From 1bd845bcb41d5b7f83745e0cb99273eb376f2ec5 Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Fri, 8 Sep 2017 20:57:09 +0200 Subject: padata: set cpu_index of unused CPUs to -1 The parallel queue per-cpu data structure gets initialized only for CPUs in the 'pcpu' CPU mask set. This is not sufficient as the reorder timer may run on a different CPU and might wrongly decide it's the target CPU for the next reorder item as per-cpu memory gets memset(0) and we might be waiting for the first CPU in cpumask.pcpu, i.e. cpu_index 0. Make the '__this_cpu_read(pd->pqueue->cpu_index) == next_queue->cpu_index' compare in padata_get_next() fail in this case by initializing the cpu_index member of all per-cpu parallel queues. Use -1 for unused ones. Signed-off-by: Mathias Krause Signed-off-by: Herbert Xu --- kernel/padata.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel/padata.c') diff --git a/kernel/padata.c b/kernel/padata.c index 868f947166d7..1b9b4bac4a9b 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -384,8 +384,14 @@ static void padata_init_pqueues(struct parallel_data *pd) struct padata_parallel_queue *pqueue; cpu_index = 0; - for_each_cpu(cpu, pd->cpumask.pcpu) { + for_each_possible_cpu(cpu) { pqueue = per_cpu_ptr(pd->pqueue, cpu); + + if (!cpumask_test_cpu(cpu, pd->cpumask.pcpu)) { + pqueue->cpu_index = -1; + continue; + } + pqueue->pd = pd; pqueue->cpu_index = cpu_index; cpu_index++; -- cgit v1.2.3 From cf5868c8a22dc2854b96e9569064bb92365549ca Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Fri, 8 Sep 2017 20:57:10 +0200 Subject: padata: ensure the reorder timer callback runs on the correct CPU The reorder timer function runs on the CPU where the timer interrupt was handled which is not necessarily one of the CPUs of the 'pcpu' CPU mask set. Ensure the padata_reorder() callback runs on the correct CPU, which is one in the 'pcpu' CPU mask set and, preferrably, the next expected one. Do so by comparing the current CPU with the expected target CPU. If they match, call padata_reorder() right away. If they differ, schedule a work item on the target CPU that does the padata_reorder() call for us. Signed-off-by: Mathias Krause Signed-off-by: Herbert Xu --- kernel/padata.c | 43 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 42 insertions(+), 1 deletion(-) (limited to 'kernel/padata.c') diff --git a/kernel/padata.c b/kernel/padata.c index 1b9b4bac4a9b..b4066147bce4 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -275,11 +275,51 @@ static void padata_reorder(struct parallel_data *pd) return; } +static void invoke_padata_reorder(struct work_struct *work) +{ + struct padata_parallel_queue *pqueue; + struct parallel_data *pd; + + local_bh_disable(); + pqueue = container_of(work, struct padata_parallel_queue, reorder_work); + pd = pqueue->pd; + padata_reorder(pd); + local_bh_enable(); +} + static void padata_reorder_timer(unsigned long arg) { struct parallel_data *pd = (struct parallel_data *)arg; + unsigned int weight; + int target_cpu, cpu; - padata_reorder(pd); + cpu = get_cpu(); + + /* We don't lock pd here to not interfere with parallel processing + * padata_reorder() calls on other CPUs. We just need any CPU out of + * the cpumask.pcpu set. It would be nice if it's the right one but + * it doesn't matter if we're off to the next one by using an outdated + * pd->processed value. + */ + weight = cpumask_weight(pd->cpumask.pcpu); + target_cpu = padata_index_to_cpu(pd, pd->processed % weight); + + /* ensure to call the reorder callback on the correct CPU */ + if (cpu != target_cpu) { + struct padata_parallel_queue *pqueue; + struct padata_instance *pinst; + + /* The timer function is serialized wrt itself -- no locking + * needed. + */ + pinst = pd->pinst; + pqueue = per_cpu_ptr(pd->pqueue, target_cpu); + queue_work_on(target_cpu, pinst->wq, &pqueue->reorder_work); + } else { + padata_reorder(pd); + } + + put_cpu(); } static void padata_serial_worker(struct work_struct *serial_work) @@ -399,6 +439,7 @@ static void padata_init_pqueues(struct parallel_data *pd) __padata_list_init(&pqueue->reorder); __padata_list_init(&pqueue->parallel); INIT_WORK(&pqueue->work, padata_parallel_worker); + INIT_WORK(&pqueue->reorder_work, invoke_padata_reorder); atomic_set(&pqueue->num_obj, 0); } } -- cgit v1.2.3 From 350ef88e7e922354f82a931897ad4a4ce6c686ff Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Fri, 8 Sep 2017 20:57:11 +0200 Subject: