From 5dc06c5a70b79a323152bec7e55783e705767e63 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 23 Aug 2011 14:49:55 +0200 Subject: block: remove READ_META and WRITE_META Replace all occurnanced of the undocumented READ_META with READ | REQ_META and remove the unused WRITE_META define. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 178cdb4f1d4a..eae44c981173 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -162,10 +162,8 @@ struct inodes_stat_t { #define READA RWA_MASK #define READ_SYNC (READ | REQ_SYNC) -#define READ_META (READ | REQ_META) #define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE) #define WRITE_ODIRECT (WRITE | REQ_SYNC) -#define WRITE_META (WRITE | REQ_META) #define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH) #define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA) #define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA) -- cgit v1.2.3-71-gd317 From 65299a3b788bd274bed92f9fa3232082c9f3ea70 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 23 Aug 2011 14:50:29 +0200 Subject: block: separate priority boosting from REQ_META Add a new REQ_PRIO to let requests preempt others in the cfq I/O schedule, and lave REQ_META purely for marking requests as metadata in blktrace. All existing callers of REQ_META except for XFS are updated to also set REQ_PRIO for now. Signed-off-by: Christoph Hellwig Reviewed-by: Namhyung Kim Signed-off-by: Jens Axboe --- block/cfq-iosched.c | 20 ++++++++++---------- drivers/mmc/card/block.c | 3 +++ fs/ext3/inode.c | 4 ++-- fs/ext3/namei.c | 3 ++- fs/ext4/inode.c | 4 ++-- fs/ext4/namei.c | 3 ++- fs/gfs2/log.c | 4 ++-- fs/gfs2/meta_io.c | 6 +++--- fs/gfs2/ops_fstype.c | 2 +- fs/gfs2/quota.c | 2 +- include/linux/blk_types.h | 6 ++++-- 11 files changed, 32 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index a33bd4377c61..16ace89613bc 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -130,8 +130,8 @@ struct cfq_queue { unsigned long slice_end; long slice_resid; - /* pending metadata requests */ - int meta_pending; + /* pending priority requests */ + int prio_pending; /* number of requests that are on the dispatch list or inside driver */ int dispatched; @@ -684,8 +684,8 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2, if (rq_is_sync(rq1) != rq_is_sync(rq2)) return rq_is_sync(rq1) ? rq1 : rq2; - if ((rq1->cmd_flags ^ rq2->cmd_flags) & REQ_META) - return rq1->cmd_flags & REQ_META ? rq1 : rq2; + if ((rq1->cmd_flags ^ rq2->cmd_flags) & REQ_PRIO) + return rq1->cmd_flags & REQ_PRIO ? rq1 : rq2; s1 = blk_rq_pos(rq1); s2 = blk_rq_pos(rq2); @@ -1612,9 +1612,9 @@ static void cfq_remove_request(struct request *rq) cfqq->cfqd->rq_queued--; cfq_blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg, rq_data_dir(rq), rq_is_sync(rq)); - if (rq->cmd_flags & REQ_META) { - WARN_ON(!cfqq->meta_pending); - cfqq->meta_pending--; + if (rq->cmd_flags & REQ_PRIO) { + WARN_ON(!cfqq->prio_pending); + cfqq->prio_pending--; } } @@ -3372,7 +3372,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq, * So both queues are sync. Let the new request get disk time if * it's a metadata request and the current queue is doing regular IO. */ - if ((rq->cmd_flags & REQ_META) && !cfqq->meta_pending) + if ((rq->cmd_flags & REQ_PRIO) && !cfqq->prio_pending) return true; /* @@ -3439,8 +3439,8 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, struct cfq_io_context *cic = RQ_CIC(rq); cfqd->rq_queued++; - if (rq->cmd_flags & REQ_META) - cfqq->meta_pending++; + if (rq->cmd_flags & REQ_PRIO) + cfqq->prio_pending++; cfq_update_io_thinktime(cfqd, cfqq, cic); cfq_update_io_seektime(cfqd, cfqq, rq); diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 1ff5486213fb..4c1a648d00fc 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -926,6 +926,9 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq, /* * Reliable writes are used to implement Forced Unit Access and * REQ_META accesses, and are supported only on MMCs. + * + * XXX: this really needs a good explanation of why REQ_META + * is treated special. */ bool do_rel_wr = ((req->cmd_flags & REQ_FUA) || (req->cmd_flags & REQ_META)) && diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index bba7b96e0d9b..12661e1deedd 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1134,7 +1134,7 @@ struct buffer_head *ext3_bread(handle_t *handle, struct inode *inode, return bh; if (buffer_uptodate(bh)) return bh; - ll_rw_block(READ | REQ_META, 1, &bh); + ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; @@ -2807,7 +2807,7 @@ make_io: trace_ext3_load_inode(inode); get_bh(bh); bh->b_end_io = end_buffer_read_sync; - submit_bh(READ | REQ_META, bh); + submit_bh(READ | REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { ext3_error(inode->i_sb, "ext3_get_inode_loc", diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index c7d4032aa82a..0629e09f6511 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -922,7 +922,8 @@ restart: bh = ext3_getblk(NULL, dir, b++, 0, &err); bh_use[ra_max] = bh; if (bh) - ll_rw_block(READ | REQ_META, 1, &bh); + ll_rw_block(READ | REQ_META | REQ_PRIO, + 1, &bh); } } if ((bh = bh_use[ra_ptr++]) == NULL) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 1dfa18feeb3e..c7cbb3d85d9e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -650,7 +650,7 @@ struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode, return bh; if (buffer_uptodate(bh)) return bh; - ll_rw_block(READ | REQ_META, 1, &bh); + ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; @@ -3301,7 +3301,7 @@ make_io: trace_ext4_load_inode(inode); get_bh(bh); bh->b_end_io = end_buffer_read_sync; - submit_bh(READ | REQ_META, bh); + submit_bh(READ | REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { EXT4_ERROR_INODE_BLOCK(inode, block, diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index d36315ae629e..1c924faeb6c8 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -922,7 +922,8 @@ restart: bh = ext4_getblk(NULL, dir, b++, 0, &err); bh_use[ra_max] = bh; if (bh) - ll_rw_block(READ | REQ_META, 1, &bh); + ll_rw_block(READ | REQ_META | REQ_PRIO, + 1, &bh); } } if ((bh = bh_use[ra_ptr++]) == NULL) diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 85c62923ee29..598646434362 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -624,9 +624,9 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull) bh->b_end_io = end_buffer_write_sync; get_bh(bh); if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) - submit_bh(WRITE_SYNC | REQ_META, bh); + submit_bh(WRITE_SYNC | REQ_META | REQ_PRIO, bh); else - submit_bh(WRITE_FLUSH_FUA | REQ_META, bh); + submit_bh(WRITE_FLUSH_FUA | REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 747238cd9f96..be29858900f6 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -37,7 +37,7 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb { struct buffer_head *bh, *head; int nr_underway = 0; - int write_op = REQ_META | + int write_op = REQ_META | REQ_PRIO | (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE); BUG_ON(!PageLocked(page)); @@ -225,7 +225,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, } bh->b_end_io = end_buffer_read_sync; get_bh(bh); - submit_bh(READ_SYNC | REQ_META, bh); + submit_bh(READ_SYNC | REQ_META | REQ_PRIO, bh); if (!