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 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 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 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 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 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