaled, (long)(rsp->jiffies_force_qs - jiffies), (int)(jiffies & 0xffff), @@ -196,7 +196,7 @@ static int rcuhier_open(struct inode *inode, struct file *file) return single_open(file, show_rcuhier, NULL); } -static struct file_operations rcuhier_fops = { +static const struct file_operations rcuhier_fops = { .owner = THIS_MODULE, .open = rcuhier_open, .read = seq_read, @@ -222,7 +222,7 @@ static int rcugp_open(struct inode *inode, struct file *file) return single_open(file, show_rcugp, NULL); } -static struct file_operations rcugp_fops = { +static const struct file_operations rcugp_fops = { .owner = THIS_MODULE, .open = rcugp_open, .read = seq_read, @@ -276,7 +276,7 @@ static int rcu_pending_open(struct inode *inode, struct file *file) return single_open(file, show_rcu_pending, NULL); } -static struct file_operations rcu_pending_fops = { +static const struct file_operations rcu_pending_fops = { .owner = THIS_MODULE, .open = rcu_pending_open, .read = seq_read, -- cgit v1.2.3 From 74908a0009eb36054190ab80deb9671014efed96 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 17 Sep 2009 17:47:12 -0700 Subject: include/linux/cred.h: fix build mips allmodconfig: include/linux/cred.h: In function `creds_are_invalid': include/linux/cred.h:187: error: `PAGE_SIZE' undeclared (first use in this function) include/linux/cred.h:187: error: (Each undeclared identifier is reported only once include/linux/cred.h:187: error: for each function it appears in.) Fixes commit b6dff3ec5e116e3af6f537d4caedcad6b9e5082a Author: David Howells AuthorDate: Fri Nov 14 10:39:16 2008 +1100 Commit: James Morris CommitDate: Fri Nov 14 10:39:16 2008 +1100 CRED: Separate task security context from task_struct I think. It's way too large to be inlined anyway. Dunno if this needs an EXPORT_SYMBOL() yet. Cc: David Howells Cc: James Morris Cc: Serge Hallyn Signed-off-by: Andrew Morton Acked-by: David Howells Signed-off-by: James Morris --- include/linux/cred.h | 18 +----------------- kernel/cred.c | 18 ++++++++++++++++++ 2 files changed, 19 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cred.h b/include/linux/cred.h index fb371601a3b4..4e3387a89cb9 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -176,23 +176,7 @@ extern void __invalid_creds(const struct cred *, const char *, unsigned); extern void __validate_process_creds(struct task_struct *, const char *, unsigned); -static inline bool creds_are_invalid(const struct cred *cred) -{ - if (cred->magic != CRED_MAGIC) - return true; - if (atomic_read(&cred->usage) < atomic_read(&cred->subscribers)) - return true; -#ifdef CONFIG_SECURITY_SELINUX - if (selinux_is_enabled()) { - if ((unsigned long) cred->security < PAGE_SIZE) - return true; - if ((*(u32 *)cred->security & 0xffffff00) == - (POISON_FREE << 24 | POISON_FREE << 16 | POISON_FREE << 8)) - return true; - } -#endif - return false; -} +extern bool creds_are_invalid(const struct cred *cred); static inline void __validate_creds(const struct cred *cred, const char *file, unsigned line) diff --git a/kernel/cred.c b/kernel/cred.c index d7f7a01082eb..70bda79fae24 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -782,6 +782,24 @@ EXPORT_SYMBOL(set_create_files_as); #ifdef CONFIG_DEBUG_CREDENTIALS +bool creds_are_invalid(const struct cred *cred) +{ + if (cred->magic != CRED_MAGIC) + return true; + if (atomic_read(&cred->usage) < atomic_read(&cred->subscribers)) + return true; +#ifdef CONFIG_SECURITY_SELINUX + if (selinux_is_enabled()) { + if ((unsigned long) cred->security < PAGE_SIZE) + return true; + if ((*(u32 *)cred->security & 0xffffff00) == + (POISON_FREE << 24 | POISON_FREE << 16 | POISON_FREE << 8)) + return true; + } +#endif + return false; +} + /* * dump invalid credentials */ -- cgit v1.2.3 From 97363c6a4f93a20380b4a9e11f35e27fed68a517 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Wed, 23 Sep 2009 14:36:38 -0400 Subject: sunrpc: xdr_xcode_hyper helpers cannot presume 64-bit alignment Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 7da466ba4b0d..f5cc0898bc53 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -11,6 +11,7 @@ #include #include +#include #include /* @@ -117,14 +118,14 @@ static inline __be32 *xdr_encode_array(__be32 *p, const void *s, unsigned int le static inline __be32 * xdr_encode_hyper(__be32 *p, __u64 val) { - *(__be64 *)p = cpu_to_be64(val); + put_unaligned_be64(val, p); return p + 2; } static inline __be32 * xdr_decode_hyper(__be32 *p, __u64 *valp) { - *valp = be64_to_cpup((__be64 *)p); + *valp = get_unaligned_be64(p); return p + 2; } -- cgit v1.2.3 From a0219d948dd712561817b0d7c95fd2f10b698203 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 24 Sep 2009 09:34:35 -0600 Subject: cpumask: remove dangerous CPU_MASK_ALL_PTR (Thanks to Al Viro for reminding me of this, via Ingo) CPU_MASK_ALL is the (deprecated) "all bits set" cpumask, defined as so: #define CPU_MASK_ALL (cpumask_t) { { ... } } Taking the address of such a temporary is questionable at best, unfortunately 321a8e9d (cpumask: add CPU_MASK_ALL_PTR macro) added CPU_MASK_ALL_PTR: #define CPU_MASK_ALL_PTR (&CPU_MASK_ALL) Which formalizes this practice. One day gcc could bite us over this usage (though we seem to have gotten away with it so far). Now all callers are removed, we kill it. Signed-off-by: Rusty Russell Acked-by: Ingo Molnar Reported-by: Al Viro Cc: Mike Travis --- include/linux/cpumask.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 9b1d458aac6e..c0ab3588129d 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -324,8 +324,6 @@ static inline const struct cpumask *get_cpu_mask(unsigned int cpu) [BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD \ } } -#define CPU_MASK_ALL_PTR (&CPU_MASK_ALL) - #else #define CPU_MASK_ALL \ @@ -336,7 +334,6 @@ static inline const struct cpumask *get_cpu_mask(unsigned int cpu) /* cpu_mask_all is in init/main.c */ extern cpumask_t cpu_mask_all; -#define CPU_MASK_ALL_PTR (&cpu_mask_all) #endif -- cgit v1.2.3 From 72d78d05cbaa69f2a32f5f9d65a4551ba0da571f Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 24 Sep 2009 09:34:36 -0600 Subject: cpumask: remove unused cpu_mask_all It's only defined for NR_CPUS > BITS_PER_LONG; cpu_all_mask is always defined (and const). Signed-off-by: Rusty Russell --- include/linux/cpumask.h | 3 --- init/main.c | 5 ----- 2 files changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index c0ab3588129d..dbb8367ecf56 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -332,9 +332,6 @@ static inline const struct cpumask *get_cpu_mask(unsigned int cpu) [BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD \ } } -/* cpu_mask_all is in init/main.c */ -extern cpumask_t cpu_mask_all; - #endif #define CPU_MASK_NONE \ diff --git a/init/main.c b/init/main.c index 6107223124e4..51695cee1864 100644 --- a/init/main.c +++ b/init/main.c @@ -360,11 +360,6 @@ static inline void smp_prepare_cpus(unsigned int maxcpus) { } #else -#if NR_CPUS > BITS_PER_LONG -cpumask_t cpu_mask_all __read_mostly = CPU_MASK_ALL; -EXPORT_SYMBOL(cpu_mask_all); -#endif - /* Setup number of possible processor ids */ int nr_cpu_ids __read_mostly = NR_CPUS; EXPORT_SYMBOL(nr_cpu_ids); -- cgit v1.2.3 From ef79f8e191722dbc1fc33bdfc448f572266c37e9 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 24 Sep 2009 09:34:37 -0600 Subject: cpumask: remove unused mask field from struct irqaction. Up until 1.1.83, the primitive human tribes used struct sigaction for interrupts. The sa_mask field was overloaded to hold a pointer to the name. When someone created the new "struct irqaction" they carried across the "mask" field as a kind of ancestor worship: the fact that it was unused makes clear its spiritual significance. Signed-off-by: Rusty Russell --- include/linux/interrupt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 8e9e151f811e..894ed7180bff 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -97,7 +97,6 @@ typedef irqreturn_t (*irq_handler_t)(int, void *); struct irqaction { irq_handler_t handler; unsigned long flags; - cpumask_t mask; const char *name; void *dev_id; struct irqaction *next; -- cgit v1.2.3 From 144e2ce6115c0a1ee4cb5c935360ea4e2966b0ce Mon Sep 17 00:00:00 2001 From: Nobuhiro Iwamatsu Date: Mon, 15 Jun 2009 12:16:54 +0900 Subject: cpumask: Remove mask field from comments By 7be23e278f, mask field was deleted by irqaction. However, it was not deleted from comment. Signed-off-by: Nobuhiro Iwamatsu CC: Rusty Russell Signed-off-by: Rusty Russell --- include/linux/interrupt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 894ed7180bff..b78cf8194957 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -84,7 +84,6 @@ typedef irqreturn_t (*irq_handler_t)(int, void *); * struct irqaction - per interrupt action descriptor * @handler: interrupt handler function * @flags: flags (see IRQF_* above) - * @mask: no comment as it is useless and about to be removed * @name: name of the device * @dev_id: cookie to identify the device * @next: pointer to the next irqaction for shared interrupts -- cgit v1.2.3 From e0ad955680878998ff7dc51ce06ddad12260423a Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 24 Sep 2009 09:34:38 -0600 Subject: cpumask: don't define set_cpus_allowed() if CONFIG_CPUMASK_OFFSTACK=y You're not supposed to pass cpumasks on the stack in that case. Signed-off-by: Rusty Russell --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index cbf2a3b46280..848d1f20086e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1817,10 +1817,13 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p, return 0; } #endif + +#ifndef CONFIG_CPUMASK_OFFSTACK static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask) { return set_cpus_allowed_ptr(p, &new_mask); } +#endif /* * Architectures can set this to 1 if they have specified -- cgit v1.2.3 From fe71a3c7dc8cfe0f239c04b4fc6501f4aa56aa0a Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 24 Sep 2009 09:34:40 -0600 Subject: cpumask: remove the deprecated smp_call_function_mask() Everyone is now using smp_call_function_many(). Signed-off-by: Rusty Russell --- include/linux/smp.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index 9e3d8af09207..39c64bae776d 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -73,15 +73,6 @@ int smp_call_function(void(*func)(void *info), void *info, int wait); void smp_call_function_many(const struct cpumask *mask, void (*func)(void *info), void *info, bool wait); -/* Deprecated: Use smp_call_function_many which takes a pointer to the mask. */ -static inline int -smp_call_function_mask(cpumask_t mask, void(*func)(void *info), void *info, - int wait) -{ - smp_call_function_many(&mask, func, info, wait); - return 0; -} - void __smp_call_function_single(int cpuid, struct call_single_data *data, int wait); @@ -144,8 +135,6 @@ static inline int up_smp_call_function(void (*func)(void *), void *info) static inline void smp_send_reschedule(int cpu) { } #define num_booting_cpus() 1 #define smp_prepare_boot_cpu() do {} while (0) -#define smp_call_function_mask(mask, func, info, wait) \ - (up_smp_call_function(func, info)) #define smp_call_function_many(mask, func, info, wait) \ (up_smp_call_function(func, info)) static inline void init_call_single_data(void) -- cgit v1.2.3 From 6f401420e2822c24c36e6e1c657f6e7f7f777a93 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 24 Sep 2009 09:34:40 -0600 Subject: cpumask: remove obsolete topology_core_siblings and topology_thread_siblings: core There were replaced by topology_core_cpumask and topology_thread_cpumask. Signed-off-by: Rusty Russell --- include/linux/topology.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index 809b26c07090..fc0bf3edeb67 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -211,12 +211,6 @@ int arch_update_cpu_topology(void); #ifndef topology_core_id #define topology_core_id(cpu) ((void)(cpu), 0) #endif -#ifndef topology_thread_siblings -#define topology_thread_siblings(cpu) cpumask_of_cpu(cpu) -#endif -#ifndef topology_core_siblings -#define topology_core_siblings(cpu) cpumask_of_cpu(cpu) -#endif #ifndef topology_thread_cpumask #define topology_thread_cpumask(cpu) cpumask_of(cpu) #endif -- cgit v1.2.3 From 4b805b17382c11a8b1c9bb8053ce9d1dcde0701a Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 24 Sep 2009 09:34:52 -0600 Subject: cpumask: remove unused deprecated functions, avoid accusations of insanity We're not forcing removal of the old cpu_ functions, but we might as well delete the now-unused ones. Especially CPUMASK_ALLOC and friends. I actually got a phone call (!) from a hacker who thought I had introduced them as the new cpumask API. He seemed bewildered that I had lost all taste. Signed-off-by: Rusty Russell Cc: benh@kernel.crashing.org --- include/linux/cpumask.h | 112 +----------------------------------------------- 1 file changed, 1 insertion(+), 111 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index dbb8367ecf56..e162d13c65ab 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -15,10 +15,6 @@ * see bitmap_scnprintf() and bitmap_parse_user() in lib/bitmap.c. * For details of cpulist_scnprintf() and cpulist_parse(), see * bitmap_scnlistprintf() and bitmap_parselist(), also in bitmap.c. - * For details of cpu_remap(), see bitmap_bitremap in lib/bitmap.c - * For details of cpus_remap(), see bitmap_remap in lib/bitmap.c. - * For details of cpus_onto(), see bitmap_onto in lib/bitmap.c. - * For details of cpus_fold(), see bitmap_fold in lib/bitmap.c. * * . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . * Note: The alternate operations with the suffix "_nr" are used @@ -47,22 +43,17 @@ * void cpus_or(dst, src1, src2) dst = src1 | src2 [union] * void cpus_xor(dst, src1, src2) dst = src1 ^ src2 * int cpus_andnot(dst, src1, src2) dst = src1 & ~src2 - * void cpus_complement(dst, src) dst = ~src * * int cpus_equal(mask1, mask2) Does mask1 == mask2? * int cpus_intersects(mask1, mask2) Do mask1 and mask2 intersect? * int cpus_subset(mask1, mask2) Is mask1 a subset of mask2? * int cpus_empty(mask) Is mask empty (no bits sets)? - * int cpus_full(mask) Is mask full (all bits sets)? * int cpus_weight(mask) Hamming weigh - number of set bits - * int cpus_weight_nr(mask) Same using nr_cpu_ids instead of NR_CPUS * - * void cpus_shift_right(dst, src, n) Shift right * void cpus_shift_left(dst, src, n) Shift left * * int first_cpu(mask) Number lowest set bit, or NR_CPUS * int next_cpu(cpu, mask) Next cpu past 'cpu', or NR_CPUS - * int next_cpu_nr(cpu, mask) Next cpu past 'cpu', or nr_cpu_ids * * cpumask_t cpumask_of_cpu(cpu) Return cpumask with bit 'cpu' set * (can be used as an lvalue) @@ -70,45 +61,10 @@ * CPU_MASK_NONE Initializer - no bits set * unsigned long *cpus_addr(mask) Array of unsigned long's in mask * - * CPUMASK_ALLOC kmalloc's a structure that is a composite of many cpumask_t - * variables, and CPUMASK_PTR provides pointers to each field. - * - * The structure should be defined something like this: - * struct my_cpumasks { - * cpumask_t mask1; - * cpumask_t mask2; - * }; - * - * Usage is then: - * CPUMASK_ALLOC(my_cpumasks); - * CPUMASK_PTR(mask1, my_cpumasks); - * CPUMASK_PTR(mask2, my_cpumasks); - * - * --- DO NOT reference cpumask_t pointers until this check --- - * if (my_cpumasks == NULL) - * "kmalloc failed"... - * - * References are now pointers to the cpumask_t variables (*mask1, ...) - * - *if NR_CPUS > BITS_PER_LONG - * CPUMASK_ALLOC(m) Declares and allocates struct m *m = - * kmalloc(sizeof(*m), GFP_KERNEL) - * CPUMASK_FREE(m) Macro for kfree(m) - *else - * CPUMASK_ALLOC(m) Declares struct m _m, *m = &_m - * CPUMASK_FREE(m) Nop - *endif - * CPUMASK_PTR(v, m) Declares cpumask_t *v = &(m->v) - * ------------------------------------------------------------------------ - * * int cpumask_scnprintf(buf, len, mask) Format cpumask for printing * int cpumask_parse_user(ubuf, ulen, mask) Parse ascii string as cpumask * int cpulist_scnprintf(buf, len, mask) Format cpumask as list for printing * int cpulist_parse(buf, map) Parse ascii string as cpulist - * int cpu_remap(oldbit, old, new) newbit = map(old, new)(oldbit) - * void cpus_remap(dst, src, old, new) *dst = map(old, new)(src) - * void cpus_onto(dst, orig, relmap) *dst = orig relative to relmap - * void cpus_fold(dst, orig, sz) dst bits = orig bits mod sz * * for_each_cpu_mask(cpu, mask) for-loop cpu over mask using NR_CPUS * for_each_cpu_mask_nr(cpu, mask) for-loop cpu over mask using nr_cpu_ids @@ -142,7 +98,6 @@ #include typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; -extern cpumask_t _unused_cpumask_arg_; #ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS #define cpu_set(cpu, dst) __cpu_set((cpu), &(dst)) @@ -207,13 +162,6 @@ static inline int __cpus_andnot(cpumask_t *dstp, const cpumask_t *src1p, return bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); } -#define cpus_complement(dst, src) __cpus_complement(&(dst), &(src), NR_CPUS) -static inline void __cpus_complement(cpumask_t *dstp, - const cpumask_t *srcp, int nbits) -{ - bitmap_complement(dstp->bits, srcp->bits, nbits); -} - #define cpus_equal(src1, src2) __cpus_equal(&(src1), &(src2), NR_CPUS) static inline int __cpus_equal(const cpumask_t *src1p, const cpumask_t *src2p, int nbits) @@ -241,26 +189,12 @@ static inline int __cpus_empty(const cpumask_t *srcp, int nbits) return bitmap_empty(srcp->bits, nbits); } -#define cpus_full(cpumask) __cpus_full(&(cpumask), NR_CPUS) -static inline int __cpus_full(const cpumask_t *srcp, int nbits) -{ - return bitmap_full(srcp->bits, nbits); -} - #define cpus_weight(cpumask) __cpus_weight(&(cpumask), NR_CPUS) static inline int __cpus_weight(const cpumask_t *srcp, int nbits) { return bitmap_weight(srcp->bits, nbits); } -#define cpus_shift_right(dst, src, n) \ - __cpus_shift_right(&(dst), &(src), (n), NR_CPUS) -static inline void __cpus_shift_right(cpumask_t *dstp, - const cpumask_t *srcp, int n, int nbits) -{ - bitmap_shift_right(dstp->bits, srcp->bits, n, nbits); -} - #define cpus_shift_left(dst, src, n) \ __cpus_shift_left(&(dst), &(src), (n), NR_CPUS) static inline void __cpus_shift_left(cpumask_t *dstp, @@ -346,46 +280,6 @@ static inline const struct cpumask *get_cpu_mask(unsigned int cpu) #define cpus_addr(src) ((src).bits) -#if NR_CPUS > BITS_PER_LONG -#define CPUMASK_ALLOC(m) struct m *m = kmalloc(sizeof(*m), GFP_KERNEL) -#define CPUMASK_FREE(m) kfree(m) -#else -#define CPUMASK_ALLOC(m) struct m _m, *m = &_m -#define CPUMASK_FREE(m) -#endif -#define CPUMASK_PTR(v, m) cpumask_t *v = &(m->v) - -#define cpu_remap(oldbit, old, new) \ - __cpu_remap((oldbit), &(old), &(new), NR_CPUS) -static inline int __cpu_remap(int oldbit, - const cpumask_t *oldp, const cpumask_t *newp, int nbits) -{ - return bitmap_bitremap(oldbit, oldp->bits, newp->bits, nbits); -} - -#define cpus_remap(dst, src, old, new) \ - __cpus_remap(&(dst), &(src), &(old), &(new), NR_CPUS) -static inline void __cpus_remap(cpumask_t *dstp, const cpumask_t *srcp, - const cpumask_t *oldp, const cpumask_t *newp, int nbits) -{ - bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits); -} - -#define cpus_onto(dst, orig, relmap) \ - __cpus_onto(&(dst), &(orig), &(relmap), NR_CPUS) -static inline void __cpus_onto(cpumask_t *dstp, const cpumask_t *origp, - const cpumask_t *relmapp, int nbits) -{ - bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits); -} - -#define cpus_fold(dst, orig, sz) \ - __cpus_fold(&(dst), &(orig), sz, NR_CPUS) -static inline void __cpus_fold(cpumask_t *dstp, const cpumask_t *origp, - int sz, int nbits) -{ - bitmap_fold(dstp->bits, origp->bits, sz, nbits); -} #endif /* !CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS */ #if NR_CPUS == 1 @@ -419,18 +313,14 @@ int __any_online_cpu(const cpumask_t *mask); #ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS #if NR_CPUS <= 64 -#define next_cpu_nr(n, src) next_cpu(n, src) -#define cpus_weight_nr(cpumask) cpus_weight(cpumask) #define for_each_cpu_mask_nr(cpu, mask) for_each_cpu_mask(cpu, mask) #else /* NR_CPUS > 64 */ int __next_cpu_nr(int n, const cpumask_t *srcp); -#define next_cpu_nr(n, src) __next_cpu_nr((n), &(src)) -#define cpus_weight_nr(cpumask) __cpus_weight(&(cpumask), nr_cpu_ids) #define for_each_cpu_mask_nr(cpu, mask) \ for ((cpu) = -1; \ - (cpu) = next_cpu_nr((cpu), (mask)), \ + (cpu) = __next_cpu_nr((cpu), &(mask)), \ (cpu) < nr_cpu_ids; ) #endif /* NR_CPUS > 64 */ -- cgit v1.2.3 From 6ba2ef7baac23a5d9bb85e28b882d16b439a2293 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 24 Sep 2009 09:34:53 -0600 Subject: cpumask: Move deprecated functions to end of header. The new ones have pretty kerneldoc. Move the old ones to the end to avoid confusing people. Signed-off-by: Rusty Russell Cc: benh@kernel.crashing.org --- include/linux/cpumask.h | 593 ++++++++++++++++++++---------------------------- 1 file changed, 252 insertions(+), 341 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index e162d13c65ab..789cf5f920ce 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -3,328 +3,37 @@ /* * Cpumasks provide a bitmap suitable for representing the - * set of CPU's in a system, one bit position per CPU number. - * - * The new cpumask_ ops take a "struct cpumask *"; the old ones - * use cpumask_t. - * - * See detailed comments in the file linux/bitmap.h describing the - * data type on which these cpumasks are based. - * - * For details of cpumask_scnprintf() and cpumask_parse_user(), - * see bitmap_scnprintf() and bitmap_parse_user() in lib/bitmap.c. - * For details of cpulist_scnprintf() and cpulist_parse(), see - * bitmap_scnlistprintf() and bitmap_parselist(), also in bitmap.c. - * - * . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . - * Note: The alternate operations with the suffix "_nr" are used - * to limit the range of the loop to nr_cpu_ids instead of - * NR_CPUS when NR_CPUS > 64 for performance reasons. - * If NR_CPUS is <= 64 then most assembler bitmask - * operators execute faster with a constant range, so - * the operator will continue to use NR_CPUS. - * - * Another consideration is that nr_cpu_ids is initialized - * to NR_CPUS and isn't lowered until the possible cpus are - * discovered (including any disabled cpus). So early uses - * will span the entire range of NR_CPUS. - * . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . - * - * The obsolescent cpumask operations are: - * - * void cpu_set(cpu, mask) turn on bit 'cpu' in mask - * void cpu_clear(cpu, mask) turn off bit 'cpu' in mask - * void cpus_setall(mask) set all bits - * void cpus_clear(mask) clear all bits - * int cpu_isset(cpu, mask) true iff bit 'cpu' set in mask - * int cpu_test_and_set(cpu, mask) test and set bit 'cpu' in mask - * - * int cpus_and(dst, src1, src2) dst = src1 & src2 [intersection] - * void cpus_or(dst, src1, src2) dst = src1 | src2 [union] - * void cpus_xor(dst, src1, src2) dst = src1 ^ src2 - * int cpus_andnot(dst, src1, src2) dst = src1 & ~src2 - * - * int cpus_equal(mask1, mask2) Does mask1 == mask2? - * int cpus_intersects(mask1, mask2) Do mask1 and mask2 intersect? - * int cpus_subset(mask1, mask2) Is mask1 a subset of mask2? - * int cpus_empty(mask) Is mask empty (no bits sets)? - * int cpus_weight(mask) Hamming weigh - number of set bits - * - * void cpus_shift_left(dst, src, n) Shift left - * - * int first_cpu(mask) Number lowest set bit, or NR_CPUS - * int next_cpu(cpu, mask) Next cpu past 'cpu', or NR_CPUS - * - * cpumask_t cpumask_of_cpu(cpu) Return cpumask with bit 'cpu' set - * (can be used as an lvalue) - * CPU_MASK_ALL Initializer - all bits set - * CPU_MASK_NONE Initializer - no bits set - * unsigned long *cpus_addr(mask) Array of unsigned long's in mask - * - * int cpumask_scnprintf(buf, len, mask) Format cpumask for printing - * int cpumask_parse_user(ubuf, ulen, mask) Parse ascii string as cpumask - * int cpulist_scnprintf(buf, len, mask) Format cpumask as list for printing - * int cpulist_parse(buf, map) Parse ascii string as cpulist - * - * for_each_cpu_mask(cpu, mask) for-loop cpu over mask using NR_CPUS - * for_each_cpu_mask_nr(cpu, mask) for-loop cpu over mask using nr_cpu_ids - * - * int num_online_cpus() Number of online CPUs - * int num_possible_cpus() Number of all possible CPUs - * int num_present_cpus() Number of present CPUs - * - * int cpu_online(cpu) Is some cpu online? - * int cpu_possible(cpu) Is some cpu possible? - * int cpu_present(cpu) Is some cpu present (can schedule)? - * - * int any_online_cpu(mask) First online cpu in mask - * - * for_each_possible_cpu(cpu) for-loop cpu over cpu_possible_map - * for_each_online_cpu(cpu) for-loop cpu over cpu_online_map - * for_each_present_cpu(cpu) for-loop cpu over cpu_present_map - * - * Subtlety: - * 1) The 'type-checked' form of cpu_isset() causes gcc (3.3.2, anyway) - * to generate slightly worse code. Note for example the additional - * 40 lines of assembly code compiling the "for each possible cpu" - * loops buried in the disk_stat_read() macros calls when compiling - * drivers/block/genhd.c (arch i386, CONFIG_SMP=y). So use a simple - * one-line #define for cpu_isset(), instead of wrapping an inline - * inside a macro, the way we do the other calls. + * set of CPU's in a system, one bit position per CPU number. In general, + * only nr_cpu_ids (<= NR_CPUS) bits are valid. */ - #include #include #include typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; -#ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS -#define cpu_set(cpu, dst) __cpu_set((cpu), &(dst)) -static inline void __cpu_set(int cpu, volatile cpumask_t *dstp) -{ - set_bit(cpu, dstp->bits); -} - -#define cpu_clear(cpu, dst) __cpu_clear((cpu), &(dst)) -static inline void __cpu_clear(int cpu, volatile cpumask_t *dstp) -{ - clear_bit(cpu, dstp->bits); -} - -#define cpus_setall(dst) __cpus_setall(&(dst), NR_CPUS) -static inline void __cpus_setall(cpumask_t *dstp, int nbits) -{ - bitmap_fill(dstp->bits, nbits); -} - -#define cpus_clear(dst) __cpus_clear(&(dst), NR_CPUS) -static inline void __cpus_clear(cpumask_t *dstp, int nbits) -{ - bitmap_zero(dstp->bits, nbits); -} - -/* No static inline type checking - see Subtlety (1) above. */ -#define cpu_isset(cpu, cpumask) test_bit((cpu), (cpumask).bits) - -#define cpu_test_and_set(cpu, cpumask) __cpu_test_and_set((cpu), &(cpumask)) -static inline int __cpu_test_and_set(int cpu, cpumask_t *addr) -{ - return test_and_set_bit(cpu, addr->bits); -} - -#define cpus_and(dst, src1, src2) __cpus_and(&(dst), &(src1), &(src2), NR_CPUS) -static inline int __cpus_and(cpumask_t *dstp, const cpumask_t *src1p, - const cpumask_t *src2p, int nbits) -{ - return bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); -} - -#define cpus_or(dst, src1, src2) __cpus_or(&(dst), &(src1), &(src2), NR_CPUS) -static inline void __cpus_or(cpumask_t *dstp, const cpumask_t *src1p, - const cpumask_t *src2p, int nbits) -{ - bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits); -} - -#define cpus_xor(dst, src1, src2) __cpus_xor(&(dst), &(src1), &(src2), NR_CPUS) -static inline void __cpus_xor(cpumask_t *dstp, const cpumask_t *src1p, - const cpumask_t *src2p, int nbits) -{ - bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits); -} - -#define cpus_andnot(dst, src1, src2) \ - __cpus_andnot(&(dst), &(src1), &(src2), NR_CPUS) -static inline int __cpus_andnot(cpumask_t *dstp, const cpumask_t *src1p, - const cpumask_t *src2p, int nbits) -{ - return bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); -} - -#define cpus_equal(src1, src2) __cpus_equal(&(src1), &(src2), NR_CPUS) -static inline int __cpus_equal(const cpumask_t *src1p, - const cpumask_t *src2p, int nbits) -{ - return bitmap_equal(src1p->bits, src2p->bits, nbits); -} - -#define cpus_intersects(src1, src2) __cpus_intersects(&(src1), &(src2), NR_CPUS) -static inline int __cpus_intersects(const cpumask_t *src1p, - const cpumask_t *src2p, int nbits) -{ - return bitmap_intersects(src1p->bits, src2p->bits, nbits); -} - -#define cpus_subset(src1, src2) __cpus_subset(&(src1), &(src2), NR_CPUS) -static inline int __cpus_subset(const cpumask_t *src1p, - const cpumask_t *src2p, int nbits) -{ - return bitmap_subset(src1p->bits, src2p->bits, nbits); -} - -#define cpus_empty(src) __cpus_empty(&(src), NR_CPUS) -static inline int __cpus_empty(const cpumask_t *srcp, int nbits) -{ - return bitmap_empty(srcp->bits, nbits); -} - -#define cpus_weight(cpumask) __cpus_weight(&(cpumask), NR_CPUS) -static inline int __cpus_weight(const cpumask_t *srcp, int nbits) -{ - return bitmap_weight(srcp->bits, nbits); -} - -#define cpus_shift_left(dst, src, n) \ - __cpus_shift_left(&(dst), &(src), (n), NR_CPUS) -static inline void __cpus_shift_left(cpumask_t *dstp, - const cpumask_t *srcp, int n, int nbits) -{ - bitmap_shift_left(dstp->bits, srcp->bits, n, nbits); -} -#endif /* !CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS */ - /** - * to_cpumask - convert an NR_CPUS bitmap to a struct cpumask * - * @bitmap: the bitmap + * cpumask_bits - get the bits in a cpumask + * @maskp: the struct cpumask * * - * There are a few places where cpumask_var_t isn't appropriate and - * static cpumasks must be used (eg. very early boot), yet we don't - * expose the definition of 'struct cpumask'. - * - * This does the conversion, and can be used as a constant initializer. + * You should only assume nr_cpu_ids bits of this mask are valid. This is + * a macro so it's const-correct. */ -#define to_cpumask(bitmap) \ - ((struct cpumask *)(1 ? (bitmap) \ - : (void *)sizeof(__check_is_bitmap(bitmap)))) - -static inline int __check_is_bitmap(const unsigned long *bitmap) -{ - return 1; -} - -/* - * Special-case data structure for "single bit set only" constant CPU masks. - * - * We pre-generate all the 64 (or 32) possible bit positions, with enough - * padding to the left and the right, and return the constant pointer - * appropriately offset. - */ -extern const unsigned long - cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)]; - -static inline const struct cpumask *get_cpu_mask(unsigned int cpu) -{ - const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG]; - p -= cpu / BITS_PER_LONG; - return to_cpumask(p); -} - -#ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS -/* - * In cases where we take the address of the cpumask immediately, - * gcc optimizes it out (it's a constant) and there's no huge stack - * variable created: - */ -#define cpumask_of_cpu(cpu) (*get_cpu_mask(cpu)) - - -#define CPU_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(NR_CPUS) - -#if NR_CPUS <= BITS_PER_LONG - -#define CPU_MASK_ALL \ -(cpumask_t) { { \ - [BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD \ -} } - -#else - -#define CPU_MASK_ALL \ -(cpumask_t) { { \ - [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ - [BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD \ -} } - -#endif - -#define CPU_MASK_NONE \ -(cpumask_t) { { \ - [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ -} } - -#define CPU_MASK_CPU0 \ -(cpumask_t) { { \ - [0] = 1UL \ -} } - -#define cpus_addr(src) ((src).bits) - -#endif /* !CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS */ +#define cpumask_bits(maskp) ((maskp)->bits) #if NR_CPUS == 1 - #define nr_cpu_ids 1 -#ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS -#define first_cpu(src) ({ (void)(src); 0; }) -#define next_cpu(n, src) ({ (void)(src); 1; }) -#define any_online_cpu(mask) 0 -#define for_each_cpu_mask(cpu, mask) \ - for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) -#endif /* !CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS */ -#else /* NR_CPUS > 1 */ - +#else extern int nr_cpu_ids; -#ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS -int __first_cpu(const cpumask_t *srcp); -int __next_cpu(int n, const cpumask_t *srcp); -int __any_online_cpu(const cpumask_t *mask); - -#define first_cpu(src) __first_cpu(&(src)) -#define next_cpu(n, src) __next_cpu((n), &(src)) -#define any_online_cpu(mask) __any_online_cpu(&(mask)) -#define for_each_cpu_mask(cpu, mask) \ - for ((cpu) = -1; \ - (cpu) = next_cpu((cpu), (mask)), \ - (cpu) < NR_CPUS; ) -#endif /* !CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS */ #endif -#ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS -#if NR_CPUS <= 64 - -#define for_each_cpu_mask_nr(cpu, mask) for_each_cpu_mask(cpu, mask) - -#else /* NR_CPUS > 64 */ - -int __next_cpu_nr(int n, const cpumask_t *srcp); -#define for_each_cpu_mask_nr(cpu, mask) \ - for ((cpu) = -1; \ - (cpu) = __next_cpu_nr((cpu), &(mask)), \ - (cpu) < nr_cpu_ids; ) - -#endif /* NR_CPUS > 64 */ -#endif /* !CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS */ +#ifdef CONFIG_CPUMASK_OFFSTACK +/* Assuming NR_CPUS is huge, a runtime limit is more efficient. Also, + * not all bits may be allocated. */ +#define nr_cpumask_bits nr_cpu_ids +#else +#define nr_cpumask_bits NR_CPUS +#endif /* * The following particular system cpumasks and operations manage @@ -371,12 +80,6 @@ extern const struct cpumask *const cpu_online_mask; extern const struct cpumask *const cpu_present_mask; extern const struct cpumask *const cpu_active_mask; -/* These strip const, as traditionally they weren't const. */ -#define cpu_possible_map (*(cpumask_t *)cpu_possible_mask) -#define cpu_online_map (*(cpumask_t *)cpu_online_mask) -#define cpu_present_map (*(cpumask_t *)cpu_present_mask) -#define cpu_active_map (*(cpumask_t *)cpu_active_mask) - #if NR_CPUS > 1 #define num_online_cpus() cpumask_weight(cpu_online_mask) #define num_possible_cpus() cpumask_weight(cpu_possible_mask) @@ -395,35 +98,6 @@ extern const struct cpumask *const cpu_active_mask; #define cpu_active(cpu) ((cpu) == 0) #endif -#define cpu_is_offline(cpu) unlikely(!cpu_online(cpu)) - -/* These are the new versions of the cpumask operators: passed by pointer. - * The older versions will be implemented in terms of these, then deleted. */ -#define cpumask_bits(maskp) ((maskp)->bits) - -#if NR_CPUS <= BITS_PER_LONG -#define CPU_BITS_ALL \ -{ \ - [BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD \ -} - -#else /* NR_CPUS > BITS_PER_LONG */ - -#define CPU_BITS_ALL \ -{ \ - [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ - [BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD \ -} -#endif /* NR_CPUS > BITS_PER_LONG */ - -#ifdef CONFIG_CPUMASK_OFFSTACK -/* Assuming NR_CPUS is huge, a runtime limit is more efficient. Also, - * not all bits may be allocated. */ -#define nr_cpumask_bits nr_cpu_ids -#else -#define nr_cpumask_bits NR_CPUS -#endif - /* verify cpu argument to cpumask_* operators */ static inline unsigned int cpumask_check(unsigned int cpu) { @@ -984,4 +658,241 @@ void set_cpu_active(unsigned int cpu, bool active); void init_cpu_present(const struct cpumask *src); void init_cpu_possible(const struct cpumask *src); void init_cpu_online(const struct cpumask *src); + +/** + * to_cpumask - convert an NR_CPUS bitmap to a struct cpumask * + * @bitmap: the bitmap + * + * There are a few places where cpumask_var_t isn't appropriate and + * static cpumasks must be used (eg. very early boot), yet we don't + * expose the definition of 'struct cpumask'. + * + * This does the conversion, and can be used as a constant initializer. + */ +#define to_cpumask(bitmap) \ + ((struct cpumask *)(1 ? (bitmap) \ + : (void *)sizeof(__check_is_bitmap(bitmap)))) + +static inline int __check_is_bitmap(const unsigned long *bitmap) +{ + return 1; +} + +/* + * Special-case data structure for "single bit set only" constant CPU masks. + * + * We pre-generate all the 64 (or 32) possible bit positions, with enough + * padding to the left and the right, and return the constant pointer + * appropriately offset. + */ +extern const unsigned long + cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)]; + +static inline const struct cpumask *get_cpu_mask(unsigned int cpu) +{ + const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG]; + p -= cpu / BITS_PER_LONG; + return to_cpumask(p); +} + +#define cpu_is_offline(cpu) unlikely(!cpu_online(cpu)) + +#if NR_CPUS <= BITS_PER_LONG +#define CPU_BITS_ALL \ +{ \ + [BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD \ +} + +#else /* NR_CPUS > BITS_PER_LONG */ + +#define CPU_BITS_ALL \ +{ \ + [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ + [BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD \ +} +#endif /* NR_CPUS > BITS_PER_LONG */ + +/* + * + * From here down, all obsolete. Use cpumask_ variants! + * + */ +#ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS +/* These strip const, as traditionally they weren't const. */ +#define cpu_possible_map (*(cpumask_t *)cpu_possible_mask) +#define cpu_online_map (*(cpumask_t *)cpu_online_mask) +#define cpu_present_map (*(cpumask_t *)cpu_present_mask) +#define cpu_active_map (*(cpumask_t *)cpu_active_mask) + +#define cpumask_of_cpu(cpu) (*get_cpu_mask(cpu)) + +#define CPU_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(NR_CPUS) + +#if NR_CPUS <= BITS_PER_LONG + +#define CPU_MASK_ALL \ +(cpumask_t) { { \ + [BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD \ +} } + +#else + +#define CPU_MASK_ALL \ +(cpumask_t) { { \ + [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ + [BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD \ +} } + +#endif + +#define CPU_MASK_NONE \ +(cpumask_t) { { \ + [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ +} } + +#define CPU_MASK_CPU0 \ +(cpumask_t) { { \ + [0] = 1UL \ +} } + +#if NR_CPUS == 1 +#define first_cpu(src) ({ (void)(src); 0; }) +#define next_cpu(n, src) ({ (void)(src); 1; }) +#define any_online_cpu(mask) 0 +#define for_each_cpu_mask(cpu, mask) \ + for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) +#else /* NR_CPUS > 1 */ +int __first_cpu(const cpumask_t *srcp); +int __next_cpu(int n, const cpumask_t *srcp); +int __any_online_cpu(const cpumask_t *mask); + +#define first_cpu(src) __first_cpu(&(src)) +#define next_cpu(n, src) __next_cpu((n), &(src)) +#define any_online_cpu(mask) __any_online_cpu(&(mask)) +#define for_each_cpu_mask(cpu, mask) \ + for ((cpu) = -1; \ + (cpu) = next_cpu((cpu), (mask)), \ + (cpu) < NR_CPUS; ) +#endif /* SMP */ + +#if NR_CPUS <= 64 + +#define for_each_cpu_mask_nr(cpu, mask) for_each_cpu_mask(cpu, mask) + +#else /* NR_CPUS > 64 */ + +int __next_cpu_nr(int n, const cpumask_t *srcp); +#define for_each_cpu_mask_nr(cpu, mask) \ + for ((cpu) = -1; \ + (cpu) = __next_cpu_nr((cpu), &(mask)), \ + (cpu) < nr_cpu_ids; ) + +#endif /* NR_CPUS > 64 */ + +#define cpus_addr(src) ((src).bits) + +#define cpu_set(cpu, dst) __cpu_set((cpu), &(dst)) +static inline void __cpu_set(int cpu, volatile cpumask_t *dstp) +{ + set_bit(cpu, dstp->bits); +} + +#define cpu_clear(cpu, dst) __cpu_clear((cpu), &(dst)) +static inline void __cpu_clear(int cpu, volatile cpumask_t *dstp) +{ + clear_bit(cpu, dstp->bits); +} + +#define cpus_setall(dst) __cpus_setall(&(dst), NR_CPUS) +static inline void __cpus_setall(cpumask_t *dstp, int nbits) +{ + bitmap_fill(dstp->bits, nbits); +} + +#define cpus_clear(dst) __cpus_clear(&(dst), NR_CPUS) +static inline void __cpus_clear(cpumask_t *dstp, int nbits) +{ + bitmap_zero(dstp->bits, nbits); +} + +/* No static inline type checking - see Subtlety (1) above. */ +#define cpu_isset(cpu, cpumask) test_bit((cpu), (cpumask).bits) + +#define cpu_test_and_set(cpu, cpumask) __cpu_test_and_set((cpu), &(cpumask)) +static inline int __cpu_test_and_set(int cpu, cpumask_t *addr) +{ + return test_and_set_bit(cpu, addr->bits); +} + +#define cpus_and(dst, src1, src2) __cpus_and(&(dst), &(src1), &(src2), NR_CPUS) +static inline int __cpus_and(cpumask_t *dstp, const cpumask_t *src1p, + const cpumask_t *src2p, int nbits) +{ + return bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); +} + +#define cpus_or(dst, src1, src2) __cpus_or(&(dst), &(src1), &(src2), NR_CPUS) +static inline void __cpus_or(cpumask_t *dstp, const cpumask_t *src1p, + const cpumask_t *src2p, int nbits) +{ + bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits); +} + +#define cpus_xor(dst, src1, src2) __cpus_xor(&(dst), &(src1), &(src2), NR_CPUS) +static inline void __cpus_xor(cpumask_t *dstp, const cpumask_t *src1p, + const cpumask_t *src2p, int nbits) +{ + bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits); +} + +#define cpus_andnot(dst, src1, src2) \ + __cpus_andnot(&(dst), &(src1), &(src2), NR_CPUS) +static inline int __cpus_andnot(cpumask_t *dstp, const cpumask_t *src1p, + const cpumask_t *src2p, int nbits) +{ + return bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); +} + +#define cpus_equal(src1, src2) __cpus_equal(&(src1), &(src2), NR_CPUS) +static inline int __cpus_equal(const cpumask_t *src1p, + const cpumask_t *src2p, int nbits) +{ + return bitmap_equal(src1p->bits, src2p->bits, nbits); +} + +#define cpus_intersects(src1, src2) __cpus_intersects(&(src1), &(src2), NR_CPUS) +static inline int __cpus_intersects(const cpumask_t *src1p, + const cpumask_t *src2p, int nbits) +{ + return bitmap_intersects(src1p->bits, src2p->bits, nbits); +} + +#define cpus_subset(src1, src2) __cpus_subset(&(src1), &(src2), NR_CPUS) +static inline int __cpus_subset(const cpumask_t *src1p, + const cpumask_t *src2p, int nbits) +{ + return bitmap_subset(src1p->bits, src2p->bits, nbits); +} + +#define cpus_empty(src) __cpus_empty(&(src), NR_CPUS) +static inline int __cpus_empty(const cpumask_t *srcp, int nbits) +{ + return bitmap_empty(srcp->bits, nbits); +} + +#define cpus_weight(cpumask) __cpus_weight(&(cpumask), NR_CPUS) +static inline int __cpus_weight(const cpumask_t *srcp, int nbits) +{ + return bitmap_weight(srcp->bits, nbits); +} + +#define cpus_shift_left(dst, src, n) \ + __cpus_shift_left(&(dst), &(src), (n), NR_CPUS) +static inline void __cpus_shift_left(cpumask_t *dstp, + const cpumask_t *srcp, int n, int nbits) +{ + bitmap_shift_left(dstp->bits, srcp->bits, n, nbits); +} +#endif /* !CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS */ + #endif /* __LINUX_CPUMASK_H */ -- cgit v1.2.3 From 2bcd57ab61e7cabed626226a3771617981c11ce1 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 24 Sep 2009 04:22:25 +0400 Subject: headers: utsname.h redux * remove asm/atomic.h inclusion from linux/utsname.h -- not needed after kref conversion * remove linux/utsname.h inclusion from files which do not need it NOTE: it looks like fs/binfmt_elf.c do not need utsname.h, however due to some personality stuff it _is_ needed -- cowardly leave ELF-related headers and files alone. Signed-off-by: Alexey Dobriyan Signed-off-by: Linus Torvalds --- arch/alpha/kernel/process.c | 1 - arch/arm/kernel/sys_arm.c | 1 - arch/frv/kernel/sys_frv.c | 1 - arch/h8300/kernel/sys_h8300.c | 1 - arch/m68k/kernel/sys_m68k.c | 1 - arch/m68knommu/kernel/sys_m68k.c | 1 - arch/microblaze/kernel/sys_microblaze.c | 1 - arch/mn10300/kernel/sys_mn10300.c | 1 - arch/parisc/kernel/sys_parisc32.c | 1 - arch/powerpc/kernel/setup-common.c | 1 - arch/powerpc/kernel/sys_ppc32.c | 1 - arch/s390/kernel/compat_linux.c | 1 - arch/s390/kernel/process.c | 1 - arch/sh/kernel/sys_sh32.c | 1 - arch/sh/kernel/sys_sh64.c | 1 - arch/sparc/kernel/sys_sparc32.c | 1 - arch/sparc/kernel/systbls.h | 3 ++- arch/x86/kernel/dumpstack_32.c | 1 - arch/x86/kernel/dumpstack_64.c | 1 - arch/x86/kernel/traps.c | 1 - drivers/media/video/usbvision/usbvision-core.c | 1 - drivers/media/video/usbvision/usbvision-i2c.c | 1 - drivers/media/video/usbvision/usbvision-video.c | 1 - drivers/s390/char/zcore.c | 1 - drivers/usb/gadget/f_loopback.c | 1 - drivers/usb/gadget/f_obex.c | 1 - drivers/usb/gadget/f_sourcesink.c | 1 - drivers/usb/gadget/u_audio.c | 1 - drivers/usb/gadget/u_ether.c | 1 - fs/gfs2/ops_inode.c | 1 - fs/lockd/xdr.c | 1 - fs/lockd/xdr4.c | 1 - fs/nfs/nfs2xdr.c | 1 - fs/nfs/nfs3proc.c | 1 - fs/nfs/nfs3xdr.c | 1 - fs/nfs/nfs4proc.c | 1 - fs/nfs/nfs4xdr.c | 1 - fs/nfs/proc.c | 1 - fs/nfsd/nfs4idmap.c | 1 - fs/ocfs2/dlm/dlmast.c | 1 - fs/ocfs2/dlm/dlmconvert.c | 1 - fs/ocfs2/dlm/dlmdebug.c | 1 - fs/ocfs2/dlm/dlmdomain.c | 1 - fs/ocfs2/dlm/dlmlock.c | 1 - fs/ocfs2/dlm/dlmmaster.c | 1 - fs/ocfs2/dlm/dlmrecovery.c | 1 - fs/ocfs2/dlm/dlmthread.c | 1 - fs/ocfs2/dlm/dlmunlock.c | 1 - fs/ocfs2/super.c | 1 - fs/ocfs2/symlink.c | 1 - include/linux/utsname.h | 1 - init/main.c | 1 - kernel/power/swap.c | 1 - kernel/sysctl.c | 1 - kernel/uid16.c | 1 - net/sunrpc/auth_null.c | 1 - 56 files changed, 2 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index 3a2fb7a02db4..289039bb6bb2 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c index b3ec641b5cf8..78ecaac65206 100644 --- a/arch/arm/kernel/sys_arm.c +++ b/arch/arm/kernel/sys_arm.c @@ -25,7 +25,6 @@ #include #include #include -#include #include #include diff --git a/arch/frv/kernel/sys_frv.c b/arch/frv/kernel/sys_frv.c index baadc97f8627..2b6b5289cdcc 100644 --- a/arch/frv/kernel/sys_frv.c +++ b/arch/frv/kernel/sys_frv.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include diff --git a/arch/h8300/kernel/sys_h8300.c b/arch/h8300/kernel/sys_h8300.c index 2745656dcc52..8cb5d73a0e35 100644 --- a/arch/h8300/kernel/sys_h8300.c +++ b/arch/h8300/kernel/sys_h8300.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c index 7f54efaf60bb..7deb402bfc75 100644 --- a/arch/m68k/kernel/sys_m68k.c +++ b/arch/m68k/kernel/sys_m68k.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include diff --git a/arch/m68knommu/kernel/sys_m68k.c b/arch/m68knommu/kernel/sys_m68k.c index 700281638629..efdd090778a3 100644 --- a/arch/m68knommu/kernel/sys_m68k.c +++ b/arch/m68knommu/kernel/sys_m68k.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include diff --git a/arch/microblaze/kernel/sys_microblaze.c b/arch/microblaze/kernel/sys_microblaze.c index b96f1682bb24..07cabed4b947 100644 --- a/arch/microblaze/kernel/sys_microblaze.c +++ b/arch/microblaze/kernel/sys_microblaze.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/mn10300/kernel/sys_mn10300.c b/arch/mn10300/kernel/sys_mn10300.c index 3e52a1054327..8ca5af00334c 100644 --- a/arch/mn10300/kernel/sys_mn10300.c +++ b/arch/mn10300/kernel/sys_mn10300.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c index 92a0acaa0d12..561388b17c91 100644 --- a/arch/parisc/kernel/sys_parisc32.c +++ b/arch/parisc/kernel/sys_parisc32.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 1d5570a1e456..74cd1a7d0d4b 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -24,7 +24,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index 1cc5e9e5da96..b97c2d67f4ac 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 5519cb745106..0debcec23a39 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -24,7 +24,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 59fe6ecc6ed3..5417eb57271a 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -27,7 +27,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/sh/kernel/sys_sh32.c b/arch/sh/kernel/sys_sh32.c index 63ba12836eae..eb68bfdd86e6 100644 --- a/arch/sh/kernel/sys_sh32.c +++ b/arch/sh/kernel/sys_sh32.c @@ -9,7 +9,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/sh/kernel/sys_sh64.c b/arch/sh/kernel/sys_sh64.c index 91fb8445a5a0..287235768bc5 100644 --- a/arch/sh/kernel/sys_sh64.c +++ b/arch/sh/kernel/sys_sh64.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c index f5000a460c05..04e28b2671c8 100644 --- a/arch/sparc/kernel/sys_sparc32.c +++ b/arch/sparc/kernel/sys_sparc32.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/sparc/kernel/systbls.h b/arch/sparc/kernel/systbls.h index 15c2d752b2bc..a63c5d2d9849 100644 --- a/arch/sparc/kernel/systbls.h +++ b/arch/sparc/kernel/systbls.h @@ -3,10 +3,11 @@ #include #include -#include #include #include +struct new_utsname; + extern asmlinkage unsigned long sys_getpagesize(void); extern asmlinkage unsigned long sparc_brk(unsigned long brk); extern asmlinkage long sparc_pipe(struct pt_regs *regs); diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index bca5fba91c9e..f7dd2a7c3bf4 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -5,7 +5,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 54b0a3276766..a071e6be177e 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -5,7 +5,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 9346e102338d..a665c71352b8 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/media/video/usbvision/usbvision-core.c b/drivers/media/video/usbvision/usbvision-core.c index 6ba16abeebdd..e0f91e4ab653 100644 --- a/drivers/media/video/usbvision/usbvision-core.c +++ b/drivers/media/video/usbvision/usbvision-core.c @@ -28,7 +28,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/media/video/usbvision/usbvision-i2c.c b/drivers/media/video/usbvision/usbvision-i2c.c index f97fd06d5948..c19f51dba2ee 100644 --- a/drivers/media/video/usbvision/usbvision-i2c.c +++ b/drivers/media/video/usbvision/usbvision-i2c.c @@ -28,7 +28,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/media/video/usbvision/usbvision-video.c b/drivers/media/video/usbvision/usbvision-video.c index 90d9b5c0e9a7..a2a50d608a3f 100644 --- a/drivers/media/video/usbvision/usbvision-video.c +++ b/drivers/media/video/usbvision/usbvision-video.c @@ -52,7 +52,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c index c431198bdbc4..82daa3c1dc9c 100644 --- a/drivers/s390/char/zcore.c +++ b/drivers/s390/char/zcore.c @@ -14,7 +14,6 @@ #include #include -#include #include #include #include diff --git a/drivers/usb/gadget/f_loopback.c b/drivers/usb/gadget/f_loopback.c index eb6ddfc20857..6cb29d3df575 100644 --- a/drivers/usb/gadget/f_loopback.c +++ b/drivers/usb/gadget/f_loopback.c @@ -22,7 +22,6 @@ /* #define VERBOSE_DEBUG */ #include -#include #include #include "g_zero.h" diff --git a/drivers/usb/gadget/f_obex.c b/drivers/usb/gadget/f_obex.c index 46d6266f30ec..b4a3ba654ea5 100644 --- a/drivers/usb/gadget/f_obex.c +++ b/drivers/usb/gadget/f_obex.c @@ -24,7 +24,6 @@ /* #define VERBOSE_DEBUG */ #include -#include #include #include "u_serial.h" diff --git a/drivers/usb/gadget/f_sourcesink.c b/drivers/usb/gadget/f_sourcesink.c index bffe91d525f9..09cba273d2db 100644 --- a/drivers/usb/gadget/f_sourcesink.c +++ b/drivers/usb/gadget/f_sourcesink.c @@ -22,7 +22,6 @@ /* #define VERBOSE_DEBUG */ #include -#include #include #include "g_zero.h" diff --git a/drivers/usb/gadget/u_audio.c b/drivers/usb/gadget/u_audio.c index b5200d551458..8252595d619d 100644 --- a/drivers/usb/gadget/u_audio.c +++ b/drivers/usb/gadget/u_audio.c @@ -10,7 +10,6 @@ */ #include -#include #include #include #include diff --git a/drivers/usb/gadget/u_ether.c b/drivers/usb/gadget/u_ether.c index f8751ff863cd..2fc02bd95848 100644 --- a/drivers/usb/gadget/u_ether.c +++ b/drivers/usb/gadget/u_ether.c @@ -23,7 +23,6 @@ /* #define VERBOSE_DEBUG */ #include -#include #include #include #include diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c index c3ac18054057..247436c10deb 100644 --- a/fs/gfs2/ops_inode.c +++ b/fs/gfs2/ops_inode.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index 0336f2beacde..b583ab0a4cbb 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -8,7 +8,6 @@ #include #include -#include #include #include diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index e1d528653192..ad9dbbc9145d 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -9,7 +9,6 @@ #include #include -#include #include #include diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index c862c9340f9a..5e078b222b4e 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index ee6a13f05443..3f8881d1a050 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -7,7 +7,6 @@ */ #include -#include #include #include #include diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 35869a4921f1..5fe5492fbd29 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index be6544aef41f..ed7c269e2514 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -36,7 +36,6 @@ */ #include -#include #include #include #include diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index cfc30d362f94..83ad47cbdd8a 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -39,7 +39,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 7be72d90d49d..ef583854d8d0 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -32,7 +32,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index cdfa86fa1471..ba2c199592fd 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -38,7 +38,6 @@ #include #include -#include #include #include #include diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c index 81eff8e58322..01cf8cc3d286 100644 --- a/fs/ocfs2/dlm/dlmast.c +++ b/fs/ocfs2/dlm/dlmast.c @@ -30,7 +30,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c index 75997b4deaf3..ca96bce50e18 100644 --- a/fs/ocfs2/dlm/dlmconvert.c +++ b/fs/ocfs2/dlm/dlmconvert.c @@ -30,7 +30,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c index c5c88124096d..ca46002ec10e 100644 --- a/fs/ocfs2/dlm/dlmdebug.c +++ b/fs/ocfs2/dlm/dlmdebug.c @@ -27,7 +27,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 4d9e6b288dd8..0334000676d3 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -28,7 +28,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c index 83a9f2972ac8..437698e9465f 100644 --- a/fs/ocfs2/dlm/dlmlock.c +++ b/fs/ocfs2/dlm/dlmlock.c @@ -30,7 +30,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index f8b653fcd4dd..83bcaf266b35 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -30,7 +30,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 43e6e3280569..d9fa3d22e17c 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -30,7 +30,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c index 98569e86c613..52ec020ea78b 100644 --- a/fs/ocfs2/dlm/dlmthread.c +++ b/fs/ocfs2/dlm/dlmthread.c @@ -30,7 +30,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c index 756f5b0998e0..00f53b2aea76 100644 --- a/fs/ocfs2/dlm/dlmunlock.c +++ b/fs/ocfs2/dlm/dlmunlock.c @@ -30,7 +30,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 24feb449a1dc..4cc3c890a2cd 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -28,7 +28,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/ocfs2/symlink.c b/fs/ocfs2/symlink.c index 579dd1b1110f..e3421030a69f 100644 --- a/fs/ocfs2/symlink.c +++ b/fs/ocfs2/symlink.c @@ -38,7 +38,6 @@ #include #include #include -#include #include #define MLOG_MASK_PREFIX ML_NAMEI diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 3656b300de3a..69f39974c041 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -36,7 +36,6 @@ struct new_utsname { #include #include #include -#include struct uts_namespace { struct kref kref; diff --git a/init/main.c b/init/main.c index 6107223124e4..76961db298f0 100644 --- a/init/main.c +++ b/init/main.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 8ba052c86d48..b101cdc4df3f 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -13,7 +13,6 @@ #include #include -#include #include #include #include diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 0dfaa47d7cb6..7f4f57bea4ce 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -26,7 +26,6 @@ #include #include #include -#include #include #include #include diff --git a/kernel/uid16.c b/kernel/uid16.c index 0314501688b9..419209893d87 100644 --- a/kernel/uid16.c +++ b/kernel/uid16.c @@ -4,7 +4,6 @@ */ #include -#include #include #include #include diff --git a/net/sunrpc/auth_null.c b/net/sunrpc/auth_null.c index c70dd7f5258e..1db618f56ecb 100644 --- a/net/sunrpc/auth_null.c +++ b/net/sunrpc/auth_null.c @@ -8,7 +8,6 @@ #include #include -#include #include #ifdef RPC_DEBUG -- 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 --- fs/hugetlbfs/inode.c | 33 ++++----------------------------- fs/inode.c | 21 +++++++++++++++++++-- include/linux/fs.h | 1 + 3 files changed, 24 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index eba6d552d9c9..478a169a262d 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -380,36 +380,11 @@ static void hugetlbfs_delete_inode(struct inode *inode) static void hugetlbfs_forget_inode(struct inode *inode) __releases(inode_lock) { - struct super_block *sb = inode->i_sb; - - if (!hlist_unhashed(&inode->i_hash)) { - if (!(inode->i_state & (I_DIRTY|I_SYNC))) - list_move(&inode->i_list, &inode_unused); - inodes_stat.nr_unused++; - if (!sb || (sb->s_flags & MS_ACTIVE)) { - spin_unlock(&inode_lock); - return; - } - inode->i_state |= I_WILL_FREE; - spin_unlock(&inode_lock); - /* - * write_inode_now is a noop as we set BDI_CAP_NO_WRITEBACK - * in our backing_dev_info. - */ - write_inode_now(inode, 1); - spin_lock(&inode_lock); - inode->i_state &= ~I_WILL_FREE; - inodes_stat.nr_unused--; - hlist_del_init(&inode->i_hash); + if (generic_detach_inode(inode)) { + truncate_hugepages(inode, 0); + clear_inode(inode); + destroy_inode(inode); } - list_del_init(&inode->i_list); - list_del_init(&inode->i_sb_list); - inode->i_state |= I_FREEING; - inodes_stat.nr_inodes--; - spin_unlock(&inode_lock); - truncate_hugepages(inode, 0); - clear_inode(inode); - destroy_inode(inode); } static void hugetlbfs_drop_inode(struct inode *inode) diff --git a/fs/inode.c b/fs/inode.c index 07d775ea6161..fa506d539653 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1241,7 +1241,16 @@ void generic_delete_inode(struct inode *inode) } EXPORT_SYMBOL(generic_delete_inode); -static void generic_forget_inode(struct inode *inode) +/** + * generic_detach_inode - remove inode from inode lists + * @inode: inode to remove + * + * Remove inode from inode lists, write it if it's dirty. This is just an + * internal VFS helper exported for hugetlbfs. Do not use! + * + * Returns 1 if inode should be completely destroyed. + */ +int generic_detach_inode(struct inode *inode) { struct super_block *sb = inode->i_sb; @@ -1251,7 +1260,7 @@ static void generic_forget_inode(struct inode *inode) inodes_stat.nr_unused++; if (sb->s_flags & MS_ACTIVE) { spin_unlock(&inode_lock); - return; + return 0; } WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_WILL_FREE; @@ -1269,6 +1278,14 @@ static void generic_forget_inode(struct inode *inode) inode->i_state |= I_FREEING; inodes_stat.nr_inodes--; spin_unlock(&inode_lock); + return 1; +} +EXPORT_SYMBOL_GPL(generic_detach_inode); + +static void generic_forget_inode(struct inode *inode) +{ + if (!generic_detach_inode(inode)) + return; if (inode->i_data.nrpages) truncate_inode_pages(&inode->i_data, 0); clear_inode(inode); 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 --- fs/super.c | 10 ++++++++++ include/linux/fs.h | 2 +- 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/super.c b/fs/super.c index 0e7207b9815c..4906e2d8f400 100644 --- a/fs/super.c +++ b/fs/super.c @@ -892,6 +892,16 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void if (error) goto out_sb; + /* + * filesystems should never set s_maxbytes larger than MAX_LFS_FILESIZE + * but s_maxbytes was an unsigned long long for many releases. Throw + * this warning for a little while to try and catch filesystems that + * violate this rule. This warning should be either removed or + * converted to a BUG() in 2.6.34. + */ + WARN((mnt->mnt_sb->s_maxbytes < 0), "%s set sb->s_maxbytes to " + "negative value (%lld)\n", type->name, mnt->mnt_sb->s_maxbytes); + mnt->mnt_mountpoint = mnt->mnt_root; mnt->mnt_parent = mnt; up_write(&mnt->mnt_sb->s_umount); 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 --- fs/seq_file.c | 75 +++++++++++++++++++++++++----------------------- include/linux/seq_file.h | 38 ++++++++++++++++++++++++ 2 files changed, 77 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/fs/seq_file.c b/fs/seq_file.c index 66efd0aa8fb3..eae7d9dbf3ff 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -429,20 +429,21 @@ EXPORT_SYMBOL(mangle_path); */ int seq_path(struct seq_file *m, struct path *path, char *esc) { - if (m->count < m->size) { - char *s = m->buf + m->count; - char *p = d_path(path, s, m->size - m->count); + char *buf; + size_t size = seq_get_buf(m, &buf); + int res = -1; + + if (size) { + char *p = d_path(path, buf, size); if (!IS_ERR(p)) { - s = mangle_path(s, p, esc); - if (s) { - p = m->buf + m->count; - m->count = s - m->buf; - return s - p; - } + char *end = mangle_path(buf, p, esc); + if (end) + res = end - buf; } } - m->count = m->size; - return -1; + seq_commit(m, res); + + return res; } EXPORT_SYMBOL(seq_path); @@ -454,27 +455,28 @@ EXPORT_SYMBOL(seq_path); int seq_path_root(struct seq_file *m, struct path *path, struct path *root, char *esc) { - int err = -ENAMETOOLONG; - if (m->count < m->size) { - char *s = m->buf + m->count; + char *buf; + size_t size = seq_get_buf(m, &buf); + int res = -ENAMETOOLONG; + + if (size) { char *p; spin_lock(&dcache_lock); - p = __d_path(path, root, s, m->size - m->count); + p = __d_path(path, root, buf, size); spin_unlock(&dcache_lock); - err = PTR_ERR(p); + res = PTR_ERR(p); if (!IS_ERR(p)) { - s = mangle_path(s, p, esc); - if (s) { - p = m->buf + m->count; - m->count = s - m->buf; - return 0; - } - err = -ENAMETOOLONG; + char *end = mangle_path(buf, p, esc); + if (end) + res = end - buf; + else + res = -ENAMETOOLONG; } } - m->count = m->size; - return err; + seq_commit(m, res); + + return res < 0 ? res : 0; } /* @@ -482,20 +484,21 @@ int seq_path_root(struct seq_file *m, struct path *path, struct path *root, */ int seq_dentry(struct seq_file *m, struct dentry *dentry, char *esc) { - if (m->count < m->size) { - char *s = m->buf + m->count; - char *p = dentry_path(dentry, s, m->size - m->count); + char *buf; + size_t size = seq_get_buf(m, &buf); + int res = -1; + + if (size) { + char *p = dentry_path(dentry, buf, size); if (!IS_ERR(p)) { - s = mangle_path(s, p, esc); - if (s) { - p = m->buf + m->count; - m->count = s - m->buf; - return s - p; - } + char *end = mangle_path(buf, p, esc); + if (end) + res = end - buf; } } - m->count = m->size; - return -1; + seq_commit(m, res); + + return res; } int seq_bitmap(struct seq_file *m, const unsigned long *bits, 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 --- fs/block_dev.c | 8 +------- fs/super.c | 9 +++++++-- include/linux/fs.h | 1 - 3 files changed, 8 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/block_dev.c b/fs/block_dev.c index 5d1ed50bd46c..22506eb4a58e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -216,8 +216,6 @@ EXPORT_SYMBOL(fsync_bdev); * freeze_bdev -- lock a filesystem and force it into a consistent state * @bdev: blockdevice to lock * - * This takes the block device bd_mount_sem to make sure no new mounts - * happen on bdev until thaw_bdev() is called. * If a superblock is found on this device, we take the s_umount semaphore * on it to make sure nobody unmounts until the snapshot creation is done. * The reference counter (bd_fsfreeze_count) guarantees that only the last @@ -240,7 +238,6 @@ struct super_block *freeze_bdev(struct block_device *bdev) } bdev->bd_fsfreeze_count++; - down(&bdev->bd_mount_sem); sb = get_super(bdev); if (sb && !(sb->s_flags & MS_RDONLY)) { sb->s_frozen = SB_FREEZE_WRITE; @@ -260,7 +257,6 @@ struct super_block *freeze_bdev(struct block_device *bdev) "VFS:Filesystem freeze failed\n"); sb->s_frozen = SB_UNFROZEN; drop_super(sb); - up(&bdev->bd_mount_sem); bdev->bd_fsfreeze_count--; mutex_unlock(&bdev->bd_fsfreeze_mutex); return ERR_PTR(error); @@ -271,7 +267,7 @@ struct super_block *freeze_bdev(struct block_device *bdev) sync_blockdev(bdev); mutex_unlock(&bdev->bd_fsfreeze_mutex); - return sb; /* thaw_bdev releases s->s_umount and bd_mount_sem */ + return sb; /* thaw_bdev releases s->s_umount */ } EXPORT_SYMBOL(freeze_bdev); @@ -321,7 +317,6 @@ int thaw_bdev(struct block_device *bdev, struct super_block *sb) drop_super(sb); } - up(&bdev->bd_mount_sem); mutex_unlock(&bdev->bd_fsfreeze_mutex); return 0; } @@ -430,7 +425,6 @@ static void init_once(void *foo) memset(bdev, 0, sizeof(*bdev)); mutex_init(&bdev->bd_mutex); - sema_init(&bdev->bd_mount_sem, 1); INIT_LIST_HEAD(&bdev->bd_inodes); INIT_LIST_HEAD(&bdev->bd_list); #ifdef CONFIG_SYSFS diff --git a/fs/super.c b/fs/super.c index 4906e2d8f400..1cb26a3e3df0 100644 --- a/fs/super.c +++ b/fs/super.c @@ -743,9 +743,14 @@ int get_sb_bdev(struct file_system_type *fs_type, * will protect the lockfs code from trying to start a snapshot * while we are mounting */ - down(&bdev->bd_mount_sem); + mutex_lock(&bdev->bd_fsfreeze_mutex); + if (bdev->bd_fsfreeze_count > 0) { + mutex_unlock(&bdev->bd_fsfreeze_mutex); + error = -EBUSY; + goto error_bdev; + } s = sget(fs_type, test_bdev_super, set_bdev_super, bdev); - up(&bdev->bd_mount_sem); + mutex_unlock(&bdev->bd_fsfreeze_mutex); if (IS_ERR(s)) goto error_s; 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 --- fs/block_dev.c | 132 +++++++++++++++++++++++++++++------------------------ fs/super.c | 48 ++++++++++++++++++- include/linux/fs.h | 1 + 3 files changed, 120 insertions(+), 61 deletions(-) (limited to 'include/linux') diff --git a/fs/block_dev.c b/fs/block_dev.c index 22506eb4a58e..9cf4b926f8e4 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -230,43 +230,54 @@ struct super_block *freeze_bdev(struct block_device *bdev) int error = 0; mutex_lock(&bdev->bd_fsfreeze_mutex); - if (bdev->bd_fsfreeze_count > 0) { - bdev->bd_fsfreeze_count++; + if (++bdev->bd_fsfreeze_count > 1) { + /* + * We don't even need to grab a reference - the first call + * to freeze_bdev grab an active reference and only the last + * thaw_bdev drops it. + */ sb = get_super(bdev); + drop_super(sb); mutex_unlock(&bdev->bd_fsfreeze_mutex); return sb; } - bdev->bd_fsfreeze_count++; - - sb = get_super(bdev); - if (sb && !(sb->s_flags & MS_RDONLY)) { - sb->s_frozen = SB_FREEZE_WRITE; - smp_wmb(); - - sync_filesystem(sb); - - sb->s_frozen = SB_FREEZE_TRANS; - smp_wmb(); - - sync_blockdev(sb->s_bdev); - - if (sb->s_op->freeze_fs) { - error = sb->s_op->freeze_fs(sb); - if (error) { - printk(KERN_ERR - "VFS:Filesystem freeze failed\n"); - sb->s_frozen = SB_UNFROZEN; - drop_super(sb); - bdev->bd_fsfreeze_count--; - mutex_unlock(&bdev->bd_fsfreeze_mutex); - return ERR_PTR(error); - } + + sb = get_active_super(bdev); + if (!sb) + goto out; + if (sb->s_flags & MS_RDONLY) { + deactivate_locked_super(sb); + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return sb; + } + + sb->s_frozen = SB_FREEZE_WRITE; + smp_wmb(); + + sync_filesystem(sb); + + sb->s_frozen = SB_FREEZE_TRANS; + smp_wmb(); + + sync_blockdev(sb->s_bdev); + + if (sb->s_op->freeze_fs) { + error = sb->s_op->freeze_fs(sb); + if (error) { + printk(KERN_ERR + "VFS:Filesystem freeze failed\n"); + sb->s_frozen = SB_UNFROZEN; + deactivate_locked_super(sb); + bdev->bd_fsfreeze_count--; + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return ERR_PTR(error); } } + up_write(&sb->s_umount); + out: sync_blockdev(bdev); mutex_unlock(&bdev->bd_fsfreeze_mutex); - return sb; /* thaw_bdev releases s->s_umount */ } EXPORT_SYMBOL(freeze_bdev); @@ -280,43 +291,44 @@ EXPORT_SYMBOL(freeze_bdev); */ int thaw_bdev(struct block_device *bdev, struct super_block *sb) { - int error = 0; + int error = -EINVAL; mutex_lock(&bdev->bd_fsfreeze_mutex); - if (!bdev->bd_fsfreeze_count) { - mutex_unlock(&bdev->bd_fsfreeze_mutex); - return -EINVAL; - } - - bdev->bd_fsfreeze_count--; - if (bdev->bd_fsfreeze_count > 0) { - if (sb) - drop_super(sb); - mutex_unlock(&bdev->bd_fsfreeze_mutex); - return 0; - } - - if (sb) { - BUG_ON(sb->s_bdev != bdev); - if (!(sb->s_flags & MS_RDONLY)) { - if (sb->s_op->unfreeze_fs) { - error = sb->s_op->unfreeze_fs(sb); - if (error) { - printk(KERN_ERR - "VFS:Filesystem thaw failed\n"); - sb->s_frozen = SB_FREEZE_TRANS; - bdev->bd_fsfreeze_count++; - mutex_unlock(&bdev->bd_fsfreeze_mutex); - return error; - } - } - sb->s_frozen = SB_UNFROZEN; - smp_wmb(); - wake_up(&sb->s_wait_unfrozen); + if (!bdev->bd_fsfreeze_count) + goto out_unlock; + + error = 0; + if (--bdev->bd_fsfreeze_count > 0) + goto out_unlock; + + if (!sb) + goto out_unlock; + + BUG_ON(sb->s_bdev != bdev); + down_write(&sb->s_umount); + if (sb->s_flags & MS_RDONLY) + goto out_deactivate; + + if (sb->s_op->unfreeze_fs) { + error = sb->s_op->unfreeze_fs(sb); + if (error) { + printk(KERN_ERR + "VFS:Filesystem thaw failed\n"); + sb->s_frozen = SB_FREEZE_TRANS; + bdev->bd_fsfreeze_count++; + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return error; } - drop_super(sb); } + sb->s_frozen = SB_UNFROZEN; + smp_wmb(); + wake_up(&sb->s_wait_unfrozen); + +out_deactivate: + if (sb) + deactivate_locked_super(sb); +out_unlock: mutex_unlock(&bdev->bd_fsfreeze_mutex); return 0; } diff --git a/fs/super.c b/fs/super.c index 1cb26a3e3df0..19eb70b374bc 100644 --- a/fs/super.c +++ b/fs/super.c @@ -465,6 +465,48 @@ rescan: } EXPORT_SYMBOL(get_super); + +/** + * get_active_super - get an active reference to the superblock of a device + * @bdev: device to get the superblock for + * + * Scans the superblock list and finds the superblock of the file system + * mounted on the device given. Returns the superblock with an active + * reference and s_umount held exclusively or %NULL if none was found. + */ +struct super_block *get_active_super(struct block_device *bdev) +{ + struct super_block *sb; + + if (!bdev) + return NULL; + + spin_lock(&sb_lock); + list_for_each_entry(sb, &super_blocks, s_list) { + if (sb->s_bdev != bdev) + continue; + + sb->s_count++; + spin_unlock(&sb_lock); + down_write(&sb->s_umount); + if (sb->s_root) { + spin_lock(&sb_lock); + if (sb->s_count > S_BIAS) { + atomic_inc(&sb->s_active); + sb->s_count--; + spin_unlock(&sb_lock); + return sb; + } + spin_unlock(&sb_lock); + } + up_write(&sb->s_umount); + put_super(sb); + yield(); + spin_lock(&sb_lock); + } + spin_unlock(&sb_lock); + return NULL; +} struct super_block * user_get_super(dev_t dev) { @@ -527,11 +569,15 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force) { int retval; int remount_rw; - + + if (sb->s_frozen != SB_UNFROZEN) + return -EBUSY; + #ifdef CONFIG_BLOCK if (!