(flags & DIO_WAIT)) return 0; @@ -435,7 +435,7 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen) if (buffer_uptodate(first_bh)) goto out; if (!buffer_locked(first_bh)) - ll_rw_block(READ_SYNC | REQ_META, 1, &first_bh); + ll_rw_block(READ_SYNC | REQ_META | REQ_PRIO, 1, &first_bh); dblock++; extlen--; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 3bc073a4cf82..079587e53849 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -224,7 +224,7 @@ static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector, int silent) bio->bi_end_io = end_bio_io_page; bio->bi_private = page; - submit_bio(READ_SYNC | REQ_META, bio); + submit_bio(READ_SYNC | REQ_META | REQ_PRIO, bio); wait_on_page_locked(page); bio_put(bio); if (!PageUptodate(page)) { diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 053434049dbb..0e8bb13381e4 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -709,7 +709,7 @@ get_a_page: set_buffer_uptodate(bh); if (!buffer_uptodate(bh)) { - ll_rw_block(READ | REQ_META, 1, &bh); + ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) goto unlock_out; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 32f0076e844b..71fc53bb8f1c 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -124,6 +124,7 @@ enum rq_flag_bits { __REQ_SYNC, /* request is sync (sync write or read) */ __REQ_META, /* metadata io request */ + __REQ_PRIO, /* boost priority in cfq */ __REQ_DISCARD, /* request to discard sectors */ __REQ_SECURE, /* secure discard (used with __REQ_DISCARD) */ @@ -161,14 +162,15 @@ enum rq_flag_bits { #define REQ_FAILFAST_DRIVER (1 << __REQ_FAILFAST_DRIVER) #define REQ_SYNC (1 << __REQ_SYNC) #define REQ_META (1 << __REQ_META) +#define REQ_PRIO (1 << __REQ_PRIO) #define REQ_DISCARD (1 << __REQ_DISCARD) #define REQ_NOIDLE (1 << __REQ_NOIDLE) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) #define REQ_COMMON_MASK \ - (REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_DISCARD | \ - REQ_NOIDLE | REQ_FLUSH | REQ_FUA | REQ_SECURE) + (REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | \ + REQ_DISCARD | REQ_NOIDLE | REQ_FLUSH | REQ_FUA | REQ_SECURE) #define REQ_CLONE_MASK REQ_COMMON_MASK #define REQ_RAHEAD (1 << __REQ_RAHEAD) -- cgit v1.2.3-71-gd317 From 56ebdaf2fa3c5276be201c5d1aff1490b682ecf2 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 24 Aug 2011 16:04:34 +0200 Subject: block: simplify force plug flush code a little bit Cleaning up the code a little bit. attempt_plug_merge() traverses the plug list anyway, we can do the request counting there, so stack size is reduced a little bit. The motivation here is I suspect if we should count the requests for each queue (task could handle multiple disks in the meantime), but my test doesn't show it's worthy doing. If somebody proves we should do it, below change will make that more easier. Signed-off-by: Shaohua Li Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- block/blk-core.c | 13 +++++++------ include/linux/blkdev.h | 1 - 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 67dba6941194..b2ed78afd9f0 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1167,7 +1167,7 @@ static bool bio_attempt_front_merge(struct request_queue *q, * true if merge was successful, otherwise false. */ static bool attempt_plug_merge(struct task_struct *tsk, struct request_queue *q, - struct bio *bio) + struct bio *bio, unsigned int *request_count) { struct blk_plug *plug; struct request *rq; @@ -1176,10 +1176,13 @@ static bool attempt_plug_merge(struct task_struct *tsk, struct request_queue *q, plug = tsk->plug; if (!plug) goto out; + *request_count = 0; list_for_each_entry_reverse(rq, &plug->list, queuelist) { int el_ret; + (*request_count)++; + if (rq->q != q) continue; @@ -1219,6 +1222,7 @@ static int __make_request(struct request_queue *q, struct bio *bio) struct blk_plug *plug; int el_ret, rw_flags, where = ELEVATOR_INSERT_SORT; struct request *req; + unsigned int request_count = 0; /* * low level driver can indicate that it wants pages above a @@ -1237,7 +1241,7 @@ static int __make_request(struct request_queue *q, struct bio *bio) * Check if we can merge with the plugged list before grabbing * any locks. */ - if (attempt_plug_merge(current, q, bio)) + if (attempt_plug_merge(current, q, bio, &request_count)) goto out; spin_lock_irq(q->queue_lock); @@ -1302,9 +1306,8 @@ get_rq: if (__rq->q != q) plug->should_sort = 1; } - if (plug->count >= BLK_MAX_REQUEST_COUNT) + if (request_count >= BLK_MAX_REQUEST_COUNT) blk_flush_plug_list(plug, false); - plug->count++; list_add_tail(&req->queuelist, &plug->list); drive_stat_acct(req, 1); } else { @@ -2634,7 +2637,6 @@ void blk_start_plug(struct blk_plug *plug) INIT_LIST_HEAD(&plug->list); INIT_LIST_HEAD(&plug->cb_list); plug->should_sort = 0; - plug->count = 0; /* * If this is a nested plug, don't actually assign it. It will be @@ -2718,7 +2720,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) return; list_splice_init(&plug->list, &list); - plug->count = 0; if (plug->should_sort) { list_sort(NULL, &list, plug_rq_cmp); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 84b15d54f8c2..7fbaa9103344 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -873,7 +873,6 @@ struct blk_plug { struct list_head list; struct list_head cb_list; unsigned int should_sort; - unsigned int count; }; #define BLK_MAX_REQUEST_COUNT 16 -- cgit v1.2.3-71-gd317 From 8efcc57dedfebc99c3cd39564e3fc47cd1a24b75 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 3 Aug 2011 18:04:29 +0900 Subject: mfd: Fix value of WM8994_CONFIGURE_GPIO This needs to be an out of band value for the register and on this device registers are 16 bit so we must shift left one to the 17th bit. Signed-off-by: Mark Brown Cc: stable@kernel.org Signed-off-by: Samuel Ortiz --- include/linux/mfd/wm8994/pdata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/wm8994/pdata.h b/include/linux/mfd/wm8994/pdata.h index d12f8d635a81..97cf4f27d647 100644 --- a/include/linux/mfd/wm8994/pdata.h +++ b/include/linux/mfd/wm8994/pdata.h @@ -26,7 +26,7 @@ struct wm8994_ldo_pdata { struct regulator_init_data *init_data; }; -#define WM8994_CONFIGURE_GPIO 0x8000 +#define WM8994_CONFIGURE_GPIO 0x10000 #define WM8994_DRC_REGS 5 #define WM8994_EQ_REGS 20 -- cgit v1.2.3-71-gd317 From 185efc0f9a1f2d6ad6d4782c5d9e529f3290567f Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 14 Sep 2011 16:21:58 -0700 Subject: memcg: Revert "memcg: add memory.vmscan_stat" Revert the post-3.0 commit 82f9d486e59f5 ("memcg: add memory.vmscan_stat"). The implementation of per-memcg reclaim statistics violates how memcg hierarchies usually behave: hierarchically. The reclaim statistics are accounted to child memcgs and the parent hitting the limit, but not to hierarchy levels in between. Usually, hierarchical statistics are perfectly recursive, with each level representing the sum of itself and all its children. Since this exports statistics to userspace, this may lead to confusion and problems with changing things after the release, so revert it now, we can try again later. Signed-off-by: Johannes Weiner Acked-by: KAMEZAWA Hiroyuki Cc: Daisuke Nishimura Cc: Michal Hocko Cc: Ying Han Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/memory.txt | 85 +------------------ include/linux/memcontrol.h | 19 ----- include/linux/swap.h | 6 ++ mm/memcontrol.c | 172 ++------------------------------------- mm/vmscan.c | 39 ++------- 5 files changed, 18 insertions(+), 303 deletions(-) (limited to 'include/linux') diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index 6f3c598971fc..06eb6d957c83 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -380,7 +380,7 @@ will be charged as a new owner of it. 5.2 stat file -5.2.1 memory.stat file includes following statistics +memory.stat file includes following statistics # per-memory cgroup local status cache - # of bytes of page cache memory. @@ -438,89 +438,6 @@ Note: file_mapped is accounted only when the memory cgroup is owner of page cache.) -5.2.2 memory.vmscan_stat - -memory.vmscan_stat includes statistics information for memory scanning and -freeing, reclaiming. The statistics shows memory scanning information since -memory cgroup creation and can be reset to 0 by writing 0 as - - #echo 0 > ../memory.vmscan_stat - -This file contains following statistics. - -[param]_[file_or_anon]_pages_by_[reason]_[under_heararchy] -[param]_elapsed_ns_by_[reason]_[under_hierarchy] - -For example, - - scanned_file_pages_by_limit indicates the number of scanned - file pages at vmscan. - -Now, 3 parameters are supported - - scanned - the number of pages scanned by vmscan - rotated - the number of pages activated at vmscan - freed - the number of pages freed by vmscan - -If "rotated" is high against scanned/freed, the memcg seems busy. - -Now, 2 reason are supported - - limit - the memory cgroup's limit - system - global memory pressure + softlimit - (global memory pressure not under softlimit is not handled now) - -When under_hierarchy is