From cc5b83a9f884fe8722a275069a5a6fde39988455 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 3 Mar 2010 07:46:59 -0800 Subject: rcu: Add control variables to lockdep_rcu_dereference() diagnostics Add the values of rcu_scheduler_active() and debug_locks() to the lockdep_rcu_dereference() output to help diagnose RCU lockdep splats that occur shortly after the scheduler starts. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <1267631219-8713-4-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- kernel/lockdep.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/lockdep.c') diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 0c30d0455de1..681bc2e1e187 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -3822,6 +3822,7 @@ void lockdep_rcu_dereference(const char *file, const int line) printk("%s:%d invoked rcu_dereference_check() without protection!\n", file, line); printk("\nother info that might help us debug this:\n\n"); + printk("\nrcu_scheduler_active = %d, debug_locks = %d\n", rcu_scheduler_active, debug_locks); lockdep_print_held_locks(curr); printk("\nstack backtrace:\n"); dump_stack(); -- cgit v1.2.1 From db2c4c7791cd04512093d05afc693c3511a65fd7 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 2 Feb 2010 23:34:40 +0100 Subject: lockdep: Move lock events under lockdep recursion protection There are rcu locked read side areas in the path where we submit a trace event. And these rcu_read_(un)lock() trigger lock events, which create recursive events. One pair in do_perf_sw_event: __lock_acquire | |--96.11%-- lock_acquire | | | |--27.21%-- do_perf_sw_event | | perf_tp_event | | | | | |--49.62%-- ftrace_profile_lock_release | | | lock_release | | | | | | | |--33.85%-- _raw_spin_unlock Another pair in perf_output_begin/end: __lock_acquire |--23.40%-- perf_output_begin | | __perf_event_overflow | | perf_swevent_overflow | | perf_swevent_add | | perf_swevent_ctx_event | | do_perf_sw_event | | perf_tp_event | | | | | |--55.37%-- ftrace_profile_lock_acquire | | | lock_acquire | | | | | | | |--37.31%-- _raw_spin_lock The problem is not that much the trace recursion itself, as we have a recursion protection already (though it's always wasteful to recurse). But the trace events are outside the lockdep recursion protection, then each lockdep event triggers a lock trace, which will trigger two other lockdep events. Here the recursive lock trace event won't be taken because of the trace recursion, so the recursion stops there but lockdep will still analyse these new events: To sum up, for each lockdep events we have: lock_*() | trace lock_acquire | ----- rcu_read_lock() | | | lock_acquire() | | | trace_lock_acquire() (stopped) | | | lockdep analyze | ----- rcu_read_unlock() | lock_release | trace_lock_release() (stopped) | lockdep analyze And you can repeat the above two times as we have two rcu read side sections when we submit an event. This is fixed in this patch by moving the lock trace event under the lockdep recursion protection. Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Steven Rostedt Cc: Paul Mackerras Cc: Hitoshi Mitake Cc: Li Zefan Cc: Lai Jiangshan Cc: Masami Hiramatsu Cc: Jens Axboe --- kernel/lockdep.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'kernel/lockdep.c') diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 0c30d0455de1..65b5f5b7c298 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -3211,8 +3211,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, { unsigned long flags; - trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip); - if (unlikely(current->lockdep_recursion)) return; @@ -3220,6 +3218,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, check_flags(flags); current->lockdep_recursion = 1; + trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip); __lock_acquire(lock, subclass, trylock, read, check, irqs_disabled_flags(flags), nest_lock, ip, 0); current->lockdep_recursion = 0; @@ -3232,14 +3231,13 @@ void lock_release(struct lockdep_map *lock, int nested, { unsigned long flags; - trace_lock_release(lock, nested, ip); - if (unlikely(current->lockdep_recursion)) return; raw_local_irq_save(flags); check_flags(flags); current->lockdep_recursion = 1; + trace_lock_release(lock, nested, ip); __lock_release(lock, nested, ip); current->lockdep_recursion = 0; raw_local_irq_restore(flags); @@ -3413,8 +3411,6 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; - trace_lock_contended(lock, ip); - if (unlikely(!lock_stat)) return; @@ -3424,6 +3420,7 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip) raw_local_irq_save(flags); check_flags(flags); current->lockdep_recursion = 1; + trace_lock_contended(lock, ip); __lock_contended(lock, ip); current->lockdep_recursion = 0; raw_local_irq_restore(flags); -- cgit v1.2.1 From 10fad5e46f6c7bdfb01b1a012380a38e3c6ab346 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 10 Mar 2010 18:57:54 +0900 Subject: percpu, module: implement and use is_kernel/module_percpu_address() lockdep has custom code to check whether a pointer belongs to static percpu area which is somewhat broken. Implement proper is_kernel/module_percpu_address() and replace the custom code. On UP, percpu variables are regular static variables and can't be distinguished from them. Always return %false on UP. Signed-off-by: Tejun Heo Acked-by: Peter Zijlstra Cc: Rusty Russell Cc: Ingo Molnar --- kernel/lockdep.c | 21 +++++---------------- 1 file changed, 5 insertions(+), 16 deletions(-) (limited to 'kernel/lockdep.c') diff --git a/kernel/lockdep.c b/kernel/lockdep.c index c927a549db2c..9bbb9c841e48 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -582,9 +582,6 @@ static int static_obj(void *obj) unsigned long start = (unsigned long) &_stext, end = (unsigned long) &_end, addr = (unsigned long) obj; -#ifdef CONFIG_SMP - int i; -#endif /* * static variable? @@ -595,24 +592,16 @@ static int static_obj(void *obj) if (arch_is_kernel_data(addr)) return 1; -#ifdef CONFIG_SMP /* - * percpu var? + * in-kernel percpu var? */ - for_each_possible_cpu(i) { - start = (unsigned long) &__per_cpu_start + per_cpu_offset(i); - end = (unsigned long) &__per_cpu_start + PERCPU_ENOUGH_ROOM - + per_cpu_offset(i); - - if ((addr >= start) && (addr < end)) - return 1; - } -#endif + if (is_kernel_percpu_address(addr)) + return 1; /* - * module var? + * module static or percpu var? */ - return is_module_address(addr); + return is_module_address(addr) || is_module_percpu_address(addr); } /* -- cgit v1.2.1 From 5a0e3ad6af8660be21ca98a971cd00f331318c05 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 24 Mar 2010 17:04:11 +0900 Subject: include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo Guess-its-ok-by: Christoph Lameter Cc: Ingo Molnar Cc: Lee Schermerhorn --- kernel/lockdep.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/lockdep.c') diff --git a/kernel/lockdep.c b/kernel/lockdep.c index c927a549db2c..367f72452ff4 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -43,6 +43,7 @@ #include #include #include +#include #include -- cgit v1.2.1