(flags & MS_RDONLY) && bdev_read_only(sb->s_bdev)) return -EACCES; #endif + if (flags & MS_RDONLY) acct_auto_close(sb); shrink_dcache_sb(sb); 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 --- Documentation/vm/locking | 2 +- fs/attr.c | 46 ++++++++++++++++++++++++++++++++-- include/linux/fs.h | 3 ++- include/linux/mm.h | 5 ++-- mm/filemap.c | 2 +- mm/memory.c | 62 +++------------------------------------------- mm/mremap.c | 4 +-- mm/nommu.c | 40 ------------------------------ mm/truncate.c | 64 ++++++++++++++++++++++++++++++++++++++++++++++++ 9 files changed, 120 insertions(+), 108 deletions(-) (limited to 'include/linux') diff --git a/Documentation/vm/locking b/Documentation/vm/locking index f366fa956179..25fadb448760 100644 --- a/Documentation/vm/locking +++ b/Documentation/vm/locking @@ -80,7 +80,7 @@ Note: PTL can also be used to guarantee that no new clones using the mm start up ... this is a loose form of stability on mm_users. For example, it is used in copy_mm to protect against a racing tlb_gather_mmu single address space optimization, so that the zap_page_range (from -vmtruncate) does not lose sending ipi's to cloned threads that might +truncate) does not lose sending ipi's to cloned threads that might be spawned underneath it and go to user mode to drag in pte's into tlbs. swap_lock diff --git a/fs/attr.c b/fs/attr.c index 9fe1b1bd30a8..96d394bdaddf 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -18,7 +18,7 @@ /* Taken over from the old code... */ /* POSIX UID/GID verification for setting inode attributes. */ -int inode_change_ok(struct inode *inode, struct iattr *attr) +int inode_change_ok(const struct inode *inode, struct iattr *attr) { int retval = -EPERM; unsigned int ia_valid = attr->ia_valid; @@ -60,9 +60,51 @@ fine: error: return retval; } - EXPORT_SYMBOL(inode_change_ok); +/** + * inode_newsize_ok - may this inode be truncated to a given size + * @inode: the inode to be truncated + * @offset: the new size to assign to the inode + * @Returns: 0 on success, -ve errno on failure + * + * inode_newsize_ok will check filesystem limits and ulimits to check that the + * new inode size is within limits. inode_newsize_ok will also send SIGXFSZ + * when necessary. Caller must not proceed with inode size change if failure is + * returned. @inode must be a file (not directory), with appropriate + * permissions to allow truncate (inode_newsize_ok does NOT check these + * conditions). + * + * inode_newsize_ok must be called with i_mutex held. + */ +int inode_newsize_ok(const struct inode *inode, loff_t offset) +{ + if (inode->i_size < offset) { + unsigned long limit; + + limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur; + if (limit != RLIM_INFINITY && offset > limit) + goto out_sig; + if (offset > inode->i_sb->s_maxbytes) + goto out_big; + } else { + /* + * truncation of in-use swapfiles is disallowed - it would + * cause subsequent swapout to scribble on the now-freed + * blocks. + */ + if (IS_SWAPFILE(inode)) + return -ETXTBSY; + } + + return 0; +out_sig: + send_sig(SIGXFSZ, current, 0); +out_big: + return -EFBIG; +} +EXPORT_SYMBOL(inode_newsize_ok); + int inode_setattr(struct inode * inode, struct iattr * attr) { unsigned int ia_valid = attr->ia_valid; 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, diff --git a/mm/filemap.c b/mm/filemap.c index bcc7372aebbc..33349adb227a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -58,7 +58,7 @@ /* * Lock ordering: * - * ->i_mmap_lock (vmtruncate) + * ->i_mmap_lock (truncate_pagecache) * ->private_lock (__free_pte->__set_page_dirty_buffers) * ->swap_lock (exclusive_swap_page, others) * ->mapping->tree_lock diff --git a/mm/memory.c b/mm/memory.c index b1443ac07c00..ebcd3decac89 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -297,7 +297,8 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr = vma->vm_start; /* - * Hide vma from rmap and vmtruncate before freeing pgtables + * Hide vma from rmap and truncate_pagecache before freeing + * pgtables */ anon_vma_unlink(vma); unlink_file_vma(vma); @@ -2407,7 +2408,7 @@ restart: * @mapping: the address space containing mmaps to be unmapped. * @holebegin: byte in first page to unmap, relative to the start of * the underlying file. This will be rounded down to a PAGE_SIZE - * boundary. Note that this is different from vmtruncate(), which + * boundary. Note that this is different from truncate_pagecache(), which * must keep the partial page. In contrast, we must get rid of * partial pages. * @holelen: size of prospective hole in bytes. This will be rounded @@ -2458,63 +2459,6 @@ void unmap_mapping_range(struct address_space *mapping, } EXPORT_SYMBOL(unmap_mapping_range); -/** - * vmtruncate - unmap mappings "freed" by truncate() syscall - * @inode: inode of the file used - * @offset: file offset to start truncating - * - * NOTE! We have to be ready to update the memory sharing - * between the file and the memory map for a potential last - * incomplete page. Ugly, but necessary. - */ -int vmtruncate(struct inode * inode, loff_t offset) -{ - if (inode->i_size < offset) { - unsigned long limit; - - limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur; - if (limit != RLIM_INFINITY && offset > limit) - goto out_sig; - if (offset > inode->i_sb->s_maxbytes) - goto out_big; - i_size_write(inode, offset); - } else { - struct address_space *mapping = inode->i_mapping; - - /* - * truncation of in-use swapfiles is disallowed - it would - * cause subsequent swapout to scribble on the now-freed - * blocks. - */ - if (IS_SWAPFILE(inode)) - return -ETXTBSY; - i_size_write(inode, offset); - - /* - * unmap_mapping_range is called twice, first simply for - * efficiency so that truncate_inode_pages does fewer - * single-page unmaps. However after this first call, and - * before truncate_inode_pages finishes, it is possible for - * private pages to be COWed, which remain after - * truncate_inode_pages finishes, hence the second - * unmap_mapping_range call must be made for correctness. - */ - unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1); - truncate_inode_pages(mapping, offset); - unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1); - } - - if (inode->i_op->truncate) - inode->i_op->truncate(inode); - return 0; - -out_sig: - send_sig(SIGXFSZ, current, 0); -out_big: - return -EFBIG; -} -EXPORT_SYMBOL(vmtruncate); - int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end) { struct address_space *mapping = inode->i_mapping; diff --git a/mm/mremap.c b/mm/mremap.c index 20a07dba6be0..97bff2547719 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -86,8 +86,8 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, if (vma->vm_file) { /* * Subtle point from Rajesh Venkatasubramanian: before - * moving file-based ptes, we must lock vmtruncate out, - * since it might clean the dst vma before the src vma, + * moving file-based ptes, we must lock truncate_pagecache + * out, since it might clean the dst vma before the src vma, * and we propagate stale pages into the dst afterward. */ mapping = vma->vm_file->f_mapping; diff --git a/mm/nommu.c b/mm/nommu.c index 8d484241d034..56a446f05971 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -82,46 +82,6 @@ DECLARE_RWSEM(nommu_region_sem); struct vm_operations_struct generic_file_vm_ops = { }; -/* - * Handle all mappings that got truncated by a "truncate()" - * system call. - * - * NOTE! We have to be ready to update the memory sharing - * between the file and the memory map for a potential last - * incomplete page. Ugly, but necessary. - */ -int vmtruncate(struct inode *inode, loff_t offset) -{ - struct address_space *mapping = inode->i_mapping; - unsigned long limit; - - if (inode->i_size < offset) - goto do_expand; - i_size_write(inode, offset); - - truncate_inode_pages(mapping, offset); - goto out_truncate; - -do_expand: - limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur; - if (limit != RLIM_INFINITY && offset > limit) - goto out_sig; - if (offset > inode->i_sb->s_maxbytes) - goto out; - i_size_write(inode, offset); - -out_truncate: - if (inode->i_op->truncate) - inode->i_op->truncate(inode); - return 0; -out_sig: - send_sig(SIGXFSZ, current, 0); -out: - return -EFBIG; -} - -EXPORT_SYMBOL(vmtruncate); - /* * Return the total memory allocated for this pointer, not * just what the caller asked for. diff --git a/mm/truncate.c b/mm/truncate.c index ccc3ecf7cb98..5900afca0fa9 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -465,3 +465,67 @@ int invalidate_inode_pages2(struct address_space *mapping) return invalidate_inode_pages2_range(mapping, 0, -1); } EXPORT_SYMBOL_GPL(invalidate_inode_pages2); + +/** + * truncate_pagecache - unmap and remove pagecache that has been truncated + * @inode: inode + * @old: old file offset + * @new: new file offset + * + * inode's new i_size must already be written before truncate_pagecache + * is called. + * + * This function should typically be called before the filesystem + * releases resources associated with the freed range (eg. deallocates + * blocks). This way, pagecache will always stay logically coherent + * with on-disk format, and the filesystem would not have to deal with + * situations such as writepage being called for a page that has already + * had its underlying blocks deallocated. + */ +void truncate_pagecache(struct inode *inode, loff_t old, loff_t new) +{ + if (new < old) { + struct address_space *mapping = inode->i_mapping; + + /* + * unmap_mapping_range is called twice, first simply for + * efficiency so that truncate_inode_pages does fewer + * single-page unmaps. However after this first call, and + * before truncate_inode_pages finishes, it is possible for + * private pages to be COWed, which remain after + * truncate_inode_pages finishes, hence the second + * unmap_mapping_range call must be made for correctness. + */ + unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1); + truncate_inode_pages(mapping, new); + unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1); + } +} +EXPORT_SYMBOL(truncate_pagecache); + +/** + * vmtruncate - unmap mappings "freed" by truncate() syscall + * @inode: inode of the file used + * @offset: file offset to start truncating + * + * NOTE! We have to be ready to update the memory sharing + * between the file and the memory map for a potential last + * incomplete page. Ugly, but necessary. + */ +int vmtruncate(struct inode *inode, loff_t offset) +{ + loff_t oldsize; + int error; + + error = inode_newsize_ok(inode, offset); + if (error) + return error; + oldsize = inode->i_size; + i_size_write(inode, offset); + truncate_pagecache(inode, oldsize, offset); + if (inode->i_op->truncate) + inode->i_op->truncate(inode); + + return error; +} +EXPORT_SYMBOL(vmtruncate); -- 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 +++++++++++ kernel/time/Makefile | 2 +- kernel/time/timeconv.c | 127 +++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 156 insertions(+), 1 deletion(-) create mode 100644 kernel/time/timeconv.c (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 diff --git a/kernel/time/Makefile b/kernel/time/Makefile index 0b0a6366c9d4..ee266620b06c 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -1,4 +1,4 @@ -obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o +obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o timeconv.o obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD) += clockevents.o obj-$(CONFIG_GENERIC_CLOCKEVENTS) += tick-common.o diff --git a/kernel/time/timeconv.c b/kernel/time/timeconv.c new file mode 100644 index 000000000000..86628e755f38 --- /dev/null +++ b/kernel/time/timeconv.c @@ -0,0 +1,127 @@ +/* + * Copyright (C) 1993, 1994, 1995, 1996, 1997 Free Software Foundation, Inc. + * This file is part of the GNU C Library. + * Contributed by Paul Eggert (eggert@twinsun.com). + * + * The GNU C Library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Library General Public License as + * published by the Free Software Foundation; either version 2 of the + * License, or (at your option) any later version. + * + * The GNU C Library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Library General Public License for more details. + * + * You should have received a copy of the GNU Library General Public + * License along with the GNU C Library; see the file COPYING.LIB. If not, + * write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 02111-1307, USA. + */ + +/* + * Converts the calendar time to broken-down time representation + * Based on code from glibc-2.6 + * + * 2009-7-14: + * Moved from glibc-2.6 to kernel by Zhaolei + */ + +#include +#include + +/* + * Nonzero if YEAR is a leap year (every 4 years, + * except every 100th isn't, and every 400th is). + */ +static int __isleap(long year) +{ + return (year) % 4 == 0 && ((year) % 100 != 0 || (year) % 400 == 0); +} + +/* do a mathdiv for long type */ +static long math_div(long a, long b) +{ + return a / b - (a % b < 0); +} + +/* How many leap years between y1 and y2, y1 must less or equal to y2 */ +static long leaps_between(long y1, long y2) +{ + long leaps1 = math_div(y1 - 1, 4) - math_div(y1 - 1, 100) + + math_div(y1 - 1, 400); + long leaps2 = math_div(y2 - 1, 4) - math_div(y2 - 1, 100) + + math_div(y2 - 1, 400); + return leaps2 - leaps1; +} + +/* How many days come before each month (0-12). */ +static const unsigned short __mon_yday[2][13] = { + /* Normal years. */ + {0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365}, + /* Leap years. */ + {0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366} +}; + +#define SECS_PER_HOUR (60 * 60) +#define SECS_PER_DAY (SECS_PER_HOUR * 24) + +/** + * time_to_tm - converts the calendar time to local broken-down time + * + * @totalsecs the number of seconds elapsed since 00:00:00 on January 1, 1970, + * Coordinated Universal Time (UTC). + * @offset offset seconds adding to totalsecs. + * @result pointer to struct tm variable to receive broken-down time + */ +void time_to_tm(time_t totalsecs, int offset, struct tm *result) +{ + long days, rem, y; + const unsigned short *ip; + + days = totalsecs / SECS_PER_DAY; + rem = totalsecs % SECS_PER_DAY; + rem += offset; + while (rem < 0) { + rem += SECS_PER_DAY; + --days; + } + while (rem >= SECS_PER_DAY) { + rem -= SECS_PER_DAY; + ++days; + } + + result->tm_hour = rem / SECS_PER_HOUR; + rem %= SECS_PER_HOUR; + result->tm_min = rem / 60; + result->tm_sec = rem % 60; + + /* January 1, 1970 was a Thursday. */ + result->tm_wday = (4 + days) % 7; + if (result->tm_wday < 0) + result->tm_wday += 7; + + y = 1970; + + while (days < 0 || days >= (__isleap(y) ? 366 : 365)) { + /* Guess a corrected year, assuming 365 days per year. */ + long yg = y + math_div(days, 365); + + /* Adjust DAYS and Y to match the guessed year. */ + days -= (yg - y) * 365 + leaps_between(y, yg); + y = yg; + } + + result->tm_year = y - 1900; + + result->tm_yday = days; + + ip = __mon_yday[__isleap(y)]; + for (y = 11; days < ip[y]; y--) + continue; + days -= ip[y]; + + result->tm_mon = y; + result->tm_mday = days + 1; +} +EXPORT_SYMBOL(time_to_tm); -- 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 +++--- kernel/cgroup.c | 95 +++++++++++++------------------------------------- 2 files changed, 31 insertions(+), 75 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; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 14efffed72c8..22db0a7cf1fa 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1121,7 +1121,6 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) INIT_LIST_HEAD(&cgrp->children); INIT_LIST_HEAD(&cgrp->css_sets); INIT_LIST_HEAD(&cgrp->release_list); - INIT_LIST_HEAD(&cgrp->pids_list); init_rwsem(&cgrp->pids_mutex); } @@ -2431,30 +2430,12 @@ err: return ret; } -/* - * Cache pids for all threads in the same pid namespace that are - * opening the same "tasks" file. - */ -struct cgroup_pids { - /* The node in cgrp->pids_list */ - struct list_head list; - /* The cgroup those pids belong to */ - struct cgroup *cgrp; - /* The namepsace those pids belong to */ - struct pid_namespace *ns; - /* Array of process ids in the cgroup */ - pid_t *tasks_pids; - /* How many files are using the this tasks_pids array */ - int use_count; - /* Length of the current tasks_pids array */ - int length; -}; - static int cmppid(const void *a, const void *b) { return *(pid_t *)a - *(pid_t *)b; } + /* * seq_file methods for the "tasks" file. The seq_file position is the * next pid to display; the seq_file iterator is a pointer to the pid @@ -2469,47 +2450,45 @@ static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos) * after a seek to the start). Use a binary-search to find the * next pid to display, if any */ - struct cgroup_pids *cp = s->private; - struct cgroup *cgrp = cp->cgrp; + struct cgroup *cgrp = s->private; int index = 0, pid = *pos; int *iter; down_read(&cgrp->pids_mutex); if (pid) { - int end = cp->length; + int end = cgrp->pids_length; while (index < end) { int mid = (index + end) / 2; - if (cp->tasks_pids[mid] == pid) { + if (cgrp->tasks_pids[mid] == pid) { index = mid; break; - } else if (cp->tasks_pids[mid] <= pid) + } else if (cgrp->tasks_pids[mid] <= pid) index = mid + 1; else end = mid; } } /* If we're off the end of the array, we're done */ - if (index >= cp->length) + if (index >= cgrp->pids_length) return NULL; /* Update the abstract position to be the actual pid that we found */ - iter = cp->tasks_pids + index; + iter = cgrp->tasks_pids + index; *pos = *iter; return iter; } static void cgroup_tasks_stop(struct seq_file *s, void *v) { - struct cgroup_pids *cp = s->private; - struct cgroup *cgrp = cp->cgrp; + struct cgroup *cgrp = s->private; up_read(&cgrp->pids_mutex); } static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos) { - struct cgroup_pids *cp = s->private; + struct cgroup *cgrp = s->private; int *p = v; - int *end = cp->tasks_pids + cp->length; + int *end = cgrp->tasks_pids + cgrp->pids_length; /* * Advance to the next pid in the array. If this goes off the @@ -2536,33 +2515,26 @@ static const struct seq_operations cgroup_tasks_seq_operations = { .show = cgroup_tasks_show, }; -static void release_cgroup_pid_array(struct cgroup_pids *cp) +static void release_cgroup_pid_array(struct cgroup *cgrp) { - struct cgroup *cgrp = cp->cgrp; - down_write(&cgrp->pids_mutex); - BUG_ON(!cp->use_count); - if (!--cp->use_count) { - list_del(&cp->list); - put_pid_ns(cp->ns); - kfree(cp->tasks_pids); - kfree(cp); + BUG_ON(!cgrp->pids_use_count); + if (!--cgrp->pids_use_count) { + kfree(cgrp->tasks_pids); + cgrp->tasks_pids = NULL; + cgrp->pids_length = 0; } up_write(&cgrp->pids_mutex); } static int cgroup_tasks_release(struct inode *inode, struct file *file) { - struct seq_file *seq; - struct cgroup_pids *cp; + struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent); if (!(file->f_mode & FMODE_READ)) return 0; - seq = file->private_data; - cp = seq->private; - - release_cgroup_pid_array(cp); + release_cgroup_pid_array(cgrp); return seq_release(inode, file); } @@ -2581,8 +2553,6 @@ static struct file_operations cgroup_tasks_operations = { static int cgroup_tasks_open(struct inode *unused, struct file *file) { struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent); - struct pid_namespace *ns = current->nsproxy->pid_ns; - struct cgroup_pids *cp; pid_t *pidarray; int npids; int retval; @@ -2609,37 +2579,20 @@ static int cgroup_tasks_open(struct inode *unused, struct file *file) * array if necessary */ down_write(&cgrp->pids_mutex); - - list_for_each_entry(cp, &cgrp->pids_list, list) { - if (ns == cp->ns) - goto found; - } - - cp = kzalloc(sizeof(*cp), GFP_KERNEL); - if (!cp) { - up_write(&cgrp->pids_mutex); - kfree(pidarray); - return -ENOMEM; - } - cp->cgrp = cgrp; - cp->ns = ns; - get_pid_ns(ns); - list_add(&cp->list, &cgrp->pids_list); -found: - kfree(cp->tasks_pids); - cp->tasks_pids = pidarray; - cp->length = npids; - cp->use_count++; + kfree(cgrp->tasks_pids); + cgrp->tasks_pids = pidarray; + cgrp->pids_length = npids; + cgrp->pids_use_count++; up_write(&cgrp->pids_mutex); file->f_op = &cgroup_tasks_operations; retval = seq_open(file, &cgroup_tasks_seq_operations); if (retval) { - release_cgroup_pid_array(cp); + release_cgroup_pid_array(cgrp); return retval; } - ((struct seq_file *)file->private_data)->private = cp; + ((struct seq_file *)file->private_data)->private = cgrp; return 0; } -- 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 ++-- kernel/cgroup.c | 278 ++++++++++++++++++++++++++++++------------------- 2 files changed, 186 insertions(+), 114 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; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 22db0a7cf1fa..a9433f50e53d 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1121,7 +1121,8 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) INIT_LIST_HEAD(&cgrp->children); INIT_LIST_HEAD(&cgrp->css_sets); INIT_LIST_HEAD(&cgrp->release_list); - init_rwsem(&cgrp->pids_mutex); + init_rwsem(&(cgrp->tasks.mutex)); + init_rwsem(&(cgrp->procs.mutex)); } static void init_cgroup_root(struct cgroupfs_root *root) @@ -1637,15 +1638,6 @@ static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid) return ret; } -/* The various types of files and directories in a cgroup file system */ -enum cgroup_filetype { - FILE_ROOT, - FILE_DIR, - FILE_TASKLIST, - FILE_NOTIFY_ON_RELEASE, - FILE_RELEASE_AGENT, -}; - /** * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive. * @cgrp: the cgroup to be checked for liveness @@ -2343,7 +2335,7 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan) } /* - * Stuff for reading the 'tasks' file. + * Stuff for reading the 'tasks'/'procs' files. * * Reading this file can return large amounts of data if a cgroup has * *lots* of attached tasks. So it may need several calls to read(), @@ -2353,27 +2345,106 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan) */ /* - * Load into 'pidarray' up to 'npids' of the tasks using cgroup - * 'cgrp'. Return actual number of pids loaded. No need to - * task_lock(p) when reading out p->cgroup, since we're in an RCU - * read section, so the css_set can't go away, and is - * immutable after creation. + * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries + * If the new stripped list is sufficiently smaller and there's enough memory + * to allocate a new buffer, will let go of the unneeded memory. Returns the + * number of unique elements. */ -static int pid_array_load(pid_t *pidarray, int npids, struct cgroup *cgrp) +/* is the size difference enough that we should re-allocate the array? */ +#define PIDLIST_REALLOC_DIFFERENCE(old, new) ((old) - PAGE_SIZE >= (new)) +static int pidlist_uniq(pid_t **p, int length) { - int n = 0, pid; + int src, dest = 1; + pid_t *list = *p; + pid_t *newlist; + + /* + * we presume the 0th element is unique, so i starts at 1. trivial + * edge cases first; no work needs to be done for either + */ + if (length == 0 || length == 1) + return length; + /* src and dest walk down the list; dest counts unique elements */ + for (src = 1; src < length; src++) { + /* find next unique element */ + while (list[src] == list[src-1]) { + src++; + if (src == length) + goto after; + } + /* dest always points to where the next unique element goes */ + list[dest] = list[src]; + dest++; + } +after: + /* + * if the length difference is large enough, we want to allocate a + * smaller buffer to save memory. if this fails due to out of memory, + * we'll just stay with what we've got. + */ + if (PIDLIST_REALLOC_DIFFERENCE(length, dest)) { + newlist = krealloc(list, dest * sizeof(pid_t), GFP_KERNEL); + if (newlist) + *p = newlist; + } + return dest; +} + +static int cmppid(const void *a, const void *b) +{ + return *(pid_t *)a - *(pid_t *)b; +} + +/* + * Load a cgroup's pidarray with either procs' tgids or tasks' pids + */ +static int pidlist_array_load(struct cgroup *cgrp, bool procs) +{ + pid_t *array; + int length; + int pid, n = 0; /* used for populating the array */ struct cgroup_iter it; struct task_struct *tsk; + struct cgroup_pidlist *l; + + /* + * If cgroup gets more users after we read count, we won't have + * enough space - tough. This race is indistinguishable to the + * caller from the case that the additional cgroup users didn't + * show up until sometime later on. + */ + length = cgroup_task_count(cgrp); + array = kmalloc(length * sizeof(pid_t), GFP_KERNEL); + if (!array) + return -ENOMEM; + /* now, populate the array */ cgroup_iter_start(cgrp, &it); while ((tsk = cgroup_iter_next(cgrp, &it))) { - if (unlikely(n == npids)) + if (unlikely(n == length)) break; - pid = task_pid_vnr(tsk); - if (pid > 0) - pidarray[n++] = pid; + /* get tgid or pid for procs or tasks file respectively */ + pid = (procs ? task_tgid_vnr(tsk) : task_pid_vnr(tsk)); + if (pid > 0) /* make sure to only use valid results */ + array[n++] = pid; } cgroup_iter_end(cgrp, &it); - return n; + length = n; + /* now sort & (if procs) strip out duplicates */ + sort(array, length, sizeof(pid_t), cmppid, NULL); + if (procs) { + length = pidlist_uniq(&array, length); + l = &(cgrp->procs); + } else { + l = &(cgrp->tasks); + } + /* store array in cgroup, freeing old if necessary */ + down_write(&l->mutex); + kfree(l->list); + l->list = array; + l->length = length; + l->use_count++; + up_write(&l->mutex); + return 0; } /** @@ -2430,19 +2501,14 @@ err: return ret; } -static int cmppid(const void *a, const void *b) -{ - return *(pid_t *)a - *(pid_t *)b; -} - /* - * seq_file methods for the "tasks" file. The seq_file position is the + * seq_file methods for the tasks/procs files. The seq_file position is the * next pid to display; the seq_file iterator is a pointer to the pid - * in the cgroup->tasks_pids array. + * in the cgroup->l->list array. */ -static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos) +static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) { /* * Initially we receive a position value that corresponds to @@ -2450,46 +2516,45 @@ static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos) * after a seek to the start). Use a binary-search to find the * next pid to display, if any */ - struct cgroup *cgrp = s->private; + struct cgroup_pidlist *l = s->private; int index = 0, pid = *pos; int *iter; - down_read(&cgrp->pids_mutex); + down_read(&l->mutex); if (pid) { - int end = cgrp->pids_length; + int end = l->length; while (index < end) { int mid = (index + end) / 2; - if (cgrp->tasks_pids[mid] == pid) { + if (l->list[mid] == pid) { index = mid; break; - } else if (cgrp->tasks_pids[mid] <= pid) + } else if (l->list[mid] <= pid) index = mid + 1; else end = mid; } } /* If we're off the end of the array, we're done */ - if (index >= cgrp->pids_length) + if (index >= l->length) return NULL; /* Update the abstract position to be the actual pid that we found */ - iter = cgrp->tasks_pids + index; + iter = l->list + index; *pos = *iter; return iter; } -static void cgroup_tasks_stop(struct seq_file *s, void *v) +static void cgroup_pidlist_stop(struct seq_file *s, void *v) { - struct cgroup *cgrp = s->private; - up_read(&cgrp->pids_mutex); + struct cgroup_pidlist *l = s->private; + up_read(&l->mutex); } -static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos) +static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos) { - struct cgroup *cgrp = s->private; - int *p = v; - int *end = cgrp->tasks_pids + cgrp->pids_length; - + struct cgroup_pidlist *l = s->private; + pid_t *p = v; + pid_t *end = l->list + l->length; /* * Advance to the next pid in the array. If this goes off the * end, we're done @@ -2503,98 +2568,94 @@ static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos) } } -static int cgroup_tasks_show(struct seq_file *s, void *v) +static int cgroup_pidlist_show(struct seq_file *s, void *v) { return seq_printf(s, "%d\n", *(int *)v); } -static const struct seq_operations cgroup_tasks_seq_operations = { - .start = cgroup_tasks_start, - .stop = cgroup_tasks_stop, - .next = cgroup_tasks_next, - .show = cgroup_tasks_show, +/* + * seq_operations functions for iterating on pidlists through seq_file - + * independent of whether it's tasks or procs + */ +static const struct seq_operations cgroup_pidlist_seq_operations = { + .start = cgroup_pidlist_start, + .stop = cgroup_pidlist_stop, + .next = cgroup_pidlist_next, + .show = cgroup_pidlist_show, }; -static void release_cgroup_pid_array(struct cgroup *cgrp) +static void cgroup_release_pid_array(struct cgroup_pidlist *l) { - down_write(&cgrp->pids_mutex); - BUG_ON(!cgrp->pids_use_count); - if (!--cgrp->pids_use_count) { - kfree(cgrp->tasks_pids); - cgrp->tasks_pids = NULL; - cgrp->pids_length = 0; + down_write(&l->mutex); + BUG_ON(!l->use_count); + if (!--l->use_count) { + kfree(l->list); + l->list = NULL; + l->length = 0; } - up_write(&cgrp->pids_mutex); + up_write(&l->mutex); } -static int cgroup_tasks_release(struct inode *inode, struct file *file) +static int cgroup_pidlist_release(struct inode *inode, struct file *file) { - struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent); - + struct cgroup_pidlist *l; if (!(file->f_mode & FMODE_READ)) return 0; - - release_cgroup_pid_array(cgrp); + /* + * the seq_file will only be initialized if the file was opened for + * reading; hence we check if it's not null only in that case. + */ + l = ((struct seq_file *)file->private_data)->private; + cgroup_release_pid_array(l); return seq_release(inode, file); } -static struct file_operations cgroup_tasks_operations = { +static const struct file_operations cgroup_pidlist_operations = { .read = seq_read, .llseek = seq_lseek, .write = cgroup_file_write, - .release = cgroup_tasks_release, + .release = cgroup_pidlist_release, }; /* - * Handle an open on 'tasks' file. Prepare an array containing the - * process id's of tasks currently attached to the cgroup being opened. + * The following functions handle opens on a file that displays a pidlist + * (tasks or procs). Prepare an array of the process/thread IDs of whoever's + * in the cgroup. */ - -static int cgroup_tasks_open(struct inode *unused, struct file *file) +/* helper function for the two below it */ +static int cgroup_pidlist_open(struct file *file, bool procs) { struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent); - pid_t *pidarray; - int npids; + struct cgroup_pidlist *l = (procs ? &cgrp->procs : &cgrp->tasks); int retval; /* Nothing to do for write-only files */ if (!(file->f_mode & FMODE_READ)) return 0; - /* - * If cgroup gets more users after we read count, we won't have - * enough space - tough. This race is indistinguishable to the - * caller from the case that the additional cgroup users didn't - * show up until sometime later on. - */ - npids = cgroup_task_count(cgrp); - pidarray = kmalloc(npids * sizeof(pid_t), GFP_KERNEL); - if (!pidarray) - return -ENOMEM; - npids = pid_array_load(pidarray, npids, cgrp); - sort(pidarray, npids, sizeof(pid_t), cmppid, NULL); - - /* - * Store the array in the cgroup, freeing the old - * array if necessary - */ - down_write(&cgrp->pids_mutex); - kfree(cgrp->tasks_pids); - cgrp->tasks_pids = pidarray; - cgrp->pids_length = npids; - cgrp->pids_use_count++; - up_write(&cgrp->pids_mutex); - - file->f_op = &cgroup_tasks_operations; + /* have the array populated */ + retval = pidlist_array_load(cgrp, procs); + if (retval) + return retval; + /* configure file information */ + file->f_op = &cgroup_pidlist_operations; - retval = seq_open(file, &cgroup_tasks_seq_operations); + retval = seq_open(file, &cgroup_pidlist_seq_operations); if (retval) { - release_cgroup_pid_array(cgrp); + cgroup_release_pid_array(l); return retval; } - ((struct seq_file *)file->private_data)->private = cgrp; + ((struct seq_file *)file->private_data)->private = l; return 0; } +static int cgroup_tasks_open(struct inode *unused, struct file *file) +{ + return cgroup_pidlist_open(file, false); +} +static int cgroup_procs_open(struct inode *unused, struct file *file) +{ + return cgroup_pidlist_open(file, true); +} static u64 cgroup_read_notify_on_release(struct cgroup *cgrp, struct cftype *cft) @@ -2617,21 +2678,27 @@ static int cgroup_write_notify_on_release(struct cgroup *cgrp, /* * for the common functions, 'private' gives the type of file */ +/* for hysterical raisins, we can't put this on the older files */ +#define CGROUP_FILE_GENERIC_PREFIX "cgroup." static struct cftype files[] = { { .name = "tasks", .open = cgroup_tasks_open, .write_u64 = cgroup_tasks_write, - .release = cgroup_tasks_release, - .private = FILE_TASKLIST, + .release = cgroup_pidlist_release, .mode = S_IRUGO | S_IWUSR, }, - + { + .name = CGROUP_FILE_GENERIC_PREFIX "procs", + .open = cgroup_procs_open, + /* .write_u64 = cgroup_procs_write, TODO */ + .release = cgroup_pidlist_release, + .mode = S_IRUGO, + }, { .name = "notify_on_release", .read_u64 = cgroup_read_notify_on_release, .write_u64 = cgroup_write_notify_on_release, - .private = FILE_NOTIFY_ON_RELEASE, }, }; @@ -2640,7 +2707,6 @@ static struct cftype cft_release_agent = { .read_seq_string = cgroup_release_agent_show, .write_string = cgroup_release_agent_write, .max_write_len = PATH_MAX, - .private = FILE_RELEASE_AGENT, }; static int cgroup_populate_dir(struct cgroup *cgrp) -- 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 +++++++++++++--- kernel/cgroup.c | 107 +++++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 119 insertions(+), 22 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; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index a9433f50e53d..97194ba12014 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -776,6 +776,12 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode) */ deactivate_super(cgrp->root->sb); + /* + * if we're getting rid of the cgroup, refcount should ensure + * that there are no pidlists left. + */ + BUG_ON(!list_empty(&cgrp->pidlists)); + call_rcu(&cgrp->rcu_head, free_cgroup_rcu); } iput(inode); @@ -1121,8 +1127,8 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) INIT_LIST_HEAD(&cgrp->children); INIT_LIST_HEAD(&cgrp->css_sets); INIT_LIST_HEAD(&cgrp->release_list); - init_rwsem(&(cgrp->tasks.mutex)); - init_rwsem(&(cgrp->procs.mutex)); + INIT_LIST_HEAD(&cgrp->pidlists); + mutex_init(&cgrp->pidlist_mutex); } static void init_cgroup_root(struct cgroupfs_root *root) @@ -2395,10 +2401,60 @@ static int cmppid(const void *a, const void *b) return *(pid_t *)a - *(pid_t *)b; } +/* + * find the appropriate pidlist for our purpose (given procs vs tasks) + * returns with the lock on that pidlist already held, and takes care + * of the use count, or returns NULL with no locks held if we're out of + * memory. + */ +static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp, + enum cgroup_filetype type) +{ + struct cgroup_pidlist *l; + /* don't need task_nsproxy() if we're looking at ourself */ + struct pid_namespace *ns = get_pid_ns(current->nsproxy->pid_ns); + /* + * We can't drop the pidlist_mutex before taking the l->mutex in case + * the last ref-holder is trying to remove l from the list at the same + * time. Holding the pidlist_mutex precludes somebody taking whichever + * list we find out from under us - compare release_pid_array(). + */ + mutex_lock(&cgrp->pidlist_mutex); + list_for_each_entry(l, &cgrp->pidlists, links) { + if (l->key.type == type && l->key.ns == ns) { + /* found a matching list - drop the extra refcount */ + put_pid_ns(ns); + /* make sure l doesn't vanish out from under us */ + down_write(&l->mutex); + mutex_unlock(&cgrp->pidlist_mutex); + l->use_count++; + return l; + } + } + /* entry not found; create a new one */ + l = kmalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL); + if (!l) { + mutex_unlock(&cgrp->pidlist_mutex); + put_pid_ns(ns); + return l; + } + init_rwsem(&l->mutex); + down_write(&l->mutex); + l->key.type = type; + l->key.ns = ns; + l->use_count = 0; /* don't increment here */ + l->list = NULL; + l->owner = cgrp; + list_add(&l->links, &cgrp->pidlists); + mutex_unlock(&cgrp->pidlist_mutex); + return l; +} + /* * Load a cgroup's pidarray with either procs' tgids or tasks' pids */ -static int pidlist_array_load(struct cgroup *cgrp, bool procs) +static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, + struct cgroup_pidlist **lp) { pid_t *array; int length; @@ -2423,7 +2479,10 @@ static int pidlist_array_load(struct cgroup *cgrp, bool procs) if (unlikely(n == length)) break; /* get tgid or pid for procs or tasks file respectively */ - pid = (procs ? task_tgid_vnr(tsk) : task_pid_vnr(tsk)); + if (type == CGROUP_FILE_PROCS) + pid = task_tgid_vnr(tsk); + else + pid = task_pid_vnr(tsk); if (pid > 0) /* make sure to only use valid results */ array[n++] = pid; } @@ -2431,19 +2490,20 @@ static int pidlist_array_load(struct cgroup *cgrp, bool procs) length = n; /* now sort & (if procs) strip out duplicates */ sort(array, length, sizeof(pid_t), cmppid, NULL); - if (procs) { + if (type == CGROUP_FILE_PROCS) length = pidlist_uniq(&array, length); - l = &(cgrp->procs); - } else { - l = &(cgrp->tasks); + l = cgroup_pidlist_find(cgrp, type); + if (!l) { + kfree(array); + return -ENOMEM; } - /* store array in cgroup, freeing old if necessary */ - down_write(&l->mutex); + /* store array, freeing old if necessary - lock already held */ kfree(l->list); l->list = array; l->length = length; l->use_count++; up_write(&l->mutex); + *lp = l; return 0; } @@ -2586,13 +2646,26 @@ static const struct seq_operations cgroup_pidlist_seq_operations = { static void cgroup_release_pid_array(struct cgroup_pidlist *l) { + /* + * the case where we're the last user of this particular pidlist will + * have us remove it from the cgroup's list, which entails taking the + * mutex. since in pidlist_find the pidlist->lock depends on cgroup-> + * pidlist_mutex, we have to take pidlist_mutex first. + */ + mutex_lock(&l->owner->pidlist_mutex); down_write(&l->mutex); BUG_ON(!l->use_count); if (!--l->use_count) { + /* we're the last user if refcount is 0; remove and free */ + list_del(&l->links); + mutex_unlock(&l->owner->pidlist_mutex); kfree(l->list); - l->list = NULL; - l->length = 0; + put_pid_ns(l->key.ns); + up_write(&l->mutex); + kfree(l); + return; } + mutex_unlock(&l->owner->pidlist_mutex); up_write(&l->mutex); } @@ -2623,10 +2696,10 @@ static const struct file_operations cgroup_pidlist_operations = { * in the cgroup. */ /* helper function for the two below it */ -static int cgroup_pidlist_open(struct file *file, bool procs) +static int cgroup_pidlist_open(struct file *file, enum cgroup_filetype type) { struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent); - struct cgroup_pidlist *l = (procs ? &cgrp->procs : &cgrp->tasks); + struct cgroup_pidlist *l; int retval; /* Nothing to do for write-only files */ @@ -2634,7 +2707,7 @@ static int cgroup_pidlist_open(struct file *file, bool procs) return 0; /* have the array populated */ - retval = pidlist_array_load(cgrp, procs); + retval = pidlist_array_load(cgrp, type, &l); if (retval) return retval; /* configure file information */ @@ -2650,11 +2723,11 @@ static int cgroup_pidlist_open(struct file *file, bool procs) } static int cgroup_tasks_open(struct inode *unused, struct file *file) { - return cgroup_pidlist_open(file, false); + return cgroup_pidlist_open(file, CGROUP_FILE_TASKS); } static int cgroup_procs_open(struct inode *unused, struct file *file) { - return cgroup_pidlist_open(file, true); + return cgroup_pidlist_open(file, CGROUP_FILE_PROCS); } static u64 cgroup_read_notify_on_release(struct cgroup *cgrp, -- 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 +++ kernel/cgroup.c | 8 +++++++- 2 files changed, 10 insertions(+), 1 deletion(-) (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; }; /* diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 3e356b05b2d5..bf8dd1a9f2d1 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -267,6 +267,12 @@ static struct hlist_head *css_set_hash(struct cgroup_subsys_state *css[]) return &css_set_table[index]; } +static void free_css_set_rcu(struct rcu_head *obj) +{ + struct css_set *cg = container_of(obj, struct css_set, rcu_head); + kfree(cg); +} + /* We don't maintain the lists running through each css_set to its * task until after the first call to cgroup_iter_start(). This * reduces the fork()/exit() overhead for people who have cgroups @@ -310,7 +316,7 @@ static void __put_css_set(struct css_set *cg, int taskexit) } write_unlock(&css_set_lock); - kfree(cg); + call_rcu(&cg->rcu_head, free_css_set_rcu); } /* -- 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 --- Documentation/cgroups/cgroups.txt | 12 +++++-- include/linux/cgroup.h | 7 +++-- kernel/cgroup.c | 4 +-- kernel/cgroup_freezer.c | 15 ++++++++- kernel/cpuset.c | 66 ++++++++++++++++++++++++++++++--------- kernel/ns_cgroup.c | 16 ++++++++-- kernel/sched.c | 35 +++++++++++++++++++-- mm/memcontrol.c | 3 +- security/device_cgroup.c | 3 +- 9 files changed, 131 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt index 4bccfc19196b..455d4e6d346d 100644 --- a/Documentation/cgroups/cgroups.txt +++ b/Documentation/cgroups/cgroups.txt @@ -521,7 +521,7 @@ rmdir() will fail with it. From this behavior, pre_destroy() can be called multiple times against a cgroup. int can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct task_struct *task) + struct task_struct *task, bool threadgroup) (cgroup_mutex held by caller) Called prior to moving a task into a cgroup; if the subsystem @@ -529,14 +529,20 @@ returns an error, this will abort the attach operation. If a NULL task is passed, then a successful result indicates that *any* unspecified task can be moved into the cgroup. Note that this isn't called on a fork. If this method returns 0 (success) then this should -remain valid while the caller holds cgroup_mutex. +remain valid while the caller holds cgroup_mutex. If threadgroup is +true, then a successful result indicates that all threads in the given +thread's threadgroup can be moved together. void attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup *old_cgrp, struct task_struct *task) + struct cgroup *old_cgrp, struct task_struct *task, + bool threadgroup) (cgroup_mutex held by caller) Called after the task has been attached to the cgroup, to allow any post-attachment activity that requires memory allocations or blocking. +If threadgroup is true, the subsystem should take care of all threads +in the specified thread's threadgroup. Currently does not support any +subsystem that might need the old_cgrp for every thread in the group. void fork(struct cgroup_subsy *ss, struct task_struct *task) 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, diff --git a/kernel/cgroup.c b/kernel/cgroup.c index bf8dd1a9f2d1..7ccba4bc5e3b 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1552,7 +1552,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) for_each_subsys(root, ss) { if (ss->can_attach) { - retval = ss->can_attach(ss, cgrp, tsk); + retval = ss->can_attach(ss, cgrp, tsk, false); if (retval) return retval; } @@ -1590,7 +1590,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) for_each_subsys(root, ss) { if (ss->attach) - ss->attach(ss, cgrp, oldcgrp, tsk); + ss->attach(ss, cgrp, oldcgrp, tsk, false); } set_bit(CGRP_RELEASABLE, &oldcgrp->flags); synchronize_rcu(); diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index fb249e2bcada..59e9ef6aab40 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -159,7 +159,7 @@ static bool is_task_frozen_enough(struct task_struct *task) */ static int freezer_can_attach(struct cgroup_subsys *ss, struct cgroup *new_cgroup, - struct task_struct *task) + struct task_struct *task, bool threadgroup) { struct freezer *freezer; @@ -177,6 +177,19 @@ static int freezer_can_attach(struct cgroup_subsys *ss, if (freezer->state == CGROUP_FROZEN) return -EBUSY; + if (threadgroup) { + struct task_struct *c; + + rcu_read_lock(); + list_for_each_entry_rcu(c, &task->thread_group, thread_group) { + if (is_task_frozen_enough(c)) { + rcu_read_unlock(); + return -EBUSY; + } + } + rcu_read_unlock(); + } + return 0; } diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 7e75a41bd508..b5cb469d2545 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1324,9 +1324,10 @@ static int fmeter_getrate(struct fmeter *fmp) static cpumask_var_t cpus_attach; /* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */ -static int cpuset_can_attach(struct cgroup_subsys *ss, - struct cgroup *cont, struct task_struct *tsk) +static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont, + struct task_struct *tsk, bool threadgroup) { + int ret; struct cpuset *cs = cgroup_cs(cont); if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)) @@ -1343,18 +1344,51 @@ static int cpuset_can_attach(struct cgroup_subsys *ss, if (tsk->flags & PF_THREAD_BOUND) return -EINVAL; - return security_task_setscheduler(tsk, 0, NULL); + ret = security_task_setscheduler(tsk, 0, NULL); + if (ret) + return ret; + if (threadgroup) { + struct task_struct *c; + + rcu_read_lock(); + list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { + ret = security_task_setscheduler(c, 0, NULL); + if (ret) { + rcu_read_unlock(); + return ret; + } + } + rcu_read_unlock(); + } + return 0; +} + +static void cpuset_attach_task(struct task_struct *tsk, nodemask_t *to, + struct cpuset *cs) +{ + int err; + /* + * can_attach beforehand should guarantee that this doesn't fail. + * TODO: have a better way to handle failure here + */ + err = set_cpus_allowed_ptr(tsk, cpus_attach); + WARN_ON_ONCE(err); + + task_lock(tsk); + cpuset_change_task_nodemask(tsk, to); + task_unlock(tsk); + cpuset_update_task_spread_flag(cs, tsk); + } -static void cpuset_attach(struct cgroup_subsys *ss, - struct cgroup *cont, struct cgroup *oldcont, - struct task_struct *tsk) +static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont, + struct cgroup *oldcont, struct task_struct *tsk, + bool threadgroup) { nodemask_t from, to; struct mm_struct *mm; struct cpuset *cs = cgroup_cs(cont); struct cpuset *oldcs = cgroup_cs(oldcont); - int err; if (cs == &top_cpuset) { cpumask_copy(cpus_attach, cpu_possible_mask); @@ -1363,15 +1397,19 @@ static void cpuset_attach(struct cgroup_subsys *ss, guarantee_online_cpus(cs, cpus_attach); guarantee_online_mems(cs, &to); } - err = set_cpus_allowed_ptr(tsk, cpus_attach); - if (err) - return; - task_lock(tsk); - cpuset_change_task_nodemask(tsk, &to); - task_unlock(tsk); - cpuset_update_task_spread_flag(cs, tsk); + /* do per-task migration stuff possibly for each in the threadgroup */ + cpuset_attach_task(tsk, &to, cs); + if (threadgroup) { + struct task_struct *c; + rcu_read_lock(); + list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { + cpuset_attach_task(c, &to, cs); + } + rcu_read_unlock(); + } + /* change mm; only needs to be done once even if threadgroup */ from = oldcs->mems_allowed; to = cs->mems_allowed; mm = get_task_mm(tsk); diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c index 5aa854f9e5ae..2a5dfec8efe0 100644 --- a/kernel/ns_cgroup.c +++ b/kernel/ns_cgroup.c @@ -42,8 +42,8 @@ int ns_cgroup_clone(struct task_struct *task, struct pid *pid) * (hence either you are in the same cgroup as task, or in an * ancestor cgroup thereof) */ -static int ns_can_attach(struct cgroup_subsys *ss, - struct cgroup *new_cgroup, struct task_struct *task) +static int ns_can_attach(struct cgroup_subsys *ss, struct cgroup *new_cgroup, + struct task_struct *task, bool threadgroup) { if (current != task) { if (!capable(CAP_SYS_ADMIN)) @@ -56,6 +56,18 @@ static int ns_can_attach(struct cgroup_subsys *ss, if (!cgroup_is_descendant(new_cgroup, task)) return -EPERM; + if (threadgroup) { + struct task_struct *c; + rcu_read_lock(); + list_for_each_entry_rcu(c, &task->thread_group, thread_group) { + if (!cgroup_is_descendant(new_cgroup, c)) { + rcu_read_unlock(); + return -EPERM; + } + } + rcu_read_unlock(); + } + return 0; } diff --git a/kernel/sched.c b/kernel/sched.c index 2f76e06bea58..0d0361b9dbb3 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -10377,8 +10377,7 @@ cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) } static int -cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct task_struct *tsk) +cpu_cgroup_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk) { #ifdef CONFIG_RT_GROUP_SCHED if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk)) @@ -10388,15 +10387,45 @@ cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, if (tsk->sched_class != &fair_sched_class) return -EINVAL; #endif + return 0; +} +static int +cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct task_struct *tsk, bool threadgroup) +{ + int retval = cpu_cgroup_can_attach_task(cgrp, tsk); + if (retval) + return retval; + if (threadgroup) { + struct task_struct *c; + rcu_read_lock(); + list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { + retval = cpu_cgroup_can_attach_task(cgrp, c); + if (retval) { + rcu_read_unlock(); + return retval; + } + } + rcu_read_unlock(); + } return 0; } static void cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup *old_cont, struct task_struct *tsk) + struct cgroup *old_cont, struct task_struct *tsk, + bool threadgroup) { sched_move_task(tsk); + if (threadgroup) { + struct task_struct *c; + rcu_read_lock(); + list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { + sched_move_task(c); + } + rcu_read_unlock(); + } } #ifdef CONFIG_FAIR_GROUP_SCHED diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9b10d8753784..cf2e717f5c12 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2612,7 +2612,8 @@ static int mem_cgroup_populate(struct cgroup_subsys *ss, static void mem_cgroup_move_task(struct cgroup_subsys *ss, struct cgroup *cont, struct cgroup *old_cont, - struct task_struct *p) + struct task_struct *p, + bool threadgroup) { mutex_lock(&memcg_tasklist); /* diff --git a/security/device_cgroup.c b/security/device_cgroup.c index b8186bac8b7e..6cf8fd2b79e8 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -61,7 +61,8 @@ static inline struct dev_cgroup *task_devcgroup(struct task_struct *task) struct cgroup_subsys devices_subsys; static int devcgroup_can_attach(struct cgroup_subsys *ss, - struct cgroup *new_cgroup, struct task_struct *task) + struct cgroup *new_cgroup, struct task_struct *task, + bool threadgroup) { if (current != task && !capable(CAP_SYS_ADMIN)) return -EPERM; -- 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 --- Documentation/cgroups/memory.txt | 4 +++ include/linux/page_cgroup.h | 13 ++++++++++ mm/memcontrol.c | 54 +++++++++++++++++++++++++++++----------- 3 files changed, 57 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index 23d1262c0775..ab0a02172cf4 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -179,6 +179,9 @@ The reclaim algorithm has not been modified for cgroups, except that pages that are selected for reclaiming come from the per cgroup LRU list. +NOTE: Reclaim does not work for the root cgroup, since we cannot set any +limits on the root cgroup. + 2. Locking The memory controller uses the following hierarchy @@ -210,6 +213,7 @@ We can alter the memory limit: NOTE: We can use a suffix (k, K, m, M, g or G) to indicate values in kilo, mega or gigabytes. NOTE: We can write "-1" to reset the *.limit_in_bytes(unlimited). +NOTE: We cannot set limits on the root cgroup any more. # cat /cgroups/0/memory.limit_in_bytes 4194304 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) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index cf2e717f5c12..b0757660663f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -43,6 +43,7 @@ struct cgroup_subsys mem_cgroup_subsys __read_mostly; #define MEM_CGROUP_RECLAIM_RETRIES 5 +struct mem_cgroup *root_mem_cgroup __read_mostly; #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP /* Turned on only when memory cgroup is enabled && really_do_swap_account = 1 */ @@ -200,13 +201,8 @@ enum charge_type { #define PCGF_CACHE (1UL << PCG_CACHE) #define PCGF_USED (1UL << PCG_USED) #define PCGF_LOCK (1UL << PCG_LOCK) -static const unsigned long -pcg_default_flags[NR_CHARGE_TYPE] = { - PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* File Cache */ - PCGF_USED | PCGF_LOCK, /* Anon */ - PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* Shmem */ - 0, /* FORCE */ -}; +/* Not used, but added here for completeness */ +#define PCGF_ACCT (1UL << PCG_ACCT) /* for encoding cft->private value on file */ #define _MEM (0) @@ -354,6 +350,11 @@ static int mem_cgroup_walk_tree(struct mem_cgroup *root, void *data, return ret; } +static inline bool mem_cgroup_is_root(struct mem_cgroup *mem) +{ + return (mem == root_mem_cgroup); +} + /* * Following LRU functions are allowed to be used without PCG_LOCK. * Operations are called by routine of global LRU independently from memcg. @@ -371,22 +372,24 @@ static int mem_cgroup_walk_tree(struct mem_cgroup *root, void *data, void mem_cgroup_del_lru_list(struct page *page, enum lru_list lru) { struct page_cgroup *pc; - struct mem_cgroup *mem; struct mem_cgroup_per_zone *mz; if (mem_cgroup_disabled()) return; pc = lookup_page_cgroup(page); /* can happen while we handle swapcache. */ - if (list_empty(&pc->lru) || !pc->mem_cgroup) + if (!TestClearPageCgroupAcctLRU(pc)) return; + VM_BUG_ON(!pc->mem_cgroup); /* * We don't check PCG_USED bit. It's cleared when the "page" is finally * removed from global LRU. */ mz = page_cgroup_zoneinfo(pc); - mem = pc->mem_cgroup; MEM_CGROUP_ZSTAT(mz, lru) -= 1; + if (mem_cgroup_is_root(pc->mem_cgroup)) + return; + VM_BUG_ON(list_empty(&pc->lru)); list_del_init(&pc->lru); return; } @@ -410,8 +413,8 @@ void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru) * For making pc->mem_cgroup visible, insert smp_rmb() here. */ smp_rmb(); - /* unused page is not rotated. */ - if (!PageCgroupUsed(pc)) + /* unused or root page is not rotated. */ + if (!PageCgroupUsed(pc) || mem_cgroup_is_root(pc->mem_cgroup)) return; mz = page_cgroup_zoneinfo(pc); list_move(&pc->lru, &mz->lists[lru]); @@ -425,6 +428,7 @@ void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru) if (mem_cgroup_disabled()) return; pc = lookup_page_cgroup(page); + VM_BUG_ON(PageCgroupAcctLRU(pc)); /* * Used bit is set without atomic ops but after smp_wmb(). * For making pc->mem_cgroup visible, insert smp_rmb() here. @@ -435,6 +439,9 @@ void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru) mz = page_cgroup_zoneinfo(pc); MEM_CGROUP_ZSTAT(mz, lru) += 1; + SetPageCgroupAcctLRU(pc); + if (mem_cgroup_is_root(pc->mem_cgroup)) + return; list_add(&pc->lru, &mz->lists[lru]); } @@ -469,7 +476,7 @@ static void mem_cgroup_lru_add_after_commit_swapcache(struct page *page) spin_lock_irqsave(&zone->lru_lock, flags); /* link when the page is linked to LRU but page_cgroup isn't */ - if (PageLRU(page) && list_empty(&pc->lru)) + if (PageLRU(page) && !PageCgroupAcctLRU(pc)) mem_cgroup_add_lru_list(page, page_lru(page)); spin_unlock_irqrestore(&zone->lru_lock, flags); } @@ -1125,9 +1132,22 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, css_put(&mem->css); return; } + pc->mem_cgroup = mem; smp_wmb(); - pc->flags = pcg_default_flags[ctype]; + switch (ctype) { + case MEM_CGROUP_CHARGE_TYPE_CACHE: + case MEM_CGROUP_CHARGE_TYPE_SHMEM: + SetPageCgroupCache(pc); + SetPageCgroupUsed(pc); + break; + case MEM_CGROUP_CHARGE_TYPE_MAPPED: + ClearPageCgroupCache(pc); + SetPageCgroupUsed(pc); + break; + default: + break; + } mem_cgroup_charge_statistics(mem, pc, true); @@ -2083,6 +2103,10 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, name = MEMFILE_ATTR(cft->private); switch (name) { case RES_LIMIT: + if (mem_cgroup_is_root(memcg)) { /* Can't set limit on root */ + ret = -EINVAL; + break; + } /* This function does all necessary parse...reuse it */ ret = res_counter_memparse_write_strategy(buffer, &val); if (ret) @@ -2549,6 +2573,7 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) if (cont->parent == NULL) { enable_swap_cgroup(); parent = NULL; + root_mem_cgroup = mem; } else { parent = mem_cgroup_from_cont(cont->parent); mem->use_hierarchy = parent->use_hierarchy; @@ -2577,6 +2602,7 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) return &mem->css; free_out: __mem_cgroup_free(mem); + root_mem_cgroup = NULL; return ERR_PTR(error); } -- 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 +++++++++++++++++++++++++++++++++++++++++++++ kernel/res_counter.c | 3 +++ mm/memcontrol.c | 20 ++++++++++++++++ 3 files changed, 81 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 diff --git a/kernel/res_counter.c b/kernel/res_counter.c index e1338f074314..bcdabf37c40b 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -19,6 +19,7 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent) { spin_lock_init(&counter->lock); counter->limit = RESOURCE_MAX; + counter->soft_limit = RESOURCE_MAX; counter->parent = parent; } @@ -101,6 +102,8 @@ res_counter_member(struct res_counter *counter, int member) return &counter->limit; case RES_FAILCNT: return &counter->failcnt; + case RES_SOFT_LIMIT: + return &counter->soft_limit; }; BUG(); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index eb9571815f0c..4ad3e6be045d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2123,6 +2123,20 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, else ret = mem_cgroup_resize_memsw_limit(memcg, val); break; + case RES_SOFT_LIMIT: + ret = res_counter_memparse_write_strategy(buffer, &val); + if (ret) + break; + /* + * For memsw, soft limits are hard to implement in terms + * of semantics, for now, we support soft limits for + * control without swap + */ + if (type == _MEM) + ret = res_counter_set_soft_limit(&memcg->res, val); + else + ret = -EINVAL; + break; default: ret = -EINVAL; /* should be BUG() ? */ break; @@ -2375,6 +2389,12 @@ static struct cftype mem_cgroup_files[] = { .write_string = mem_cgroup_write, .read_u64 = mem_cgroup_read, }, + { + .name = "soft_limit_in_bytes", + .private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT), + .write_string = mem_cgroup_write, + .read_u64 = mem_cgroup_read, + }, { .name = "failcnt", .private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT), -- 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 +- kernel/res_counter.c | 18 ++- mm/memcontrol.c | 300 +++++++++++++++++++++++++++++++++++++------- 3 files changed, 277 insertions(+), 47 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) { diff --git a/kernel/res_counter.c b/kernel/res_counter.c index bcdabf37c40b..88faec23e833 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -37,17 +37,27 @@ int res_counter_charge_locked(struct res_counter *counter, unsigned long val) } int res_counter_charge(struct res_counter *counter, unsigned long val, - struct res_counter **limit_fail_at) + struct res_counter **limit_fail_at, + struct res_counter **soft_limit_fail_at) { int ret; unsigned long flags; struct res_counter *c, *u; *limit_fail_at = NULL; + if (soft_limit_fail_at) + *soft_limit_fail_at = NULL; local_irq_save(flags); for (c = counter; c != NULL; c = c->parent) { spin_lock(&c->lock); ret = res_counter_charge_locked(c, val); + /* + * With soft limits, we return the highest ancestor + * that exceeds its soft limit + */ + if (soft_limit_fail_at && + !res_counter_soft_limit_check_locked(c)) + *soft_limit_fail_at = c; spin_unlock(&c->lock); if (ret < 0) { *limit_fail_at = c; @@ -75,7 +85,8 @@ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val) counter->usage -= 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) { unsigned long flags; struct res_counter *c; @@ -83,6 +94,9 @@ void res_counter_uncharge(struct res_counter *counter, unsigned long val) local_irq_save(flags); for (c = counter; c != NULL; c = c->parent) { spin_lock(&c->lock); + if (was_soft_limit_excess) + *was_soft_limit_excess = + !res_counter_soft_limit_check_locked(c); res_counter_uncharge_locked(c, val); spin_unlock(&c->lock); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4ad3e6be045d..0ed325943cd1 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include @@ -54,6 +55,7 @@ static int really_do_swap_account __initdata = 1; /* for remember boot option*/ #endif static DEFINE_MUTEX(memcg_tasklist); /* can be hold under cgroup_mutex */ +#define SOFTLIMIT_EVENTS_THRESH (1000) /* * Statistics for memory cgroup. @@ -67,6 +69,7 @@ enum mem_cgroup_stat_index { MEM_CGROUP_STAT_MAPPED_FILE, /* # of pages charged as file rss */ MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */ MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */ + MEM_CGROUP_STAT_EVENTS, /* sum of pagein + pageout for internal use */ MEM_CGROUP_STAT_NSTATS, }; @@ -79,6 +82,20 @@ struct mem_cgroup_stat { struct mem_cgroup_stat_cpu cpustat[0]; }; +static inline void +__mem_cgroup_stat_reset_safe(struct mem_cgroup_stat_cpu *stat, + enum mem_cgroup_stat_index idx) +{ + stat->count[idx] = 0; +} + +static inline s64 +__mem_cgroup_stat_read_local(struct mem_cgroup_stat_cpu *stat, + enum mem_cgroup_stat_index idx) +{ + return stat->count[idx]; +} + /* * For accounting under irq disable, no need for increment preempt count. */ @@ -118,6 +135,10 @@ struct mem_cgroup_per_zone { unsigned long count[NR_LRU_LISTS]; struct zone_reclaim_stat reclaim_stat; + struct rb_node tree_node; /* RB tree node */ + unsigned long long usage_in_excess;/* Set to the value by which */ + /* the soft limit is exceeded*/ + bool on_tree; }; /* Macro for accessing counter */ #define MEM_CGROUP_ZSTAT(mz, idx) ((mz)->count[(idx)]) @@ -130,6 +151,26 @@ struct mem_cgroup_lru_info { struct mem_cgroup_per_node *nodeinfo[MAX_NUMNODES]; }; +/* + * Cgroups above their limits are maintained in a RB-Tree, independent of + * their hierarchy representation + */ + +struct mem_cgroup_tree_per_zone { + struct rb_root rb_root; + spinlock_t lock; +}; + +struct mem_cgroup_tree_per_node { + struct mem_cgroup_tree_per_zone rb_tree_per_zone[MAX_NR_ZONES]; +}; + +struct mem_cgroup_tree { + struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES]; +}; + +static struct mem_cgroup_tree soft_limit_tree __read_mostly; + /* * The memory controller data structure. The memory controller controls both * page cache and RSS per cgroup. We would eventually like to provide @@ -215,6 +256,150 @@ static void mem_cgroup_get(struct mem_cgroup *mem); static void mem_cgroup_put(struct mem_cgroup *mem); static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem); +static struct mem_cgroup_per_zone * +mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid) +{ + return &mem->info.nodeinfo[nid]->zoneinfo[zid]; +} + +static struct mem_cgroup_per_zone * +page_cgroup_zoneinfo(struct page_cgroup *pc) +{ + struct mem_cgroup *mem = pc->mem_cgroup; + int nid = page_cgroup_nid(pc); + int zid = page_cgroup_zid(pc); + + if (!mem) + return NULL; + + return mem_cgroup_zoneinfo(mem, nid, zid); +} + +static struct mem_cgroup_tree_per_zone * +soft_limit_tree_node_zone(int nid, int zid) +{ + return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; +} + +static struct mem_cgroup_tree_per_zone * +soft_limit_tree_from_page(struct page *page) +{ + int nid = page_to_nid(page); + int zid = page_zonenum(page); + + return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; +} + +static void +mem_cgroup_insert_exceeded(struct mem_cgroup *mem, + struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz) +{ + struct rb_node **p = &mctz->rb_root.rb_node; + struct rb_node *parent = NULL; + struct mem_cgroup_per_zone *mz_node; + + if (mz->on_tree) + return; + + mz->usage_in_excess = res_counter_soft_limit_excess(&mem->res); + spin_lock(&mctz->lock); + while (*p) { + parent = *p; + mz_node = rb_entry(parent, struct mem_cgroup_per_zone, + tree_node); + if (mz->usage_in_excess < mz_node->usage_in_excess) + p = &(*p)->rb_left; + /* + * We can't avoid mem cgroups that are over their soft + * limit by the same amount + */ + else if (mz->usage_in_excess >= mz_node->usage_in_excess) + p = &(*p)->rb_right; + } + rb_link_node(&mz->tree_node, parent, p); + rb_insert_color(&mz->tree_node, &mctz->rb_root); + mz->on_tree = true; + spin_unlock(&mctz->lock); +} + +static void +mem_cgroup_remove_exceeded(struct mem_cgroup *mem, + struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz) +{ + spin_lock(&mctz->lock); + rb_erase(&mz->tree_node, &mctz->rb_root); + mz->on_tree = false; + spin_unlock(&mctz->lock); +} + +static bool mem_cgroup_soft_limit_check(struct mem_cgroup *mem) +{ + bool ret = false; + int cpu; + s64 val; + struct mem_cgroup_stat_cpu *cpustat; + + cpu = get_cpu(); + cpustat = &mem->stat.cpustat[cpu]; + val = __mem_cgroup_stat_read_local(cpustat, MEM_CGROUP_STAT_EVENTS); + if (unlikely(val > SOFTLIMIT_EVENTS_THRESH)) { + __mem_cgroup_stat_reset_safe(cpustat, MEM_CGROUP_STAT_EVENTS); + ret = true; + } + put_cpu(); + return ret; +} + +static void mem_cgroup_update_tree(struct mem_cgroup *mem, struct page *page) +{ + unsigned long long prev_usage_in_excess, new_usage_in_excess; + bool updated_tree = false; + struct mem_cgroup_per_zone *mz; + struct mem_cgroup_tree_per_zone *mctz; + + mz = mem_cgroup_zoneinfo(mem, page_to_nid(page), page_zonenum(page)); + mctz = soft_limit_tree_from_page(page); + + /* + * We do updates in lazy mode, mem's are removed + * lazily from the per-zone, per-node rb tree + */ + prev_usage_in_excess = mz->usage_in_excess; + + new_usage_in_excess = res_counter_soft_limit_excess(&mem->res); + if (prev_usage_in_excess) { + mem_cgroup_remove_exceeded(mem, mz, mctz); + updated_tree = true; + } + if (!new_usage_in_excess) + goto done; + mem_cgroup_insert_exceeded(mem, mz, mctz); + +done: + if (updated_tree) { + spin_lock(&mctz->lock); + mz->usage_in_excess = new_usage_in_excess; + spin_unlock(&mctz->lock); + } +} + +static void mem_cgroup_remove_from_trees(struct mem_cgroup *mem) +{ + int node, zone; + struct mem_cgroup_per_zone *mz; + struct mem_cgroup_tree_per_zone *mctz; + + for_each_node_state(node, N_POSSIBLE) { + for (zone = 0; zone < MAX_NR_ZONES; zone++) { + mz = mem_cgroup_zoneinfo(mem, node, zone); + mctz = soft_limit_tree_node_zone(node, zone); + mem_cgroup_remove_exceeded(mem, mz, mctz); + } + } +} + static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, struct page_cgroup *pc, bool charge) @@ -236,28 +421,10 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, else __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_PGPGOUT_COUNT, 1); + __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_EVENTS, 1); put_cpu(); } -static struct mem_cgroup_per_zone * -mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid) -{ - return &mem->info.nodeinfo[nid]->zoneinfo[zid]; -} - -static struct mem_cgroup_per_zone * -page_cgroup_zoneinfo(struct page_cgroup *pc) -{ - struct mem_cgroup *mem = pc->mem_cgroup; - int nid = page_cgroup_nid(pc); - int zid = page_cgroup_zid(pc); - - if (!mem) - return NULL; - - return mem_cgroup_zoneinfo(mem, nid, zid); -} - static unsigned long mem_cgroup_get_local_zonestat(struct mem_cgroup *mem, enum lru_list idx) { @@ -972,11 +1139,11 @@ done: */ static int __mem_cgroup_try_charge(struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup **memcg, - bool oom) + bool oom, struct page *page) { - struct mem_cgroup *mem, *mem_over_limit; + struct mem_cgroup *mem, *mem_over_limit, *mem_over_soft_limit; int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; - struct res_counter *fail_res; + struct res_counter *fail_res, *soft_fail_res = NULL; if (unlikely(test_thread_flag(TIF_MEMDIE))) { /* Don't account this! */ @@ -1006,16 +1173,17 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, int ret; bool noswap = false; - ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res); + ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res, + &soft_fail_res); if (likely(!ret)) { if (!do_swap_account) break; ret = res_counter_charge(&mem->memsw, PAGE_SIZE, - &fail_res); + &fail_res, NULL); if (likely(!ret)) break; /* mem+swap counter fails */ - res_counter_uncharge(&mem->res, PAGE_SIZE); + res_counter_uncharge(&mem->res, PAGE_SIZE, NULL); noswap = true; mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw); @@ -1053,13 +1221,23 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, goto nomem; } } + /* + * Insert just the ancestor, we should trickle down to the correct + * cgroup for reclaim, since the other nodes will be below their + * soft limit + */ + if (soft_fail_res) { + mem_over_soft_limit = + mem_cgroup_from_res_counter(soft_fail_res, res); + if (mem_cgroup_soft_limit_check(mem_over_soft_limit)) + mem_cgroup_update_tree(mem_over_soft_limit, page); + } return 0; nomem: css_put(&mem->css); return -ENOMEM; } - /* * A helper function to get mem_cgroup from ID. must be called under * rcu_read_lock(). The caller must check css_is_removed() or some if @@ -1126,9 +1304,9 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, lock_page_cgroup(pc); if (unlikely(PageCgroupUsed(pc))) { unlock_page_cgroup(pc); - res_counter_uncharge(&mem->res, PAGE_SIZE); + res_counter_uncharge(&mem->res, PAGE_SIZE, NULL); if (do_swap_account) - res_counter_uncharge(&mem->memsw, PAGE_SIZE); + res_counter_uncharge(&mem->memsw, PAGE_SIZE, NULL); css_put(&mem->css); return; } @@ -1205,7 +1383,7 @@ static int mem_cgroup_move_account(struct page_cgroup *pc, if (pc->mem_cgroup != from) goto out; - res_counter_uncharge(&from->res, PAGE_SIZE); + res_counter_uncharge(&from->res, PAGE_SIZE, NULL); mem_cgroup_charge_statistics(from, pc, false); page = pc->page; @@ -1225,7 +1403,7 @@ static int mem_cgroup_move_account(struct page_cgroup *pc, } if (do_swap_account) - res_counter_uncharge(&from->memsw, PAGE_SIZE); + res_counter_uncharge(&from->memsw, PAGE_SIZE, NULL); css_put(&from->css); css_get(&to->css); @@ -1265,7 +1443,7 @@ static int mem_cgroup_move_parent(struct page_cgroup *pc, parent = mem_cgroup_from_cont(pcg); - ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false); + ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false, page); if (ret || !parent) return ret; @@ -1295,9 +1473,9 @@ uncharge: /* drop extra refcnt by try_charge() */ css_put(&parent->css); /* uncharge if move fails */ - res_counter_uncharge(&parent->res, PAGE_SIZE); + res_counter_uncharge(&parent->res, PAGE_SIZE, NULL); if (do_swap_account) - res_counter_uncharge(&parent->memsw, PAGE_SIZE); + res_counter_uncharge(&parent->memsw, PAGE_SIZE, NULL); return ret; } @@ -1322,7 +1500,7 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, prefetchw(pc); mem = memcg; - ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true); + ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true, page); if (ret || !mem) return ret; @@ -1441,14 +1619,14 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm, if (!mem) goto charge_cur_mm; *ptr = mem; - ret = __mem_cgroup_try_charge(NULL, mask, ptr, true); + ret = __mem_cgroup_try_charge(NULL, mask, ptr, true, page); /* drop extra refcnt from tryget */ css_put(&mem->css); return ret; charge_cur_mm: if (unlikely(!mm)) mm = &init_mm; - return __mem_cgroup_try_charge(mm, mask, ptr, true); + return __mem_cgroup_try_charge(mm, mask, ptr, true, page); } static void @@ -1486,7 +1664,7 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, * This recorded memcg can be obsolete one. So, avoid * calling css_tryget */ - res_counter_uncharge(&memcg->memsw, PAGE_SIZE); + res_counter_uncharge(&memcg->memsw, PAGE_SIZE, NULL); mem_cgroup_put(memcg); } rcu_read_unlock(); @@ -1511,9 +1689,9 @@ void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem) return; if (!mem) return; - res_counter_uncharge(&mem->res, PAGE_SIZE); + res_counter_uncharge(&mem->res, PAGE_SIZE, NULL); if (do_swap_account) - res_counter_uncharge(&mem->memsw, PAGE_SIZE); + res_counter_uncharge(&mem->memsw, PAGE_SIZE, NULL); css_put(&mem->css); } @@ -1527,6 +1705,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) struct page_cgroup *pc; struct mem_cgroup *mem = NULL; struct mem_cgroup_per_zone *mz; + bool soft_limit_excess = false; if (mem_cgroup_disabled()) return NULL; @@ -1565,9 +1744,9 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) break; } - res_counter_uncharge(&mem->res, PAGE_SIZE); + res_counter_uncharge(&mem->res, PAGE_SIZE, &soft_limit_excess); if (do_swap_account && (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT)) - res_counter_uncharge(&mem->memsw, PAGE_SIZE); + res_counter_uncharge(&mem->memsw, PAGE_SIZE, NULL); mem_cgroup_charge_statistics(mem, pc, false); ClearPageCgroupUsed(pc); @@ -1581,6 +1760,8 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) mz = page_cgroup_zoneinfo(pc); unlock_page_cgroup(pc); + if (soft_limit_excess && mem_cgroup_soft_limit_check(mem)) + mem_cgroup_update_tree(mem, page); /* at swapout, this memcg will be accessed to record to swap */ if (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT) css_put(&mem->css); @@ -1656,7 +1837,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t ent) * We uncharge this because swap is freed. * This memcg can be obsolete one. We avoid calling css_tryget */ - res_counter_uncharge(&memcg->memsw, PAGE_SIZE); + res_counter_uncharge(&memcg->memsw, PAGE_SIZE, NULL); mem_cgroup_put(memcg); } rcu_read_unlock(); @@ -1685,7 +1866,8 @@ int mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr) unlock_page_cgroup(pc); if (mem) { - ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false); + ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false, + page); css_put(&mem->css); } *ptr = mem; @@ -2194,6 +2376,7 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) res_counter_reset_failcnt(&mem->memsw); break; } + return 0; } @@ -2489,6 +2672,7 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) mz = &pn->zoneinfo[zone]; for_each_lru(l) INIT_LIST_HEAD(&mz->lists[l]); + mz->usage_in_excess = 0; } return 0; } @@ -2534,6 +2718,7 @@ static void __mem_cgroup_free(struct mem_cgroup *mem) { int node; + mem_cgroup_remove_from_trees(mem); free_css_id(&mem_cgroup_subsys, &mem->css); for_each_node_state(node, N_POSSIBLE) @@ -2582,6 +2767,31 @@ static void __init enable_swap_cgroup(void) } #endif +static int mem_cgroup_soft_limit_tree_init(void) +{ + struct mem_cgroup_tree_per_node *rtpn; + struct mem_cgroup_tree_per_zone *rtpz; + int tmp, node, zone; + + for_each_node_state(node, N_POSSIBLE) { + tmp = node; + if (!node_state(node, N_NORMAL_MEMORY)) + tmp = -1; + rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp); + if (!rtpn) + return 1; + + soft_limit_tree.rb_tree_per_node[node] = rtpn; + + for (zone = 0; zone < MAX_NR_ZONES; zone++) { + rtpz = &rtpn->rb_tree_per_zone[zone]; + rtpz->rb_root = RB_ROOT; + spin_lock_init(&rtpz->lock); + } + } + return 0; +} + static struct cgroup_subsys_state * __ref mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) { @@ -2596,11 +2806,15 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) for_each_node_state(node, N_POSSIBLE) if (alloc_mem_cgroup_per_zone_info(mem, node)) goto free_out; + /* root ? */ if (cont->parent == NULL) { enable_swap_cgroup(); parent = NULL; root_mem_cgroup = mem; + if (mem_cgroup_soft_limit_tree_init()) + goto free_out; + } else { parent = mem_cgroup_from_cont(cont->parent); mem->use_hierarchy = parent->use_hierarchy; -- 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 + mm/memcontrol.c | 226 ++++++++++++++++++++++++++++++++++++++++++--- mm/vmscan.c | 45 ++++++++- 4 files changed, 271 insertions(+), 15 deletions(-) (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; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 90f0b13e1c3c..011aba6cad70 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -139,6 +139,8 @@ struct mem_cgroup_per_zone { unsigned long long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ bool on_tree; + struct mem_cgroup *mem; /* Back pointer, we cannot */ + /* use container_of */ }; /* Macro for accessing counter */ #define MEM_CGROUP_ZSTAT(mz, idx) ((mz)->count[(idx)]) @@ -228,6 +230,13 @@ struct mem_cgroup { struct mem_cgroup_stat stat; }; +/* + * Maximum loops in mem_cgroup_hierarchical_reclaim(), used for soft + * limit reclaim to prevent infinite loops, if they ever occur. + */ +#define MEM_CGROUP_MAX_RECLAIM_LOOPS (100) +#define MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS (2) + enum charge_type { MEM_CGROUP_CHARGE_TYPE_CACHE = 0, MEM_CGROUP_CHARGE_TYPE_MAPPED, @@ -259,6 +268,8 @@ enum charge_type { #define MEM_CGROUP_RECLAIM_NOSWAP (1 << MEM_CGROUP_RECLAIM_NOSWAP_BIT) #define MEM_CGROUP_RECLAIM_SHRINK_BIT 0x1 #define MEM_CGROUP_RECLAIM_SHRINK (1 << MEM_CGROUP_RECLAIM_SHRINK_BIT) +#define MEM_CGROUP_RECLAIM_SOFT_BIT 0x2 +#define MEM_CGROUP_RECLAIM_SOFT (1 << MEM_CGROUP_RECLAIM_SOFT_BIT) static void mem_cgroup_get(struct mem_cgroup *mem); static void mem_cgroup_put(struct mem_cgroup *mem); @@ -299,7 +310,7 @@ soft_limit_tree_from_page(struct page *page) } static void -mem_cgroup_insert_exceeded(struct mem_cgroup *mem, +__mem_cgroup_insert_exceeded(struct mem_cgroup *mem, struct mem_cgroup_per_zone *mz, struct mem_cgroup_tree_per_zone *mctz) { @@ -311,7 +322,6 @@ mem_cgroup_insert_exceeded(struct mem_cgroup *mem, return; mz->usage_in_excess = res_counter_soft_limit_excess(&mem->res); - spin_lock(&mctz->lock); while (*p) { parent = *p; mz_node = rb_entry(parent, struct mem_cgroup_per_zone, @@ -328,6 +338,26 @@ mem_cgroup_insert_exceeded(struct mem_cgroup *mem, rb_link_node(&mz->tree_node, parent, p); rb_insert_color(&mz->tree_node, &mctz->rb_root); mz->on_tree = true; +} + +static void +__mem_cgroup_remove_exceeded(struct mem_cgroup *mem, + struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz) +{ + if (!mz->on_tree) + return; + rb_erase(&mz->tree_node, &mctz->rb_root); + mz->on_tree = false; +} + +static void +mem_cgroup_insert_exceeded(struct mem_cgroup *mem, + struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz) +{ + spin_lock(&mctz->lock); + __mem_cgroup_insert_exceeded(mem, mz, mctz); spin_unlock(&mctz->lock); } @@ -337,8 +367,7 @@ mem_cgroup_remove_exceeded(struct mem_cgroup *mem, struct mem_cgroup_tree_per_zone *mctz) { spin_lock(&mctz->lock); - rb_erase(&mz->tree_node, &mctz->rb_root); - mz->on_tree = false; + __mem_cgroup_remove_exceeded(mem, mz, mctz); spin_unlock(&mctz->lock); } @@ -408,6 +437,47 @@ static void mem_cgroup_remove_from_trees(struct mem_cgroup *mem) } } +static inline unsigned long mem_cgroup_get_excess(struct mem_cgroup *mem) +{ + return res_counter_soft_limit_excess(&mem->res) >> PAGE_SHIFT; +} + +static struct mem_cgroup_per_zone * +__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) +{ + struct rb_node *rightmost = NULL; + struct mem_cgroup_per_zone *mz = NULL; + +retry: + rightmost = rb_last(&mctz->rb_root); + if (!rightmost) + goto done; /* Nothing to reclaim from */ + + mz = rb_entry(rightmost, struct mem_cgroup_per_zone, tree_node); + /* + * Remove the node now but someone else can add it back, + * we will to add it back at the end of reclaim to its correct + * position in the tree. + */ + __mem_cgroup_remove_exceeded(mz->mem, mz, mctz); + if (!res_counter_soft_limit_excess(&mz->mem->res) || + !css_tryget(&mz->mem->css)) + goto retry; +done: + return mz; +} + +static struct mem_cgroup_per_zone * +mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) +{ + struct mem_cgroup_per_zone *mz; + + spin_lock(&mctz->lock); + mz = __mem_cgroup_largest_soft_limit_node(mctz); + spin_unlock(&mctz->lock); + return mz; +} + static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, struct page_cgroup *pc, bool charge) @@ -1037,6 +1107,7 @@ mem_cgroup_select_victim(struct mem_cgroup *root_mem) * If shrink==true, for avoiding to free too much, this returns immedieately. */ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, + struct zone *zone, gfp_t gfp_mask, unsigned long reclaim_options) { @@ -1045,23 +1116,53 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, int loop = 0; bool noswap = reclaim_options & MEM_CGROUP_RECLAIM_NOSWAP; bool shrink = reclaim_options & MEM_CGROUP_RECLAIM_SHRINK; + bool check_soft = reclaim_options & MEM_CGROUP_RECLAIM_SOFT; + unsigned long excess = mem_cgroup_get_excess(root_mem); /* If memsw_is_minimum==1, swap-out is of-no-use. */ if (root_mem->memsw_is_minimum) noswap = true; - while (loop < 2) { + while (1) { victim = mem_cgroup_select_victim(root_mem); - if (victim == root_mem) + if (victim == root_mem) { loop++; + if (loop >= 2) { + /* + * If we have not been able to reclaim + * anything, it might because there are + * no reclaimable pages under this hierarchy + */ + if (!check_soft || !total) { + css_put(&victim->css); + break; + } + /* + * We want to do more targetted reclaim. + * excess >> 2 is not to excessive so as to + * reclaim too much, nor too less that we keep + * coming back to reclaim from this cgroup + */ + if (total >= (excess >> 2) || + (loop > MEM_CGROUP_MAX_RECLAIM_LOOPS)) { + css_put(&victim->css); + break; + } + } + } if (!mem_cgroup_local_usage(&victim->stat)) { /* this cgroup's local usage == 0 */ css_put(&victim->css); continue; } /* we use swappiness of local cgroup */ - ret = try_to_free_mem_cgroup_pages(victim, gfp_mask, noswap, - get_swappiness(victim)); + if (check_soft) + ret = mem_cgroup_shrink_node_zone(victim, gfp_mask, + noswap, get_swappiness(victim), zone, + zone->zone_pgdat->node_id); + else + ret = try_to_free_mem_cgroup_pages(victim, gfp_mask, + noswap, get_swappiness(victim)); css_put(&victim->css); /* * At shrinking usage, we can't check we should stop here or @@ -1071,7 +1172,10 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, if (shrink) return ret; total += ret; - if (mem_cgroup_check_under_limit(root_mem)) + if (check_soft) { + if (res_counter_check_under_soft_limit(&root_mem->res)) + return total; + } else if (mem_cgroup_check_under_limit(root_mem)) return 1 + total; } return total; @@ -1206,8 +1310,8 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, if (!