added in the tail, the number indicates the -total memcg scan of its children and itself. - -elapsed_ns is a elapsed time in nanosecond. This may include sleep time -and not indicates CPU usage. So, please take this as just showing -latency. - -Here is an example. - -# cat /cgroup/memory/A/memory.vmscan_stat -scanned_pages_by_limit 9471864 -scanned_anon_pages_by_limit 6640629 -scanned_file_pages_by_limit 2831235 -rotated_pages_by_limit 4243974 -rotated_anon_pages_by_limit 3971968 -rotated_file_pages_by_limit 272006 -freed_pages_by_limit 2318492 -freed_anon_pages_by_limit 962052 -freed_file_pages_by_limit 1356440 -elapsed_ns_by_limit 351386416101 -scanned_pages_by_system 0 -scanned_anon_pages_by_system 0 -scanned_file_pages_by_system 0 -rotated_pages_by_system 0 -rotated_anon_pages_by_system 0 -rotated_file_pages_by_system 0 -freed_pages_by_system 0 -freed_anon_pages_by_system 0 -freed_file_pages_by_system 0 -elapsed_ns_by_system 0 -scanned_pages_by_limit_under_hierarchy 9471864 -scanned_anon_pages_by_limit_under_hierarchy 6640629 -scanned_file_pages_by_limit_under_hierarchy 2831235 -rotated_pages_by_limit_under_hierarchy 4243974 -rotated_anon_pages_by_limit_under_hierarchy 3971968 -rotated_file_pages_by_limit_under_hierarchy 272006 -freed_pages_by_limit_under_hierarchy 2318492 -freed_anon_pages_by_limit_under_hierarchy 962052 -freed_file_pages_by_limit_under_hierarchy 1356440 -elapsed_ns_by_limit_under_hierarchy 351386416101 -scanned_pages_by_system_under_hierarchy 0 -scanned_anon_pages_by_system_under_hierarchy 0 -scanned_file_pages_by_system_under_hierarchy 0 -rotated_pages_by_system_under_hierarchy 0 -rotated_anon_pages_by_system_under_hierarchy 0 -rotated_file_pages_by_system_under_hierarchy 0 -freed_pages_by_system_under_hierarchy 0 -freed_anon_pages_by_system_under_hierarchy 0 -freed_file_pages_by_system_under_hierarchy 0 -elapsed_ns_by_system_under_hierarchy 0 - 5.3 swappiness Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only. diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 3b535db00a94..343bd7661f2a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -39,16 +39,6 @@ extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, struct mem_cgroup *mem_cont, int active, int file); -struct memcg_scanrecord { - struct mem_cgroup *mem; /* scanend memory cgroup */ - struct mem_cgroup *root; /* scan target hierarchy root */ - int context; /* scanning context (see memcontrol.c) */ - unsigned long nr_scanned[2]; /* the number of scanned pages */ - unsigned long nr_rotated[2]; /* the number of rotated pages */ - unsigned long nr_freed[2]; /* the number of freed pages */ - unsigned long elapsed; /* nsec of time elapsed while scanning */ -}; - #ifdef CONFIG_CGROUP_MEM_RES_CTLR /* * All "charge" functions with gfp_mask should use GFP_KERNEL or @@ -127,15 +117,6 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page); extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p); -extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem, - gfp_t gfp_mask, bool noswap, - struct memcg_scanrecord *rec); -extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, - gfp_t gfp_mask, bool noswap, - struct zone *zone, - struct memcg_scanrecord *rec, - unsigned long *nr_scanned); - #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP extern int do_swap_account; #endif diff --git a/include/linux/swap.h b/include/linux/swap.h index 14d62490922e..c71f84bb62ec 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -252,6 +252,12 @@ static inline void lru_cache_add_file(struct page *page) extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); extern int __isolate_lru_page(struct page *page, int mode, int file); +extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem, + gfp_t gfp_mask, bool noswap); +extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, + gfp_t gfp_mask, bool noswap, + struct zone *zone, + unsigned long *nr_scanned); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; extern int remove_mapping(struct address_space *mapping, struct page *page); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ebd1e86bef1c..3508777837c7 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -204,50 +204,6 @@ struct mem_cgroup_eventfd_list { static void mem_cgroup_threshold(struct mem_cgroup *mem); static void mem_cgroup_oom_notify(struct mem_cgroup *mem); -enum { - SCAN_BY_LIMIT, - SCAN_BY_SYSTEM, - NR_SCAN_CONTEXT, - SCAN_BY_SHRINK, /* not recorded now */ -}; - -enum { - SCAN, - SCAN_ANON, - SCAN_FILE, - ROTATE, - ROTATE_ANON, - ROTATE_FILE, - FREED, - FREED_ANON, - FREED_FILE, - ELAPSED, - NR_SCANSTATS, -}; - -struct scanstat { - spinlock_t lock; - unsigned long stats[NR_SCAN_CONTEXT][NR_SCANSTATS]; - unsigned long rootstats[NR_SCAN_CONTEXT][NR_SCANSTATS]; -}; - -const char *scanstat_string[NR_SCANSTATS] = { - "scanned_pages", - "scanned_anon_pages", - "scanned_file_pages", - "rotated_pages", - "rotated_anon_pages", - "rotated_file_pages", - "freed_pages", - "freed_anon_pages", - "freed_file_pages", - "elapsed_ns", -}; -#define SCANSTAT_WORD_LIMIT "_by_limit" -#define SCANSTAT_WORD_SYSTEM "_by_system" -#define SCANSTAT_WORD_HIERARCHY "_under_hierarchy" - - /* * The memory controller data structure. The memory controller controls both * page cache and RSS per cgroup. We would eventually like to provide @@ -313,8 +269,7 @@ struct mem_cgroup { /* For oom notifier event fd */ struct list_head oom_notify; - /* For recording LRU-scan statistics */ - struct scanstat scanstat; + /* * Should we move charges of a task when a task is moved into this * mem_cgroup ? And what type of charges should we move ? @@ -1678,44 +1633,6 @@ bool mem_cgroup_reclaimable(struct mem_cgroup *mem, bool noswap) } #endif -static void __mem_cgroup_record_scanstat(unsigned long *stats, - struct memcg_scanrecord *rec) -{ - - stats[SCAN] += rec->nr_scanned[0] + rec->nr_scanned[1]; - stats[SCAN_ANON] += rec->nr_scanned[0]; - stats[SCAN_FILE] += rec->nr_scanned[1]; - - stats[ROTATE] += rec->nr_rotated[0] + rec->nr_rotated[1]; - stats[ROTATE_ANON] += rec->nr_rotated[0]; - stats[ROTATE_FILE] += rec->nr_rotated[1]; - - stats[FREED] += rec->nr_freed[0] + rec->nr_freed[1]; - stats[FREED_ANON] += rec->nr_freed[0]; - stats[FREED_FILE] += rec->nr_freed[1]; - - stats[ELAPSED] += rec->elapsed; -} - -static void mem_cgroup_record_scanstat(struct memcg_scanrecord *rec) -{ - struct mem_cgroup *mem; - int context = rec->context; - - if (context >= NR_SCAN_CONTEXT) - return; - - mem = rec->mem; - spin_lock(&mem->scanstat.lock); - __mem_cgroup_record_scanstat(mem->scanstat.stats[context], rec); - spin_unlock(&mem->scanstat.lock); - - mem = rec->root; - spin_lock(&mem->scanstat.lock); - __mem_cgroup_record_scanstat(mem->scanstat.rootstats[context], rec); - spin_unlock(&mem->scanstat.lock); -} - /* * Scan the hierarchy if needed to reclaim memory. We remember the last child * we reclaimed from, so that we don't end up penalizing one child extensively @@ -1740,9 +1657,8 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, 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; - struct memcg_scanrecord rec; unsigned long excess; - unsigned long scanned; + unsigned long nr_scanned; excess = res_counter_soft_limit_excess(&root_mem->res) >> PAGE_SHIFT; @@ -1750,15 +1666,6 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, if (!check_soft && !shrink && root_mem->memsw_is_minimum) noswap = true; - if (shrink) - rec.context = SCAN_BY_SHRINK; - else if (check_soft) - rec.context = SCAN_BY_SYSTEM; - else - rec.context = SCAN_BY_LIMIT; - - rec.root = root_mem; - while (1) { victim = mem_cgroup_select_victim(root_mem); if (victim == root_mem) { @@ -1799,23 +1706,14 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, css_put(&victim->css); continue; } - rec.mem = victim; - rec.nr_scanned[0] = 0; - rec.nr_scanned[1] = 0; - rec.nr_rotated[0] = 0; - rec.nr_rotated[1] = 0; - rec.nr_freed[0] = 0; - rec.nr_freed[1] = 0; - rec.elapsed = 0; /* we use swappiness of local cgroup */ if (check_soft) { ret = mem_cgroup_shrink_node_zone(victim, gfp_mask, - noswap, zone, &rec, &scanned); - *total_scanned += scanned; + noswap, zone, &nr_scanned); + *total_scanned += nr_scanned; } else ret = try_to_free_mem_cgroup_pages(victim, gfp_mask, - noswap, &rec); - mem_cgroup_record_scanstat(&rec); + noswap); css_put(&victim->css); /* * At shrinking usage, we can't check we should stop here or @@ -3854,18 +3752,14 @@ try_to_free: /* try to free all pages in this cgroup */ shrink = 1; while (nr_retries && mem->res.usage > 0) { - struct memcg_scanrecord rec; int progress; if (signal_pending(current)) { ret = -EINTR; goto out; } - rec.context = SCAN_BY_SHRINK; - rec.mem = mem; - rec.root = mem; progress = try_to_free_mem_cgroup_pages(mem, GFP_KERNEL, - false, &rec); + false); if (!progress) { nr_retries--; /* maybe some writeback is necessary */ @@ -4709,54 +4603,6 @@ static int mem_control_numa_stat_open(struct inode *unused, struct file *file) } #endif /* CONFIG_NUMA */ -static int mem_cgroup_vmscan_stat_read(struct cgroup *cgrp, - struct cftype *cft, - struct cgroup_map_cb *cb) -{ - struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp); - char string[64]; - int i; - - for (i = 0; i < NR_SCANSTATS; i++) { - strcpy(string, scanstat_string[i]); - strcat(string, SCANSTAT_WORD_LIMIT); - cb->fill(cb, string, mem->scanstat.stats[SCAN_BY_LIMIT][i]); - } - - for (i = 0; i < NR_SCANSTATS; i++) { - strcpy(string, scanstat_string[i]); - strcat(string, SCANSTAT_WORD_SYSTEM); - cb->fill(cb, string, mem->scanstat.stats[SCAN_BY_SYSTEM][i]); - } - - for (i = 0; i < NR_SCANSTATS; i++) { - strcpy(string, scanstat_string[i]); - strcat(string, SCANSTAT_WORD_LIMIT); - strcat(string, SCANSTAT_WORD_HIERARCHY); - cb->fill(cb, string, mem->scanstat.rootstats[SCAN_BY_LIMIT][i]); - } - for (i = 0; i < NR_SCANSTATS; i++) { - strcpy(string, scanstat_string[i]); - strcat(string, SCANSTAT_WORD_SYSTEM); - strcat(string, SCANSTAT_WORD_HIERARCHY); - cb->fill(cb, string, mem->scanstat.rootstats[SCAN_BY_SYSTEM][i]); - } - return 0; -} - -static int mem_cgroup_reset_vmscan_stat(struct cgroup *cgrp, - unsigned int event) -{ - struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp); - - spin_lock(&mem->scanstat.lock); - memset(&mem->scanstat.stats, 0, sizeof(mem->scanstat.stats)); - memset(&mem->scanstat.rootstats, 0, sizeof(mem->scanstat.rootstats)); - spin_unlock(&mem->scanstat.lock); - return 0; -} - - static struct cftype mem_cgroup_files[] = { { .name = "usage_in_bytes", @@ -4827,11 +4673,6 @@ static struct cftype mem_cgroup_files[] = { .mode = S_IRUGO, }, #endif - { - .name = "vmscan_stat", - .read_map = mem_cgroup_vmscan_stat_read, - .trigger = mem_cgroup_reset_vmscan_stat, - }, }; #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP @@ -5095,7 +4936,6 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) atomic_set(&mem->refcnt, 1); mem->move_charge_at_immigrate = 0; mutex_init(&mem->thresholds_lock); - spin_lock_init(&mem->scanstat.lock); return &mem->css; free_out: __mem_cgroup_free(mem); diff --git a/mm/vmscan.c b/mm/vmscan.c index e49bcb6d4948..b55699cd9067 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -105,7 +105,6 @@ struct scan_control { /* Which cgroup do we reclaim from */ struct mem_cgroup *mem_cgroup; - struct memcg_scanrecord *memcg_record; /* * Nodemask of nodes allowed by the caller. If NULL, all nodes @@ -1349,8 +1348,6 @@ putback_lru_pages(struct zone *zone, struct scan_control *sc, int file = is_file_lru(lru); int numpages = hpage_nr_pages(page); reclaim_stat->recent_rotated[file] += numpages; - if (!scanning_global_lru(sc)) - sc->memcg_record->nr_rotated[file] += numpages; } if (!pagevec_add(&pvec, page)) { spin_unlock_irq(&zone->lru_lock); @@ -1394,10 +1391,6 @@ static noinline_for_stack void update_isolated_counts(struct zone *zone, reclaim_stat->recent_scanned[0] += *nr_anon; reclaim_stat->recent_scanned[1] += *nr_file; - if (!scanning_global_lru(sc)) { - sc->memcg_record->nr_scanned[0] += *nr_anon; - sc->memcg_record->nr_scanned[1] += *nr_file; - } } /* @@ -1511,9 +1504,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, nr_reclaimed += shrink_page_list(&page_list, zone, sc); } - if (!scanning_global_lru(sc)) - sc->memcg_record->nr_freed[file] += nr_reclaimed; - local_irq_disable(); if (current_is_kswapd()) __count_vm_events(KSWAPD_STEAL, nr_reclaimed); @@ -1613,8 +1603,6 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, } reclaim_stat->recent_scanned[file] += nr_taken; - if (!scanning_global_lru(sc)) - sc->memcg_record->nr_scanned[file] += nr_taken; __count_zone_vm_events(PGREFILL, zone, pgscanned); if (file) @@ -1666,8 +1654,6 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, * get_scan_ratio. */ reclaim_stat->recent_rotated[file] += nr_rotated; - if (!scanning_global_lru(sc)) - sc->memcg_record->nr_rotated[file] += nr_rotated; move_active_pages_to_lru(zone, &l_active, LRU_ACTIVE + file * LRU_FILE); @@ -2265,10 +2251,9 @@ 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, - struct zone *zone, - struct memcg_scanrecord *rec, - unsigned long *scanned) + gfp_t gfp_mask, bool noswap, + struct zone *zone, + unsigned long *nr_scanned) { struct scan_control sc = { .nr_scanned = 0, @@ -2278,9 +2263,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, .may_swap = !noswap, .order = 0, .mem_cgroup = mem, - .memcg_record = rec, }; - ktime_t start, end; sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); @@ -2289,7 +2272,6 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, sc.may_writepage, sc.gfp_mask); - start = ktime_get(); /* * NOTE: Although we can get the priority field, using it * here is not a good idea, since it limits the pages we can scan. @@ -2298,25 +2280,19 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, * the priority and make it zero. */ shrink_zone(0, zone, &sc); - end = ktime_get(); - - if (rec) - rec->elapsed += ktime_to_ns(ktime_sub(end, start)); - *scanned = sc.nr_scanned; trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); + *nr_scanned = sc.nr_scanned; return sc.nr_reclaimed; } unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, gfp_t gfp_mask, - bool noswap, - struct memcg_scanrecord *rec) + bool noswap) { struct zonelist *zonelist; unsigned long nr_reclaimed; - ktime_t start, end; int nid; struct scan_control sc = { .may_writepage = !laptop_mode, @@ -2325,7 +2301,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, .nr_to_reclaim = SWAP_CLUSTER_MAX, .order = 0, .mem_cgroup = mem_cont, - .memcg_record = rec, .nodemask = NULL, /* we don't care the placement */ .gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), @@ -2334,7 +2309,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, .gfp_mask = sc.gfp_mask, }; - start = ktime_get(); /* * Unlike direct reclaim via alloc_pages(), memcg's reclaim doesn't * take care of from where we get pages. So the node where we start the @@ -2349,9 +2323,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, sc.gfp_mask); nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink); - end = ktime_get(); - if (rec) - rec->elapsed += ktime_to_ns(ktime_sub(end, start)); trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); -- cgit v1.2.3-71-gd317 From 4f5b04800a224aadb6cffcbbc3d3fa26e2367c7f Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 14 Sep 2011 16:22:29 -0700 Subject: drivers/gpio/gpio-generic.c: fix build errors Building a kernel with hotplug disabled results in a link failure: `bgpio_remove' referenced in section `___ksymtab_gpl+bgpio_remove' of drivers/built-in.o: defined in discarded section `.devexit.text' of drivers/built-in.o This is because of bgpio_remove() is exported. It is illegal to export symbols which are discarded either at link time or as part of an init/exit section. Fix this by dropping the __devexit attributation from bgpio_remove(). Also drop the __devinit attributation from bgpio_init(). Signed-off-by: Russell King Cc: Grant Likely Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/gpio/gpio-generic.c | 15 +++++---------- include/linux/basic_mmio_gpio.h | 15 +++++---------- 2 files changed, 10 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpio/gpio-generic.c b/drivers/gpio/gpio-generic.c index 