padata: ensure padata_do_serial() runs on the correct CPU If the algorithm we're parallelizing is asynchronous we might change CPUs between padata_do_parallel() and padata_do_serial(). However, we don't expect this to happen as we need to enqueue the padata object into the per-cpu reorder queue we took it from, i.e. the same-cpu's parallel queue. Ensure we're not switching CPUs for a given padata object by tracking the CPU within the padata object. If the serial callback gets called on the wrong CPU, defer invoking padata_reorder() via a kernel worker on the CPU we're expected to run on. Signed-off-by: Mathias Krause Signed-off-by: Herbert Xu --- kernel/padata.c | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'kernel/padata.c') diff --git a/kernel/padata.c b/kernel/padata.c index b4066147bce4..f262c9a4e70a 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -131,6 +131,7 @@ int padata_do_parallel(struct padata_instance *pinst, padata->cb_cpu = cb_cpu; target_cpu = padata_cpu_hash(pd); + padata->cpu = target_cpu; queue = per_cpu_ptr(pd->pqueue, target_cpu); spin_lock(&queue->parallel.lock); @@ -363,10 +364,21 @@ void padata_do_serial(struct padata_priv *padata) int cpu; struct padata_parallel_queue *pqueue; struct parallel_data *pd; + int reorder_via_wq = 0; pd = padata->pd; cpu = get_cpu(); + + /* We need to run on the same CPU padata_do_parallel(.., padata, ..) + * was called on -- or, at least, enqueue the padata object into the + * correct per-cpu queue. + */ + if (cpu != padata->cpu) { + reorder_via_wq = 1; + cpu = padata->cpu; + } + pqueue = per_cpu_ptr(pd->pqueue, cpu); spin_lock(&pqueue->reorder.lock); @@ -376,7 +388,13 @@ void padata_do_serial(struct padata_priv *padata) put_cpu(); - padata_reorder(pd); + /* If we're running on the wrong CPU, call padata_reorder() via a + * kernel worker. + */ + if (reorder_via_wq) + queue_work_on(cpu, pd->pinst->wq, &pqueue->reorder_work); + else + padata_reorder(pd); } EXPORT_SYMBOL(padata_do_serial); -- cgit v1.2.3 From e99e88a9d2b067465adaa9c111ada99a041bef9a Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 14:43:17 -0700 Subject: treewide: setup_timer() -> timer_setup() This converts all remaining cases of the old setup_timer() API into using timer_setup(), where the callback argument is the structure already holding the struct timer_list. These should have no behavioral changes, since they just change which pointer is passed into the callback with the same available pointers after conversion. It handles the following examples, in addition to some other variations. Casting from unsigned long: void my_callback(unsigned long data) { struct something *ptr = (struct something *)data; ... } ... setup_timer(&ptr->my_timer, my_callback, ptr); and forced object casts: void my_callback(struct something *ptr) { ... } ... setup_timer(&ptr->my_timer, my_callback, (unsigned long)ptr); become: void my_callback(struct timer_list *t) { struct something *ptr = from_timer(ptr, t, my_timer); ... } ... timer_setup(&ptr->my_timer, my_callback, 0); Direct function assignments: void my_callback(unsigned long data) { struct something *ptr = (struct something *)data; ... } ... ptr->my_timer.function = my_callback; have a temporary cast added, along with converting the args: void my_callback(struct timer_list *t) { struct something *ptr = from_timer(ptr, t, my_timer); ... } ... ptr->my_timer.function = (TIMER_FUNC_TYPE)my_callback; And finally, callbacks without a data assignment: void my_callback(unsigned long data) { ... } ... setup_timer(&ptr->my_timer, my_callback, 0); have their argument renamed to verify they're unused during conversion: void my_callback(struct timer_list *unused) { ... } ... timer_setup(&ptr->my_timer, my_callback, 0); The conversion is done with the following Coccinelle script: spatch --very-quiet --all-includes --include-headers \ -I ./arch/x86/include -I ./arch/x86/include/generated \ -I ./include -I ./arch/x86/include/uapi \ -I ./arch/x86/include/generated/uapi -I ./include/uapi \ -I ./include/generated/uapi --include ./include/linux/kconfig.h \ --dir . \ --cocci-file ~/src/data/timer_setup.cocci @fix_address_of@ expression e; @@ setup_timer( -&(e) +&e , ...) // Update any raw setup_timer() usages that have a NULL callback, but // would otherwise match change_timer_function_usage, since the latter // will update all function assignments done in the face of a NULL // function initialization in