(gfp_mask & __GFP_WAIT)) goto nomem; - ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, gfp_mask, - flags); + ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, NULL, + gfp_mask, flags); if (ret) continue; @@ -2018,8 +2122,9 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, if (!ret) break; - progress = mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, - MEM_CGROUP_RECLAIM_SHRINK); + progress = mem_cgroup_hierarchical_reclaim(memcg, NULL, + GFP_KERNEL, + MEM_CGROUP_RECLAIM_SHRINK); curusage = res_counter_read_u64(&memcg->res, RES_USAGE); /* Usage is reduced ? */ if (curusage >= oldusage) @@ -2071,7 +2176,7 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, if (!ret) break; - mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, + mem_cgroup_hierarchical_reclaim(memcg, NULL, GFP_KERNEL, MEM_CGROUP_RECLAIM_NOSWAP | MEM_CGROUP_RECLAIM_SHRINK); curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); @@ -2084,6 +2189,97 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, return ret; } +unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, + gfp_t gfp_mask, int nid, + int zid) +{ + unsigned long nr_reclaimed = 0; + struct mem_cgroup_per_zone *mz, *next_mz = NULL; + unsigned long reclaimed; + int loop = 0; + struct mem_cgroup_tree_per_zone *mctz; + + if (order > 0) + return 0; + + mctz = soft_limit_tree_node_zone(nid, zid); + /* + * This loop can run a while, specially if mem_cgroup's continuously + * keep exceeding their soft limit and putting the system under + * pressure + */ + do { + if (next_mz) + mz = next_mz; + else + mz = mem_cgroup_largest_soft_limit_node(mctz); + if (!mz) + break; + + reclaimed = mem_cgroup_hierarchical_reclaim(mz->mem, zone, + gfp_mask, + MEM_CGROUP_RECLAIM_SOFT); + nr_reclaimed += reclaimed; + spin_lock(&mctz->lock); + + /* + * If we failed to reclaim anything from this memory cgroup + * it is time to move on to the next cgroup + */ + next_mz = NULL; + if (!reclaimed) { + do { + /* + * Loop until we find yet another one. + * + * By the time we get the soft_limit lock + * again, someone might have aded the + * group back on the RB tree. Iterate to + * make sure we get a different mem. + * mem_cgroup_largest_soft_limit_node returns + * NULL if no other cgroup is present on + * the tree + */ + next_mz = + __mem_cgroup_largest_soft_limit_node(mctz); + if (next_mz == mz) { + css_put(&next_mz->mem->css); + next_mz = NULL; + } else /* next_mz == NULL or other memcg */ + break; + } while (1); + } + mz->usage_in_excess = + res_counter_soft_limit_excess(&mz->mem->res); + __mem_cgroup_remove_exceeded(mz->mem, mz, mctz); + /* + * One school of thought says that we should not add + * back the node to the tree if reclaim returns 0. + * But our reclaim could return 0, simply because due + * to priority we are exposing a smaller subset of + * memory to reclaim from. Consider this as a longer + * term TODO. + */ + if (mz->usage_in_excess) + __mem_cgroup_insert_exceeded(mz->mem, mz, mctz); + spin_unlock(&mctz->lock); + css_put(&mz->mem->css); + loop++; + /* + * Could not reclaim anything and there are no more + * mem cgroups to try or we seem to be looping without + * reclaiming anything. + */ + if (!nr_reclaimed && + (next_mz == NULL || + loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS)) + break; + } while (!nr_reclaimed); + if (next_mz) + css_put(&next_mz->mem->css); + return nr_reclaimed; +} + /* * This routine traverse page_cgroup in given list and drop them all. * *And* this routine doesn't reclaim page itself, just removes page_cgroup. @@ -2686,6 +2882,8 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) for_each_lru(l) INIT_LIST_HEAD(&mz->lists[l]); mz->usage_in_excess = 0; + mz->on_tree = false; + mz->mem = mem; } return 0; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 613e89f471d9..2423782214ab 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1836,11 +1836,45 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, #ifdef CONFIG_CGROUP_MEM_RES_CTLR +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) +{ + struct scan_control sc = { + .may_writepage = !laptop_mode, + .may_unmap = 1, + .may_swap = !noswap, + .swap_cluster_max = SWAP_CLUSTER_MAX, + .swappiness = swappiness, + .order = 0, + .mem_cgroup = mem, + .isolate_pages = mem_cgroup_isolate_pages, + }; + nodemask_t nm = nodemask_of_node(nid); + + sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | + (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); + sc.nodemask = &nm; + sc.nr_reclaimed = 0; + sc.nr_scanned = 0; + /* + * NOTE: Although we can get the priority field, using it + * here is not a good idea, since it limits the pages we can scan. + * if we don't reclaim here, the shrink_zone from balance_pgdat + * will pick up pages from other mem cgroup's as well. We hack + * the priority and make it zero. + */ + shrink_zone(0, zone, &sc); + return sc.nr_reclaimed; +} + unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, gfp_t gfp_mask, bool noswap, unsigned int swappiness) { + struct zonelist *zonelist; struct scan_control sc = { .may_writepage = !laptop_mode, .may_unmap = 1, @@ -1852,7 +1886,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, .isolate_pages = mem_cgroup_isolate_pages, .nodemask = NULL, /* we don't care the placement */ }; - struct zonelist *zonelist; sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); @@ -1974,6 +2007,7 @@ loop_again: for (i = 0; i <= end_zone; i++) { struct zone *zone = pgdat->node_zones + i; int nr_slab; + int nid, zid; if (!populated_zone(zone)) continue; @@ -1988,6 +2022,15 @@ loop_again: temp_priority[i] = priority; sc.nr_scanned = 0; note_zone_scanning_priority(zone, priority); + + nid = pgdat->node_id; + zid = zone_idx(zone); + /* + * Call soft limit reclaim before calling shrink_zone. + * For now we ignore the return value + */ + mem_cgroup_soft_limit_reclaim(zone, order, sc.gfp_mask, + nid, zid); /* * We put equal pressure on every zone, unless one * zone has way too many pages free already. -- 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 + kernel/exit.c | 5 +++++ kernel/ptrace.c | 11 +++++++---- kernel/signal.c | 9 --------- 4 files changed, 13 insertions(+), 13 deletions(-) (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); diff --git a/kernel/exit.c b/kernel/exit.c index 60d6fdcc9265..782b2e1f7ca2 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1575,6 +1575,11 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk) return 0; } +void __wake_up_parent(struct task_struct *p, struct task_struct *parent) +{ + wake_up_interruptible_sync(&parent->signal->wait_chldexit); +} + static long do_wait(struct wait_opts *wo) { DECLARE_WAITQUEUE(wait, current); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 307c285af59e..23bd09cd042e 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -266,9 +266,10 @@ static int ignoring_children(struct sighand_struct *sigh) * or self-reaping. Do notification now if it would have happened earlier. * If it should reap itself, return true. * - * If it's our own child, there is no notification to do. - * But if our normal children self-reap, then this child - * was prevented by ptrace and we must reap it now. + * If it's our own child, there is no notification to do. But if our normal + * children self-reap, then this child was prevented by ptrace and we must + * reap it now, in that case we must also wake up sub-threads sleeping in + * do_wait(). */ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p) { @@ -278,8 +279,10 @@ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p) if (!task_detached(p) && thread_group_empty(p)) { if (!same_thread_group(p->real_parent, tracer)) do_notify_parent(p, p->exit_signal); - else if (ignoring_children(tracer->sighand)) + else if (ignoring_children(tracer->sighand)) { + __wake_up_parent(p, tracer); p->exit_signal = -1; + } } if (task_detached(p)) { /* Mark it as in the process of being reaped. */ diff --git a/kernel/signal.c b/kernel/signal.c index 64c5deeaca5d..534ea81cde47 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1382,15 +1382,6 @@ ret: return ret; } -/* - * Wake up any threads in the parent blocked in wait* syscalls. - */ -static inline void __wake_up_parent(struct task_struct *p, - struct task_struct *parent) -{ - wake_up_interruptible_sync(&parent->signal->wait_chldexit); -} - /* * Let a parent know about the death of a child. * For a stopped/continued status change, use do_notify_parent_cldstop instead. -- 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 ++++++++++++----- kernel/signal.c | 97 +++++++++++++++++++++++------------------------ 2 files changed, 72 insertions(+), 59 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 diff --git a/kernel/signal.c b/kernel/signal.c index 534ea81cde47..5d3b3f8f219b 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -705,7 +705,7 @@ static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns) if (why) { /* - * The first thread which returns from finish_stop() + * The first thread which returns from do_signal_stop() * will take ->siglock, notice SIGNAL_CLD_MASK, and * notify its parent. See get_signal_to_deliver(). */ @@ -1664,29 +1664,6 @@ void ptrace_notify(int exit_code) spin_unlock_irq(¤t->sighand->siglock); } -static void -finish_stop(int stop_count) -{ - /* - * If there are no other threads in the group, or if there is - * a group stop in progress and we are the last to stop, - * report to the parent. When ptraced, every thread reports itself. - */ - if (tracehook_notify_jctl(stop_count == 0, CLD_STOPPED)) { - read_lock(&tasklist_lock); - do_notify_parent_cldstop(current, CLD_STOPPED); - read_unlock(&tasklist_lock); - } - - do { - schedule(); - } while (try_to_freeze()); - /* - * Now we don't run again until continued. - */ - current->exit_code = 0; -} - /* * This performs the stopping for SIGSTOP and other stop signals. * We have to stop all threads in the thread group. @@ -1696,15 +1673,9 @@ finish_stop(int stop_count) static int do_signal_stop(int signr) { struct signal_struct *sig = current->signal; - int stop_count; + int notify; - if (sig->group_stop_count > 0) { - /* - * There is a group stop in progress. We don't need to - * start another one. - */ - stop_count = --sig->group_stop_count; - } else { + if (!sig->group_stop_count) { struct task_struct *t; if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED) || @@ -1716,7 +1687,7 @@ static int do_signal_stop(int signr) */ sig->group_exit_code = signr; - stop_count = 0; + sig->group_stop_count = 1; for (t = next_thread(current); t != current; t = next_thread(t)) /* * Setting state to TASK_STOPPED for a group @@ -1725,19 +1696,44 @@ static int do_signal_stop(int signr) */ if (!(t->flags & PF_EXITING) && !task_is_stopped_or_traced(t)) { - stop_count++; + sig->group_stop_count++; signal_wake_up(t, 0); } - sig->group_stop_count = stop_count; } + /* + * If there are no other threads in the group, or if there is + * a group stop in progress and we are the last to stop, report + * to the parent. When ptraced, every thread reports itself. + */ + notify = sig->group_stop_count == 1 ? CLD_STOPPED : 0; + notify = tracehook_notify_jctl(notify, CLD_STOPPED); + /* + * tracehook_notify_jctl() can drop and reacquire siglock, so + * we keep ->group_stop_count != 0 before the call. If SIGCONT + * or SIGKILL comes in between ->group_stop_count == 0. + */ + if (sig->group_stop_count) { + if (!--sig->group_stop_count) + sig->flags = SIGNAL_STOP_STOPPED; + current->exit_code = sig->group_exit_code; + __set_current_state(TASK_STOPPED); + } + spin_unlock_irq(¤t->sighand->siglock); - if (stop_count == 0) - sig->flags = SIGNAL_STOP_STOPPED; - current->exit_code = sig->group_exit_code; - __set_current_state(TASK_STOPPED); + if (notify) { + read_lock(&tasklist_lock); + do_notify_parent_cldstop(current, notify); + read_unlock(&tasklist_lock); + } + + /* Now we don't run again until woken by SIGCONT or SIGKILL */ + do { + schedule(); + } while (try_to_freeze()); + + tracehook_finish_jctl(); + current->exit_code = 0; - spin_unlock_irq(¤t->sighand->siglock); - finish_stop(stop_count); return 1; } @@ -1806,14 +1802,15 @@ relock: int why = (signal->flags & SIGNAL_STOP_CONTINUED) ? CLD_CONTINUED : CLD_STOPPED; signal->flags &= ~SIGNAL_CLD_MASK; - spin_unlock_irq(&sighand->siglock); - if (unlikely(!tracehook_notify_jctl(1, why))) - goto relock; + why = tracehook_notify_jctl(why, CLD_CONTINUED); + spin_unlock_irq(&sighand->siglock); - read_lock(&tasklist_lock); - do_notify_parent_cldstop(current->group_leader, why); - read_unlock(&tasklist_lock); + if (why) { + read_lock(&tasklist_lock); + do_notify_parent_cldstop(current->group_leader, why); + read_unlock(&tasklist_lock); + } goto relock; } @@ -1978,14 +1975,14 @@ void exit_signals(struct task_struct *tsk) if (unlikely(tsk->signal->group_stop_count) && !--tsk->signal->group_stop_count) { tsk->signal->flags = SIGNAL_STOP_STOPPED; - group_stop = 1; + group_stop = tracehook_notify_jctl(CLD_STOPPED, CLD_STOPPED); } out: spin_unlock_irq(&tsk->sighand->siglock); - if (unlikely(group_stop) && tracehook_notify_jctl(1, CLD_STOPPED)) { + if (unlikely(group_stop)) { read_lock(&tasklist_lock); - do_notify_parent_cldstop(tsk, CLD_STOPPED); + do_notify_parent_cldstop(tsk, group_stop); read_unlock(&tasklist_lock); } } -- 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 --- fs/exec.c | 14 +++++--------- include/linux/binfmts.h | 2 +- 2 files changed, 6 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/exec.c b/fs/exec.c index 8efbdc606a1e..6dc92c39dd94 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1395,18 +1395,14 @@ out_ret: return retval; } -int set_binfmt(struct linux_binfmt *new) +void set_binfmt(struct linux_binfmt *new) { - struct linux_binfmt *old = current->binfmt; + if (current->binfmt) + module_put(current->binfmt->module); - if (new) { - if (!try_module_get(new->module)) - return -1; - } current->binfmt = new; - if (old) - module_put(old->module); - return 0; + if (new) + __module_get(new->module); } EXPORT_SYMBOL(set_binfmt); 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 ++ kernel/signal.c | 56 ++++++++++++++++++++++++-------------------------- 2 files changed, 29 insertions(+), 29 deletions(-) (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, diff --git a/kernel/signal.c b/kernel/signal.c index 5d3b3f8f219b..c6d7a24a86a1 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -971,6 +971,20 @@ specific_send_sig_info(int sig, struct siginfo *info, struct task_struct *t) return send_signal(sig, info, t, 0); } +int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, + bool group) +{ + unsigned long flags; + int ret = -ESRCH; + + if (lock_task_sighand(p, &flags)) { + ret = send_signal(sig, info, p, group); + unlock_task_sighand(p, &flags); + } + + return ret; +} + /* * Force a signal that the process can't ignore: if necessary * we unblock the signal and change any SIG_IGN to SIG_DFL. @@ -1068,18 +1082,10 @@ struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long */ int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p) { - unsigned long flags; - int ret; - - ret = check_kill_permission(sig, info, p); + int ret = check_kill_permission(sig, info, p); - if (!ret && sig) { - ret = -ESRCH; - if (lock_task_sighand(p, &flags)) { - ret = __group_send_sig_info(sig, info, p); - unlock_task_sighand(p, &flags); - } - } + if (!ret && sig) + ret = do_send_sig_info(sig, info, p, true); return ret; } @@ -1224,15 +1230,9 @@ static int kill_something_info(int sig, struct siginfo *info, pid_t pid) * These are for backward compatibility with the rest of the kernel source. */ -/* - * The caller must ensure the task can't exit. - */ int send_sig_info(int sig, struct siginfo *info, struct task_struct *p) { - int ret; - unsigned long flags; - /* * Make sure legacy kernel users don't send in bad values * (normal paths check this in check_kill_permission). @@ -1240,10 +1240,7 @@ send_sig_info(int sig, struct siginfo *info, struct task_struct *p) if (!valid_signal(sig)) return -EINVAL; - spin_lock_irqsave(&p->sighand->siglock, flags); - ret = specific_send_sig_info(sig, info, p); - spin_unlock_irqrestore(&p->sighand->siglock, flags); - return ret; + return do_send_sig_info(sig, info, p, false); } #define __si_special(priv) \ @@ -2278,7 +2275,6 @@ static int do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info) { struct task_struct *p; - unsigned long flags; int error = -ESRCH; rcu_read_lock(); @@ -2288,14 +2284,16 @@ do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info) /* * The null signal is a permissions and process existence * probe. No signal is actually delivered. - * - * If lock_task_sighand() fails we pretend the task dies - * after receiving the signal. The window is tiny, and the - * signal is private anyway. */ - if (!error && sig && lock_task_sighand(p, &flags)) { - error = specific_send_sig_info(sig, info, p); - unlock_task_sighand(p, &flags); + if (!error && sig) { + error = do_send_sig_info(sig, info, p, false); + /* + * If lock_task_sighand() failed we pretend the task + * dies after receiving the signal. The window is tiny, + * and the signal is private anyway. + */ + if (unlikely(error == -ESRCH)) + error = 0; } } rcu_read_unlock(); -- 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 ++++- kernel/signal.c | 6 ------ 2 files changed, 4 insertions(+), 7 deletions(-) (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) { diff --git a/kernel/signal.c b/kernel/signal.c index c6d7a24a86a1..6705320784fd 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1050,12 +1050,6 @@ void zap_other_threads(struct task_struct *p) } } -int __fatal_signal_pending(struct task_struct *tsk) -{ - return sigismember(&tsk->pending.signal, SIGKILL); -} -EXPORT_SYMBOL(__fatal_signal_pending); - struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long *flags) { struct sighand_struct *sighand; -- 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 --- arch/frv/kernel/pm.c | 14 +++---- arch/mips/lasat/sysctl.c | 18 ++++----- arch/s390/appldata/appldata_base.c | 9 ++--- arch/s390/kernel/debug.c | 4 +- arch/s390/mm/cmm.c | 4 +- arch/x86/include/asm/nmi.h | 3 +- arch/x86/kernel/apic/nmi.c | 4 +- arch/x86/kernel/vsyscall_64.c | 10 +---- drivers/cdrom/cdrom.c | 8 ++-- drivers/char/random.c | 4 +- drivers/net/wireless/arlan-proc.c | 28 +++++++------- drivers/parport/procfs.c | 12 +++--- fs/coda/coda_int.h | 1 + fs/drop_caches.c | 4 +- fs/file_table.c | 6 +-- fs/proc/proc_sysctl.c | 2 +- fs/xfs/linux-2.6/xfs_sysctl.c | 3 +- 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 +++--- include/net/ip.h | 2 +- include/net/ndisc.h | 2 - ipc/ipc_sysctl.c | 16 ++++---- ipc/mq_sysctl.c | 8 ++-- kernel/hung_task.c | 4 +- kernel/sched.c | 4 +- kernel/sched_fair.c | 4 +- kernel/slow-work.c | 12 +++--- kernel/softlockup.c | 4 +- kernel/sysctl.c | 78 ++++++++++++++++---------------------- kernel/trace/ftrace.c | 4 +- kernel/trace/trace_stack.c | 4 +- kernel/utsname_sysctl.c | 4 +- mm/hugetlb.c | 12 +++--- mm/page-writeback.c | 20 +++++----- mm/page_alloc.c | 24 ++++++------ mm/vmscan.c | 4 +- net/bridge/br_netfilter.c | 4 +- net/decnet/dn_dev.c | 5 +-- net/decnet/sysctl_net_decnet.c | 2 - net/ipv4/devinet.c | 12 +++--- net/ipv4/route.c | 7 ++-- net/ipv4/sysctl_net_ipv4.c | 16 ++++---- net/ipv6/addrconf.c | 8 ++-- net/ipv6/ndisc.c | 8 ++-- net/ipv6/route.c | 4 +- net/irda/irsysctl.c | 8 ++-- net/netfilter/ipvs/ip_vs_ctl.c | 8 ++-- net/netfilter/nf_log.c | 4 +- net/phonet/sysctl.c | 4 +- net/sunrpc/sysctl.c | 4 +- net/sunrpc/xprtrdma/svc_rdma.c | 2 +- security/min_addr.c | 4 +- 60 files changed, 239 insertions(+), 270 deletions(-) (limited to 'include/linux') diff --git a/arch/frv/kernel/pm.c b/arch/frv/kernel/pm.c index be722fc1acff..0d4d3e3a4cfc 100644 --- a/arch/frv/kernel/pm.c +++ b/arch/frv/kernel/pm.c @@ -150,7 +150,7 @@ static int user_atoi(char __user *ubuf, size_t len) /* * Send us to sleep. */ -static int sysctl_pm_do_suspend(ctl_table *ctl, int write, struct file *filp, +static int sysctl_pm_do_suspend(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *fpos) { int retval, mode; @@ -198,13 +198,13 @@ static int try_set_cmode(int new_cmode) } -static int cmode_procctl(ctl_table *ctl, int write, struct file *filp, +static int cmode_procctl(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *fpos) { int new_cmode; if (!write) - return proc_dointvec(ctl, write, filp, buffer, lenp, fpos); + return proc_dointvec(ctl, write, buffer, lenp, fpos); new_cmode = user_atoi(buffer, *lenp); @@ -301,13 +301,13 @@ static int try_set_cm(int new_cm) return 0; } -static int p0_procctl(ctl_table *ctl, int write, struct file *filp, +static int p0_procctl(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *fpos) { int new_p0; if (!write) - return proc_dointvec(ctl, write, filp, buffer, lenp, fpos); + return proc_dointvec(ctl, write, buffer, lenp, fpos); new_p0 = user_atoi(buffer, *lenp); @@ -345,13 +345,13 @@ static int p0_sysctl(ctl_table *table, return 1; } -static int cm_procctl(ctl_table *ctl, int write, struct file *filp, +static int cm_procctl(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *fpos) { int new_cm; if (!write) - return proc_dointvec(ctl, write, filp, buffer, lenp, fpos); + return proc_dointvec(ctl, write, buffer, lenp, fpos); new_cm = user_atoi(buffer, *lenp); diff --git a/arch/mips/lasat/sysctl.c b/arch/mips/lasat/sysctl.c index 3f04d4c406b7..b3deed8db619 100644 --- a/arch/mips/lasat/sysctl.c +++ b/arch/mips/lasat/sysctl.c @@ -56,12 +56,12 @@ int sysctl_lasatstring(ctl_table *table, /* And the same for proc */ -int proc_dolasatstring(ctl_table *table, int write, struct file *filp, +int proc_dolasatstring(ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int r; - r = proc_dostring(table, write, filp, buffer, lenp, ppos); + r = proc_dostring(table, write, buffer, lenp, ppos); if ((!write) || r) return r; @@ -71,12 +71,12 @@ int proc_dolasatstring(ctl_table *table, int write, struct file *filp, } /* proc function to write EEPROM after changing int entry */ -int proc_dolasatint(ctl_table *table, int write, struct file *filp, +int proc_dolasatint(ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int r; - r = proc_dointvec(table, write, filp, buffer, lenp, ppos); + r = proc_dointvec(table, write, buffer, lenp, ppos); if ((!write) || r) return r; @@ -89,7 +89,7 @@ int proc_dolasatint(ctl_table *table, int write, struct file *filp, static int rtctmp; /* proc function to read/write RealTime Clock */ -int proc_dolasatrtc(ctl_table *table, int write, struct file *filp, +int proc_dolasatrtc(ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct timespec ts; @@ -102,7 +102,7 @@ int proc_dolasatrtc(ctl_table *table, int write, struct file *filp, if (rtctmp < 0) rtctmp = 0; } - r = proc_dointvec(table, write, filp, buffer, lenp, ppos); + r = proc_dointvec(table, write, buffer, lenp, ppos); if (r) return r; @@ -154,7 +154,7 @@ int sysctl_lasat_rtc(ctl_table *table, #endif #ifdef CONFIG_INET -int proc_lasat_ip(ctl_table *table, int write, struct file *filp, +int proc_lasat_ip(ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { unsigned int ip; @@ -231,12 +231,12 @@ static int sysctl_lasat_prid(ctl_table *table, return 0; } -int proc_lasat_prid(ctl_table *table, int write, struct file *filp, +int proc_lasat_prid(ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int r; - r = proc_dointvec(table, write, filp, buffer, lenp, ppos); + r = proc_dointvec(table, write, buffer, lenp, ppos); if (r < 0) return r; if (write) { diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index 264528e4f58d..b55fd7ed1c31 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -50,10 +50,9 @@ static struct platform_device *appldata_pdev; * /proc entries (sysctl) */ static const char appldata_proc_name[APPLDATA_PROC_NAME_LENGTH] = "appldata"; -static int appldata_timer_handler(ctl_table *ctl, int write, struct file *filp, +static int appldata_timer_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos); static int appldata_interval_handler(ctl_table *ctl, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos); @@ -247,7 +246,7 @@ __appldata_vtimer_setup(int cmd) * Start/Stop timer, show status of timer (0 = not active, 1 = active) */ static int -appldata_timer_handler(ctl_table *ctl, int write, struct file *filp, +appldata_timer_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int len; @@ -289,7 +288,7 @@ out: * current timer interval. */ static int -appldata_interval_handler(ctl_table *ctl, int write, struct file *filp, +appldata_interval_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int len, interval; @@ -335,7 +334,7 @@ out: * monitoring (0 = not in process, 1 = in process) */ static int -appldata_generic_handler(ctl_table *ctl, int write, struct file *filp, +appldata_generic_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct appldata_ops *ops = NULL, *tmp_ops; diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 4c512561687d..20f282c911c2 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -881,11 +881,11 @@ static int debug_active=1; * if debug_active is already off */ static int -s390dbf_procactive(ctl_table *table, int write, struct file *filp, +s390dbf_procactive(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { if (!write || debug_stoppable || !debug_active) - return proc_dointvec(table, write, filp, buffer, lenp, ppos); + return proc_dointvec(table, write, buffer, lenp, ppos); else return 0; } diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 413c240cbca7..b201135cc18c 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -262,7 +262,7 @@ cmm_skip_blanks(char *cp, char **endp) static struct ctl_table cmm_table[]; static int -cmm_pages_handler(ctl_table *ctl, int write, struct file *filp, +cmm_pages_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char buf[16], *p; @@ -303,7 +303,7 @@ cmm_pages_handler(ctl_table *ctl, int write, struct file *filp, } static int -cmm_timeout_handler(ctl_table *ctl, int write, struct file *filp, +cmm_timeout_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char buf[64], *p; diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index e63cf7d441e1..139d4c1a33a7 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -40,8 +40,7 @@ extern unsigned int nmi_watchdog; #define NMI_INVALID 3 struct ctl_table; -struct file; -extern int proc_nmi_enabled(struct ctl_table *, int , struct file *, +extern int proc_nmi_enabled(struct ctl_table *, int , void __user *, size_t *, loff_t *); extern int unknown_nmi_panic; diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c index cb66a22d98ad..7ff61d6a188a 100644 --- a/arch/x86/kernel/apic/nmi.c +++ b/arch/x86/kernel/apic/nmi.c @@ -508,14 +508,14 @@ static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu) /* * proc handler for /proc/sys/kernel/nmi */ -int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file, +int proc_nmi_enabled(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { int old_state; nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0; old_state = nmi_watchdog_enabled; - proc_dointvec(table, write, file, buffer, length, ppos); + proc_dointvec(table, write, buffer, length, ppos); if (!!old_state == !!nmi_watchdog_enabled) return 0; diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index cf53a78e2dcf..8cb4974ff599 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -228,19 +228,11 @@ static long __vsyscall(3) venosys_1(void) } #ifdef CONFIG_SYSCTL - -static int -vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return proc_dointvec(ctl, write, filp, buffer, lenp, ppos); -} - static ctl_table kernel_table2[] = { { .procname = "vsyscall64", .data = &vsyscall_gtod_data.sysctl_enabled, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = vsyscall_sysctl_change }, + .proc_handler = proc_dointvec }, {} }; diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 71d1b9bab70b..614da5b8613a 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -3412,7 +3412,7 @@ static int cdrom_print_info(const char *header, int val, char *info, return 0; } -static int cdrom_sysctl_info(ctl_table *ctl, int write, struct file * filp, +static int cdrom_sysctl_info(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int pos; @@ -3489,7 +3489,7 @@ static int cdrom_sysctl_info(ctl_table *ctl, int write, struct file * filp, goto done; doit: mutex_unlock(&cdrom_mutex); - return proc_dostring(ctl, write, filp, buffer, lenp, ppos); + return proc_dostring(ctl, write, buffer, lenp, ppos); done: printk(KERN_INFO "cdrom: info buffer too small\n"); goto doit; @@ -3525,12 +3525,12 @@ static void cdrom_update_settings(void) mutex_unlock(&cdrom_mutex); } -static int cdrom_sysctl_handler(ctl_table *ctl, int write, struct file * filp, +static int cdrom_sysctl_handler(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; - ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write) { diff --git a/drivers/char/random.c b/drivers/char/random.c index d8a9255e1a3f..04b505e5a5e2 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1231,7 +1231,7 @@ static char sysctl_bootid[16]; * as an ASCII string in the standard UUID format. If accesses via the * sysctl system call, it is returned as 16 bytes of binary data. */ -static int proc_do_uuid(ctl_table *table, int write, struct file *filp, +static int proc_do_uuid(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { ctl_table fake_table; @@ -1254,7 +1254,7 @@ static int proc_do_uuid(ctl_table *table, int write, struct file *filp, fake_table.data = buf; fake_table.maxlen = sizeof(buf); - return proc_dostring(&fake_table, write, filp, buffer, lenp, ppos); + return proc_dostring(&fake_table, write, buffer, lenp, ppos); } static int uuid_strategy(ctl_table *table, diff --git a/drivers/net/wireless/arlan-proc.c b/drivers/net/wireless/arlan-proc.c index 2ab1d59870f4..a8b689635a3b 100644 --- a/drivers/net/wireless/arlan-proc.c +++ b/drivers/net/wireless/arlan-proc.c @@ -402,7 +402,7 @@ static int arlan_setup_card_by_book(struct net_device *dev) static char arlan_drive_info[ARLAN_STR_SIZE] = "A655\n\0"; -static int arlan_sysctl_info(ctl_table * ctl, int write, struct file *filp, +static int arlan_sysctl_info(ctl_table * ctl, int write, void __user *buffer, size_t * lenp, loff_t *ppos) { int i; @@ -629,7 +629,7 @@ final: *lenp = pos; if (!write) - retv = proc_dostring(ctl, write, filp, buffer, lenp, ppos); + retv = proc_dostring(ctl, write, buffer, lenp, ppos); else { *lenp = 0; @@ -639,7 +639,7 @@ final: } -static int arlan_sysctl_info161719(ctl_table * ctl, int write, struct file *filp, +static int arlan_sysctl_info161719(ctl_table * ctl, int write, void __user *buffer, size_t * lenp, loff_t *ppos) { int i; @@ -669,11 +669,11 @@ static int arlan_sysctl_info161719(ctl_table * ctl, int write, struct file *filp final: *lenp = pos; - retv = proc_dostring(ctl, write, filp, buffer, lenp, ppos); + retv = proc_dostring(ctl, write, buffer, lenp, ppos); return retv; } -static int arlan_sysctl_infotxRing(ctl_table * ctl, int write, struct file *filp, +static int arlan_sysctl_infotxRing(ctl_table * ctl, int write, void __user *buffer, size_t * lenp, loff_t *ppos) { int i; @@ -698,11 +698,11 @@ static int arlan_sysctl_infotxRing(ctl_table * ctl, int write, struct file *filp SARLBNpln(u_char, txBuffer, 0x800); final: *lenp = pos; - retv = proc_dostring(ctl, write, filp, buffer, lenp, ppos); + retv = proc_dostring(ctl, write, buffer, lenp, ppos); return retv; } -static int arlan_sysctl_inforxRing(ctl_table * ctl, int write, struct file *filp, +static int arlan_sysctl_inforxRing(ctl_table * ctl, int write, void __user *buffer, size_t * lenp, loff_t *ppos) { int i; @@ -726,11 +726,11 @@ static int arlan_sysctl_inforxRing(ctl_table * ctl, int write, struct file *filp SARLBNpln(u_char, rxBuffer, 0x800); final: *lenp = pos; - retv = proc_dostring(ctl, write, filp, buffer, lenp, ppos); + retv = proc_dostring(ctl, write, buffer, lenp, ppos); return retv; } -static int arlan_sysctl_info18(ctl_table * ctl, int write, struct file *filp, +static int arlan_sysctl_info18(ctl_table * ctl, int write, void __user *buffer, size_t * lenp, loff_t *ppos) { int i; @@ -756,7 +756,7 @@ static int arlan_sysctl_info18(ctl_table * ctl, int write, struct file *filp, final: *lenp = pos; - retv = proc_dostring(ctl, write, filp, buffer, lenp, ppos); + retv = proc_dostring(ctl, write, buffer, lenp, ppos); return retv; } @@ -766,7 +766,7 @@ final: static char conf_reset_result[200]; -static int arlan_configure(ctl_table * ctl, int write, struct file *filp, +static int arlan_configure(ctl_table * ctl, int write, void __user *buffer, size_t * lenp, loff_t *ppos) { int pos = 0; @@ -788,10 +788,10 @@ static int arlan_configure(ctl_table * ctl, int write, struct file *filp, return -1; *lenp = pos; - return proc_dostring(ctl, write, filp, buffer, lenp, ppos); + return proc_dostring(ctl, write, buffer, lenp, ppos); } -static int arlan_sysctl_reset(ctl_table * ctl, int write, struct file *filp, +static int arlan_sysctl_reset(ctl_table * ctl, int write, void __user *buffer, size_t * lenp, loff_t *ppos) { int pos = 0; @@ -811,7 +811,7 @@ static int arlan_sysctl_reset(ctl_table * ctl, int write, struct file *filp, } else return -1; *lenp = pos + 3; - return proc_dostring(ctl, write, filp, buffer, lenp, ppos); + return proc_dostring(ctl, write, buffer, lenp, ppos); } diff --git a/drivers/parport/procfs.c b/drivers/parport/procfs.c index 554e11f9e1ce..8eefe56f1cbe 100644 --- a/drivers/parport/procfs.c +++ b/drivers/parport/procfs.c @@ -31,7 +31,7 @@ #define PARPORT_MIN_SPINTIME_VALUE 1 #define PARPORT_MAX_SPINTIME_VALUE 1000 -static int do_active_device(ctl_table *table, int write, struct file *filp, +static int do_active_device(ctl_table *table, int write, void __user *result, size_t *lenp, loff_t *ppos) { struct parport *port = (struct parport *)table->extra1; @@ -68,7 +68,7 @@ static int do_active_device(ctl_table *table, int write, struct file *filp, } #ifdef CONFIG_PARPORT_1284 -static int do_autoprobe(ctl_table *table, int write, struct file *filp, +static int do_autoprobe(ctl_table *table, int write, void __user *result, size_t *lenp, loff_t *ppos) { struct parport_device_info *info = table->extra2; @@ -111,7 +111,7 @@ static int do_autoprobe(ctl_table *table, int write, struct file *filp, #endif /* IEEE1284.3 support. */ static int do_hardware_base_addr (ctl_table *table, int write, - struct file *filp, void __user *result, + void __user *result, size_t *lenp, loff_t *ppos) { struct parport *port = (struct parport *)table->extra1; @@ -139,7 +139,7 @@ static int do_hardware_base_addr (ctl_table *table, int write, } static int do_hardware_irq (ctl_table *table, int write, - struct file *filp, void __user *result, + void __user *result, size_t *lenp, loff_t *ppos) { struct parport *port = (struct parport *)table->extra1; @@ -167,7 +167,7 @@ static int do_hardware_irq (ctl_table *table, int write, } static int do_hardware_dma (ctl_table *table, int write, - struct file *filp, void __user *result, + void __user *result, size_t *lenp, loff_t *ppos) { struct parport *port = (struct parport *)table->extra1; @@ -195,7 +195,7 @@ static int do_hardware_dma (ctl_table *table, int write, } static int do_hardware_modes (ctl_table *table, int write, - struct file *filp, void __user *result, + void __user *result, size_t *lenp, loff_t *ppos) { struct parport *port = (struct parport *)table->extra1; diff --git a/fs/coda/coda_int.h b/fs/coda/coda_int.h index 8ccd5ed81d9c..d99860a33890 100644 --- a/fs/coda/coda_int.h +++ b/fs/coda/coda_int.h @@ -2,6 +2,7 @@ #define _CODA_INT_ struct dentry; +struct file; extern struct file_system_type coda_fs_type; extern unsigned long coda_timeout; diff --git a/fs/drop_caches.c b/fs/drop_caches.c index a2edb7913447..31f4b0e6d72c 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -63,9 +63,9 @@ static void drop_slab(void) } int drop_caches_sysctl_handler(ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, loff_t *ppos) + void __user *buffer, size_t *length, loff_t *ppos) { - proc_dointvec_minmax(table, write, file, buffer, length, ppos); + proc_dointvec_minmax(table, write, buffer, length, ppos); if (write) { if (sysctl_drop_caches & 1) drop_pagecache(); diff --git a/fs/file_table.c b/fs/file_table.c index 334ce39881f8..8eb44042e009 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -74,14 +74,14 @@ EXPORT_SYMBOL_GPL(get_max_files); * Handle nr_files sysctl */ #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) -int proc_nr_files(ctl_table *table, int write, struct file *filp, +int proc_nr_files(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { files_stat.nr_files = get_nr_files(); - return proc_dointvec(table, write, filp, buffer, lenp, ppos); + return proc_dointvec(table, write, buffer, lenp, ppos); } #else -int proc_nr_files(ctl_table *table, int write, struct file *filp, +int proc_nr_files(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 9b1e4e9a16bf..f667e8aeabdf 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -153,7 +153,7 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf, /* careful: calling conventions are nasty here */ res = count; - error = table->proc_handler(table, write, filp, buf, &res, ppos); + error = table->proc_handler(table, write, buf, &res, ppos); if (!error) error = res; out: diff --git a/fs/xfs/linux-2.6/xfs_sysctl.c b/fs/xfs/linux-2.6/xfs_sysctl.c index 916c0ffb6083..c5bc67c4e3bb 100644 --- a/fs/xfs/linux-2.6/xfs_sysctl.c +++ b/fs/xfs/linux-2.6/xfs_sysctl.c @@ -26,7 +26,6 @@ STATIC int xfs_stats_clear_proc_handler( ctl_table *ctl, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -34,7 +33,7 @@ xfs_stats_clear_proc_handler( int c, ret, *valp = ctl->data; __uint32_t vn_active; - ret = proc_dointvec_minmax(ctl, write, filp, buffer, lenp, ppos); + ret = proc_dointvec_minmax(ctl, write, buffer, lenp, ppos); if (!ret && write && *valp) { printk("XFS Clearing xfsstats\n"); 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, diff --git a/include/net/ip.h b/include/net/ip.h index 72c36926c26d..5b26a0bd178e 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -399,7 +399,7 @@ extern void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport, * fed into the routing cache should use these handlers. */ int ipv4_doint_and_flush(ctl_table *ctl, int write, - struct file* filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos); int ipv4_doint_and_flush_strategy(ctl_table *table, void __user *oldval, size_t __user *oldlenp, diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 1459ed3e2697..f76f22d05721 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -55,7 +55,6 @@ enum { #include struct ctl_table; -struct file; struct inet6_dev; struct net_device; struct net_proto_family; @@ -139,7 +138,6 @@ extern int igmp6_event_report(struct sk_buff *skb); #ifdef CONFIG_SYSCTL extern int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, - struct file * filp, void __user *buffer, size_t *lenp, loff_t *ppos); diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c index 40eab7314aeb..7d3704750efc 100644 --- a/ipc/ipc_sysctl.c +++ b/ipc/ipc_sysctl.c @@ -27,18 +27,18 @@ static void *get_ipc(ctl_table *table) } #ifdef CONFIG_PROC_SYSCTL -static int proc_ipc_dointvec(ctl_table *table, int write, struct file *filp, +static int proc_ipc_dointvec(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table ipc_table; memcpy(&ipc_table, table, sizeof(ipc_table)); ipc_table.data = get_ipc(table); - return proc_dointvec(&ipc_table, write, filp, buffer, lenp, ppos); + return proc_dointvec(&ipc_table, write, buffer, lenp, ppos); } static int proc_ipc_callback_dointvec(ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) + void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table ipc_table; size_t lenp_bef = *lenp; @@ -47,7 +47,7 @@ static int proc_ipc_callback_dointvec(ctl_table *table, int write, memcpy(&ipc_table, table, sizeof(ipc_table)); ipc_table.data = get_ipc(table); - rc = proc_dointvec(&ipc_table, write, filp, buffer, lenp, ppos); + rc = proc_dointvec(&ipc_table, write, buffer, lenp, ppos); if (write && !rc && lenp_bef == *lenp) /* @@ -61,13 +61,13 @@ static int proc_ipc_callback_dointvec(ctl_table *table, int write, } static int proc_ipc_doulongvec_minmax(ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) + void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table ipc_table; memcpy(&ipc_table, table, sizeof(ipc_table)); ipc_table.data = get_ipc(table); - return proc_doulongvec_minmax(&ipc_table, write, filp, buffer, + return proc_doulongvec_minmax(&ipc_table, write, buffer, lenp, ppos); } @@ -95,7 +95,7 @@ static void ipc_auto_callback(int val) } static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) + void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table ipc_table; size_t lenp_bef = *lenp; @@ -106,7 +106,7 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write, ipc_table.data = get_ipc(table); oldval = *((int *)(ipc_table.data)); - rc = proc_dointvec_minmax(&ipc_table, write, filp, buffer, lenp, ppos); + rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos); if (write && !rc && lenp_bef == *lenp) { int newval = *((int *)(ipc_table.data)); diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c index 24ae46dfe45d..8a058711fc10 100644 --- a/ipc/mq_sysctl.c +++ b/ipc/mq_sysctl.c @@ -31,24 +31,24 @@ static void *get_mq(ctl_table *table) return which; } -static int proc_mq_dointvec(ctl_table *table, int write, struct file *filp, +static int proc_mq_dointvec(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table mq_table; memcpy(&mq_table, table, sizeof(mq_table)); mq_table.data = get_mq(table); - return proc_dointvec(&mq_table, write, filp, buffer, lenp, ppos); + return proc_dointvec(&mq_table, write, buffer, lenp, ppos); } static int proc_mq_dointvec_minmax(ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) + void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table mq_table; memcpy(&mq_table, table, sizeof(mq_table)); mq_table.data = get_mq(table); - return proc_dointvec_minmax(&mq_table, write, filp, buffer, + return proc_dointvec_minmax(&mq_table, write, buffer, lenp, ppos); } #else diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 022a4927b785..d4e841747400 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -171,12 +171,12 @@ static unsigned long timeout_jiffies(unsigned long timeout) * Process updating of timeout sysctl */ 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) { int ret; - ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos); + ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret || !write) goto out; diff --git a/kernel/sched.c b/kernel/sched.c index 0d0361b9dbb3..ee61f454a98b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -10312,7 +10312,7 @@ static int sched_rt_global_constraints(void) #endif /* CONFIG_RT_GROUP_SCHED */ 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) { int ret; @@ -10323,7 +10323,7 @@ int sched_rt_handler(struct ctl_table *table, int write, old_period = sysctl_sched_rt_period; old_runtime = sysctl_sched_rt_runtime; - ret = proc_dointvec(table, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(table, write, buffer, lenp, ppos); if (!ret && write) { ret = sched_rt_global_constraints(); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index ecc637a0d591..4e777b47eeda 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -384,10 +384,10 @@ static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq) #ifdef CONFIG_SCHED_DEBUG int sched_nr_latency_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) { - int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret || !write) return ret; diff --git a/kernel/slow-work.c b/kernel/slow-work.c index 09d7519557d3..0d31135efbf4 100644 --- a/kernel/slow-work.c +++ b/kernel/slow-work.c @@ -26,10 +26,10 @@ static void slow_work_cull_timeout(unsigned long); static void slow_work_oom_timeout(unsigned long); #ifdef CONFIG_SYSCTL -static int slow_work_min_threads_sysctl(struct ctl_table *, int, struct file *, +static int slow_work_min_threads_sysctl(struct ctl_table *, int, void __user *, size_t *, loff_t *); -static int slow_work_max_threads_sysctl(struct ctl_table *, int , struct file *, +static int slow_work_max_threads_sysctl(struct ctl_table *, int , void __user *, size_t *, loff_t *); #endif @@ -493,10 +493,10 @@ static void slow_work_oom_timeout(unsigned long data) * Handle adjustment of the minimum number of threads */ static int slow_work_min_threads_sysctl(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); int n; if (ret == 0) { @@ -521,10 +521,10 @@ static int slow_work_min_threads_sysctl(struct ctl_table *table, int write, * Handle adjustment of the maximum number of threads */ static int slow_work_max_threads_sysctl(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); int n; if (ret == 0) { diff --git a/kernel/softlockup.c b/kernel/softlockup.c index 88796c330838..81324d12eb35 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -90,11 +90,11 @@ void touch_all_softlockup_watchdogs(void) EXPORT_SYMBOL(touch_all_softlockup_watchdogs); 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) { touch_all_softlockup_watchdogs(); - return proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + return proc_dointvec_minmax(table, write, buffer, lenp, ppos); } /* diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 37abb8c3995b..a02697b7cb97 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -163,9 +163,9 @@ extern int max_lock_depth; #endif #ifdef CONFIG_PROC_SYSCTL -static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp, +static int proc_do_cad_pid(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -static int proc_taint(struct ctl_table *table, int write, struct file *filp, +static int proc_taint(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); #endif @@ -2226,7 +2226,7 @@ void sysctl_head_put(struct ctl_table_header *head) #ifdef CONFIG_PROC_SYSCTL static int _proc_do_string(void* data, int maxlen, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { size_t len; @@ -2287,7 +2287,6 @@ static int _proc_do_string(void* data, int maxlen, int write, * proc_dostring - read a string sysctl * @table: the sysctl table * @write: %TRUE if this is a write to the sysctl file - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -2301,10 +2300,10 @@ static int _proc_do_string(void* data, int maxlen, int write, * * Returns 0 on success. */ -int proc_dostring(struct ctl_table *table, int write, struct file *filp, +int proc_dostring(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return _proc_do_string(table->data, table->maxlen, write, filp, + return _proc_do_string(table->data, table->maxlen, write, buffer, lenp, ppos); } @@ -2329,7 +2328,7 @@ static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp, } static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, - int write, struct file *filp, void __user *buffer, + int write, void __user *buffer, size_t *lenp, loff_t *ppos, int (*conv)(int *negp, unsigned long *lvalp, int *valp, int write, void *data), @@ -2436,13 +2435,13 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, #undef TMPBUFLEN } -static int do_proc_dointvec(struct ctl_table *table, int write, struct file *filp, +static int do_proc_dointvec(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos, int (*conv)(int *negp, unsigned long *lvalp, int *valp, int write, void *data), void *data) { - return __do_proc_dointvec(table->data, table, write, filp, + return __do_proc_dointvec(table->data, table, write, buffer, lenp, ppos, conv, data); } @@ -2450,7 +2449,6 @@ static int do_proc_dointvec(struct ctl_table *table, int write, struct file *fil * proc_dointvec - read a vector of integers * @table: the sysctl table * @write: %TRUE if this is a write to the sysctl file - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -2460,10 +2458,10 @@ static int do_proc_dointvec(struct ctl_table *table, int write, struct file *fil * * Returns 0 on success. */ -int proc_dointvec(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_dointvec(table,write,filp,buffer,lenp,ppos, + return do_proc_dointvec(table,write,buffer,lenp,ppos, NULL,NULL); } @@ -2471,7 +2469,7 @@ int proc_dointvec(struct ctl_table *table, int write, struct file *filp, * Taint values can only be increased * This means we can safely use a temporary. */ -static int proc_taint(struct ctl_table *table, int write, struct file *filp, +static int proc_taint(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; @@ -2483,7 +2481,7 @@ static int proc_taint(struct ctl_table *table, int write, struct file *filp, t = *table; t.data = &tmptaint; - err = proc_doulongvec_minmax(&t, write, filp, buffer, lenp, ppos); + err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos); if (err < 0) return err; @@ -2535,7 +2533,6 @@ static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp, * proc_dointvec_minmax - read a vector of integers with min/max values * @table: the sysctl table * @write: %TRUE if this is a write to the sysctl file - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -2548,19 +2545,18 @@ static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp, * * Returns 0 on success. */ -int proc_dointvec_minmax(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec_minmax(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct do_proc_dointvec_minmax_conv_param param = { .min = (int *) table->extra1, .max = (int *) table->extra2, }; - return do_proc_dointvec(table, write, filp, buffer, lenp, ppos, + return do_proc_dointvec(table, write, buffer, lenp, ppos, do_proc_dointvec_minmax_conv, ¶m); } static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos, unsigned long convmul, @@ -2665,21 +2661,19 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int } static int do_proc_doulongvec_minmax(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos, unsigned long convmul, unsigned long convdiv) { return __do_proc_doulongvec_minmax(table->data, table, write, - filp, buffer, lenp, ppos, convmul, convdiv); + buffer, lenp, ppos, convmul, convdiv); } /** * proc_doulongvec_minmax - read a vector of long integers with min/max values * @table: the sysctl table * @write: %TRUE if this is a write to the sysctl file - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -2692,17 +2686,16 @@ static int do_proc_doulongvec_minmax(struct ctl_table *table, int write, * * Returns 0 on success. */ -int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp, +int proc_doulongvec_minmax(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos, 1l, 1l); + return do_proc_doulongvec_minmax(table, write, buffer, lenp, ppos, 1l, 1l); } /** * proc_doulongvec_ms_jiffies_minmax - read a vector of millisecond values with min/max values * @table: the sysctl table * @write: %TRUE if this is a write to the sysctl file - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -2717,11 +2710,10 @@ int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp * Returns 0 on success. */ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_doulongvec_minmax(table, write, filp, buffer, + return do_proc_doulongvec_minmax(table, write, buffer, lenp, ppos, HZ, 1000l); } @@ -2797,7 +2789,6 @@ static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp, * proc_dointvec_jiffies - read a vector of integers as seconds * @table: the sysctl table * @write: %TRUE if this is a write to the sysctl file - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -2809,10 +2800,10 @@ static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp, * * Returns 0 on success. */ -int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec_jiffies(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_dointvec(table,write,filp,buffer,lenp,ppos, + return do_proc_dointvec(table,write,buffer,lenp,ppos, do_proc_dointvec_jiffies_conv,NULL); } @@ -2820,7 +2811,6 @@ int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp, * proc_dointvec_userhz_jiffies - read a vector of integers as 1/USER_HZ seconds * @table: the sysctl table * @write: %TRUE if this is a write to the sysctl file - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: pointer to the file position @@ -2832,10 +2822,10 @@ int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp, * * Returns 0 on success. */ -int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_dointvec(table,write,filp,buffer,lenp,ppos, + return do_proc_dointvec(table,write,buffer,lenp,ppos, do_proc_dointvec_userhz_jiffies_conv,NULL); } @@ -2843,7 +2833,6 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file * proc_dointvec_ms_jiffies - read a vector of integers as 1 milliseconds * @table: the sysctl table * @write: %TRUE if this is a write to the sysctl file - * @filp: the file structure * @buffer: the user buffer * @lenp: the size of the user buffer * @ppos: file position @@ -2856,14 +2845,14 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file * * Returns 0 on success. */ -int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_dointvec(table, write, filp, buffer, lenp, ppos, + return do_proc_dointvec(table, write, buffer, lenp, ppos, do_proc_dointvec_ms_jiffies_conv, NULL); } -static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp, +static int proc_do_cad_pid(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct pid *new_pid; @@ -2872,7 +2861,7 @@ static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp tmp = pid_vnr(cad_pid); - r = __do_proc_dointvec(&tmp, table, write, filp, buffer, + r = __do_proc_dointvec(&tmp, table, write, buffer, lenp, ppos, NULL, NULL); if (r || !write) return r; @@ -2887,50 +2876,49 @@ static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp #else /* CONFIG_PROC_FS */ -int proc_dostring(struct ctl_table *table, int write, struct file *filp, +int proc_dostring(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec_minmax(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec_minmax(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec_jiffies(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, struct file *filp, +int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } -int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp, +int proc_doulongvec_minmax(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 23df7771c937..a142579765bf 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3015,7 +3015,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops) int ftrace_enable_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) { int ret; @@ -3025,7 +3025,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, mutex_lock(&ftrace_lock); - ret = proc_dointvec(table, write, file, buffer, lenp, ppos); + ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled)) goto out; diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 0f6facb050a1..8504ac71e4e8 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -296,14 +296,14 @@ static const struct file_operations stack_trace_fops = { 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) { int ret; mutex_lock(&stack_sysctl_mutex); - ret = proc_dointvec(table, write, file, buffer, lenp, ppos); + ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret || !write || (last_stack_tracer_enabled == !!stack_tracer_enabled)) diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c index 92359cc747a7..69eae358a726 100644 --- a/kernel/utsname_sysctl.c +++ b/kernel/utsname_sysctl.c @@ -42,14 +42,14 @@ static void put_uts(ctl_table *table, int write, void *which) * Special case of dostring for the UTS structure. This has locks * to observe. Should this be in kernel/sys.c ???? */ -static int proc_do_uts_string(ctl_table *table, int write, struct file *filp, +static int proc_do_uts_string(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table uts_table; int r; memcpy(&uts_table, table, sizeof(uts_table)); uts_table.data = get_uts(table, write); - r = proc_dostring(&uts_table,write,filp,buffer,lenp, ppos); + r = proc_dostring(&uts_table,write,buffer,lenp, ppos); put_uts(table, write, uts_table.data); return r; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 815dbd4a6dcb..6f048fcc749c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1537,7 +1537,7 @@ static unsigned int cpuset_mems_nr(unsigned int *array) #ifdef CONFIG_SYSCTL int hugetlb_sysctl_handler(struct ctl_table *table, int write, - struct file *file, void __user *buffer, + void __user *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; @@ -1548,7 +1548,7 @@ int hugetlb_sysctl_handler(struct ctl_table *table, int write, table->data = &tmp; table->maxlen = sizeof(unsigned long); - proc_doulongvec_minmax(table, write, file, buffer, length, ppos); + proc_doulongvec_minmax(table, write, buffer, length, ppos); if (write) h->max_huge_pages = set_max_huge_pages(h, tmp); @@ -1557,10 +1557,10 @@ int hugetlb_sysctl_handler(struct ctl_table *table, int write, } int hugetlb_treat_movable_handler(struct ctl_table *table, int write, - struct file *file, void __user *buffer, + void __user *buffer, size_t *length, loff_t *ppos) { - proc_dointvec(table, write, file, buffer, length, ppos); + proc_dointvec(table, write, buffer, length, ppos); if (hugepages_treat_as_movable) htlb_alloc_mask = GFP_HIGHUSER_MOVABLE; else @@ -1569,7 +1569,7 @@ int hugetlb_treat_movable_handler(struct ctl_table *table, int write, } int hugetlb_overcommit_handler(struct ctl_table *table, int write, - struct file *file, void __user *buffer, + void __user *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; @@ -1580,7 +1580,7 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, table->data = &tmp; table->maxlen = sizeof(unsigned long); - proc_doulongvec_minmax(table, write, file, buffer, length, ppos); + proc_doulongvec_minmax(table, write, buffer, length, ppos); if (write) { spin_lock(&hugetlb_lock); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 5f378dd58802..be197f71b096 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -155,37 +155,37 @@ static void update_completion_period(void) } 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) { int ret; - ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) dirty_background_bytes = 0; return ret; } 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) { int ret; - ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos); + ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) dirty_background_ratio = 0; return ret; } 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) { int old_ratio = vm_dirty_ratio; int ret; - ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_ratio != old_ratio) { update_completion_period(); vm_dirty_bytes = 0; @@ -195,13 +195,13 @@ int dirty_ratio_handler(struct ctl_table *table, int write, 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) { unsigned long old_bytes = vm_dirty_bytes; int ret; - ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos); + ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_bytes != old_bytes) { update_completion_period(); vm_dirty_ratio = 0; @@ -686,9 +686,9 @@ static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0); * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ int dirty_writeback_centisecs_handler(ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, loff_t *ppos) + void __user *buffer, size_t *length, loff_t *ppos) { - proc_dointvec(table, write, file, buffer, length, ppos); + proc_dointvec(table, write, buffer, length, ppos); return 0; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5717f27a0704..88248b3c20bb 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2373,7 +2373,7 @@ early_param("numa_zonelist_order", setup_numa_zonelist_order); * sysctl handler for numa_zonelist_order */ int numa_zonelist_order_handler(ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, + void __user *buffer, size_t *length, loff_t *ppos) { char saved_string[NUMA_ZONELIST_ORDER_LEN]; @@ -2382,7 +2382,7 @@ int numa_zonelist_order_handler(ctl_table *table, int write, if (write) strncpy(saved_string, (char*)table->data, NUMA_ZONELIST_ORDER_LEN); - ret = proc_dostring(table, write, file, buffer, length, ppos); + ret = proc_dostring(table, write, buffer, length, ppos); if (ret) return ret; if (write) { @@ -4706,9 +4706,9 @@ module_init(init_per_zone_wmark_min) * changes. */ int min_free_kbytes_sysctl_handler(ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, loff_t *ppos) + void __user *buffer, size_t *length, loff_t *ppos) { - proc_dointvec(table, write, file, buffer, length, ppos); + proc_dointvec(table, write, buffer, length, ppos); if (write) setup_per_zone_wmarks(); return 0; @@ -4716,12 +4716,12 @@ int min_free_kbytes_sysctl_handler(ctl_table *table, int write, #ifdef CONFIG_NUMA int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, loff_t *ppos) + void __user *buffer, size_t *length, loff_t *ppos) { struct zone *zone; int rc; - rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos); + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); if (rc) return rc; @@ -4732,12 +4732,12 @@ int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write, } int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, loff_t *ppos) + void __user *buffer, size_t *length, loff_t *ppos) { struct zone *zone; int rc; - rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos); + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); if (rc) return rc; @@ -4758,9 +4758,9 @@ int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write, * if in function of the boot time zone sizes. */ int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, loff_t *ppos) + void __user *buffer, size_t *length, loff_t *ppos) { - proc_dointvec_minmax(table, write, file, buffer, length, ppos); + proc_dointvec_minmax(table, write, buffer, length, ppos); setup_per_zone_lowmem_reserve(); return 0; } @@ -4772,13 +4772,13 @@ int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write, */ int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, loff_t *ppos) + void __user *buffer, size_t *length, loff_t *ppos) { struct zone *zone; unsigned int cpu; int ret; - ret = proc_dointvec_minmax(table, write, file, buffer, length, ppos); + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); if (!write || (ret == -EINVAL)) return ret; for_each_populated_zone(zone) { diff --git a/mm/vmscan.c b/mm/vmscan.c index 2423782214ab..f444b7409085 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2844,10 +2844,10 @@ static void scan_all_zones_unevictable_pages(void) unsigned long scan_unevictable_pages; int scan_unevictable_handler(struct ctl_table *table, int write, - struct file *file, void __user *buffer, + void __user *buffer, size_t *length, loff_t *ppos) { - proc_doulongvec_minmax(table, write, file, buffer, length, ppos); + proc_doulongvec_minmax(table, write, buffer, length, ppos); if (write && *(unsigned long *)table->data) scan_all_zones_unevictable_pages(); diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 907a82e9023d..a16a2342f6bf 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -965,12 +965,12 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = { #ifdef CONFIG_SYSCTL static -int brnf_sysctl_call_tables(ctl_table * ctl, int write, struct file *filp, +int brnf_sysctl_call_tables(ctl_table * ctl, int write, void __user * buffer, size_t * lenp, loff_t * ppos) { int ret; - ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write && *(int *)(ctl->data)) *(int *)(ctl->data) = 1; diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 1c6a5bb6f0c8..6e1f085db06a 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -164,7 +164,7 @@ static int max_t3[] = { 8191 }; /* Must fit in 16 bits when multiplied by BCT3MU static int min_priority[1]; static int max_priority[] = { 127 }; /* From DECnet spec */ -static int dn_forwarding_proc(ctl_table *, int, struct file *, +static int dn_forwarding_proc(ctl_table *, int, void __user *, size_t *, loff_t *); static int dn_forwarding_sysctl(ctl_table *table, void __user *oldval, size_t __user *oldlenp, @@ -274,7 +274,6 @@ static void dn_dev_sysctl_unregister(struct dn_dev_parms *parms) } static int dn_forwarding_proc(ctl_table *table, int write, - struct file *filep, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -290,7 +289,7 @@ static int dn_forwarding_proc(ctl_table *table, int write, dn_db = dev->dn_ptr; old = dn_db->parms.forwarding; - err = proc_dointvec(table, write, filep, buffer, lenp, ppos); + err = proc_dointvec(table, write, buffer, lenp, ppos); if ((err >= 0) && write) { if (dn_db->parms.forwarding < 0) diff --git a/net/decnet/sysctl_net_decnet.c b/net/decnet/sysctl_net_decnet.c index 5bcd592ae6dd..26b0ab1e9f56 100644 --- a/net/decnet/sysctl_net_decnet.c +++ b/net/decnet/sysctl_net_decnet.c @@ -165,7 +165,6 @@ static int dn_node_address_strategy(ctl_table *table, } static int dn_node_address_handler(ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -276,7 +275,6 @@ static int dn_def_dev_strategy(ctl_table *table, static int dn_def_dev_handler(ctl_table *table, int write, - struct file * filp, void __user *buffer, size_t *lenp, loff_t *ppos) { diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 07336c6201f0..e92f1fd28aa5 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1270,10 +1270,10 @@ static void inet_forward_change(struct net *net) } static int devinet_conf_proc(ctl_table *ctl, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write) { struct ipv4_devconf *cnf = ctl->extra1; @@ -1342,12 +1342,12 @@ static int devinet_conf_sysctl(ctl_table *table, } static int devinet_sysctl_forward(ctl_table *ctl, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; - int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write && *valp != val) { struct net *net = ctl->extra2; @@ -1372,12 +1372,12 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write, } int ipv4_doint_and_flush(ctl_table *ctl, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; - int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); struct net *net = ctl->extra2; if (write && *valp != val) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index df9347314538..bb4199252026 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3036,7 +3036,7 @@ void ip_rt_multicast_event(struct in_device *in_dev) #ifdef CONFIG_SYSCTL static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos) { if (write) { @@ -3046,7 +3046,7 @@ static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write, memcpy(&ctl, __ctl, sizeof(ctl)); ctl.data = &flush_delay; - proc_dointvec(&ctl, write, filp, buffer, lenp, ppos); + proc_dointvec(&ctl, write, buffer, lenp, ppos); net = (struct net *)__ctl->extra1; rt_cache_flush(net, flush_delay); @@ -3106,12 +3106,11 @@ static void rt_secret_reschedule(int old) } static int ipv4_sysctl_rt_secret_interval(ctl_table *ctl, int write, - struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { int old = ip_rt_secret_interval; - int ret = proc_dointvec_jiffies(ctl, write, filp, buffer, lenp, ppos); + int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); rt_secret_reschedule(old); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 4710d219f06a..2dcf04d9b005 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -36,7 +36,7 @@ static void set_local_port_range(int range[2]) } /* Validate changes from /proc interface. */ -static int ipv4_local_port_range(ctl_table *table, int write, struct file *filp, +static int ipv4_local_port_range(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -51,7 +51,7 @@ static int ipv4_local_port_range(ctl_table *table, int write, struct file *filp, }; inet_get_local_port_range(range, range + 1); - ret = proc_dointvec_minmax(&tmp, write, filp, buffer, lenp, ppos); + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) { if (range[1] < range[0]) @@ -91,7 +91,7 @@ static int ipv4_sysctl_local_port_range(ctl_table *table, } -static int proc_tcp_congestion_control(ctl_table *ctl, int write, struct file * filp, +static int proc_tcp_congestion_control(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char val[TCP_CA_NAME_MAX]; @@ -103,7 +103,7 @@ static int proc_tcp_congestion_control(ctl_table *ctl, int write, struct file * tcp_get_default_congestion_control(val); - ret = proc_dostring(&tbl, write, filp, buffer, lenp, ppos); + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) ret = tcp_set_default_congestion_control(val); return ret; @@ -129,7 +129,7 @@ static int sysctl_tcp_congestion_control(ctl_table *table, } static int proc_tcp_available_congestion_control(ctl_table *ctl, - int write, struct file * filp, + int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -140,13 +140,13 @@ static int proc_tcp_available_congestion_control(ctl_table *ctl, if (!tbl.data) return -ENOMEM; tcp_get_available_congestion_control(tbl.data, TCP_CA_BUF_MAX); - ret = proc_dostring(&tbl, write, filp, buffer, lenp, ppos); + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); kfree(tbl.data); return ret; } static int proc_allowed_congestion_control(ctl_table *ctl, - int write, struct file * filp, + int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -158,7 +158,7 @@ static int proc_allowed_congestion_control(ctl_table *ctl, return -ENOMEM; tcp_get_allowed_congestion_control(tbl.data, tbl.maxlen); - ret = proc_dostring(&tbl, write, filp, buffer, lenp, ppos); + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) ret = tcp_set_allowed_congestion_control(tbl.data); kfree(tbl.data); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 55f486d89c88..1fd0a3d775d2 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3986,14 +3986,14 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) #ifdef CONFIG_SYSCTL static -int addrconf_sysctl_forward(ctl_table *ctl, int write, struct file * filp, +int addrconf_sysctl_forward(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; int ret; - ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write) ret = addrconf_fixup_forwarding(ctl, valp, val); @@ -4090,14 +4090,14 @@ static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int old) } static -int addrconf_sysctl_disable(ctl_table *ctl, int write, struct file * filp, +int addrconf_sysctl_disable(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; int ret; - ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write) ret = addrconf_disable_ipv6(ctl, valp, val); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 7015478797f6..498b9b0b0fad 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1735,7 +1735,7 @@ static void ndisc_warn_deprecated_sysctl(struct ctl_table *ctl, } } -int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, struct file * filp, void __user *buffer, size_t *lenp, loff_t *ppos) +int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct net_device *dev = ctl->extra1; struct inet6_dev *idev; @@ -1746,16 +1746,16 @@ int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, struct file * f ndisc_warn_deprecated_sysctl(ctl, "syscall", dev ? dev->name : "default"); if (strcmp(ctl->procname, "retrans_time") == 0) - ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); else if (strcmp(ctl->procname, "base_reachable_time") == 0) ret = proc_dointvec_jiffies(ctl, write, - filp, buffer, lenp, ppos); + buffer, lenp, ppos); else if ((strcmp(ctl->procname, "retrans_time_ms") == 0) || (strcmp(ctl->procname, "base_reachable_time_ms") == 0)) ret = proc_dointvec_ms_jiffies(ctl, write, - filp, buffer, lenp, ppos); + buffer, lenp, ppos); else ret = -1; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 77aecbe8ff6c..d6fe7646a8ff 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2524,13 +2524,13 @@ static const struct file_operations rt6_stats_seq_fops = { #ifdef CONFIG_SYSCTL static -int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, struct file * filp, +int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; int delay = net->ipv6.sysctl.flush_delay; if (write) { - proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + proc_dointvec(ctl, write, buffer, lenp, ppos); fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net); return 0; } else diff --git a/net/irda/irsysctl.c b/net/irda/irsysctl.c index 57f8817c3979..5c86567e5a78 100644 --- a/net/irda/irsysctl.c +++ b/net/irda/irsysctl.c @@ -73,12 +73,12 @@ static int min_lap_keepalive_time = 100; /* 100us */ /* For other sysctl, I've no idea of the range. Maybe Dag could help * us on that - Jean II */ -static int do_devname(ctl_table *table, int write, struct file *filp, +static int do_devname(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; - ret = proc_dostring(table, write, filp, buffer, lenp, ppos); + ret = proc_dostring(table, write, buffer, lenp, ppos); if (ret == 0 && write) { struct ias_value *val; @@ -90,12 +90,12 @@ static int do_devname(ctl_table *table, int write, struct file *filp, } -static int do_discovery(ctl_table *table, int write, struct file *filp, +static int do_discovery(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; - ret = proc_dointvec(table, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret) return ret; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index fba2892b99e1..446e9bd4b4bc 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1496,14 +1496,14 @@ static int ip_vs_zero_all(void) static int -proc_do_defense_mode(ctl_table *table, int write, struct file * filp, +proc_do_defense_mode(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = table->data; int val = *valp; int rc; - rc = proc_dointvec(table, write, filp, buffer, lenp, ppos); + rc = proc_dointvec(table, write, buffer, lenp, ppos); if (write && (*valp != val)) { if ((*valp < 0) || (*valp > 3)) { /* Restore the correct value */ @@ -1517,7 +1517,7 @@ proc_do_defense_mode(ctl_table *table, int write, struct file * filp, static int -proc_do_sync_threshold(ctl_table *table, int write, struct file *filp, +proc_do_sync_threshold(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = table->data; @@ -1527,7 +1527,7 @@ proc_do_sync_threshold(ctl_table *table, int write, struct file *filp, /* backup the value first */ memcpy(val, valp, sizeof(val)); - rc = proc_dointvec(table, write, filp, buffer, lenp, ppos); + rc = proc_dointvec(table, write, buffer, lenp, ppos); if (write && (valp[0] < 0 || valp[1] < 0 || valp[0] >= valp[1])) { /* Restore the correct value */ memcpy(valp, val, sizeof(val)); diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 4e620305f28c..c93494fef8ef 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -226,7 +226,7 @@ static char nf_log_sysctl_fnames[NFPROTO_NUMPROTO-NFPROTO_UNSPEC][3]; static struct ctl_table nf_log_sysctl_table[NFPROTO_NUMPROTO+1]; static struct ctl_table_header *nf_log_dir_header; -static int nf_log_proc_dostring(ctl_table *table, int write, struct file *filp, +static int nf_log_proc_dostring(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { const struct nf_logger *logger; @@ -260,7 +260,7 @@ static int nf_log_proc_dostring(ctl_table *table, int write, struct file *filp, table->data = "NONE"; else table->data = logger->name; - r = proc_dostring(table, write, filp, buffer, lenp, ppos); + r = proc_dostring(table, write, buffer, lenp, ppos); mutex_unlock(&nf_log_mutex); } diff --git a/net/phonet/sysctl.c b/net/phonet/sysctl.c index 7b5749ee2765..2220f3322326 100644 --- a/net/phonet/sysctl.c +++ b/net/phonet/sysctl.c @@ -56,7 +56,7 @@ void phonet_get_local_port_range(int *min, int *max) } while (read_seqretry(&local_port_range_lock, seq)); } -static int proc_local_port_range(ctl_table *table, int write, struct file *filp, +static int proc_local_port_range(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -70,7 +70,7 @@ static int proc_local_port_range(ctl_table *table, int write, struct file *filp, .extra2 = &local_port_range_max, }; - ret = proc_dointvec_minmax(&tmp, write, filp, buffer, lenp, ppos); + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) { if (range[1] < range[0]) diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c index 5231f7aaac0e..42f9748ae093 100644 --- a/net/sunrpc/sysctl.c +++ b/net/sunrpc/sysctl.c @@ -56,7 +56,7 @@ rpc_unregister_sysctl(void) } } -static int proc_do_xprt(ctl_table *table, int write, struct file *file, +static int proc_do_xprt(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char tmpbuf[256]; @@ -71,7 +71,7 @@ static int proc_do_xprt(ctl_table *table, int write, struct file *file, } static int -proc_dodebug(ctl_table *table, int write, struct file *file, +proc_dodebug(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { char tmpbuf[20], c, *s; diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index 87101177825b..35fb68b9c8ec 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -80,7 +80,7 @@ struct kmem_cache *svc_rdma_ctxt_cachep; * current value. */ static int read_reset_stat(ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos) { atomic_t *stat = (atomic_t *)table->data; diff --git a/security/min_addr.c b/security/min_addr.c index 14cc7b3b8d03..c844eed7915d 100644 --- a/security/min_addr.c +++ b/security/min_addr.c @@ -28,12 +28,12 @@ static void update_mmap_min_addr(void) * sysctl handler which just sets dac_mmap_min_addr = the new value and then * calls update_mmap_min_addr() so non MAP_FIXED hints get rounded properly */ -int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp, +int mmap_min_addr_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; - ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos); + ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); update_mmap_min_addr(); -- 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 ++--- kernel/fork.c | 11 +++++++++-- 2 files changed, 11 insertions(+), 5 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 diff --git a/kernel/fork.c b/kernel/fork.c index b51fd2ccb2f1..e49f181ba1ca 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -434,6 +434,14 @@ __setup("coredump_filter=", coredump_filter_setup); #include +static void mm_init_aio(struct mm_struct *mm) +{ +#ifdef CONFIG_AIO + spin_lock_init(&mm->ioctx_lock); + INIT_HLIST_HEAD(&mm->ioctx_list); +#endif +} + static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) { atomic_set(&mm->mm_users, 1); @@ -447,10 +455,9 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) set_mm_counter(mm, file_rss, 0); set_mm_counter(mm, anon_rss, 0); spin_lock_init(&mm->page_table_lock); - spin_lock_init(&mm->ioctx_lock); - INIT_HLIST_HEAD(&mm->ioctx_list); mm->free_area_cache = TASK_UNMAPPED_BASE; mm->cached_hole_size = ~0UL; + mm_init_aio(mm); mm_init_owner(mm, p); if (likely(!mm_alloc_pgd(mm))) { -- 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 --- fs/exec.c | 10 ++++++---- include/linux/mm_types.h | 2 ++ include/linux/sched.h | 1 - kernel/exit.c | 2 -- kernel/fork.c | 13 +++++++------ 5 files changed, 15 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/fs/exec.c b/fs/exec.c index 6dc92c39dd94..d49be6bc1793 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1397,10 +1397,12 @@ out_ret: void set_binfmt(struct linux_binfmt *new) { - if (current->binfmt) - module_put(current->binfmt->module); + struct mm_struct *mm = current->mm; + + if (mm->binfmt) + module_put(mm->binfmt->module); - current->binfmt = new; + mm->binfmt = new; if (new) __module_get(new->module); } @@ -1770,7 +1772,7 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs) audit_core_dumps(signr); - binfmt = current->binfmt; + binfmt = mm->binfmt; if (!binfmt || !binfmt->core_dump) goto fail; 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 */ diff --git a/kernel/exit.c b/kernel/exit.c index 6c75ff83a8fe..5859f598c951 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -976,8 +976,6 @@ NORET_TYPE void do_exit(long code) disassociate_ctty(1); module_put(task_thread_info(tsk)->exec_domain->module); - if (tsk->binfmt) - module_put(tsk->binfmt->module); proc_exit_connector(tsk); diff --git a/kernel/fork.c b/kernel/fork.c index e49f181ba1ca..266c6af6ef1b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -518,6 +518,8 @@ void mmput(struct mm_struct *mm) spin_unlock(&mmlist_lock); } put_swap_token(mm); + if (mm->binfmt) + module_put(mm->binfmt->module); mmdrop(mm); } } @@ -643,9 +645,14 @@ struct mm_struct *dup_mm(struct task_struct *tsk) mm->hiwater_rss = get_mm_rss(mm); mm->hiwater_vm = mm->total_vm; + if (mm->binfmt && !try_module_get(mm->binfmt->module)) + goto free_pt; + return mm; free_pt: + /* don't put binfmt in mmput, we haven't got module yet */ + mm->binfmt = NULL; mmput(mm); fail_nomem: @@ -1037,9 +1044,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (!try_module_get(task_thread_info(p)->exec_domain->module)) goto bad_fork_cleanup_count; - if (p->binfmt && !try_module_get(p->binfmt->module)) - goto bad_fork_cleanup_put_domain; - p->did_exec = 0; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ copy_flags(clone_flags, p); @@ -1327,9 +1331,6 @@ bad_fork_cleanup_cgroup: #endif cgroup_exit(p, cgroup_callbacks_done); delayacct_tsk_free(p); - if (p->binfmt) - module_put(p->binfmt->module); -bad_fork_cleanup_put_domain: module_put(task_thread_info(p)->exec_domain->module); bad_fork_cleanup_count: atomic_dec(&p->cred->user->processes); -- 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 ++++-- kernel/module.c | 91 +++++++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 94 insertions(+), 7 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 */ diff --git a/kernel/module.c b/kernel/module.c index e6bc4b28aa62..97f4d5e15535 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1862,13 +1862,68 @@ static char elf_type(const Elf_Sym *sym, return '?'; } +static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs, + unsigned int shnum) +{ + const Elf_Shdr *sec; + + if (src->st_shndx == SHN_UNDEF + || src->st_shndx >= shnum + || !src->st_name) + return false; + + sec = sechdrs + src->st_shndx; + if (!