231714def4d2..4e24436b0f82 100644 --- a/drivers/gpio/gpio-generic.c +++ b/drivers/gpio/gpio-generic.c @@ -351,7 +351,7 @@ static int bgpio_setup_direction(struct bgpio_chip *bgc, return 0; } -int __devexit bgpio_remove(struct bgpio_chip *bgc) +int bgpio_remove(struct bgpio_chip *bgc) { int err = gpiochip_remove(&bgc->gc); @@ -361,15 +361,10 @@ int __devexit bgpio_remove(struct bgpio_chip *bgc) } EXPORT_SYMBOL_GPL(bgpio_remove); -int __devinit bgpio_init(struct bgpio_chip *bgc, - struct device *dev, - unsigned long sz, - void __iomem *dat, - void __iomem *set, - void __iomem *clr, - void __iomem *dirout, - void __iomem *dirin, - bool big_endian) +int bgpio_init(struct bgpio_chip *bgc, struct device *dev, + unsigned long sz, void __iomem *dat, void __iomem *set, + void __iomem *clr, void __iomem *dirout, void __iomem *dirin, + bool big_endian) { int ret; diff --git a/include/linux/basic_mmio_gpio.h b/include/linux/basic_mmio_gpio.h index 98999cf107ce..feb912196745 100644 --- a/include/linux/basic_mmio_gpio.h +++ b/include/linux/basic_mmio_gpio.h @@ -63,15 +63,10 @@ static inline struct bgpio_chip *to_bgpio_chip(struct gpio_chip *gc) return container_of(gc, struct bgpio_chip, gc); } -int __devexit bgpio_remove(struct bgpio_chip *bgc); -int __devinit bgpio_init(struct bgpio_chip *bgc, - struct device *dev, - unsigned long sz, - void __iomem *dat, - void __iomem *set, - void __iomem *clr, - void __iomem *dirout, - void __iomem *dirin, - bool big_endian); +int bgpio_remove(struct bgpio_chip *bgc); +int bgpio_init(struct bgpio_chip *bgc, struct device *dev, + unsigned long sz, void __iomem *dat, void __iomem *set, + void __iomem *clr, void __iomem *dirout, void __iomem *dirin, + bool big_endian); #endif /* __BASIC_MMIO_GPIO_H */ -- cgit v1.2.3-71-gd317 From 946cedccbd7387488d2cee5da92cdfeb28d2e670 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 30 Aug 2011 03:21:44 +0000 Subject: tcp: Change possible SYN flooding messages "Possible SYN flooding on port xxxx " messages can fill logs on servers. Change logic to log the message only once per listener, and add two new SNMP counters to track : TCPReqQFullDoCookies : number of times a SYNCOOKIE was replied to client TCPReqQFullDrop : number of times a SYN request was dropped because syncookies were not enabled. Based on a prior patch from Tom Herbert, and suggestions from David. Signed-off-by: Eric Dumazet CC: Tom Herbert Signed-off-by: David S. Miller --- include/linux/snmp.h | 2 ++ include/net/request_sock.h | 3 ++- include/net/tcp.h | 3 +++ net/ipv4/proc.c | 2 ++ net/ipv4/tcp_ipv4.c | 49 ++++++++++++++++++++++++++-------------------- net/ipv6/tcp_ipv6.c | 31 +++-------------------------- 6 files changed, 40 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/include/linux/snmp.h b/include/linux/snmp.h index 12b2b18e50c1..e16557a357e5 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -231,6 +231,8 @@ enum LINUX_MIB_TCPDEFERACCEPTDROP, LINUX_MIB_IPRPFILTER, /* IP Reverse Path Filter (rp_filter) */ LINUX_MIB_TCPTIMEWAITOVERFLOW, /* TCPTimeWaitOverflow */ + LINUX_MIB_TCPREQQFULLDOCOOKIES, /* TCPReqQFullDoCookies */ + LINUX_MIB_TCPREQQFULLDROP, /* TCPReqQFullDrop */ __LINUX_MIB_MAX }; diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 99e6e19b57c2..4c0766e201e3 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -96,7 +96,8 @@ extern int sysctl_max_syn_backlog; */ struct listen_sock { u8 max_qlen_log; - /* 3 bytes hole, try to use */ + u8 synflood_warned; + /* 2 bytes hole, try to use */ int qlen; int qlen_young; int clock_hand; diff --git a/include/net/tcp.h b/include/net/tcp.h index 149a415d1e0a..e9b48b094683 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -460,6 +460,9 @@ extern int tcp_write_wakeup(struct sock *); extern void tcp_send_fin(struct sock *sk); extern void tcp_send_active_reset(struct sock *sk, gfp_t priority); extern int tcp_send_synack(struct sock *); +extern int tcp_syn_flood_action(struct sock *sk, + const struct sk_buff *skb, + const char *proto); extern void tcp_push_one(struct sock *, unsigned int mss_now); extern void tcp_send_ack(struct sock *sk); extern void tcp_send_delayed_ack(struct sock *sk); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index b14ec7d03b6e..4bfad5da94f4 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -254,6 +254,8 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPDeferAcceptDrop", LINUX_MIB_TCPDEFERACCEPTDROP), SNMP_MIB_ITEM("IPReversePathFilter", LINUX_MIB_IPRPFILTER), SNMP_MIB_ITEM("TCPTimeWaitOverflow", LINUX_MIB_TCPTIMEWAITOVERFLOW), + SNMP_MIB_ITEM("TCPReqQFullDoCookies", LINUX_MIB_TCPREQQFULLDOCOOKIES), + SNMP_MIB_ITEM("TCPReqQFullDrop", LINUX_MIB_TCPREQQFULLDROP), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1c12b8ec849d..c34f01513945 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -808,20 +808,38 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req) kfree(inet_rsk(req)->opt); } -static void syn_flood_warning(const struct sk_buff *skb) +/* + * Return 1 if a syncookie should be sent + */ +int tcp_syn_flood_action(struct sock *sk, + const struct sk_buff *skb, + const char *proto) { - const char *msg; + const char *msg = "Dropping request"; + int want_cookie = 0; + struct listen_sock *lopt; + + #ifdef CONFIG_SYN_COOKIES - if (sysctl_tcp_syncookies) + if (sysctl_tcp_syncookies) { msg = "Sending cookies"; - else + want_cookie = 1; + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES); + } else #endif - msg = "Dropping request"; + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); - pr_info("TCP: Possible SYN flooding on port %d. %s.\n", - ntohs(tcp_hdr(skb)->dest), msg); + lopt = inet_csk(sk)->icsk_accept_queue.listen_opt; + if (!lopt->synflood_warned) { + lopt->synflood_warned = 1; + pr_info("%s: Possible SYN flooding on port %d. %s. " + " Check SNMP counters.\n", + proto, ntohs(tcp_hdr(skb)->dest), msg); + } + return want_cookie; } +EXPORT_SYMBOL(tcp_syn_flood_action); /* * Save and compile IPv4 options into the request_sock if needed. @@ -1235,11 +1253,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) __be32 saddr = ip_hdr(skb)->saddr; __be32 daddr = ip_hdr(skb)->daddr; __u32 isn = TCP_SKB_CB(skb)->when; -#ifdef CONFIG_SYN_COOKIES int want_cookie = 0; -#else -#define want_cookie 0 /* Argh, why doesn't gcc optimize this :( */ -#endif /* Never answer to SYNs send to broadcast or multicast */ if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) @@ -1250,14 +1264,9 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) * evidently real one. */ if (inet_csk_reqsk_queue_is_full(sk) && !isn) { - if (net_ratelimit()) - syn_flood_warning(skb); -#ifdef CONFIG_SYN_COOKIES - if (sysctl_tcp_syncookies) { - want_cookie = 1; - } else -#endif - goto drop; + want_cookie = tcp_syn_flood_action(sk, skb, "TCP"); + if (!want_cookie) + goto drop; } /* Accept backlog is full. If we have already queued enough @@ -1303,9 +1312,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) while (l-- > 0) *c++ ^= *hash_location++; -#ifdef CONFIG_SYN_COOKIES want_cookie = 0; /* not our kind of cookie */ -#endif tmp_ext.cookie_out_never = 0; /* false */ tmp_ext.cookie_plus = tmp_opt.cookie_plus; } else if (!tp->rx_opt.cookie_in_always) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d1fb63f4aeb7..3c9fa618b69d 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -531,20 +531,6 @@ static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req, return tcp_v6_send_synack(sk, req, rvp); } -static inline void syn_flood_warning(struct sk_buff *skb) -{ -#ifdef CONFIG_SYN_COOKIES - if (sysctl_tcp_syncookies) - printk(KERN_INFO - "TCPv6: Possible SYN flooding on port %d. " - "Sending cookies.\n", ntohs(tcp_hdr(skb)->dest)); - else -#endif - printk(KERN_INFO - "TCPv6: Possible SYN flooding on port %d. " - "Dropping request.