From 73c101011926c5832e6e141682180c4debe2cf45 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 8 Mar 2011 13:19:51 +0100 Subject: block: initial patch for on-stack per-task plugging This patch adds support for creating a queuing context outside of the queue itself. This enables us to batch up pieces of IO before grabbing the block device queue lock and submitting them to the IO scheduler. The context is created on the stack of the process and assigned in the task structure, so that we can auto-unplug it if we hit a schedule event. The current queue plugging happens implicitly if IO is submitted to an empty device, yet callers have to remember to unplug that IO when they are going to wait for it. This is an ugly API and has caused bugs in the past. Additionally, it requires hacks in the vm (->sync_page() callback) to handle that logic. By switching to an explicit plugging scheme we make the API a lot nicer and can get rid of the ->sync_page() hack in the vm. Signed-off-by: Jens Axboe --- include/linux/sched.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 777d8a5ed06b..96ac22643742 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -99,6 +99,7 @@ struct robust_list_head; struct bio_list; struct fs_struct; struct perf_event_context; +struct blk_plug; /* * List of flags we want to share for kernel threads, @@ -1429,6 +1430,11 @@ struct task_struct { /* stacked block device info */ struct bio_list *bio_list; +#ifdef CONFIG_BLOCK +/* stack plugging */ + struct blk_plug *plug; +#endif + /* VM state */ struct reclaim_state *reclaim_state; -- cgit v1.2.2 From 207205a2ba2655652fe46a60b49838af6c16a919 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 22 Mar 2011 16:30:44 -0700 Subject: kthread: NUMA aware kthread_create_on_node() All kthreads being created from a single helper task, they all use memory from a single node for their kernel stack and task struct. This patch suite creates kthread_create_on_node(), adding a 'cpu' parameter to parameters already used by kthread_create(). This parameter serves in allocating memory for the new kthread on its memory node if possible. Signed-off-by: Eric Dumazet Acked-by: David S. Miller Reviewed-by: Andi Kleen Acked-by: Rusty Russell Cc: Tejun Heo Cc: Tony Luck Cc: Fenghua Yu Cc: David Howells Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index c15936fe998b..4b601be3dace 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1471,6 +1471,7 @@ struct task_struct { #ifdef CONFIG_NUMA struct mempolicy *mempolicy; /* Protected by alloc_lock */ short il_next; + short pref_node_fork; #endif atomic_t fs_excl; /* holding fs exclusive resources */ struct rcu_head rcu; -- cgit v1.2.2 From e815f0a84fc9a98e5cc3ef0b520122e5e18520e7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jonathan=20Neusch=C3=A4fer?= Date: Mon, 21 Mar 2011 20:24:47 +0100 Subject: sched.h: Fix a typo ("its") MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The sentence uses the possessive pronoun, which is spelled without an apostrophe. Signed-off-by: Jonathan Neuschäfer Cc: Jiri Kosina Cc: Peter Zijlstra LKML-Reference: <1300735487-2406-1-git-send-email-j.neuschaefer@gmx.net> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index c15936fe998b..e89f1292c301 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -516,7 +516,7 @@ struct thread_group_cputimer { struct autogroup; /* - * NOTE! "signal_struct" does not have it's own + * NOTE! "signal_struct" does not have its own * locking, because a shared signal_struct always * implies a shared sighand_struct, so locking * sighand_struct is always a proper superset of -- cgit v1.2.2 From 7ffd4ca7a2cdd7a18f0b499a4e9e0e7cf36ba018 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 23 Mar 2011 16:42:35 -0700 Subject: memcg: convert uncharge batching from bytes to page granularity We never uncharge subpage quantities. Signed-off-by: Johannes Weiner Acked-by: KAMEZAWA Hiroyuki Cc: Daisuke Nishimura Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4b601be3dace..98fc7ed4b191 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1524,8 +1524,8 @@ struct task_struct { struct memcg_batch_info { int do_batch; /* incremented when batch uncharge started */ struct mem_cgroup *memcg; /* target memcg of uncharge */ - unsigned long bytes; /* uncharged usage */ - unsigned long memsw_bytes; /* uncharged mem+swap usage */ + unsigned long nr_pages; /* uncharged usage */ + unsigned long memsw_nr_pages; /* uncharged mem+swap usage */ } memcg_batch; #endif }; -- cgit v1.2.2 From 25985edcedea6396277003854657b5f3cb31a628 Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Wed, 30 Mar 2011 22:57:33 -0300 Subject: Fix common misspellings Fixes generated by 'codespell' and manually reviewed. Signed-off-by: Lucas De Marchi --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 83bd2e2982fc..4ec2c027e92c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -854,7 +854,7 @@ extern int __weak arch_sd_sibiling_asym_packing(void); /* * Optimise SD flags for power savings: - * SD_BALANCE_NEWIDLE helps agressive task consolidation and power savings. + * SD_BALANCE_NEWIDLE helps aggressive task consolidation and power savings. * Keep default SD flags if sched_{smt,mc}_power_saving=0 */ -- cgit v1.2.2 From 4471a675dfc7ca676c165079e91c712b09dc9ce4 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Thu, 14 Apr 2011 15:22:09 -0700 Subject: brk: COMPAT_BRK: fix detection of randomized brk 5520e89 ("brk: fix min_brk lower bound computation for COMPAT_BRK") tried to get the whole logic of brk randomization for legacy (libc5-based) applications finally right. It turns out that the way to detect whether brk has actually been randomized in the end or not introduced by that patch still doesn't work for those binaries, as reported by Geert: : /sbin/init from my old m68k ramdisk exists prematurely. : : Before the patch: : : | brk(0x80005c8e) = 0x80006000 : : After the patch: : : | brk(0x80005c8e) = 0x80005c8e : : Old libc5 considers brk() to have failed if the return value is not : identical to the requested value. I don't like it, but currently see no better option than a bit flag in task_struct to catch the CONFIG_COMPAT_BRK && randomize_va_space == 2 case. Signed-off-by: Jiri Kosina Tested-by: Geert Uytterhoeven Reported-by: Geert Uytterhoeven Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4ec2c027e92c..18d63cea2848 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1254,6 +1254,9 @@ struct task_struct { #endif struct mm_struct *mm, *active_mm; +#ifdef CONFIG_COMPAT_BRK + unsigned brk_randomized:1; +#endif #if defined(SPLIT_RSS_COUNTING) struct task_rss_stat rss_stat; #endif -- cgit v1.2.2 From bf26c018490c2fce7fe9b629083b96ce0e6ad019 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 7 Apr 2011 16:53:20 +0200 Subject: ptrace: Prepare to fix racy accesses on task breakpoints When a task is traced and is in a stopped state, the tracer may execute a ptrace request to examine the tracee state and get its task struct. Right after, the tracee can be killed and thus its breakpoints released. This can happen concurrently when the tracer is in the middle of reading or modifying these breakpoints, leading to dereferencing a freed pointer. Hence, to prepare the fix, create a generic breakpoint reference holding API. When a reference on the breakpoints of a task is held, the breakpoints won't be released until the last reference is dropped. After that, no more ptrace request on the task's breakpoints can be serviced for the tracer. Reported-by: Oleg Nesterov Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Will Deacon Cc: Prasad Cc: Paul Mundt Cc: v2.6.33.. Link: http://lkml.kernel.org/r/1302284067-7860-2-git-send-email-fweisbec@gmail.com --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 18d63cea2848..781abd137673 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1537,6 +1537,9 @@ struct task_struct { unsigned long memsw_nr_pages; /* uncharged mem+swap usage */ } memcg_batch; #endif +#ifdef CONFIG_HAVE_HW_BREAKPOINT + atomic_t ptrace_bp_refcnt; +#endif }; /* Future-safe accessor for struct task_struct's cpus_allowed. */ -- cgit v1.2.2