From 02f726949f2be0967aa4871dd4e47d3967779b26 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 31 May 2010 18:13:25 +0200 Subject: sched, trace: Fix sched_switch() prev_state argument For CONFIG_PREEMPT=y kernels the sched_switch(.prev_state) argument isn't useful because we can get preempted with current->state != TASK_RUNNING without actually getting removed from the runqueue. Cure this by treating all preempted tasks as runnable from the tracer's point of view. Signed-off-by: Peter Zijlstra Cautiously-acked-by: Steven Rostedt LKML-Reference: <1275322715.27810.23323.camel@twins> Signed-off-by: Ingo Molnar --- include/trace/events/sched.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 4f733ecea46..b9e1dd6c620 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -115,6 +115,23 @@ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new, TP_PROTO(struct task_struct *p, int success), TP_ARGS(p, success)); +#ifdef CREATE_TRACE_POINTS +static inline long __trace_sched_switch_state(struct task_struct *p) +{ + long state = p->state; + +#ifdef CONFIG_PREEMPT + /* + * For all intents and purposes a preempted task is a running task. + */ + if (task_thread_info(p)->preempt_count & PREEMPT_ACTIVE) + state = TASK_RUNNING; +#endif + + return state; +} +#endif + /* * Tracepoint for task switches, performed by the scheduler: */ @@ -139,7 +156,7 @@ TRACE_EVENT(sched_switch, memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN); __entry->prev_pid = prev->pid; __entry->prev_prio = prev->prio; - __entry->prev_state = prev->state; + __entry->prev_state = __trace_sched_switch_state(prev); memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN); __entry->next_pid = next->pid; __entry->next_prio = next->prio; -- cgit v1.2.3 From b9b76dfaac6fa2c289ee8a005be637afd2da7e2f Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 3 Jun 2010 23:34:09 +0200 Subject: tracing: Fix null pointer deref with SEND_SIG_FORCED BUG: unable to handle kernel NULL pointer dereference at 0000000000000006 IP: [] ftrace_raw_event_signal_generate+0x87/0x140 TP_STORE_SIGINFO() forgets about SEND_SIG_FORCED, fix. We should probably export is_si_special() and change TP_STORE_SIGINFO() to use it in the longer term. Signed-off-by: Oleg Nesterov Acked-by: Roland McGrath Cc: Steven Rostedt Cc: Andrew Morton Cc: Jason Baron Cc: Masami Hiramatsu Cc: 2.6.33.x-2.6.34.x LKML-Reference: <20100603213409.GA8307@redhat.com> Signed-off-by: Frederic Weisbecker --- include/trace/events/signal.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/signal.h b/include/trace/events/signal.h index 814566c99d2..17df43464df 100644 --- a/include/trace/events/signal.h +++ b/include/trace/events/signal.h @@ -10,7 +10,8 @@ #define TP_STORE_SIGINFO(__entry, info) \ do { \ - if (info == SEND_SIG_NOINFO) { \ + if (info == SEND_SIG_NOINFO || \ + info == SEND_SIG_FORCED) { \ __entry->errno = 0; \ __entry->code = SI_USER; \ } else if (info == SEND_SIG_PRIV) { \ -- cgit v1.2.3 From 0b5649278e39a068aaf91399941bab1b4a4a3cc2 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 9 Jun 2010 10:37:18 +1000 Subject: writeback: pay attention to wbc->nr_to_write in write_cache_pages If a filesystem writes more than one page in ->writepage, write_cache_pages fails to notice this and continues to attempt writeback when wbc->nr_to_write has gone negative - this trace was captured from XFS: wbc_writeback_start: towrt=1024 wbc_writepage: towrt=1024 wbc_writepage: towrt=0 wbc_writepage: towrt=-1 wbc_writepage: towrt=-5 wbc_writepage: towrt=-21 wbc_writepage: towrt=-85 This has adverse effects on filesystem writeback behaviour. write_cache_pages() needs to terminate after a certain number of pages are written, not after a certain number of calls to ->writepage are made. This is a regression introduced by 17bc6c30cf6bfffd816bdc53682dd46fc34a2cf4 ("vfs: Add no_nrwrite_index_update writeback control flag"), but cannot be reverted directly due to subsequent bug fixes that have gone in on top of it. Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Linus Torvalds --- include/linux/writeback.h | 9 --------- include/trace/events/ext4.h | 5 +---- mm/page-writeback.c | 15 +++++---------- 3 files changed, 6 insertions(+), 23 deletions(-) (limited to 'include/trace') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index f64134653a8..d63ef8f9609 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -56,15 +56,6 @@ struct writeback_control { unsigned for_reclaim:1; /* Invoked from the page allocator */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned more_io:1; /* more io to be dispatched */ - /* - * write_cache_pages() won't update wbc->nr_to_write and - * mapping->writeback_index if no_nrwrite_index_update - * is set. write_cache_pages() may write more than we - * requested and we want to make sure nr_to_write and - * writeback_index are updated in a consistent manner - * so we use a single control to update them - */ - unsigned no_nrwrite_index_update:1; }; /* diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index f5b1ba90e95..f3865c7b416 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -306,7 +306,6 @@ TRACE_EVENT(ext4_da_writepages_result, __field( int, pages_written ) __field( long, pages_skipped ) __field( char, more_io ) - __field( char, no_nrwrite_index_update ) __field( pgoff_t, writeback_index ) ), @@ -317,16 +316,14 @@ TRACE_EVENT(ext4_da_writepages_result, __entry->pages_written = pages_written; __entry->pages_skipped = wbc->pages_skipped; __entry->more_io = wbc->more_io; - __entry->no_nrwrite_index_update = wbc->no_nrwrite_index_update; __entry->writeback_index = inode->i_mapping->writeback_index; ), - TP_printk("dev %s ino %lu ret %d pages_written %d pages_skipped %ld more_io %d no_nrwrite_index_update %d writeback_index %lu", + TP_printk("dev %s ino %lu ret %d pages_written %d pages_skipped %ld more_io %d writeback_index %lu", jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino, __entry->ret, __entry->pages_written, __entry->pages_skipped, __entry->more_io, - __entry->no_nrwrite_index_update, (unsigned long) __entry->writeback_index) ); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 5fa63bdf52e..b3dbb8040ed 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -835,7 +835,6 @@ int write_cache_pages(struct address_space *mapping, pgoff_t done_index; int cycled; int range_whole = 0; - long nr_to_write = wbc->nr_to_write; pagevec_init(&pvec, 0); if (wbc->range_cyclic) { @@ -935,11 +934,10 @@ continue_unlock: done = 1; break; } - } + } - if (nr_to_write > 0) { - nr_to_write--; - if (nr_to_write == 0 && + if (wbc->nr_to_write > 0) { + if (--wbc->nr_to_write == 0 && wbc->sync_mode == WB_SYNC_NONE) { /* * We stop writing back only if we are @@ -970,11 +968,8 @@ continue_unlock: end = writeback_index - 1; goto retry; } - if (!wbc->no_nrwrite_index_update) { - if (wbc->range_cyclic || (range_whole && nr_to_write > 0)) - mapping->writeback_index = done_index; - wbc->nr_to_write = nr_to_write; - } + if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) + mapping->writeback_index = done_index; return ret; } -- cgit v1.2.3