\n", ntohs(tcp_hdr(skb)->dest)); -} - static void tcp_v6_reqsk_destructor(struct request_sock *req) { kfree_skb(inet6_rsk(req)->pktopts); @@ -1179,11 +1165,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); __u32 isn = TCP_SKB_CB(skb)->when; struct dst_entry *dst = NULL; -#ifdef CONFIG_SYN_COOKIES int want_cookie = 0; -#else -#define want_cookie 0 -#endif if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_conn_request(sk, skb); @@ -1192,14 +1174,9 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) goto drop; if (inet_csk_reqsk_queue_is_full(sk) && !isn) { - if (net_ratelimit()) - syn_flood_warning(skb); -#ifdef CONFIG_SYN_COOKIES - if (sysctl_tcp_syncookies) - want_cookie = 1; - else -#endif - goto drop; + want_cookie = tcp_syn_flood_action(sk, skb, "TCPv6"); + if (!want_cookie) + goto drop; } if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) @@ -1249,9 +1226,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) while (l-- > 0) *c++ ^= *hash_location++; -#ifdef CONFIG_SYN_COOKIES want_cookie = 0; /* not our kind of cookie */ -#endif tmp_ext.cookie_out_never = 0; /* false */ tmp_ext.cookie_plus = tmp_opt.cookie_plus; } else if (!tp->rx_opt.cookie_in_always) { -- cgit v1.2.3-71-gd317 From 48c830120f2a20b44220aa26feda9ed15f49eaab Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 31 Aug 2011 08:03:29 +0000 Subject: net: copy userspace buffers on device forwarding dev_forward_skb loops an skb back into host networking stack which might hang on the memory indefinitely. In particular, this can happen in macvtap in bridged mode. Copy the userspace fragments to avoid blocking the sender in that case. As this patch makes skb_copy_ubufs extern now, I also added some documentation and made it clear the SKBTX_DEV_ZEROCOPY flag automatically instead of doing it in all callers. This can be made into a separate patch if people feel it's worth it. Signed-off-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + net/core/dev.c | 8 ++++++++ net/core/skbuff.c | 22 +++++++++++++++++----- 3 files changed, 26 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7b996ed86d5b..8bd383caa363 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -524,6 +524,7 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, extern bool skb_recycle_check(struct sk_buff *skb, int skb_size); extern struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); +extern int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); extern struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); extern struct sk_buff *skb_copy(const struct sk_buff *skb, diff --git a/net/core/dev.c b/net/core/dev.c index 17d67b579beb..b10ff0a71855 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1515,6 +1515,14 @@ static inline bool is_skb_forwardable(struct net_device *dev, */ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { + if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { + if (skb_copy_ubufs(skb, GFP_ATOMIC)) { + atomic_long_inc(&dev->rx_dropped); + kfree_skb(skb); + return NET_RX_DROP; + } + } + skb_orphan(skb); nf_reset(skb); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 27002dffe7ed..387703f56fce 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -611,8 +611,21 @@ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src) } EXPORT_SYMBOL_GPL(skb_morph); -/* skb frags copy userspace buffers to kernel */ -static int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) +/* skb_copy_ubufs - copy userspace skb frags buffers to kernel + * @skb: the skb to modify + * @gfp_mask: allocation priority + * + * This must be called on SKBTX_DEV_ZEROCOPY skb. + * It will copy all frags into kernel and drop the reference + * to userspace pages. + * + * If this function is called from an interrupt gfp_mask() must be + * %GFP_ATOMIC. + * + * Returns 0 on success or a negative error code on failure + * to allocate kernel memory to copy to. + */ +int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) { int i; int num_frags = skb_shinfo(skb)->nr_frags; @@ -652,6 +665,8 @@ static int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) skb_shinfo(skb)->frags[i - 1].page = head; head = (struct page *)head->private; } + + skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY; return 0; } @@ -677,7 +692,6 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { if (skb_copy_ubufs(skb, gfp_mask)) return NULL; - skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY; } n = skb + 1; @@ -803,7 +817,6 @@ struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) n = NULL; goto out; } - skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i]; @@ -896,7 +909,6 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { if (skb_copy_ubufs(skb, gfp_mask)) goto nofrags; - skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) get_page(skb_shinfo(skb)->frags[i].page); -- cgit v1.2.3-71-gd317 From 5bd078dda4d4fbdb4bd138a6bd5b6e274c019ed2 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 14 Sep 2011 11:31:36 -0500 Subject: irq: Add declaration of irq_domain_simple_ops to irqdomain.h irq_domain_simple_ops is exported, but is not declared in irqdomain.h, so add it. Signed-off-by: Rob Herring Cc: Grant Likely Cc: marc.zyngier@arm.com Cc: thomas.abraham@linaro.org Cc: jamie@jamieiles.com Cc: b-cousson@ti.com Cc: shawn.guo@linaro.org Cc: linux-arm-kernel@lists.infradead.org Cc: devicetree-discuss@lists.ozlabs.org Link: http://lkml.kernel.org/r/1316017900-19918-2-git-send-email-robherring2@gmail.com Signed-off-by: Thomas Gleixner --- include/linux/irqdomain.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index e807ad687a07..3ad553e8eae2 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -80,6 +80,7 @@ extern void irq_domain_del(struct irq_domain *domain); #endif /* CONFIG_IRQ_DOMAIN */ #if defined(CONFIG_IRQ_DOMAIN) && defined(CONFIG_OF_IRQ) +extern struct irq_domain_ops irq_domain_simple_ops; extern void irq_domain_add_simple(struct device_node *controller, int irq_base); extern void irq_domain_generate_simple(const struct of_device_id *match, u64 phys_base, unsigned int irq_start); -- cgit v1.2.3-71-gd317 From b6cf8788a3382c2000743a0e393bcc8aeb0601cb Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 20 Sep 2011 17:07:29 +0200 Subject: [S390] kvm: extension capability for new address space layout 598841ca9919d008b520114d8a4378c4ce4e40a1 ([S390] use gmap address spaces for kvm guest images) changed kvm on s390 to use a separate address space for kvm guests. We can now put KVM guests anywhere in the user address mode with a size up to 8PB - as long as the memory is 1MB-aligned. This change was done without KVM extension capability bit. The change was added after 3.0, but we still have a chance to add a feature bit before 3.1 (keeping the releases in a sane state). We use number 71 to avoid collisions with other pending kvm patches as requested by Alexander Graf. Signed-off-by: Christian Borntraeger Acked-by: Avi Kivity Cc: Alexander Graf Signed-off-by: Heiko Carstens --- arch/s390/kvm/kvm-s390.c | 1 + include/linux/kvm.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index b4eced131e5c..dc2b580e27bc 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -123,6 +123,7 @@ int kvm_dev_ioctl_check_extension(long ext) switch (ext) { case KVM_CAP_S390_PSW: + case KVM_CAP_S390_GMAP: r = 1; break; default: diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 2c366b52f505..aace6b8691a2 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -553,6 +553,7 @@ struct kvm_ppc_pvinfo { #define KVM_CAP_SPAPR_TCE 63 #define KVM_CAP_PPC_SMT 64 #define KVM_CAP_PPC_RMA 65 +#define KVM_CAP_S390_GMAP 71 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3-71-gd317 From d94c177beeb4469cd4f6e83354ab0223353e98ed Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 26 Sep 2011 17:44:55 -0700 Subject: vfs pathname lookup: Add LOOKUP_AUTOMOUNT flag Since we've now turned around and made LOOKUP_FOLLOW *not* force an automount, we want to add the ability to force an automount event on lookup even if we don't happen to have one of the other flags that force it implicitly (LOOKUP_OPEN, LOOKUP_DIRECTORY, LOOKUP_PARENT..) Most cases will never want to use this, since you'd normally want to delay automounting as long as possible, which usually implies LOOKUP_OPEN (when we open a file or directory, we really cannot avoid the automount any more). But Trond argued sufficiently forcefully that at a minimum bind mounting a file and quotactl will want to force the automount lookup. Some other cases (like nfs_follow_remote_path()) could use it too, although LOOKUP_DIRECTORY would work there as well. This commit just adds the flag and logic, no users yet, though. It also doesn't actually touch the LOOKUP_NO_AUTOMOUNT flag that is related, and was made irrelevant by the same change that made us not follow on LOOKUP_FOLLOW. Cc: Trond Myklebust Cc: Ian Kent Cc: Jeff Layton Cc: Miklos Szeredi Cc: David Howells Cc: Al Viro Cc: Greg KH Signed-off-by: Linus Torvalds --- fs/namei.c | 2 +- include/linux/namei.