(sec->sh_flags & SHF_ALLOC) +#ifndef CONFIG_KALLSYMS_ALL + || !(sec->sh_flags & SHF_EXECINSTR) +#endif + || (sec->sh_entsize & INIT_OFFSET_MASK)) + return false; + + return true; +} + +static unsigned long layout_symtab(struct module *mod, + Elf_Shdr *sechdrs, + unsigned int symindex, + const Elf_Ehdr *hdr, + const char *secstrings) +{ + unsigned long symoffs; + Elf_Shdr *symsect = sechdrs + symindex; + const Elf_Sym *src; + unsigned int i, nsrc, ndst; + + /* Put symbol section at end of init part of module. */ + symsect->sh_flags |= SHF_ALLOC; + symsect->sh_entsize = get_offset(mod, &mod->init_size, symsect, + symindex) | INIT_OFFSET_MASK; + DEBUGP("\t%s\n", secstrings + symsect->sh_name); + + src = (void *)hdr + symsect->sh_offset; + nsrc = symsect->sh_size / sizeof(*src); + for (ndst = i = 1; i < nsrc; ++i, ++src) + if (is_core_symbol(src, sechdrs, hdr->e_shnum)) + ++ndst; + + /* Append room for core symbols at end of core part. */ + symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1); + mod->core_size = symoffs + ndst * sizeof(Elf_Sym); + + return symoffs; +} + static void add_kallsyms(struct module *mod, Elf_Shdr *sechdrs, + unsigned int shnum, unsigned int symindex, unsigned int strindex, + unsigned long symoffs, const char *secstrings) { - unsigned int i; + unsigned int i, ndst; + const Elf_Sym *src; + Elf_Sym *dst; mod->symtab = (void *)sechdrs[symindex].sh_addr; mod->num_symtab = sechdrs[symindex].sh_size / sizeof(Elf_Sym); @@ -1878,12 +1933,32 @@ static void add_kallsyms(struct module *mod, for (i = 0; i < mod->num_symtab; i++) mod->symtab[i].st_info = elf_type(&mod->symtab[i], sechdrs, secstrings, mod); + + mod->core_symtab = dst = mod->module_core + symoffs; + src = mod->symtab; + *dst = *src; + for (ndst = i = 1; i < mod->num_symtab; ++i, ++src) { + if (!is_core_symbol(src, sechdrs, shnum)) + continue; + dst[ndst] = *src; + ++ndst; + } + mod->core_num_syms = ndst; } #else +static inline unsigned long layout_symtab(struct module *mod, + Elf_Shdr *sechdrs, + unsigned int symindex, + const Elf_Hdr *hdr, + const char *secstrings) +{ +} static inline void add_kallsyms(struct module *mod, Elf_Shdr *sechdrs, + unsigned int shnum, unsigned int symindex, unsigned int strindex, + unsigned long symoffs, const char *secstrings) { } @@ -1959,6 +2034,9 @@ static noinline struct module *load_module(void __user *umod, struct module *mod; long err = 0; void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */ +#ifdef CONFIG_KALLSYMS + unsigned long symoffs; +#endif mm_segment_t old_fs; DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n", @@ -2041,8 +2119,7 @@ static noinline struct module *load_module(void __user *umod, sechdrs[infoindex].sh_flags &= ~(unsigned long)SHF_ALLOC; sechdrs[versindex].sh_flags &= ~(unsigned long)SHF_ALLOC; #ifdef CONFIG_KALLSYMS - /* Keep symbol and string tables for decoding later. */ - sechdrs[symindex].sh_flags |= SHF_ALLOC; + /* Keep string table for decoding later. */ sechdrs[strindex].sh_flags |= SHF_ALLOC; #endif @@ -2109,6 +2186,7 @@ static noinline struct module *load_module(void __user *umod, this is done generically; there doesn't appear to be any special cases for the architectures. */ layout_sections(mod, hdr, sechdrs, secstrings); + symoffs = layout_symtab(mod, sechdrs, symindex, hdr, secstrings); /* Do the allocs. */ ptr = module_alloc_update_bounds(mod->core_size); @@ -2313,7 +2391,8 @@ static noinline struct module *load_module(void __user *umod, percpu_modcopy(mod->percpu, (void *)sechdrs[pcpuindex].sh_addr, sechdrs[pcpuindex].sh_size); - add_kallsyms(mod, sechdrs, symindex, strindex, secstrings); + add_kallsyms(mod, sechdrs, hdr->e_shnum, symindex, strindex, + symoffs, secstrings); if (!mod->taints) { struct _ddebug *debug; @@ -2491,6 +2570,10 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, /* Drop initial reference. */ module_put(mod); trim_init_extable(mod); +#ifdef CONFIG_KALLSYMS + mod->num_symtab = mod->core_num_syms; + mod->symtab = mod->core_symtab; +#endif module_free(mod, mod->module_init); mod->module_init = NULL; mod->init_size = 0; -- 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 +- kernel/module.c | 68 +++++++++++++++++++++++++++++++++++++++++--------- 2 files changed, 57 insertions(+), 13 deletions(-) (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; diff --git a/kernel/module.c b/kernel/module.c index 97f4d5e15535..39827c3d9484 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1886,12 +1886,17 @@ static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs, static unsigned long layout_symtab(struct module *mod, Elf_Shdr *sechdrs, unsigned int symindex, + unsigned int strindex, const Elf_Ehdr *hdr, - const char *secstrings) + const char *secstrings, + unsigned long *pstroffs, + unsigned long *strmap) { unsigned long symoffs; Elf_Shdr *symsect = sechdrs + symindex; + Elf_Shdr *strsect = sechdrs + strindex; const Elf_Sym *src; + const char *strtab; unsigned int i, nsrc, ndst; /* Put symbol section at end of init part of module. */ @@ -1902,14 +1907,31 @@ static unsigned long layout_symtab(struct module *mod, src = (void *)hdr + symsect->sh_offset; nsrc = symsect->sh_size / sizeof(*src); + strtab = (void *)hdr + strsect->sh_offset; for (ndst = i = 1; i < nsrc; ++i, ++src) - if (is_core_symbol(src, sechdrs, hdr->e_shnum)) + if (is_core_symbol(src, sechdrs, hdr->e_shnum)) { + unsigned int j = src->st_name; + + while(!__test_and_set_bit(j, strmap) && strtab[j]) + ++j; ++ndst; + } /* Append room for core symbols at end of core part. */ symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1); mod->core_size = symoffs + ndst * sizeof(Elf_Sym); + /* Put string table section at end of init part of module. */ + strsect->sh_flags |= SHF_ALLOC; + strsect->sh_entsize = get_offset(mod, &mod->init_size, strsect, + strindex) | INIT_OFFSET_MASK; + DEBUGP("\t%s\n", secstrings + strsect->sh_name); + + /* Append room for core symbols' strings at end of core part. */ + *pstroffs = mod->core_size; + __set_bit(0, strmap); + mod->core_size += bitmap_weight(strmap, strsect->sh_size); + return symoffs; } @@ -1919,11 +1941,14 @@ static void add_kallsyms(struct module *mod, unsigned int symindex, unsigned int strindex, unsigned long symoffs, - const char *secstrings) + unsigned long stroffs, + const char *secstrings, + unsigned long *strmap) { unsigned int i, ndst; const Elf_Sym *src; Elf_Sym *dst; + char *s; mod->symtab = (void *)sechdrs[symindex].sh_addr; mod->num_symtab = sechdrs[symindex].sh_size / sizeof(Elf_Sym); @@ -1941,16 +1966,25 @@ static void add_kallsyms(struct module *mod, if (!is_core_symbol(src, sechdrs, shnum)) continue; dst[ndst] = *src; + dst[ndst].st_name = bitmap_weight(strmap, dst[ndst].st_name); ++ndst; } mod->core_num_syms = ndst; + + mod->core_strtab = s = mod->module_core + stroffs; + for (*s = 0, i = 1; i < sechdrs[strindex].sh_size; ++i) + if (test_bit(i, strmap)) + *++s = mod->strtab[i]; } #else static inline unsigned long layout_symtab(struct module *mod, Elf_Shdr *sechdrs, unsigned int symindex, + unsigned int strindex, const Elf_Hdr *hdr, - const char *secstrings) + const char *secstrings, + unsigned long *pstroffs, + unsigned long *strmap) { } static inline void add_kallsyms(struct module *mod, @@ -1959,7 +1993,9 @@ static inline void add_kallsyms(struct module *mod, unsigned int symindex, unsigned int strindex, unsigned long symoffs, - const char *secstrings) + unsigned long stroffs, + const char *secstrings, + const unsigned long *strmap) { } #endif /* CONFIG_KALLSYMS */ @@ -2035,7 +2071,7 @@ static noinline struct module *load_module(void __user *umod, long err = 0; void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */ #ifdef CONFIG_KALLSYMS - unsigned long symoffs; + unsigned long symoffs, stroffs, *strmap; #endif mm_segment_t old_fs; @@ -2118,10 +2154,6 @@ static noinline struct module *load_module(void __user *umod, /* Don't keep modinfo and version sections. */ sechdrs[infoindex].sh_flags &= ~(unsigned long)SHF_ALLOC; sechdrs[versindex].sh_flags &= ~(unsigned long)SHF_ALLOC; -#ifdef CONFIG_KALLSYMS - /* Keep string table for decoding later. */ - sechdrs[strindex].sh_flags |= SHF_ALLOC; -#endif /* Check module struct version now, before we try to use module. */ if (!check_modstruct_version(sechdrs, versindex, mod)) { @@ -2157,6 +2189,13 @@ static noinline struct module *load_module(void __user *umod, goto free_hdr; } + strmap = kzalloc(BITS_TO_LONGS(sechdrs[strindex].sh_size) + * sizeof(long), GFP_KERNEL); + if (!strmap) { + err = -ENOMEM; + goto free_mod; + } + if (find_module(mod->name)) { err = -EEXIST; goto free_mod; @@ -2186,7 +2225,8 @@ static noinline struct module *load_module(void __user *umod, this is done generically; there doesn't appear to be any special cases for the architectures. */ layout_sections(mod, hdr, sechdrs, secstrings); - symoffs = layout_symtab(mod, sechdrs, symindex, hdr, secstrings); + symoffs = layout_symtab(mod, sechdrs, symindex, strindex, hdr, + secstrings, &stroffs, strmap); /* Do the allocs. */ ptr = module_alloc_update_bounds(mod->core_size); @@ -2392,7 +2432,9 @@ static noinline struct module *load_module(void __user *umod, sechdrs[pcpuindex].sh_size); add_kallsyms(mod, sechdrs, hdr->e_shnum, symindex, strindex, - symoffs, secstrings); + symoffs, stroffs, secstrings, strmap); + kfree(strmap); + strmap = NULL; if (!mod->taints) { struct _ddebug *debug; @@ -2481,6 +2523,7 @@ static noinline struct module *load_module(void __user *umod, percpu_modfree(percpu); free_mod: kfree(args); + kfree(strmap); free_hdr: vfree(hdr); return ERR_PTR(err); @@ -2573,6 +2616,7 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, #ifdef CONFIG_KALLSYMS mod->num_symtab = mod->core_num_syms; mod->symtab = mod->core_symtab; + mod->strtab = mod->core_strtab; #endif module_free(mod, mod->module_init); mod->module_init = NULL; -- 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 18a1166de994685d770425086b2bcc1ba567f7ed Mon Sep 17 00:00:00 2001 From: Rémi Denis-Courmont Date: Wed, 23 Sep 2009 03:17:11 +0000 Subject: Phonet: error on broadcast sending (unimplemented) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If we ever implement this, then we can stop returning an error. Signed-off-by: Rémi Denis-Courmont Signed-off-by: David S. Miller --- include/linux/phonet.h | 1 + net/phonet/af_phonet.c | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phonet.h b/include/linux/phonet.h index 1ef5a0781831..e5126cff9b2a 100644 --- a/include/linux/phonet.h +++ b/include/linux/phonet.h @@ -38,6 +38,7 @@ #define PNPIPE_IFINDEX 2 #define PNADDR_ANY 0 +#define PNADDR_BROADCAST 0xFC #define PNPORT_RESOURCE_ROUTING 0 /* Values for PNPIPE_ENCAP option */ diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index a662e62a99cf..f60c0c2aacba 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -168,6 +168,12 @@ static int pn_send(struct sk_buff *skb, struct net_device *dev, goto drop; } + /* Broadcast sending is not implemented */ + if (pn_addr(dst) == PNADDR_BROADCAST) { + err = -EOPNOTSUPP; + goto drop; + } + skb_reset_transport_header(skb); WARN_ON(skb_headroom(skb) & 1); /* HW assumes word alignment */ skb_push(skb, sizeof(struct phonethdr)); -- cgit v1.2.3 From b8273570f802a7658827dcb077b0b517ba75a289 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 24 Sep 2009 15:44:05 -0700 Subject: genetlink: fix netns vs. netlink table locking (2) Similar to commit d136f1bd366fdb7e747ca7e0218171e7a00a98a5, there's a bug when unregistering a generic netlink family, which is caught by the might_sleep() added in that commit: BUG: sleeping function called from invalid context at net/netlink/af_netlink.c:183 in_atomic(): 1, irqs_disabled(): 0, pid: 1510, name: rmmod 2 locks held by rmmod/1510: #0: (genl_mutex){+.+.+.}, at: [] genl_unregister_family+0x2b/0x130 #1: (rcu_read_lock){.+.+..}, at: [] __genl_unregister_mc_group+0x1c/0x120 Pid: 1510, comm: rmmod Not tainted 2.6.31-wl #444 Call Trace: [] __might_sleep+0x119/0x150 [] netlink_table_grab+0x21/0x100 [] netlink_clear_multicast_users+0x23/0x60 [] __genl_unregister_mc_group+0x71/0x120 [] genl_unregister_family+0x56/0x130 [] nl80211_exit+0x15/0x20 [cfg80211] [] cfg80211_exit+0x1a/0x40 [cfg80211] Fix in the same way by grabbing the netlink table lock before doing rcu_read_lock(). Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 + net/netlink/af_netlink.c | 19 +++++++++++-------- net/netlink/genetlink.c | 4 +++- 3 files changed, 15 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 080f6ba9e73a..ab5d3126831f 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -187,6 +187,7 @@ extern struct sock *netlink_kernel_create(struct net *net, extern void netlink_kernel_release(struct sock *sk); extern int __netlink_change_ngroups(struct sock *sk, unsigned int groups); extern int netlink_change_ngroups(struct sock *sk, unsigned int groups); +extern void __netlink_clear_multicast_users(struct sock *sk, unsigned int group); extern void netlink_clear_multicast_users(struct sock *sk, unsigned int group); extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err); extern int netlink_has_listeners(struct sock *sk, unsigned int group); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 55180b99562a..a4bafbf15097 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1609,6 +1609,16 @@ int netlink_change_ngroups(struct sock *sk, unsigned int groups) return err; } +void __netlink_clear_multicast_users(struct sock *ksk, unsigned int group) +{ + struct sock *sk; + struct hlist_node *node; + struct netlink_table *tbl = &nl_table[ksk->sk_protocol]; + + sk_for_each_bound(sk, node, &tbl->mc_list) + netlink_update_socket_mc(nlk_sk(sk), group, 0); +} + /** * netlink_clear_multicast_users - kick off multicast listeners * @@ -1619,15 +1629,8 @@ int netlink_change_ngroups(struct sock *sk, unsigned int groups) */ void netlink_clear_multicast_users(struct sock *ksk, unsigned int group) { - struct sock *sk; - struct hlist_node *node; - struct netlink_table *tbl = &nl_table[ksk->sk_protocol]; - netlink_table_grab(); - - sk_for_each_bound(sk, node, &tbl->mc_list) - netlink_update_socket_mc(nlk_sk(sk), group, 0); - + __netlink_clear_multicast_users(ksk, group); netlink_table_ungrab(); } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 566941e03363..44ff3f3810fa 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -220,10 +220,12 @@ static void __genl_unregister_mc_group(struct genl_family *family, struct net *net; BUG_ON(grp->family != family); + netlink_table_grab(); rcu_read_lock(); for_each_net_rcu(net) - netlink_clear_multicast_users(net->genl_sock, grp->id); + __netlink_clear_multicast_users(net->genl_sock, grp->id); rcu_read_unlock(); + netlink_table_ungrab(); clear_bit(grp->id, mc_groups); list_del(&grp->list); -- 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 From a72bfd4dea053bb8e2233902c3f1893ef5485802 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 26 Sep 2009 00:07:46 +0200 Subject: writeback: pass in super_block to bdi_start_writeback() Sometimes we only want to write pages from a specific super_block, so allow that to be passed in. This fixes a problem with commit 56a131dcf7ed36c3c6e36bea448b674ea85ed5bb causing writeback on all super_blocks on a bdi, where we only really want to sync a specific sb from writeback_inodes_sb(). Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 6 ++++-- include/linux/backing-dev.h | 3 ++- mm/page-writeback.c | 2 +- 3 files changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index fb61178c86e3..9d5360c4c2af 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -250,9 +250,11 @@ static void bdi_sync_writeback(struct backing_dev_info *bdi, * completion. Caller need not hold sb s_umount semaphore. * */ -void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages) +void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb, + long nr_pages) { struct wb_writeback_args args = { + .sb = sb, .sync_mode = WB_SYNC_NONE, .nr_pages = nr_pages, .range_cyclic = 1, @@ -1206,7 +1208,7 @@ void writeback_inodes_sb(struct super_block *sb) nr_to_write = nr_dirty + nr_unstable + (inodes_stat.nr_inodes - inodes_stat.nr_unused); - bdi_start_writeback(sb->s_bdi, nr_to_write); + bdi_start_writeback(sb->s_bdi, sb, nr_to_write); } EXPORT_SYMBOL(writeback_inodes_sb); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 0ee33c2e6129..b449e738533a 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -101,7 +101,8 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...); int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); void bdi_unregister(struct backing_dev_info *bdi); -void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages); +void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb, + long nr_pages); int bdi_writeback_task(struct bdi_writeback *wb); int bdi_has_dirty_io(struct backing_dev_info *bdi); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 69b5fbabc8bd..a3b14090b1fb 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -596,7 +596,7 @@ static void balance_dirty_pages(struct address_space *mapping, (!laptop_mode && ((global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS)) > background_thresh))) - bdi_start_writeback(bdi, 0); + bdi_start_writeback(bdi, NULL, 0); } void set_page_dirty_balance(struct page *page, int page_mkwrite) -- cgit v1.2.3 From 1d1764c39815db55e10b2d78732db4d6dd9d6039 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sat, 26 Sep 2009 19:37:22 +0400 Subject: headers: kref.h redux * remove asm/atomic.h inclusion from kref.h -- not needed, linux/types.h is enough for atomic_t * remove linux/kref.h inclusion from files which do not need it. Signed-off-by: Alexey Dobriyan Signed-off-by: Linus Torvalds --- drivers/net/irda/kingsun-sir.c | 1 - drivers/net/irda/ks959-sir.c | 1 - drivers/net/irda/ksdazzle-sir.c | 1 - drivers/net/irda/mcs7780.c | 1 - drivers/scsi/pmcraid.h | 1 - drivers/usb/misc/sisusbvga/sisusb_init.c | 1 - include/linux/ipc.h | 2 -- include/linux/kref.h | 1 - include/linux/nfs_fs.h | 1 - 9 files changed, 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/irda/kingsun-sir.c b/drivers/net/irda/kingsun-sir.c index 2fc30b449eea..cb90d640007a 100644 --- a/drivers/net/irda/kingsun-sir.c +++ b/drivers/net/irda/kingsun-sir.c @@ -66,7 +66,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/net/irda/ks959-sir.c b/drivers/net/irda/ks959-sir.c index f4d13fc51cbc..b54d3b48045e 100644 --- a/drivers/net/irda/ks959-sir.c +++ b/drivers/net/irda/ks959-sir.c @@ -118,7 +118,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/net/irda/ksdazzle-sir.c b/drivers/net/irda/ksdazzle-sir.c index 5f9d73353972..8d713ebac15b 100644 --- a/drivers/net/irda/ksdazzle-sir.c +++ b/drivers/net/irda/ksdazzle-sir.c @@ -82,7 +82,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/net/irda/mcs7780.c b/drivers/net/irda/mcs7780.c index b3d30bcb88e7..c0e0bb9401d3 100644 --- a/drivers/net/irda/mcs7780.c +++ b/drivers/net/irda/mcs7780.c @@ -50,7 +50,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/scsi/pmcraid.h b/drivers/scsi/pmcraid.h index 614b3a764fed..3441b3f90827 100644 --- a/drivers/scsi/pmcraid.h +++ b/drivers/scsi/pmcraid.h @@ -26,7 +26,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/usb/misc/sisusbvga/sisusb_init.c b/drivers/usb/misc/sisusbvga/sisusb_init.c index 273de5d0934e..0ab990744830 100644 --- a/drivers/usb/misc/sisusbvga/sisusb_init.c +++ b/drivers/usb/misc/sisusbvga/sisusb_init.c @@ -43,7 +43,6 @@ #include #include #include -#include #include "sisusb.h" diff --git a/include/linux/ipc.h b/include/linux/ipc.h index b8826107b518..3b1594d662b0 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -78,8 +78,6 @@ struct ipc_kludge { #define IPCCALL(version,op) ((version)<<16 | (op)) #ifdef __KERNEL__ - -#include #include #define IPCMNI 32768 /* <= MAX_INT limit for ipc arrays (including sysctl changes) */ diff --git a/include/linux/kref.h b/include/linux/kref.h index 0cef6badd6fb..b0cb0ebad9e6 100644 --- a/include/linux/kref.h +++ b/include/linux/kref.h @@ -16,7 +16,6 @@ #define _KREF_H_ #include -#include struct kref { atomic_t refcount; diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index f6b90240dd41..d09db1bc9083 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -40,7 +40,6 @@ #ifdef __KERNEL__ #include -#include #include #include #include -- cgit v1.2.3 From d1f8297a96b0d70f17704296a6666468f2087ce6 Mon Sep 17 00:00:00 2001 From: Sascha Hlusiak Date: Sat, 26 Sep 2009 20:28:07 -0700 Subject: Revert "sit: stateless autoconf for isatap" This reverts commit 645069299a1c7358cf7330afe293f07552f11a5d. While the code does not actually break anything, it does not completely follow RFC5214 yet. After talking back with Fred L. Templin, I agree that completing the ISATAP specific RS/RA code, would pollute the kernel a lot with code that is better implemented in userspace. The kernel should not send RS packages for ISATAP at all. Signed-off-by: Sascha Hlusiak Acked-by: Fred L. Templin Signed-off-by: David S. Miller --- include/linux/if_tunnel.h | 2 +- include/net/ipip.h | 7 ------ net/ipv6/ndisc.c | 1 - net/ipv6/sit.c | 58 ----------------------------------------------- 4 files changed, 1 insertion(+), 67 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_tunnel.h b/include/linux/if_tunnel.h index 5eb9b0f857e0..5a9aae4adb44 100644 --- a/include/linux/if_tunnel.h +++ b/include/linux/if_tunnel.h @@ -44,7 +44,7 @@ struct ip_tunnel_prl { __u16 flags; __u16 __reserved; __u32 datalen; - __u32 rs_delay; + __u32 __reserved2; /* data follows */ }; diff --git a/include/net/ipip.h b/include/net/ipip.h index 76e3ea6e2fe5..87acf8f3a155 100644 --- a/include/net/ipip.h +++ b/include/net/ipip.h @@ -27,18 +27,11 @@ struct ip_tunnel unsigned int prl_count; /* # of entries in PRL */ }; -/* ISATAP: default interval between RS in secondy */ -#define IPTUNNEL_RS_DEFAULT_DELAY (900) - struct ip_tunnel_prl_entry { struct ip_tunnel_prl_entry *next; __be32 addr; u16 flags; - unsigned long rs_delay; - struct timer_list rs_timer; - struct ip_tunnel *tunnel; - spinlock_t lock; }; #define IPTUNNEL_XMIT() do { \ diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 498b9b0b0fad..f74e4e2cdd06 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -658,7 +658,6 @@ void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, &icmp6h, NULL, send_sllao ? ND_OPT_SOURCE_LL_ADDR : 0); } -EXPORT_SYMBOL(ndisc_send_rs); static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb) diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index fcb539628847..d65e0c496cc0 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -15,7 +15,6 @@ * Roger Venning : 6to4 support * Nate Thompson : 6to4 support * Fred Templin : isatap support - * Sascha Hlusiak : stateless autoconf for isatap */ #include @@ -223,44 +222,6 @@ failed: return NULL; } -static void ipip6_tunnel_rs_timer(unsigned long data) -{ - struct ip_tunnel_prl_entry *p = (struct ip_tunnel_prl_entry *) data; - struct inet6_dev *ifp; - struct inet6_ifaddr *addr; - - spin_lock(&p->lock); - ifp = __in6_dev_get(p->tunnel->dev); - - read_lock_bh(&ifp->lock); - for (addr = ifp->addr_list; addr; addr = addr->if_next) { - struct in6_addr rtr; - - if (!(ipv6_addr_type(&addr->addr) & IPV6_ADDR_LINKLOCAL)) - continue; - - /* Send RS to guessed linklocal address of router - * - * Better: send to ff02::2 encapsuled in unicast directly - * to router-v4 instead of guessing the v6 address. - * - * Cisco/Windows seem to not set the u/l bit correctly, - * so we won't guess right. - */ - ipv6_addr_set(&rtr, htonl(0xFE800000), 0, 0, 0); - if (!__ipv6_isatap_ifid(rtr.s6_addr + 8, - p->addr)) { - ndisc_send_rs(p->tunnel->dev, &addr->addr, &rtr); - } - } - read_unlock_bh(&ifp->lock); - - mod_timer(&p->rs_timer, jiffies + HZ * p->rs_delay); - spin_unlock(&p->lock); - - return; -} - static struct ip_tunnel_prl_entry * __ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr) { @@ -319,7 +280,6 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t, continue; kp[c].addr = prl->addr; kp[c].flags = prl->flags; - kp[c].rs_delay = prl->rs_delay; c++; if (kprl.addr != htonl(INADDR_ANY)) break; @@ -369,23 +329,11 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg) } p->next = t->prl; - p->tunnel = t; t->prl = p; t->prl_count++; - - spin_lock_init(&p->lock); - setup_timer(&p->rs_timer, ipip6_tunnel_rs_timer, (unsigned long) p); update: p->addr = a->addr; p->flags = a->flags; - p->rs_delay = a->rs_delay; - if (p->rs_delay == 0) - p->rs_delay = IPTUNNEL_RS_DEFAULT_DELAY; - spin_lock(&p->lock); - del_timer(&p->rs_timer); - if (p->flags & PRL_DEFAULT) - mod_timer(&p->rs_timer, jiffies + 1); - spin_unlock(&p->lock); out: write_unlock(&ipip6_lock); return err; @@ -404,9 +352,6 @@ ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) if ((*p)->addr == a->addr) { x = *p; *p = x->next; - spin_lock(&x->lock); - del_timer(&x->rs_timer); - spin_unlock(&x->lock); kfree(x); t->prl_count--; goto out; @@ -417,9 +362,6 @@ ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) while (t->prl) { x = t->prl; t->prl = t->prl->next; - spin_lock(&x->lock); - del_timer(&x->rs_timer); - spin_unlock(&x->lock); kfree(x); t->prl_count--; } -- cgit v1.2.3 From f0f37e2f77731b3473fa6bd5ee53255d9a9cdb40 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sun, 27 Sep 2009 22:29:37 +0400 Subject: const: mark struct vm_struct_operations * mark struct vm_area_struct::vm_ops as const * mark vm_ops in AGP code But leave TTM code alone, something is fishy there with global vm_ops being used. Signed-off-by: Alexey Dobriyan Signed-off-by: Linus Torvalds --- arch/ia64/ia32/binfmt_elf32.c | 4 ++-- arch/powerpc/platforms/cell/spufs/file.c | 14 +++++++------- arch/x86/pci/i386.c | 2 +- drivers/char/agp/agp.h | 2 +- drivers/char/agp/alpha-agp.c | 2 +- drivers/char/mem.c | 2 +- drivers/char/mspec.c | 2 +- drivers/gpu/drm/drm_vm.c | 8 ++++---- drivers/gpu/drm/radeon/radeon_ttm.c | 2 +- drivers/gpu/drm/ttm/ttm_bo_vm.c | 2 +- drivers/ieee1394/dma.c | 2 +- drivers/infiniband/hw/ehca/ehca_uverbs.c | 2 +- drivers/infiniband/hw/ipath/ipath_file_ops.c | 2 +- drivers/infiniband/hw/ipath/ipath_mmap.c | 2 +- drivers/media/video/cafe_ccic.c | 2 +- drivers/media/video/et61x251/et61x251_core.c | 2 +- drivers/media/video/gspca/gspca.c | 2 +- drivers/media/video/meye.c | 2 +- drivers/media/video/sn9c102/sn9c102_core.c | 2 +- drivers/media/video/stk-webcam.c | 2 +- drivers/media/video/uvc/uvc_v4l2.c | 2 +- drivers/media/video/videobuf-dma-contig.c | 2 +- drivers/media/video/videobuf-dma-sg.c | 2 +- drivers/media/video/videobuf-vmalloc.c | 2 +- drivers/media/video/vino.c | 2 +- drivers/media/video/zc0301/zc0301_core.c | 2 +- drivers/media/video/zoran/zoran_driver.c | 2 +- drivers/misc/sgi-gru/grufile.c | 2 +- drivers/misc/sgi-gru/grutables.h | 2 +- drivers/scsi/sg.c | 2 +- drivers/uio/uio.c | 2 +- drivers/usb/mon/mon_bin.c | 2 +- drivers/video/fb_defio.c | 2 +- drivers/video/omap/dispc.c | 2 +- fs/btrfs/file.c | 2 +- fs/ext4/file.c | 2 +- fs/fuse/file.c | 2 +- fs/gfs2/file.c | 2 +- fs/ncpfs/mmap.c | 2 +- fs/nfs/file.c | 4 ++-- fs/nilfs2/file.c | 2 +- fs/ocfs2/mmap.c | 2 +- fs/sysfs/bin.c | 4 ++-- fs/ubifs/file.c | 2 +- fs/xfs/linux-2.6/xfs_file.c | 4 ++-- include/linux/agp_backend.h | 2 +- include/linux/hugetlb.h | 2 +- include/linux/mm_types.h | 2 +- include/linux/ramfs.h | 2 +- ipc/shm.c | 4 ++-- kernel/perf_event.c | 2 +- kernel/relay.c | 2 +- mm/filemap.c | 2 +- mm/filemap_xip.c | 2 +- mm/hugetlb.c | 2 +- mm/mmap.c | 2 +- mm/nommu.c | 2 +- mm/shmem.c | 4 ++-- net/packet/af_packet.c | 2 +- sound/core/pcm_native.c | 8 ++++---- sound/usb/usx2y/us122l.c | 2 +- sound/usb/usx2y/usX2Yhwdep.c | 2 +- sound/usb/usx2y/usx2yhwdeppcm.c | 2 +- virt/kvm/kvm_main.c | 4 ++-- 64 files changed, 83 insertions(+), 83 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/ia32/binfmt_elf32.c b/arch/ia64/ia32/binfmt_elf32.c index f92bdaac8976..c69552bf893e 100644 --- a/arch/ia64/ia32/binfmt_elf32.c +++ b/arch/ia64/ia32/binfmt_elf32.c @@ -69,11 +69,11 @@ ia32_install_gate_page (struct vm_area_struct *vma, struct vm_fault *vmf) } -static struct vm_operations_struct ia32_shared_page_vm_ops = { +static const struct vm_operations_struct ia32_shared_page_vm_ops = { .fault = ia32_install_shared_page }; -static struct vm_operations_struct ia32_gate_page_vm_ops = { +static const struct vm_operations_struct ia32_gate_page_vm_ops = { .fault = ia32_install_gate_page }; diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 8f079b865ad0..961309446170 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -309,7 +309,7 @@ static int spufs_mem_mmap_access(struct vm_area_struct *vma, return len; } -static struct vm_operations_struct spufs_mem_mmap_vmops = { +static const struct vm_operations_struct spufs_mem_mmap_vmops = { .fault = spufs_mem_mmap_fault, .access = spufs_mem_mmap_access, }; @@ -436,7 +436,7 @@ static int spufs_cntl_mmap_fault(struct vm_area_struct *vma, return spufs_ps_fault(vma, vmf, 0x4000, SPUFS_CNTL_MAP_SIZE); } -static struct vm_operations_struct spufs_cntl_mmap_vmops = { +static const struct vm_operations_struct spufs_cntl_mmap_vmops = { .fault = spufs_cntl_mmap_fault, }; @@ -1143,7 +1143,7 @@ spufs_signal1_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) #endif } -static struct vm_operations_struct spufs_signal1_mmap_vmops = { +static const struct vm_operations_struct spufs_signal1_mmap_vmops = { .fault = spufs_signal1_mmap_fault, }; @@ -1279,7 +1279,7 @@ spufs_signal2_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) #endif } -static struct vm_operations_struct spufs_signal2_mmap_vmops = { +static const struct vm_operations_struct spufs_signal2_mmap_vmops = { .fault = spufs_signal2_mmap_fault, }; @@ -1397,7 +1397,7 @@ spufs_mss_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return spufs_ps_fault(vma, vmf, 0x0000, SPUFS_MSS_MAP_SIZE); } -static struct vm_operations_struct spufs_mss_mmap_vmops = { +static const struct vm_operations_struct spufs_mss_mmap_vmops = { .fault = spufs_mss_mmap_fault, }; @@ -1458,7 +1458,7 @@ spufs_psmap_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return spufs_ps_fault(vma, vmf, 0x0000, SPUFS_PS_MAP_SIZE); } -static struct vm_operations_struct spufs_psmap_mmap_vmops = { +static const struct vm_operations_struct spufs_psmap_mmap_vmops = { .fault = spufs_psmap_mmap_fault, }; @@ -1517,7 +1517,7 @@ spufs_mfc_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return spufs_ps_fault(vma, vmf, 0x3000, SPUFS_MFC_MAP_SIZE); } -static struct vm_operations_struct spufs_mfc_mmap_vmops = { +static const struct vm_operations_struct spufs_mfc_mmap_vmops = { .fault = spufs_mfc_mmap_fault, }; diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 52e62e57fedd..b22d13b0c71d 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -266,7 +266,7 @@ void pcibios_set_master(struct pci_dev *dev) pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat); } -static struct vm_operations_struct pci_mmap_ops = { +static const struct vm_operations_struct pci_mmap_ops = { .access = generic_access_phys, }; diff --git a/drivers/char/agp/agp.h b/drivers/char/agp/agp.h index d6f36c004d9b..870f12cfed93 100644 --- a/drivers/char/agp/agp.h +++ b/drivers/char/agp/agp.h @@ -131,7 +131,7 @@ struct agp_bridge_driver { struct agp_bridge_data { const struct agp_version *version; const struct agp_bridge_driver *driver; - struct vm_operations_struct *vm_ops; + const struct vm_operations_struct *vm_ops; void *previous_size; void *current_size; void *dev_private_data; diff --git a/drivers/char/agp/alpha-agp.c b/drivers/char/agp/alpha-agp.c index 5ea4da8e9954..dd84af4d4f7e 100644 --- a/drivers/char/agp/alpha-agp.c +++ b/drivers/char/agp/alpha-agp.c @@ -40,7 +40,7 @@ static struct aper_size_info_fixed alpha_core_agp_sizes[] = { 0, 0, 0 }, /* filled in by alpha_core_agp_setup */ }; -struct vm_operations_struct alpha_core_agp_vm_ops = { +static const struct vm_operations_struct alpha_core_agp_vm_ops = { .fault = alpha_core_agp_vm_fault, }; diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 6c8b65d069e5..a074fceb67d3 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -301,7 +301,7 @@ static inline int private_mapping_ok(struct vm_area_struct *vma) } #endif -static struct vm_operations_struct mmap_mem_ops = { +static const struct vm_operations_struct mmap_mem_ops = { #ifdef CONFIG_HAVE_IOREMAP_PROT .access = generic_access_phys #endif diff --git a/drivers/char/mspec.c b/drivers/char/mspec.c index 30f095a8c2d4..1997270bb6f4 100644 --- a/drivers/char/mspec.c +++ b/drivers/char/mspec.c @@ -239,7 +239,7 @@ mspec_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return VM_FAULT_NOPAGE; } -static struct vm_operations_struct mspec_vm_ops = { +static const struct vm_operations_struct mspec_vm_ops = { .open = mspec_open, .close = mspec_close, .fault = mspec_fault, diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c index 7e1fbe5d4779..4ac900f4647f 100644 --- a/drivers/gpu/drm/drm_vm.c +++ b/drivers/gpu/drm/drm_vm.c @@ -369,28 +369,28 @@ static int drm_vm_sg_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } /** AGP virtual memory operations */ -static struct vm_operations_struct drm_vm_ops = { +static const struct vm_operations_struct drm_vm_ops = { .fault = drm_vm_fault, .open = drm_vm_open, .close = drm_vm_close, }; /** Shared virtual memory operations */ -static struct vm_operations_struct drm_vm_shm_ops = { +static const struct vm_operations_struct drm_vm_shm_ops = { .fault = drm_vm_shm_fault, .open = drm_vm_open, .close = drm_vm_shm_close, }; /** DMA virtual memory operations */ -static struct vm_operations_struct drm_vm_dma_ops = { +static const struct vm_operations_struct drm_vm_dma_ops = { .fault = drm_vm_dma_fault, .open = drm_vm_open, .close = drm_vm_close, }; /** Scatter-gather virtual memory operations */ -static struct vm_operations_struct drm_vm_sg_ops = { +static const struct vm_operations_struct drm_vm_sg_ops = { .fault = drm_vm_sg_fault, .open = drm_vm_open, .close = drm_vm_close, diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index acd889c94549..5b1cf04a011a 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -530,7 +530,7 @@ void radeon_ttm_fini(struct radeon_device *rdev) } static struct vm_operations_struct radeon_ttm_vm_ops; -static struct vm_operations_struct *ttm_vm_ops = NULL; +static const struct vm_operations_struct *ttm_vm_ops = NULL; static int radeon_ttm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 33de7637c0c6..1c040d040338 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -228,7 +228,7 @@ static void ttm_bo_vm_close(struct vm_area_struct *vma) vma->vm_private_data = NULL; } -static struct vm_operations_struct ttm_bo_vm_ops = { +static const struct vm_operations_struct ttm_bo_vm_ops = { .fault = ttm_bo_vm_fault, .open = ttm_bo_vm_open, .close = ttm_bo_vm_close diff --git a/drivers/ieee1394/dma.c b/drivers/ieee1394/dma.c index 1aba8c13fe8f..8e7e3344c4b3 100644 --- a/drivers/ieee1394/dma.c +++ b/drivers/ieee1394/dma.c @@ -247,7 +247,7 @@ static int dma_region_pagefault(struct vm_area_struct *vma, return 0; } -static struct vm_operations_struct dma_region_vm_ops = { +static const struct vm_operations_struct dma_region_vm_ops = { .fault = dma_region_pagefault, }; diff --git a/drivers/infiniband/hw/ehca/ehca_uverbs.c b/drivers/infiniband/hw/ehca/ehca_uverbs.c index 3cb688d29131..f1565cae8ec6 100644 --- a/drivers/infiniband/hw/ehca/ehca_uverbs.c +++ b/drivers/infiniband/hw/ehca/ehca_uverbs.c @@ -95,7 +95,7 @@ static void ehca_mm_close(struct vm_area_struct *vma) vma->vm_start, vma->vm_end, *count); } -static struct vm_operations_struct vm_ops = { +static const struct vm_operations_struct vm_ops = { .open = ehca_mm_open, .close = ehca_mm_close, }; diff --git a/drivers/infiniband/hw/ipath/ipath_file_ops.c b/drivers/infiniband/hw/ipath/ipath_file_ops.c index 38a287006612..40dbe54056c7 100644 --- a/drivers/infiniband/hw/ipath/ipath_file_ops.c +++ b/drivers/infiniband/hw/ipath/ipath_file_ops.c @@ -1151,7 +1151,7 @@ static int ipath_file_vma_fault(struct vm_area_struct *vma, return 0; } -static struct vm_operations_struct ipath_file_vm_ops = { +static const struct vm_operations_struct ipath_file_vm_ops = { .fault = ipath_file_vma_fault, }; diff --git a/drivers/infiniband/hw/ipath/ipath_mmap.c b/drivers/infiniband/hw/ipath/ipath_mmap.c index fa830e22002f..b28865faf435 100644 --- a/drivers/infiniband/hw/ipath/ipath_mmap.c +++ b/drivers/infiniband/hw/ipath/ipath_mmap.c @@ -74,7 +74,7 @@ static void ipath_vma_close(struct vm_area_struct *vma) kref_put(&ip->ref, ipath_release_mmap_info); } -static struct vm_operations_struct ipath_vm_ops = { +static const struct vm_operations_struct ipath_vm_ops = { .open = ipath_vma_open, .close = ipath_vma_close, }; diff --git a/drivers/media/video/cafe_ccic.c b/drivers/media/video/cafe_ccic.c index 657c481d255c..10230cb3d210 100644 --- a/drivers/media/video/cafe_ccic.c +++ b/drivers/media/video/cafe_ccic.c @@ -1325,7 +1325,7 @@ static void cafe_v4l_vm_close(struct vm_area_struct *vma) mutex_unlock(&sbuf->cam->s_mutex); } -static struct vm_operations_struct cafe_v4l_vm_ops = { +static const struct vm_operations_struct cafe_v4l_vm_ops = { .open = cafe_v4l_vm_open, .close = cafe_v4l_vm_close }; diff --git a/drivers/media/video/et61x251/et61x251_core.c b/drivers/media/video/et61x251/et61x251_core.c index 74092f436be6..88987a57cf7b 100644 --- a/drivers/media/video/et61x251/et61x251_core.c +++ b/drivers/media/video/et61x251/et61x251_core.c @@ -1496,7 +1496,7 @@ static void et61x251_vm_close(struct vm_area_struct* vma) } -static struct vm_operations_struct et61x251_vm_ops = { +static const struct vm_operations_struct et61x251_vm_ops = { .open = et61x251_vm_open, .close = et61x251_vm_close, }; diff --git a/drivers/media/video/gspca/gspca.c b/drivers/media/video/gspca/gspca.c index cf6540da1e42..23d3fb776918 100644 --- a/drivers/media/video/gspca/gspca.c +++ b/drivers/media/video/gspca/gspca.c @@ -99,7 +99,7 @@ static void gspca_vm_close(struct vm_area_struct *vma) frame->v4l2_buf.flags &= ~V4L2_BUF_FLAG_MAPPED; } -static struct vm_operations_struct gspca_vm_ops = { +static const struct vm_operations_struct gspca_vm_ops = { .open = gspca_vm_open, .close = gspca_vm_close, }; diff --git a/drivers/media/video/meye.c b/drivers/media/video/meye.c index d0765bed79c9..4b1bc05a462c 100644 --- a/drivers/media/video/meye.c +++ b/drivers/media/video/meye.c @@ -1589,7 +1589,7 @@ static void meye_vm_close(struct vm_area_struct *vma) meye.vma_use_count[idx]--; } -static struct vm_operations_struct meye_vm_ops = { +static const struct vm_operations_struct meye_vm_ops = { .open = meye_vm_open, .close = meye_vm_close, }; diff --git a/drivers/media/video/sn9c102/sn9c102_core.c b/drivers/media/video/sn9c102/sn9c102_core.c index 9d84c94e8a40..4a7711c3e745 100644 --- a/drivers/media/video/sn9c102/sn9c102_core.c +++ b/drivers/media/video/sn9c102/sn9c102_core.c @@ -2077,7 +2077,7 @@ static void sn9c102_vm_close(struct vm_area_struct* vma) } -static struct vm_operations_struct sn9c102_vm_ops = { +static const struct vm_operations_struct sn9c102_vm_ops = { .open = sn9c102_vm_open, .close = sn9c102_vm_close, }; diff --git a/drivers/media/video/stk-webcam.c b/drivers/media/video/stk-webcam.c index 0b996ea4134e..6b41865f42bd 100644 --- a/drivers/media/video/stk-webcam.c +++ b/drivers/media/video/stk-webcam.c @@ -790,7 +790,7 @@ static void stk_v4l_vm_close(struct vm_area_struct *vma) if (sbuf->mapcount == 0) sbuf->v4lbuf.flags &= ~V4L2_BUF_FLAG_MAPPED; } -static struct vm_operations_struct stk_v4l_vm_ops = { +static const struct vm_operations_struct stk_v4l_vm_ops = { .open = stk_v4l_vm_open, .close = stk_v4l_vm_close }; diff --git a/drivers/media/video/uvc/uvc_v4l2.c b/drivers/media/video/uvc/uvc_v4l2.c index 9e7351569b5d..a2bdd806efab 100644 --- a/drivers/media/video/uvc/uvc_v4l2.c +++ b/drivers/media/video/uvc/uvc_v4l2.c @@ -1069,7 +1069,7 @@ static void uvc_vm_close(struct vm_area_struct *vma) buffer->vma_use_count--; } -static struct vm_operations_struct uvc_vm_ops = { +static const struct vm_operations_struct uvc_vm_ops = { .open = uvc_vm_open, .close = uvc_vm_close, }; diff --git a/drivers/media/video/videobuf-dma-contig.c b/drivers/media/video/videobuf-dma-contig.c index d09ce83a9429..635ffc7b0391 100644 --- a/drivers/media/video/videobuf-dma-contig.c +++ b/drivers/media/video/videobuf-dma-contig.c @@ -105,7 +105,7 @@ static void videobuf_vm_close(struct vm_area_struct *vma) } } -static struct vm_operations_struct videobuf_vm_ops = { +static const struct vm_operations_struct videobuf_vm_ops = { .open = videobuf_vm_open, .close = videobuf_vm_close, }; diff --git a/drivers/media/video/videobuf-dma-sg.c b/drivers/media/video/videobuf-dma-sg.c index a8dd22ace3fb..53cdd67cebe1 100644 --- a/drivers/media/video/videobuf-dma-sg.c +++ b/drivers/media/video/videobuf-dma-sg.c @@ -394,7 +394,7 @@ videobuf_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return 0; } -static struct vm_operations_struct videobuf_vm_ops = +static const struct vm_operations_struct videobuf_vm_ops = { .open = videobuf_vm_open, .close = videobuf_vm_close, diff --git a/drivers/media/video/videobuf-vmalloc.c b/drivers/media/video/videobuf-vmalloc.c index 30ae30f99ccc..35f3900c5633 100644 --- a/drivers/media/video/videobuf-vmalloc.c +++ b/drivers/media/video/videobuf-vmalloc.c @@ -116,7 +116,7 @@ static void videobuf_vm_close(struct vm_area_struct *vma) return; } -static struct vm_operations_struct videobuf_vm_ops = +static const struct vm_operations_struct videobuf_vm_ops = { .open = videobuf_vm_open, .close = videobuf_vm_close, diff --git a/drivers/media/video/vino.c b/drivers/media/video/vino.c index cd6a3446ab7e..b034a81d2b1c 100644 --- a/drivers/media/video/vino.c +++ b/drivers/media/video/vino.c @@ -3857,7 +3857,7 @@ static void vino_vm_close(struct vm_area_struct *vma) dprintk("vino_vm_close(): count = %d\n", fb->map_count); } -static struct vm_operations_struct vino_vm_ops = { +static const struct vm_operations_struct vino_vm_ops = { .open = vino_vm_open, .close = vino_vm_close, }; diff --git a/drivers/media/video/zc0301/zc0301_core.c b/drivers/media/video/zc0301/zc0301_core.c index b3c6436b33ba..312a71336fd0 100644 --- a/drivers/media/video/zc0301/zc0301_core.c +++ b/drivers/media/video/zc0301/zc0301_core.c @@ -935,7 +935,7 @@ static void zc0301_vm_close(struct vm_area_struct* vma) } -static struct vm_operations_struct zc0301_vm_ops = { +static const struct vm_operations_struct zc0301_vm_ops = { .open = zc0301_vm_open, .close = zc0301_vm_close, }; diff --git a/drivers/media/video/zoran/zoran_driver.c b/drivers/media/video/zoran/zoran_driver.c index bcdefb1bcb3d..47137deafcfd 100644 --- a/drivers/media/video/zoran/zoran_driver.c +++ b/drivers/media/video/zoran/zoran_driver.c @@ -3172,7 +3172,7 @@ zoran_vm_close (struct vm_area_struct *vma) mutex_unlock(&zr->resource_lock); } -static struct vm_operations_struct zoran_vm_ops = { +static const struct vm_operations_struct zoran_vm_ops = { .open = zoran_vm_open, .close = zoran_vm_close, }; diff --git a/drivers/misc/sgi-gru/grufile.c b/drivers/misc/sgi-gru/grufile.c index aed609832bc2..300e7ba391a0 100644 --- a/drivers/misc/sgi-gru/grufile.c +++ b/drivers/misc/sgi-gru/grufile.c @@ -438,7 +438,7 @@ static struct miscdevice gru_miscdev = { .fops = &gru_fops, }; -struct vm_operations_struct gru_vm_ops = { +const struct vm_operations_struct gru_vm_ops = { .close = gru_vma_close, .fault = gru_fault, }; diff --git a/drivers/misc/sgi-gru/grutables.h b/drivers/misc/sgi-gru/grutables.h index 34ab3d453919..46990bcfa536 100644 --- a/drivers/misc/sgi-gru/grutables.h +++ b/drivers/misc/sgi-gru/grutables.h @@ -624,7 +624,7 @@ static inline int is_kernel_context(struct gru_thread_state *gts) */ struct gru_unload_context_req; -extern struct vm_operations_struct gru_vm_ops; +extern const struct vm_operations_struct gru_vm_ops; extern struct device *grudev; extern struct gru_vma_data *gru_alloc_vma_data(struct vm_area_struct *vma, diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 848b59466850..0cb049f5cc56 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1185,7 +1185,7 @@ sg_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return VM_FAULT_SIGBUS; } -static struct vm_operations_struct sg_mmap_vm_ops = { +static const struct vm_operations_struct sg_mmap_vm_ops = { .fault = sg_vma_fault, }; diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index 03efb065455f..a9d707047202 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -658,7 +658,7 @@ static int uio_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return 0; } -static struct vm_operations_struct uio_vm_ops = { +static const struct vm_operations_struct uio_vm_ops = { .open = uio_vma_open, .close = uio_vma_close, .fault = uio_vma_fault, diff --git a/drivers/usb/mon/mon_bin.c b/drivers/usb/mon/mon_bin.c index dfdc43e2e00d..9ed3e741bee1 100644 --- a/drivers/usb/mon/mon_bin.c +++ b/drivers/usb/mon/mon_bin.c @@ -1174,7 +1174,7 @@ static int mon_bin_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return 0; } -static struct vm_operations_struct mon_bin_vm_ops = { +static const struct vm_operations_struct mon_bin_vm_ops = { .open = mon_bin_vma_open, .close = mon_bin_vma_close, .fault = mon_bin_vma_fault, diff --git a/drivers/video/fb_defio.c b/drivers/video/fb_defio.c index 0a7a6679ee6e..c27ab1ed9604 100644 --- a/drivers/video/fb_defio.c +++ b/drivers/video/fb_defio.c @@ -125,7 +125,7 @@ page_already_added: return 0; } -static struct vm_operations_struct fb_deferred_io_vm_ops = { +static const struct vm_operations_struct fb_deferred_io_vm_ops = { .fault = fb_deferred_io_fault, .page_mkwrite = fb_deferred_io_mkwrite, }; diff --git a/drivers/video/omap/dispc.c b/drivers/video/omap/dispc.c index 80a11d078df4..f16e42154229 100644 --- a/drivers/video/omap/dispc.c +++ b/drivers/video/omap/dispc.c @@ -1035,7 +1035,7 @@ static void mmap_user_close(struct vm_area_struct *vma) atomic_dec(&dispc.map_count[plane]); } -static struct vm_operations_struct mmap_user_ops = { +static const struct vm_operations_struct mmap_user_ops = { .open = mmap_user_open, .close = mmap_user_close, }; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 571ad3c13b47..a3492a3ad96b 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1184,7 +1184,7 @@ out: return ret > 0 ? EIO : ret; } -static struct vm_operations_struct btrfs_file_vm_ops = { +static const struct vm_operations_struct btrfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = btrfs_page_mkwrite, }; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 5ca3eca70a1e..9630583cef28 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -81,7 +81,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, return generic_file_aio_write(iocb, iov, nr_segs, pos); } -static struct vm_operations_struct ext4_file_vm_ops = { +static const struct vm_operations_struct ext4_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = ext4_page_mkwrite, }; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index cbc464043b6f..a3492f7d207c 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1313,7 +1313,7 @@ static int fuse_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) return 0; } -static struct vm_operations_struct fuse_file_vm_ops = { +static const struct vm_operations_struct fuse_file_vm_ops = { .close = fuse_vma_close, .fault = filemap_fault, .page_mkwrite = fuse_page_mkwrite, diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 166f38fbd246..4eb308aa3234 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -418,7 +418,7 @@ out: return ret; } -static struct vm_operations_struct gfs2_vm_ops = { +static const struct vm_operations_struct gfs2_vm_ops = { .fault = filemap_fault, .page_mkwrite = gfs2_page_mkwrite, }; diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c index 5d8dcb9ee326..15458decdb8a 100644 --- a/fs/ncpfs/mmap.c +++ b/fs/ncpfs/mmap.c @@ -95,7 +95,7 @@ static int ncp_file_mmap_fault(struct vm_area_struct *area, return VM_FAULT_MAJOR; } -static struct vm_operations_struct ncp_file_mmap = +static const struct vm_operations_struct ncp_file_mmap = { .fault = ncp_file_mmap_fault, }; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 86d6b4db1096..f5fdd39e037a 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -59,7 +59,7 @@ static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl); static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl); static int nfs_setlease(struct file *file, long arg, struct file_lock **fl); -static struct vm_operations_struct nfs_file_vm_ops; +static const struct vm_operations_struct nfs_file_vm_ops; const struct file_operations nfs_file_operations = { .llseek = nfs_file_llseek, @@ -572,7 +572,7 @@ out_unlock: return VM_FAULT_SIGBUS; } -static struct vm_operations_struct nfs_file_vm_ops = { +static const struct vm_operations_struct nfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = nfs_vm_page_mkwrite, }; diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index fc8278c77cdd..7d7b4983dee3 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -117,7 +117,7 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) return 0; } -struct vm_operations_struct nilfs_file_vm_ops = { +static const struct vm_operations_struct nilfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = nilfs_page_mkwrite, }; diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index b606496b72ec..39737613424a 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -202,7 +202,7 @@ out: return ret; } -static struct vm_operations_struct ocfs2_file_vm_ops = { +static const struct vm_operations_struct ocfs2_file_vm_ops = { .fault = ocfs2_fault, .page_mkwrite = ocfs2_page_mkwrite, }; diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c index 2524714bece1..60c702bc10ae 100644 --- a/fs/sysfs/bin.c +++ b/fs/sysfs/bin.c @@ -40,7 +40,7 @@ struct bin_buffer { struct mutex mutex; void *buffer; int mmapped; - struct vm_operations_struct *vm_ops; + const struct vm_operations_struct *vm_ops; struct file *file; struct hlist_node list; }; @@ -331,7 +331,7 @@ static int bin_migrate(struct vm_area_struct *vma, const nodemask_t *from, } #endif -static struct vm_operations_struct bin_vm_ops = { +static const struct vm_operations_struct bin_vm_ops = { .open = bin_vma_open, .close = bin_vma_close, .fault = bin_fault, diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 2e6481a7701c..1009adc8d602 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1534,7 +1534,7 @@ out_unlock: return err; } -static struct vm_operations_struct ubifs_file_vm_ops = { +static const struct vm_operations_struct ubifs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = ubifs_vm_page_mkwrite, }; diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c index 988d8f87bc0f..629370974e57 100644 --- a/fs/xfs/linux-2.6/xfs_file.c +++ b/fs/xfs/linux-2.6/xfs_file.c @@ -42,7 +42,7 @@ #include -static struct vm_operations_struct xfs_file_vm_ops; +static const struct vm_operations_struct xfs_file_vm_ops; STATIC ssize_t xfs_file_aio_read( @@ -280,7 +280,7 @@ const struct file_operations xfs_dir_file_operations = { .fsync = xfs_file_fsync, }; -static struct vm_operations_struct xfs_file_vm_ops = { +static const struct vm_operations_struct xfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = xfs_vm_page_mkwrite, }; diff --git a/include/linux/agp_backend.h b/include/linux/agp_backend.h index 880130f7311f..9101ed64f803 100644 --- a/include/linux/agp_backend.h +++ b/include/linux/agp_backend.h @@ -53,7 +53,7 @@ struct agp_kern_info { int current_memory; bool cant_use_aperture; unsigned long page_mask; - struct vm_operations_struct *vm_ops; + const struct vm_operations_struct *vm_ops; }; /* diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 16937995abd4..41a59afc70fa 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -163,7 +163,7 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) } extern const struct file_operations hugetlbfs_file_operations; -extern struct vm_operations_struct hugetlb_vm_ops; +extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, int acct, struct user_struct **user, int creat_flags); int hugetlb_get_quota(struct address_space *mapping, long delta); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 21d6aa45206a..84a524afb3dc 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -171,7 +171,7 @@ struct vm_area_struct { struct anon_vma *anon_vma; /* Serialized by page_table_lock */ /* Function pointers to deal with this struct. */ - struct vm_operations_struct * vm_ops; + const struct vm_operations_struct *vm_ops; /* Information about our backing store: */ unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h index 37aaf2b39863..4e768dda87b0 100644 --- a/include/linux/ramfs.h +++ b/include/linux/ramfs.h @@ -17,7 +17,7 @@ extern int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma); #endif extern const struct file_operations ramfs_file_operations; -extern struct vm_operations_struct generic_file_vm_ops; +extern const struct vm_operations_struct generic_file_vm_ops; extern int __init init_rootfs(void); #endif diff --git a/ipc/shm.c b/ipc/shm.c index 9eb1488b543b..464694e0aa4a 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -55,7 +55,7 @@ struct shm_file_data { #define shm_file_data(file) (*((struct shm_file_data **)&(file)->private_data)) static const struct file_operations shm_file_operations; -static struct vm_operations_struct shm_vm_ops; +static const struct vm_operations_struct shm_vm_ops; #define shm_ids(ns) ((ns)->ids[IPC_SHM_IDS]) @@ -312,7 +312,7 @@ static const struct file_operations shm_file_operations = { .get_unmapped_area = shm_get_unmapped_area, }; -static struct vm_operations_struct shm_vm_ops = { +static const struct vm_operations_struct shm_vm_ops = { .open = shm_open, /* callback for a new vm-area open */ .close = shm_close, /* callback for when the vm-area is released */ .fault = shm_fault, diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 76ac4db405e9..0f86feb6db0c 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2253,7 +2253,7 @@ static void perf_mmap_close(struct vm_area_struct *vma) } } -static struct vm_operations_struct perf_mmap_vmops = { +static const struct vm_operations_struct perf_mmap_vmops = { .open = perf_mmap_open, .close = perf_mmap_close, .fault = perf_mmap_fault, diff --git a/kernel/relay.c b/kernel/relay.c index bc188549788f..760c26209a3c 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -60,7 +60,7 @@ static int relay_buf_fault(struct vm_area_struct *vma, struct vm_fault *vmf) /* * vm_ops for relay file mappings. */ -static struct vm_operations_struct relay_file_mmap_ops = { +static const struct vm_operations_struct relay_file_mmap_ops = { .fault = relay_buf_fault, .close = relay_file_mmap_close, }; diff --git a/mm/filemap.c b/mm/filemap.c index 6c84e598b4a9..ef169f37156d 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1611,7 +1611,7 @@ page_not_uptodate: } EXPORT_SYMBOL(filemap_fault); -struct vm_operations_struct generic_file_vm_ops = { +const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, }; diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 427dfe3ce78c..1888b2d71bb8 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -296,7 +296,7 @@ out: } } -static struct vm_operations_struct xip_file_vm_ops = { +static const struct vm_operations_struct xip_file_vm_ops = { .fault = xip_file_fault, }; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6f048fcc749c..5d7601b02874 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1721,7 +1721,7 @@ static int hugetlb_vm_op_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return 0; } -struct vm_operations_struct hugetlb_vm_ops = { +const struct vm_operations_struct hugetlb_vm_ops = { .fault = hugetlb_vm_op_fault, .open = hugetlb_vm_op_open, .close = hugetlb_vm_op_close, diff --git a/mm/mmap.c b/mm/mmap.c index 21d4029a07b3..73f5e4b64010 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2282,7 +2282,7 @@ static void special_mapping_close(struct vm_area_struct *vma) { } -static struct vm_operations_struct special_mapping_vmops = { +static const struct vm_operations_struct special_mapping_vmops = { .close = special_mapping_close, .fault = special_mapping_fault, }; diff --git a/mm/nommu.c b/mm/nommu.c index c73aa4753d79..5189b5aed8c0 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -79,7 +79,7 @@ static struct kmem_cache *vm_region_jar; struct rb_root nommu_region_tree = RB_ROOT; DECLARE_RWSEM(nommu_region_sem); -struct vm_operations_struct generic_file_vm_ops = { +const struct vm_operations_struct generic_file_vm_ops = { }; /* diff --git a/mm/shmem.c b/mm/shmem.c index ccf446a9faa1..356dd99566ec 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -218,7 +218,7 @@ static const struct file_operations shmem_file_operations; static const struct inode_operations shmem_inode_operations; static const struct inode_operations shmem_dir_inode_operations; static const struct inode_operations shmem_special_inode_operations; -static struct vm_operations_struct shmem_vm_ops; +static const struct vm_operations_struct shmem_vm_ops; static struct backing_dev_info shmem_backing_dev_info __read_mostly = { .ra_pages = 0, /* No readahead */ @@ -2498,7 +2498,7 @@ static const struct super_operations shmem_ops = { .put_super = shmem_put_super, }; -static struct vm_operations_struct shmem_vm_ops = { +static const struct vm_operations_struct shmem_vm_ops = { .fault = shmem_fault, #ifdef CONFIG_NUMA .set_policy = shmem_set_policy, diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index d3d52c66cdc2..103d5611b818 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2084,7 +2084,7 @@ static void packet_mm_close(struct vm_area_struct *vma) atomic_dec(&pkt_sk(sk)->mapped); } -static struct vm_operations_struct packet_mmap_ops = { +static const struct vm_operations_struct packet_mmap_ops = { .open = packet_mm_open, .close = packet_mm_close, }; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 561d6d95a2d3..ab73edf2c89a 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -2985,7 +2985,7 @@ static int snd_pcm_mmap_status_fault(struct vm_area_struct *area, return 0; } -static struct vm_operations_struct snd_pcm_vm_ops_status = +static const struct vm_operations_struct snd_pcm_vm_ops_status = { .fault = snd_pcm_mmap_status_fault, }; @@ -3024,7 +3024,7 @@ static int snd_pcm_mmap_control_fault(struct vm_area_struct *area, return 0; } -static struct vm_operations_struct snd_pcm_vm_ops_control = +static const struct vm_operations_struct snd_pcm_vm_ops_control = { .fault = snd_pcm_mmap_control_fault, }; @@ -3094,7 +3094,7 @@ static int snd_pcm_mmap_data_fault(struct vm_area_struct *area, return 0; } -static struct vm_operations_struct snd_pcm_vm_ops_data = +static const struct vm_operations_struct snd_pcm_vm_ops_data = { .open = snd_pcm_mmap_data_open, .close = snd_pcm_mmap_data_close, @@ -3118,7 +3118,7 @@ static int snd_pcm_default_mmap(struct snd_pcm_substream *substream, * mmap the DMA buffer on I/O memory area */ #if SNDRV_PCM_INFO_MMAP_IOMEM -static struct vm_operations_struct snd_pcm_vm_ops_data_mmio = +static const struct vm_operations_struct snd_pcm_vm_ops_data_mmio = { .open = snd_pcm_mmap_data_open, .close = snd_pcm_mmap_data_close, diff --git a/sound/usb/usx2y/us122l.c b/sound/usb/usx2y/us122l.c index fd44946ce4b3..99f33766cd51 100644 --- a/sound/usb/usx2y/us122l.c +++ b/sound/usb/usx2y/us122l.c @@ -154,7 +154,7 @@ static void usb_stream_hwdep_vm_close(struct vm_area_struct *area) snd_printdd(KERN_DEBUG "%i\n", atomic_read(&us122l->mmap_count)); } -static struct vm_operations_struct usb_stream_hwdep_vm_ops = { +static const struct vm_operations_struct usb_stream_hwdep_vm_ops = { .open = usb_stream_hwdep_vm_open, .fault = usb_stream_hwdep_vm_fault, .close = usb_stream_hwdep_vm_close, diff --git a/sound/usb/usx2y/usX2Yhwdep.c b/sound/usb/usx2y/usX2Yhwdep.c index f3d8f71265dd..52e04b2f35d3 100644 --- a/sound/usb/usx2y/usX2Yhwdep.c +++ b/sound/usb/usx2y/usX2Yhwdep.c @@ -53,7 +53,7 @@ static int snd_us428ctls_vm_fault(struct vm_area_struct *area, return 0; } -static struct vm_operations_struct us428ctls_vm_ops = { +static const struct vm_operations_struct us428ctls_vm_ops = { .fault = snd_us428ctls_vm_fault, }; diff --git a/sound/usb/usx2y/usx2yhwdeppcm.c b/sound/usb/usx2y/usx2yhwdeppcm.c index 117946f2debb..4b2304c2e02d 100644 --- a/sound/usb/usx2y/usx2yhwdeppcm.c +++ b/sound/usb/usx2y/usx2yhwdeppcm.c @@ -697,7 +697,7 @@ static int snd_usX2Y_hwdep_pcm_vm_fault(struct vm_area_struct *area, } -static struct vm_operations_struct snd_usX2Y_hwdep_pcm_vm_ops = { +static const struct vm_operations_struct snd_usX2Y_hwdep_pcm_vm_ops = { .open = snd_usX2Y_hwdep_pcm_vm_open, .close = snd_usX2Y_hwdep_pcm_vm_close, .fault = snd_usX2Y_hwdep_pcm_vm_fault, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 034a798b0431..b5e7e3f1183f 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1713,7 +1713,7 @@ static int kvm_vcpu_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return 0; } -static struct vm_operations_struct kvm_vcpu_vm_ops = { +static const struct vm_operations_struct kvm_vcpu_vm_ops = { .fault = kvm_vcpu_fault, }; @@ -2317,7 +2317,7 @@ static int kvm_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return 0; } -static struct vm_operations_struct kvm_vm_vm_ops = { +static const struct vm_operations_struct kvm_vm_vm_ops = { .fault = kvm_vm_fault, }; -- cgit v1.2.3 From f278a2f7bbc2239f479eaf63d0b3ae573b1d746c Mon Sep 17 00:00:00 2001 From: Dave Young Date: Sun, 27 Sep 2009 16:00:42 +0000 Subject: tty: Fix regressions caused by commit b50989dc The following commit made console open fails while booting: commit b50989dc444599c8b21edc23536fc305f4e9b7d5 Author: Alan Cox Date: Sat Sep 19 13:13:22 2009 -0700 tty: make the kref destructor occur asynchronously Due to tty release routines run in a workqueue now, error like the following will be reported while booting: INIT open /dev/console Input/output error It also causes hibernation regression to appear as reported at http://bugzilla.kernel.org/show_bug.cgi?id=14229 The reason is that now there's latency issue with closing, but when we open a "closing not finished" tty, -EIO will be returned. Fix it as per the following Alan's suggestion: Fun but it's actually not a bug and the fix is wrong in itself as the port may be closing but not yet being destructed, in which case it seems to do the wrong thing. Opening a tty that is closing (and could be closing for long periods) is supposed to return -EIO. I suspect a better way to deal with this and keep the old console timing is to split tty->shutdown into two functions. tty->shutdown() - called synchronously just before we dump the tty onto the waitqueue for destruction tty->cleanup() - called when the destructor runs. We would then do the shutdown part which can occur in IRQ context fine, before queueing the rest of the release (from tty->magic = 0 ... the end) to occur asynchronously The USB update in -next would then need a call like if (tty->cleanup) tty->cleanup(tty); at the top of the async function and the USB shutdown to be split between shutdown and cleanup as the USB resource cleanup and final tidy cannot occur synchronously as it needs to sleep. In other words the logic becomes final kref put make object unfindable async clean it up Signed-off-by: Dave Young [ rjw: Rebased on top of 2.6.31-git, reworked the changelog. ] Signed-off-by: "Rafael J. Wysocki" [ Changed serial naming to match new rules, dropped tty_shutdown as per comments from Alan Stern - Linus ] Signed-off-by: Linus Torvalds --- drivers/char/tty_io.c | 15 ++++++++++----- drivers/usb/serial/usb-serial.c | 14 ++++++-------- include/linux/tty_driver.h | 13 +++++++++++-- 3 files changed, 27 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/tty_io.c b/drivers/char/tty_io.c index ea18a129b0b5..59499ee0fe6a 100644 --- a/drivers/char/tty_io.c +++ b/drivers/char/tty_io.c @@ -1389,7 +1389,7 @@ EXPORT_SYMBOL(tty_shutdown); * of ttys that the driver keeps. * * This method gets called from a work queue so that the driver private - * shutdown ops can sleep (needed for USB at least) + * cleanup ops can sleep (needed for USB at least) */ static void release_one_tty(struct work_struct *work) { @@ -1397,10 +1397,9 @@ static void release_one_tty(struct work_struct *work) container_of(work, struct tty_struct, hangup_work); struct tty_driver *driver = tty->driver; - if (tty->ops->shutdown) - tty->ops->shutdown(tty); - else - tty_shutdown(tty); + if (tty->ops->cleanup) + tty->ops->cleanup(tty); + tty->magic = 0; tty_driver_kref_put(driver); module_put(driver->owner); @@ -1415,6 +1414,12 @@ static void release_one_tty(struct work_struct *work) static void queue_release_one_tty(struct kref *kref) { struct tty_struct *tty = container_of(kref, struct tty_struct, kref); + + if (tty->ops->shutdown) + tty->ops->shutdown(tty); + else + tty_shutdown(tty); + /* The hangup queue is now free so we can reuse it rather than waste a chunk of memory for each port */ INIT_WORK(&tty->hangup_work, release_one_tty); diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c index ff75a3589e7e..aa6b2ae951ae 100644 --- a/drivers/usb/serial/usb-serial.c +++ b/drivers/usb/serial/usb-serial.c @@ -192,7 +192,7 @@ void usb_serial_put(struct usb_serial *serial) * This is the first place a new tty gets used. Hence this is where we * acquire references to the usb_serial structure and the driver module, * where we store a pointer to the port, and where we do an autoresume. - * All these actions are reversed in serial_release(). + * All these actions are reversed in serial_cleanup(). */ static int serial_install(struct tty_driver *driver, struct tty_struct *tty) { @@ -339,15 +339,16 @@ static void serial_close(struct tty_struct *tty, struct file *filp) } /** - * serial_release - free resources post close/hangup + * serial_cleanup - free resources post close/hangup * @port: port to free up * * Do the resource freeing and refcount dropping for the port. * Avoid freeing the console. * - * Called when the last tty kref is dropped. + * Called asynchronously after the last tty kref is dropped, + * and the tty layer has already done the tty_shutdown(tty); */ -static void serial_release(struct tty_struct *tty) +static void serial_cleanup(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; struct usb_serial *serial; @@ -361,9 +362,6 @@ static void serial_release(struct tty_struct *tty) dbg("%s - port %d", __func__, port->number); - /* Standard shutdown processing */ - tty_shutdown(tty); - tty->driver_data = NULL; serial = port->serial; @@ -1210,7 +1208,7 @@ static const struct tty_operations serial_ops = { .chars_in_buffer = serial_chars_in_buffer, .tiocmget = serial_tiocmget, .tiocmset = serial_tiocmset, - .shutdown = serial_release, + .cleanup = serial_cleanup, .install = serial_install, .proc_fops = &serial_proc_fops, }; diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 3566129384a4..b08677982525 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -45,8 +45,16 @@ * * void (*shutdown)(struct tty_struct * tty); * - * This routine is called when a particular tty device is closed for - * the last time freeing up the resources. + * This routine is called synchronously when a particular tty device + * is closed for the last time freeing up the resources. + * + * + * void (*cleanup)(struct tty_struct * tty); + * + * This routine is called asynchronously when a particular tty device + * is closed for the last time freeing up the resources. This is + * actually the second part of shutdown for routines that might sleep. + * * * int (*write)(struct tty_struct * tty, * const unsigned char *buf, int count); @@ -233,6 +241,7 @@ struct tty_operations { int (*open)(struct tty_struct * tty, struct file * filp); void (*close)(struct tty_struct * tty, struct file * filp); void (*shutdown)(struct tty_struct *tty); + void (*cleanup)(struct tty_struct *tty); int (*write)(struct tty_struct * tty, const unsigned char *buf, int count); int (*put_char)(struct tty_struct *tty, unsigned char ch); -- cgit v1.2.3 From bf6993276f74d46776f35c45ddef29b981b1d1c6 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 30 Sep 2009 00:32:06 -0400 Subject: jbd2: Use tracepoints for history file The /proc/fs/jbd2//history was maintained manually; by using tracepoints, we can get all of the existing functionality of the /proc file plus extra capabilities thanks to the ftrace infrastructure. We save memory as a bonus. Signed-off-by: "Theodore Ts'o" --- fs/jbd2/checkpoint.c | 7 ++ fs/jbd2/commit.c | 59 +++++++------- fs/jbd2/journal.c | 187 +++----------------------------------------- include/linux/jbd2.h | 27 ++----- include/trace/events/jbd2.h | 78 ++++++++++++++++++ 5 files changed, 130 insertions(+), 228 deletions(-) (limited to 'include/linux') diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 5d70b3e6d49b..ca0f5eb62b20 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -643,6 +643,7 @@ out: int __jbd2_journal_remove_checkpoint(struct journal_head *jh) { + struct transaction_chp_stats_s *stats; transaction_t *transaction; journal_t *journal; int ret = 0; @@ -679,6 +680,12 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) /* OK, that was the last buffer for the transaction: we can now safely remove this transaction from the log */ + stats = &transaction->t_chp_stats; + if (stats->cs_chp_time) + stats->cs_chp_time = jbd2_time_diff(stats->cs_chp_time, + jiffies); + trace_jbd2_checkpoint_stats(journal->j_fs_dev->bd_dev, + transaction->t_tid, stats); __jbd2_journal_drop_transaction(journal, transaction); kfree(transaction); diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 26d991ddc1e6..d4cfd6d2779e 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -410,10 +410,10 @@ void jbd2_journal_commit_transaction(journal_t *journal) if (commit_transaction->t_synchronous_commit) write_op = WRITE_SYNC_PLUG; trace_jbd2_commit_locking(journal, commit_transaction); - stats.u.run.rs_wait = commit_transaction->t_max_wait; - stats.u.run.rs_locked = jiffies; - stats.u.run.rs_running = jbd2_time_diff(commit_transaction->t_start, - stats.u.run.rs_locked); + stats.run.rs_wait = commit_transaction->t_max_wait; + stats.run.rs_locked = jiffies; + stats.run.rs_running = jbd2_time_diff(commit_transaction->t_start, + stats.run.rs_locked); spin_lock(&commit_transaction->t_handle_lock); while (commit_transaction->t_updates) { @@ -486,9 +486,9 @@ void jbd2_journal_commit_transaction(journal_t *journal) jbd2_journal_switch_revoke_table(journal); trace_jbd2_commit_flushing(journal, commit_transaction); - stats.u.run.rs_flushing = jiffies; - stats.u.run.rs_locked = jbd2_time_diff(stats.u.run.rs_locked, - stats.u.run.rs_flushing); + stats.run.rs_flushing = jiffies; + stats.run.rs_locked = jbd2_time_diff(stats.run.rs_locked, + stats.run.rs_flushing); commit_transaction->t_state = T_FLUSH; journal->j_committing_transaction = commit_transaction; @@ -523,11 +523,11 @@ void jbd2_journal_commit_transaction(journal_t *journal) spin_unlock(&journal->j_state_lock); trace_jbd2_commit_logging(journal, commit_transaction); - stats.u.run.rs_logging = jiffies; - stats.u.run.rs_flushing = jbd2_time_diff(stats.u.run.rs_flushing, - stats.u.run.rs_logging); - stats.u.run.rs_blocks = commit_transaction->t_outstanding_credits; - stats.u.run.rs_blocks_logged = 0; + stats.run.rs_logging = jiffies; + stats.run.rs_flushing = jbd2_time_diff(stats.run.rs_flushing, + stats.run.rs_logging); + stats.run.rs_blocks = commit_transaction->t_outstanding_credits; + stats.run.rs_blocks_logged = 0; J_ASSERT(commit_transaction->t_nr_buffers <= commit_transaction->t_outstanding_credits); @@ -695,7 +695,7 @@ start_journal_io: submit_bh(write_op, bh); } cond_resched(); - stats.u.run.rs_blocks_logged += bufs; + stats.run.rs_blocks_logged += bufs; /* Force a new descriptor to be generated next time round the loop. */ @@ -988,33 +988,30 @@ restart_loop: J_ASSERT(commit_transaction->t_state == T_COMMIT); commit_transaction->t_start = jiffies; - stats.u.run.rs_logging = jbd2_time_diff(stats.u.run.rs_logging, - commit_transaction->t_start); + stats.run.rs_logging = jbd2_time_diff(stats.run.rs_logging, + commit_transaction->t_start); /* - * File the transaction for history + * File the transaction statistics */ - stats.ts_type = JBD2_STATS_RUN; stats.ts_tid = commit_transaction->t_tid; - stats.u.run.rs_handle_count = commit_transaction->t_handle_count; - spin_lock(&journal->j_history_lock); - memcpy(journal->j_history + journal->j_history_cur, &stats, - sizeof(stats)); - if (++journal->j_history_cur == journal->j_history_max) - journal->j_history_cur = 0; + stats.run.rs_handle_count = commit_transaction->t_handle_count; + trace_jbd2_run_stats(journal->j_fs_dev->bd_dev, + commit_transaction->t_tid, &stats.run); /* * Calculate overall stats */ + spin_lock(&journal->j_history_lock); journal->j_stats.ts_tid++; - journal->j_stats.u.run.rs_wait += stats.u.run.rs_wait; - journal->j_stats.u.run.rs_running += stats.u.run.rs_running; - journal->j_stats.u.run.rs_locked += stats.u.run.rs_locked; - journal->j_stats.u.run.rs_flushing += stats.u.run.rs_flushing; - journal->j_stats.u.run.rs_logging += stats.u.run.rs_logging; - journal->j_stats.u.run.rs_handle_count += stats.u.run.rs_handle_count; - journal->j_stats.u.run.rs_blocks += stats.u.run.rs_blocks; - journal->j_stats.u.run.rs_blocks_logged += stats.u.run.rs_blocks_logged; + journal->j_stats.run.rs_wait += stats.run.rs_wait; + journal->j_stats.run.rs_running += stats.run.rs_running; + journal->j_stats.run.rs_locked += stats.run.rs_locked; + journal->j_stats.run.rs_flushing += stats.run.rs_flushing; + journal->j_stats.run.rs_logging += stats.run.rs_logging; + journal->j_stats.run.rs_handle_count += stats.run.rs_handle_count; + journal->j_stats.run.rs_blocks += stats.run.rs_blocks; + journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged; spin_unlock(&journal->j_history_lock); commit_transaction->t_state = T_FINISHED; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 977a8dafb76d..761af77491f5 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -676,153 +676,6 @@ struct jbd2_stats_proc_session { int max; }; -static void *jbd2_history_skip_empty(struct jbd2_stats_proc_session *s, - struct transaction_stats_s *ts, - int first) -{ - if (ts == s->stats + s->max) - ts = s->stats; - if (!first && ts == s->stats + s->start) - return NULL; - while (ts->ts_type == 0) { - ts++; - if (ts == s->stats + s->max) - ts = s->stats; - if (ts == s->stats + s->start) - return NULL; - } - return ts; - -} - -static void *jbd2_seq_history_start(struct seq_file *seq, loff_t *pos) -{ - struct jbd2_stats_proc_session *s = seq->private; - struct transaction_stats_s *ts; - int l = *pos; - - if (l == 0) - return SEQ_START_TOKEN; - ts = jbd2_history_skip_empty(s, s->stats + s->start, 1); - if (!ts) - return NULL; - l--; - while (l) { - ts = jbd2_history_skip_empty(s, ++ts, 0); - if (!ts) - break; - l--; - } - return ts; -} - -static void *jbd2_seq_history_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct jbd2_stats_proc_session *s = seq->private; - struct transaction_stats_s *ts = v; - - ++*pos; - if (v == SEQ_START_TOKEN) - return jbd2_history_skip_empty(s, s->stats + s->start, 1); - else - return jbd2_history_skip_empty(s, ++ts, 0); -} - -static int jbd2_seq_history_show(struct seq_file *seq, void *v) -{ - struct transaction_stats_s *ts = v; - if (v == SEQ_START_TOKEN) { - seq_printf(seq, "%-4s %-5s %-5s %-5s %-5s %-5s %-5s %-6s %-5s " - "%-5s %-5s %-5s %-5s %-5s\n", "R/C", "tid", - "wait", "run", "lock", "flush", "log", "hndls", - "block", "inlog", "ctime", "write", "drop", - "close"); - return 0; - } - if (ts->ts_type == JBD2_STATS_RUN) - seq_printf(seq, "%-4s %-5lu %-5u %-5u %-5u %-5u %-5u " - "%-6lu %-5lu %-5lu\n", "R", ts->ts_tid, - jiffies_to_msecs(ts->u.run.rs_wait), - jiffies_to_msecs(ts->u.run.rs_running), - jiffies_to_msecs(ts->u.run.rs_locked), - jiffies_to_msecs(ts->u.run.rs_flushing), - jiffies_to_msecs(ts->u.run.rs_logging), - ts->u.run.rs_handle_count, - ts->u.run.rs_blocks, - ts->u.run.rs_blocks_logged); - else if (ts->ts_type == JBD2_STATS_CHECKPOINT) - seq_printf(seq, "%-4s %-5lu %48s %-5u %-5lu %-5lu %-5lu\n", - "C", ts->ts_tid, " ", - jiffies_to_msecs(ts->u.chp.cs_chp_time), - ts->u.chp.cs_written, ts->u.chp.cs_dropped, - ts->u.chp.cs_forced_to_close); - else - J_ASSERT(0); - return 0; -} - -static void jbd2_seq_history_stop(struct seq_file *seq, void *v) -{ -} - -static const struct seq_operations jbd2_seq_history_ops = { - .start = jbd2_seq_history_start, - .next = jbd2_seq_history_next, - .stop = jbd2_seq_history_stop, - .show = jbd2_seq_history_show, -}; - -static int jbd2_seq_history_open(struct inode *inode, struct file *file) -{ - journal_t *journal = PDE(inode)->data; - struct jbd2_stats_proc_session *s; - int rc, size; - - s = kmalloc(sizeof(*s), GFP_KERNEL); - if (s == NULL) - return -ENOMEM; - size = sizeof(struct transaction_stats_s) * journal->j_history_max; - s->stats = kmalloc(size, GFP_KERNEL); - if (s->stats == NULL) { - kfree(s); - return -ENOMEM; - } - spin_lock(&journal->j_history_lock); - memcpy(s->stats, journal->j_history, size); - s->max = journal->j_history_max; - s->start = journal->j_history_cur % s->max; - spin_unlock(&journal->j_history_lock); - - rc = seq_open(file, &jbd2_seq_history_ops); - if (rc == 0) { - struct seq_file *m = file->private_data; - m->private = s; - } else { - kfree(s->stats); - kfree(s); - } - return rc; - -} - -static int jbd2_seq_history_release(struct inode *inode, struct file *file) -{ - struct seq_file *seq = file->private_data; - struct jbd2_stats_proc_session *s = seq->private; - - kfree(s->stats); - kfree(s); - return seq_release(inode, file); -} - -static struct file_operations jbd2_seq_history_fops = { - .owner = THIS_MODULE, - .open = jbd2_seq_history_open, - .read = seq_read, - .llseek = seq_lseek, - .release = jbd2_seq_history_release, -}; - static void *jbd2_seq_info_start(struct seq_file *seq, loff_t *pos) { return *pos ? NULL : SEQ_START_TOKEN; @@ -839,29 +692,29 @@ static int jbd2_seq_info_show(struct seq_file *seq, void *v) if (v != SEQ_START_TOKEN) return 0; - seq_printf(seq, "%lu transaction, each upto %u blocks\n", + seq_printf(seq, "%lu transaction, each up to %u blocks\n", s->stats->ts_tid, s->journal->j_max_transaction_buffers); if (s->stats->ts_tid == 0) return 0; seq_printf(seq, "average: \n %ums waiting for transaction\n", - jiffies_to_msecs(s->stats->u.run.rs_wait / s->stats->ts_tid)); + jiffies_to_msecs(s->stats->run.rs_wait / s->stats->ts_tid)); seq_printf(seq, " %ums running transaction\n", - jiffies_to_msecs(s->stats->u.run.rs_running / s->stats->ts_tid)); + jiffies_to_msecs(s->stats->run.rs_running / s->stats->ts_tid)); seq_printf(seq, " %ums transaction was being locked\n", - jiffies_to_msecs(s->stats->u.run.rs_locked / s->stats->ts_tid)); + jiffies_to_msecs(s->stats->run.rs_locked / s->stats->ts_tid)); seq_printf(seq, " %ums flushing data (in ordered mode)\n", - jiffies_to_msecs(s->stats->u.run.rs_flushing / s->stats->ts_tid)); + jiffies_to_msecs(s->stats->run.rs_flushing / s->stats->ts_tid)); seq_printf(seq, " %ums logging transaction\n", - jiffies_to_msecs(s->stats->u.run.rs_logging / s->stats->ts_tid)); + jiffies_to_msecs(s->stats->run.rs_logging / s->stats->ts_tid)); seq_printf(seq, " %lluus average transaction commit time\n", div_u64(s->journal->j_average_commit_time, 1000)); seq_printf(seq, " %lu handles per transaction\n", - s->stats->u.run.rs_handle_count / s->stats->ts_tid); + s->stats->run.rs_handle_count / s->stats->ts_tid); seq_printf(seq, " %lu blocks per transaction\n", - s->stats->u.run.rs_blocks / s->stats->ts_tid); + s->stats->run.rs_blocks / s->stats->ts_tid); seq_printf(seq, " %lu logged blocks per transaction\n", - s->stats->u.run.rs_blocks_logged / s->stats->ts_tid); + s->stats->run.rs_blocks_logged / s->stats->ts_tid); return 0; } @@ -931,8 +784,6 @@ static void jbd2_stats_proc_init(journal_t *journal) { journal->j_proc_entry = proc_mkdir(journal->j_devname, proc_jbd2_stats); if (journal->j_proc_entry) { - proc_create_data("history", S_IRUGO, journal->j_proc_entry, - &jbd2_seq_history_fops, journal); proc_create_data("info", S_IRUGO, journal->j_proc_entry, &jbd2_seq_info_fops, journal); } @@ -941,27 +792,9 @@ static void jbd2_stats_proc_init(journal_t *journal) static void jbd2_stats_proc_exit(journal_t *journal) { remove_proc_entry("info", journal->j_proc_entry); - remove_proc_entry("history", journal->j_proc_entry); remove_proc_entry(journal->j_devname, proc_jbd2_stats); } -static void journal_init_stats(journal_t *journal) -{ - int size; - - if (!proc_jbd2_stats) - return; - - journal->j_history_max = 100; - size = sizeof(struct transaction_stats_s) * journal->j_history_max; - journal->j_history = kzalloc(size, GFP_KERNEL); - if (!journal->j_history) { - journal->j_history_max = 0; - return; - } - spin_lock_init(&journal->j_history_lock); -} - /* * Management for journal control blocks: functions to create and * destroy journal_t structures, and to initialise and read existing @@ -1006,7 +839,7 @@ static journal_t * journal_init_common (void) goto fail; } - journal_init_stats(journal); + spin_lock_init(&journal->j_history_lock); return journal; fail: diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 52695d3dfd0b..f1011f7f3d41 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -464,9 +464,9 @@ struct handle_s */ struct transaction_chp_stats_s { unsigned long cs_chp_time; - unsigned long cs_forced_to_close; - unsigned long cs_written; - unsigned long cs_dropped; + __u32 cs_forced_to_close; + __u32 cs_written; + __u32 cs_dropped; }; /* The transaction_t type is the guts of the journaling mechanism. It @@ -668,23 +668,16 @@ struct transaction_run_stats_s { unsigned long rs_flushing; unsigned long rs_logging; - unsigned long rs_handle_count; - unsigned long rs_blocks; - unsigned long rs_blocks_logged; + __u32 rs_handle_count; + __u32 rs_blocks; + __u32 rs_blocks_logged; }; struct transaction_stats_s { - int ts_type; unsigned long ts_tid; - union { - struct transaction_run_stats_s run; - struct transaction_chp_stats_s chp; - } u; + struct transaction_run_stats_s run; }; -#define JBD2_STATS_RUN 1 -#define JBD2_STATS_CHECKPOINT 2 - static inline unsigned long jbd2_time_diff(unsigned long start, unsigned long end) { @@ -988,12 +981,6 @@ struct journal_s /* * Journal statistics */ - struct transaction_stats_s *j_history; - int j_history_max; - int j_history_cur; - /* - * Protect the transactions statistics history - */ spinlock_t j_history_lock; struct proc_dir_entry *j_proc_entry; struct transaction_stats_s j_stats; diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h index b851f0b4701c..3c60b75adb9e 100644 --- a/include/trace/events/jbd2.h +++ b/include/trace/events/jbd2.h @@ -7,6 +7,9 @@ #include #include +struct transaction_chp_stats_s; +struct transaction_run_stats_s; + TRACE_EVENT(jbd2_checkpoint, TP_PROTO(journal_t *journal, int result), @@ -162,6 +165,81 @@ TRACE_EVENT(jbd2_submit_inode_data, jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino) ); +TRACE_EVENT(jbd2_run_stats, + TP_PROTO(dev_t dev, unsigned long tid, + struct transaction_run_stats_s *stats), + + TP_ARGS(dev, tid, stats), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( unsigned long, tid ) + __field( unsigned long, wait ) + __field( unsigned long, running ) + __field( unsigned long, locked ) + __field( unsigned long, flushing ) + __field( unsigned long, logging ) + __field( __u32, handle_count ) + __field( __u32, blocks ) + __field( __u32, blocks_logged ) + ), + + TP_fast_assign( + __entry->dev = dev; + __entry->tid = tid; + __entry->wait = stats->rs_wait; + __entry->running = stats->rs_running; + __entry->locked = stats->rs_locked; + __entry->flushing = stats->rs_flushing; + __entry->logging = stats->rs_logging; + __entry->handle_count = stats->rs_handle_count; + __entry->blocks = stats->rs_blocks; + __entry->blocks_logged = stats->rs_blocks_logged; + ), + + TP_printk("dev %s tid %lu wait %u running %u locked %u flushing %u " + "logging %u handle_count %u blocks %u blocks_logged %u", + jbd2_dev_to_name(__entry->dev), __entry->tid, + jiffies_to_msecs(__entry->wait), + jiffies_to_msecs(__entry->running), + jiffies_to_msecs(__entry->locked), + jiffies_to_msecs(__entry->flushing), + jiffies_to_msecs(__entry->logging), + __entry->handle_count, __entry->blocks, + __entry->blocks_logged) +); + +TRACE_EVENT(jbd2_checkpoint_stats, + TP_PROTO(dev_t dev, unsigned long tid, + struct transaction_chp_stats_s *stats), + + TP_ARGS(dev, tid, stats), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( unsigned long, tid ) + __field( unsigned long, chp_time ) + __field( __u32, forced_to_close ) + __field( __u32, written ) + __field( __u32, dropped ) + ), + + TP_fast_assign( + __entry->dev = dev; + __entry->tid = tid; + __entry->chp_time = stats->cs_chp_time; + __entry->forced_to_close= stats->cs_forced_to_close; + __entry->written = stats->cs_written; + __entry->dropped = stats->cs_dropped; + ), + + TP_printk("dev %s tid %lu chp_time %u forced_to_close %u " + "written %u dropped %u", + jbd2_dev_to_name(__entry->dev), __entry->tid, + jiffies_to_msecs(__entry->chp_time), + __entry->forced_to_close, __entry->written, __entry->dropped) +); + #endif /* _TRACE_JBD2_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 9fcd66e572b94974365a9119b073e0a43d496eb7 Mon Sep 17 00:00:00 2001 From: Maxime Bizon Date: Fri, 18 Sep 2009 13:04:58 +0200 Subject: MIPS: BCM63xx: Add serial driver for bcm63xx integrated UART. Signed-off-by: Maxime Bizon Acked-by: Greg Kroah-Hartman Signed-off-by: Ralf Baechle --- arch/mips/bcm63xx/Makefile | 2 +- arch/mips/bcm63xx/boards/board_bcm963xx.c | 3 + arch/mips/bcm63xx/dev-uart.c | 41 + .../include/asm/mach-bcm63xx/bcm63xx_dev_uart.h | 6 + drivers/serial/Kconfig | 19 + drivers/serial/Makefile | 1 + drivers/serial/bcm63xx_uart.c | 890 +++++++++++++++++++++ include/linux/serial_core.h | 3 + 8 files changed, 964 insertions(+), 1 deletion(-) create mode 100644 arch/mips/bcm63xx/dev-uart.c create mode 100644 arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_uart.h create mode 100644 drivers/serial/bcm63xx_uart.c (limited to 'include/linux') diff --git a/arch/mips/bcm63xx/Makefile b/arch/mips/bcm63xx/Makefile index aaa585cf26e3..cff75de8449b 100644 --- a/arch/mips/bcm63xx/Makefile +++ b/arch/mips/bcm63xx/Makefile @@ -1,5 +1,5 @@ obj-y += clk.o cpu.o cs.o gpio.o irq.o prom.o setup.o timer.o \ - dev-dsp.o dev-enet.o + dev-dsp.o dev-enet.o dev-uart.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-y += boards/ diff --git a/arch/mips/bcm63xx/boards/board_bcm963xx.c b/arch/mips/bcm63xx/boards/board_bcm963xx.c index 12add0ca9fed..5a327f3a7167 100644 --- a/arch/mips/bcm63xx/boards/board_bcm963xx.c +++ b/arch/mips/bcm63xx/boards/board_bcm963xx.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #define PFX "board_bcm963xx: " @@ -792,6 +793,8 @@ int __init board_register_devices(void) { u32 val; + bcm63xx_uart_register(); + if (board.has_enet0 && !board_get_mac_address(board.enet0.mac_addr)) bcm63xx_enet_register(0, &board.enet0); diff --git a/arch/mips/bcm63xx/dev-uart.c b/arch/mips/bcm63xx/dev-uart.c new file mode 100644 index 000000000000..5f3d89c4a988 --- /dev/null +++ b/arch/mips/bcm63xx/dev-uart.c @@ -0,0 +1,41 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 2008 Maxime Bizon + */ + +#include +#include +#include +#include +#include + +static struct resource uart_resources[] = { + { + .start = -1, /* filled at runtime */ + .end = -1, /* filled at runtime */ + .flags = IORESOURCE_MEM, + }, + { + .start = -1, /* filled at runtime */ + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device bcm63xx_uart_device = { + .name = "bcm63xx_uart", + .id = 0, + .num_resources = ARRAY_SIZE(uart_resources), + .resource = uart_resources, +}; + +int __init bcm63xx_uart_register(void) +{ + uart_resources[0].start = bcm63xx_regset_address(RSET_UART0); + uart_resources[0].end = uart_resources[0].start; + uart_resources[0].end += RSET_UART_SIZE - 1; + uart_resources[1].start = bcm63xx_get_irq_number(IRQ_UART0); + return platform_device_register(&bcm63xx_uart_device); +} diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_uart.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_uart.h new file mode 100644 index 000000000000..bf348f573bbc --- /dev/null +++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_uart.h @@ -0,0 +1,6 @@ +#ifndef BCM63XX_DEV_UART_H_ +#define BCM63XX_DEV_UART_H_ + +int bcm63xx_uart_register(void); + +#endif /* BCM63XX_DEV_UART_H_ */ diff --git a/drivers/serial/Kconfig b/drivers/serial/Kconfig index 03422ce878cf..e70712044a7e 100644 --- a/drivers/serial/Kconfig +++ b/drivers/serial/Kconfig @@ -1458,4 +1458,23 @@ config SERIAL_TIMBERDALE ---help--- Add support for UART controller on timberdale. +config SERIAL_BCM63XX + tristate "bcm63xx serial port support" + select SERIAL_CORE + depends on BCM63XX + help + If you have a bcm63xx CPU, you can enable its onboard + serial port by enabling this options. + + To compile this driver as a module, choose M here: the + module will be called bcm963xx_uart. + +config SERIAL_BCM63XX_CONSOLE + bool "Console on bcm63xx serial port" + depends on SERIAL_BCM63XX=y + select SERIAL_CORE_CONSOLE + help + If you have enabled the serial port on the bcm63xx CPU + you can make it the console by answering Y to this option. + endmenu diff --git a/drivers/serial/Makefile b/drivers/serial/Makefile index 97f6fcc8b432..d21d5dd5d048 100644 --- a/drivers/serial/Makefile +++ b/drivers/serial/Makefile @@ -34,6 +34,7 @@ obj-$(CONFIG_SERIAL_CLPS711X) += clps711x.o obj-$(CONFIG_SERIAL_PXA) += pxa.o obj-$(CONFIG_SERIAL_PNX8XXX) += pnx8xxx_uart.o obj-$(CONFIG_SERIAL_SA1100) += sa1100.o +obj-$(CONFIG_SERIAL_BCM63XX) += bcm63xx_uart.o obj-$(CONFIG_SERIAL_BFIN) += bfin_5xx.o obj-$(CONFIG_SERIAL_BFIN_SPORT) += bfin_sport_uart.o obj-$(CONFIG_SERIAL_SAMSUNG) += samsung.o diff --git a/drivers/serial/bcm63xx_uart.c b/drivers/serial/bcm63xx_uart.c new file mode 100644 index 000000000000..beddaa6e9069 --- /dev/null +++ b/drivers/serial/bcm63xx_uart.c @@ -0,0 +1,890 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Derived from many drivers using generic_serial interface. + * + * Copyright (C) 2008 Maxime Bizon + * + * Serial driver for BCM63xx integrated UART. + * + * Hardware flow control was _not_ tested since I only have RX/TX on + * my board. + */ + +#if defined(CONFIG_SERIAL_BCM63XX_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ) +#define SUPPORT_SYSRQ +#endif + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +#define BCM63XX_NR_UARTS 1 + +static struct uart_port ports[BCM63XX_NR_UARTS]; + +/* + * rx interrupt mask / stat + * + * mask: + * - rx fifo full + * - rx fifo above threshold + * - rx fifo not empty for too long + */ +#define UART_RX_INT_MASK (UART_IR_MASK(UART_IR_RXOVER) | \ + UART_IR_MASK(UART_IR_RXTHRESH) | \ + UART_IR_MASK(UART_IR_RXTIMEOUT)) + +#define UART_RX_INT_STAT (UART_IR_STAT(UART_IR_RXOVER) | \ + UART_IR_STAT(UART_IR_RXTHRESH) | \ + UART_IR_STAT(UART_IR_RXTIMEOUT)) + +/* + * tx interrupt mask / stat + * + * mask: + * - tx fifo empty + * - tx fifo below threshold + */ +#define UART_TX_INT_MASK (UART_IR_MASK(UART_IR_TXEMPTY) | \ + UART_IR_MASK(UART_IR_TXTRESH)) + +#define UART_TX_INT_STAT (UART_IR_STAT(UART_IR_TXEMPTY) | \ + UART_IR_STAT(UART_IR_TXTRESH)) + +/* + * external input interrupt + * + * mask: any edge on CTS, DCD + */ +#define UART_EXTINP_INT_MASK (UART_EXTINP_IRMASK(UART_EXTINP_IR_CTS) | \ + UART_EXTINP_IRMASK(UART_EXTINP_IR_DCD)) + +/* + * handy uart register accessor + */ +static inline unsigned int bcm_uart_readl(struct uart_port *port, + unsigned int offset) +{ + return bcm_readl(port->membase + offset); +} + +static inline void bcm_uart_writel(struct uart_port *port, + unsigned int value, unsigned int offset) +{ + bcm_writel(value, port->membase + offset); +} + +/* + * serial core request to check if uart tx fifo is empty + */ +static unsigned int bcm_uart_tx_empty(struct uart_port *port) +{ + unsigned int val; + + val = bcm_uart_readl(port, UART_IR_REG); + return (val & UART_IR_STAT(UART_IR_TXEMPTY)) ? 1 : 0; +} + +/* + * serial core request to set RTS and DTR pin state and loopback mode + */ +static void bcm_uart_set_mctrl(struct uart_port *port, unsigned int mctrl) +{ + unsigned int val; + + val = bcm_uart_readl(port, UART_MCTL_REG); + val &= ~(UART_MCTL_DTR_MASK | UART_MCTL_RTS_MASK); + /* invert of written value is reflected on the pin */ + if (!(mctrl & TIOCM_DTR)) + val |= UART_MCTL_DTR_MASK; + if (!(mctrl & TIOCM_RTS)) + val |= UART_MCTL_RTS_MASK; + bcm_uart_writel(port, val, UART_MCTL_REG); + + val = bcm_uart_readl(port, UART_CTL_REG); + if (mctrl & TIOCM_LOOP) + val |= UART_CTL_LOOPBACK_MASK; + else + val &= ~UART_CTL_LOOPBACK_MASK; + bcm_uart_writel(port, val, UART_CTL_REG); +} + +/* + * serial core request to return RI, CTS, DCD and DSR pin state + */ +static unsigned int bcm_uart_get_mctrl(struct uart_port *port) +{ + unsigned int val, mctrl; + + mctrl = 0; + val = bcm_uart_readl(port, UART_EXTINP_REG); + if (val & UART_EXTINP_RI_MASK) + mctrl |= TIOCM_RI; + if (val & UART_EXTINP_CTS_MASK) + mctrl |= TIOCM_CTS; + if (val & UART_EXTINP_DCD_MASK) + mctrl |= TIOCM_CD; + if (val & UART_EXTINP_DSR_MASK) + mctrl |= TIOCM_DSR; + return mctrl; +} + +/* + * serial core request to disable tx ASAP (used for flow control) + */ +static void bcm_uart_stop_tx(struct uart_port *port) +{ + unsigned int val; + + val = bcm_uart_readl(port, UART_CTL_REG); + val &= ~(UART_CTL_TXEN_MASK); + bcm_uart_writel(port, val, UART_CTL_REG); + + val = bcm_uart_readl(port, UART_IR_REG); + val &= ~UART_TX_INT_MASK; + bcm_uart_writel(port, val, UART_IR_REG); +} + +/* + * serial core request to (re)enable tx + */ +static void bcm_uart_start_tx(struct uart_port *port) +{ + unsigned int val; + + val = bcm_uart_readl(port, UART_IR_REG); + val |= UART_TX_INT_MASK; + bcm_uart_writel(port, val, UART_IR_REG); + + val = bcm_uart_readl(port, UART_CTL_REG); + val |= UART_CTL_TXEN_MASK; + bcm_uart_writel(port, val, UART_CTL_REG); +} + +/* + * serial core request to stop rx, called before port shutdown + */ +static void bcm_uart_stop_rx(struct uart_port *port) +{ + unsigned int val; + + val = bcm_uart_readl(port, UART_IR_REG); + val &= ~UART_RX_INT_MASK; + bcm_uart_writel(port, val, UART_IR_REG); +} + +/* + * serial core request to enable modem status interrupt reporting + */ +static void bcm_uart_enable_ms(struct uart_port *port) +{ + unsigned int val; + + val = bcm_uart_readl(port, UART_IR_REG); + val |= UART_IR_MASK(UART_IR_EXTIP); + bcm_uart_writel(port, val, UART_IR_REG); +} + +/* + * serial core request to start/stop emitting break char + */ +static void bcm_uart_break_ctl(struct uart_port *port, int ctl) +{ + unsigned long flags; + unsigned int val; + + spin_lock_irqsave(&port->lock, flags); + + val = bcm_uart_readl(port, UART_CTL_REG); + if (ctl) + val |= UART_CTL_XMITBRK_MASK; + else + val &= ~UART_CTL_XMITBRK_MASK; + bcm_uart_writel(port, val, UART_CTL_REG); + + spin_unlock_irqrestore(&port->lock, flags); +} + +/* + * return port type in string format + */ +static const char *bcm_uart_type(struct uart_port *port) +{ + return (port->type == PORT_BCM63XX) ? "bcm63xx_uart" : NULL; +} + +/* + * read all chars in rx fifo and send them to core + */ +static void bcm_uart_do_rx(struct uart_port *port) +{ + struct tty_struct *tty; + unsigned int max_count; + + /* limit number of char read in interrupt, should not be + * higher than fifo size anyway since we're much faster than + * serial port */ + max_count = 32; + tty = port->info->port.tty; + do { + unsigned int iestat, c, cstat; + char flag; + + /* get overrun/fifo empty information from ier + * register */ + iestat = bcm_uart_readl(port, UART_IR_REG); + if (!(iestat & UART_IR_STAT(UART_IR_RXNOTEMPTY))) + break; + + cstat = c = bcm_uart_readl(port, UART_FIFO_REG); + port->icount.rx++; + flag = TTY_NORMAL; + c &= 0xff; + + if (unlikely((cstat & UART_FIFO_ANYERR_MASK))) { + /* do stats first */ + if (cstat & UART_FIFO_BRKDET_MASK) { + port->icount.brk++; + if (uart_handle_break(port)) + continue; + } + + if (cstat & UART_FIFO_PARERR_MASK) + port->icount.parity++; + if (cstat & UART_FIFO_FRAMEERR_MASK) + port->icount.frame++; + + /* update flag wrt read_status_mask */ + cstat &= port->read_status_mask; + if (cstat & UART_FIFO_BRKDET_MASK) + flag = TTY_BREAK; + if (cstat & UART_FIFO_FRAMEERR_MASK) + flag = TTY_FRAME; + if (cstat & UART_FIFO_PARERR_MASK) + flag = TTY_PARITY; + } + + if (uart_handle_sysrq_char(port, c)) + continue; + + if (unlikely(iestat & UART_IR_STAT(UART_IR_RXOVER))) { + port->icount.overrun++; + tty_insert_flip_char(tty, 0, TTY_OVERRUN); + } + + if ((cstat & port->ignore_status_mask) == 0) + tty_insert_flip_char(tty, c, flag); + + } while (--max_count); + + tty_flip_buffer_push(tty); +} + +/* + * fill tx fifo with chars to send, stop when fifo is about to be full + * or when all chars have been sent. + */ +static void bcm_uart_do_tx(struct uart_port *port) +{ + struct circ_buf *xmit; + unsigned int val, max_count; + + if (port->x_char) { + bcm_uart_writel(port, port->x_char, UART_FIFO_REG); + port->icount.tx++; + port->x_char = 0; + return; + } + + if (uart_tx_stopped(port)) { + bcm_uart_stop_tx(port); + return; + } + + xmit = &port->info->xmit; + if (uart_circ_empty(xmit)) + goto txq_empty; + + val = bcm_uart_readl(port, UART_MCTL_REG); + val = (val & UART_MCTL_TXFIFOFILL_MASK) >> UART_MCTL_TXFIFOFILL_SHIFT; + max_count = port->fifosize - val; + + while (max_count--) { + unsigned int c; + + c = xmit->buf[xmit->tail]; + bcm_uart_writel(port, c, UART_FIFO_REG); + xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1); + port->icount.tx++; + if (uart_circ_empty(xmit)) + break; + } + + if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) + uart_write_wakeup(port); + + if (uart_circ_empty(xmit)) + goto txq_empty; + return; + +txq_empty: + /* nothing to send, disable transmit interrupt */ + val = bcm_uart_readl(port, UART_IR_REG); + val &= ~UART_TX_INT_MASK; + bcm_uart_writel(port, val, UART_IR_REG); + return; +} + +/* + * process uart interrupt + */ +static irqreturn_t bcm_uart_interrupt(int irq, void *dev_id) +{ + struct uart_port *port; + unsigned int irqstat; + + port = dev_id; + spin_lock(&port->lock); + + irqstat = bcm_uart_readl(port, UART_IR_REG); + if (irqstat & UART_RX_INT_STAT) + bcm_uart_do_rx(port); + + if (irqstat & UART_TX_INT_STAT) + bcm_uart_do_tx(port); + + if (irqstat & UART_IR_MASK(UART_IR_EXTIP)) { + unsigned int estat; + + estat = bcm_uart_readl(port, UART_EXTINP_REG); + if (estat & UART_EXTINP_IRSTAT(UART_EXTINP_IR_CTS)) + uart_handle_cts_change(port, + estat & UART_EXTINP_CTS_MASK); + if (estat & UART_EXTINP_IRSTAT(UART_EXTINP_IR_DCD)) + uart_handle_dcd_change(port, + estat & UART_EXTINP_DCD_MASK); + } + + spin_unlock(&port->lock); + return IRQ_HANDLED; +} + +/* + * enable rx & tx operation on uart + */ +static void bcm_uart_enable(struct uart_port *port) +{ + unsigned int val; + + val = bcm_uart_readl(port, UART_CTL_REG); + val |= (UART_CTL_BRGEN_MASK | UART_CTL_TXEN_MASK | UART_CTL_RXEN_MASK); + bcm_uart_writel(port, val, UART_CTL_REG); +} + +/* + * disable rx & tx operation on uart + */ +static void bcm_uart_disable(struct uart_port *port) +{ + unsigned int val; + + val = bcm_uart_readl(port, UART_CTL_REG); + val &= ~(UART_CTL_BRGEN_MASK | UART_CTL_TXEN_MASK | + UART_CTL_RXEN_MASK); + bcm_uart_writel(port, val, UART_CTL_REG); +} + +/* + * clear all unread data in rx fifo and unsent data in tx fifo + */ +static void bcm_uart_flush(struct uart_port *port) +{ + unsigned int val; + + /* empty rx and tx fifo */ + val = bcm_uart_readl(port, UART_CTL_REG); + val |= UART_CTL_RSTRXFIFO_MASK | UART_CTL_RSTTXFIFO_MASK; + bcm_uart_writel(port, val, UART_CTL_REG); + + /* read any pending char to make sure all irq status are + * cleared */ + (void)bcm_uart_readl(port, UART_FIFO_REG); +} + +/* + * serial core request to initialize uart and start rx operation + */ +static int bcm_uart_startup(struct uart_port *port) +{ + unsigned int val; + int ret; + + /* mask all irq and flush port */ + bcm_uart_disable(port); + bcm_uart_writel(port, 0, UART_IR_REG); + bcm_uart_flush(port); + + /* clear any pending external input interrupt */ + (void)bcm_uart_readl(port, UART_EXTINP_REG); + + /* set rx/tx fifo thresh to fifo half size */ + val = bcm_uart_readl(port, UART_MCTL_REG); + val &= ~(UART_MCTL_RXFIFOTHRESH_MASK | UART_MCTL_TXFIFOTHRESH_MASK); + val |= (port->fifosize / 2) << UART_MCTL_RXFIFOTHRESH_SHIFT; + val |= (port->fifosize / 2) << UART_MCTL_TXFIFOTHRESH_SHIFT; + bcm_uart_writel(port, val, UART_MCTL_REG); + + /* set rx fifo timeout to 1 char time */ + val = bcm_uart_readl(port, UART_CTL_REG); + val &= ~UART_CTL_RXTMOUTCNT_MASK; + val |= 1 << UART_CTL_RXTMOUTCNT_SHIFT; + bcm_uart_writel(port, val, UART_CTL_REG); + + /* report any edge on dcd and cts */ + val = UART_EXTINP_INT_MASK; + val |= UART_EXTINP_DCD_NOSENSE_MASK; + val |= UART_EXTINP_CTS_NOSENSE_MASK; + bcm_uart_writel(port, val, UART_EXTINP_REG); + + /* register irq and enable rx interrupts */ + ret = request_irq(port->irq, bcm_uart_interrupt, 0, + bcm_uart_type(port), port); + if (ret) + return ret; + bcm_uart_writel(port, UART_RX_INT_MASK, UART_IR_REG); + bcm_uart_enable(port); + return 0; +} + +/* + * serial core request to flush & disable uart + */ +static void bcm_uart_shutdown(struct uart_port *port) +{ + unsigned long flags; + + spin_lock_irqsave(&port->lock, flags); + bcm_uart_writel(port, 0, UART_IR_REG); + spin_unlock_irqrestore(&port->lock, flags); + + bcm_uart_disable(port); + bcm_uart_flush(port); + free_irq(port->irq, port); +} + +/* + * serial core request to change current uart setting + */ +static void bcm_uart_set_termios(struct uart_port *port, + struct ktermios *new, + struct ktermios *old) +{ + unsigned int ctl, baud, quot, ier; + unsigned long flags; + + spin_lock_irqsave(&port->lock, flags); + + /* disable uart while changing speed */ + bcm_uart_disable(port); + bcm_uart_flush(port); + + /* update Control register */ + ctl = bcm_uart_readl(port, UART_CTL_REG); + ctl &= ~UART_CTL_BITSPERSYM_MASK; + + switch (new->c_cflag & CSIZE) { + case CS5: + ctl |= (0 << UART_CTL_BITSPERSYM_SHIFT); + break; + case CS6: + ctl |= (1 << UART_CTL_BITSPERSYM_SHIFT); + break; + case CS7: + ctl |= (2 << UART_CTL_BITSPERSYM_SHIFT); + break; + default: + ctl |= (3 << UART_CTL_BITSPERSYM_SHIFT); + break; + } + + ctl &= ~UART_CTL_STOPBITS_MASK; + if (new->c_cflag & CSTOPB) + ctl |= UART_CTL_STOPBITS_2; + else + ctl |= UART_CTL_STOPBITS_1; + + ctl &= ~(UART_CTL_RXPAREN_MASK | UART_CTL_TXPAREN_MASK); + if (new->c_cflag & PARENB) + ctl |= (UART_CTL_RXPAREN_MASK | UART_CTL_TXPAREN_MASK); + ctl &= ~(UART_CTL_RXPAREVEN_MASK | UART_CTL_TXPAREVEN_MASK); + if (new->c_cflag & PARODD) + ctl |= (UART_CTL_RXPAREVEN_MASK | UART_CTL_TXPAREVEN_MASK); + bcm_uart_writel(port, ctl, UART_CTL_REG); + + /* update Baudword register */ + baud = uart_get_baud_rate(port, new, old, 0, port->uartclk / 16); + quot = uart_get_divisor(port, baud) - 1; + bcm_uart_writel(port, quot, UART_BAUD_REG); + + /* update Interrupt register */ + ier = bcm_uart_readl(port, UART_IR_REG); + + ier &= ~UART_IR_MASK(UART_IR_EXTIP); + if (UART_ENABLE_MS(port, new->c_cflag)) + ier |= UART_IR_MASK(UART_IR_EXTIP); + + bcm_uart_writel(port, ier, UART_IR_REG); + + /* update read/ignore mask */ + port->read_status_mask = UART_FIFO_VALID_MASK; + if (new->c_iflag & INPCK) { + port->read_status_mask |= UART_FIFO_FRAMEERR_MASK; + port->read_status_mask |= UART_FIFO_PARERR_MASK; + } + if (new->c_iflag & (BRKINT)) + port->read_status_mask |= UART_FIFO_BRKDET_MASK; + + port->ignore_status_mask = 0; + if (new->c_iflag & IGNPAR) + port->ignore_status_mask |= UART_FIFO_PARERR_MASK; + if (new->c_iflag & IGNBRK) + port->ignore_status_mask |= UART_FIFO_BRKDET_MASK; + if (!(new->c_cflag & CREAD)) + port->ignore_status_mask |= UART_FIFO_VALID_MASK; + + uart_update_timeout(port, new->c_cflag, baud); + bcm_uart_enable(port); + spin_unlock_irqrestore(&port->lock, flags); +} + +/* + * serial core request to claim uart iomem + */ +static int bcm_uart_request_port(struct uart_port *port) +{ + unsigned int size; + + size = RSET_UART_SIZE; + if (!request_mem_region(port->mapbase, size, "bcm63xx")) { + dev_err(port->dev, "Memory region busy\n"); + return -EBUSY; + } + + port->membase = ioremap(port->mapbase, size); + if (!port->membase) { + dev_err(port->dev, "Unable to map registers\n"); + release_mem_region(port->mapbase, size); + return -EBUSY; + } + return 0; +} + +/* + * serial core request to release uart iomem + */ +static void bcm_uart_release_port(struct uart_port *port) +{ + release_mem_region(port->mapbase, RSET_UART_SIZE); + iounmap(port->membase); +} + +/* + * serial core request to do any port required autoconfiguration + */ +static void bcm_uart_config_port(struct uart_port *port, int flags) +{ + if (flags & UART_CONFIG_TYPE) { + if (bcm_uart_request_port(port)) + return; + port->type = PORT_BCM63XX; + } +} + +/* + * serial core request to check that port information in serinfo are + * suitable + */ +static int bcm_uart_verify_port(struct uart_port *port, + struct serial_struct *serinfo) +{ + if (port->type != PORT_BCM63XX) + return -EINVAL; + if (port->irq != serinfo->irq) + return -EINVAL; + if (port->iotype != serinfo->io_type) + return -EINVAL; + if (port->mapbase != (unsigned long)serinfo->iomem_base) + return -EINVAL; + return 0; +} + +/* serial core callbacks */ +static struct uart_ops bcm_uart_ops = { + .tx_empty = bcm_uart_tx_empty, + .get_mctrl = bcm_uart_get_mctrl, + .set_mctrl = bcm_uart_set_mctrl, + .start_tx = bcm_uart_start_tx, + .stop_tx = bcm_uart_stop_tx, + .stop_rx = bcm_uart_stop_rx, + .enable_ms = bcm_uart_enable_ms, + .break_ctl = bcm_uart_break_ctl, + .startup = bcm_uart_startup, + .shutdown = bcm_uart_shutdown, + .set_termios = bcm_uart_set_termios, + .type = bcm_uart_type, + .release_port = bcm_uart_release_port, + .request_port = bcm_uart_request_port, + .config_port = bcm_uart_config_port, + .verify_port = bcm_uart_verify_port, +}; + + + +#ifdef CONFIG_SERIAL_BCM63XX_CONSOLE +static inline void wait_for_xmitr(struct uart_port *port) +{ + unsigned int tmout; + + /* Wait up to 10ms for the character(s) to be sent. */ + tmout = 10000; + while (--tmout) { + unsigned int val; + + val = bcm_uart_readl(port, UART_IR_REG); + if (val & UART_IR_STAT(UART_IR_TXEMPTY)) + break; + udelay(1); + } + + /* Wait up to 1s for flow control if necessary */ + if (port->flags & UPF_CONS_FLOW) { + tmout = 1000000; + while (--tmout) { + unsigned int val; + + val = bcm_uart_readl(port, UART_EXTINP_REG); + if (val & UART_EXTINP_CTS_MASK) + break; + udelay(1); + } + } +} + +/* + * output given char + */ +static void bcm_console_putchar(struct uart_port *port, int ch) +{ + wait_for_xmitr(port); + bcm_uart_writel(port, ch, UART_FIFO_REG); +} + +/* + * console core request to output given string + */ +static void bcm_console_write(struct console *co, const char *s, + unsigned int count) +{ + struct uart_port *port; + unsigned long flags; + int locked; + + port = &ports[co->index]; + + local_irq_save(flags); + if (port->sysrq) { + /* bcm_uart_interrupt() already took the lock */ + locked = 0; + } else if (oops_in_progress) { + locked = spin_trylock(&port->lock); + } else { + spin_lock(&port->lock); + locked = 1; + } + + /* call helper to deal with \r\n */ + uart_console_write(port, s, count, bcm_console_putchar); + + /* and wait for char to be transmitted */ + wait_for_xmitr(port); + + if (locked) + spin_unlock(&port->lock); + local_irq_restore(flags); +} + +/* + * console core request to setup given console, find matching uart + * port and setup it. + */ +static int bcm_console_setup(struct console *co, char *options) +{ + struct uart_port *port; + int baud = 9600; + int bits = 8; + int parity = 'n'; + int flow = 'n'; + + if (co->index < 0 || co->index >= BCM63XX_NR_UARTS) + return -EINVAL; + port = &ports[co->index]; + if (!port->membase) + return -ENODEV; + if (options) + uart_parse_options(options, &baud, &parity, &bits, &flow); + + return uart_set_options(port, co, baud, parity, bits, flow); +} + +static struct uart_driver bcm_uart_driver; + +static struct console bcm63xx_console = { + .name = "ttyS", + .write = bcm_console_write, + .device = uart_console_device, + .setup = bcm_console_setup, + .flags = CON_PRINTBUFFER, + .index = -1, + .data = &bcm_uart_driver, +}; + +static int __init bcm63xx_console_init(void) +{ + register_console(&bcm63xx_console); + return 0; +} + +console_initcall(bcm63xx_console_init); + +#define BCM63XX_CONSOLE (&bcm63xx_console) +#else +#define BCM63XX_CONSOLE NULL +#endif /* CONFIG_SERIAL_BCM63XX_CONSOLE */ + +static struct uart_driver bcm_uart_driver = { + .owner = THIS_MODULE, + .driver_name = "bcm63xx_uart", + .dev_name = "ttyS", + .major = TTY_MAJOR, + .minor = 64, + .nr = 1, + .cons = BCM63XX_CONSOLE, +}; + +/* + * platform driver probe/remove callback + */ +static int __devinit bcm_uart_probe(struct platform_device *pdev) +{ + struct resource *res_mem, *res_irq; + struct uart_port *port; + struct clk *clk; + int ret; + + if (pdev->id < 0 || pdev->id >= BCM63XX_NR_UARTS) + return -EINVAL; + + if (ports[pdev->id].membase) + return -EBUSY; + + res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res_mem) + return -ENODEV; + + res_irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); + if (!res_irq) + return -ENODEV; + + clk = clk_get(&pdev->dev, "periph"); + if (IS_ERR(clk)) + return -ENODEV; + + port = &ports[pdev->id]; + memset(port, 0, sizeof(*port)); + port->iotype = UPIO_MEM; + port->mapbase = res_mem->start; + port->irq = res_irq->start; + port->ops = &bcm_uart_ops; + port->flags = UPF_BOOT_AUTOCONF; + port->dev = &pdev->dev; + port->fifosize = 16; + port->uartclk = clk_get_rate(clk) / 2; + clk_put(clk); + + ret = uart_add_one_port(&bcm_uart_driver, port); + if (ret) { + kfree(port); + return ret; + } + platform_set_drvdata(pdev, port); + return 0; +} + +static int __devexit bcm_uart_remove(struct platform_device *pdev) +{ + struct uart_port *port; + + port = platform_get_drvdata(pdev); + uart_remove_one_port(&bcm_uart_driver, port); + platform_set_drvdata(pdev, NULL); + /* mark port as free */ + ports[pdev->id].membase = 0; + return 0; +} + +/* + * platform driver stuff + */ +static struct platform_driver bcm_uart_platform_driver = { + .probe = bcm_uart_probe, + .remove = __devexit_p(bcm_uart_remove), + .driver = { + .owner = THIS_MODULE, + .name = "bcm63xx_uart", + }, +}; + +static int __init bcm_uart_init(void) +{ + int ret; + + ret = uart_register_driver(&bcm_uart_driver); + if (ret) + return ret; + + ret = platform_driver_register(&bcm_uart_platform_driver); + if (ret) + uart_unregister_driver(&bcm_uart_driver); + + return ret; +} + +static void __exit bcm_uart_exit(void) +{ + platform_driver_unregister(&bcm_uart_platform_driver); + uart_unregister_driver(&bcm_uart_driver); +} + +module_init(bcm_uart_init); +module_exit(bcm_uart_exit); + +MODULE_AUTHOR("Maxime Bizon "); +MODULE_DESCRIPTION("Broadcom 63 -- cgit v1.2.3 From b7058842c940ad2c08dd829b21e5c92ebe3b8758 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 30 Sep 2009 16:12:20 -0700 Subject: net: Make setsockopt() optlen be unsigned. This provides safety against negative optlen at the type level instead of depending upon (sometimes non-trivial) checks against this sprinkled all over the the place, in each and every implementation. Based upon work done by Arjan van de Ven and feedback from Linus Torvalds. Signed-off-by: David S. Miller --- drivers/atm/ambassador.c | 8 ----- drivers/atm/eni.c | 2 +- drivers/atm/firestream.c | 2 +- drivers/atm/fore200e.c | 2 +- drivers/atm/horizon.c | 2 +- drivers/atm/iphase.c | 2 +- drivers/atm/zatm.c | 2 +- drivers/isdn/mISDN/socket.c | 2 +- drivers/net/pppol2tp.c | 2 +- include/linux/atmdev.h | 2 +- include/linux/mroute.h | 4 +-- include/linux/mroute6.h | 4 +-- include/linux/net.h | 8 ++--- include/linux/netfilter.h | 4 +-- include/net/compat.h | 4 +-- include/net/inet_connection_sock.h | 6 ++-- include/net/ip.h | 4 +-- include/net/ipv6.h | 4 +-- include/net/sctp/structs.h | 4 +-- include/net/sock.h | 12 ++++---- include/net/tcp.h | 4 +-- include/net/udp.h | 2 +- net/atm/common.c | 2 +- net/atm/common.h | 2 +- net/atm/pvc.c | 2 +- net/atm/svc.c | 2 +- net/ax25/af_ax25.c | 2 +- net/bluetooth/hci_sock.c | 2 +- net/bluetooth/l2cap.c | 4 +-- net/bluetooth/rfcomm/sock.c | 4 +-- net/bluetooth/sco.c | 2 +- net/can/raw.c | 2 +- net/compat.c | 12 ++++---- net/core/sock.c | 8 ++--- net/dccp/dccp.h | 4 +-- net/dccp/proto.c | 10 +++--- net/decnet/af_decnet.c | 6 ++-- net/ieee802154/dgram.c | 2 +- net/ieee802154/raw.c | 2 +- net/ipv4/inet_connection_sock.c | 2 +- net/ipv4/ip_sockglue.c | 6 ++-- net/ipv4/ipmr.c | 2 +- net/ipv4/raw.c | 6 ++-- net/ipv4/tcp.c | 6 ++-- net/ipv4/udp.c | 6 ++-- net/ipv4/udp_impl.h | 4 +-- net/ipv6/ip6mr.c | 2 +- net/ipv6/ipv6_sockglue.c | 6 ++-- net/ipv6/raw.c | 6 ++-- net/ipv6/udp.c | 4 +-- net/ipv6/udp_impl.h | 4 +-- net/ipx/af_ipx.c | 2 +- net/irda/af_irda.c | 2 +- net/iucv/af_iucv.c | 2 +- net/llc/af_llc.c | 2 +- net/netfilter/nf_sockopt.c | 4 +-- net/netlink/af_netlink.c | 2 +- net/netrom/af_netrom.c | 2 +- net/packet/af_packet.c | 2 +- net/phonet/pep.c | 2 +- net/rds/af_rds.c | 2 +- net/rose/af_rose.c | 2 +- net/rxrpc/af_rxrpc.c | 2 +- net/sctp/socket.c | 62 ++++++++++++++++++++------------------ net/socket.c | 2 +- net/tipc/socket.c | 2 +- net/x25/af_x25.c | 2 +- 67 files changed, 149 insertions(+), 153 deletions(-) (limited to 'include/linux') diff --git a/drivers/atm/ambassador.c b/drivers/atm/ambassador.c index 703364b52170..66e181345b3a 100644 --- a/drivers/atm/ambassador.c +++ b/drivers/atm/ambassador.c @@ -1306,14 +1306,6 @@ static void amb_close (struct atm_vcc * atm_vcc) { return; } -/********** Set socket options for a VC **********/ - -// int amb_getsockopt (struct atm_vcc * atm_vcc, int level, int optname, void * optval, int optlen); - -/********** Set socket options for a VC **********/ - -// int amb_setsockopt (struct atm_vcc * atm_vcc, int level, int optname, void * optval, int optlen); - /********** Send **********/ static int amb_send (struct atm_vcc * atm_vcc, struct sk_buff * skb) { diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c index 5503bfc8e132..0c3026145443 100644 --- a/drivers/atm/eni.c +++ b/drivers/atm/eni.c @@ -2031,7 +2031,7 @@ static int eni_getsockopt(struct atm_vcc *vcc,int level,int optname, static int eni_setsockopt(struct atm_vcc *vcc,int level,int optname, - void __user *optval,int optlen) + void __user *optval,unsigned int optlen) { return -EINVAL; } diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c index b119640e1ee9..cd5049af47a9 100644 --- a/drivers/atm/firestream.c +++ b/drivers/atm/firestream.c @@ -1244,7 +1244,7 @@ static int fs_getsockopt(struct atm_vcc *vcc,int level,int optname, static int fs_setsockopt(struct atm_vcc *vcc,int level,int optname, - void __user *optval,int optlen) + void __user *optval,unsigned int optlen) { func_enter (); func_exit (); diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c index 10f000dbe448..f766cc46b4c4 100644 --- a/drivers/atm/fore200e.c +++ b/drivers/atm/fore200e.c @@ -1795,7 +1795,7 @@ fore200e_getsockopt(struct atm_vcc* vcc, int level, int optname, void __user *op static int -fore200e_setsockopt(struct atm_vcc* vcc, int level, int optname, void __user *optval, int optlen) +fore200e_setsockopt(struct atm_vcc* vcc, int level, int optname, void __user *optval, unsigned int optlen) { /* struct fore200e* fore200e = FORE200E_DEV(vcc->dev); */ diff --git a/drivers/atm/horizon.c b/drivers/atm/horizon.c index 01ce241dbeae..4e49021e67ee 100644 --- a/drivers/atm/horizon.c +++ b/drivers/atm/horizon.c @@ -2590,7 +2590,7 @@ static int hrz_getsockopt (struct atm_vcc * atm_vcc, int level, int optname, } static int hrz_setsockopt (struct atm_vcc * atm_vcc, int level, int optname, - void *optval, int optlen) { + void *optval, unsigned int optlen) { hrz_dev * dev = HRZ_DEV(atm_vcc->dev); PRINTD (DBG_FLOW|DBG_VCC, "hrz_setsockopt"); switch (level) { diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c index 78c9736c3579..b2c1b37ab2e4 100644 --- a/drivers/atm/iphase.c +++ b/drivers/atm/iphase.c @@ -2862,7 +2862,7 @@ static int ia_getsockopt(struct atm_vcc *vcc, int level, int optname, } static int ia_setsockopt(struct atm_vcc *vcc, int level, int optname, - void __user *optval, int optlen) + void __user *optval, unsigned int optlen) { IF_EVENT(printk(">ia_setsockopt\n");) return -EINVAL; diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c index 752b1ba81f7e..2e9635be048c 100644 --- a/drivers/atm/zatm.c +++ b/drivers/atm/zatm.c @@ -1517,7 +1517,7 @@ static int zatm_getsockopt(struct atm_vcc *vcc,int level,int optname, static int zatm_setsockopt(struct atm_vcc *vcc,int level,int optname, - void __user *optval,int optlen) + void __user *optval,unsigned int optlen) { return -EINVAL; } diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c index c36f52137456..feb0fa45b664 100644 --- a/drivers/isdn/mISDN/socket.c +++ b/drivers/isdn/mISDN/socket.c @@ -415,7 +415,7 @@ data_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) } static int data_sock_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int len) + char __user *optval, unsigned int len) { struct sock *sk = sock->sk; int err = 0, opt = 0; diff --git a/drivers/net/pppol2tp.c b/drivers/net/pppol2tp.c index cc394d073755..5910df60c93e 100644 --- a/drivers/net/pppol2tp.c +++ b/drivers/net/pppol2tp.c @@ -2179,7 +2179,7 @@ static int pppol2tp_session_setsockopt(struct sock *sk, * session or the special tunnel type. */ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct pppol2tp_session *session = sk->sk_user_data; diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index 086e5c362d3a..817b23705c91 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -397,7 +397,7 @@ struct atmdev_ops { /* only send is required */ int (*getsockopt)(struct atm_vcc *vcc,int level,int optname, void __user *optval,int optlen); int (*setsockopt)(struct atm_vcc *vcc,int level,int optname, - void __user *optval,int optlen); + void __user *optval,unsigned int optlen); int (*send)(struct atm_vcc *vcc,struct sk_buff *skb); int (*send_oam)(struct atm_vcc *vcc,void *cell,int flags); void (*phy_put)(struct atm_dev *dev,unsigned char value, diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 0d45b4e8d367..08bc776d05e2 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -145,14 +145,14 @@ static inline int ip_mroute_opt(int opt) #endif #ifdef CONFIG_IP_MROUTE -extern int ip_mroute_setsockopt(struct sock *, int, char __user *, int); +extern int ip_mroute_setsockopt(struct sock *, int, char __user *, unsigned int); extern int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *); extern int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg); extern int ip_mr_init(void); #else static inline int ip_mroute_setsockopt(struct sock *sock, - int optname, char __user *optval, int optlen) + int optname, char __user *optval, unsigned int optlen) { return -ENOPROTOOPT; } diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index 43dc97e32183..b191865a6ca3 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -134,7 +134,7 @@ static inline int ip6_mroute_opt(int opt) struct sock; #ifdef CONFIG_IPV6_MROUTE -extern int ip6_mroute_setsockopt(struct sock *, int, char __user *, int); +extern int ip6_mroute_setsockopt(struct sock *, int, char __user *, unsigned int); extern int ip6_mroute_getsockopt(struct sock *, int, char __user *, int __user *); extern int ip6_mr_input(struct sk_buff *skb); extern int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg); @@ -143,7 +143,7 @@ extern void ip6_mr_cleanup(void); #else static inline int ip6_mroute_setsockopt(struct sock *sock, - int optname, char __user *optval, int optlen) + int optname, char __user *optval, unsigned int optlen) { return -ENOPROTOOPT; } diff --git a/include/linux/net.h b/include/linux/net.h index 9040a10584f7..529a0931711d 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -178,11 +178,11 @@ struct proto_ops { int (*listen) (struct socket *sock, int len); int (*shutdown) (struct socket *sock, int flags); int (*setsockopt)(struct socket *sock, int level, - int optname, char __user *optval, int optlen); + int optname, char __user *optval, unsigned int optlen); int (*getsockopt)(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); int (*compat_setsockopt)(struct socket *sock, int level, - int optname, char __user *optval, int optlen); + int optname, char __user *optval, unsigned int optlen); int (*compat_getsockopt)(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); int (*sendmsg) (struct kiocb *iocb, struct socket *sock, @@ -256,7 +256,7 @@ extern int kernel_getpeername(struct socket *sock, struct sockaddr *addr, extern int kernel_getsockopt(struct socket *sock, int level, int optname, char *optval, int *optlen); extern int kernel_setsockopt(struct socket *sock, int level, int optname, - char *optval, int optlen); + char *optval, unsigned int optlen); extern int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); extern int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg); @@ -313,7 +313,7 @@ SOCKCALL_WRAP(name, compat_ioctl, (struct socket *sock, unsigned int cmd, \ SOCKCALL_WRAP(name, listen, (struct socket *sock, int len), (sock, len)) \ SOCKCALL_WRAP(name, shutdown, (struct socket *sock, int flags), (sock, flags)) \ SOCKCALL_WRAP(name, setsockopt, (struct socket *sock, int level, int optname, \ - char __user *optval, int optlen), (sock, level, optname, optval, optlen)) \ + char __user *optval, unsigned int optlen), (sock, level, optname, optval, optlen)) \ SOCKCALL_WRAP(name, getsockopt, (struct socket *sock, int level, int optname, \ char __user *optval, int __user *optlen), (sock, level, optname, optval, optlen)) \ SOCKCALL_WRAP(name, sendmsg, (struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t len), \ diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 48cfe51bfddc..6132b5e6d9d3 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -221,12 +221,12 @@ __ret;}) /* Call setsockopt() */ int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, - int len); + unsigned int len); int nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, int *len); int compat_nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, - char __user *opt, int len); + char __user *opt, unsigned int len); int compat_nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, int *len); diff --git a/include/net/compat.h b/include/net/compat.h index 5bbf8bf9efea..7c3002832d05 100644 --- a/include/net/compat.h +++ b/include/net/compat.h @@ -40,8 +40,8 @@ extern int put_cmsg_compat(struct msghdr*, int, int, int, void *); extern int cmsghdr_from_user_compat_to_kern(struct msghdr *, struct sock *, unsigned char *, int); -extern int compat_mc_setsockopt(struct sock *, int, int, char __user *, int, - int (*)(struct sock *, int, int, char __user *, int)); +extern int compat_mc_setsockopt(struct sock *, int, int, char __user *, unsigned int, + int (*)(struct sock *, int, int, char __user *, unsigned int)); extern int compat_mc_getsockopt(struct sock *, int, int, char __user *, int __user *, int (*)(struct sock *, int, int, char __user *, int __user *)); diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 03cffd9f64e3..696d6e4ce68a 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -48,13 +48,13 @@ struct inet_connection_sock_af_ops { u16 net_header_len; u16 sockaddr_len; int (*setsockopt)(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); #ifdef CONFIG_COMPAT int (*compat_setsockopt)(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); int (*compat_getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); @@ -332,5 +332,5 @@ extern void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr); extern int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); #endif /* _INET_CONNECTION_SOCK_H */ diff --git a/include/net/ip.h b/include/net/ip.h index 5b26a0bd178e..2f47e5482b55 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -381,10 +381,10 @@ extern int ip_options_rcv_srr(struct sk_buff *skb); extern void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb); extern int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc); -extern int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, int optlen); +extern int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); extern int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int compat_ip_setsockopt(struct sock *sk, int level, - int optname, char __user *optval, int optlen); + int optname, char __user *optval, unsigned int optlen); extern int compat_ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *)); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index ad9a51130254..8c31d8a0c1fe 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -550,7 +550,7 @@ extern int ipv6_find_tlv(struct sk_buff *skb, int offset, int type); extern int ipv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, - int optlen); + unsigned int optlen); extern int ipv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, @@ -559,7 +559,7 @@ extern int compat_ipv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, - int optlen); + unsigned int optlen); extern int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 42d00ced5eb8..6e5f0e0c7967 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -544,7 +544,7 @@ struct sctp_af { int level, int optname, char __user *optval, - int optlen); + unsigned int optlen); int (*getsockopt) (struct sock *sk, int level, int optname, @@ -554,7 +554,7 @@ struct sctp_af { int level, int optname, char __user *optval, - int optlen); + unsigned int optlen); int (*compat_getsockopt) (struct sock *sk, int level, int optname, diff --git a/include/net/sock.h b/include/net/sock.h index 950409dcec3d..1621935aad5b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -624,7 +624,7 @@ struct proto { void (*shutdown)(struct sock *sk, int how); int (*setsockopt)(struct sock *sk, int level, int optname, char __user *optval, - int optlen); + unsigned int optlen); int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *option); @@ -632,7 +632,7 @@ struct proto { int (*compat_setsockopt)(struct sock *sk, int level, int optname, char __user *optval, - int optlen); + unsigned int optlen); int (*compat_getsockopt)(struct sock *sk, int level, int optname, char __user *optval, @@ -951,7 +951,7 @@ extern void sock_rfree(struct sk_buff *skb); extern int sock_setsockopt(struct socket *sock, int level, int op, char __user *optval, - int optlen); + unsigned int optlen); extern int sock_getsockopt(struct socket *sock, int level, int op, char __user *optval, @@ -993,7 +993,7 @@ extern int sock_no_shutdown(struct socket *, int); extern int sock_no_getsockopt(struct socket *, int , int, char __user *, int __user *); extern int sock_no_setsockopt(struct socket *, int, int, - char __user *, int); + char __user *, unsigned int); extern int sock_no_sendmsg(struct kiocb *, struct socket *, struct msghdr *, size_t); extern int sock_no_recvmsg(struct kiocb *, struct socket *, @@ -1015,11 +1015,11 @@ extern int sock_common_getsockopt(struct socket *sock, int level, int optname, extern int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size, int flags); extern int sock_common_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); extern int compat_sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); extern int compat_sock_common_setsockopt(struct socket *sock, int level, - int optname, char __user *optval, int optlen); + int optname, char __user *optval, unsigned int optlen); extern void sk_common_release(struct sock *sk); diff --git a/include/net/tcp.h b/include/net/tcp.h index 56b76027b85e..03a49c703377 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -394,13 +394,13 @@ extern int tcp_getsockopt(struct sock *sk, int level, int __user *optlen); extern int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, - int optlen); + unsigned int optlen); extern int compat_tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int compat_tcp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); extern void tcp_set_keepalive(struct sock *sk, int val); extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, diff --git a/include/net/udp.h b/include/net/udp.h index 5fb029f817a3..f98abd2ce709 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -144,7 +144,7 @@ extern unsigned int udp_poll(struct file *file, struct socket *sock, extern int udp_lib_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int udp_lib_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen, + char __user *optval, unsigned int optlen, int (*push_pending_frames)(struct sock *)); extern struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, diff --git a/net/atm/common.c b/net/atm/common.c index 8c4d843eb17f..950bd16d2383 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -679,7 +679,7 @@ static int check_qos(const struct atm_qos *qos) } int vcc_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct atm_vcc *vcc; unsigned long value; diff --git a/net/atm/common.h b/net/atm/common.h index 92e2981f479f..f48a76b6cdf4 100644 --- a/net/atm/common.h +++ b/net/atm/common.h @@ -21,7 +21,7 @@ unsigned int vcc_poll(struct file *file, struct socket *sock, poll_table *wait); int vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int vcc_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int vcc_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); int vcc_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); diff --git a/net/atm/pvc.c b/net/atm/pvc.c index e1d22d9430dd..d4c024504f99 100644 --- a/net/atm/pvc.c +++ b/net/atm/pvc.c @@ -59,7 +59,7 @@ static int pvc_connect(struct socket *sock,struct sockaddr *sockaddr, } static int pvc_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int error; diff --git a/net/atm/svc.c b/net/atm/svc.c index 7b831b526d0b..f90d143c4b25 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -446,7 +446,7 @@ int svc_change_qos(struct atm_vcc *vcc,struct atm_qos *qos) static int svc_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct atm_vcc *vcc = ATM_SD(sock); diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 4102de1022ee..cd1c3dc0fe01 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -534,7 +534,7 @@ ax25_cb *ax25_create_cb(void) */ static int ax25_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; ax25_cb *ax25; diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 4f9621f759a0..75302a986067 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -466,7 +466,7 @@ drop: goto done; } -static int hci_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int len) +static int hci_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int len) { struct hci_ufilter uf = { .opcode = 0 }; struct sock *sk = sock->sk; diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index b03012564647..555d9da1869b 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -1698,7 +1698,7 @@ static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct ms return bt_sock_recvmsg(iocb, sock, msg, len, flags); } -static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, int optlen) +static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct l2cap_options opts; @@ -1755,7 +1755,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __us return err; } -static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) +static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct bt_security sec; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 0b85e8116859..8a20aaf1f231 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -730,7 +730,7 @@ out: return copied ? : err; } -static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, int optlen) +static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int err = 0; @@ -766,7 +766,7 @@ static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, char __u return err; } -static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) +static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct bt_security sec; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 13c27f17192c..77f4153bdb5e 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -644,7 +644,7 @@ static int sco_sock_sendmsg(struct kiocb *iocb, struct socket *sock, return err; } -static int sco_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) +static int sco_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int err = 0; diff --git a/net/can/raw.c b/net/can/raw.c index db3152df7d2b..b5e897922d32 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -411,7 +411,7 @@ static int raw_getname(struct socket *sock, struct sockaddr *uaddr, } static int raw_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); diff --git a/net/compat.c b/net/compat.c index 12728b17a226..a407c3addbae 100644 --- a/net/compat.c +++ b/net/compat.c @@ -331,7 +331,7 @@ struct compat_sock_fprog { }; static int do_set_attach_filter(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct compat_sock_fprog __user *fprog32 = (struct compat_sock_fprog __user *)optval; struct sock_fprog __user *kfprog = compat_alloc_user_space(sizeof(struct sock_fprog)); @@ -351,7 +351,7 @@ static int do_set_attach_filter(struct socket *sock, int level, int optname, } static int do_set_sock_timeout(struct socket *sock, int level, - int optname, char __user *optval, int optlen) + int optname, char __user *optval, unsigned int optlen) { struct compat_timeval __user *up = (struct compat_timeval __user *) optval; struct timeval ktime; @@ -373,7 +373,7 @@ static int do_set_sock_timeout(struct socket *sock, int level, } static int compat_sock_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (optname == SO_ATTACH_FILTER) return do_set_attach_filter(sock, level, optname, @@ -385,7 +385,7 @@ static int compat_sock_setsockopt(struct socket *sock, int level, int optname, } asmlinkage long compat_sys_setsockopt(int fd, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int err; struct socket *sock; @@ -558,8 +558,8 @@ struct compat_group_filter { int compat_mc_setsockopt(struct sock *sock, int level, int optname, - char __user *optval, int optlen, - int (*setsockopt)(struct sock *,int,int,char __user *,int)) + char __user *optval, unsigned int optlen, + int (*setsockopt)(struct sock *,int,int,char __user *,unsigned int)) { char __user *koptval = optval; int koptlen = optlen; diff --git a/net/core/sock.c b/net/core/sock.c index 524712a7b154..77fbfed332e8 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -446,7 +446,7 @@ static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool) */ int sock_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int val; @@ -1697,7 +1697,7 @@ int sock_no_shutdown(struct socket *sock, int how) EXPORT_SYMBOL(sock_no_shutdown); int sock_no_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { return -EOPNOTSUPP; } @@ -2018,7 +2018,7 @@ EXPORT_SYMBOL(sock_common_recvmsg); * Set socket options on an inet socket. */ int sock_common_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; @@ -2028,7 +2028,7 @@ EXPORT_SYMBOL(sock_common_setsockopt); #ifdef CONFIG_COMPAT int compat_sock_common_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index d6bc47363b1c..5ef32c2f0d6a 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -290,14 +290,14 @@ extern int dccp_disconnect(struct sock *sk, int flags); extern int dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); #ifdef CONFIG_COMPAT extern int compat_dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int compat_dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); #endif extern int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg); extern int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, diff --git a/net/dccp/proto.c b/net/dccp/proto.c index bc4467082a00..a156319fd0ac 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -393,7 +393,7 @@ out: EXPORT_SYMBOL_GPL(dccp_ioctl); static int dccp_setsockopt_service(struct sock *sk, const __be32 service, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct dccp_sock *dp = dccp_sk(sk); struct dccp_service_list *sl = NULL; @@ -464,7 +464,7 @@ static int dccp_setsockopt_cscov(struct sock *sk, int cscov, bool rx) } static int dccp_setsockopt_ccid(struct sock *sk, int type, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { u8 *val; int rc = 0; @@ -494,7 +494,7 @@ static int dccp_setsockopt_ccid(struct sock *sk, int type, } static int do_dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct dccp_sock *dp = dccp_sk(sk); int val, err = 0; @@ -546,7 +546,7 @@ static int do_dccp_setsockopt(struct sock *sk, int level, int optname, } int dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level != SOL_DCCP) return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level, @@ -559,7 +559,7 @@ EXPORT_SYMBOL_GPL(dccp_setsockopt); #ifdef CONFIG_COMPAT int compat_dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level != SOL_DCCP) return inet_csk_compat_setsockopt(sk, level, optname, diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 77d40289653c..7a58c87baf17 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -157,7 +157,7 @@ static struct hlist_head dn_sk_hash[DN_SK_HASH_SIZE]; static struct hlist_head dn_wild_sk; static atomic_t decnet_memory_allocated; -static int __dn_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen, int flags); +static int __dn_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen, int flags); static int __dn_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen, int flags); static struct hlist_head *dn_find_list(struct sock *sk) @@ -1325,7 +1325,7 @@ out: return err; } -static int dn_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) +static int dn_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int err; @@ -1337,7 +1337,7 @@ static int dn_setsockopt(struct socket *sock, int level, int optname, char __use return err; } -static int __dn_setsockopt(struct socket *sock, int level,int optname, char __user *optval, int optlen, int flags) +static int __dn_setsockopt(struct socket *sock, int level,int optname, char __user *optval, unsigned int optlen, int flags) { struct sock *sk = sock->sk; struct dn_scp *scp = DN_SK(sk); diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index 51593a48f2dd..a413b1bf4465 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -414,7 +414,7 @@ static int dgram_getsockopt(struct sock *sk, int level, int optname, } static int dgram_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct dgram_sock *ro = dgram_sk(sk); int val; diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c index 13198859982e..30e74eee07d6 100644 --- a/net/ieee802154/raw.c +++ b/net/ieee802154/raw.c @@ -244,7 +244,7 @@ static int raw_getsockopt(struct sock *sk, int level, int optname, } static int raw_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { return -EOPNOTSUPP; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 22cd19ee44e5..4351ca2cf0b8 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -714,7 +714,7 @@ int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname, EXPORT_SYMBOL_GPL(inet_csk_compat_getsockopt); int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { const struct inet_connection_sock *icsk = inet_csk(sk); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 5a0693576e82..0c0b6e363a20 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -440,7 +440,7 @@ out: */ static int do_ip_setsockopt(struct sock *sk, int level, - int optname, char __user *optval, int optlen) + int optname, char __user *optval, unsigned int optlen) { struct inet_sock *inet = inet_sk(sk); int val = 0, err; @@ -950,7 +950,7 @@ e_inval: } int ip_setsockopt(struct sock *sk, int level, - int optname, char __user *optval, int optlen) + int optname, char __user *optval, unsigned int optlen) { int err; @@ -975,7 +975,7 @@ EXPORT_SYMBOL(ip_setsockopt); #ifdef CONFIG_COMPAT int compat_ip_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int err; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index c43ec2d51ce2..630a56df7b47 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -931,7 +931,7 @@ static void mrtsock_destruct(struct sock *sk) * MOSPF/PIM router set up we can clean this up. */ -int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int optlen) +int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen) { int ret; struct vifctl vif; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index ebb1e5848bc6..757c9171e7c2 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -741,7 +741,7 @@ out: return ret; } static int do_raw_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (optname == ICMP_FILTER) { if (inet_sk(sk)->num != IPPROTO_ICMP) @@ -753,7 +753,7 @@ static int do_raw_setsockopt(struct sock *sk, int level, int optname, } static int raw_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level != SOL_RAW) return ip_setsockopt(sk, level, optname, optval, optlen); @@ -762,7 +762,7 @@ static int raw_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_COMPAT static int compat_raw_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level != SOL_RAW) return compat_ip_setsockopt(sk, level, optname, optval, optlen); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 21387ebabf00..5a15e7629d8e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2032,7 +2032,7 @@ int tcp_disconnect(struct sock *sk, int flags) * Socket option code for TCP. */ static int do_tcp_setsockopt(struct sock *sk, int level, - int optname, char __user *optval, int optlen) + int optname, char __user *optval, unsigned int optlen) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); @@ -2220,7 +2220,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, } int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, - int optlen) + unsigned int optlen) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -2232,7 +2232,7 @@ int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, #ifdef CONFIG_COMPAT int compat_tcp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level != SOL_TCP) return inet_csk_compat_setsockopt(sk, level, optname, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ebaaa7f973d7..3326aff65906 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1359,7 +1359,7 @@ void udp_destroy_sock(struct sock *sk) * Socket option code for UDP */ int udp_lib_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen, + char __user *optval, unsigned int optlen, int (*push_pending_frames)(struct sock *)) { struct udp_sock *up = udp_sk(sk); @@ -1441,7 +1441,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, EXPORT_SYMBOL(udp_lib_setsockopt); int udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_setsockopt(sk, level, optname, optval, optlen, @@ -1451,7 +1451,7 @@ int udp_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_COMPAT int compat_udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_setsockopt(sk, level, optname, optval, optlen, diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h index 9f4a6165f722..aaad650d47d9 100644 --- a/net/ipv4/udp_impl.h +++ b/net/ipv4/udp_impl.h @@ -11,13 +11,13 @@ extern void __udp4_lib_err(struct sk_buff *, u32, struct udp_table *); extern int udp_v4_get_port(struct sock *sk, unsigned short snum); extern int udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); extern int udp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); #ifdef CONFIG_COMPAT extern int compat_udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); extern int compat_udp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); #endif diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 090675e269ee..716153941fc4 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1281,7 +1281,7 @@ int ip6mr_sk_done(struct sock *sk) * MOSPF/PIM router set up we can clean this up. */ -int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int optlen) +int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen) { int ret; struct mif6ctl vif; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index f5e0682b402d..14f54eb5a7fc 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -123,7 +123,7 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk, } static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); @@ -773,7 +773,7 @@ e_inval: } int ipv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int err; @@ -801,7 +801,7 @@ EXPORT_SYMBOL(ipv6_setsockopt); #ifdef CONFIG_COMPAT int compat_ipv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int err; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 7d675b8d82d3..4f24570b0869 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -957,7 +957,7 @@ static int rawv6_geticmpfilter(struct sock *sk, int level, int optname, static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct raw6_sock *rp = raw6_sk(sk); int val; @@ -1000,7 +1000,7 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, } static int rawv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { switch(level) { case SOL_RAW: @@ -1024,7 +1024,7 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_COMPAT static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { switch (level) { case SOL_RAW: diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index b265b7047d3e..3a60f12b34ed 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1044,7 +1044,7 @@ void udpv6_destroy_sock(struct sock *sk) * Socket option code for UDP */ int udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_setsockopt(sk, level, optname, optval, optlen, @@ -1054,7 +1054,7 @@ int udpv6_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_COMPAT int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_setsockopt(sk, level, optname, optval, optlen, diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index 6bb303471e20..d7571046bfc4 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -16,10 +16,10 @@ extern int udp_v6_get_port(struct sock *sk, unsigned short snum); extern int udpv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); #ifdef CONFIG_COMPAT extern int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); + char __user *optval, unsigned int optlen); extern int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); #endif diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index f1118d92a191..66c7a20011f3 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -1292,7 +1292,7 @@ const char *ipx_device_name(struct ipx_interface *intrfc) * socket object. */ static int ipx_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int opt; diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 50b43c57d5d8..dd35641835f4 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1826,7 +1826,7 @@ static int irda_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon * */ static int irda_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct irda_sock *self = irda_sk(sk); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index d985d163dcfc..bada1b9c670b 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1387,7 +1387,7 @@ static int iucv_sock_release(struct socket *sock) /* getsockopt and setsockopt */ static int iucv_sock_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct iucv_sock *iucv = iucv_sk(sk); diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index c45eee1c0e8d..7aa4fd170104 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -973,7 +973,7 @@ static int llc_ui_ioctl(struct socket *sock, unsigned int cmd, * Set various connection specific parameters. */ static int llc_ui_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); diff --git a/net/netfilter/nf_sockopt.c b/net/netfilter/nf_sockopt.c index 8ab829f86574..f042ae521557 100644 --- a/net/netfilter/nf_sockopt.c +++ b/net/netfilter/nf_sockopt.c @@ -113,7 +113,7 @@ static int nf_sockopt(struct sock *sk, u_int8_t pf, int val, } int nf_setsockopt(struct sock *sk, u_int8_t pf, int val, char __user *opt, - int len) + unsigned int len) { return nf_sockopt(sk, pf, val, opt, &len, 0); } @@ -154,7 +154,7 @@ static int compat_nf_sockopt(struct sock *sk, u_int8_t pf, int val, } int compat_nf_setsockopt(struct sock *sk, u_int8_t pf, - int val, char __user *opt, int len) + int val, char __user *opt, unsigned int len) { return compat_nf_sockopt(sk, pf, val, opt, &len, 0); } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index dd85320907cb..19e98007691c 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1150,7 +1150,7 @@ static void netlink_update_socket_mc(struct netlink_sock *nlk, } static int netlink_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index ce1a34b99c23..7a834952f67f 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -301,7 +301,7 @@ void nr_destroy_socket(struct sock *sk) */ static int nr_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct nr_sock *nr = nr_sk(sk); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index d3d52c66cdc2..1238949e66a9 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1701,7 +1701,7 @@ static void packet_flush_mclist(struct sock *sk) } static int -packet_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) +packet_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); diff --git a/net/phonet/pep.c b/net/phonet/pep.c index b8252d289cd7..5f32d217535b 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -742,7 +742,7 @@ static int pep_init(struct sock *sk) } static int pep_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct pep_sock *pn = pep_sk(sk); int val = 0, err = 0; diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 6b58aeff4c7a..98e05382fd3c 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -248,7 +248,7 @@ static int rds_cong_monitor(struct rds_sock *rs, char __user *optval, } static int rds_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct rds_sock *rs = rds_sk_to_rs(sock->sk); int ret; diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 1e166c9685aa..502cce76621d 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -370,7 +370,7 @@ void rose_destroy_socket(struct sock *sk) */ static int rose_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct rose_sock *rose = rose_sk(sk); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index bfe493ebf27c..a86afceaa94f 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -507,7 +507,7 @@ out: * set RxRPC socket options */ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct rxrpc_sock *rx = rxrpc_sk(sock->sk); unsigned min_sec_level; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 89af37a6c871..c8d05758661d 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2027,7 +2027,8 @@ out: * instead a error will be indicated to the user. */ static int sctp_setsockopt_disable_fragments(struct sock *sk, - char __user *optval, int optlen) + char __user *optval, + unsigned int optlen) { int val; @@ -2043,7 +2044,7 @@ static int sctp_setsockopt_disable_fragments(struct sock *sk, } static int sctp_setsockopt_events(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { if (optlen > sizeof(struct sctp_event_subscribe)) return -EINVAL; @@ -2064,7 +2065,7 @@ static int