From f41d911f8c49a5d65c86504c19e8204bb605c4fd Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 22 Aug 2009 13:56:52 -0700 Subject: rcu: Merge preemptable-RCU functionality into hierarchical RCU Create a kernel/rcutree_plugin.h file that contains definitions for preemptable RCU (or, under the #else branch of the #ifdef, empty definitions for the classic non-preemptable semantics). These definitions fit into plugins defined in kernel/rcutree.c for this purpose. This variant of preemptable RCU uses a new algorithm whose read-side expense is roughly that of classic hierarchical RCU under CONFIG_PREEMPT. This new algorithm's update-side expense is similar to that of classic hierarchical RCU, and, in absence of read-side preemption or blocking, is exactly that of classic hierarchical RCU. Perhaps more important, this new algorithm has a much simpler implementation, saving well over 1,000 lines of code compared to mainline's implementation of preemptable RCU, which will hopefully be retired in favor of this new algorithm. The simplifications are obtained by maintaining per-task nesting state for running tasks, and using a simple lock-protected algorithm to handle accounting when tasks block within RCU read-side critical sections, making use of lessons learned while creating numerous user-level RCU implementations over the past 18 months. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: akpm@linux-foundation.org Cc: mathieu.desnoyers@polymtl.ca Cc: josht@linux.vnet.ibm.com Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org LKML-Reference: <12509746134003-git-send-email-> Signed-off-by: Ingo Molnar --- include/linux/init_task.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux/init_task.h') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 7fc01b13be43..971a968831bf 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -94,6 +94,20 @@ extern struct group_info init_groups; # define CAP_INIT_BSET CAP_INIT_EFF_SET #endif +#ifdef CONFIG_PREEMPT_RCU +#define INIT_TASK_RCU_PREEMPT(tsk) \ + .rcu_read_lock_nesting = 0, \ + .rcu_flipctr_idx = 0, +#elif defined(CONFIG_TREE_PREEMPT_RCU) +#define INIT_TASK_RCU_PREEMPT(tsk) \ + .rcu_read_lock_nesting = 0, \ + .rcu_read_unlock_special = 0, \ + .rcu_blocked_cpu = -1, \ + .rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry), +#else +#define INIT_TASK_RCU_PREEMPT(tsk) +#endif + extern struct cred init_cred; #ifdef CONFIG_PERF_COUNTERS @@ -173,6 +187,7 @@ extern struct cred init_cred; INIT_LOCKDEP \ INIT_FTRACE_GRAPH \ INIT_TRACE_RECURSION \ + INIT_TASK_RCU_PREEMPT(tsk) \ } -- cgit v1.2.3 From 6b3ef48adf847f7adf11c870e3ffacac150f1564 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 22 Aug 2009 13:56:53 -0700 Subject: rcu: Remove CONFIG_PREEMPT_RCU Now that CONFIG_TREE_PREEMPT_RCU is in place, there is no further need for CONFIG_PREEMPT_RCU. Remove it, along with whatever subtle bugs it may (or may not) contain. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: akpm@linux-foundation.org Cc: mathieu.desnoyers@polymtl.ca Cc: josht@linux.vnet.ibm.com Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org LKML-Reference: <125097461396-git-send-email-> Signed-off-by: Ingo Molnar --- include/linux/init_task.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux/init_task.h') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 971a968831bf..79d4baee31b6 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -94,11 +94,7 @@ extern struct group_info init_groups; # define CAP_INIT_BSET CAP_INIT_EFF_SET #endif -#ifdef CONFIG_PREEMPT_RCU -#define INIT_TASK_RCU_PREEMPT(tsk) \ - .rcu_read_lock_nesting = 0, \ - .rcu_flipctr_idx = 0, -#elif defined(CONFIG_TREE_PREEMPT_RCU) +#ifdef CONFIG_TREE_PREEMPT_RCU #define INIT_TASK_RCU_PREEMPT(tsk) \ .rcu_read_lock_nesting = 0, \ .rcu_read_unlock_special = 0, \ -- cgit v1.2.3 From dd5d19bafd90d33043a4a14b2e2d98612caa293c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 27 Aug 2009 14:58:16 -0700 Subject: rcu: Create rcutree plugins to handle hotplug CPU for multi-level trees When offlining CPUs from a multi-level tree, there is the possibility of offlining the last CPU from a given node when there are preempted RCU read-side critical sections that started life on one of the CPUs on that node. In this case, the corresponding tasks will be enqueued via the task_struct's rcu_node_entry list_head onto one of the rcu_node's blocked_tasks[] lists. These tasks need to be moved somewhere else so that they will prevent the current grace period from ending. That somewhere is the root rcu_node. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: akpm@linux-foundation.org Cc: mathieu.desnoyers@polymtl.ca Cc: josht@linux.vnet.ibm.com Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org LKML-Reference: <20090827215816.GA30472@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- include/linux/init_task.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/init_task.h') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 79d4baee31b6..9e7f2e8fc66e 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -98,7 +98,7 @@ extern struct group_info init_groups; #define INIT_TASK_RCU_PREEMPT(tsk) \ .rcu_read_lock_nesting = 0, \ .rcu_read_unlock_special = 0, \ - .rcu_blocked_cpu = -1, \ + .rcu_blocked_node = NULL, \ .rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry), #else #define INIT_TASK_RCU_PREEMPT(tsk) -- cgit v1.2.3 From cdd6c482c9ff9c55475ee7392ec8f672eddb7be6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 21 Sep 2009 12:02:48 +0200 Subject: perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian Acked-by: Peter Zijlstra Acked-by: Paul Mackerras Reviewed-by: Arjan van de Ven Cc: Mike Galbraith Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Steven Rostedt Cc: Benjamin Herrenschmidt Cc: David Howells Cc: Kyle McMartin Cc: Martin Schwidefsky Cc: "David S. Miller" Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/init_task.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux/init_task.h') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 9e7f2e8fc66e..21a6f5d9af22 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -106,13 +106,13 @@ extern struct group_info init_groups; extern struct cred init_cred; -#ifdef CONFIG_PERF_COUNTERS -# define INIT_PERF_COUNTERS(tsk) \ - .perf_counter_mutex = \ - __MUTEX_INITIALIZER(tsk.perf_counter_mutex), \ - .perf_counter_list = LIST_HEAD_INIT(tsk.perf_counter_list), +#ifdef CONFIG_PERF_EVENTS +# define INIT_PERF_EVENTS(tsk) \ + .perf_event_mutex = \ + __MUTEX_INITIALIZER(tsk.perf_event_mutex), \ + .perf_event_list = LIST_HEAD_INIT(tsk.perf_event_list), #else -# define INIT_PERF_COUNTERS(tsk) +# define INIT_PERF_EVENTS(tsk) #endif /* @@ -178,7 +178,7 @@ extern struct cred init_cred; }, \ .dirties = INIT_PROP_LOCAL_SINGLE(dirties), \ INIT_IDS \ - INIT_PERF_COUNTERS(tsk) \ + INIT_PERF_EVENTS(tsk) \ INIT_TRACE_IRQFLAGS \ INIT_LOCKDEP \ INIT_FTRACE_GRAPH \ -- cgit v1.2.3