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/namei.c b/fs/namei.c index f4788365ea22..09606fd83d57 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -739,7 +739,7 @@ static int follow_automount(struct path *path, unsigned flags, * of the daemon to instantiate them before they can be used. */ if (!(flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY | - LOOKUP_OPEN | LOOKUP_CREATE)) && + LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) && path->dentry->d_inode) return -EISDIR; diff --git a/include/linux/namei.h b/include/linux/namei.h index 76fe2c62ae71..e13dac7caab2 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -48,6 +48,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; */ #define LOOKUP_FOLLOW 0x0001 #define LOOKUP_DIRECTORY 0x0002 +#define LOOKUP_AUTOMOUNT 0x0004 #define LOOKUP_PARENT 0x0010 #define LOOKUP_REVAL 0x0020 -- cgit v1.2.3-71-gd317 From b6c8069d3577481390b3f24a8434ad72a3235594 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 27 Sep 2011 08:12:33 -0700 Subject: vfs: remove LOOKUP_NO_AUTOMOUNT flag That flag no longer makes sense, since we don't look up automount points as eagerly any more. Additionally, it turns out that the NO_AUTOMOUNT handling was buggy to begin with: it would avoid automounting even for cases where we really *needed* to do the automount handling, and could return ENOENT for autofs entries that hadn't been instantiated yet. With our new non-eager automount semantics, one discussion has been about adding a AT_AUTOMOUNT flag to vfs_fstatat (and thus the newfstatat() and fstatat64() system calls), but it's probably not worth it: you can always force at least directory automounting by simply adding the final '/' to the filename, which works for *all* of the stat family system calls, old and new. So AT_NO_AUTOMOUNT (and thus LOOKUP_NO_AUTOMOUNT) really were just a result of our bad default behavior. Acked-by: Ian Kent Acked-by: Trond Myklebust Signed-off-by: Linus Torvalds --- fs/namei.c | 6 ------ fs/stat.c | 2 -- include/linux/namei.h | 2 +- 3 files changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/namei.c b/fs/namei.c index 09606fd83d57..0b3138de2a3b 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -721,12 +721,6 @@ static int follow_automount(struct path *path, unsigned flags, if (!path->dentry->d_op || !path->dentry->d_op->d_automount) return -EREMOTE; - /* We don't want to mount if someone supplied AT_NO_AUTOMOUNT - * and this is the terminal part of the path. - */ - if ((flags & LOOKUP_NO_AUTOMOUNT) && !(flags & LOOKUP_PARENT)) - return -EISDIR; /* we actually want to stop here */ - /* We don't want to mount if someone's just doing a stat - * unless they're stat'ing a directory and appended a '/' to * the name. diff --git a/fs/stat.c b/fs/stat.c index ba5316ffac61..78a3aa83c7ea 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -81,8 +81,6 @@ int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, if (!(flag & AT_SYMLINK_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; - if (flag & AT_NO_AUTOMOUNT) - lookup_flags |= LOOKUP_NO_AUTOMOUNT; if (flag & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; diff --git a/include/linux/namei.h b/include/linux/namei.h index e13dac7caab2..409328d1cbbb 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -53,7 +53,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_PARENT 0x0010 #define LOOKUP_REVAL 0x0020 #define LOOKUP_RCU 0x0040 -#define LOOKUP_NO_AUTOMOUNT 0x0080 + /* * Intent data */ -- cgit v1.2.3-71-gd317 From f75159e9936143177b442afc78150b7a7ad8aa07 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Tue, 20 Sep 2011 01:25:41 +0000 Subject: ptp: fix L2 event message recognition The IEEE 1588 standard defines two kinds of messages, event and general messages. Event messages require time stamping, and general do not. When using UDP transport, two separate ports are used for the two message types. The BPF designed to recognize event messages incorrectly classifies L2 general messages as event messages. This commit fixes the issue by extending the filter to check the message type field for L2 PTP packets. Event messages are be distinguished from general messages by testing the "general" bit. Signed-off-by: Richard Cochran Cc: Signed-off-by: David S. Miller --- include/linux/ptp_classify.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index e07e2742a865..1dc420ba213a 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -51,6 +51,7 @@ #define PTP_CLASS_V2_VLAN (PTP_CLASS_V2 | PTP_CLASS_VLAN) #define PTP_EV_PORT 319 +#define PTP_GEN_BIT 0x08 /* indicates general message, if set in message type */ #define OFF_ETYPE 12 #define OFF_IHL 14 @@ -116,14 +117,20 @@ static inline int ptp_filter_init(struct sock_filter *f, int len) {OP_OR, 0, 0, PTP_CLASS_IPV6 }, /* */ \ {OP_RETA, 0, 0, 0 }, /* */ \ /*L3x*/ {OP_RETK, 0, 0, PTP_CLASS_NONE }, /* */ \ -/*L40*/ {OP_JEQ, 0, 6, ETH_P_8021Q }, /* f goto L50 */ \ +/*L40*/ {OP_JEQ, 0, 9, ETH_P_8021Q }, /* f goto L50 */ \ {OP_LDH, 0, 0, OFF_ETYPE + 4 }, /* */ \ - {OP_JEQ, 0, 9, ETH_P_1588 }, /* f goto L60 */ \ + {OP_JEQ, 0, 15, ETH_P_1588 }, /* f goto L60 */ \ + {OP_LDB, 0, 0, ETH_HLEN + VLAN_HLEN }, /* */ \ + {OP_AND, 0, 0, PTP_GEN_BIT }, /* */ \ + {OP_JEQ, 0, 12, 0 }, /* f goto L6x */ \ {OP_LDH, 0, 0, ETH_HLEN + VLAN_HLEN }, /* */ \ {OP_AND, 0, 0, PTP_CLASS_VMASK }, /* */ \ {OP_OR, 0, 0, PTP_CLASS_VLAN }, /* */ \ {OP_RETA, 0, 0, 0 }, /* */ \ -/*L50*/ {OP_JEQ, 0, 4, ETH_P_1588 }, /* f goto L61 */ \ +/*L50*/ {OP_JEQ, 0, 7, ETH_P_1588 }, /* f goto L61 */ \ + {OP_LDB, 0, 0, ETH_HLEN }, /* */ \ + {OP_AND, 0, 0, PTP_GEN_BIT }, /* */ \ + {OP_JEQ, 0, 4, 0 }, /* f goto L6x */ \ {OP_LDH, 0, 0, ETH_HLEN }, /* */ \ {OP_AND, 0, 0, PTP_CLASS_VMASK }, /* */ \ {OP_OR, 0, 0, PTP_CLASS_L2 }, /* */ \ -- cgit v1.2.3-71-gd317 From d670ec13178d0fd8680e6742a2bc6e04f28f87d8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 1 Sep 2011 12:42:04 +0200 Subject: posix-cpu-timers: Cure SMP wobbles David reported: Attached below is a watered-down version of rt/tst-cpuclock2.c from GLIBC. Just build it with "gcc -o test test.c -lpthread -lrt" or similar. Run it several times, and you will see cases where the main thread will measure a process clock difference before and after the nanosleep which is smaller than the cpu-burner thread's individual thread clock difference. This doesn't make any sense since the cpu-burner thread is part of the top-level process's thread group. I've reproduced this on both x86-64 and sparc64 (using both 32-bit and 64-bit binaries). For example: [davem@boricha build-x86_64-linux]$ ./test process: before(0.001221967) after(0.498624371) diff(497402404) thread: before(0.000081692) after(0.498316431) diff(498234739) self: before(0.001223521) after(0.001240219) diff(16698) [davem@boricha build-x86_64-linux]$ The diff of 'process' should always be >= the diff of 'thread'. I make sure to wrap the 'thread' clock measurements the most tightly around the nanosleep() call, and that the 'process' clock measurements are the outer-most ones. --- #include #include #include #include #include #include #include #include static pthread_barrier_t barrier; static void *chew_cpu(void *arg) { pthread_barrier_wait(&barrier); while (1) __asm__ __volatile__("" : : : "memory"); return NULL; } int main(void) { clockid_t process_clock, my_thread_clock, th_clock; struct timespec process_before, process_after; struct timespec me_before, me_after; struct timespec th_before, th_after; struct timespec