sctp_setsockopt_events(struct sock *sk, char __user *optval, * association is closed. */ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); @@ -2318,7 +2319,8 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, } static int sctp_setsockopt_peer_addr_params(struct sock *sk, - char __user *optval, int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_paddrparams params; struct sctp_transport *trans = NULL; @@ -2430,7 +2432,7 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk, */ static int sctp_setsockopt_delayed_ack(struct sock *sk, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sctp_sack_info params; struct sctp_transport *trans = NULL; @@ -2546,7 +2548,7 @@ static int sctp_setsockopt_delayed_ack(struct sock *sk, * by the change). With TCP-style sockets, this option is inherited by * sockets derived from a listener socket. */ -static int sctp_setsockopt_initmsg(struct sock *sk, char __user *optval, int optlen) +static int sctp_setsockopt_initmsg(struct sock *sk, char __user *optval, unsigned int optlen) { struct sctp_initmsg sinit; struct sctp_sock *sp = sctp_sk(sk); @@ -2583,7 +2585,8 @@ static int sctp_setsockopt_initmsg(struct sock *sk, char __user *optval, int opt * to this call if the caller is using the UDP model. */ static int sctp_setsockopt_default_send_param(struct sock *sk, - char __user *optval, int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_sndrcvinfo info; struct sctp_association *asoc; @@ -2622,7 +2625,7 @@ static int sctp_setsockopt_default_send_param(struct sock *sk, * association peer's addresses. */ static int sctp_setsockopt_primary_addr(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_prim prim; struct sctp_transport *trans; @@ -2651,7 +2654,7 @@ static int sctp_setsockopt_primary_addr(struct sock *sk, char __user *optval, * integer boolean flag. */ static int sctp_setsockopt_nodelay(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { int val; @@ -2676,7 +2679,8 @@ static int sctp_setsockopt_nodelay(struct sock *sk, char __user *optval, * be changed. * */ -static int sctp_setsockopt_rtoinfo(struct sock *sk, char __user *optval, int optlen) { +static int sctp_setsockopt_rtoinfo(struct sock *sk, char __user *optval, unsigned int optlen) +{ struct sctp_rtoinfo rtoinfo; struct sctp_association *asoc; @@ -2728,7 +2732,7 @@ static int sctp_setsockopt_rtoinfo(struct sock *sk, char __user *optval, int opt * See [SCTP] for more information. * */ -static int sctp_setsockopt_associnfo(struct sock *sk, char __user *optval, int optlen) +static int sctp_setsockopt_associnfo(struct sock *sk, char __user *optval, unsigned int optlen) { struct sctp_assocparams assocparams; @@ -2800,7 +2804,7 @@ static int sctp_setsockopt_associnfo(struct sock *sk, char __user *optval, int o * addresses and a user will receive both PF_INET6 and PF_INET type * addresses on the socket. */ -static int sctp_setsockopt_mappedv4(struct sock *sk, char __user *optval, int optlen) +static int sctp_setsockopt_mappedv4(struct sock *sk, char __user *optval, unsigned int optlen) { int val; struct sctp_sock *sp = sctp_sk(sk); @@ -2844,7 +2848,7 @@ static int sctp_setsockopt_mappedv4(struct sock *sk, char __user *optval, int op * changed (effecting future associations only). * assoc_value: This parameter specifies the maximum size in bytes. */ -static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, int optlen) +static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned int optlen) { struct sctp_assoc_value params; struct sctp_association *asoc; @@ -2899,7 +2903,7 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, int optl * set primary request: */ static int sctp_setsockopt_peer_primary_addr(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_sock *sp; struct sctp_endpoint *ep; @@ -2950,7 +2954,7 @@ static int sctp_setsockopt_peer_primary_addr(struct sock *sk, char __user *optva } static int sctp_setsockopt_adaptation_layer(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_setadaptation adaptation; @@ -2979,7 +2983,7 @@ static int sctp_setsockopt_adaptation_layer(struct sock *sk, char __user *optval * saved with outbound messages. */ static int sctp_setsockopt_context(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_assoc_value params; struct sctp_sock *sp; @@ -3030,7 +3034,7 @@ static int sctp_setsockopt_context(struct sock *sk, char __user *optval, */ static int sctp_setsockopt_fragment_interleave(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { int val; @@ -3063,7 +3067,7 @@ static int sctp_setsockopt_fragment_interleave(struct sock *sk, */ static int sctp_setsockopt_partial_delivery_point(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { u32 val; @@ -3096,7 +3100,7 @@ static int sctp_setsockopt_partial_delivery_point(struct sock *sk, */ static int sctp_setsockopt_maxburst(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_assoc_value params; struct sctp_sock *sp; @@ -3140,8 +3144,8 @@ static int sctp_setsockopt_maxburst(struct sock *sk, * will only effect future associations on the socket. */ static int sctp_setsockopt_auth_chunk(struct sock *sk, - char __user *optval, - int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_authchunk val; @@ -3172,8 +3176,8 @@ static int sctp_setsockopt_auth_chunk(struct sock *sk, * endpoint requires the peer to use. */ static int sctp_setsockopt_hmac_ident(struct sock *sk, - char __user *optval, - int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_hmacalgo *hmacs; u32 idents; @@ -3215,7 +3219,7 @@ out: */ static int sctp_setsockopt_auth_key(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_authkey *authkey; struct sctp_association *asoc; @@ -3260,8 +3264,8 @@ out: * the association shared key. */ static int sctp_setsockopt_active_key(struct sock *sk, - char __user *optval, - int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_authkeyid val; struct sctp_association *asoc; @@ -3288,8 +3292,8 @@ static int sctp_setsockopt_active_key(struct sock *sk, * This set option will delete a shared secret key from use. */ static int sctp_setsockopt_del_key(struct sock *sk, - char __user *optval, - int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_authkeyid val; struct sctp_association *asoc; @@ -3332,7 +3336,7 @@ static int sctp_setsockopt_del_key(struct sock *sk, * optlen - the size of the buffer. */ SCTP_STATIC int sctp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int retval = 0; diff --git a/net/socket.c b/net/socket.c index 41e8847508aa..75655365b5fd 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2391,7 +2391,7 @@ int kernel_getsockopt(struct socket *sock, int level, int optname, } int kernel_setsockopt(struct socket *sock, int level, int optname, - char *optval, int optlen) + char *optval, unsigned int optlen) { mm_segment_t oldfs = get_fs(); int err; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index e8254e809b79..e6d9abf7440e 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1658,7 +1658,7 @@ restart: */ static int setsockopt(struct socket *sock, - int lvl, int opt, char __user *ov, int ol) + int lvl, int opt, char __user *ov, unsigned int ol) { struct sock *sk = sock->sk; struct tipc_port *tport = tipc_sk_port(sk); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 5e6c072c64d3..7fa9c7ad3d3b 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -409,7 +409,7 @@ static void x25_destroy_socket(struct sock *sk) */ static int x25_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int opt; struct sock *sk = sock->sk; -- cgit v1.2.3 From 48c0d4d4c04dd520c55e0fd756fa4e7c83de3d13 Mon Sep 17 00:00:00 2001 From: Zdenek Kabelac Date: Fri, 25 Sep 2009 06:19:26 +0200 Subject: Add missing blk_trace_remove_sysfs to be in pair with blk_trace_init_sysfs Add missing blk_trace_remove_sysfs to be in pair with blk_trace_init_sysfs introduced in commit 1d54ad6da9192fed5dd3b60224d9f2dfea0dcd82. Release kobject also in case the request_fn is NULL. Problem was noticed via kmemleak backtrace when some sysfs entries were note properly destroyed during device removal: unreferenced object 0xffff88001aa76640 (size 80): comm "lvcreate", pid 2120, jiffies 4294885144 hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 f0 65 a7 1a 00 88 ff ff .........e...... 90 66 a7 1a 00 88 ff ff 86 1d 53 81 ff ff ff ff .f........S..... backtrace: [] kmemleak_alloc+0x26/0x60 [] kmem_cache_alloc+0x133/0x1c0 [] sysfs_new_dirent+0x41/0x120 [] sysfs_add_file_mode+0x3c/0xb0 [] internal_create_group+0xc1/0x1a0 [] sysfs_create_group+0x13/0x20 [] blk_trace_init_sysfs+0x14/0x20 [] blk_register_queue+0x3c/0xf0 [] add_disk+0x94/0x160 [] dm_create+0x598/0x6e0 [dm_mod] [] dev_create+0x51/0x350 [dm_mod] [] ctl_ioctl+0x1a3/0x240 [dm_mod] [] dm_compat_ctl_ioctl+0x12/0x20 [dm_mod] [] compat_sys_ioctl+0xcd/0x4f0 [] sysenter_dispatch+0x7/0x2c [] 0xffffffffffffffff Signed-off-by: Zdenek Kabelac Reviewed-by: Li Zefan Signed-off-by: Jens Axboe --- block/blk-sysfs.c | 11 ++++++----- include/linux/blktrace_api.h | 2 ++ kernel/trace/blktrace.c | 5 +++++ 3 files changed, 13 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index b78c9c3e2670..8a6d81afb284 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -452,6 +452,7 @@ int blk_register_queue(struct gendisk *disk) if (ret) { kobject_uevent(&q->kobj, KOBJ_REMOVE); kobject_del(&q->kobj); + blk_trace_remove_sysfs(disk_to_dev(disk)); return ret; } @@ -465,11 +466,11 @@ void blk_unregister_queue(struct gendisk *disk) if (WARN_ON(!q)) return; - if (q->request_fn) { + if (q->request_fn) elv_unregister_queue(q); - kobject_uevent(&q->kobj, KOBJ_REMOVE); - kobject_del(&q->kobj); - kobject_put(&disk_to_dev(disk)->kobj); - } + kobject_uevent(&q->kobj, KOBJ_REMOVE); + kobject_del(&q->kobj); + blk_trace_remove_sysfs(disk_to_dev(disk)); + kobject_put(&disk_to_dev(disk)->kobj); } diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 7e4350ece0f8..622939a23299 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -198,6 +198,7 @@ extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, char __user *arg); extern int blk_trace_startstop(struct request_queue *q, int start); extern int blk_trace_remove(struct request_queue *q); +extern void blk_trace_remove_sysfs(struct device *dev); extern int blk_trace_init_sysfs(struct device *dev); extern struct attribute_group blk_trace_attr_group; @@ -211,6 +212,7 @@ extern struct attribute_group blk_trace_attr_group; # define blk_trace_startstop(q, start) (-ENOTTY) # define blk_trace_remove(q) (-ENOTTY) # define blk_add_trace_msg(q, fmt, ...) do { } while (0) +# define blk_trace_remove_sysfs(struct device *dev) do { } while (0) static inline int blk_trace_init_sysfs(struct device *dev) { return 0; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 3eb159c277c8..60b5c5a3d4b4 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1657,6 +1657,11 @@ int blk_trace_init_sysfs(struct device *dev) return sysfs_create_group(&dev->kobj, &blk_trace_attr_group); } +void blk_trace_remove_sysfs(struct device *dev) +{ + sysfs_remove_group(&dev->kobj, &blk_trace_attr_group); +} + #endif /* CONFIG_BLK_DEV_IO_TRACE */ #ifdef CONFIG_EVENT_TRACING -- cgit v1.2.3 From c15227de132f1295f3db6b7df9079956b1020fd8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 30 Sep 2009 13:52:12 +0200 Subject: block: use normal I/O path for discard requests prepare_discard_fn() was being called in a place where memory allocation was effectively impossible. This makes it inappropriate for all but the most trivial translations of Linux's DISCARD operation to the block command set. Additionally adding a payload there makes the ownership of the bio backing unclear as it's now allocated by the device driver and not the submitter as usual. It is replaced with QUEUE_FLAG_DISCARD which is used to indicate whether the queue supports discard operations or not. blkdev_issue_discard now allocates a one-page, sector-length payload which is the right thing for the common ATA and SCSI implementations. The mtd implementation of prepare_discard_fn() is replaced with simply checking for the request being a discard. Largely based on a previous patch from Matthew Wilcox which did the prepare_discard_fn but not the different payload allocation yet. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-barrier.c | 35 ++++++++++++++++++++++++++++++----- block/blk-core.c | 3 +-- block/blk-settings.c | 17 ----------------- drivers/mtd/mtd_blkdevs.c | 19 +++++-------------- drivers/staging/dst/dcore.c | 2 +- include/linux/blkdev.h | 6 ++---- 6 files changed, 39 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/block/blk-barrier.c b/block/blk-barrier.c index 6593ab39cfe9..21f5025c3945 100644 --- a/block/blk-barrier.c +++ b/block/blk-barrier.c @@ -350,6 +350,7 @@ static void blkdev_discard_end_io(struct bio *bio, int err) if (bio->bi_private) complete(bio->bi_private); + __free_page(bio_page(bio)); bio_put(bio); } @@ -372,26 +373,44 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, struct request_queue *q = bdev_get_queue(bdev); int type = flags & DISCARD_FL_BARRIER ? DISCARD_BARRIER : DISCARD_NOBARRIER; + struct bio *bio; + struct page *page; int ret = 0; if (!q) return -ENXIO; - if (!q->prepare_discard_fn) + if (!blk_queue_discard(q)) return -EOPNOTSUPP; while (nr_sects && !ret) { - struct bio *bio = bio_alloc(gfp_mask, 0); - if (!bio) - return -ENOMEM; + unsigned int sector_size = q->limits.logical_block_size; + bio = bio_alloc(gfp_mask, 1); + if (!bio) + goto out; + bio->bi_sector = sector; bio->bi_end_io = blkdev_discard_end_io; bio->bi_bdev = bdev; if (flags & DISCARD_FL_WAIT) bio->bi_private = &wait; - bio->bi_sector = sector; + /* + * Add a zeroed one-sector payload as that's what + * our current implementations need. If we'll ever need + * more the interface will need revisiting. + */ + page = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!page) + goto out_free_bio; + if (bio_add_pc_page(q, bio, page, sector_size, 0) < sector_size) + goto out_free_page; + /* + * And override the bio size - the way discard works we + * touch many more blocks on disk than the actual payload + * length. + */ if (nr_sects > queue_max_hw_sectors(q)) { bio->bi_size = queue_max_hw_sectors(q) << 9; nr_sects -= queue_max_hw_sectors(q); @@ -414,5 +433,11 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, bio_put(bio); } return ret; +out_free_page: + __free_page(page); +out_free_bio: + bio_put(bio); +out: + return -ENOMEM; } EXPORT_SYMBOL(blkdev_issue_discard); diff --git a/block/blk-core.c b/block/blk-core.c index 8135228e4b29..80a020dd1580 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1124,7 +1124,6 @@ void init_request_from_bio(struct request *req, struct bio *bio) req->cmd_flags |= REQ_DISCARD; if (bio_rw_flagged(bio, BIO_RW_BARRIER)) req->cmd_flags |= REQ_SOFTBARRIER; - req->q->prepare_discard_fn(req->q, req); } else if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) req->cmd_flags |= REQ_HARDBARRIER; @@ -1470,7 +1469,7 @@ static inline void __generic_make_request(struct bio *bio) goto end_io; if (bio_rw_flagged(bio, BIO_RW_DISCARD) && - !q->prepare_discard_fn) { + !blk_queue_discard(q)) { err = -EOPNOTSUPP; goto end_io; } diff --git a/block/blk-settings.c b/block/blk-settings.c index eaf122ff5f16..d29498ef1eb5 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -33,23 +33,6 @@ void blk_queue_prep_rq(struct request_queue *q, prep_rq_fn *pfn) } EXPORT_SYMBOL(blk_queue_prep_rq); -/** - * blk_queue_set_discard - set a discard_sectors function for queue - * @q: queue - * @dfn: prepare_discard function - * - * It's possible for a queue to register a discard callback which is used - * to transform a discard request into the appropriate type for the - * hardware. If none is registered, then discard requests are failed - * with %EOPNOTSUPP. - * - */ -void blk_queue_set_discard(struct request_queue *q, prepare_discard_fn *dfn) -{ - q->prepare_discard_fn = dfn; -} -EXPORT_SYMBOL(blk_queue_set_discard); - /** * blk_queue_merge_bvec - set a merge_bvec function for queue * @q: queue diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 0acbf4f5be50..8ca17a3e96ea 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -32,14 +32,6 @@ struct mtd_blkcore_priv { spinlock_t queue_lock; }; -static int blktrans_discard_request(struct request_queue *q, - struct request *req) -{ - req->cmd_type = REQ_TYPE_LINUX_BLOCK; - req->cmd[0] = REQ_LB_OP_DISCARD; - return 0; -} - static int do_blktrans_request(struct mtd_blktrans_ops *tr, struct mtd_blktrans_dev *dev, struct request *req) @@ -52,10 +44,6 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr, buf = req->buffer; - if (req->cmd_type == REQ_TYPE_LINUX_BLOCK && - req->cmd[0] == REQ_LB_OP_DISCARD) - return tr->discard(dev, block, nsect); - if (!blk_fs_request(req)) return -EIO; @@ -63,6 +51,9 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr, get_capacity(req->rq_disk)) return -EIO; + if (blk_discard_rq(req)) + return tr->discard(dev, block, nsect); + switch(rq_data_dir(req)) { case READ: for (; nsect > 0; nsect--, block++, buf += tr->blksize) @@ -380,8 +371,8 @@ int register_mtd_blktrans(struct mtd_blktrans_ops *tr) tr->blkcore_priv->rq->queuedata = tr; blk_queue_logical_block_size(tr->blkcore_priv->rq, tr->blksize); if (tr->discard) - blk_queue_set_discard(tr->blkcore_priv->rq, - blktrans_discard_request); + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, + tr->blkcore_priv->rq); tr->blkshift = ffs(tr->blksize) - 1; diff --git a/drivers/staging/dst/dcore.c b/drivers/staging/dst/dcore.c index ac8577358ba0..5e8db0677582 100644 --- a/drivers/staging/dst/dcore.c +++ b/drivers/staging/dst/dcore.c @@ -102,7 +102,7 @@ static int dst_request(struct request_queue *q, struct bio *bio) struct dst_node *n = q->queuedata; int err = -EIO; - if (bio_empty_barrier(bio) && !q->prepare_discard_fn) { + if (bio_empty_barrier(bio) && !blk_queue_discard(q)) { /* * This is a dirty^Wnice hack, but if we complete this * operation with -EOPNOTSUPP like intended, XFS diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e23a86cae5ac..f62d45e87618 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -82,7 +82,6 @@ enum rq_cmd_type_bits { enum { REQ_LB_OP_EJECT = 0x40, /* eject request */ REQ_LB_OP_FLUSH = 0x41, /* flush request */ - REQ_LB_OP_DISCARD = 0x42, /* discard sectors */ }; /* @@ -261,7 +260,6 @@ typedef void (request_fn_proc) (struct request_queue *q); typedef int (make_request_fn) (struct request_queue *q, struct bio *bio); typedef int (prep_rq_fn) (struct request_queue *, struct request *); typedef void (unplug_fn) (struct request_queue *); -typedef int (prepare_discard_fn) (struct request_queue *, struct request *); struct bio_vec; struct bvec_merge_data { @@ -340,7 +338,6 @@ struct request_queue make_request_fn *make_request_fn; prep_rq_fn *prep_rq_fn; unplug_fn *unplug_fn; - prepare_discard_fn *prepare_discard_fn; merge_bvec_fn *merge_bvec_fn; prepare_flush_fn *prepare_flush_fn; softirq_done_fn *softirq_done_fn; @@ -460,6 +457,7 @@ struct request_queue #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 15 /* do IO stats */ #define QUEUE_FLAG_CQ 16 /* hardware does queuing */ +#define QUEUE_FLAG_DISCARD 17 /* supports DISCARD */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_CLUSTER) | \ @@ -591,6 +589,7 @@ enum { #define blk_queue_flushing(q) ((q)->ordseq) #define blk_queue_stackable(q) \ test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags) +#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) #define blk_fs_request(rq) ((rq)->cmd_type == REQ_TYPE_FS) #define blk_pc_request(rq) ((rq)->cmd_type == REQ_TYPE_BLOCK_PC) @@ -955,7 +954,6 @@ extern void blk_queue_merge_bvec(struct request_queue *, merge_bvec_fn *); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); -extern void blk_queue_set_discard(struct request_queue *, prepare_discard_fn *); extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); -- cgit v1.2.3 From 67efc9258010da35b27b3854d0880c7e193004ed Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 30 Sep 2009 13:54:20 +0200 Subject: block: allow large discard requests Currently we set the bio size to the byte equivalent of the blocks to be trimmed when submitting the initial DISCARD ioctl. That means it is subject to the max_hw_sectors limitation of the HBA which is much lower than the size of a DISCARD request we can support. Add a separate max_discard_sectors tunable to limit the size for discard requests. We limit the max discard request size in bytes to 32bit as that is the limit for bio->bi_size. This could be much larger if we had a way to pass that information through the block layer. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-barrier.c | 10 ++++++---- block/blk-core.c | 3 ++- block/blk-settings.c | 13 +++++++++++++ include/linux/blkdev.h | 3 +++ 4 files changed, 24 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/block/blk-barrier.c b/block/blk-barrier.c index 21f5025c3945..8873b9b439ff 100644 --- a/block/blk-barrier.c +++ b/block/blk-barrier.c @@ -385,6 +385,8 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, while (nr_sects && !ret) { unsigned int sector_size = q->limits.logical_block_size; + unsigned int max_discard_sectors = + min(q->limits.max_discard_sectors, UINT_MAX >> 9); bio = bio_alloc(gfp_mask, 1); if (!bio) @@ -411,10 +413,10 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, * touch many more blocks on disk than the actual payload * length. */ - if (nr_sects > queue_max_hw_sectors(q)) { - bio->bi_size = queue_max_hw_sectors(q) << 9; - nr_sects -= queue_max_hw_sectors(q); - sector += queue_max_hw_sectors(q); + if (nr_sects > max_discard_sectors) { + bio->bi_size = max_discard_sectors << 9; + nr_sects -= max_discard_sectors; + sector += max_discard_sectors; } else { bio->bi_size = nr_sects << 9; nr_sects = 0; diff --git a/block/blk-core.c b/block/blk-core.c index 80a020dd1580..34504f309728 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1436,7 +1436,8 @@ static inline void __generic_make_request(struct bio *bio) goto end_io; } - if (unlikely(nr_sectors > queue_max_hw_sectors(q))) { + if (unlikely(!bio_rw_flagged(bio, BIO_RW_DISCARD) && + nr_sectors > queue_max_hw_sectors(q))) { printk(KERN_ERR "bio too big device %s (%u > %u)\n", bdevname(bio->bi_bdev, b), bio_sectors(bio), diff --git a/block/blk-settings.c b/block/blk-settings.c index d29498ef1eb5..e0695bca7027 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -96,6 +96,7 @@ void blk_set_default_limits(struct queue_limits *lim) lim->max_segment_size = MAX_SEGMENT_SIZE; lim->max_sectors = BLK_DEF_MAX_SECTORS; lim->max_hw_sectors = INT_MAX; + lim->max_discard_sectors = SAFE_MAX_SECTORS; lim->logical_block_size = lim->physical_block_size = lim->io_min = 512; lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT); lim->alignment_offset = 0; @@ -238,6 +239,18 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_sectors) } EXPORT_SYMBOL(blk_queue_max_hw_sectors); +/** + * blk_queue_max_discard_sectors - set max sectors for a single discard + * @q: the request queue for the device + * @max_discard: maximum number of sectors to discard + **/ +void blk_queue_max_discard_sectors(struct request_queue *q, + unsigned int max_discard_sectors) +{ + q->limits.max_discard_sectors = max_discard_sectors; +} +EXPORT_SYMBOL(blk_queue_max_discard_sectors); + /** * blk_queue_max_phys_segments - set max phys segments for a request for this queue * @q: the request queue for the device diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f62d45e87618..1a03b715dfad 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -311,6 +311,7 @@ struct queue_limits { unsigned int alignment_offset; unsigned int io_min; unsigned int io_opt; + unsigned int max_discard_sectors; unsigned short logical_block_size; unsigned short max_hw_segments; @@ -928,6 +929,8 @@ extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short); extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); +extern void blk_queue_max_discard_sectors(struct request_queue *q, + unsigned int max_discard_sectors); extern void blk_queue_logical_block_size(struct request_queue *, unsigned short); extern void blk_queue_physical_block_size(struct request_queue *, unsigned short); extern void blk_queue_alignment_offset(struct request_queue *q, -- cgit v1.2.3 From b0da3f0dada78832c9da03ad2152ae76bd9a2496 Mon Sep 17 00:00:00 2001 From: Jun'ichi Nomura Date: Thu, 1 Oct 2009 21:16:13 +0200 Subject: Add a tracepoint for block request remapping Since 2.6.31 now has request-based device-mapper, it's useful to have a tracepoint for request-remapping as well as bio-remapping. This patch adds a tracepoint for request-remapping, trace_block_rq_remap(). Signed-off-by: Kiyoshi Ueda Signed-off-by: Jun'ichi Nomura Cc: Alasdair G Kergon Cc: Li Zefan Signed-off-by: Jens Axboe --- block/blk-core.c | 1 + include/linux/blktrace_api.h | 2 +- include/trace/events/block.h | 33 +++++++++++++++++++++++++++++++++ kernel/trace/blktrace.c | 34 ++++++++++++++++++++++++++++++++++ 4 files changed, 69 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 34504f309728..ddaaea4fdffc 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -34,6 +34,7 @@ #include "blk.h" EXPORT_TRACEPOINT_SYMBOL_GPL(block_remap); +EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete); static int __make_request(struct request_queue *q, struct bio *bio); diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 622939a23299..3b73b9992b26 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -212,7 +212,7 @@ extern struct attribute_group blk_trace_attr_group; # define blk_trace_startstop(q, start) (-ENOTTY) # define blk_trace_remove(q) (-ENOTTY) # define blk_add_trace_msg(q, fmt, ...) do { } while (0) -# define blk_trace_remove_sysfs(struct device *dev) do { } while (0) +# define blk_trace_remove_sysfs(dev) do { } while (0) static inline int blk_trace_init_sysfs(struct device *dev) { return 0; diff --git a/include/trace/events/block.h b/include/trace/events/block.h index d86af94691c2..00405b5f624a 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -488,6 +488,39 @@ TRACE_EVENT(block_remap, (unsigned long long)__entry->old_sector) ); +TRACE_EVENT(block_rq_remap, + + TP_PROTO(struct request_queue *q, struct request *rq, dev_t dev, + sector_t from), + + TP_ARGS(q, rq, dev, from), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( sector_t, sector ) + __field( unsigned int, nr_sector ) + __field( dev_t, old_dev ) + __field( sector_t, old_sector ) + __array( char, rwbs, 6 ) + ), + + TP_fast_assign( + __entry->dev = disk_devt(rq->rq_disk); + __entry->sector = blk_rq_pos(rq); + __entry->nr_sector = blk_rq_sectors(rq); + __entry->old_dev = dev; + __entry->old_sector = from; + blk_fill_rwbs_rq(__entry->rwbs, rq); + ), + + TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, + (unsigned long long)__entry->sector, + __entry->nr_sector, + MAJOR(__entry->old_dev), MINOR(__entry->old_dev), + (unsigned long long)__entry->old_sector) +); + #endif /* _TRACE_BLOCK_H */ /* This part must be outside protection */ diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 60b5c5a3d4b4..d9d6206e0b14 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -855,6 +855,37 @@ static void blk_add_trace_remap(struct request_queue *q, struct bio *bio, sizeof(r), &r); } +/** + * blk_add_trace_rq_remap - Add a trace for a request-remap operation + * @q: queue the io is for + * @rq: the source request + * @dev: target device + * @from: source sector + * + * Description: + * Device mapper remaps request to other devices. + * Add a trace for that action. + * + **/ +static void blk_add_trace_rq_remap(struct request_queue *q, + struct request *rq, dev_t dev, + sector_t from) +{ + struct blk_trace *bt = q->blk_trace; + struct blk_io_trace_remap r; + + if (likely(!bt)) + return; + + r.device_from = cpu_to_be32(dev); + r.device_to = cpu_to_be32(disk_devt(rq->rq_disk)); + r.sector_from = cpu_to_be64(from); + + __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), + rq_data_dir(rq), BLK_TA_REMAP, !!rq->errors, + sizeof(r), &r); +} + /** * blk_add_driver_data - Add binary message with driver-specific data * @q: queue the io is for @@ -922,10 +953,13 @@ static void blk_register_tracepoints(void) WARN_ON(ret); ret = register_trace_block_remap(blk_add_trace_remap); WARN_ON(ret); + ret = register_trace_block_rq_remap(blk_add_trace_rq_remap); + WARN_ON(ret); } static void blk_unregister_tracepoints(void) { + unregister_trace_block_rq_remap(blk_add_trace_rq_remap); unregister_trace_block_remap(blk_add_trace_remap); unregister_trace_block_split(blk_add_trace_split); unregister_trace_block_unplug_io(blk_add_trace_unplug_io); -- cgit v1.2.3 From 828c09509b9695271bcbdc53e9fc9a6a737148d2 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 1 Oct 2009 15:43:56 -0700 Subject: const: constify remaining file_operations [akpm@linux-foundation.org: fix KVM] Signed-off-by: Alexey Dobriyan Acked-by: Mike Frysinger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/mach-ns9xxx/clock.c | 2 +- arch/blackfin/mach-bf561/coreb.c | 2 +- arch/cris/arch-v10/drivers/sync_serial.c | 2 +- arch/cris/arch-v32/drivers/mach-fs/gpio.c | 2 +- arch/powerpc/kvm/timing.c | 2 +- arch/powerpc/platforms/cell/spufs/file.c | 2 +- arch/powerpc/platforms/pseries/dtl.c | 2 +- arch/x86/xen/debugfs.c | 2 +- drivers/acpi/video.c | 2 +- drivers/block/cciss.c | 2 +- drivers/char/apm-emulation.c | 2 +- drivers/char/bfin-otp.c | 2 +- drivers/char/xilinx_hwicap/xilinx_hwicap.c | 2 +- drivers/gpio/gpiolib.c | 2 +- drivers/hwmon/fschmd.c | 2 +- drivers/lguest/lguest_user.c | 2 +- drivers/media/dvb/dvb-core/dmxdev.c | 2 +- drivers/media/dvb/firewire/firedtv-ci.c | 2 +- drivers/misc/phantom.c | 2 +- drivers/misc/sgi-gru/grufile.c | 3 +-- drivers/mmc/core/debugfs.c | 2 +- drivers/s390/cio/qdio_debug.c | 2 +- drivers/s390/cio/qdio_perf.c | 2 +- drivers/scsi/sg.c | 43 +++++++++++++++++++++--------- drivers/spi/spidev.c | 2 +- drivers/usb/class/usbtmc.c | 2 +- drivers/usb/gadget/printer.c | 2 +- drivers/usb/host/whci/debug.c | 6 ++--- drivers/usb/misc/rio500.c | 3 +-- drivers/uwb/uwb-debug.c | 6 ++--- fs/btrfs/ctree.h | 2 +- fs/btrfs/file.c | 2 +- fs/btrfs/inode.c | 4 +-- fs/jbd2/journal.c | 2 +- fs/nfsd/nfsctl.c | 2 +- fs/nilfs2/dir.c | 2 +- fs/nilfs2/file.c | 2 +- fs/nilfs2/mdt.c | 2 +- fs/nilfs2/nilfs.h | 4 +-- fs/ocfs2/cluster/heartbeat.c | 2 +- fs/ocfs2/cluster/netdebug.c | 4 +-- fs/ocfs2/dlm/dlmdebug.c | 8 +++--- fs/ocfs2/super.c | 2 +- fs/omfs/dir.c | 2 +- fs/omfs/file.c | 2 +- fs/omfs/omfs.h | 4 +-- include/linux/cgroup.h | 2 +- include/linux/fs.h | 2 +- kernel/cgroup.c | 10 +++---- kernel/kprobes.c | 4 +-- kernel/rcutree_trace.c | 10 +++---- kernel/sched.c | 2 +- kernel/time/timer_list.c | 2 +- kernel/time/timer_stats.c | 2 +- samples/tracepoints/tracepoint-sample.c | 2 +- security/integrity/ima/ima_fs.c | 10 +++---- virt/kvm/kvm_main.c | 2 +- 57 files changed, 110 insertions(+), 95 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-ns9xxx/clock.c b/arch/arm/mach-ns9xxx/clock.c index 44ed20d4a388..cf81cbc57544 100644 --- a/arch/arm/mach-ns9xxx/clock.c +++ b/arch/arm/mach-ns9xxx/clock.c @@ -195,7 +195,7 @@ static int clk_debugfs_open(struct inode *inode, struct file *file) return single_open(file, clk_debugfs_show, NULL); } -static struct file_operations clk_debugfs_operations = { +static const struct file_operations clk_debugfs_operations = { .open = clk_debugfs_open, .read = seq_read, .llseek = seq_lseek, diff --git a/arch/blackfin/mach-bf561/coreb.c b/arch/blackfin/mach-bf561/coreb.c index 93635a766f9c..1e60a92dd602 100644 --- a/arch/blackfin/mach-bf561/coreb.c +++ b/arch/blackfin/mach-bf561/coreb.c @@ -48,7 +48,7 @@ coreb_ioctl(struct inode *inode, struct file *file, unsigned int cmd, unsigned l return ret; } -static struct file_operations coreb_fops = { +static const struct file_operations coreb_fops = { .owner = THIS_MODULE, .ioctl = coreb_ioctl, }; diff --git a/arch/cris/arch-v10/drivers/sync_serial.c b/arch/cris/arch-v10/drivers/sync_serial.c index 6cc1a0319a5d..562b9a7feae7 100644 --- a/arch/cris/arch-v10/drivers/sync_serial.c +++ b/arch/cris/arch-v10/drivers/sync_serial.c @@ -244,7 +244,7 @@ static unsigned sync_serial_prescale_shadow; #define NUMBER_OF_PORTS 2 -static struct file_operations sync_serial_fops = { +static const struct file_operations sync_serial_fops = { .owner = THIS_MODULE, .write = sync_serial_write, .read = sync_serial_read, diff --git a/arch/cris/arch-v32/drivers/mach-fs/gpio.c b/arch/cris/arch-v32/drivers/mach-fs/gpio.c index fe1fde893887..d89ab80498ed 100644 --- a/arch/cris/arch-v32/drivers/mach-fs/gpio.c +++ b/arch/cris/arch-v32/drivers/mach-fs/gpio.c @@ -855,7 +855,7 @@ gpio_leds_ioctl(unsigned int cmd, unsigned long arg) return 0; } -struct file_operations gpio_fops = { +static const struct file_operations gpio_fops = { .owner = THIS_MODULE, .poll = gpio_poll, .ioctl = gpio_ioctl, diff --git a/arch/powerpc/kvm/timing.c b/arch/powerpc/kvm/timing.c index 47ee603f558e..2aa371e30079 100644 --- a/arch/powerpc/kvm/timing.c +++ b/arch/powerpc/kvm/timing.c @@ -201,7 +201,7 @@ static int kvmppc_exit_timing_open(struct inode *inode, struct file *file) return single_open(file, kvmppc_exit_timing_show, inode->i_private); } -static struct file_operations kvmppc_exit_timing_fops = { +static const struct file_operations kvmppc_exit_timing_fops = { .owner = THIS_MODULE, .open = kvmppc_exit_timing_open, .read = seq_read, diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 961309446170..884e8bcec499 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -147,7 +147,7 @@ static int __fops ## _open(struct inode *inode, struct file *file) \ __simple_attr_check_format(__fmt, 0ull); \ return spufs_attr_open(inode, file, __get, __set, __fmt); \ } \ -static struct file_operations __fops = { \ +static const struct file_operations __fops = { \ .owner = THIS_MODULE, \ .open = __fops ## _open, \ .release = spufs_attr_release, \ diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index ab69925d579b..937a544a236d 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -209,7 +209,7 @@ static ssize_t dtl_file_read(struct file *filp, char __user *buf, size_t len, return n_read * sizeof(struct dtl_entry); } -static struct file_operations dtl_fops = { +static const struct file_operations dtl_fops = { .open = dtl_file_open, .release = dtl_file_release, .read = dtl_file_read, diff --git a/arch/x86/xen/debugfs.c b/arch/x86/xen/debugfs.c index b53225d2cac3..e133ce25e290 100644 --- a/arch/x86/xen/debugfs.c +++ b/arch/x86/xen/debugfs.c @@ -100,7 +100,7 @@ static int xen_array_release(struct inode *inode, struct file *file) return 0; } -static struct file_operations u32_array_fops = { +static const struct file_operations u32_array_fops = { .owner = THIS_MODULE, .open = u32_array_open, .release= xen_array_release, diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c index a4fddb24476f..f6e54bf8dd96 100644 --- a/drivers/acpi/video.c +++ b/drivers/acpi/video.c @@ -285,7 +285,7 @@ static int acpi_video_device_brightness_open_fs(struct inode *inode, struct file *file); static ssize_t acpi_video_device_write_brightness(struct file *file, const char __user *buffer, size_t count, loff_t *data); -static struct file_operations acpi_video_device_brightness_fops = { +static const struct file_operations acpi_video_device_brightness_fops = { .owner = THIS_MODULE, .open = acpi_video_device_brightness_open_fs, .read = seq_read, diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index 24c3e21ab263..1ece0b47b581 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -426,7 +426,7 @@ out: return err; } -static struct file_operations cciss_proc_fops = { +static const struct file_operations cciss_proc_fops = { .owner = THIS_MODULE, .open = cciss_seq_open, .read = seq_read, diff --git a/drivers/char/apm-emulation.c b/drivers/char/apm-emulation.c index aaca40283be9..4f568cb9af3f 100644 --- a/drivers/char/apm-emulation.c +++ b/drivers/char/apm-emulation.c @@ -393,7 +393,7 @@ static int apm_open(struct inode * inode, struct file * filp) return as ? 0 : -ENOMEM; } -static struct file_operations apm_bios_fops = { +static const struct file_operations apm_bios_fops = { .owner = THIS_MODULE, .read = apm_read, .poll = apm_poll, diff --git a/drivers/char/bfin-otp.c b/drivers/char/bfin-otp.c index e3dd24bff514..836d4f0a876f 100644 --- a/drivers/char/bfin-otp.c +++ b/drivers/char/bfin-otp.c @@ -217,7 +217,7 @@ static long bfin_otp_ioctl(struct file *filp, unsigned cmd, unsigned long arg) # define bfin_otp_ioctl NULL #endif -static struct file_operations bfin_otp_fops = { +static const struct file_operations bfin_otp_fops = { .owner = THIS_MODULE, .unlocked_ioctl = bfin_otp_ioctl, .read = bfin_otp_read, diff --git a/drivers/char/xilinx_hwicap/xilinx_hwicap.c b/drivers/char/xilinx_hwicap/xilinx_hwicap.c index f40ab699860f..4846d50199f3 100644 --- a/drivers/char/xilinx_hwicap/xilinx_hwicap.c +++ b/drivers/char/xilinx_hwicap/xilinx_hwicap.c @@ -559,7 +559,7 @@ static int hwicap_release(struct inode *inode, struct file *file) return status; } -static struct file_operations hwicap_fops = { +static const struct file_operations hwicap_fops = { .owner = THIS_MODULE, .write = hwicap_write, .read = hwicap_read, diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index bb11a429394a..662ed923d9eb 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1487,7 +1487,7 @@ static int gpiolib_open(struct inode *inode, struct file *file) return single_open(file, gpiolib_show, NULL); } -static struct file_operations gpiolib_operations = { +static const struct file_operations gpiolib_operations = { .open = gpiolib_open, .read = seq_read, .llseek = seq_lseek, diff --git a/drivers/hwmon/fschmd.c b/drivers/hwmon/fschmd.c index ea955edde87e..2a7a85a6dc36 100644 --- a/drivers/hwmon/fschmd.c +++ b/drivers/hwmon/fschmd.c @@ -915,7 +915,7 @@ static int watchdog_ioctl(struct inode *inode, struct file *filp, return ret; } -static struct file_operations watchdog_fops = { +static const struct file_operations watchdog_fops = { .owner = THIS_MODULE, .llseek = no_llseek, .open = watchdog_open, diff --git a/drivers/lguest/lguest_user.c b/drivers/lguest/lguest_user.c index b4d3f7ca554f..bd1632388e4a 100644 --- a/drivers/lguest/lguest_user.c +++ b/drivers/lguest/lguest_user.c @@ -508,7 +508,7 @@ static int close(struct inode *inode, struct file *file) * uses: reading and writing a character device called /dev/lguest. All the * work happens in the read(), write() and close() routines: */ -static struct file_operations lguest_fops = { +static const struct file_operations lguest_fops = { .owner = THIS_MODULE, .release = close, .write = write, diff --git a/drivers/media/dvb/dvb-core/dmxdev.c b/drivers/media/dvb/dvb-core/dmxdev.c index 3750ff48cba1..516414983593 100644 --- a/drivers/media/dvb/dvb-core/dmxdev.c +++ b/drivers/media/dvb/dvb-core/dmxdev.c @@ -1203,7 +1203,7 @@ static unsigned int dvb_dvr_poll(struct file *file, poll_table *wait) return mask; } -static struct file_operations dvb_dvr_fops = { +static const struct file_operations dvb_dvr_fops = { .owner = THIS_MODULE, .read = dvb_dvr_read, .write = dvb_dvr_write, diff --git a/drivers/media/dvb/firewire/firedtv-ci.c b/drivers/media/dvb/firewire/firedtv-ci.c index eeb80d0ea3ff..853e04b7cb36 100644 --- a/drivers/media/dvb/firewire/firedtv-ci.c +++ b/drivers/media/dvb/firewire/firedtv-ci.c @@ -215,7 +215,7 @@ static unsigned int fdtv_ca_io_poll(struct file *file, poll_table *wait) return POLLIN; } -static struct file_operations fdtv_ca_fops = { +static const struct file_operations fdtv_ca_fops = { .owner = THIS_MODULE, .ioctl = dvb_generic_ioctl, .open = dvb_generic_open, diff --git a/drivers/misc/phantom.c b/drivers/misc/phantom.c index fa57b67593ae..90a95ce8dc34 100644 --- a/drivers/misc/phantom.c +++ b/drivers/misc/phantom.c @@ -271,7 +271,7 @@ static unsigned int phantom_poll(struct file *file, poll_table *wait) return mask; } -static struct file_operations phantom_file_ops = { +static const struct file_operations phantom_file_ops = { .open = phantom_open, .release = phantom_release, .unlocked_ioctl = phantom_ioctl, diff --git a/drivers/misc/sgi-gru/grufile.c b/drivers/misc/sgi-gru/grufile.c index 300e7ba391a0..41c8fe2a928c 100644 --- a/drivers/misc/sgi-gru/grufile.c +++ b/drivers/misc/sgi-gru/grufile.c @@ -53,7 +53,6 @@ struct gru_stats_s gru_stats; /* Guaranteed user available resources on each node */ static int max_user_cbrs, max_user_dsr_bytes; -static struct file_operations gru_fops; static struct miscdevice gru_miscdev; @@ -426,7 +425,7 @@ static void __exit gru_exit(void) gru_proc_exit(); } -static struct file_operations gru_fops = { +static const struct file_operations gru_fops = { .owner = THIS_MODULE, .unlocked_ioctl = gru_file_unlocked_ioctl, .mmap = gru_file_mmap, diff --git a/drivers/mmc/core/debugfs.c b/drivers/mmc/core/debugfs.c index 610dbd1fcc82..96d10f40fb23 100644 --- a/drivers/mmc/core/debugfs.c +++ b/drivers/mmc/core/debugfs.c @@ -240,7 +240,7 @@ static int mmc_ext_csd_release(struct inode *inode, struct file *file) return 0; } -static struct file_operations mmc_dbg_ext_csd_fops = { +static const struct file_operations mmc_dbg_ext_csd_fops = { .open = mmc_ext_csd_open, .read = mmc_ext_csd_read, .release = mmc_ext_csd_release, diff --git a/drivers/s390/cio/qdio_debug.c b/drivers/s390/cio/qdio_debug.c index 1b78f639ead3..76769978285f 100644 --- a/drivers/s390/cio/qdio_debug.c +++ b/drivers/s390/cio/qdio_debug.c @@ -125,7 +125,7 @@ static int qstat_seq_open(struct inode *inode, struct file *filp) filp->f_path.dentry->d_inode->i_private); } -static struct file_operations debugfs_fops = { +static const struct file_operations debugfs_fops = { .owner = THIS_MODULE, .open = qstat_seq_open, .read = seq_read, diff --git a/drivers/s390/cio/qdio_perf.c b/drivers/s390/cio/qdio_perf.c index eff943923c6f..968e3c7c2632 100644 --- a/drivers/s390/cio/qdio_perf.c +++ b/drivers/s390/cio/qdio_perf.c @@ -84,7 +84,7 @@ static int qdio_perf_seq_open(struct inode *inode, struct file *filp) return single_open(filp, qdio_perf_proc_show, NULL); } -static struct file_operations qdio_perf_proc_fops = { +static const struct file_operations qdio_perf_proc_fops = { .owner = THIS_MODULE, .open = qdio_perf_seq_open, .read = seq_read, diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 0cb049f5cc56..747a5e5c1276 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1317,7 +1317,7 @@ static void sg_rq_end_io(struct request *rq, int uptodate) } } -static struct file_operations sg_fops = { +static const struct file_operations sg_fops = { .owner = THIS_MODULE, .read = sg_read, .write = sg_write, @@ -2194,9 +2194,11 @@ static int sg_proc_seq_show_int(struct seq_file *s, void *v); static int sg_proc_single_open_adio(struct inode *inode, struct file *file); static ssize_t sg_proc_write_adio(struct file *filp, const char __user *buffer, size_t count, loff_t *off); -static struct file_operations adio_fops = { - /* .owner, .read and .llseek added in sg_proc_init() */ +static const struct file_operations adio_fops = { + .owner = THIS_MODULE, .open = sg_proc_single_open_adio, + .read = seq_read, + .llseek = seq_lseek, .write = sg_proc_write_adio, .release = single_release, }; @@ -2204,23 +2206,32 @@ static struct file_operations adio_fops = { static int sg_proc_single_open_dressz(struct inode *inode, struct file *file); static ssize_t sg_proc_write_dressz(struct file *filp, const char __user *buffer, size_t count, loff_t *off); -static struct file_operations dressz_fops = { +static const struct file_operations dressz_fops = { + .owner = THIS_MODULE, .open = sg_proc_single_open_dressz, + .read = seq_read, + .llseek = seq_lseek, .write = sg_proc_write_dressz, .release = single_release, }; static int sg_proc_seq_show_version(struct seq_file *s, void *v); static int sg_proc_single_open_version(struct inode *inode, struct file *file); -static struct file_operations version_fops = { +static const struct file_operations version_fops = { + .owner = THIS_MODULE, .open = sg_proc_single_open_version, + .read = seq_read, + .llseek = seq_lseek, .release = single_release, }; static int sg_proc_seq_show_devhdr(struct seq_file *s, void *v); static int sg_proc_single_open_devhdr(struct inode *inode, struct file *file); -static struct file_operations devhdr_fops = { +static const struct file_operations devhdr_fops = { + .owner = THIS_MODULE, .open = sg_proc_single_open_devhdr, + .read = seq_read, + .llseek = seq_lseek, .release = single_release, }; @@ -2229,8 +2240,11 @@ static int sg_proc_open_dev(struct inode *inode, struct file *file); static void * dev_seq_start(struct seq_file *s, loff_t *pos); static void * dev_seq_next(struct seq_file *s, void *v, loff_t *pos); static void dev_seq_stop(struct seq_file *s, void *v); -static struct file_operations dev_fops = { +static const struct file_operations dev_fops = { + .owner = THIS_MODULE, .open = sg_proc_open_dev, + .read = seq_read, + .llseek = seq_lseek, .release = seq_release, }; static const struct seq_operations dev_seq_ops = { @@ -2242,8 +2256,11 @@ static const struct seq_operations dev_seq_ops = { static int sg_proc_seq_show_devstrs(struct seq_file *s, void *v); static int sg_proc_open_devstrs(struct inode *inode, struct file *file); -static struct file_operations devstrs_fops = { +static const struct file_operations devstrs_fops = { + .owner = THIS_MODULE, .open = sg_proc_open_devstrs, + .read = seq_read, + .llseek = seq_lseek, .release = seq_release, }; static const struct seq_operations devstrs_seq_ops = { @@ -2255,8 +2272,11 @@ static const struct seq_operations devstrs_seq_ops = { static int sg_proc_seq_show_debug(struct seq_file *s, void *v); static int sg_proc_open_debug(struct inode *inode, struct file *file); -static struct file_operations debug_fops = { +static const struct file_operations debug_fops = { + .owner = THIS_MODULE, .open = sg_proc_open_debug, + .read = seq_read, + .llseek = seq_lseek, .release = seq_release, }; static const struct seq_operations debug_seq_ops = { @@ -2269,7 +2289,7 @@ static const struct seq_operations debug_seq_ops = { struct sg_proc_leaf { const char * name; - struct file_operations * fops; + const struct file_operations * fops; }; static struct sg_proc_leaf sg_proc_leaf_arr[] = { @@ -2295,9 +2315,6 @@ sg_proc_init(void) for (k = 0; k < num_leaves; ++k) { leaf = &sg_proc_leaf_arr[k]; mask = leaf->fops->write ? S_IRUGO | S_IWUSR : S_IRUGO; - leaf->fops->owner = THIS_MODULE; - leaf->fops->read = seq_read; - leaf->fops->llseek = seq_lseek; proc_create(leaf->name, mask, sg_proc_sgp, leaf->fops); } return 0; diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index f921bd1109e1..5d23983f02fc 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -537,7 +537,7 @@ static int spidev_release(struct inode *inode, struct file *filp) return status; } -static struct file_operations spidev_fops = { +static const struct file_operations spidev_fops = { .owner = THIS_MODULE, /* REVISIT switch to aio primitives, so that userspace * gets more complete API coverage. It'll simplify things diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index 333ee02e7b2b..864f0ba6a344 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -993,7 +993,7 @@ skip_io_on_zombie: return retval; } -static struct file_operations fops = { +static const struct file_operations fops = { .owner = THIS_MODULE, .read = usbtmc_read, .write = usbtmc_write, diff --git a/drivers/usb/gadget/printer.c b/drivers/usb/gadget/printer.c index 29500154d00c..2d867fd22413 100644 --- a/drivers/usb/gadget/printer.c +++ b/drivers/usb/gadget/printer.c @@ -875,7 +875,7 @@ printer_ioctl(struct file *fd, unsigned int code, unsigned long arg) } /* used after endpoint configuration */ -static struct file_operations printer_io_operations = { +static const struct file_operations printer_io_operations = { .owner = THIS_MODULE, .open = printer_open, .read = printer_read, diff --git a/drivers/usb/host/whci/debug.c b/drivers/usb/host/whci/debug.c index cf2d45946c57..2273c815941f 100644 --- a/drivers/usb/host/whci/debug.c +++ b/drivers/usb/host/whci/debug.c @@ -134,7 +134,7 @@ static int pzl_open(struct inode *inode, struct file *file) return single_open(file, pzl_print, inode->i_private); } -static struct file_operations di_fops = { +static const struct file_operations di_fops = { .open = di_open, .read = seq_read, .llseek = seq_lseek, @@ -142,7 +142,7 @@ static struct file_operations di_fops = { .owner = THIS_MODULE, }; -static struct file_operations asl_fops = { +static const struct file_operations asl_fops = { .open = asl_open, .read = seq_read, .llseek = seq_lseek, @@ -150,7 +150,7 @@ static struct file_operations asl_fops = { .owner = THIS_MODULE, }; -static struct file_operations pzl_fops = { +static const struct file_operations pzl_fops = { .open = pzl_open, .read = seq_read, .llseek = seq_lseek, diff --git a/drivers/usb/misc/rio500.c b/drivers/usb/misc/rio500.c index d645f3899fe1..32d0199d0c32 100644 --- a/drivers/usb/misc/rio500.c +++ b/drivers/usb/misc/rio500.c @@ -429,8 +429,7 @@ read_rio(struct file *file, char __user *buffer, size_t count, loff_t * ppos) return read_count; } -static struct -file_operations usb_rio_fops = { +static const struct file_operations usb_rio_fops = { .owner = THIS_MODULE, .read = read_rio, .write = write_rio, diff --git a/drivers/uwb/uwb-debug.c b/drivers/uwb/uwb-debug.c index 4a42993700c1..2eecec0c13c9 100644 --- a/drivers/uwb/uwb-debug.c +++ b/drivers/uwb/uwb-debug.c @@ -205,7 +205,7 @@ static ssize_t command_write(struct file *file, const char __user *buf, return ret < 0 ? ret : len; } -static struct file_operations command_fops = { +static const struct file_operations command_fops = { .open = command_open, .write = command_write, .read = NULL, @@ -255,7 +255,7 @@ static int reservations_open(struct inode *inode, struct file *file) return single_open(file, reservations_print, inode->i_private); } -static struct file_operations reservations_fops = { +static const struct file_operations reservations_fops = { .open = reservations_open, .read = seq_read, .llseek = seq_lseek, @@ -283,7 +283,7 @@ static int drp_avail_open(struct inode *inode, struct file *file) return single_open(file, drp_avail_print, inode->i_private); } -static struct file_operations drp_avail_fops = { +static const struct file_operations drp_avail_fops = { .open = drp_avail_open, .read = seq_read, .llseek = seq_lseek, diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 80599b4e42bd..4484eb3408af 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2326,7 +2326,7 @@ int btrfs_sync_file(struct file *file, struct dentry *dentry, int datasync); int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end, int skip_pinned); int btrfs_check_file(struct btrfs_root *root, struct inode *inode); -extern struct file_operations btrfs_file_operations; +extern const struct file_operations btrfs_file_operations; int btrfs_drop_extents(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode, u64 start, u64 end, u64 locked_end, diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index a3492a3ad96b..9ed17dbe5c6e 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1196,7 +1196,7 @@ static int btrfs_file_mmap(struct file *filp, struct vm_area_struct *vma) return 0; } -struct file_operations btrfs_file_operations = { +const struct file_operations btrfs_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, .aio_read = generic_file_aio_read, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index e9b76bcd1c12..b9fe06d751c0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -62,7 +62,7 @@ static const struct inode_operations btrfs_special_inode_operations; static const struct inode_operations btrfs_file_inode_operations; static const struct address_space_operations btrfs_aops; static const struct address_space_operations btrfs_symlink_aops; -static struct file_operations btrfs_dir_file_operations; +static const struct file_operations btrfs_dir_file_operations; static struct extent_io_ops btrfs_extent_io_ops; static struct kmem_cache *btrfs_inode_cachep; @@ -5544,7 +5544,7 @@ static const struct inode_operations btrfs_dir_ro_inode_operations = { .permission = btrfs_permission, }; -static struct file_operations btrfs_dir_file_operations = { +static const struct file_operations btrfs_dir_file_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .readdir = btrfs_real_readdir, diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 761af77491f5..b0ab5219becb 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -770,7 +770,7 @@ static int jbd2_seq_info_release(struct inode *inode, struct file *file) return seq_release(inode, file); } -static struct file_operations jbd2_seq_info_fops = { +static const struct file_operations jbd2_seq_info_fops = { .owner = THIS_MODULE, .open = jbd2_seq_info_open, .read = seq_read, diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 00388d2a3c99..5c01fc148ce8 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -176,7 +176,7 @@ static const struct file_operations exports_operations = { extern int nfsd_pool_stats_open(struct inode *inode, struct file *file); extern int nfsd_pool_stats_release(struct inode *inode, struct file *file); -static struct file_operations pool_stats_operations = { +static const struct file_operations pool_stats_operations = { .open = nfsd_pool_stats_open, .read = seq_read, .llseek = seq_lseek, diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index 1a4fa04cf071..e097099bfc8f 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -697,7 +697,7 @@ not_empty: return 0; } -struct file_operations nilfs_dir_operations = { +const struct file_operations nilfs_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .readdir = nilfs_readdir, diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 7d7b4983dee3..30292df443ce 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -134,7 +134,7 @@ static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma) * We have mostly NULL's here: the current defaults are ok for * the nilfs filesystem. */ -struct file_operations nilfs_file_operations = { +const struct file_operations nilfs_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, .write = do_sync_write, diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index b18c4998f8d0..f6326112d647 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -433,7 +433,7 @@ static const struct address_space_operations def_mdt_aops = { }; static const struct inode_operations def_mdt_iops; -static struct file_operations def_mdt_fops; +static const struct file_operations def_mdt_fops; /* * NILFS2 uses pseudo inodes for meta data files such as DAT, cpfile, sufile, diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index bad7368782d0..4da6f67e9a91 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -294,9 +294,9 @@ void nilfs_clear_gcdat_inode(struct the_nilfs *); /* * Inodes and files operations */ -extern struct file_operations nilfs_dir_operations; +extern const struct file_operations nilfs_dir_operations; extern const struct inode_operations nilfs_file_inode_operations; -extern struct file_operations nilfs_file_operations; +extern const struct file_operations nilfs_file_operations; extern const struct address_space_operations nilfs_aops; extern const struct inode_operations nilfs_dir_inode_operations; extern const struct inode_operations nilfs_special_inode_operations; diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 09cc25d04611..c452d116b892 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -966,7 +966,7 @@ static ssize_t o2hb_debug_read(struct file *file, char __user *buf, } #endif /* CONFIG_DEBUG_FS */ -static struct file_operations o2hb_debug_fops = { +static const struct file_operations o2hb_debug_fops = { .open = o2hb_debug_open, .release = o2hb_debug_release, .read = o2hb_debug_read, diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c index cfb2be708abe..da794bc07a6c 100644 --- a/fs/ocfs2/cluster/netdebug.c +++ b/fs/ocfs2/cluster/netdebug.c @@ -207,7 +207,7 @@ static int nst_fop_release(struct inode *inode, struct file *file) return seq_release_private(inode, file); } -static struct file_operations nst_seq_fops = { +static const struct file_operations nst_seq_fops = { .open = nst_fop_open, .read = seq_read, .llseek = seq_lseek, @@ -388,7 +388,7 @@ static int sc_fop_release(struct inode *inode, struct file *file) return seq_release_private(inode, file); } -static struct file_operations sc_seq_fops = { +static const struct file_operations sc_seq_fops = { .open = sc_fop_open, .read = seq_read, .llseek = seq_lseek, diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c index ca46002ec10e..42b0bad7a612 100644 --- a/fs/ocfs2/dlm/dlmdebug.c +++ b/fs/ocfs2/dlm/dlmdebug.c @@ -478,7 +478,7 @@ bail: return -ENOMEM; } -static struct file_operations debug_purgelist_fops = { +static const struct file_operations debug_purgelist_fops = { .open = debug_purgelist_open, .release = debug_buffer_release, .read = debug_buffer_read, @@ -538,7 +538,7 @@ bail: return -ENOMEM; } -static struct file_operations debug_mle_fops = { +static const struct file_operations debug_mle_fops = { .open = debug_mle_open, .release = debug_buffer_release, .read = debug_buffer_read, @@ -741,7 +741,7 @@ static int debug_lockres_release(struct inode *inode, struct file *file) return seq_release_private(inode, file); } -static struct file_operations debug_lockres_fops = { +static const struct file_operations debug_lockres_fops = { .open = debug_lockres_open, .release = debug_lockres_release, .read = seq_read, @@ -925,7 +925,7 @@ bail: return -ENOMEM; } -static struct file_operations debug_state_fops = { +static const struct file_operations debug_state_fops = { .open = debug_state_open, .release = debug_buffer_release, .read = debug_buffer_read, diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 4cc3c890a2cd..c0e48aeebb1c 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -373,7 +373,7 @@ static ssize_t ocfs2_debug_read(struct file *file, char __user *buf, } #endif /* CONFIG_DEBUG_FS */ -static struct file_operations ocfs2_osb_debug_fops = { +static const struct file_operations ocfs2_osb_debug_fops = { .open = ocfs2_osb_debug_open, .release = ocfs2_debug_release, .read = ocfs2_debug_read, diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c index 3680bae335b5..b42d62419034 100644 --- a/fs/omfs/dir.c +++ b/fs/omfs/dir.c @@ -498,7 +498,7 @@ const struct inode_operations omfs_dir_inops = { .rmdir = omfs_rmdir, }; -struct file_operations omfs_dir_operations = { +const struct file_operations omfs_dir_operations = { .read = generic_read_dir, .readdir = omfs_readdir, .llseek = generic_file_llseek, diff --git a/fs/omfs/file.c b/fs/omfs/file.c index 4845fbb18e6e..399487c09364 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -322,7 +322,7 @@ static sector_t omfs_bmap(struct address_space *mapping, sector_t block) return generic_block_bmap(mapping, block, omfs_get_block); } -struct file_operations omfs_file_operations = { +const struct file_operations omfs_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, .write = do_sync_write, diff --git a/fs/omfs/omfs.h b/fs/omfs/omfs.h index df71039945ac..ebe2fdbe535e 100644 --- a/fs/omfs/omfs.h +++ b/fs/omfs/omfs.h @@ -44,14 +44,14 @@ extern int omfs_allocate_range(struct super_block *sb, int min_request, extern int omfs_clear_range(struct super_block *sb, u64 block, int count); /* dir.c */ -extern struct file_operations omfs_dir_operations; +extern const struct file_operations omfs_dir_operations; extern const struct inode_operations omfs_dir_inops; extern int omfs_make_empty(struct inode *inode, struct super_block *sb); extern int omfs_is_bad(struct omfs_sb_info *sbi, struct omfs_header *header, u64 fsblock); /* file.c */ -extern struct file_operations omfs_file_operations; +extern const struct file_operations omfs_file_operations; extern const struct inode_operations omfs_file_inops; extern const struct address_space_operations omfs_aops; extern void omfs_make_empty_table(struct buffer_head *bh, int offset); diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b62bb9294d0c..0008dee66514 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -37,7 +37,7 @@ extern void cgroup_exit(struct task_struct *p, int run_callbacks); extern int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); -extern struct file_operations proc_cgroup_operations; +extern const struct file_operations proc_cgroup_operations; /* Define the enumeration of all cgroup subsystems */ #define SUBSYS(_x) _x ## _subsys_id, diff --git a/include/linux/fs.h b/include/linux/fs.h index 2adaa2529f18..a1e6899d4b6c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2446,7 +2446,7 @@ static int __fops ## _open(struct inode *inode, struct file *file) \ __simple_attr_check_format(__fmt, 0ull); \ return simple_attr_open(inode, file, __get, __set, __fmt); \ } \ -static struct file_operations __fops = { \ +static const struct file_operations __fops = { \ .owner = THIS_MODULE, \ .open = __fops ## _open, \ .release = simple_attr_release, \ diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 7ccba4bc5e3b..d2b88596efde 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -703,7 +703,7 @@ static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode); static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry); static int cgroup_populate_dir(struct cgroup *cgrp); static const struct inode_operations cgroup_dir_inode_operations; -static struct file_operations proc_cgroupstats_operations; +static const struct file_operations proc_cgroupstats_operations; static struct backing_dev_info cgroup_backing_dev_info = { .name = "cgroup", @@ -1863,7 +1863,7 @@ static int cgroup_seqfile_release(struct inode *inode, struct file *file) return single_release(inode, file); } -static struct file_operations cgroup_seqfile_operations = { +static const struct file_operations cgroup_seqfile_operations = { .read = seq_read, .write = cgroup_file_write, .llseek = seq_lseek, @@ -1922,7 +1922,7 @@ static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry, return simple_rename(old_dir, old_dentry, new_dir, new_dentry); } -static struct file_operations cgroup_file_operations = { +static const struct file_operations cgroup_file_operations = { .read = cgroup_file_read, .write = cgroup_file_write, .llseek = generic_file_llseek, @@ -3369,7 +3369,7 @@ static int cgroup_open(struct inode *inode, struct file *file) return single_open(file, proc_cgroup_show, pid); } -struct file_operations proc_cgroup_operations = { +const struct file_operations proc_cgroup_operations = { .open = cgroup_open, .read = seq_read, .llseek = seq_lseek, @@ -3398,7 +3398,7 @@ static int cgroupstats_open(struct inode *inode, struct file *file) return single_open(file, proc_cgroupstats_show, NULL); } -static struct file_operations proc_cgroupstats_operations = { +static const struct file_operations proc_cgroupstats_operations = { .open = cgroupstats_open, .read = seq_read, .llseek = seq_lseek, diff --git a/kernel/kprobes.c b/kernel/kprobes.c index cfadc1291d0b..5240d75f4c60 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1333,7 +1333,7 @@ static int __kprobes kprobes_open(struct inode *inode, struct file *filp) return seq_open(filp, &kprobes_seq_ops); } -static struct file_operations debugfs_kprobes_operations = { +static const struct file_operations debugfs_kprobes_operations = { .open = kprobes_open, .read = seq_read, .llseek = seq_lseek, @@ -1515,7 +1515,7 @@ static ssize_t write_enabled_file_bool(struct file *file, return count; } -static struct file_operations fops_kp = { +static const struct file_operations fops_kp = { .read = read_enabled_file_bool, .write = write_enabled_file_bool, }; diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index c89f5e9fd173..179e6ad80dc0 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -93,7 +93,7 @@ static int rcudata_open(struct inode *inode, struct file *file) return single_open(file, show_rcudata, NULL); } -static struct file_operations rcudata_fops = { +static const struct file_operations rcudata_fops = { .owner = THIS_MODULE, .open = rcudata_open, .read = seq_read, @@ -145,7 +145,7 @@ static int rcudata_csv_open(struct inode *inode, struct file *file) return single_open(file, show_rcudata_csv, NULL); } -static struct file_operations rcudata_csv_fops = { +static const struct file_operations rcudata_csv_fops = { .owner = THIS_MODULE, .open = rcudata_csv_open, .read = seq_read, @@ -196,7 +196,7 @@ static int rcuhier_open(struct inode *inode, struct file *file) return single_open(file, show_rcuhier, NULL); } -static struct file_operations rcuhier_fops = { +static const struct file_operations rcuhier_fops = { .owner = THIS_MODULE, .open = rcuhier_open, .read = seq_read, @@ -222,7 +222,7 @@ static int rcugp_open(struct inode *inode, struct file *file) return single_open(file, show_rcugp, NULL); } -static struct file_operations rcugp_fops = { +static const struct file_operations rcugp_fops = { .owner = THIS_MODULE, .open = rcugp_open, .read = seq_read, @@ -276,7 +276,7 @@ static int rcu_pending_open(struct inode *inode, struct file *file) return single_open(file, show_rcu_pending, NULL); } -static struct file_operations rcu_pending_fops = { +static const struct file_operations rcu_pending_fops = { .owner = THIS_MODULE, .open = rcu_pending_open, .read = seq_read, diff --git a/kernel/sched.c b/kernel/sched.c index ee61f454a98b..1535f3884b88 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -780,7 +780,7 @@ static int sched_feat_open(struct inode *inode, struct file *filp) return single_open(filp, sched_feat_show, NULL); } -static struct file_operations sched_feat_fops = { +static const struct file_operations sched_feat_fops = { .open = sched_feat_open, .write = sched_feat_write, .read = seq_read, diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index fddd69d16e03..1b5b7aa2fdfd 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -275,7 +275,7 @@ static int timer_list_open(struct inode *inode, struct file *filp) return single_open(filp, timer_list_show, NULL); } -static struct file_operations timer_list_fops = { +static const struct file_operations timer_list_fops = { .open = timer_list_open, .read = seq_read, .llseek = seq_lseek, diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c index 4cde8b9c716f..ee5681f8d7ec 100644 --- a/kernel/time/timer_stats.c +++ b/kernel/time/timer_stats.c @@ -395,7 +395,7 @@ static int tstats_open(struct inode *inode, struct file *filp) return single_open(filp, tstats_show, NULL); } -static struct file_operations tstats_fops = { +static const struct file_operations tstats_fops = { .open = tstats_open, .read = seq_read, .write = tstats_write, diff --git a/samples/tracepoints/tracepoint-sample.c b/samples/tracepoints/tracepoint-sample.c index 9cf80a11e8b6..26fab33ffa8c 100644 --- a/samples/tracepoints/tracepoint-sample.c +++ b/samples/tracepoints/tracepoint-sample.c @@ -28,7 +28,7 @@ static int my_open(struct inode *inode, struct file *file) return -EPERM; } -static struct file_operations mark_ops = { +static const struct file_operations mark_ops = { .open = my_open, }; diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c index 8e9777b76405..0c72c9c38956 100644 --- a/security/integrity/ima/ima_fs.c +++ b/security/integrity/ima/ima_fs.c @@ -43,7 +43,7 @@ static ssize_t ima_show_htable_violations(struct file *filp, return ima_show_htable_value(buf, count, ppos, &ima_htable.violations); } -static struct file_operations ima_htable_violations_ops = { +static const struct file_operations ima_htable_violations_ops = { .read = ima_show_htable_violations }; @@ -55,7 +55,7 @@ static ssize_t ima_show_measurements_count(struct file *filp, } -static struct file_operations ima_measurements_count_ops = { +static const struct file_operations ima_measurements_count_ops = { .read = ima_show_measurements_count }; @@ -158,7 +158,7 @@ static int ima_measurements_open(struct inode *inode, struct file *file) return seq_open(file, &ima_measurments_seqops); } -static struct file_operations ima_measurements_ops = { +static const struct file_operations ima_measurements_ops = { .open = ima_measurements_open, .read = seq_read, .llseek = seq_lseek, @@ -233,7 +233,7 @@ static int ima_ascii_measurements_open(struct inode *inode, struct file *file) return seq_open(file, &ima_ascii_measurements_seqops); } -static struct file_operations ima_ascii_measurements_ops = { +static const struct file_operations ima_ascii_measurements_ops = { .open = ima_ascii_measurements_open, .read = seq_read, .llseek = seq_lseek, @@ -313,7 +313,7 @@ static int ima_release_policy(struct inode *inode, struct file *file) return 0; } -static struct file_operations ima_measure_policy_ops = { +static const struct file_operations ima_measure_policy_ops = { .open = ima_open_policy, .write = ima_write_policy, .release = ima_release_policy diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index b5e7e3f1183f..e79c54034bcd 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2625,7 +2625,7 @@ static int vcpu_stat_get(void *_offset, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, NULL, "%llu\n"); -static struct file_operations *stat_fops[] = { +static const struct file_operations *stat_fops[] = { [KVM_STAT_VCPU] = &vcpu_stat_fops, [KVM_STAT_VM] = &vm_stat_fops, }; -- cgit v1.2.3 From 4e649152cbaa1aedd01821d200ab9d597fe469e4 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Thu, 1 Oct 2009 15:44:11 -0700 Subject: memcg: some modification to softlimit under hierarchical memory reclaim. This patch clean up/fixes for memcg's uncharge soft limit path. Problems: Now, res_counter_charge()/uncharge() handles softlimit information at charge/uncharge and softlimit-check is done when event counter per memcg goes over limit. Now, event counter per memcg is updated only when memory usage is over soft limit. Here, considering hierarchical memcg management, ancesotors should be taken care of. Now, ancerstors(hierarchy) are handled in charge() but not in uncharge(). This is not good. Prolems: 1. memcg's event counter incremented only when softlimit hits. That's bad. It makes event counter hard to be reused for other purpose. 2. At uncharge, only the lowest level rescounter is handled. This is bug. Because ancesotor's event counter is not incremented, children should take care of them. 3. res_counter_uncharge()'s 3rd argument is NULL in most case. ops under res_counter->lock should be small. No "if" sentense is better. Fixes: * Removed soft_limit_xx poitner and checks in charge and uncharge. Do-check-only-when-necessary scheme works enough well without them. * make event-counter of memcg incremented at every charge/uncharge. (per-cpu area will be accessed soon anyway) * All ancestors are checked at soft-limit-check. This is necessary because ancesotor's event counter may never be modified. Then, they should be checked at the same time. Reviewed-by: Daisuke Nishimura Signed-off-by: KAMEZAWA Hiroyuki Cc: Paul Menage Cc: Li Zefan Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/res_counter.h | 6 +-- kernel/res_counter.c | 18 +------ mm/memcontrol.c | 113 ++++++++++++++++++++------------------------ 3 files changed, 54 insertions(+), 83 deletions(-) (limited to 'include/linux') diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index 731af71cddc9..fcb9884df618 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -114,8 +114,7 @@ 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, - struct res_counter **soft_limit_at); + unsigned long val, struct res_counter **limit_fail_at); /* * uncharge - tell that some portion of the resource is released @@ -128,8 +127,7 @@ 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, - bool *was_soft_limit_excess); +void res_counter_uncharge(struct res_counter *counter, unsigned long val); static inline bool res_counter_limit_check_locked(struct res_counter *cnt) { diff --git a/kernel/res_counter.c b/kernel/res_counter.c index 88faec23e833..bcdabf37c40b 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -37,27 +37,17 @@ int res_counter_charge_locked(struct res_counter *counter, unsigned long val) } int res_counter_charge(struct res_counter *counter, unsigned long val, - struct res_counter **limit_fail_at, - struct res_counter **soft_limit_fail_at) + struct res_counter **limit_fail_at) { int ret; unsigned long flags; struct res_counter *c, *u; *limit_fail_at = NULL; - if (soft_limit_fail_at) - *soft_limit_fail_at = NULL; local_irq_save(flags); for (c = counter; c != NULL; c = c->parent) { spin_lock(&c->lock); ret = res_counter_charge_locked(c, val); - /* - * With soft limits, we return the highest ancestor - * that exceeds its soft limit - */ - if (soft_limit_fail_at && - !res_counter_soft_limit_check_locked(c)) - *soft_limit_fail_at = c; spin_unlock(&c->lock); if (ret < 0) { *limit_fail_at = c; @@ -85,8 +75,7 @@ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val) counter->usage -= val; } -void res_counter_uncharge(struct res_counter *counter, unsigned long val, - bool *was_soft_limit_excess) +void res_counter_uncharge(struct res_counter *counter, unsigned long val) { unsigned long flags; struct res_counter *c; @@ -94,9 +83,6 @@ void res_counter_uncharge(struct res_counter *counter, unsigned long val, local_irq_save(flags); for (c = counter; c != NULL; c = c->parent) { spin_lock(&c->lock); - if (was_soft_limit_excess) - *was_soft_limit_excess = - !res_counter_soft_limit_check_locked(c); res_counter_uncharge_locked(c, val); spin_unlock(&c->lock); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 21a30629ca80..1ae8c439584a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -352,16 +352,6 @@ __mem_cgroup_remove_exceeded(struct mem_cgroup *mem, mz->on_tree = false; } -static void -mem_cgroup_insert_exceeded(struct mem_cgroup *mem, - struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz) -{ - spin_lock(&mctz->lock); - __mem_cgroup_insert_exceeded(mem, mz, mctz); - spin_unlock(&mctz->lock); -} - static void mem_cgroup_remove_exceeded(struct mem_cgroup *mem, struct mem_cgroup_per_zone *mz, @@ -392,34 +382,40 @@ static bool mem_cgroup_soft_limit_check(struct mem_cgroup *mem) static void mem_cgroup_update_tree(struct mem_cgroup *mem, struct page *page) { - unsigned long long prev_usage_in_excess, new_usage_in_excess; - bool updated_tree = false; + unsigned long long new_usage_in_excess; struct mem_cgroup_per_zone *mz; struct mem_cgroup_tree_per_zone *mctz; - - mz = mem_cgroup_zoneinfo(mem, page_to_nid(page), page_zonenum(page)); + int nid = page_to_nid(page); + int zid = page_zonenum(page); mctz = soft_limit_tree_from_page(page); /* - * We do updates in lazy mode, mem's are removed - * lazily from the per-zone, per-node rb tree + * Necessary to update all ancestors when hierarchy is used. + * because their event counter is not touched. */ - prev_usage_in_excess = mz->usage_in_excess; - - new_usage_in_excess = res_counter_soft_limit_excess(&mem->res); - if (prev_usage_in_excess) { - mem_cgroup_remove_exceeded(mem, mz, mctz); - updated_tree = true; - } - if (!new_usage_in_excess) - goto done; - mem_cgroup_insert_exceeded(mem, mz, mctz); - -done: - if (updated_tree) { - spin_lock(&mctz->lock); - mz->usage_in_excess = new_usage_in_excess; - spin_unlock(&mctz->lock); + for (; mem; mem = parent_mem_cgroup(mem)) { + mz = mem_cgroup_zoneinfo(mem, nid, zid); + new_usage_in_excess = + res_counter_soft_limit_excess(&mem->res); + /* + * We have to update the tree if mz is on RB-tree or + * mem is over its softlimit. + */ + if (new_usage_in_excess || mz->on_tree) { + spin_lock(&mctz->lock); + /* if on-tree, remove it */ + if (mz->on_tree) + __mem_cgroup_remove_exceeded(mem, mz, mctz); + /* + * if over soft limit, insert again. mz->usage_in_excess + * will be updated properly. + */ + if (new_usage_in_excess) + __mem_cgroup_insert_exceeded(mem, mz, mctz); + else + mz->usage_in_excess = 0; + spin_unlock(&mctz->lock); + } } } @@ -1271,9 +1267,9 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup **memcg, bool oom, struct page *page) { - struct mem_cgroup *mem, *mem_over_limit, *mem_over_soft_limit; + struct mem_cgroup *mem, *mem_over_limit; int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; - struct res_counter *fail_res, *soft_fail_res = NULL; + struct res_counter *fail_res; if (unlikely(test_thread_flag(TIF_MEMDIE))) { /* Don't account this! */ @@ -1305,17 +1301,16 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, if (mem_cgroup_is_root(mem)) goto done; - ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res, - &soft_fail_res); + ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res); if (likely(!ret)) { if (!do_swap_account) break; ret = res_counter_charge(&mem->memsw, PAGE_SIZE, - &fail_res, NULL); + &fail_res); if (likely(!ret)) break; /* mem+swap counter fails */ - res_counter_uncharge(&mem->res, PAGE_SIZE, NULL); + res_counter_uncharge(&mem->res, PAGE_SIZE); flags |= MEM_CGROUP_RECLAIM_NOSWAP; mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw); @@ -1354,16 +1349,11 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, } } /* - * Insert just the ancestor, we should trickle down to the correct - * cgroup for reclaim, since the other nodes will be below their - * soft limit + * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree. + * if they exceeds softlimit. */ - if (soft_fail_res) { - mem_over_soft_limit = - mem_cgroup_from_res_counter(soft_fail_res, res); - if (mem_cgroup_soft_limit_check(mem_over_soft_limit)) - mem_cgroup_update_tree(mem_over_soft_limit, page); - } + if (mem_cgroup_soft_limit_check(mem)) + mem_cgroup_update_tree(mem, page); done: return 0; nomem: @@ -1438,10 +1428,9 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, if (unlikely(PageCgroupUsed(pc))) { unlock_page_cgroup(pc); if (!mem_cgroup_is_root(mem)) { - res_counter_uncharge(&mem->res, PAGE_SIZE, NULL); + res_counter_uncharge(&mem->res, PAGE_SIZE); if (do_swap_account) - res_counter_uncharge(&mem->memsw, PAGE_SIZE, - NULL); + res_counter_uncharge(&mem->memsw, PAGE_SIZE); } css_put(&mem->css); return; @@ -1520,7 +1509,7 @@ static int mem_cgroup_move_account(struct page_cgroup *pc, goto out; if (!mem_cgroup_is_root(from)) - res_counter_uncharge(&from->res, PAGE_SIZE, NULL); + res_counter_uncharge(&from->res, PAGE_SIZE); mem_cgroup_charge_statistics(from, pc, false); page = pc->page; @@ -1540,7 +1529,7 @@ static int mem_cgroup_move_account(struct page_cgroup *pc, } if (do_swap_account && !mem_cgroup_is_root(from)) - res_counter_uncharge(&from->memsw, PAGE_SIZE, NULL); + res_counter_uncharge(&from->memsw, PAGE_SIZE); css_put(&from->css); css_get(&to->css); @@ -1611,9 +1600,9 @@ uncharge: css_put(&parent->css); /* uncharge if move fails */ if (!mem_cgroup_is_root(parent)) { - res_counter_uncharge(&parent->res, PAGE_SIZE, NULL); + res_counter_uncharge(&parent->res, PAGE_SIZE); if (do_swap_account) - res_counter_uncharge(&parent->memsw, PAGE_SIZE, NULL); + res_counter_uncharge(&parent->memsw, PAGE_SIZE); } return ret; } @@ -1804,8 +1793,7 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, * calling css_tryget */ if (!mem_cgroup_is_root(memcg)) - res_counter_uncharge(&memcg->memsw, PAGE_SIZE, - NULL); + res_counter_uncharge(&memcg->memsw, PAGE_SIZE); mem_cgroup_swap_statistics(memcg, false); mem_cgroup_put(memcg); } @@ -1832,9 +1820,9 @@ void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem) if (!mem) return; if (!mem_cgroup_is_root(mem)) { - res_counter_uncharge(&mem->res, PAGE_SIZE, NULL); + res_counter_uncharge(&mem->res, PAGE_SIZE); if (do_swap_account) - res_counter_uncharge(&mem->memsw, PAGE_SIZE, NULL); + res_counter_uncharge(&mem->memsw, PAGE_SIZE); } css_put(&mem->css); } @@ -1849,7 +1837,6 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) struct page_cgroup *pc; struct mem_cgroup *mem = NULL; struct mem_cgroup_per_zone *mz; - bool soft_limit_excess = false; if (mem_cgroup_disabled()) return NULL; @@ -1889,10 +1876,10 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) } if (!mem_cgroup_is_root(mem)) { - res_counter_uncharge(&mem->res, PAGE_SIZE, &soft_limit_excess); + res_counter_uncharge(&mem->res, PAGE_SIZE); if (do_swap_account && (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT)) - res_counter_uncharge(&mem->memsw, PAGE_SIZE, NULL); + res_counter_uncharge(&mem->memsw, PAGE_SIZE); } if (ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) mem_cgroup_swap_statistics(mem, true); @@ -1909,7 +1896,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) mz = page_cgroup_zoneinfo(pc); unlock_page_cgroup(pc); - if (soft_limit_excess && mem_cgroup_soft_limit_check(mem)) + if (mem_cgroup_soft_limit_check(mem)) mem_cgroup_update_tree(mem, page); /* at swapout, this memcg will be accessed to record to swap */ if (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT) @@ -1987,7 +1974,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t ent) * This memcg can be obsolete one. We avoid calling css_tryget */ if (!mem_cgroup_is_root(memcg)) - res_counter_uncharge(&memcg->memsw, PAGE_SIZE, NULL); + res_counter_uncharge(&memcg->memsw, PAGE_SIZE); mem_cgroup_swap_statistics(memcg, false); mem_cgroup_put(memcg); } -- cgit v1.2.3 From 329bd4119c8a0afea95f9db6d6b402a2f2b40e84 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Fri, 2 Oct 2009 15:23:21 +0200 Subject: initcalls: Add early_initcall() for modules Complete the early_initcall() API by making it available in modules too. To be used by the EDAC/MCE code. Signed-off-by: Borislav Petkov Acked-by: Linus Torvalds Cc: Andi Kleen LKML-Reference: <20091002132321.GC28682@aftab> Signed-off-by: Ingo Molnar --- include/linux/init.