sleeptime; unsigned long diff; pthread_t th; int err; err = clock_getcpuclockid(0, &process_clock); if (err) return 1; err = pthread_getcpuclockid(pthread_self(), &my_thread_clock); if (err) return 1; pthread_barrier_init(&barrier, NULL, 2); err = pthread_create(&th, NULL, chew_cpu, NULL); if (err) return 1; err = pthread_getcpuclockid(th, &th_clock); if (err) return 1; pthread_barrier_wait(&barrier); err = clock_gettime(process_clock, &process_before); if (err) return 1; err = clock_gettime(my_thread_clock, &me_before); if (err) return 1; err = clock_gettime(th_clock, &th_before); if (err) return 1; sleeptime.tv_sec = 0; sleeptime.tv_nsec = 500000000; nanosleep(&sleeptime, NULL); err = clock_gettime(th_clock, &th_after); if (err) return 1; err = clock_gettime(my_thread_clock, &me_after); if (err) return 1; err = clock_gettime(process_clock, &process_after); if (err) return 1; diff = process_after.tv_nsec - process_before.tv_nsec; printf("process: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n", process_before.tv_sec, process_before.tv_nsec, process_after.tv_sec, process_after.tv_nsec, diff); diff = th_after.tv_nsec - th_before.tv_nsec; printf("thread: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n", th_before.tv_sec, th_before.tv_nsec, th_after.tv_sec, th_after.tv_nsec, diff); diff = me_after.tv_nsec - me_before.tv_nsec; printf("self: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n", me_before.tv_sec, me_before.tv_nsec, me_after.tv_sec, me_after.tv_nsec, diff); return 0; } This is due to us using p->se.sum_exec_runtime in thread_group_cputime() where we iterate the thread group and sum all data. This does not take time since the last schedule operation (tick or otherwise) into account. We can cure this by using task_sched_runtime() at the cost of having to take locks. This also means we can (and must) do away with thread_group_sched_runtime() since the modified thread_group_cputime() is now more accurate and would deadlock when called from thread_group_sched_runtime(). Aside of that it makes the function safe on 32 bit systems. The old code added t->se.sum_exec_runtime unprotected. sum_exec_runtime is a 64bit value and could be changed on another cpu at the same time. Reported-by: David Miller Signed-off-by: Peter Zijlstra Cc: stable@kernel.org Link: http://lkml.kernel.org/r/1314874459.7945.22.camel@twins Tested-by: David Miller Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 1 - kernel/posix-cpu-timers.c | 5 +++-- kernel/sched.c | 24 ------------------------ 3 files changed, 3 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4ac2c0578e0f..41d0237fd449 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1956,7 +1956,6 @@ static inline void disable_sched_clock_irqtime(void) {} extern unsigned long long task_sched_runtime(struct task_struct *task); -extern unsigned long long thread_group_sched_runtime(struct task_struct *task); /* sched_exec is called by processes performing an exec */ #ifdef CONFIG_SMP diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 58f405b581e7..c8008dd58ef2 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -250,7 +250,7 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) do { times->utime = cputime_add(times->utime, t->utime); times->stime = cputime_add(times->stime, t->stime); - times->sum_exec_runtime += t->se.sum_exec_runtime; + times->sum_exec_runtime += task_sched_runtime(t); } while_each_thread(tsk, t); out: rcu_read_unlock(); @@ -312,7 +312,8 @@ static int cpu_clock_sample_group(const clockid_t which_clock, cpu->cpu = cputime.utime; break; case CPUCLOCK_SCHED: - cpu->sched = thread_group_sched_runtime(p); + thread_group_cputime(p, &cputime); + cpu->sched = cputime.sum_exec_runtime; break; } return 0; diff --git a/kernel/sched.c b/kernel/sched.c index d249ea88428c..b50b0f0c9aa9 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3724,30 +3724,6 @@ unsigned long long task_sched_runtime(struct task_struct *p) return ns; } -/* - * Return sum_exec_runtime for the thread group. - * In case the task is currently running, return the sum plus current's - * pending runtime that have not been accounted yet. - * - * Note that the thread group might have other running tasks as well, - * so the return value not includes other pending runtime that other - * running tasks might have. - */ -unsigned long long thread_group_sched_runtime(struct task_struct *p) -{ - struct task_cputime totals; - unsigned long flags; - struct rq *rq; - u64 ns; - - rq = task_rq_lock(p, &flags); - thread_group_cputime(p, &totals); - ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq); - task_rq_unlock(rq, p, &flags); - - return ns; -} - /* * Account user cpu time to a process. * @p: the process that the cpu time gets accounted to -- cgit v1.2.3-71-gd317 From 5f39e6705faade2e89d119958a8c51b9b6e2c53c Mon Sep 17 00:00:00 2001 From: Jon Mason Date: Mon, 3 Oct 2011 09:50:20 -0500 Subject: PCI: Disable MPS configuration by default Add the ability to disable PCI-E MPS turning and using the BIOS configured MPS defaults. Due to the number of issues recently discovered on some x86 chipsets, make this the default behavior. Also, add the option for peer to peer DMA MPS configuration. Peer to peer DMA is outside the scope of this patch, but MPS configuration could prevent it from working by having the MPS on one root port different than the MPS on another. To work around this, simply make the system wide MPS the smallest possible value (128B). Signed-off-by: Jon Mason Acked-by: Benjamin Herrenschmidt Signed-off-by: Linus Torvalds --- drivers/pci/pci.c | 6 +++++- drivers/pci/probe.c | 14 +++++++++++++- include/linux/pci.h | 3 ++- 3 files changed, 20 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 4e84fd4a4312..e9651f0a8817 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -77,7 +77,7 @@ unsigned long pci_cardbus_mem_size = DEFAULT_CARDBUS_MEM_SIZE; unsigned long pci_hotplug_io_size = DEFAULT_HOTPLUG_IO_SIZE; unsigned long pci_hotplug_mem_size = DEFAULT_HOTPLUG_MEM_SIZE; -enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_SAFE; +enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_TUNE_OFF; /* * The default CLS is used if arch didn't set CLS explicitly and not @@ -3568,10 +3568,14 @@ static int __init pci_setup(char *str) pci_hotplug_io_size = memparse(str + 9, &str); } else if (!strncmp(str, "hpmemsize=", 10)) { pci_hotplug_mem_size = memparse(str + 10, &str); + } else if (!strncmp(str, "pcie_bus_tune_off", 17)) { + pcie_bus_config = PCIE_BUS_TUNE_OFF; } else if (!strncmp(str, "pcie_bus_safe", 13)) { pcie_bus_config = PCIE_BUS_SAFE; } else if (!strncmp(str, "pcie_bus_perf", 13)) { pcie_bus_config = PCIE_BUS_PERFORMANCE; + } else if (!strncmp(str, "pcie_bus_peer2peer", 18)) { + pcie_bus_config = PCIE_BUS_PEER2PEER; } else { printk(KERN_ERR "PCI: Unknown option `%s'\n", str); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index f3f94a5c068f..6ab6bd3df4b2 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1458,12 +1458,24 @@ static int pcie_bus_configure_set(struct pci_dev *dev, void *data) */ void pcie_bus_configure_settings(struct pci_bus *bus, u8 mpss) { - u8 smpss = mpss; + u8 smpss; if (!pci_is_pcie(bus->self)) return; + if (pcie_bus_config == PCIE_BUS_TUNE_OFF) + return; + + /* FIXME - Peer to peer DMA is possible, though the endpoint would need + * to be aware to the MPS of the destination. To work around this, + * simply force the MPS of the entire system to the smallest possible. + */ + if (pcie_bus_config == PCIE_BUS_PEER2PEER) + smpss = 0; + if (pcie_bus_config == PCIE_BUS_SAFE) { + smpss = mpss; + pcie_find_smpss(bus->self, &smpss); pci_walk_bus(bus, pcie_find_smpss, &smpss); } diff --git a/include/linux/pci.h b/include/linux/pci.h index 8c230cbcbb48..9fc01226055b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -621,8 +621,9 @@ struct pci_driver { extern void pcie_bus_configure_settings(struct pci_bus *bus, u8 smpss); enum pcie_bus_config_types { - PCIE_BUS_PERFORMANCE, + PCIE_BUS_TUNE_OFF, PCIE_BUS_SAFE, + PCIE_BUS_PERFORMANCE, PCIE_BUS_PEER2PEER, }; -- cgit v1.2.3-71-gd317