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index 400adbb45414..ff8bde520d03 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -271,6 +271,7 @@ void __init parse_early_options(char *cmdline); #else /* MODULE */ /* Don't use these in modules, but some people do... */ +#define early_initcall(fn) module_init(fn) #define core_initcall(fn) module_init(fn) #define postcore_initcall(fn) module_init(fn) #define arch_initcall(fn) module_init(fn) -- cgit v1.2.3 From 293500a23f4b0698cb04abfecfc9a954d8ab2742 Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Fri, 2 Oct 2009 02:40:04 +0000 Subject: connector: Keep the skb in cn_callback_data Signed-off-by: Philipp Reisner Acked-by: Lars Ellenberg Acked-by: Evgeniy Polyakov Signed-off-by: David S. Miller --- drivers/connector/cn_queue.c | 3 ++- drivers/connector/connector.c | 11 +++++------ include/linux/connector.h | 4 ++-- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/connector/cn_queue.c b/drivers/connector/cn_queue.c index 4a1dfe1f4ba9..b4cfac93f723 100644 --- a/drivers/connector/cn_queue.c +++ b/drivers/connector/cn_queue.c @@ -78,8 +78,9 @@ void cn_queue_wrapper(struct work_struct *work) struct cn_callback_entry *cbq = container_of(work, struct cn_callback_entry, work); struct cn_callback_data *d = &cbq->data; + struct cn_msg *msg = NLMSG_DATA(nlmsg_hdr(d->skb)); - d->callback(d->callback_priv); + d->callback(msg); d->destruct_data(d->ddata); d->ddata = NULL; diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index 74f52af79563..fc9887fa453f 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -129,10 +129,11 @@ EXPORT_SYMBOL_GPL(cn_netlink_send); /* * Callback helper - queues work and setup destructor for given data. */ -static int cn_call_callback(struct cn_msg *msg, void (*destruct_data)(void *), void *data) +static int cn_call_callback(struct sk_buff *skb, void (*destruct_data)(void *), void *data) { struct cn_callback_entry *__cbq, *__new_cbq; struct cn_dev *dev = &cdev; + struct cn_msg *msg = NLMSG_DATA(nlmsg_hdr(skb)); int err = -ENODEV; spin_lock_bh(&dev->cbdev->queue_lock); @@ -140,7 +141,7 @@ static int cn_call_callback(struct cn_msg *msg, void (*destruct_data)(void *), v if (cn_cb_equal(&__cbq->id.id, &msg->id)) { if (likely(!work_pending(&__cbq->work) && __cbq->data.ddata == NULL)) { - __cbq->data.callback_priv = msg; + __cbq->data.skb = skb; __cbq->data.ddata = data; __cbq->data.destruct_data = destruct_data; @@ -156,7 +157,7 @@ static int cn_call_callback(struct cn_msg *msg, void (*destruct_data)(void *), v __new_cbq = kzalloc(sizeof(struct cn_callback_entry), GFP_ATOMIC); if (__new_cbq) { d = &__new_cbq->data; - d->callback_priv = msg; + d->skb = skb; d->callback = __cbq->data.callback; d->ddata = data; d->destruct_data = destruct_data; @@ -191,7 +192,6 @@ static int cn_call_callback(struct cn_msg *msg, void (*destruct_data)(void *), v */ static void cn_rx_skb(struct sk_buff *__skb) { - struct cn_msg *msg; struct nlmsghdr *nlh; int err; struct sk_buff *skb; @@ -208,8 +208,7 @@ static void cn_rx_skb(struct sk_buff *__skb) return; } - msg = NLMSG_DATA(nlh); - err = cn_call_callback(msg, (void (*)(void *))kfree_skb, skb); + err = cn_call_callback(skb, (void (*)(void *))kfree_skb, skb); if (err < 0) kfree_skb(skb); } diff --git a/include/linux/connector.h b/include/linux/connector.h index 47ebf416f512..05a7a14126d8 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -134,8 +134,8 @@ struct cn_callback_id { struct cn_callback_data { void (*destruct_data) (void *); void *ddata; - - void *callback_priv; + + struct sk_buff *skb; void (*callback) (struct cn_msg *); void *free; -- cgit v1.2.3 From 7069331dbe7155f23966f5944109f909fea0c7e4 Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Fri, 2 Oct 2009 02:40:05 +0000 Subject: connector: Provide the sender's credentials to the callback Signed-off-by: Philipp Reisner Acked-by: Lars Ellenberg Acked-by: Evgeniy Polyakov Signed-off-by: David S. Miller --- Documentation/connector/cn_test.c | 2 +- Documentation/connector/connector.txt | 8 ++++---- drivers/connector/cn_queue.c | 7 ++++--- drivers/connector/connector.c | 4 ++-- drivers/md/dm-log-userspace-transfer.c | 2 +- drivers/staging/dst/dcore.c | 2 +- drivers/staging/pohmelfs/config.c | 2 +- drivers/video/uvesafb.c | 2 +- drivers/w1/w1_netlink.c | 2 +- include/linux/connector.h | 6 +++--- 10 files changed, 19 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/Documentation/connector/cn_test.c b/Documentation/connector/cn_test.c index 1711adc33373..b07add3467f1 100644 --- a/Documentation/connector/cn_test.c +++ b/Documentation/connector/cn_test.c @@ -34,7 +34,7 @@ static char cn_test_name[] = "cn_test"; static struct sock *nls; static struct timer_list cn_test_timer; -static void cn_test_callback(struct cn_msg *msg) +static void cn_test_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp) { pr_info("%s: %lu: idx=%x, val=%x, seq=%u, ack=%u, len=%d: %s.\n", __func__, jiffies, msg->id.idx, msg->id.val, diff --git a/Documentation/connector/connector.txt b/Documentation/connector/connector.txt index 81e6bf6ead57..78c9466a9aa8 100644 --- a/Documentation/connector/connector.txt +++ b/Documentation/connector/connector.txt @@ -23,7 +23,7 @@ handling, etc... The Connector driver allows any kernelspace agents to use netlink based networking for inter-process communication in a significantly easier way: -int cn_add_callback(struct cb_id *id, char *name, void (*callback) (void *)); +int cn_add_callback(struct cb_id *id, char *name, void (*callback) (struct cn_msg *, struct netlink_skb_parms *)); void cn_netlink_send(struct cn_msg *msg, u32 __group, int gfp_mask); struct cb_id @@ -53,15 +53,15 @@ struct cn_msg Connector interfaces. /*****************************************/ -int cn_add_callback(struct cb_id *id, char *name, void (*callback) (void *)); +int cn_add_callback(struct cb_id *id, char *name, void (*callback) (struct cn_msg *, struct netlink_skb_parms *)); Registers new callback with connector core. struct cb_id *id - unique connector's user identifier. It must be registered in connector.h for legal in-kernel users. char *name - connector's callback symbolic name. - void (*callback) (void *) - connector's callback. - Argument must be dereferenced to struct cn_msg *. + void (*callback) (struct cn..) - connector's callback. + cn_msg and the sender's credentials void cn_del_callback(struct cb_id *id); diff --git a/drivers/connector/cn_queue.c b/drivers/connector/cn_queue.c index b4cfac93f723..163c3e3d0d11 100644 --- a/drivers/connector/cn_queue.c +++ b/drivers/connector/cn_queue.c @@ -79,8 +79,9 @@ void cn_queue_wrapper(struct work_struct *work) container_of(work, struct cn_callback_entry, work); struct cn_callback_data *d = &cbq->data; struct cn_msg *msg = NLMSG_DATA(nlmsg_hdr(d->skb)); + struct netlink_skb_parms *nsp = &NETLINK_CB(d->skb); - d->callback(msg); + d->callback(msg, nsp); d->destruct_data(d->ddata); d->ddata = NULL; @@ -90,7 +91,7 @@ void cn_queue_wrapper(struct work_struct *work) static struct cn_callback_entry * cn_queue_alloc_callback_entry(char *name, struct cb_id *id, - void (*callback)(struct cn_msg *)) + void (*callback)(struct cn_msg *, struct netlink_skb_parms *)) { struct cn_callback_entry *cbq; @@ -124,7 +125,7 @@ int cn_cb_equal(struct cb_id *i1, struct cb_id *i2) } int cn_queue_add_callback(struct cn_queue_dev *dev, char *name, struct cb_id *id, - void (*callback)(struct cn_msg *)) + void (*callback)(struct cn_msg *, struct netlink_skb_parms *)) { struct cn_callback_entry *cbq, *__cbq; int found = 0; diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index fc9887fa453f..e59f0ab8f828 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -269,7 +269,7 @@ static void cn_notify(struct cb_id *id, u32 notify_event) * May sleep. */ int cn_add_callback(struct cb_id *id, char *name, - void (*callback)(struct cn_msg *)) + void (*callback)(struct cn_msg *, struct netlink_skb_parms *)) { int err; struct cn_dev *dev = &cdev; @@ -351,7 +351,7 @@ static int cn_ctl_msg_equals(struct cn_ctl_msg *m1, struct cn_ctl_msg *m2) * * Used for notification of a request's processing. */ -static void cn_callback(struct cn_msg *msg) +static void cn_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp) { struct cn_ctl_msg *ctl; struct cn_ctl_entry *ent; diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c index ba0edad2d048..556131f7d847 100644 --- a/drivers/md/dm-log-userspace-transfer.c +++ b/drivers/md/dm-log-userspace-transfer.c @@ -129,7 +129,7 @@ static int fill_pkg(struct cn_msg *msg, struct dm_ulog_request *tfr) * This is the connector callback that delivers data * that was sent from userspace. */ -static void cn_ulog_callback(void *data) +static void cn_ulog_callback(void *data, struct netlink_skb_parms *nsp) { struct cn_msg *msg = (struct cn_msg *)data; struct dm_ulog_request *tfr = (struct dm_ulog_request *)(msg + 1); diff --git a/drivers/staging/dst/dcore.c b/drivers/staging/dst/dcore.c index ac8577358ba0..3943c91e6c96 100644 --- a/drivers/staging/dst/dcore.c +++ b/drivers/staging/dst/dcore.c @@ -847,7 +847,7 @@ static dst_command_func dst_commands[] = { /* * Configuration parser. */ -static void cn_dst_callback(struct cn_msg *msg) +static void cn_dst_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp) { struct dst_ctl *ctl; int err; diff --git a/drivers/staging/pohmelfs/config.c b/drivers/staging/pohmelfs/config.c index 90f962ee5fd8..c9162b3f0bf3 100644 --- a/drivers/staging/pohmelfs/config.c +++ b/drivers/staging/pohmelfs/config.c @@ -527,7 +527,7 @@ out_unlock: return err; } -static void pohmelfs_cn_callback(struct cn_msg *msg) +static void pohmelfs_cn_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp) { int err; diff --git a/drivers/video/uvesafb.c b/drivers/video/uvesafb.c index e98baf6916b8..aa7cd959cced 100644 --- a/drivers/video/uvesafb.c +++ b/drivers/video/uvesafb.c @@ -67,7 +67,7 @@ static DEFINE_MUTEX(uvfb_lock); * find the kernel part of the task struct, copy the registers and * the buffer contents and then complete the task. */ -static void uvesafb_cn_callback(struct cn_msg *msg) +static void uvesafb_cn_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp) { struct uvesafb_task *utask; struct uvesafb_ktask *task; diff --git a/drivers/w1/w1_netlink.c b/drivers/w1/w1_netlink.c index 52ccb3d3a963..45c126fea31d 100644 --- a/drivers/w1/w1_netlink.c +++ b/drivers/w1/w1_netlink.c @@ -306,7 +306,7 @@ static int w1_netlink_send_error(struct cn_msg *rcmsg, struct w1_netlink_msg *rm return error; } -static void w1_cn_callback(struct cn_msg *msg) +static void w1_cn_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp) { struct w1_netlink_msg *m = (struct w1_netlink_msg *)(msg + 1); struct w1_netlink_cmd *cmd; diff --git a/include/linux/connector.h b/include/linux/connector.h index 05a7a14126d8..545728e20b63 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -136,7 +136,7 @@ struct cn_callback_data { void *ddata; struct sk_buff *skb; - void (*callback) (struct cn_msg *); + void (*callback) (struct cn_msg *, struct netlink_skb_parms *); void *free; }; @@ -167,11 +167,11 @@ struct cn_dev { struct cn_queue_dev *cbdev; }; -int cn_add_callback(struct cb_id *, char *, void (*callback) (struct cn_msg *)); +int cn_add_callback(struct cb_id *, char *, void (*callback) (struct cn_msg *, struct netlink_skb_parms *)); void cn_del_callback(struct cb_id *); int cn_netlink_send(struct cn_msg *, u32, gfp_t); -int cn_queue_add_callback(struct cn_queue_dev *dev, char *name, struct cb_id *id, void (*callback)(struct cn_msg *)); +int cn_queue_add_callback(struct cn_queue_dev *dev, char *name, struct cb_id *id, void (*callback)(struct cn_msg *, struct netlink_skb_parms *)); void cn_queue_del_callback(struct cn_queue_dev *dev, struct cb_id *id); int queue_cn_work(struct cn_callback_entry *cbq, struct work_struct *work); -- cgit v1.2.3 From f1489cfb173509a3c13444b46b6c989bad4f5b16 Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Fri, 2 Oct 2009 02:40:07 +0000 Subject: connector: Removed the destruct_data callback since it is always kfree_skb() Signed-off-by: Philipp Reisner Acked-by: Lars Ellenberg Acked-by: Evgeniy Polyakov Signed-off-by: David S. Miller --- drivers/connector/cn_queue.c | 4 ++-- drivers/connector/connector.c | 11 +++-------- include/linux/connector.h | 3 --- 3 files changed, 5 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/connector/cn_queue.c b/drivers/connector/cn_queue.c index 163c3e3d0d11..210338ea222f 100644 --- a/drivers/connector/cn_queue.c +++ b/drivers/connector/cn_queue.c @@ -83,8 +83,8 @@ void cn_queue_wrapper(struct work_struct *work) d->callback(msg, nsp); - d->destruct_data(d->ddata); - d->ddata = NULL; + kfree_skb(d->skb); + d->skb = NULL; kfree(d->free); } diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index e59f0ab8f828..f06024668f99 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -129,7 +129,7 @@ EXPORT_SYMBOL_GPL(cn_netlink_send); /* * Callback helper - queues work and setup destructor for given data. */ -static int cn_call_callback(struct sk_buff *skb, void (*destruct_data)(void *), void *data) +static int cn_call_callback(struct sk_buff *skb) { struct cn_callback_entry *__cbq, *__new_cbq; struct cn_dev *dev = &cdev; @@ -140,12 +140,9 @@ static int cn_call_callback(struct sk_buff *skb, void (*destruct_data)(void *), list_for_each_entry(__cbq, &dev->cbdev->queue_list, callback_entry) { if (cn_cb_equal(&__cbq->id.id, &msg->id)) { if (likely(!work_pending(&__cbq->work) && - __cbq->data.ddata == NULL)) { + __cbq->data.skb == NULL)) { __cbq->data.skb = skb; - __cbq->data.ddata = data; - __cbq->data.destruct_data = destruct_data; - if (queue_cn_work(__cbq, &__cbq->work)) err = 0; else @@ -159,8 +156,6 @@ static int cn_call_callback(struct sk_buff *skb, void (*destruct_data)(void *), d = &__new_cbq->data; d->skb = skb; d->callback = __cbq->data.callback; - d->ddata = data; - d->destruct_data = destruct_data; d->free = __new_cbq; __new_cbq->pdev = __cbq->pdev; @@ -208,7 +203,7 @@ static void cn_rx_skb(struct sk_buff *__skb) return; } - err = cn_call_callback(skb, (void (*)(void *))kfree_skb, skb); + err = cn_call_callback(skb); if (err < 0) kfree_skb(skb); } diff --git a/include/linux/connector.h b/include/linux/connector.h index 545728e20b63..3a14615fd35c 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -132,9 +132,6 @@ struct cn_callback_id { }; struct cn_callback_data { - void (*destruct_data) (void *); - void *ddata; - struct sk_buff *skb; void (*callback) (struct cn_msg *, struct netlink_skb_parms *); -- cgit v1.2.3 From 8e2967555571659d2c8a70dd120710110ed7bba4 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 3 Oct 2009 16:26:03 +0200 Subject: cfq-iosched: implement slower async initiate and queue ramp up This slowly ramps up the async queue depth based on the time passed since the sync IO, and doesn't allow async at all until a sync slice period has passed. Signed-off-by: Jens Axboe --- block/blk-core.c | 8 ++++++++ block/cfq-iosched.c | 56 ++++++++++++++++++++++++++++++++------------------ include/linux/blkdev.h | 4 ++++ 3 files changed, 48 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index ddaaea4fdffc..a8c7fbe52e24 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2492,6 +2492,14 @@ int kblockd_schedule_work(struct request_queue *q, struct work_struct *work) } EXPORT_SYMBOL(kblockd_schedule_work); +int kblockd_schedule_delayed_work(struct request_queue *q, + struct delayed_work *work, + unsigned long delay) +{ + return queue_delayed_work(kblockd_workqueue, work, delay); +} +EXPORT_SYMBOL(kblockd_schedule_delayed_work); + int __init blk_dev_init(void) { BUILD_BUG_ON(__REQ_NR_BITS > 8 * diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 70b48ea0e3e9..fce8a749f4be 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -150,7 +150,7 @@ struct cfq_data { * idle window management */ struct timer_list idle_slice_timer; - struct work_struct unplug_work; + struct delayed_work unplug_work; struct cfq_queue *active_queue; struct cfq_io_context *active_cic; @@ -268,11 +268,13 @@ static inline int cfq_bio_sync(struct bio *bio) * scheduler run of queue, if there are requests pending and no one in the * driver that will restart queueing */ -static inline void cfq_schedule_dispatch(struct cfq_data *cfqd) +static inline void cfq_schedule_dispatch(struct cfq_data *cfqd, + unsigned long delay) { if (cfqd->busy_queues) { cfq_log(cfqd, "schedule dispatch"); - kblockd_schedule_work(cfqd->queue, &cfqd->unplug_work); + kblockd_schedule_delayed_work(cfqd->queue, &cfqd->unplug_work, + delay); } } @@ -1316,8 +1318,6 @@ static int cfq_dispatch_requests(struct request_queue *q, int force) * Does this cfqq already have too much IO in flight? */ if (cfqq->dispatched >= max_dispatch) { - unsigned long load_at = cfqd->last_end_sync_rq + cfq_slice_sync; - /* * idle queue must always only have a single IO in flight */ @@ -1331,20 +1331,36 @@ static int cfq_dispatch_requests(struct request_queue *q, int force) return 0; /* - * If a sync request has completed recently, don't overload - * the dispatch queue yet with async requests. + * Sole queue user, allow bigger slice */ - if (cfqd->cfq_desktop && !cfq_cfqq_sync(cfqq) - && time_before(jiffies, load_at)) - return 0; + max_dispatch *= 4; + } + + /* + * Async queues must wait a bit before being allowed dispatch. + * We also ramp up the dispatch depth gradually for async IO, + * based on the last sync IO we serviced + */ + if (!cfq_cfqq_sync(cfqq) && cfqd->cfq_desktop) { + unsigned long last_sync = jiffies - cfqd->last_end_sync_rq; + unsigned int depth; /* - * we are the only queue, allow up to 4 times of 'quantum' + * must wait a bit longer */ - if (cfqq->dispatched >= 4 * max_dispatch) + if (last_sync < cfq_slice_sync) { + cfq_schedule_dispatch(cfqd, cfq_slice_sync - last_sync); return 0; + } + + depth = last_sync / cfq_slice_sync; + if (depth < max_dispatch) + max_dispatch = depth; } + if (cfqq->dispatched >= max_dispatch) + return 0; + /* * Dispatch a request from this cfqq */ @@ -1389,7 +1405,7 @@ static void cfq_put_queue(struct cfq_queue *cfqq) if (unlikely(cfqd->active_queue == cfqq)) { __cfq_slice_expired(cfqd, cfqq, 0); - cfq_schedule_dispatch(cfqd); + cfq_schedule_dispatch(cfqd, 0); } kmem_cache_free(cfq_pool, cfqq); @@ -1484,7 +1500,7 @@ static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq) { if (unlikely(cfqq == cfqd->active_queue)) { __cfq_slice_expired(cfqd, cfqq, 0); - cfq_schedule_dispatch(cfqd); + cfq_schedule_dispatch(cfqd, 0); } cfq_put_queue(cfqq); @@ -2201,7 +2217,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) } if (!rq_in_driver(cfqd)) - cfq_schedule_dispatch(cfqd); + cfq_schedule_dispatch(cfqd, 0); } /* @@ -2331,7 +2347,7 @@ queue_fail: if (cic) put_io_context(cic->ioc); - cfq_schedule_dispatch(cfqd); + cfq_schedule_dispatch(cfqd, 0); spin_unlock_irqrestore(q->queue_lock, flags); cfq_log(cfqd, "set_request fail"); return 1; @@ -2340,7 +2356,7 @@ queue_fail: static void cfq_kick_queue(struct work_struct *work) { struct cfq_data *cfqd = - container_of(work, struct cfq_data, unplug_work); + container_of(work, struct cfq_data, unplug_work.work); struct request_queue *q = cfqd->queue; spin_lock_irq(q->queue_lock); @@ -2394,7 +2410,7 @@ static void cfq_idle_slice_timer(unsigned long data) expire: cfq_slice_expired(cfqd, timed_out); out_kick: - cfq_schedule_dispatch(cfqd); + cfq_schedule_dispatch(cfqd, 0); out_cont: spin_unlock_irqrestore(cfqd->queue->queue_lock, flags); } @@ -2402,7 +2418,7 @@ out_cont: static void cfq_shutdown_timer_wq(struct cfq_data *cfqd) { del_timer_sync(&cfqd->idle_slice_timer); - cancel_work_sync(&cfqd->unplug_work); + cancel_delayed_work_sync(&cfqd->unplug_work); } static void cfq_put_async_queues(struct cfq_data *cfqd) @@ -2484,7 +2500,7 @@ static void *cfq_init_queue(struct request_queue *q) cfqd->idle_slice_timer.function = cfq_idle_slice_timer; cfqd->idle_slice_timer.data = (unsigned long) cfqd; - INIT_WORK(&cfqd->unplug_work, cfq_kick_queue); + INIT_DELAYED_WORK(&cfqd->unplug_work, cfq_kick_queue); cfqd->cfq_quantum = cfq_quantum; cfqd->cfq_fifo_expire[0] = cfq_fifo_expire[0]; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1a03b715dfad..a7323930d2ba 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1147,7 +1147,11 @@ static inline void put_dev_sector(Sector p) } struct work_struct; +struct delayed_work; int kblockd_schedule_work(struct request_queue *q, struct work_struct *work); +int kblockd_schedule_delayed_work(struct request_queue *q, + struct delayed_work *work, + unsigned long delay); #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) -- cgit v1.2.3 From ac481c20ef8f6c6f2be75d581863f40c43874ef7 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Sat, 3 Oct 2009 20:52:01 +0200 Subject: block: Topology ioctls Not all users of the topology information want to use libblkid. Provide the topology information through bdev ioctls. Also clarify sector size comments for existing BLK ioctls. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- block/compat_ioctl.c | 13 +++++++++++++ block/ioctl.c | 17 +++++++++++++++-- include/linux/blkdev.h | 35 ++++++++++++++++++++++++++++++----- include/linux/fs.h | 4 ++++ 4 files changed, 62 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c index 7865a34e0faa..9bd086c1a4d5 100644 --- a/block/compat_ioctl.c +++ b/block/compat_ioctl.c @@ -21,6 +21,11 @@ static int compat_put_int(unsigned long arg, int val) return put_user(val, (compat_int_t __user *)compat_ptr(arg)); } +static int compat_put_uint(unsigned long arg, unsigned int val) +{ + return put_user(val, (compat_uint_t __user *)compat_ptr(arg)); +} + static int compat_put_long(unsigned long arg, long val) { return put_user(val, (compat_long_t __user *)compat_ptr(arg)); @@ -734,6 +739,14 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) switch (cmd) { case HDIO_GETGEO: return compat_hdio_getgeo(disk, bdev, compat_ptr(arg)); + case BLKPBSZGET: + return compat_put_uint(arg, bdev_physical_block_size(bdev)); + case BLKIOMIN: + return compat_put_uint(arg, bdev_io_min(bdev)); + case BLKIOOPT: + return compat_put_uint(arg, bdev_io_opt(bdev)); + case BLKALIGNOFF: + return compat_put_int(arg, bdev_alignment_offset(bdev)); case BLKFLSBUF: case BLKROSET: case BLKDISCARD: diff --git a/block/ioctl.c b/block/ioctl.c index d3e6b5827a34..1f4d1de12b09 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -138,6 +138,11 @@ static int put_int(unsigned long arg, int val) return put_user(val, (int __user *)arg); } +static int put_uint(unsigned long arg, unsigned int val) +{ + return put_user(val, (unsigned int __user *)arg); +} + static int put_long(unsigned long arg, long val) { return put_user(val, (long __user *)arg); @@ -263,10 +268,18 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, return put_long(arg, (bdi->ra_pages * PAGE_CACHE_SIZE) / 512); case BLKROGET: return put_int(arg, bdev_read_only(bdev) != 0); - case BLKBSZGET: /* get the logical block size (cf. BLKSSZGET) */ + case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */ return put_int(arg, block_size(bdev)); - case BLKSSZGET: /* get block device hardware sector size */ + case BLKSSZGET: /* get block device logical block size */ return put_int(arg, bdev_logical_block_size(bdev)); + case BLKPBSZGET: /* get block device physical block size */ + return put_uint(arg, bdev_physical_block_size(bdev)); + case BLKIOMIN: + return put_uint(arg, bdev_io_min(bdev)); + case BLKIOOPT: + return put_uint(arg, bdev_io_opt(bdev)); + case BLKALIGNOFF: + return put_int(arg, bdev_alignment_offset(bdev)); case BLKSECTGET: return put_ushort(arg, queue_max_sectors(bdev_get_queue(bdev))); case BLKRASET: diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a7323930d2ba..25119041e034 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1081,25 +1081,37 @@ static inline unsigned int queue_physical_block_size(struct request_queue *q) return q->limits.physical_block_size; } +static inline int bdev_physical_block_size(struct block_device *bdev) +{ + return queue_physical_block_size(bdev_get_queue(bdev)); +} + static inline unsigned int queue_io_min(struct request_queue *q) { return q->limits.io_min; } +static inline int bdev_io_min(struct block_device *bdev) +{ + return queue_io_min(bdev_get_queue(bdev)); +} + static inline unsigned int queue_io_opt(struct request_queue *q) { return q->limits.io_opt; } +static inline int bdev_io_opt(struct block_device *bdev) +{ + return queue_io_opt(bdev_get_queue(bdev)); +} + static inline int queue_alignment_offset(struct request_queue *q) { - if (q && q->limits.misaligned) + if (q->limits.misaligned) return -1; - if (q && q->limits.alignment_offset) - return q->limits.alignment_offset; - - return 0; + return q->limits.alignment_offset; } static inline int queue_sector_alignment_offset(struct request_queue *q, @@ -1109,6 +1121,19 @@ static inline int queue_sector_alignment_offset(struct request_queue *q, & (q->limits.io_min - 1); } +static inline int bdev_alignment_offset(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (q->limits.misaligned) + return -1; + + if (bdev != bdev->bd_contains) + return bdev->bd_part->alignment_offset; + + return q->limits.alignment_offset; +} + static inline int queue_dma_alignment(struct request_queue *q) { return q ? q->dma_alignment : 511; diff --git a/include/linux/fs.h b/include/linux/fs.h index 2adaa2529f18..883eaacfd924 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -300,6 +300,10 @@ struct inodes_stat_t { #define BLKTRACESTOP _IO(0x12,117) #define BLKTRACETEARDOWN _IO(0x12,118) #define BLKDISCARD _IO(0x12,119) +#define BLKIOMIN _IO(0x12,120) +#define BLKIOOPT _IO(0x12,121) +#define BLKALIGNOFF _IO(0x12,122) +#define BLKPBSZGET _IO(0x12,123) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ -- cgit v1.2.3 From 0f78ab9899e9d6acb09d5465def618704255963b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 4 Oct 2009 21:04:38 +0200 Subject: Revert "Seperate read and write statistics of in_flight requests" This reverts commit a9327cac440be4d8333bba975cbbf76045096275. Corrado Zoccolo reports: "with 2.6.32-rc1 I started getting the following strange output from "iostat -kx 2": Linux 2.6.31bisect (et2) 04/10/2009 _i686_ (2 CPU) avg-cpu: %user %nice %system %iowait %steal %idle 10,70 0,00 3,16 15,75 0,00 70,38 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 18,22 0,00 0,67 0,01 14,77 0,02 43,94 0,01 10,53 39043915,03 2629219,87 sdb 60,89 9,68 50,79 3,04 1724,43 50,52 65,95 0,70 13,06 488437,47 2629219,87 avg-cpu: %user %nice %system %iowait %steal %idle 2,72 0,00 0,74 0,00 0,00 96,53 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 6,68 0,00 0,99 0,00 0,00 92,33 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 avg-cpu: %user %nice %system %iowait %steal %idle 4,40 0,00 0,73 1,47 0,00 93,40 Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util sda 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 0,00 100,00 sdb 0,00 4,00 0,00 3,00 0,00 28,00 18,67 0,06 19,50 333,33 100,00 Global values for service time and utilization are garbage. For interval values, utilization is always 100%, and service time is higher than normal. I bisected it down to: [a9327cac440be4d8333bba975cbbf76045096275] Seperate read and write statistics of in_flight requests and verified that reverting just that commit indeed solves the issue on 2.6.32-rc1." So until this is debugged, revert the bad commit. Signed-off-by: Jens Axboe --- block/blk-core.c | 6 +++--- block/blk-merge.c | 2 +- block/genhd.c | 4 +--- drivers/md/dm.c | 16 ++++++---------- fs/partitions/check.c | 12 +----------- include/linux/genhd.h | 21 +++++++-------------- 6 files changed, 19 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index a8c7fbe52e24..81f34311659a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -70,7 +70,7 @@ static void drive_stat_acct(struct request *rq, int new_io) part_stat_inc(cpu, part, merges[rw]); else { part_round_stats(cpu, part); - part_inc_in_flight(part, rw); + part_inc_in_flight(part); } part_stat_unlock(); @@ -1032,7 +1032,7 @@ static void part_round_stats_single(int cpu, struct hd_struct *part, if (part->in_flight) { __part_stat_add(cpu, part, time_in_queue, - part_in_flight(part) * (now - part->stamp)); + part->in_flight * (now - part->stamp)); __part_stat_add(cpu, part, io_ticks, (now - part->stamp)); } part->stamp = now; @@ -1739,7 +1739,7 @@ static void blk_account_io_done(struct request *req) part_stat_inc(cpu, part, ios[rw]); part_stat_add(cpu, part, ticks[rw], duration); part_round_stats(cpu, part); - part_dec_in_flight(part, rw); + part_dec_in_flight(part); part_stat_unlock(); } diff --git a/block/blk-merge.c b/block/blk-merge.c index 99cb5cf1f447..b0de8574fdc8 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -351,7 +351,7 @@ static void blk_account_io_merge(struct request *req) part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req)); part_round_stats(cpu, part); - part_dec_in_flight(part, rq_data_dir(req)); + part_dec_in_flight(part); part_stat_unlock(); } diff --git a/block/genhd.c b/block/genhd.c index 517e4332cb37..5a0861da324d 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -869,7 +869,6 @@ static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL); static DEVICE_ATTR(alignment_offset, S_IRUGO, disk_alignment_offset_show, NULL); static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL); static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); -static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store); @@ -889,7 +888,6 @@ static struct attribute *disk_attrs[] = { &dev_attr_alignment_offset.attr, &dev_attr_capability.attr, &dev_attr_stat.attr, - &dev_attr_inflight.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif @@ -1055,7 +1053,7 @@ static int diskstats_show(struct seq_file *seqf, void *v) part_stat_read(hd, merges[1]), (unsigned long long)part_stat_read(hd, sectors[1]), jiffies_to_msecs(part_stat_read(hd, ticks[1])), - part_in_flight(hd), + hd->in_flight, jiffies_to_msecs(part_stat_read(hd, io_ticks)), jiffies_to_msecs(part_stat_read(hd, time_in_queue)) ); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 376f1ab48a24..23e76fe0d359 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -130,7 +130,7 @@ struct mapped_device { /* * A list of ios that arrived while we were suspended. */ - atomic_t pending[2]; + atomic_t pending; wait_queue_head_t wait; struct work_struct work; struct bio_list deferred; @@ -453,14 +453,13 @@ static void start_io_acct(struct dm_io *io) { struct mapped_device *md = io->md; int cpu; - int rw = bio_data_dir(io->bio); io->start_time = jiffies; cpu = part_stat_lock(); part_round_stats(cpu, &dm_disk(md)->part0); part_stat_unlock(); - dm_disk(md)->part0.in_flight[rw] = atomic_inc_return(&md->pending[rw]); + dm_disk(md)->part0.in_flight = atomic_inc_return(&md->pending); } static void end_io_acct(struct dm_io *io) @@ -480,9 +479,8 @@ static void end_io_acct(struct dm_io *io) * After this is decremented the bio must not be touched if it is * a barrier. */ - dm_disk(md)->part0.in_flight[rw] = pending = - atomic_dec_return(&md->pending[rw]); - pending += atomic_read(&md->pending[rw^0x1]); + dm_disk(md)->part0.in_flight = pending = + atomic_dec_return(&md->pending); /* nudge anyone waiting on suspend queue */ if (!pending) @@ -1787,8 +1785,7 @@ static struct mapped_device *alloc_dev(int minor) if (!md->disk) goto bad_disk; - atomic_set(&md->pending[0], 0); - atomic_set(&md->pending[1], 0); + atomic_set(&md->pending, 0); init_waitqueue_head(&md->wait); INIT_WORK(&md->work, dm_wq_work); init_waitqueue_head(&md->eventq); @@ -2091,8 +2088,7 @@ static int dm_wait_for_completion(struct mapped_device *md, int interruptible) break; } spin_unlock_irqrestore(q->queue_lock, flags); - } else if (!atomic_read(&md->pending[0]) && - !atomic_read(&md->pending[1])) + } else if (!atomic_read(&md->pending)) break; if (interruptible == TASK_INTERRUPTIBLE && diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 7b685e10cbad..f38fee0311a7 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -248,19 +248,11 @@ ssize_t part_stat_show(struct device *dev, part_stat_read(p, merges[WRITE]), (unsigned long long)part_stat_read(p, sectors[WRITE]), jiffies_to_msecs(part_stat_read(p, ticks[WRITE])), - part_in_flight(p), + p->in_flight, jiffies_to_msecs(part_stat_read(p, io_ticks)), jiffies_to_msecs(part_stat_read(p, time_in_queue))); } -ssize_t part_inflight_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct hd_struct *p = dev_to_part(dev); - - return sprintf(buf, "%8u %8u\n", p->in_flight[0], p->in_flight[1]); -} - #ifdef CONFIG_FAIL_MAKE_REQUEST ssize_t part_fail_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -289,7 +281,6 @@ static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL); static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL); static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL); static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); -static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store); @@ -301,7 +292,6 @@ static struct attribute *part_attrs[] = { &dev_attr_size.attr, &dev_attr_alignment_offset.attr, &dev_attr_stat.attr, - &dev_attr_inflight.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 297df45ffd0a..7beaa21b3880 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -98,7 +98,7 @@ struct hd_struct { int make_it_fail; #endif unsigned long stamp; - int in_flight[2]; + int in_flight; #ifdef CONFIG_SMP struct disk_stats *dkstats; #else @@ -322,23 +322,18 @@ static inline void free_part_stats(struct hd_struct *part) #define part_stat_sub(cpu, gendiskp, field, subnd) \ part_stat_add(cpu, gendiskp, field, -subnd) -static inline void part_inc_in_flight(struct hd_struct *part, int rw) +static inline void part_inc_in_flight(struct hd_struct *part) { - part->in_flight[rw]++; + part->in_flight++; if (part->partno) - part_to_disk(part)->part0.in_flight[rw]++; + part_to_disk(part)->part0.in_flight++; } -static inline void part_dec_in_flight(struct hd_struct *part, int rw) +static inline void part_dec_in_flight(struct hd_struct *part) { - part->in_flight[rw]--; + part->in_flight--; if (part->partno) - part_to_disk(part)->part0.in_flight[rw]--; -} - -static inline int part_in_flight(struct hd_struct *part) -{ - return part->in_flight[0] + part->in_flight[1]; + part_to_disk(part)->part0.in_flight--; } /* block/blk-core.c */ @@ -551,8 +546,6 @@ extern ssize_t part_size_show(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t part_stat_show(struct device *dev, struct device_attribute *attr, char *buf); -extern ssize_t part_inflight_show(struct device *dev, - struct device_attribute *attr, char *buf); #ifdef CONFIG_FAIL_MAKE_REQUEST extern ssize_t part_fail_show(struct device *dev, struct device_attribute *attr, char *buf); -- cgit v1.2.3 From a99bbaf5ee6bad1aca0c88ea65ec6e5373e86184 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sun, 4 Oct 2009 16:11:37 +0400 Subject: headers: remove sched.h from poll.h Signed-off-by: Alexey Dobriyan Signed-off-by: Linus Torvalds --- drivers/char/dtlk.c | 1 + drivers/char/ipmi/ipmi_devintf.c | 1 + drivers/char/ipmi/ipmi_msghandler.c | 1 + drivers/firewire/core-cdev.c | 1 + drivers/hid/hidraw.c | 1 + drivers/infiniband/core/ucm.c | 1 + drivers/infiniband/core/user_mad.c | 1 + drivers/infiniband/core/uverbs_main.c | 1 + drivers/input/evdev.c | 1 + drivers/input/input.c | 1 + drivers/input/joydev.c | 1 + drivers/input/misc/uinput.c | 1 + drivers/input/mousedev.c | 1 + drivers/isdn/divert/divert_procfs.c | 1 + drivers/media/dvb/dvb-core/dmxdev.c | 1 + drivers/media/dvb/dvb-core/dvb_demux.c | 1 + drivers/media/radio/radio-cadet.c | 1 + drivers/media/video/cpia.c | 1 + drivers/mfd/ucb1400_core.c | 1 + drivers/usb/gadget/inode.c | 1 + drivers/xen/xenfs/xenbus.c | 1 + fs/anon_inodes.c | 2 ++ fs/coda/psdev.c | 1 + fs/select.c | 1 + include/linux/poll.h | 2 +- net/rfkill/core.c | 1 + 26 files changed, 27 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/char/dtlk.c b/drivers/char/dtlk.c index 52e06589821d..045c930e6320 100644 --- a/drivers/char/dtlk.c +++ b/drivers/char/dtlk.c @@ -56,6 +56,7 @@ #include /* for -EBUSY */ #include /* for request_region */ #include /* for loops_per_jiffy */ +#include #include /* cycle_kernel_lock() */ #include /* for inb_p, outb_p, inb, outb, etc. */ #include /* for get_user, etc. */ diff --git a/drivers/char/ipmi/ipmi_devintf.c b/drivers/char/ipmi/ipmi_devintf.c index 41fc11dc921c..65545de3dbf4 100644 --- a/drivers/char/ipmi/ipmi_devintf.c +++ b/drivers/char/ipmi/ipmi_devintf.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 09050797c76a..ec5e3f8df648 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index ced186d7e9a9..5089331544ed 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c index 0c6639ea03dd..ba05275e5104 100644 --- a/drivers/hid/hidraw.c +++ b/drivers/hid/hidraw.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c index 51bd9669cb1f..f504c9b00c1b 100644 --- a/drivers/infiniband/core/ucm.c +++ b/drivers/infiniband/core/ucm.c @@ -38,6 +38,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index 8c46f2257098..7de02969ed7d 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -44,6 +44,7 @@ #include #include #include +#include #include #include diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index d3fff9e008a3..aec0fbdfe7f0 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index 1148140d08a1..dee6706038aa 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -13,6 +13,7 @@ #define EVDEV_BUFFER_SIZE 64 #include +#include #include #include #include diff --git a/drivers/input/input.c b/drivers/input/input.c index 16ec33f27c5d..c6f88ebb40c7 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/input/joydev.c b/drivers/input/joydev.c index 901b2525993e..b1bd6dd32286 100644 --- a/drivers/input/joydev.c +++ b/drivers/input/joydev.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c index c5a49aba418f..d3f57245420a 100644 --- a/drivers/input/misc/uinput.c +++ b/drivers/input/misc/uinput.c @@ -30,6 +30,7 @@ * - first public version */ #include +#include #include #include #include diff --git a/drivers/input/mousedev.c b/drivers/input/mousedev.c index 966b8868f792..a13d80f7da17 100644 --- a/drivers/input/mousedev.c +++ b/drivers/input/mousedev.c @@ -13,6 +13,7 @@ #define MOUSEDEV_MINORS 32 #define MOUSEDEV_MIX 31 +#include #include #include #include diff --git a/drivers/isdn/divert/divert_procfs.c b/drivers/isdn/divert/divert_procfs.c index 8b256a617c8a..3697c409bec6 100644 --- a/drivers/isdn/divert/divert_procfs.c +++ b/drivers/isdn/divert/divert_procfs.c @@ -16,6 +16,7 @@ #else #include #endif +#include #include #include #include "isdn_divert.h" diff --git a/drivers/media/dvb/dvb-core/dmxdev.c b/drivers/media/dvb/dvb-core/dmxdev.c index 516414983593..c37790ad92d0 100644 --- a/drivers/media/dvb/dvb-core/dmxdev.c +++ b/drivers/media/dvb/dvb-core/dmxdev.c @@ -20,6 +20,7 @@ * */ +#include #include #include #include diff --git a/drivers/media/dvb/dvb-core/dvb_demux.c b/drivers/media/dvb/dvb-core/dvb_demux.c index eef6d3616626..91c537bca8ad 100644 --- a/drivers/media/dvb/dvb-core/dvb_demux.c +++ b/drivers/media/dvb/dvb-core/dvb_demux.c @@ -21,6 +21,7 @@ * */ +#include #include #include #include diff --git a/drivers/media/radio/radio-cadet.c b/drivers/media/radio/radio-cadet.c index 8b1440136c45..482d0f3be5ff 100644 --- a/drivers/media/radio/radio-cadet.c +++ b/drivers/media/radio/radio-cadet.c @@ -38,6 +38,7 @@ #include /* V4L2 API defs */ #include #include +#include #include /* outb, outb_p */ #include #include diff --git a/drivers/media/video/cpia.c b/drivers/media/video/cpia.c index 43ab0adf3b61..2377313c041a 100644 --- a/drivers/media/video/cpia.c +++ b/drivers/media/video/cpia.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/mfd/ucb1400_core.c b/drivers/mfd/ucb1400_core.c index 2afc08006e6d..fa294b6d600a 100644 --- a/drivers/mfd/ucb1400_core.c +++ b/drivers/mfd/ucb1400_core.c @@ -21,6 +21,7 @@ */ #include +#include #include unsigned int ucb1400_adc_read(struct snd_ac97 *ac97, u16 adc_channel, diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c index c44367fea185..bf0f6520c6df 100644 --- a/drivers/usb/gadget/inode.c +++ b/drivers/usb/gadget/inode.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/xen/xenfs/xenbus.c b/drivers/xen/xenfs/xenbus.c index a9592d981b10..6c4269b836b7 100644 --- a/drivers/xen/xenfs/xenbus.c +++ b/drivers/xen/xenfs/xenbus.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include #include diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index d11c51fc2a3f..2ca7a7cafdbf 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -8,8 +8,10 @@ * */ +#include #include #include +#include #include #include #include diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c index 0376ac66c44a..be4392ca2098 100644 --- a/fs/coda/psdev.c +++ b/fs/coda/psdev.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include diff --git a/fs/select.c b/fs/select.c index a201fc370223..fd38ce2e32e3 100644 --- a/fs/select.c +++ b/fs/select.c @@ -15,6 +15,7 @@ */ #include +#include #include #include #include diff --git a/include/linux/poll.h b/include/linux/poll.h index fa287f25138d..6673743946f7 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -6,10 +6,10 @@ #ifdef __KERNEL__ #include +#include #include #include #include -#include #include /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating diff --git a/net/rfkill/core.c b/net/rfkill/core.c index dbeaf2983822..ba2efb960c60 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From 9c501935a3cdcf6b1d35aaee3aa11c7a7051a305 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 5 Oct 2009 00:24:36 -0700 Subject: net: Support inclusion of before The following user-space program fails to compile: #include #include int main() { return 0; } The reason is that tests __GLIBC__ to decide whether it should define various structures and macros that are now defined for user-space by , but __GLIBC__ is not defined if no libc headers have yet been included. It seems safe to drop support for libc 5 now. Signed-off-by: Ben Hutchings Signed-off-by: Bastian Blank Signed-off-by: David S. Miller --- include/linux/socket.h | 21 +++------------------ 1 file changed, 3 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 3b461dffe244..3273a0c5043b 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -16,7 +16,7 @@ struct __kernel_sockaddr_storage { /* _SS_MAXSIZE value minus size of ss_family */ } __attribute__ ((aligned(_K_SS_ALIGNSIZE))); /* force desired alignment */ -#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2) +#ifdef __KERNEL__ #include /* arch-dependent defines */ #include /* the SIOCxxx I/O controls */ @@ -100,21 +100,6 @@ struct cmsghdr { ((mhdr)->msg_controllen - \ ((char *)(cmsg) - (char *)(mhdr)->msg_control))) -/* - * This mess will go away with glibc - */ - -#ifdef __KERNEL__ -#define __KINLINE static inline -#elif defined(__GNUC__) -#define __KINLINE static __inline__ -#elif defined(__cplusplus) -#define __KINLINE static inline -#else -#define __KINLINE static -#endif - - /* * Get the next cmsg header * @@ -128,7 +113,7 @@ struct cmsghdr { * ancillary object DATA. --ANK (980731) */ -__KINLINE struct cmsghdr * __cmsg_nxthdr(void *__ctl, __kernel_size_t __size, +static inline struct cmsghdr * __cmsg_nxthdr(void *__ctl, __kernel_size_t __size, struct cmsghdr *__cmsg) { struct cmsghdr * __ptr; @@ -140,7 +125,7 @@ __KINLINE struct cmsghdr * __cmsg_nxthdr(void *__ctl, __kernel_size_t __size, return __ptr; } -__KINLINE struct cmsghdr * cmsg_nxthdr (struct msghdr *__msg, struct cmsghdr *__cmsg) +static inline struct cmsghdr * cmsg_nxthdr (struct msghdr *__msg, struct cmsghdr *__cmsg) { return __cmsg_nxthdr(__msg->msg_control, __msg->msg_controllen, __cmsg); } -- cgit v1.2.3 From 23e018a1b083ecb4b8bb2fb43d58e7c19b5d7959 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 5 Oct 2009 08:52:35 +0200 Subject: block: get rid of kblock_schedule_delayed_work() It was briefly introduced to allow CFQ to to delayed scheduling, but we ended up removing that feature again. So lets kill the function and export, and just switch CFQ back to the normal work schedule since it is now passing in a '0' delay from all call sites. Signed-off-by: Jens Axboe --- block/blk-core.c | 8 -------- block/cfq-iosched.c | 24 +++++++++++------------- include/linux/blkdev.h | 4 ---- 3 files changed, 11 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 81f34311659a..73ecbed02605 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2492,14 +2492,6 @@ int kblockd_schedule_work(struct request_queue *q, struct work_struct *work) } EXPORT_SYMBOL(kblockd_schedule_work); -int kblockd_schedule_delayed_work(struct request_queue *q, - struct delayed_work *work, - unsigned long delay) -{ - return queue_delayed_work(kblockd_workqueue, work, delay); -} -EXPORT_SYMBOL(kblockd_schedule_delayed_work); - int __init blk_dev_init(void) { BUILD_BUG_ON(__REQ_NR_BITS > 8 * diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index ae14cbaf9d0e..690ebd96dc42 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -150,7 +150,7 @@ struct cfq_data { * idle window management */ struct timer_list idle_slice_timer; - struct delayed_work unplug_work; + struct work_struct unplug_work; struct cfq_queue *active_queue; struct cfq_io_context *active_cic; @@ -268,13 +268,11 @@ static inline int cfq_bio_sync(struct bio *bio) * scheduler run of queue, if there are requests pending and no one in the * driver that will restart queueing */ -static inline void cfq_schedule_dispatch(struct cfq_data *cfqd, - unsigned long delay) +static inline void cfq_schedule_dispatch(struct cfq_data *cfqd) { if (cfqd->busy_queues) { cfq_log(cfqd, "schedule dispatch"); - kblockd_schedule_delayed_work(cfqd->queue, &cfqd->unplug_work, - delay); + kblockd_schedule_work(cfqd->queue, &cfqd->unplug_work); } } @@ -1400,7 +1398,7 @@ static void cfq_put_queue(struct cfq_queue *cfqq) if (unlikely(cfqd->active_queue == cfqq)) { __cfq_slice_expired(cfqd, cfqq, 0); - cfq_schedule_dispatch(cfqd, 0); + cfq_schedule_dispatch(cfqd); } kmem_cache_free(cfq_pool, cfqq); @@ -1495,7 +1493,7 @@ static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq) { if (unlikely(cfqq == cfqd->active_queue)) { __cfq_slice_expired(cfqd, cfqq, 0); - cfq_schedule_dispatch(cfqd, 0); + cfq_schedule_dispatch(cfqd); } cfq_put_queue(cfqq); @@ -2213,7 +2211,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) } if (!rq_in_driver(cfqd)) - cfq_schedule_dispatch(cfqd, 0); + cfq_schedule_dispatch(cfqd); } /* @@ -2343,7 +2341,7 @@ queue_fail: if (cic) put_io_context(cic->ioc); - cfq_schedule_dispatch(cfqd, 0); + cfq_schedule_dispatch(cfqd); spin_unlock_irqrestore(q->queue_lock, flags); cfq_log(cfqd, "set_request fail"); return 1; @@ -2352,7 +2350,7 @@ queue_fail: static void cfq_kick_queue(struct work_struct *work) { struct cfq_data *cfqd = - container_of(work, struct cfq_data, unplug_work.work); + container_of(work, struct cfq_data, unplug_work); struct request_queue *q = cfqd->queue; spin_lock_irq(q->queue_lock); @@ -2406,7 +2404,7 @@ static void cfq_idle_slice_timer(unsigned long data) expire: cfq_slice_expired(cfqd, timed_out); out_kick: - cfq_schedule_dispatch(cfqd, 0); + cfq_schedule_dispatch(cfqd); out_cont: spin_unlock_irqrestore(cfqd->queue->queue_lock, flags); } @@ -2414,7 +2412,7 @@ out_cont: static void cfq_shutdown_timer_wq(struct cfq_data *cfqd) { del_timer_sync(&cfqd->idle_slice_timer); - cancel_delayed_work_sync(&cfqd->unplug_work); + cancel_work_sync(&cfqd->unplug_work); } static void cfq_put_async_queues(struct cfq_data *cfqd) @@ -2496,7 +2494,7 @@ static void *cfq_init_queue(struct request_queue *q) cfqd->idle_slice_timer.function = cfq_idle_slice_timer; cfqd->idle_slice_timer.data = (unsigned long) cfqd; - INIT_DELAYED_WORK(&cfqd->unplug_work, cfq_kick_queue); + INIT_WORK(&cfqd->unplug_work, cfq_kick_queue); cfqd->cfq_quantum = cfq_quantum; cfqd->cfq_fifo_expire[0] = cfq_fifo_expire[0]; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 25119041e034..221cecd86bd3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1172,11 +1172,7 @@ static inline void put_dev_sector(Sector p) } struct work_struct; -struct delayed_work; int kblockd_schedule_work(struct request_queue *q, struct work_struct *work); -int kblockd_schedule_delayed_work(struct request_queue *q, - struct delayed_work *work, - unsigned long delay); #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) -- cgit v1.2.3 From 3d76c082907e8f83c5d5c4572f38d53ad8f00c4b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 28 Sep 2009 07:46:32 -0700 Subject: rcu: Clean up code based on review feedback from Josh Triplett, part 3 Whitespace fixes, updated comments, and trivial code movement. o Fix whitespace error in RCU_HEAD_INIT() o Move "So where is rcu_write_lock()" comment so that it does not come between the rcu_read_unlock() header comment and the rcu_read_unlock() definition. o Move the module_param statements for blimit, qhimark, and qlowmark to immediately follow the corresponding definitions. o In __rcu_offline_cpu(), move the assignment to rdp_me inside the "if" statement, given that rdp_me is not used outside of that "if" statement. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: akpm@linux-foundation.org Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <12541491931164-git-send-email-> Signed-off-by: Ingo Molnar --- include/linux/rcupdate.h | 14 +++++++------- kernel/rcutree.c | 10 +++++----- 2 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 70331218e4b4..3ebd0b7bcb08 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -77,7 +77,7 @@ extern int rcu_scheduler_active; #error "Unknown RCU implementation specified to kernel configuration" #endif -#define RCU_HEAD_INIT { .next = NULL, .func = NULL } +#define RCU_HEAD_INIT { .next = NULL, .func = NULL } #define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT #define INIT_RCU_HEAD(ptr) do { \ (ptr)->next = NULL; (ptr)->func = NULL; \ @@ -129,12 +129,6 @@ static inline void rcu_read_lock(void) rcu_read_acquire(); } -/** - * rcu_read_unlock - marks the end of an RCU read-side critical section. - * - * See rcu_read_lock() for more information. - */ - /* * So where is rcu_write_lock()? It does not exist, as there is no * way for writers to lock out RCU readers. This is a feature, not @@ -144,6 +138,12 @@ static inline void rcu_read_lock(void) * used as well. RCU does not care how the writers keep out of each * others' way, as long as they do so. */ + +/** + * rcu_read_unlock - marks the end of an RCU read-side critical section. + * + * See rcu_read_lock() for more information. + */ static inline void rcu_read_unlock(void) { rcu_read_release(); diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 81af59b8dd88..d5597830faf5 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -122,6 +122,10 @@ static int blimit = 10; /* Maximum callbacks per softirq. */ static int qhimark = 10000; /* If this many pending, ignore blimit. */ static int qlowmark = 100; /* Once only this many pending, use blimit. */ +module_param(blimit, int, 0); +module_param(qhimark, int, 0); +module_param(qlowmark, int, 0); + static void force_quiescent_state(struct rcu_state *rsp, int relaxed); static int rcu_pending(int cpu); @@ -878,8 +882,8 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) * indefinitely delay callbacks, you have far worse things to * be worrying about. */ - rdp_me = rsp->rda[smp_processor_id()]; if (rdp->nxtlist != NULL) { + rdp_me = rsp->rda[smp_processor_id()]; *rdp_me->nxttail[RCU_NEXT_TAIL] = rdp->nxtlist; rdp_me->nxttail[RCU_NEXT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; rdp->nxtlist = NULL; @@ -1575,7 +1579,3 @@ void __init __rcu_init(void) } #include "rcutree_plugin.h" - -module_param(blimit, int, 0); -module_param(qhimark, int, 0); -module_param(qlowmark, int, 0); -- cgit v1.2.3 From f1bce7f80e3b400cf29787b0afa9c3042b959017 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 16 Sep 2009 04:16:04 +0900 Subject: libata: cosmetic updates We're about to add more SATA_* and ATA_ACPI_FILTER_* constants. Reformat them in preparation. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- drivers/ata/libata-acpi.c | 10 ---------- include/linux/ata.h | 6 +++--- include/linux/libata.h | 9 +++++++++ 3 files changed, 12 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c index 01964b6e6f6b..719e7d237dc8 100644 --- a/drivers/ata/libata-acpi.c +++ b/drivers/ata/libata-acpi.c @@ -20,16 +20,6 @@ #include -enum { - ATA_ACPI_FILTER_SETXFER = 1 << 0, - ATA_ACPI_FILTER_LOCK = 1 << 1, - ATA_ACPI_FILTER_DIPM = 1 << 2, - - ATA_ACPI_FILTER_DEFAULT = ATA_ACPI_FILTER_SETXFER | - ATA_ACPI_FILTER_LOCK | - ATA_ACPI_FILTER_DIPM, -}; - static unsigned int ata_acpi_gtf_filter = ATA_ACPI_FILTER_DEFAULT; module_param_named(acpi_gtf_filter, ata_acpi_gtf_filter, int, 0644); MODULE_PARM_DESC(acpi_gtf_filter, "filter mask for ACPI _GTF commands, set to filter out (0x1=set xfermode, 0x2=lock/freeze lock, 0x4=DIPM)"); diff --git a/include/linux/ata.h b/include/linux/ata.h index 6299a259ed19..7c5beafa972c 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -334,9 +334,9 @@ enum { SETFEATURES_SATA_DISABLE = 0x90, /* Disable use of SATA feature */ /* SETFEATURE Sector counts for SATA features */ - SATA_AN = 0x05, /* Asynchronous Notification */ - SATA_DIPM = 0x03, /* Device Initiated Power Management */ - SATA_FPDMA_AA = 0x02, /* DMA Setup FIS Auto-Activate */ + SATA_FPDMA_AA = 0x02, /* FPDMA Setup FIS Auto-Activate */ + SATA_DIPM = 0x03, /* Device Initiated Power Management */ + SATA_AN = 0x05, /* Asynchronous Notification */ /* feature values for SET_MAX */ ATA_SET_MAX_ADDR = 0x00, diff --git a/include/linux/libata.h b/include/linux/libata.h index 76319bf03e37..5b2f7491fb26 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -418,6 +418,15 @@ enum { ATA_TIMING_ACTIVE | ATA_TIMING_RECOVER | ATA_TIMING_DMACK_HOLD | ATA_TIMING_CYCLE | ATA_TIMING_UDMA, + + /* ACPI constants */ + ATA_ACPI_FILTER_SETXFER = 1 << 0, + ATA_ACPI_FILTER_LOCK = 1 << 1, + ATA_ACPI_FILTER_DIPM = 1 << 2, + + ATA_ACPI_FILTER_DEFAULT = ATA_ACPI_FILTER_SETXFER | + ATA_ACPI_FILTER_LOCK | + ATA_ACPI_FILTER_DIPM, }; enum ata_xfer_mask { -- cgit v1.2.3 From fa5b561c4ea170caf9759109acc2e961a7e83bea Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 16 Sep 2009 04:17:02 +0900 Subject: libata: implement more acpi filtering options Currently libata-acpi can only filter DIPM among SATA feature enables via _GTF. This patch adds the capability to filter out FPDMA non-zero offset, in-order guarantee and auto-activation. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- drivers/ata/libata-acpi.c | 19 +++++++++++++++---- include/linux/ata.h | 3 +++ include/linux/libata.h | 2 ++ 3 files changed, 20 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c index 719e7d237dc8..960c6a7caa83 100644 --- a/drivers/ata/libata-acpi.c +++ b/drivers/ata/libata-acpi.c @@ -22,7 +22,7 @@ static unsigned int ata_acpi_gtf_filter = ATA_ACPI_FILTER_DEFAULT; module_param_named(acpi_gtf_filter, ata_acpi_gtf_filter, int, 0644); -MODULE_PARM_DESC(acpi_gtf_filter, "filter mask for ACPI _GTF commands, set to filter out (0x1=set xfermode, 0x2=lock/freeze lock, 0x4=DIPM)"); +MODULE_PARM_DESC(acpi_gtf_filter, "filter mask for ACPI _GTF commands, set to filter out (0x1=set xfermode, 0x2=lock/freeze lock, 0x4=DIPM, 0x8=FPDMA non-zero offset, 0x10=FPDMA DMA Setup FIS auto-activate)"); #define NO_PORT_MULT 0xffff #define SATA_ADR(root, pmp) (((root) << 16) | (pmp)) @@ -637,12 +637,23 @@ static int ata_acpi_filter_tf(const struct ata_taskfile *tf, return 1; } - if (ata_acpi_gtf_filter & ATA_ACPI_FILTER_DIPM) { + if (tf->command == ATA_CMD_SET_FEATURES && + tf->feature == SETFEATURES_SATA_ENABLE) { /* inhibit enabling DIPM */ - if (tf->command == ATA_CMD_SET_FEATURES && - tf->feature == SETFEATURES_SATA_ENABLE && + if (ata_acpi_gtf_filter & ATA_ACPI_FILTER_DIPM && tf->nsect == SATA_DIPM) return 1; + + /* inhibit FPDMA non-zero offset */ + if (ata_acpi_gtf_filter & ATA_ACPI_FILTER_FPDMA_OFFSET && + (tf->nsect == SATA_FPDMA_OFFSET || + tf->nsect == SATA_FPDMA_IN_ORDER)) + return 1; + + /* inhibit FPDMA auto activation */ + if (ata_acpi_gtf_filter & ATA_ACPI_FILTER_FPDMA_AA && + tf->nsect == SATA_FPDMA_AA) + return 1; } return 0; diff --git a/include/linux/ata.h b/include/linux/ata.h index 7c5beafa972c..4fb357312b3b 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -334,9 +334,12 @@ enum { SETFEATURES_SATA_DISABLE = 0x90, /* Disable use of SATA feature */ /* SETFEATURE Sector counts for SATA features */ + SATA_FPDMA_OFFSET = 0x01, /* FPDMA non-zero buffer offsets */ SATA_FPDMA_AA = 0x02, /* FPDMA Setup FIS Auto-Activate */ SATA_DIPM = 0x03, /* Device Initiated Power Management */ + SATA_FPDMA_IN_ORDER = 0x04, /* FPDMA in-order data delivery */ SATA_AN = 0x05, /* Asynchronous Notification */ + SATA_SSP = 0x06, /* Software Settings Preservation */ /* feature values for SET_MAX */ ATA_SET_MAX_ADDR = 0x00, diff --git a/include/linux/libata.h b/include/linux/libata.h index 5b2f7491fb26..aa52794d2a03 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -423,6 +423,8 @@ enum { ATA_ACPI_FILTER_SETXFER = 1 << 0, ATA_ACPI_FILTER_LOCK = 1 << 1, ATA_ACPI_FILTER_DIPM = 1 << 2, + ATA_ACPI_FILTER_FPDMA_OFFSET = 1 << 3, /* FPDMA non-zero offset */ + ATA_ACPI_FILTER_FPDMA_AA = 1 << 4, /* FPDMA auto activate */ ATA_ACPI_FILTER_DEFAULT = ATA_ACPI_FILTER_SETXFER | ATA_ACPI_FILTER_LOCK | -- cgit v1.2.3 From 110f66d25c33c2259b1125255fa7063ab07b8340 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 16 Sep 2009 04:17:28 +0900 Subject: libata: make gtf_filter per-dev Add ->gtf_filter to ata_device and set it to ata_acpi_gtf_filter when initializing ata_link. This is to allow quirks which apply different gtf filters. Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- drivers/ata/libata-acpi.c | 17 +++++++++-------- drivers/ata/libata-core.c | 3 +++ drivers/ata/libata.h | 2 ++ include/linux/libata.h | 1 + 4 files changed, 15 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c index 960c6a7caa83..b0882cddfd4c 100644 --- a/drivers/ata/libata-acpi.c +++ b/drivers/ata/libata-acpi.c @@ -20,7 +20,7 @@ #include -static unsigned int ata_acpi_gtf_filter = ATA_ACPI_FILTER_DEFAULT; +unsigned int ata_acpi_gtf_filter = ATA_ACPI_FILTER_DEFAULT; module_param_named(acpi_gtf_filter, ata_acpi_gtf_filter, int, 0644); MODULE_PARM_DESC(acpi_gtf_filter, "filter mask for ACPI _GTF commands, set to filter out (0x1=set xfermode, 0x2=lock/freeze lock, 0x4=DIPM, 0x8=FPDMA non-zero offset, 0x10=FPDMA DMA Setup FIS auto-activate)"); @@ -603,10 +603,11 @@ static void ata_acpi_gtf_to_tf(struct ata_device *dev, tf->command = gtf->tf[6]; /* 0x1f7 */ } -static int ata_acpi_filter_tf(const struct ata_taskfile *tf, +static int ata_acpi_filter_tf(struct ata_device *dev, + const struct ata_taskfile *tf, const struct ata_taskfile *ptf) { - if (ata_acpi_gtf_filter & ATA_ACPI_FILTER_SETXFER) { + if (dev->gtf_filter & ATA_ACPI_FILTER_SETXFER) { /* libata doesn't use ACPI to configure transfer mode. * It will only confuse device configuration. Skip. */ @@ -615,7 +616,7 @@ static int ata_acpi_filter_tf(const struct ata_taskfile *tf, return 1; } - if (ata_acpi_gtf_filter & ATA_ACPI_FILTER_LOCK) { + if (dev->gtf_filter & ATA_ACPI_FILTER_LOCK) { /* BIOS writers, sorry but we don't wanna lock * features unless the user explicitly said so. */ @@ -640,18 +641,18 @@ static int ata_acpi_filter_tf(const struct ata_taskfile *tf, if (tf->command == ATA_CMD_SET_FEATURES && tf->feature == SETFEATURES_SATA_ENABLE) { /* inhibit enabling DIPM */ - if (ata_acpi_gtf_filter & ATA_ACPI_FILTER_DIPM && + if (dev->gtf_filter & ATA_ACPI_FILTER_DIPM && tf->nsect == SATA_DIPM) return 1; /* inhibit FPDMA non-zero offset */ - if (ata_acpi_gtf_filter & ATA_ACPI_FILTER_FPDMA_OFFSET && + if (dev->gtf_filter & ATA_ACPI_FILTER_FPDMA_OFFSET && (tf->nsect == SATA_FPDMA_OFFSET || tf->nsect == SATA_FPDMA_IN_ORDER)) return 1; /* inhibit FPDMA auto activation */ - if (ata_acpi_gtf_filter & ATA_ACPI_FILTER_FPDMA_AA && + if (dev->gtf_filter & ATA_ACPI_FILTER_FPDMA_AA && tf->nsect == SATA_FPDMA_AA) return 1; } @@ -705,7 +706,7 @@ static int ata_acpi_run_tf(struct ata_device *dev, pptf = &ptf; } - if (!ata_acpi_filter_tf(&tf, pptf)) { + if (!ata_acpi_filter_tf(dev, &tf, pptf)) { rtf = tf; err_mask = ata_exec_internal(dev, &rtf, NULL, DMA_NONE, NULL, 0, 0); diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 0ddaf43d68c6..b525a0981348 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5591,6 +5591,9 @@ void ata_link_init(struct ata_port *ap, struct ata_link *link, int pmp) dev->link = link; dev->devno = dev - link->device; +#ifdef CONFIG_ATA_ACPI + dev->gtf_filter = ata_acpi_gtf_filter; +#endif ata_dev_init(dev); } } diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h index be8e2628f82c..823e63096362 100644 --- a/drivers/ata/libata.h +++ b/drivers/ata/libata.h @@ -118,6 +118,8 @@ extern void ata_lpm_schedule(struct ata_port *ap, enum link_pm); /* libata-acpi.c */ #ifdef CONFIG_ATA_ACPI +extern unsigned int ata_acpi_gtf_filter; + extern void ata_acpi_associate_sata_port(struct ata_port *ap); extern void ata_acpi_associate(struct ata_host *host); extern void ata_acpi_dissociate(struct ata_host *host); diff --git a/include/linux/libata.h b/include/linux/libata.h index aa52794d2a03..87698640c091 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -598,6 +598,7 @@ struct ata_device { #ifdef CONFIG_ATA_ACPI acpi_handle acpi_handle; union acpi_object *gtf_cache; + unsigned int gtf_filter; #endif /* n_sector is CLEAR_BEGIN, read comment above CLEAR_BEGIN */ u64 n_sectors; /* size of device, if ATA */ -- cgit v1.2.3 From acf442dc560437858e6a4c904678052616f8226e Mon Sep 17 00:00:00 2001 From: Amit Kucheria Date: Mon, 5 Oct 2009 21:43:44 -0700 Subject: Input: fix rx51 board keymap The original driver was written with the KEY() macro defined as (col, row) instead of (row, col) as defined by the matrix keypad infrastructure. So the keymap was defined accordingly. Since the driver that was merged upstream uses the matrix keypad infrastructure, modify the keymap accordingly. While we are at it, fix the comments in twl4030.h and define PERSISTENT_KEY as (r,c) instead of (c, r) Tested on a RX51 (N900) device. Signed-off-by: Amit Kucheria Acked-by: Tony Lindgren Signed-off-by: Dmitry Torokhov --- arch/arm/mach-omap2/board-rx51-peripherals.c | 78 ++++++++++++++-------------- include/linux/i2c/twl4030.h | 6 +-- 2 files changed, 42 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c index 56d931a425f7..b5ce7a079995 100644 --- a/arch/arm/mach-omap2/board-rx51-peripherals.c +++ b/arch/arm/mach-omap2/board-rx51-peripherals.c @@ -37,49 +37,49 @@ static int rx51_keymap[] = { KEY(0, 0, KEY_Q), - KEY(0, 1, KEY_W), - KEY(0, 2, KEY_E), - KEY(0, 3, KEY_R), - KEY(0, 4, KEY_T), - KEY(0, 5, KEY_Y), - KEY(0, 6, KEY_U), - KEY(0, 7, KEY_I), - KEY(1, 0, KEY_O), + KEY(0, 1, KEY_O), + KEY(0, 2, KEY_P), + KEY(0, 3, KEY_COMMA), + KEY(0, 4, KEY_BACKSPACE), + KEY(0, 6, KEY_A), + KEY(0, 7, KEY_S), + KEY(1, 0, KEY_W), KEY(1, 1, KEY_D), - KEY(1, 2, KEY_DOT), - KEY(1, 3, KEY_V), - KEY(1, 4, KEY_DOWN), - KEY(2, 0, KEY_P), - KEY(2, 1, KEY_F), + KEY(1, 2, KEY_F), + KEY(1, 3, KEY_G), + KEY(1, 4, KEY_H), + KEY(1, 5, KEY_J), + KEY(1, 6, KEY_K), + KEY(1, 7, KEY_L), + KEY(2, 0, KEY_E), + KEY(2, 1, KEY_DOT), KEY(2, 2, KEY_UP), - KEY(2, 3, KEY_B), - KEY(2, 4, KEY_RIGHT), - KEY(3, 0, KEY_COMMA), - KEY(3, 1, KEY_G), - KEY(3, 2, KEY_ENTER), + KEY(2, 3, KEY_ENTER), + KEY(2, 5, KEY_Z), + KEY(2, 6, KEY_X), + KEY(2, 7, KEY_C), + KEY(3, 0, KEY_R), + KEY(3, 1, KEY_V), + KEY(3, 2, KEY_B), KEY(3, 3, KEY_N), - KEY(4, 0, KEY_BACKSPACE), - KEY(4, 1, KEY_H), - KEY(4, 3, KEY_M), + KEY(3, 4, KEY_M), + KEY(3, 5, KEY_SPACE), + KEY(3, 6, KEY_SPACE), + KEY(3, 7, KEY_LEFT), + KEY(4, 0, KEY_T), + KEY(4, 1, KEY_DOWN), + KEY(4, 2, KEY_RIGHT), KEY(4, 4, KEY_LEFTCTRL), - KEY(5, 1, KEY_J), - KEY(5, 2, KEY_Z), - KEY(5, 3, KEY_SPACE), - KEY(5, 4, KEY_LEFTSHIFT), - KEY(6, 0, KEY_A), - KEY(6, 1, KEY_K), - KEY(6, 2, KEY_X), - KEY(6, 3, KEY_SPACE), - KEY(6, 4, KEY_FN), - KEY(7, 0, KEY_S), - KEY(7, 1, KEY_L), - KEY(7, 2, KEY_C), - KEY(7, 3, KEY_LEFT), - KEY(0xff, 0, KEY_F6), - KEY(0xff, 1, KEY_F7), - KEY(0xff, 2, KEY_F8), - KEY(0xff, 4, KEY_F9), - KEY(0xff, 5, KEY_F10), + KEY(4, 5, KEY_RIGHTALT), + KEY(4, 6, KEY_LEFTSHIFT), + KEY(5, 0, KEY_Y), + KEY(6, 0, KEY_U), + KEY(7, 0, KEY_I), + KEY(7, 1, KEY_F7), + KEY(7, 2, KEY_F8), + KEY(0xff, 2, KEY_F9), + KEY(0xff, 4, KEY_F10), + KEY(0xff, 5, KEY_F11), }; static struct twl4030_keypad_data rx51_kp_data = { diff --git a/include/linux/i2c/twl4030.h b/include/linux/i2c/twl4030.h index 3fd21d7cb6bf..007572536ea9 100644 --- a/include/linux/i2c/twl4030.h +++ b/include/linux/i2c/twl4030.h @@ -305,11 +305,11 @@ struct twl4030_madc_platform_data { int irq_line; }; -/* Boards have uniqe mappings of {col, row} --> keycode. - * Column and row are 4 bits, but range only from 0..7. +/* Boards have uniqe mappings of {row, col} --> keycode. + * Column and row are 8 bits each, but range only from 0..7. * a PERSISTENT_KEY is "always on" and never reported. */ -#define PERSISTENT_KEY(c, r) KEY((c), (r), KEY_RESERVED) +#define PERSISTENT_KEY(r, c) KEY((r), (c), KEY_RESERVED) struct twl4030_keypad_data { const struct matrix_keymap_data *keymap_data; -- cgit v1.2.3 From ea2a4d3a3a929ef494952bba57a0ef1a8a877881 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 6 Oct 2009 10:34:13 +0200 Subject: [S390] 64-bit register support for 31-bit processes From: Heiko Carstens From: Martin Schwidefsky Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/include/asm/elf.h | 12 +++++++ arch/s390/include/asm/ptrace.h | 4 +++ arch/s390/include/asm/ucontext.h | 15 +++++++++ arch/s390/kernel/compat_signal.c | 35 +++++++++++++++++++- arch/s390/kernel/ptrace.c | 70 ++++++++++++++++++++++++++++++++++++++++ arch/s390/kernel/setup.c | 15 +++++++-- include/linux/elf.h | 1 + 7 files changed, 148 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index 74d0bbb7d955..e885442c1dfe 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -92,6 +92,18 @@ /* Keep this the last entry. */ #define R_390_NUM 61 +/* Bits present in AT_HWCAP. */ +#define HWCAP_S390_ESAN3 1 +#define HWCAP_S390_ZARCH 2 +#define HWCAP_S390_STFLE 4 +#define HWCAP_S390_MSA 8 +#define HWCAP_S390_LDISP 16 +#define HWCAP_S390_EIMM 32 +#define HWCAP_S390_DFP 64 +#define HWCAP_S390_HPAGE 128 +#define HWCAP_S390_ETF3EH 256 +#define HWCAP_S390_HIGH_GPRS 512 + /* * These are used to set parameters in the core dumps. */ diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index 539263fc9ab9..95dcf183a28d 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -311,6 +311,10 @@ typedef struct __u32 orig_gpr2; } s390_compat_regs; +typedef struct +{ + __u32 gprs_high[NUM_GPRS]; +} s390_compat_regs_high; #ifdef __KERNEL__ diff --git a/arch/s390/include/asm/ucontext.h b/arch/s390/include/asm/ucontext.h index d69bec0b03f5..cfb874e66c9a 100644 --- a/arch/s390/include/asm/ucontext.h +++ b/arch/s390/include/asm/ucontext.h @@ -9,6 +9,21 @@ #ifndef _ASM_S390_UCONTEXT_H #define _ASM_S390_UCONTEXT_H +#define UC_EXTENDED 0x00000001 + +#ifndef __s390x__ + +struct ucontext_extended { + unsigned long uc_flags; + struct ucontext *uc_link; + stack_t uc_stack; + _sigregs uc_mcontext; + unsigned long uc_sigmask[2]; + unsigned long uc_gprs_high[16]; +}; + +#endif + struct ucontext { unsigned long uc_flags; struct ucontext *uc_link; diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index b537cb0e9b55..eee999853a7c 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -39,6 +39,7 @@ typedef struct struct sigcontext32 sc; _sigregs32 sregs; int signo; + __u32 gprs_high[NUM_GPRS]; __u8 retcode[S390_SYSCALL_SIZE]; } sigframe32; @@ -48,6 +49,7 @@ typedef struct __u8 retcode[S390_SYSCALL_SIZE]; compat_siginfo_t info; struct ucontext32 uc; + __u32 gprs_high[NUM_GPRS]; } rt_sigframe32; int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) @@ -344,6 +346,30 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs) return 0; } +static int save_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs) +{ + __u32 gprs_high[NUM_GPRS]; + int i; + + for (i = 0; i < NUM_GPRS; i++) + gprs_high[i] = regs->gprs[i] >> 32; + + return __copy_to_user(uregs, &gprs_high, sizeof(gprs_high)); +} + +static int restore_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs) +{ + __u32 gprs_high[NUM_GPRS]; + int err, i; + + err = __copy_from_user(&gprs_high, uregs, sizeof(gprs_high)); + if (err) + return err; + for (i = 0; i < NUM_GPRS; i++) + *(__u32 *)®s->gprs[i] = gprs_high[i]; + return 0; +} + asmlinkage long sys32_sigreturn(void) { struct pt_regs *regs = task_pt_regs(current); @@ -363,6 +389,8 @@ asmlinkage long sys32_sigreturn(void) if (restore_sigregs32(regs, &frame->sregs)) goto badframe; + if (restore_sigregs_gprs_high(regs, frame->gprs_high)) + goto badframe; return regs->gprs[2]; @@ -394,6 +422,8 @@ asmlinkage long sys32_rt_sigreturn(void) if (restore_sigregs32(regs, &frame->uc.uc_mcontext)) goto badframe; + if (restore_sigregs_gprs_high(regs, frame->gprs_high)) + goto badframe; err = __get_user(ss_sp, &frame->uc.uc_stack.ss_sp); st.ss_sp = compat_ptr(ss_sp); @@ -474,6 +504,8 @@ static int setup_frame32(int sig, struct k_sigaction *ka, if (save_sigregs32(regs, &frame->sregs)) goto give_sigsegv; + if (save_sigregs_gprs_high(regs, frame->gprs_high)) + goto give_sigsegv; if (__put_user((unsigned long) &frame->sregs, &frame->sc.sregs)) goto give_sigsegv; @@ -529,13 +561,14 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, goto give_sigsegv; /* Create the ucontext. */ - err |= __put_user(0, &frame->uc.uc_flags); + err |= __put_user(UC_EXTENDED, &frame->uc.uc_flags); err |= __put_user(0, &frame->uc.uc_link); err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); err |= __put_user(sas_ss_flags(regs->gprs[15]), &frame->uc.uc_stack.ss_flags); err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size); err |= save_sigregs32(regs, &frame->uc.uc_mcontext); + err |= save_sigregs_gprs_high(regs, frame->gprs_high); err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); if (err) goto give_sigsegv; diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index a8738676b26c..653c6a178740 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -57,6 +57,7 @@ enum s390_regset { REGSET_GENERAL, REGSET_FP, + REGSET_GENERAL_EXTENDED, }; static void @@ -879,6 +880,67 @@ static int s390_compat_regs_set(struct task_struct *target, return rc; } +static int s390_compat_regs_high_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + compat_ulong_t *gprs_high; + + gprs_high = (compat_ulong_t *) + &task_pt_regs(target)->gprs[pos / sizeof(compat_ulong_t)]; + if (kbuf) { + compat_ulong_t *k = kbuf; + while (count > 0) { + *k++ = *gprs_high; + gprs_high += 2; + count -= sizeof(*k); + } + } else { + compat_ulong_t __user *u = ubuf; + while (count > 0) { + if (__put_user(*gprs_high, u++)) + return -EFAULT; + gprs_high += 2; + count -= sizeof(*u); + } + } + return 0; +} + +static int s390_compat_regs_high_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + compat_ulong_t *gprs_high; + int rc = 0; + + gprs_high = (compat_ulong_t *) + &task_pt_regs(target)->gprs[pos / sizeof(compat_ulong_t)]; + if (kbuf) { + const compat_ulong_t *k = kbuf; + while (count > 0) { + *gprs_high = *k++; + *gprs_high += 2; + count -= sizeof(*k); + } + } else { + const compat_ulong_t __user *u = ubuf; + while (count > 0 && !rc) { + unsigned long word; + rc = __get_user(word, u++); + if (rc) + break; + *gprs_high = word; + *gprs_high += 2; + count -= sizeof(*u); + } + } + + return rc; +} + static const struct user_regset s390_compat_regsets[] = { [REGSET_GENERAL] = { .core_note_type = NT_PRSTATUS, @@ -896,6 +958,14 @@ static const struct user_regset s390_compat_regsets[] = { .get = s390_fpregs_get, .set = s390_fpregs_set, }, + [REGSET_GENERAL_EXTENDED] = { + .core_note_type = NT_PRXSTATUS, + .n = sizeof(s390_compat_regs_high) / sizeof(compat_long_t), + .size = sizeof(compat_long_t), + .align = sizeof(compat_long_t), + .get = s390_compat_regs_high_get, + .set = s390_compat_regs_high_set, + }, }; static const struct user_regset_view user_s390_compat_view = { diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 9ed13a1ed376..061479ff029f 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -729,7 +729,7 @@ static void __init setup_hwcaps(void) if ((facility_list & (1UL << (31 - 22))) && (facility_list & (1UL << (31 - 30)))) - elf_hwcap |= 1UL << 8; + elf_hwcap |= HWCAP_S390_ETF3EH; /* * Check for additional facilities with store-facility-list-extended. @@ -748,11 +748,20 @@ static void __init setup_hwcaps(void) __stfle(&facility_list_extended, 1) > 0) { if ((facility_list_extended & (1ULL << (63 - 42))) && (facility_list_extended & (1ULL << (63 - 44)))) - elf_hwcap |= 1UL << 6; + elf_hwcap |= HWCAP_S390_DFP; } + /* + * Huge page support HWCAP_S390_HPAGE is bit 7. + */ if (MACHINE_HAS_HPAGE) - elf_hwcap |= 1UL << 7; + elf_hwcap |= HWCAP_S390_HPAGE; + + /* + * 64-bit register support for 31-bit processes + * HWCAP_S390_HIGH_GPRS is bit 9. + */ + elf_hwcap |= HWCAP_S390_HIGH_GPRS; switch (S390_lowcore.cpu_id.machine) { case 0x9672: diff --git a/include/linux/elf.h b/include/linux/elf.h index 45a937be6d38..90a4ed0ea0e5 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -361,6 +361,7 @@ typedef struct elf64_shdr { #define NT_PPC_VSX 0x102 /* PowerPC VSX registers */ #define NT_386_TLS 0x200 /* i386 TLS slots (struct user_desc) */ #define NT_386_IOPERM 0x201 /* x86 io permission bitmap (1=deny) */ +#define NT_PRXSTATUS 0x300 /* s390 upper register halves */ /* Note header in a PT_NOTE section */ -- cgit v1.2.3 From e13dbd7d75d1ecc315c6e3071b3c4e8fba4f6bec Mon Sep 17 00:00:00 2001 From: Chuck Ebbert Date: Tue, 6 Oct 2009 07:38:51 -0400 Subject: perf_events: Make ABI definitions available to userspace Signed-off-by: Chuck Ebbert LKML-Reference: <200910061138.n96BcqkJ004709@int-mx03.intmail.prod.int.phx2.redhat.com> Signed-off-by: Ingo Molnar --- include/linux/Kbuild | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index cff4a101f266..3f384d4b163a 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -126,6 +126,7 @@ header-y += nfs_mount.h header-y += nl80211.h header-y += param.h header-y += pci_regs.h +header-y += perf_event.h header-y += pfkeyv2.h header-y += pg.h header-y += phantom.h -- cgit v1.2.3 From 906010b2134e14a2e377decbadd357b3d0ab9c6a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 21 Sep 2009 16:08:49 +0200 Subject: perf_event: Provide vmalloc() based mmap() backing Some architectures such as Sparc, ARM and MIPS (basically everything with flush_dcache_page()) need to deal with dcache aliases by carefully placing pages in both kernel and user maps. These architectures typically have to use vmalloc_user() for this. However, on other architectures, vmalloc() is not needed and has the downsides of being more restricted and slower than regular allocations. Signed-off-by: Peter Zijlstra Acked-by: David Miller Cc: Andrew Morton Cc: Jens Axboe Cc: Paul Mackerras LKML-Reference: <1254830228.21044.272.camel@laptop> Signed-off-by: Ingo Molnar --- arch/sparc/Kconfig | 2 + include/linux/perf_event.h | 5 + init/Kconfig | 18 ++++ kernel/perf_event.c | 248 +++++++++++++++++++++++++++++++++------------ tools/perf/design.txt | 3 + 5 files changed, 214 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 97fca4695e0b..9b70a2f28dc7 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -26,6 +26,7 @@ config SPARC select RTC_CLASS select RTC_DRV_M48T59 select HAVE_PERF_EVENTS + select PERF_USE_VMALLOC select HAVE_DMA_ATTRS select HAVE_DMA_API_DEBUG @@ -48,6 +49,7 @@ config SPARC64 select RTC_DRV_SUN4V select RTC_DRV_STARFIRE select HAVE_PERF_EVENTS + select PERF_USE_VMALLOC config ARCH_DEFCONFIG string diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 3a9d36d1e92a..2e6d95f97419 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -442,6 +442,7 @@ enum perf_callchain_context { #include #include #include +#include #include #define PERF_MAX_STACK_DEPTH 255 @@ -513,6 +514,10 @@ struct file; struct perf_mmap_data { struct rcu_head rcu_head; +#ifdef CONFIG_PERF_USE_VMALLOC + struct work_struct work; +#endif + int data_order; int nr_pages; /* nr of data pages */ int writable; /* are we writable */ int nr_locked; /* nr pages mlocked */ diff --git a/init/Kconfig b/init/Kconfig index c7bac39d6c61..09c5c6431f42 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -921,6 +921,11 @@ config HAVE_PERF_EVENTS help See tools/perf/design.txt for details. +config PERF_USE_VMALLOC + bool + help + See tools/perf/design.txt for details + menu "Kernel Performance Events And Counters" config PERF_EVENTS @@ -976,6 +981,19 @@ config PERF_COUNTERS Say N if unsure. +config DEBUG_PERF_USE_VMALLOC + default n + bool "Debug: use vmalloc to back perf mmap() buffers" + depends on PERF_EVENTS && DEBUG_KERNEL + select PERF_USE_VMALLOC + help + Use vmalloc memory to back perf mmap() buffers. + + Mostly useful for debugging the vmalloc code on platforms + that don't require it. + + Say N if unsure. + endmenu config VM_EVENT_COUNTERS diff --git a/kernel/perf_event.c b/kernel/perf_event.c index e491fb087939..9d0b5c665883 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -2091,49 +2092,31 @@ unlock: rcu_read_unlock(); } -static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +static unsigned long perf_data_size(struct perf_mmap_data *data) { - struct perf_event *event = vma->vm_file->private_data; - struct perf_mmap_data *data; - int ret = VM_FAULT_SIGBUS; - - if (vmf->flags & FAULT_FLAG_MKWRITE) { - if (vmf->pgoff == 0) - ret = 0; - return ret; - } - - rcu_read_lock(); - data = rcu_dereference(event->data); - if (!data) - goto unlock; - - if (vmf->pgoff == 0) { - vmf->page = virt_to_page(data->user_page); - } else { - int nr = vmf->pgoff - 1; - - if ((unsigned)nr > data->nr_pages) - goto unlock; + return data->nr_pages << (PAGE_SHIFT + data->data_order); +} - if (vmf->flags & FAULT_FLAG_WRITE) - goto unlock; +#ifndef CONFIG_PERF_USE_VMALLOC - vmf->page = virt_to_page(data->data_pages[nr]); - } +/* + * Back perf_mmap() with regular GFP_KERNEL-0 pages. + */ - get_page(vmf->page); - vmf->page->mapping = vma->vm_file->f_mapping; - vmf->page->index = vmf->pgoff; +static struct page * +perf_mmap_to_page(struct perf_mmap_data *data, unsigned long pgoff) +{ + if (pgoff > data->nr_pages) + return NULL; - ret = 0; -unlock: - rcu_read_unlock(); + if (pgoff == 0) + return virt_to_page(data->user_page); - return ret; + return virt_to_page(data->data_pages[pgoff - 1]); } -static int perf_mmap_data_alloc(struct perf_event *event, int nr_pages) +static struct perf_mmap_data * +perf_mmap_data_alloc(struct perf_event *event, int nr_pages) { struct perf_mmap_data *data; unsigned long size; @@ -2158,19 +2141,10 @@ static int perf_mmap_data_alloc(struct perf_event *event, int nr_pages) goto fail_data_pages; } + data->data_order = 0; data->nr_pages = nr_pages; - atomic_set(&data->lock, -1); - - if (event->attr.watermark) { - data->watermark = min_t(long, PAGE_SIZE * nr_pages, - event->attr.wakeup_watermark); - } - if (!data->watermark) - data->watermark = max(PAGE_SIZE, PAGE_SIZE * nr_pages / 4); - rcu_assign_pointer(event->data, data); - - return 0; + return data; fail_data_pages: for (i--; i >= 0; i--) @@ -2182,7 +2156,7 @@ fail_user_page: kfree(data); fail: - return -ENOMEM; + return NULL; } static void perf_mmap_free_page(unsigned long addr) @@ -2193,28 +2167,169 @@ static void perf_mmap_free_page(unsigned long addr) __free_page(page); } -static void __perf_mmap_data_free(struct rcu_head *rcu_head) +static void perf_mmap_data_free(struct perf_mmap_data *data) { - struct perf_mmap_data *data; int i; - data = container_of(rcu_head, struct perf_mmap_data, rcu_head); - perf_mmap_free_page((unsigned long)data->user_page); for (i = 0; i < data->nr_pages; i++) perf_mmap_free_page((unsigned long)data->data_pages[i]); +} + +#else + +/* + * Back perf_mmap() with vmalloc memory. + * + * Required for architectures that have d-cache aliasing issues. + */ + +static struct page * +perf_mmap_to_page(struct perf_mmap_data *data, unsigned long pgoff) +{ + if (pgoff > (1UL << data->data_order)) + return NULL; + + return vmalloc_to_page((void *)data->user_page + pgoff * PAGE_SIZE); +} + +static void perf_mmap_unmark_page(void *addr) +{ + struct page *page = vmalloc_to_page(addr); + + page->mapping = NULL; +} + +static void perf_mmap_data_free_work(struct work_struct *work) +{ + struct perf_mmap_data *data; + void *base; + int i, nr; + + data = container_of(work, struct perf_mmap_data, work); + nr = 1 << data->data_order; + + base = data->user_page; + for (i = 0; i < nr + 1; i++) + perf_mmap_unmark_page(base + (i * PAGE_SIZE)); + + vfree(base); +} + +static void perf_mmap_data_free(struct perf_mmap_data *data) +{ + schedule_work(&data->work); +} + +static struct perf_mmap_data * +perf_mmap_data_alloc(struct perf_event *event, int nr_pages) +{ + struct perf_mmap_data *data; + unsigned long size; + void *all_buf; + WARN_ON(atomic_read(&event->mmap_count)); + + size = sizeof(struct perf_mmap_data); + size += sizeof(void *); + + data = kzalloc(size, GFP_KERNEL); + if (!data) + goto fail; + + INIT_WORK(&data->work, perf_mmap_data_free_work); + + all_buf = vmalloc_user((nr_pages + 1) * PAGE_SIZE); + if (!all_buf) + goto fail_all_buf; + + data->user_page = all_buf; + data->data_pages[0] = all_buf + PAGE_SIZE; + data->data_order = ilog2(nr_pages); + data->nr_pages = 1; + + return data; + +fail_all_buf: + kfree(data); + +fail: + return NULL; +} + +#endif + +static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct perf_event *event = vma->vm_file->private_data; + struct perf_mmap_data *data; + int ret = VM_FAULT_SIGBUS; + + if (vmf->flags & FAULT_FLAG_MKWRITE) { + if (vmf->pgoff == 0) + ret = 0; + return ret; + } + + rcu_read_lock(); + data = rcu_dereference(event->data); + if (!data) + goto unlock; + + if (vmf->pgoff && (vmf->flags & FAULT_FLAG_WRITE)) + goto unlock; + + vmf->page = perf_mmap_to_page(data, vmf->pgoff); + if (!vmf->page) + goto unlock; + + get_page(vmf->page); + vmf->page->mapping = vma->vm_file->f_mapping; + vmf->page->index = vmf->pgoff; + + ret = 0; +unlock: + rcu_read_unlock(); + + return ret; +} + +static void +perf_mmap_data_init(struct perf_event *event, struct perf_mmap_data *data) +{ + long max_size = perf_data_size(data); + + atomic_set(&data->lock, -1); + + if (event->attr.watermark) { + data->watermark = min_t(long, max_size, + event->attr.wakeup_watermark); + } + + if (!data->watermark) + data->watermark = max_t(long, PAGE_SIZE, max_size / 2); + + + rcu_assign_pointer(event->data, data); +} + +static void perf_mmap_data_free_rcu(struct rcu_head *rcu_head) +{ + struct perf_mmap_data *data; + + data = container_of(rcu_head, struct perf_mmap_data, rcu_head); + perf_mmap_data_free(data); kfree(data); } -static void perf_mmap_data_free(struct perf_event *event) +static void perf_mmap_data_release(struct perf_event *event) { struct perf_mmap_data *data = event->data; WARN_ON(atomic_read(&event->mmap_count)); rcu_assign_pointer(event->data, NULL); - call_rcu(&data->rcu_head, __perf_mmap_data_free); + call_rcu(&data->rcu_head, perf_mmap_data_free_rcu); } static void perf_mmap_open(struct vm_area_struct *vma) @@ -2230,11 +2345,12 @@ static void perf_mmap_close(struct vm_area_struct *vma) WARN_ON_ONCE(event->ctx->parent_ctx); if (atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) { + unsigned long size = perf_data_size(event->data); struct user_struct *user = current_user(); - atomic_long_sub(event->data->nr_pages + 1, &user->locked_vm); + atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm); vma->vm_mm->locked_vm -= event->data->nr_locked; - perf_mmap_data_free(event); + perf_mmap_data_release(event); mutex_unlock(&event->mmap_mutex); } } @@ -2252,6 +2368,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) unsigned long user_locked, user_lock_limit; struct user_struct *user = current_user(); unsigned long locked, lock_limit; + struct perf_mmap_data *data; unsigned long vma_size; unsigned long nr_pages; long user_extra, extra; @@ -2314,10 +2431,15 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) } WARN_ON(event->data); - ret = perf_mmap_data_alloc(event, nr_pages); - if (ret) + + data = perf_mmap_data_alloc(event, nr_pages); + ret = -ENOMEM; + if (!data) goto unlock; + ret = 0; + perf_mmap_data_init(event, data); + atomic_set(&event->mmap_count, 1); atomic_long_add(user_extra, &user->locked_vm); vma->vm_mm->locked_vm += extra; @@ -2505,7 +2627,7 @@ static bool perf_output_space(struct perf_mmap_data *data, unsigned long tail, if (!data->writable) return true; - mask = (data->nr_pages << PAGE_SHIFT) - 1; + mask = perf_data_size(data) - 1; offset = (offset - tail) & mask; head = (head - tail) & mask; @@ -2610,7 +2732,7 @@ void perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len) { unsigned int pages_mask; - unsigned int offset; + unsigned long offset; unsigned int size; void **pages; @@ -2619,12 +2741,14 @@ void perf_output_copy(struct perf_output_handle *handle, pages = handle->data->data_pages; do { - unsigned int page_offset; + unsigned long page_offset; + unsigned long page_size; int nr; nr = (offset >> PAGE_SHIFT) & pages_mask; - page_offset = offset & (PAGE_SIZE - 1); - size = min_t(unsigned int, PAGE_SIZE - page_offset, len); + page_size = 1UL << (handle->data->data_order + PAGE_SHIFT); + page_offset = offset & (page_size - 1); + size = min_t(unsigned int, page_size - page_offset, len); memcpy(pages[nr] + page_offset, buf, size); diff --git a/tools/perf/design.txt b/tools/perf/design.txt index f1946d107b10..fdd42a824c98 100644 --- a/tools/perf/design.txt +++ b/tools/perf/design.txt @@ -455,3 +455,6 @@ will need at least this: If your architecture does have hardware capabilities, you can override the weak stub hw_perf_event_init() to register hardware counters. + +Architectures that have d-cache aliassing issues, such as Sparc and ARM, +should select PERF_USE_VMALLOC in order to avoid these for perf mmap(). -- cgit v1.2.3 From 316d315bffa4026f28085f6b24ebcebede370ac7 Mon Sep 17 00:00:00 2001 From: Nikanth Karthikesan Date: Tue, 6 Oct 2009 20:16:55 +0200 Subject: block: Seperate read and write statistics of in_flight requests v2 Commit a9327cac440be4d8333bba975cbbf76045096275 added seperate read and write statistics of in_flight requests. And exported the number of read and write requests in progress seperately through sysfs. But Corrado Zoccolo reported getting strange output from "iostat -kx 2". Global values for service time and utilization were garbage. For interval values, utilization was always 100%, and service time is higher than normal. So this was reverted by commit 0f78ab9899e9d6acb09d5465def618704255963b The problem was in part_round_stats_single(), I missed the following: if (now == part->stamp) return; - if (part->in_flight) { + if (part_in_flight(part)) { __part_stat_add(cpu, part, time_in_queue, part_in_flight(part) * (now - part->stamp)); __part_stat_add(cpu, part, io_ticks, (now - part->stamp)); With this chunk included, the reported regression gets fixed. Signed-off-by: Nikanth Karthikesan -- Signed-off-by: Jens Axboe --- block/blk-core.c | 8 ++++---- block/blk-merge.c | 2 +- block/genhd.c | 4 +++- drivers/md/dm.c | 16 ++++++++++------ fs/partitions/check.c | 12 +++++++++++- include/linux/genhd.h | 21 ++++++++++++++------- 6 files changed, 43 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 73ecbed02605..ac0fa10f8fa5 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -70,7 +70,7 @@ static void drive_stat_acct(struct request *rq, int new_io) part_stat_inc(cpu, part, merges[rw]); else { part_round_stats(cpu, part); - part_inc_in_flight(part); + part_inc_in_flight(part, rw); } part_stat_unlock(); @@ -1030,9 +1030,9 @@ static void part_round_stats_single(int cpu, struct hd_struct *part, if (now == part->stamp) return; - if (part->in_flight) { + if (part_in_flight(part)) { __part_stat_add(cpu, part, time_in_queue, - part->in_flight * (now - part->stamp)); + part_in_flight(part) * (now - part->stamp)); __part_stat_add(cpu, part, io_ticks, (now - part->stamp)); } part->stamp = now; @@ -1739,7 +1739,7 @@ static void blk_account_io_done(struct request *req) part_stat_inc(cpu, part, ios[rw]); part_stat_add(cpu, part, ticks[rw], duration); part_round_stats(cpu, part); - part_dec_in_flight(part); + part_dec_in_flight(part, rw); part_stat_unlock(); } diff --git a/block/blk-merge.c b/block/blk-merge.c index b0de8574fdc8..99cb5cf1f447 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -351,7 +351,7 @@ static void blk_account_io_merge(struct request *req) part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req)); part_round_stats(cpu, part); - part_dec_in_flight(part); + part_dec_in_flight(part, rq_data_dir(req)); part_stat_unlock(); } diff --git a/block/genhd.c b/block/genhd.c index 5a0861da324d..517e4332cb37 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -869,6 +869,7 @@ static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL); static DEVICE_ATTR(alignment_offset, S_IRUGO, disk_alignment_offset_show, NULL); static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL); static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); +static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store); @@ -888,6 +889,7 @@ static struct attribute *disk_attrs[] = { &dev_attr_alignment_offset.attr, &dev_attr_capability.attr, &dev_attr_stat.attr, + &dev_attr_inflight.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif @@ -1053,7 +1055,7 @@ static int diskstats_show(struct seq_file *seqf, void *v) part_stat_read(hd, merges[1]), (unsigned long long)part_stat_read(hd, sectors[1]), jiffies_to_msecs(part_stat_read(hd, ticks[1])), - hd->in_flight, + part_in_flight(hd), jiffies_to_msecs(part_stat_read(hd, io_ticks)), jiffies_to_msecs(part_stat_read(hd, time_in_queue)) ); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 23e76fe0d359..376f1ab48a24 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -130,7 +130,7 @@ struct mapped_device { /* * A list of ios that arrived while we were suspended. */ - atomic_t pending; + atomic_t pending[2]; wait_queue_head_t wait; struct work_struct work; struct bio_list deferred; @@ -453,13 +453,14 @@ static void start_io_acct(struct dm_io *io) { struct mapped_device *md = io->md; int cpu; + int rw = bio_data_dir(io->bio); io->start_time = jiffies; cpu = part_stat_lock(); part_round_stats(cpu, &dm_disk(md)->part0); part_stat_unlock(); - dm_disk(md)->part0.in_flight = atomic_inc_return(&md->pending); + dm_disk(md)->part0.in_flight[rw] = atomic_inc_return(&md->pending[rw]); } static void end_io_acct(struct dm_io *io) @@ -479,8 +480,9 @@ static void end_io_acct(struct dm_io *io) * After this is decremented the bio must not be touched if it is * a barrier. */ - dm_disk(md)->part0.in_flight = pending = - atomic_dec_return(&md->pending); + dm_disk(md)->part0.in_flight[rw] = pending = + atomic_dec_return(&md->pending[rw]); + pending += atomic_read(&md->pending[rw^0x1]); /* nudge anyone waiting on suspend queue */ if (!pending) @@ -1785,7 +1787,8 @@ static struct mapped_device *alloc_dev(int minor) if (!md->disk) goto bad_disk; - atomic_set(&md->pending, 0); + atomic_set(&md->pending[0], 0); + atomic_set(&md->pending[1], 0); init_waitqueue_head(&md->wait); INIT_WORK(&md->work, dm_wq_work); init_waitqueue_head(&md->eventq); @@ -2088,7 +2091,8 @@ static int dm_wait_for_completion(struct mapped_device *md, int interruptible) break; } spin_unlock_irqrestore(q->queue_lock, flags); - } else if (!atomic_read(&md->pending)) + } else if (!atomic_read(&md->pending[0]) && + !atomic_read(&md->pending[1])) break; if (interruptible == TASK_INTERRUPTIBLE && diff --git a/fs/partitions/check.c b/fs/partitions/check.c index f38fee0311a7..7b685e10cbad 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -248,11 +248,19 @@ ssize_t part_stat_show(struct device *dev, part_stat_read(p, merges[WRITE]), (unsigned long long)part_stat_read(p, sectors[WRITE]), jiffies_to_msecs(part_stat_read(p, ticks[WRITE])), - p->in_flight, + part_in_flight(p), jiffies_to_msecs(part_stat_read(p, io_ticks)), jiffies_to_msecs(part_stat_read(p, time_in_queue))); } +ssize_t part_inflight_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct hd_struct *p = dev_to_part(dev); + + return sprintf(buf, "%8u %8u\n", p->in_flight[0], p->in_flight[1]); +} + #ifdef CONFIG_FAIL_MAKE_REQUEST ssize_t part_fail_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -281,6 +289,7 @@ static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL); static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL); static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL); static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); +static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store); @@ -292,6 +301,7 @@ static struct attribute *part_attrs[] = { &dev_attr_size.attr, &dev_attr_alignment_offset.attr, &dev_attr_stat.attr, + &dev_attr_inflight.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 7beaa21b3880..297df45ffd0a 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -98,7 +98,7 @@ struct hd_struct { int make_it_fail; #endif unsigned long stamp; - int in_flight; + int in_flight[2]; #ifdef CONFIG_SMP struct disk_stats *dkstats; #else @@ -322,18 +322,23 @@ static inline void free_part_stats(struct hd_struct *part) #define part_stat_sub(cpu, gendiskp, field, subnd) \ part_stat_add(cpu, gendiskp, field, -subnd) -static inline void part_inc_in_flight(struct hd_struct *part) +static inline void part_inc_in_flight(struct hd_struct *part, int rw) { - part->in_flight++; + part->in_flight[rw]++; if (part->partno) - part_to_disk(part)->part0.in_flight++; + part_to_disk(part)->part0.in_flight[rw]++; } -static inline void part_dec_in_flight(struct hd_struct *part) +static inline void part_dec_in_flight(struct hd_struct *part, int rw) { - part->in_flight--; + part->in_flight[rw]--; if (part->partno) - part_to_disk(part)->part0.in_flight--; + part_to_disk(part)->part0.in_flight[rw]--; +} + +static inline int part_in_flight(struct hd_struct *part) +{ + return part->in_flight[0] + part->in_flight[1]; } /* block/blk-core.c */ @@ -546,6 +551,8 @@ extern ssize_t part_size_show(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t part_stat_show(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t part_inflight_show(struct device *dev, + struct device_attribute *attr, char *buf); #ifdef CONFIG_FAIL_MAKE_REQUEST extern ssize_t part_fail_show(struct device *dev, struct device_attribute *attr, char *buf); -- cgit v1.2.3 From f8d1e548931cfa5ea9a082e020c2a47d27e5d793 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 7 Oct 2009 11:13:58 +1100 Subject: futex: Fix typo in FUTEX_WAIT/WAKE_BITSET_PRIVATE definitions Looks like a typo, FUTEX_WAKE_BITS should be FUTEX_WAIT_BITSET. Signed-off-by: Anton Blanchard LKML-Reference: <20091007001358.GE16073@kryten> Signed-off-by: Thomas Gleixner --- include/linux/futex.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/futex.h b/include/linux/futex.h index 34956c8fdebf..78b92ec9edbd 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -38,8 +38,8 @@ union ktime; #define FUTEX_LOCK_PI_PRIVATE (FUTEX_LOCK_PI | FUTEX_PRIVATE_FLAG) #define FUTEX_UNLOCK_PI_PRIVATE (FUTEX_UNLOCK_PI | FUTEX_PRIVATE_FLAG) #define FUTEX_TRYLOCK_PI_PRIVATE (FUTEX_TRYLOCK_PI | FUTEX_PRIVATE_FLAG) -#define FUTEX_WAIT_BITSET_PRIVATE (FUTEX_WAIT_BITS | FUTEX_PRIVATE_FLAG) -#define FUTEX_WAKE_BITSET_PRIVATE (FUTEX_WAKE_BITS | FUTEX_PRIVATE_FLAG) +#define FUTEX_WAIT_BITSET_PRIVATE (FUTEX_WAIT_BITSET | FUTEX_PRIVATE_FLAG) +#define FUTEX_WAKE_BITSET_PRIVATE (FUTEX_WAKE_BITSET | FUTEX_PRIVATE_FLAG) #define FUTEX_WAIT_REQUEUE_PI_PRIVATE (FUTEX_WAIT_REQUEUE_PI | \ FUTEX_PRIVATE_FLAG) #define FUTEX_CMP_REQUEUE_PI_PRIVATE (FUTEX_CMP_REQUEUE_PI | \ -- cgit v1.2.3 From 1f56f4a2b4d12c1c348cab23024024396ec7cddc Mon Sep 17 00:00:00 2001 From: Gabe Black Date: Tue, 6 Oct 2009 09:19:45 -0500 Subject: PCI quirk: TI XIO200a erroneously reports support for fast b2b transfers This quirk will disable fast back to back transfer on the secondary bus segment of the TI Bridge. Signed-off-by: Gabe Black Signed-off-by: Jesse Barnes --- drivers/pci/quirks.c | 19 +++++++++++++++++++ include/linux/pci_ids.h | 1 + 2 files changed, 20 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 6099facecd79..efa6534a6593 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -670,6 +670,25 @@ static void __devinit quirk_vt8235_acpi(struct pci_dev *dev) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8235, quirk_vt8235_acpi); +/* + * TI XIO2000a PCIe-PCI Bridge erroneously reports it supports fast back-to-back: + * Disable fast back-to-back on the secondary bus segment + */ +static void __devinit quirk_xio2000a(struct pci_dev *dev) +{ + struct pci_dev *pdev; + u16 command; + + dev_warn(&dev->dev, "TI XIO2000a quirk detected; " + "secondary bus fast back-to-back transfers disabled\n"); + list_for_each_entry(pdev, &dev->subordinate->devices, bus_list) { + pci_read_config_word(pdev, PCI_COMMAND, &command); + if (command & PCI_COMMAND_FAST_BACK) + pci_write_config_word(pdev, PCI_COMMAND, command & ~PCI_COMMAND_FAST_BACK); + } +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_TI, PCI_DEVICE_ID_TI_XIO2000A, + quirk_xio2000a); #ifdef CONFIG_X86_IO_APIC diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index da1fda8623e0..f490e7a7307a 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -776,6 +776,7 @@ #define PCI_DEVICE_ID_TI_X515 0x8036 #define PCI_DEVICE_ID_TI_XX12 0x8039 #define PCI_DEVICE_ID_TI_XX12_FM 0x803b +#define PCI_DEVICE_ID_TI_XIO2000A 0x8231 #define PCI_DEVICE_ID_TI_1130 0xac12 #define PCI_DEVICE_ID_TI_1031 0xac13 #define PCI_DEVICE_ID_TI_1131 0xac15 -- cgit v1.2.3 From e7247a15ff3bbdab0a8b402dffa1171e5c05a8e0 Mon Sep 17 00:00:00 2001 From: "jolsa@redhat.com" Date: Wed, 7 Oct 2009 19:00:35 +0200 Subject: tracing: correct module boundaries for ftrace_release When the module is about the unload we release its call records. The ftrace_release function was given wrong values representing the module core boundaries, thus not releasing its call records. Plus making ftrace_release function module specific. Signed-off-by: Jiri Olsa LKML-Reference: <1254934835-363-3-git-send-email-jolsa@redhat.com> Cc: stable@kernel.org Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 2 +- kernel/trace/ftrace.c | 12 ++++-------- 2 files changed, 5 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index cd3d2abaf30a..0b4f97d24d7f 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -241,7 +241,7 @@ extern void ftrace_enable_daemon(void); # define ftrace_set_filter(buf, len, reset) do { } while (0) # define ftrace_disable_daemon() do { } while (0) # define ftrace_enable_daemon() do { } while (0) -static inline void ftrace_release(void *start, unsigned long size) { } +static inline void ftrace_release_mod(struct module *mod) {} static inline int register_ftrace_command(struct ftrace_func_command *cmd) { return -EINVAL; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 46592feab5a6..c701476a648b 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2658,19 +2658,17 @@ static int ftrace_convert_nops(struct module *mod, } #ifdef CONFIG_MODULES -void ftrace_release(void *start, void *end) +void ftrace_release_mod(struct module *mod) { struct dyn_ftrace *rec; struct ftrace_page *pg; - unsigned long s = (unsigned long)start; - unsigned long e = (unsigned long)end; - if (ftrace_disabled || !start || start == end) + if (ftrace_disabled) return; mutex_lock(&ftrace_lock); do_for_each_ftrace_rec(pg, rec) { - if ((rec->ip >= s) && (rec->ip < e)) { + if (within_module_core(rec->ip, mod)) { /* * rec->ip is changed in ftrace_free_rec() * It should not between s and e if record was freed. @@ -2702,9 +2700,7 @@ static int ftrace_module_notify(struct notifier_block *self, mod->num_ftrace_callsites); break; case MODULE_STATE_GOING: - ftrace_release(mod->ftrace_callsites, - mod->ftrace_callsites + - mod->num_ftrace_callsites); + ftrace_release_mod(mod); break; } -- cgit v1.2.3 From d308e38fa5467fbb523fc13e4b984375c2198c3d Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Wed, 7 Oct 2009 13:53:11 -0700 Subject: include/linux/netdevice.h: fix nanodoc mismatch nanodoc was missing an ndo_-prefix. Signed-off-by: Wolfram Sang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 94958c109761..812a5f3c2abe 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -557,7 +557,7 @@ struct netdev_queue { * Callback uses when the transmitter has not made any progress * for dev->watchdog ticks. * - * struct net_device_stats* (*get_stats)(struct net_device *dev); + * struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); * Called when a user wants to get the network device usage * statistics. If not defined, the counters in dev->stats will * be used. -- cgit v1.2.3 From a4720c650b68a5fe7faed2edeb0ad12645f7ae63 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 9 Oct 2009 12:43:12 -0400 Subject: USB: serial: don't call release without attach This patch (as1295) fixes a recently-added bug in the USB serial core. If certain kinds of errors occur during probing, the core may call a serial driver's release method without previously calling the attach method. This causes some drivers (io_ti in particular) to perform an invalid memory access. The patch adds a new flag to keep track of whether or not attach has been called. Signed-off-by: Alan Stern Tested-by: Jean-Denis Girard CC: stable Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/usb-serial.c | 6 +++++- include/linux/usb/serial.h | 1 + 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c index aa6b2ae951ae..2d0f75d63ff0 100644 --- a/drivers/usb/serial/usb-serial.c +++ b/drivers/usb/serial/usb-serial.c @@ -156,7 +156,8 @@ static void destroy_serial(struct kref *kref) if (serial->minor != SERIAL_TTY_NO_MINOR) return_serial(serial); - serial->type->release(serial); + if (serial->attached) + serial->type->release(serial); /* Now that nothing is using the ports, they can be freed */ for (i = 0; i < serial->num_port_pointers; ++i) { @@ -1059,12 +1060,15 @@ int usb_serial_probe(struct usb_interface *interface, module_put(type->driver.owner); if (retval < 0) goto probe_error; + serial->attached = 1; if (retval > 0) { /* quietly accept this device, but don't bind to a serial port as it's about to disappear */ serial->num_ports = 0; goto exit; } + } else { + serial->attached = 1; } if (get_free_serial(serial, num_ports, &minor) == NULL) { diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index c17eb64d7213..ce911ebf91e8 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -150,6 +150,7 @@ struct usb_serial { struct usb_interface *interface; unsigned char disconnected:1; unsigned char suspending:1; + unsigned char attached:1; unsigned char minor; unsigned char num_ports; unsigned char num_port_pointers; -- cgit v1.2.3 From d43c36dc6b357fa1806800f18aa30123c747a6d1 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 7 Oct 2009 17:09:06 +0400 Subject: headers: remove sched.h from interrupt.h After m68k's task_thread_info() doesn't refer to current, it's possible to remove sched.h from interrupt.h and not break m68k! Many thanks to Heiko Carstens for allowing this. Signed-off-by: Alexey Dobriyan --- arch/arm/kernel/time.c | 1 + arch/arm/mach-integrator/pci_v3.c | 1 + arch/arm/plat-s3c24xx/adc.c | 1 + arch/blackfin/kernel/time.c | 1 + arch/m32r/kernel/smp.c | 1 + arch/um/drivers/line.c | 1 + arch/um/drivers/port_kern.c | 1 + arch/um/kernel/irq.c | 1 + arch/x86/kernel/cpu/mcheck/mce_intel.c | 1 + arch/x86/kernel/pci-gart_64.c | 1 + arch/x86/kernel/reboot.c | 1 + arch/xtensa/kernel/time.c | 1 + crypto/aead.c | 1 + drivers/char/applicom.c | 1 + drivers/char/epca.c | 1 + drivers/char/generic_serial.c | 1 + drivers/char/istallion.c | 1 + drivers/char/nozomi.c | 1 + drivers/char/pty.c | 1 + drivers/char/rio/riocmd.c | 1 + drivers/char/rio/rioctrl.c | 1 + drivers/char/rio/riotty.c | 1 + drivers/char/ser_a2232.c | 1 + drivers/char/stallion.c | 1 + drivers/char/tlclk.c | 1 + drivers/hwmon/sht15.c | 1 + drivers/ieee1394/raw1394.c | 1 + drivers/ieee1394/video1394.c | 1 + drivers/infiniband/core/iwcm.c | 1 + drivers/infiniband/core/ucma.c | 1 + drivers/infiniband/hw/cxgb3/iwch_provider.c | 1 + drivers/infiniband/hw/cxgb3/iwch_qp.c | 1 + drivers/infiniband/hw/ipath/ipath_driver.c | 1 + drivers/infiniband/hw/ipath/ipath_iba7220.c | 1 + drivers/infiniband/hw/ipath/ipath_intr.c | 1 + drivers/infiniband/hw/ipath/ipath_qp.c | 1 + drivers/infiniband/hw/ipath/ipath_ruc.c | 1 + drivers/infiniband/hw/ipath/ipath_ud.c | 1 + drivers/infiniband/hw/ipath/ipath_user_pages.c | 1 + drivers/infiniband/hw/ipath/ipath_user_sdma.c | 1 + drivers/infiniband/hw/ipath/ipath_verbs_mcast.c | 1 + drivers/input/keyboard/hilkbd.c | 1 + drivers/input/keyboard/sunkbd.c | 1 + drivers/input/serio/libps2.c | 1 + drivers/input/serio/serio_raw.c | 1 + drivers/input/serio/serport.c | 1 + drivers/isdn/capi/kcapi.c | 1 + drivers/isdn/hisax/arcofi.c | 1 + drivers/isdn/hisax/hfc_2bds0.c | 1 + drivers/isdn/hisax/hfc_pci.c | 1 + drivers/isdn/hysdn/hysdn_procconf.c | 1 + drivers/isdn/hysdn/hysdn_proclog.c | 1 + drivers/isdn/pcbit/drv.c | 1 + drivers/isdn/pcbit/layer2.c | 1 + drivers/isdn/sc/init.c | 1 + drivers/lguest/interrupts_and_traps.c | 1 + drivers/media/dvb/dvb-core/dvb_net.c | 1 + drivers/media/video/meye.c | 1 + drivers/media/video/videobuf-core.c | 1 + drivers/media/video/videobuf-dma-sg.c | 1 + drivers/message/fusion/mptlan.c | 1 + drivers/mfd/ucb1x00-core.c | 1 + drivers/misc/hpilo.c | 1 + drivers/misc/ibmasm/command.c | 1 + drivers/misc/ibmasm/event.c | 1 + drivers/misc/ibmasm/r_heartbeat.c | 1 + drivers/misc/phantom.c | 1 + drivers/mtd/devices/m25p80.c | 1 + drivers/mtd/devices/sst25l.c | 1 + drivers/net/bonding/bond_sysfs.c | 1 + drivers/net/depca.c | 1 + drivers/net/e100.c | 1 + drivers/net/eql.c | 1 + drivers/net/ethoc.c | 1 + drivers/net/ewrk3.c | 1 + drivers/net/forcedeth.c | 1 + drivers/net/hamachi.c | 1 + drivers/net/hamradio/baycom_epp.c | 1 + drivers/net/hamradio/baycom_ser_fdx.c | 1 + drivers/net/hamradio/baycom_ser_hdx.c | 1 + drivers/net/hamradio/hdlcdrv.c | 1 + drivers/net/hp100.c | 1 + drivers/net/igb/igb_ethtool.c | 1 + drivers/net/irda/toim3232-sir.c | 1 + drivers/net/ns83820.c | 1 + drivers/net/pcnet32.c | 1 + drivers/net/sb1000.c | 1 + drivers/net/sis900.c | 1 + drivers/net/skfp/skfddi.c | 1 + drivers/net/skge.c | 1 + drivers/net/slip.c | 1 + drivers/net/sungem.c | 1 + drivers/net/tokenring/ibmtr.c | 1 + drivers/net/typhoon.c | 1 + drivers/net/wan/cosa.c | 1 + drivers/net/wan/cycx_x25.c | 1 + drivers/net/wan/dscc4.c | 1 + drivers/net/wan/farsync.c | 1 + drivers/net/wireless/b43/pio.c | 1 + drivers/net/wireless/b43legacy/main.c | 1 + drivers/net/wireless/b43legacy/phy.c | 1 + drivers/net/wireless/hostap/hostap_info.c | 1 + drivers/net/wireless/hostap/hostap_ioctl.c | 1 + drivers/net/wireless/ipw2x00/ipw2200.c | 1 + drivers/net/wireless/iwlwifi/iwl-3945.c | 1 + drivers/net/wireless/iwlwifi/iwl-4965.c | 1 + drivers/net/wireless/iwlwifi/iwl-5000.c | 1 + drivers/net/wireless/iwlwifi/iwl-agn.c | 1 + drivers/net/wireless/iwlwifi/iwl-core.c | 1 + drivers/net/wireless/iwlwifi/iwl-hcmd.c | 1 + drivers/net/wireless/iwlwifi/iwl-tx.c | 1 + drivers/net/wireless/iwlwifi/iwl3945-base.c | 1 + drivers/net/wireless/iwmc3200wifi/cfg80211.c | 1 + drivers/net/wireless/iwmc3200wifi/commands.c | 1 + drivers/net/wireless/iwmc3200wifi/main.c | 1 + drivers/net/wireless/iwmc3200wifi/rx.c | 1 + drivers/net/wireless/libertas/cmd.c | 1 + drivers/net/wireless/libertas/tx.c | 1 + drivers/net/wireless/prism54/isl_ioctl.c | 1 + drivers/net/wireless/prism54/islpci_dev.c | 1 + drivers/net/wireless/prism54/islpci_mgt.c | 1 + drivers/net/wireless/rt2x00/rt2x00debug.c | 1 + drivers/pci/pcie/aer/aerdrv.c | 1 + drivers/rtc/interface.c | 1 + drivers/rtc/rtc-dev.c | 1 + drivers/uio/uio.c | 1 + drivers/uwb/whc-rc.c | 1 + fs/file.c | 1 + include/linux/interrupt.h | 2 +- include/linux/mmc/host.h | 1 + kernel/irq/handle.c | 1 + kernel/mutex-debug.c | 1 + kernel/time/timekeeping.c | 1 + lib/debugobjects.c | 1 + lib/fault-inject.c | 1 + mm/vmalloc.c | 1 + net/irda/ircomm/ircomm_tty_attach.c | 1 + net/irda/irlan/irlan_common.c | 1 + net/irda/irlan/irlan_eth.c | 1 + net/irda/irnet/irnet_irda.c | 1 + net/irda/irnet/irnet_ppp.c | 1 + net/mac80211/rc80211_pid_debugfs.c | 1 + net/netfilter/nf_conntrack_core.c | 1 + net/sunrpc/xprtrdma/svc_rdma_transport.c | 1 + net/wireless/core.c | 1 + 145 files changed, 145 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c index 4cdc4a0bd02d..d38cdf2c8276 100644 --- a/arch/arm/kernel/time.c +++ b/arch/arm/kernel/time.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/arm/mach-integrator/pci_v3.c b/arch/arm/mach-integrator/pci_v3.c index 901cc205015e..148d25fc636f 100644 --- a/arch/arm/mach-integrator/pci_v3.c +++ b/arch/arm/mach-integrator/pci_v3.c @@ -31,6 +31,7 @@ #include #include +#include #include #include #include diff --git a/arch/arm/plat-s3c24xx/adc.c b/arch/arm/plat-s3c24xx/adc.c index 11117a7ba911..4d36b784fb8b 100644 --- a/arch/arm/plat-s3c24xx/adc.c +++ b/arch/arm/plat-s3c24xx/adc.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/blackfin/kernel/time.c b/arch/blackfin/kernel/time.c index e5069fe6861e..bd3b53da295e 100644 --- a/arch/blackfin/kernel/time.c +++ b/arch/blackfin/kernel/time.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include diff --git a/arch/m32r/kernel/smp.c b/arch/m32r/kernel/smp.c index 1b7598e6f6e8..8a88f1f0a3e2 100644 --- a/arch/m32r/kernel/smp.c +++ b/arch/m32r/kernel/smp.c @@ -17,6 +17,7 @@ #include #include +#include #include #include #include diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index 14a102e877d6..cf8a97f34518 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -5,6 +5,7 @@ #include "linux/irqreturn.h" #include "linux/kd.h" +#include "linux/sched.h" #include "chan_kern.h" #include "irq_kern.h" #include "irq_user.h" diff --git a/arch/um/drivers/port_kern.c b/arch/um/drivers/port_kern.c index 19930081d3d8..4ebc8a34738f 100644 --- a/arch/um/drivers/port_kern.c +++ b/arch/um/drivers/port_kern.c @@ -7,6 +7,7 @@ #include "linux/interrupt.h" #include "linux/list.h" #include "linux/mutex.h" +#include "linux/workqueue.h" #include "asm/atomic.h" #include "init.h" #include "irq_kern.h" diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c index 454cdb43e351..039270b9b73b 100644 --- a/arch/um/kernel/irq.c +++ b/arch/um/kernel/irq.c @@ -10,6 +10,7 @@ #include "linux/interrupt.h" #include "linux/kernel_stat.h" #include "linux/module.h" +#include "linux/sched.h" #include "linux/seq_file.h" #include "as-layout.h" #include "kern_util.h" diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 889f665fe93d..7c785634af2b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index 98a827ee9ed7..a7f1b64f86e0 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 27349f92a6d7..a1a3cdda06e1 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -4,6 +4,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c index 19085ff0484a..19f7df30937f 100644 --- a/arch/xtensa/kernel/time.c +++ b/arch/xtensa/kernel/time.c @@ -13,6 +13,7 @@ */ #include +#include #include #include #include diff --git a/crypto/aead.c b/crypto/aead.c index d9aa733db164..0a55da70845e 100644 --- a/crypto/aead.c +++ b/crypto/aead.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include diff --git a/drivers/char/applicom.c b/drivers/char/applicom.c index 73a0765344b6..fe2cb2f5db17 100644 --- a/drivers/char/applicom.c +++ b/drivers/char/applicom.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/char/epca.c b/drivers/char/epca.c index 9d589e3144de..dde5134713e2 100644 --- a/drivers/char/epca.c +++ b/drivers/char/epca.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/char/generic_serial.c b/drivers/char/generic_serial.c index 9e4e569dc00d..d400cbd280f2 100644 --- a/drivers/char/generic_serial.c +++ b/drivers/char/generic_serial.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/char/istallion.c b/drivers/char/istallion.c index ab2f3349c5c4..402838f4083e 100644 --- a/drivers/char/istallion.c +++ b/drivers/char/istallion.c @@ -19,6 +19,7 @@ /*****************************************************************************/ #include +#include #include #include #include diff --git a/drivers/char/nozomi.c b/drivers/char/nozomi.c index ec58d8c387ff..d3400b20444f 100644 --- a/drivers/char/nozomi.c +++ b/drivers/char/nozomi.c @@ -48,6 +48,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/char/pty.c b/drivers/char/pty.c index e066c4fdf81b..62f282e67638 100644 --- a/drivers/char/pty.c +++ b/drivers/char/pty.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/char/rio/riocmd.c b/drivers/char/rio/riocmd.c index 01f2654d5a2e..f121357e5af0 100644 --- a/drivers/char/rio/riocmd.c +++ b/drivers/char/rio/riocmd.c @@ -32,6 +32,7 @@ */ #include +#include #include #include #include diff --git a/drivers/char/rio/rioctrl.c b/drivers/char/rio/rioctrl.c index 74339559f0b9..780506326a73 100644 --- a/drivers/char/rio/rioctrl.c +++ b/drivers/char/rio/rioctrl.c @@ -31,6 +31,7 @@ */ #include +#include #include #include #include diff --git a/drivers/char/rio/riotty.c b/drivers/char/rio/riotty.c index 2fb49e89b324..47fab7c33073 100644 --- a/drivers/char/rio/riotty.c +++ b/drivers/char/rio/riotty.c @@ -33,6 +33,7 @@ #define __EXPLICIT_DEF_H__ #include +#include #include #include #include diff --git a/drivers/char/ser_a2232.c b/drivers/char/ser_a2232.c index 33a2b531802e..9610861d1f5f 100644 --- a/drivers/char/ser_a2232.c +++ b/drivers/char/ser_a2232.c @@ -89,6 +89,7 @@ #include #include #include +#include #include #include diff --git a/drivers/char/stallion.c b/drivers/char/stallion.c index 53e504f41b20..db6dcfa35ba0 100644 --- a/drivers/char/stallion.c +++ b/drivers/char/stallion.c @@ -27,6 +27,7 @@ /*****************************************************************************/ #include +#include #include #include #include diff --git a/drivers/char/tlclk.c b/drivers/char/tlclk.c index 8f2284be68e1..80ea6bcfffdc 100644 --- a/drivers/char/tlclk.c +++ b/drivers/char/tlclk.c @@ -32,6 +32,7 @@ #include /* printk() */ #include /* everything... */ #include /* error codes */ +#include #include #include #include diff --git a/drivers/hwmon/sht15.c b/drivers/hwmon/sht15.c index 303c02694c3c..2da6fb2c325e 100644 --- a/drivers/hwmon/sht15.c +++ b/drivers/hwmon/sht15.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/ieee1394/raw1394.c b/drivers/ieee1394/raw1394.c index 0bc3d78ce7b1..8aa56ac07e29 100644 --- a/drivers/ieee1394/raw1394.c +++ b/drivers/ieee1394/raw1394.c @@ -29,6 +29,7 @@ #include #include +#include #include #include #include diff --git a/drivers/ieee1394/video1394.c b/drivers/ieee1394/video1394.c index d287ba79821d..949064a05675 100644 --- a/drivers/ieee1394/video1394.c +++ b/drivers/ieee1394/video1394.c @@ -30,6 +30,7 @@ */ #include #include +#include #include #include #include diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c index 625fec5a741c..0f89909abce9 100644 --- a/drivers/infiniband/core/iwcm.c +++ b/drivers/infiniband/core/iwcm.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 4346a24568fb..bb96d3c4b0f4 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c index 03cfaecc3bb7..ed7175549ebd 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_provider.c +++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/infiniband/hw/cxgb3/iwch_qp.c b/drivers/infiniband/hw/cxgb3/iwch_qp.c index 6e8653471941..1cecf98829ac 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_qp.c +++ b/drivers/infiniband/hw/cxgb3/iwch_qp.c @@ -29,6 +29,7 @@ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ +#include #include "iwch_provider.h" #include "iwch.h" #include "iwch_cm.h" diff --git a/drivers/infiniband/hw/ipath/ipath_driver.c b/drivers/infiniband/hw/ipath/ipath_driver.c index 04e88b600558..013d1380e77c 100644 --- a/drivers/infiniband/hw/ipath/ipath_driver.c +++ b/drivers/infiniband/hw/ipath/ipath_driver.c @@ -31,6 +31,7 @@ * SOFTWARE. */ +#include #include #include #include diff --git a/drivers/infiniband/hw/ipath/ipath_iba7220.c b/drivers/infiniband/hw/ipath/ipath_iba7220.c index b2a9d4c155d1..a805402dd4ae 100644 --- a/drivers/infiniband/hw/ipath/ipath_iba7220.c +++ b/drivers/infiniband/hw/ipath/ipath_iba7220.c @@ -37,6 +37,7 @@ #include #include +#include #include #include #include diff --git a/drivers/infiniband/hw/ipath/ipath_intr.c b/drivers/infiniband/hw/ipath/ipath_intr.c index 6c21b4b5ec71..c0a03ac03ee7 100644 --- a/drivers/infiniband/hw/ipath/ipath_intr.c +++ b/drivers/infiniband/hw/ipath/ipath_intr.c @@ -33,6 +33,7 @@ #include #include +#include #include "ipath_kernel.h" #include "ipath_verbs.h" diff --git a/drivers/infiniband/hw/ipath/ipath_qp.c b/drivers/infiniband/hw/ipath/ipath_qp.c index 3a5a89b609c4..cb2d3ef2ae12 100644 --- a/drivers/infiniband/hw/ipath/ipath_qp.c +++ b/drivers/infiniband/hw/ipath/ipath_qp.c @@ -32,6 +32,7 @@ */ #include +#include #include #include "ipath_verbs.h" diff --git a/drivers/infiniband/hw/ipath/ipath_ruc.c b/drivers/infiniband/hw/ipath/ipath_ruc.c index 2296832f94da..1f95bbaf7602 100644 --- a/drivers/infiniband/hw/ipath/ipath_ruc.c +++ b/drivers/infiniband/hw/ipath/ipath_ruc.c @@ -31,6 +31,7 @@ * SOFTWARE. */ +#include #include #include "ipath_verbs.h" diff --git a/drivers/infiniband/hw/ipath/ipath_ud.c b/drivers/infiniband/hw/ipath/ipath_ud.c index 6076cb61bf6a..7420715256a9 100644 --- a/drivers/infiniband/hw/ipath/ipath_ud.c +++ b/drivers/infiniband/hw/ipath/ipath_ud.c @@ -31,6 +31,7 @@ * SOFTWARE. */ +#include #include #include "ipath_verbs.h" diff --git a/drivers/infiniband/hw/ipath/ipath_user_pages.c b/drivers/infiniband/hw/ipath/ipath_user_pages.c index 855911e7396d..82878e348627 100644 --- a/drivers/infiniband/hw/ipath/ipath_user_pages.c +++ b/drivers/infiniband/hw/ipath/ipath_user_pages.c @@ -33,6 +33,7 @@ #include #include +#include #include "ipath_kernel.h" diff --git a/drivers/infiniband/hw/ipath/ipath_user_sdma.c b/drivers/infiniband/hw/ipath/ipath_user_sdma.c index 7bff4b9baa0a..be78f6643c06 100644 --- a/drivers/infiniband/hw/ipath/ipath_user_sdma.c +++ b/drivers/infiniband/hw/ipath/ipath_user_sdma.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/infiniband/hw/ipath/ipath_verbs_mcast.c b/drivers/infiniband/hw/ipath/ipath_verbs_mcast.c index d73e32232879..6923e1d986da 100644 --- a/drivers/infiniband/hw/ipath/ipath_verbs_mcast.c +++ b/drivers/infiniband/hw/ipath/ipath_verbs_mcast.c @@ -32,6 +32,7 @@ */ #include +#include #include "ipath_verbs.h" diff --git a/drivers/input/keyboard/hilkbd.c b/drivers/input/keyboard/hilkbd.c index e9d639ec283d..5f72440b50c8 100644 --- a/drivers/input/keyboard/hilkbd.c +++ b/drivers/input/keyboard/hilkbd.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #ifdef CONFIG_HP300 diff --git a/drivers/input/keyboard/sunkbd.c b/drivers/input/keyboard/sunkbd.c index 472b56639cdb..a99a04b03ee4 100644 --- a/drivers/input/keyboard/sunkbd.c +++ b/drivers/input/keyboard/sunkbd.c @@ -27,6 +27,7 @@ */ #include +#include #include #include #include diff --git a/drivers/input/serio/libps2.c b/drivers/input/serio/libps2.c index 769ba65a585a..f3876acc3e83 100644 --- a/drivers/input/serio/libps2.c +++ b/drivers/input/serio/libps2.c @@ -13,6 +13,7 @@ #include #include +#include #include #include #include diff --git a/drivers/input/serio/serio_raw.c b/drivers/input/serio/serio_raw.c index b03009bb7468..27fdaaffbb40 100644 --- a/drivers/input/serio/serio_raw.c +++ b/drivers/input/serio/serio_raw.c @@ -9,6 +9,7 @@ * the Free Software Foundation. */ +#include #include #include #include diff --git a/drivers/input/serio/serport.c b/drivers/input/serio/serport.c index b9694b6445d0..6d345112bcb7 100644 --- a/drivers/input/serio/serport.c +++ b/drivers/input/serio/serport.c @@ -15,6 +15,7 @@ #include #include +#include #include #include #include diff --git a/drivers/isdn/capi/kcapi.c b/drivers/isdn/capi/kcapi.c index 57d26360f64e..dc506ab99cac 100644 --- a/drivers/isdn/capi/kcapi.c +++ b/drivers/isdn/capi/kcapi.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/isdn/hisax/arcofi.c b/drivers/isdn/hisax/arcofi.c index d30ce5b978c2..85a8fd8dd0b7 100644 --- a/drivers/isdn/hisax/arcofi.c +++ b/drivers/isdn/hisax/arcofi.c @@ -10,6 +10,7 @@ * */ +#include #include "hisax.h" #include "isdnl1.h" #include "isac.h" diff --git a/drivers/isdn/hisax/hfc_2bds0.c b/drivers/isdn/hisax/hfc_2bds0.c index 5c46a7130e06..8d22f50760eb 100644 --- a/drivers/isdn/hisax/hfc_2bds0.c +++ b/drivers/isdn/hisax/hfc_2bds0.c @@ -11,6 +11,7 @@ */ #include +#include #include "hisax.h" #include "hfc_2bds0.h" #include "isdnl1.h" diff --git a/drivers/isdn/hisax/hfc_pci.c b/drivers/isdn/hisax/hfc_pci.c index d110a77940a4..10914731b304 100644 --- a/drivers/isdn/hisax/hfc_pci.c +++ b/drivers/isdn/hisax/hfc_pci.c @@ -20,6 +20,7 @@ #include "hfc_pci.h" #include "isdnl1.h" #include +#include #include static const char *hfcpci_revision = "$Revision: 1.48.2.4 $"; diff --git a/drivers/isdn/hysdn/hysdn_procconf.c b/drivers/isdn/hysdn/hysdn_procconf.c index 8f9f4912de32..90b35e1a4b7e 100644 --- a/drivers/isdn/hysdn/hysdn_procconf.c +++ b/drivers/isdn/hysdn/hysdn_procconf.c @@ -11,6 +11,7 @@ * */ +#include #include #include #include diff --git a/drivers/isdn/hysdn/hysdn_proclog.c b/drivers/isdn/hysdn/hysdn_proclog.c index 8991d2c8ee4a..8bcae28c4409 100644 --- a/drivers/isdn/hysdn/hysdn_proclog.c +++ b/drivers/isdn/hysdn/hysdn_proclog.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include "hysdn_defs.h" diff --git a/drivers/isdn/pcbit/drv.c b/drivers/isdn/pcbit/drv.c index 8c66bcb953a1..123c1d6c43b4 100644 --- a/drivers/isdn/pcbit/drv.c +++ b/drivers/isdn/pcbit/drv.c @@ -23,6 +23,7 @@ #include #include +#include #include #include #include diff --git a/drivers/isdn/pcbit/layer2.c b/drivers/isdn/pcbit/layer2.c index e075e8d2fce0..30f0f45e3139 100644 --- a/drivers/isdn/pcbit/layer2.c +++ b/drivers/isdn/pcbit/layer2.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/isdn/sc/init.c b/drivers/isdn/sc/init.c index dd0acd06750b..5a0774880d56 100644 --- a/drivers/isdn/sc/init.c +++ b/drivers/isdn/sc/init.c @@ -8,6 +8,7 @@ #include #include #include +#include #include "includes.h" #include "hardware.h" #include "card.h" diff --git a/drivers/lguest/interrupts_and_traps.c b/drivers/lguest/interrupts_and_traps.c index 18648180db02..daaf86631647 100644 --- a/drivers/lguest/interrupts_and_traps.c +++ b/drivers/lguest/interrupts_and_traps.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "lg.h" /* Allow Guests to use a non-128 (ie. non-Linux) syscall trap. */ diff --git a/drivers/media/dvb/dvb-core/dvb_net.c b/drivers/media/dvb/dvb-core/dvb_net.c index 8c9ae0a3a272..0241a7c5c34a 100644 --- a/drivers/media/dvb/dvb-core/dvb_net.c +++ b/drivers/media/dvb/dvb-core/dvb_net.c @@ -63,6 +63,7 @@ #include #include #include +#include #include "dvb_demux.h" #include "dvb_net.h" diff --git a/drivers/media/video/meye.c b/drivers/media/video/meye.c index 4b1bc05a462c..01e1eefcf1eb 100644 --- a/drivers/media/video/meye.c +++ b/drivers/media/video/meye.c @@ -28,6 +28,7 @@ */ #include #include +#include #include #include #include diff --git a/drivers/media/video/videobuf-core.c b/drivers/media/video/videobuf-core.c index f1ccf98c0a6f..8e93c6f25c83 100644 --- a/drivers/media/video/videobuf-core.c +++ b/drivers/media/video/videobuf-core.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include diff --git a/drivers/media/video/videobuf-dma-sg.c b/drivers/media/video/videobuf-dma-sg.c index 53cdd67cebe1..032ebae0134a 100644 --- a/drivers/media/video/videobuf-dma-sg.c +++ b/drivers/media/video/videobuf-dma-sg.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include diff --git a/drivers/message/fusion/mptlan.c b/drivers/message/fusion/mptlan.c index bc2ec2182c00..34f3f36f819b 100644 --- a/drivers/message/fusion/mptlan.c +++ b/drivers/message/fusion/mptlan.c @@ -56,6 +56,7 @@ #include #include #include +#include #define my_VERSION MPT_LINUX_VERSION_COMMON #define MYNAM "mptlan" diff --git a/drivers/mfd/ucb1x00-core.c b/drivers/mfd/ucb1x00-core.c index fea9085fe52c..60c3988f3cf3 100644 --- a/drivers/mfd/ucb1x00-core.c +++ b/drivers/mfd/ucb1x00-core.c @@ -18,6 +18,7 @@ */ #include #include +#include #include #include #include diff --git a/drivers/misc/hpilo.c b/drivers/misc/hpilo.c index 1ad27c6abcca..a92a3a742b43 100644 --- a/drivers/misc/hpilo.c +++ b/drivers/misc/hpilo.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/misc/ibmasm/command.c b/drivers/misc/ibmasm/command.c index 276d3fb68094..e2031739aa29 100644 --- a/drivers/misc/ibmasm/command.c +++ b/drivers/misc/ibmasm/command.c @@ -22,6 +22,7 @@ * */ +#include #include "ibmasm.h" #include "lowlevel.h" diff --git a/drivers/misc/ibmasm/event.c b/drivers/misc/ibmasm/event.c index 68a0a5b94795..572d41ffc186 100644 --- a/drivers/misc/ibmasm/event.c +++ b/drivers/misc/ibmasm/event.c @@ -22,6 +22,7 @@ * */ +#include #include "ibmasm.h" #include "lowlevel.h" diff --git a/drivers/misc/ibmasm/r_heartbeat.c b/drivers/misc/ibmasm/r_heartbeat.c index bec9e2c44bef..2de487ac788c 100644 --- a/drivers/misc/ibmasm/r_heartbeat.c +++ b/drivers/misc/ibmasm/r_heartbeat.c @@ -20,6 +20,7 @@ * */ +#include #include "ibmasm.h" #include "dot_command.h" diff --git a/drivers/misc/phantom.c b/drivers/misc/phantom.c index 90a95ce8dc34..04c27266f567 100644 --- a/drivers/misc/phantom.c +++ b/drivers/misc/phantom.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c index 379c316f329e..4c19269de91a 100644 --- a/drivers/mtd/devices/m25p80.c +++ b/drivers/mtd/devices/m25p80.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include diff --git a/drivers/mtd/devices/sst25l.c b/drivers/mtd/devices/sst25l.c index c2baf3353f84..0a11721f146e 100644 --- a/drivers/mtd/devices/sst25l.c +++ b/drivers/mtd/devices/sst25l.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index ff449de6f3c0..8762a27a2a18 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/depca.c b/drivers/net/depca.c index 9686c1fa28f1..7a3bdac84abe 100644 --- a/drivers/net/depca.c +++ b/drivers/net/depca.c @@ -237,6 +237,7 @@ #include #include +#include #include #include #include diff --git a/drivers/net/e100.c b/drivers/net/e100.c index 679965c2bb86..5d2f48f02251 100644 --- a/drivers/net/e100.c +++ b/drivers/net/e100.c @@ -151,6 +151,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/eql.c b/drivers/net/eql.c index d4d9a3eda695..f5b96cadeb25 100644 --- a/drivers/net/eql.c +++ b/drivers/net/eql.c @@ -111,6 +111,7 @@ * Sorry, I had to rewrite most of this for 2.5.x -DaveM */ +#include #include #include #include diff --git a/drivers/net/ethoc.c b/drivers/net/ethoc.c index 34d0c69e67f7..96f5b2a2d2c5 100644 --- a/drivers/net/ethoc.c +++ b/drivers/net/ethoc.c @@ -17,6 +17,7 @@ #include #include #include +#include #include static int buffer_size = 0x8000; /* 32 KBytes */ diff --git a/drivers/net/ewrk3.c b/drivers/net/ewrk3.c index b2a5ec8f3721..dd4ba01fd92d 100644 --- a/drivers/net/ewrk3.c +++ b/drivers/net/ewrk3.c @@ -145,6 +145,7 @@ #include #include +#include #include #include #include diff --git a/drivers/net/forcedeth.c b/drivers/net/forcedeth.c index 0a1c2bb27d4d..e1da4666f204 100644 --- a/drivers/net/forcedeth.c +++ b/drivers/net/forcedeth.c @@ -49,6 +49,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/hamachi.c b/drivers/net/hamachi.c index 1d5064a09aca..f7519a594945 100644 --- a/drivers/net/hamachi.c +++ b/drivers/net/hamachi.c @@ -145,6 +145,7 @@ static int tx_params[MAX_UNITS] = {-1, -1, -1, -1, -1, -1, -1, -1}; /* Time in jiffies before concluding the transmitter is hung. */ #define TX_TIMEOUT (5*HZ) +#include #include #include #include diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c index 7bcaf7c66243..e344c84c0ef9 100644 --- a/drivers/net/hamradio/baycom_epp.c +++ b/drivers/net/hamradio/baycom_epp.c @@ -44,6 +44,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/hamradio/baycom_ser_fdx.c b/drivers/net/hamradio/baycom_ser_fdx.c index aa4488e871b2..ed60fd664273 100644 --- a/drivers/net/hamradio/baycom_ser_fdx.c +++ b/drivers/net/hamradio/baycom_ser_fdx.c @@ -71,6 +71,7 @@ /*****************************************************************************/ +#include #include #include #include diff --git a/drivers/net/hamradio/baycom_ser_hdx.c b/drivers/net/hamradio/baycom_ser_hdx.c index 88c593596020..1686f6dcbbce 100644 --- a/drivers/net/hamradio/baycom_ser_hdx.c +++ b/drivers/net/hamradio/baycom_ser_hdx.c @@ -61,6 +61,7 @@ /*****************************************************************************/ +#include #include #include #include diff --git a/drivers/net/hamradio/hdlcdrv.c b/drivers/net/hamradio/hdlcdrv.c index 0013c409782c..91c5790c9581 100644 --- a/drivers/net/hamradio/hdlcdrv.c +++ b/drivers/net/hamradio/hdlcdrv.c @@ -42,6 +42,7 @@ /*****************************************************************************/ +#include #include #include #include diff --git a/drivers/net/hp100.c b/drivers/net/hp100.c index a9a1a99f02dd..dd8665138062 100644 --- a/drivers/net/hp100.c +++ b/drivers/net/hp100.c @@ -98,6 +98,7 @@ #include #include +#include #include #include #include diff --git a/drivers/net/igb/igb_ethtool.c b/drivers/net/igb/igb_ethtool.c index d004c359244c..deaea8fa1032 100644 --- a/drivers/net/igb/igb_ethtool.c +++ b/drivers/net/igb/igb_ethtool.c @@ -34,6 +34,7 @@ #include #include #include +#include #include "igb.h" diff --git a/drivers/net/irda/toim3232-sir.c b/drivers/net/irda/toim3232-sir.c index fcf287b749db..99e1ec02a011 100644 --- a/drivers/net/irda/toim3232-sir.c +++ b/drivers/net/irda/toim3232-sir.c @@ -120,6 +120,7 @@ #include #include #include +#include #include diff --git a/drivers/net/ns83820.c b/drivers/net/ns83820.c index c594e1946476..57fd483dbb1f 100644 --- a/drivers/net/ns83820.c +++ b/drivers/net/ns83820.c @@ -111,6 +111,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/pcnet32.c b/drivers/net/pcnet32.c index 6d28b18e7e28..c1b3f09f452c 100644 --- a/drivers/net/pcnet32.c +++ b/drivers/net/pcnet32.c @@ -31,6 +31,7 @@ static const char *const version = #include #include +#include #include #include #include diff --git a/drivers/net/sb1000.c b/drivers/net/sb1000.c index ee366c5a8fa3..c9c70ab0cce0 100644 --- a/drivers/net/sb1000.c +++ b/drivers/net/sb1000.c @@ -36,6 +36,7 @@ static char version[] = "sb1000.c:v1.1.2 6/01/98 (fventuri@mediaone.net)\n"; #include #include +#include #include #include #include diff --git a/drivers/net/sis900.c b/drivers/net/sis900.c index 97949d0a699b..c072f7f36acf 100644 --- a/drivers/net/sis900.c +++ b/drivers/net/sis900.c @@ -52,6 +52,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/skfp/skfddi.c b/drivers/net/skfp/skfddi.c index 38a508b4aad9..b27156eaf267 100644 --- a/drivers/net/skfp/skfddi.c +++ b/drivers/net/skfp/skfddi.c @@ -73,6 +73,7 @@ static const char * const boot_msg = /* Include files */ +#include #include #include #include diff --git a/drivers/net/skge.c b/drivers/net/skge.c index 01f6811f1324..8f5414348e86 100644 --- a/drivers/net/skge.c +++ b/drivers/net/skge.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/slip.c b/drivers/net/slip.c index e17c535a577e..fe3cebb984de 100644 --- a/drivers/net/slip.c +++ b/drivers/net/slip.c @@ -67,6 +67,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/sungem.c b/drivers/net/sungem.c index 305ec3d783db..7019a0d1a82b 100644 --- a/drivers/net/sungem.c +++ b/drivers/net/sungem.c @@ -38,6 +38,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/tokenring/ibmtr.c b/drivers/net/tokenring/ibmtr.c index 525bbc5b9c9d..36cb2423bcf1 100644 --- a/drivers/net/tokenring/ibmtr.c +++ b/drivers/net/tokenring/ibmtr.c @@ -108,6 +108,7 @@ in the event that chatty debug messages are desired - jjs 12/30/98 */ #define IBMTR_DEBUG_MESSAGES 0 #include +#include #ifdef PCMCIA /* required for ibmtr_cs.c to build */ #undef MODULE /* yes, really */ diff --git a/drivers/net/typhoon.c b/drivers/net/typhoon.c index d6d345229fe9..5921f5bdd764 100644 --- a/drivers/net/typhoon.c +++ b/drivers/net/typhoon.c @@ -108,6 +108,7 @@ static const int multicast_filter_limit = 32; #include #include +#include #include #include #include diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c index 66360a2a14c2..e2c33c06190b 100644 --- a/drivers/net/wan/cosa.c +++ b/drivers/net/wan/cosa.c @@ -76,6 +76,7 @@ #include #include +#include #include #include #include diff --git a/drivers/net/wan/cycx_x25.c b/drivers/net/wan/cycx_x25.c index 2573c18b6aa5..cd8cb95c5bd7 100644 --- a/drivers/net/wan/cycx_x25.c +++ b/drivers/net/wan/cycx_x25.c @@ -84,6 +84,7 @@ #include /* printk(), and other useful stuff */ #include #include /* inline memset(), etc. */ +#include #include /* kmalloc(), kfree() */ #include /* offsetof(), etc. */ #include /* WAN router definitions */ diff --git a/drivers/net/wan/dscc4.c b/drivers/net/wan/dscc4.c index 81c8aec9df92..07d00b4cf48a 100644 --- a/drivers/net/wan/dscc4.c +++ b/drivers/net/wan/dscc4.c @@ -81,6 +81,7 @@ */ #include +#include #include #include #include diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c index 3e90eb816181..beda387f2fc7 100644 --- a/drivers/net/wan/farsync.c +++ b/drivers/net/wan/farsync.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/wireless/b43/pio.c b/drivers/net/wireless/b43/pio.c index 9c1397996e0a..5e87650b07fb 100644 --- a/drivers/net/wireless/b43/pio.c +++ b/drivers/net/wireless/b43/pio.c @@ -30,6 +30,7 @@ #include "xmit.h" #include +#include static u16 generate_cookie(struct b43_pio_txqueue *q, diff --git a/drivers/net/wireless/b43legacy/main.c b/drivers/net/wireless/b43legacy/main.c index 1d9223b3d4c4..4b60148a5e61 100644 --- a/drivers/net/wireless/b43legacy/main.c +++ b/drivers/net/wireless/b43legacy/main.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/wireless/b43legacy/phy.c b/drivers/net/wireless/b43legacy/phy.c index 11319ec2d64a..aaf227203a98 100644 --- a/drivers/net/wireless/b43legacy/phy.c +++ b/drivers/net/wireless/b43legacy/phy.c @@ -31,6 +31,7 @@ #include #include +#include #include #include "b43legacy.h" diff --git a/drivers/net/wireless/hostap/hostap_info.c b/drivers/net/wireless/hostap/hostap_info.c index 6fa14a4e4b53..4dfb40a84c96 100644 --- a/drivers/net/wireless/hostap/hostap_info.c +++ b/drivers/net/wireless/hostap/hostap_info.c @@ -1,6 +1,7 @@ /* Host AP driver Info Frame processing (part of hostap.o module) */ #include +#include #include "hostap_wlan.h" #include "hostap.h" #include "hostap_ap.h" diff --git a/drivers/net/wireless/hostap/hostap_ioctl.c b/drivers/net/wireless/hostap/hostap_ioctl.c index 3f2bda881a4f..9419cebca8a5 100644 --- a/drivers/net/wireless/hostap/hostap_ioctl.c +++ b/drivers/net/wireless/hostap/hostap_ioctl.c @@ -1,6 +1,7 @@ /* ioctl() (mostly Linux Wireless Extensions) routines for Host AP driver */ #include +#include #include #include #include diff --git a/drivers/net/wireless/ipw2x00/ipw2200.c b/drivers/net/wireless/ipw2x00/ipw2200.c index 8d58e6ed4e7d..827824d45de9 100644 --- a/drivers/net/wireless/ipw2x00/ipw2200.c +++ b/drivers/net/wireless/ipw2x00/ipw2200.c @@ -30,6 +30,7 @@ ******************************************************************************/ +#include #include "ipw2200.h" diff --git a/drivers/net/wireless/iwlwifi/iwl-3945.c b/drivers/net/wireless/iwlwifi/iwl-3945.c index e70c5b0af364..68136172b823 100644 --- a/drivers/net/wireless/iwlwifi/iwl-3945.c +++ b/drivers/net/wireless/iwlwifi/iwl-3945.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/wireless/iwlwifi/iwl-4965.c b/drivers/net/wireless/iwlwifi/iwl-4965.c index a22a0501c190..6f703a041847 100644 --- a/drivers/net/wireless/iwlwifi/iwl-4965.c +++ b/drivers/net/wireless/iwlwifi/iwl-4965.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/wireless/iwlwifi/iwl-5000.c b/drivers/net/wireless/iwlwifi/iwl-5000.c index eb08f4411000..d6bc0e051043 100644 --- a/drivers/net/wireless/iwlwifi/iwl-5000.c +++ b/drivers/net/wireless/iwlwifi/iwl-5000.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c index cdc07c477457..313d3e5ee84b 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/wireless/iwlwifi/iwl-core.c b/drivers/net/wireless/iwlwifi/iwl-core.c index 484d5c1a7312..2dc928755454 100644 --- a/drivers/net/wireless/iwlwifi/iwl-core.c +++ b/drivers/net/wireless/iwlwifi/iwl-core.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include "iwl-eeprom.h" diff --git a/drivers/net/wireless/iwlwifi/iwl-hcmd.c b/drivers/net/wireless/iwlwifi/iwl-hcmd.c index 532c8d6cd8da..a6856daf14cb 100644 --- a/drivers/net/wireless/iwlwifi/iwl-hcmd.c +++ b/drivers/net/wireless/iwlwifi/iwl-hcmd.c @@ -28,6 +28,7 @@ #include #include +#include #include #include "iwl-dev.h" /* FIXME: remove */ diff --git a/drivers/net/wireless/iwlwifi/iwl-tx.c b/drivers/net/wireless/iwlwifi/iwl-tx.c index c18907544701..fb9bcfa6d947 100644 --- a/drivers/net/wireless/iwlwifi/iwl-tx.c +++ b/drivers/net/wireless/iwlwifi/iwl-tx.c @@ -28,6 +28,7 @@ *****************************************************************************/ #include +#include #include #include "iwl-eeprom.h" #include "iwl-dev.h" diff --git a/drivers/net/wireless/iwlwifi/iwl3945-base.c b/drivers/net/wireless/iwlwifi/iwl3945-base.c index c390dbd877e4..aa49230422f3 100644 --- a/drivers/net/wireless/iwlwifi/iwl3945-base.c +++ b/drivers/net/wireless/iwlwifi/iwl3945-base.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/wireless/iwmc3200wifi/cfg80211.c b/drivers/net/wireless/iwmc3200wifi/cfg80211.c index a56a2b0ac99a..f3c55658225b 100644 --- a/drivers/net/wireless/iwmc3200wifi/cfg80211.c +++ b/drivers/net/wireless/iwmc3200wifi/cfg80211.c @@ -23,6 +23,7 @@ #include #include +#include #include #include #include diff --git a/drivers/net/wireless/iwmc3200wifi/commands.c b/drivers/net/wireless/iwmc3200wifi/commands.c index 23b52fa2605f..84158b6d35d8 100644 --- a/drivers/net/wireless/iwmc3200wifi/commands.c +++ b/drivers/net/wireless/iwmc3200wifi/commands.c @@ -40,6 +40,7 @@ #include #include #include +#include #include "iwm.h" #include "bus.h" diff --git a/drivers/net/wireless/iwmc3200wifi/main.c b/drivers/net/wireless/iwmc3200wifi/main.c index d668e4756324..222eb2cf1b30 100644 --- a/drivers/net/wireless/iwmc3200wifi/main.c +++ b/drivers/net/wireless/iwmc3200wifi/main.c @@ -38,6 +38,7 @@ #include #include +#include #include #include diff --git a/drivers/net/wireless/iwmc3200wifi/rx.c b/drivers/net/wireless/iwmc3200wifi/rx.c index 40dbcbc16593..771a301003c9 100644 --- a/drivers/net/wireless/iwmc3200wifi/rx.c +++ b/drivers/net/wireless/iwmc3200wifi/rx.c @@ -38,6 +38,7 @@ #include #include +#include #include #include #include diff --git a/drivers/net/wireless/libertas/cmd.c b/drivers/net/wireless/libertas/cmd.c index 685098148e10..0a324dcd264c 100644 --- a/drivers/net/wireless/libertas/cmd.c +++ b/drivers/net/wireless/libertas/cmd.c @@ -6,6 +6,7 @@ #include #include #include +#include #include "host.h" #include "hostcmd.h" #include "decl.h" diff --git a/drivers/net/wireless/libertas/tx.c b/drivers/net/wireless/libertas/tx.c index 4c018f7a0a8d..8c3766a6e8e7 100644 --- a/drivers/net/wireless/libertas/tx.c +++ b/drivers/net/wireless/libertas/tx.c @@ -3,6 +3,7 @@ */ #include #include +#include #include "hostcmd.h" #include "radiotap.h" diff --git a/drivers/net/wireless/prism54/isl_ioctl.c b/drivers/net/wireless/prism54/isl_ioctl.c index 4c97c6ad6f5d..bc08464d8323 100644 --- a/drivers/net/wireless/prism54/isl_ioctl.c +++ b/drivers/net/wireless/prism54/isl_ioctl.c @@ -19,6 +19,7 @@ * */ +#include #include #include #include diff --git a/drivers/net/wireless/prism54/islpci_dev.c b/drivers/net/wireless/prism54/islpci_dev.c index e26d7b3ceab5..2505be56ae39 100644 --- a/drivers/net/wireless/prism54/islpci_dev.c +++ b/drivers/net/wireless/prism54/islpci_dev.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/wireless/prism54/islpci_mgt.c b/drivers/net/wireless/prism54/islpci_mgt.c index f7c677e2094d..69d2f882fd06 100644 --- a/drivers/net/wireless/prism54/islpci_mgt.c +++ b/drivers/net/wireless/prism54/islpci_mgt.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include diff --git a/drivers/net/wireless/rt2x00/rt2x00debug.c b/drivers/net/wireless/rt2x00/rt2x00debug.c index 7b3ee8c2eaef..68bc9bb1dbf9 100644 --- a/drivers/net/wireless/rt2x00/rt2x00debug.c +++ b/drivers/net/wireless/rt2x00/rt2x00debug.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include "rt2x00.h" diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c index 2ce8f9ccc66e..d49ecc94bd49 100644 --- a/drivers/pci/pcie/aer/aerdrv.c +++ b/drivers/pci/pcie/aer/aerdrv.c @@ -17,6 +17,7 @@ #include #include +#include #include #include #include diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index 4cdb31a362ca..a0c816238aa9 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -12,6 +12,7 @@ */ #include +#include #include int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm) diff --git a/drivers/rtc/rtc-dev.c b/drivers/rtc/rtc-dev.c index 8a11de9552cd..62227cd52410 100644 --- a/drivers/rtc/rtc-dev.c +++ b/drivers/rtc/rtc-dev.c @@ -13,6 +13,7 @@ #include #include +#include #include "rtc-core.h" static dev_t rtc_devt; diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index a9d707047202..e941367dd28f 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/uwb/whc-rc.c b/drivers/uwb/whc-rc.c index 1d9a6f54658e..01950c62dc8d 100644 --- a/drivers/uwb/whc-rc.c +++ b/drivers/uwb/whc-rc.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include #include diff --git a/fs/file.c b/fs/file.c index f313314f996f..87e129030ab1 100644 --- a/fs/file.c +++ b/fs/file.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index b78cf8194957..7ca72b74eec7 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -10,7 +10,6 @@ #include #include #include -#include #include #include #include @@ -610,6 +609,7 @@ extern void debug_poll_all_shared_irqs(void); static inline void debug_poll_all_shared_irqs(void) { } #endif +struct seq_file; int show_interrupts(struct seq_file *p, void *v); struct irq_desc; diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 81bb42358595..eaf36364b7d4 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -11,6 +11,7 @@ #define LINUX_MMC_HOST_H #include +#include #include diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index a81cf80554db..17c71bb565c6 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -11,6 +11,7 @@ */ #include +#include #include #include #include diff --git a/kernel/mutex-debug.c b/kernel/mutex-debug.c index 50d022e5a560..ec815a960b5d 100644 --- a/kernel/mutex-debug.c +++ b/kernel/mutex-debug.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index fb0f46fa1ecd..c3a4e2907eaa 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 2755a3bd16a1..eae56fddfa3b 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -9,6 +9,7 @@ */ #include #include +#include #include #include #include diff --git a/lib/fault-inject.c b/lib/fault-inject.c index f97af55bdd96..7e65af70635e 100644 --- a/lib/fault-inject.c +++ b/lib/fault-inject.c @@ -1,6 +1,7 @@ #include #include #include +#include #include #include #include diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 5e7aed0802bf..0f551a4a44cd 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include diff --git a/net/irda/ircomm/ircomm_tty_attach.c b/net/irda/ircomm/ircomm_tty_attach.c index eafc010907c2..3c1754023022 100644 --- a/net/irda/ircomm/ircomm_tty_attach.c +++ b/net/irda/ircomm/ircomm_tty_attach.c @@ -30,6 +30,7 @@ ********************************************************************/ #include +#include #include #include diff --git a/net/irda/irlan/irlan_common.c b/net/irda/irlan/irlan_common.c index 62116829b817..315ead3cb926 100644 --- a/net/irda/irlan/irlan_common.c +++ b/net/irda/irlan/irlan_common.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include #include diff --git a/net/irda/irlan/irlan_eth.c b/net/irda/irlan/irlan_eth.c index 7b6b631f647f..d340110f5c0c 100644 --- a/net/irda/irlan/irlan_eth.c +++ b/net/irda/irlan/irlan_eth.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include diff --git a/net/irda/irnet/irnet_irda.c b/net/irda/irnet/irnet_irda.c index cf9a4b531a98..cccc2e93234f 100644 --- a/net/irda/irnet/irnet_irda.c +++ b/net/irda/irnet/irnet_irda.c @@ -9,6 +9,7 @@ */ #include "irnet_irda.h" /* Private header */ +#include #include #include diff --git a/net/irda/irnet/irnet_ppp.c b/net/irda/irnet/irnet_ppp.c index 68cbcb19cbd8..7dea882dbb75 100644 --- a/net/irda/irnet/irnet_ppp.c +++ b/net/irda/irnet/irnet_ppp.c @@ -13,6 +13,7 @@ * 2) as a control channel (write commands, read events) */ +#include #include #include "irnet_ppp.h" /* Private header */ /* Please put other headers in irnet.h - Thanks */ diff --git a/net/mac80211/rc80211_pid_debugfs.c b/net/mac80211/rc80211_pid_debugfs.c index a59043fbb0ff..45667054a5f3 100644 --- a/net/mac80211/rc80211_pid_debugfs.c +++ b/net/mac80211/rc80211_pid_debugfs.c @@ -6,6 +6,7 @@ * published by the Free Software Foundation. */ +#include #include #include #include diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 7c9ec3dee96e..ca6e68dcd8a8 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 0cf5e8c27a10..3fa5751af0ec 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include #include diff --git a/net/wireless/core.c b/net/wireless/core.c index 45b2be3274db..a595f712b5bf 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include "nl80211.h" -- cgit v1.2.3 From c01226c3145d173a0d38f9d5b4f229cc23d99ae2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 21 Sep 2009 16:37:12 +0200 Subject: warn about use of uninstalled kernel headers User applications frequently hit problems when they try to use the kernel headers directly, rather than the exported headers. This adds an explicit warning for this case, and points to a URL holding an explanation of why this is wrong and what to do about it. Signed-off-by: Arnd Bergmann Signed-off-by: Sam Ravnborg --- include/linux/kernel.h | 6 ++++++ scripts/headers_install.pl | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d3cd23f30039..f4e3184fa054 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -659,6 +659,12 @@ extern int do_sysinfo(struct sysinfo *info); #endif /* __KERNEL__ */ +#ifndef __EXPORTED_HEADERS__ +#ifndef __KERNEL__ +#warning Attempt to use kernel headers from user space, see http://kernelnewbies.org/KernelHeaders +#endif /* __KERNEL__ */ +#endif /* __EXPORTED_HEADERS__ */ + #define SI_LOAD_SHIFT 16 struct sysinfo { long uptime; /* Seconds since boot */ diff --git a/scripts/headers_install.pl b/scripts/headers_install.pl index c6ae4052ab43..b89ca2c58fdb 100644 --- a/scripts/headers_install.pl +++ b/scripts/headers_install.pl @@ -20,7 +20,7 @@ use strict; my ($readdir, $installdir, $arch, @files) = @ARGV; -my $unifdef = "scripts/unifdef -U__KERNEL__"; +my $unifdef = "scripts/unifdef -U__KERNEL__ -D__EXPORTED_HEADERS__"; foreach my $file (@files) { local *INFILE; -- cgit v1.2.3 From 43046b606673c9c991919ff75b980b72541e9ede Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 14 Oct 2009 09:16:42 -0700 Subject: workqueue: add 'flush_delayed_work()' to run and wait for delayed work It basically turns a delayed work into an immediate work, and then waits for it to finish. --- include/linux/workqueue.h | 1 + kernel/workqueue.c | 18 ++++++++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 7ef0c7b94f31..cf24c20de9e4 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -207,6 +207,7 @@ extern int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, extern void flush_workqueue(struct workqueue_struct *wq); extern void flush_scheduled_work(void); +extern void flush_delayed_work(struct delayed_work *work); extern int schedule_work(struct work_struct *work); extern int schedule_work_on(int cpu, struct work_struct *work); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index addfe2df93b1..ccefe574dcf7 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -639,6 +639,24 @@ int schedule_delayed_work(struct delayed_work *dwork, } EXPORT_SYMBOL(schedule_delayed_work); +/** + * flush_delayed_work - block until a dwork_struct's callback has terminated + * @dwork: the delayed work which is to be flushed + * + * Any timeout is cancelled, and any pending work is run immediately. + */ +void flush_delayed_work(struct delayed_work *dwork) +{ + if (del_timer(&dwork->timer)) { + struct cpu_workqueue_struct *cwq; + cwq = wq_per_cpu(keventd_wq, get_cpu()); + __queue_work(cwq, &dwork->work); + put_cpu(); + } + flush_work(&dwork->work); +} +EXPORT_SYMBOL(flush_delayed_work); + /** * schedule_delayed_work_on - queue work in global workqueue on CPU after delay * @cpu: cpu to use -- cgit v1.2.3