setup_timer(). @change_timer_function_usage_NULL@ expression _E; identifier _timer; type _cast_data; @@ ( -setup_timer(&_E->_timer, NULL, _E); +timer_setup(&_E->_timer, NULL, 0); | -setup_timer(&_E->_timer, NULL, (_cast_data)_E); +timer_setup(&_E->_timer, NULL, 0); | -setup_timer(&_E._timer, NULL, &_E); +timer_setup(&_E._timer, NULL, 0); | -setup_timer(&_E._timer, NULL, (_cast_data)&_E); +timer_setup(&_E._timer, NULL, 0); ) @change_timer_function_usage@ expression _E; identifier _timer; struct timer_list _stl; identifier _callback; type _cast_func, _cast_data; @@ ( -setup_timer(&_E->_timer, _callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, &_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, &_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)&_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)&_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E._timer, _callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, &_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, &_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | _E->_timer@_stl.function = _callback; | _E->_timer@_stl.function = &_callback; | _E->_timer@_stl.function = (_cast_func)_callback; | _E->_timer@_stl.function = (_cast_func)&_callback; | _E._timer@_stl.function = _callback; | _E._timer@_stl.function = &_callback; | _E._timer@_stl.function = (_cast_func)_callback; | _E._timer@_stl.function = (_cast_func)&_callback; ) // callback(unsigned long arg) @change_callback_handle_cast depends on change_timer_function_usage@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _origtype; identifier _origarg; type _handletype; identifier _handle; @@ void _callback( -_origtype _origarg +struct timer_list *t ) { ( ... when != _origarg _handletype *_handle = -(_handletype *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle = -(void *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle; ... when != _handle _handle = -(_handletype *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle; ... when != _handle _handle = -(void *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg ) } // callback(unsigned long arg) without existing variable @change_callback_handle_cast_no_arg depends on change_timer_function_usage && !change_callback_handle_cast@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _origtype; identifier _origarg; type _handletype; @@ void _callback( -_origtype _origarg +struct timer_list *t ) { + _handletype *_origarg = from_timer(_origarg, t, _timer); + ... when != _origarg - (_handletype *)_origarg + _origarg ... when != _origarg } // Avoid already converted callbacks. @match_callback_converted depends on change_timer_function_usage && !change_callback_handle_cast && !change_callback_handle_cast_no_arg@ identifier change_timer_function_usage._callback; identifier t; @@ void _callback(struct timer_list *t) { ... } // callback(struct something *handle) @change_callback_handle_arg depends on change_timer_function_usage && !match_callback_converted && !change_callback_handle_cast && !change_callback_handle_cast_no_arg@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _handletype; identifier _handle; @@ void _callback( -_handletype *_handle +struct timer_list *t ) { + _handletype *_handle = from_timer(_handle, t, _timer); ... } // If change_callback_handle_arg ran on an empty function, remove // the added handler. @unchange_callback_handle_arg depends on change_timer_function_usage && change_callback_handle_arg@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _handletype; identifier _handle; identifier t; @@ void _callback(struct timer_list *t) { - _handletype *_handle = from_timer(_handle, t, _timer); } // We only want to refactor the setup_timer() data argument if we've found // the matching callback. This undoes changes in change_timer_function_usage. @unchange_timer_function_usage depends on change_timer_function_usage && !change_callback_handle_cast && !change_callback_handle_cast_no_arg && !change_callback_handle_arg@ expression change_timer_function_usage._E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type change_timer_function_usage._cast_data; @@ ( -timer_setup(&_E->_timer, _callback, 0); +setup_timer(&_E->_timer, _callback, (_cast_data)_E); | -timer_setup(&_E._timer, _callback, 0); +setup_timer(&_E._timer, _callback, (_cast_data)&_E); ) // If we fixed a callback from a .function assignment, fix the // assignment cast now. @change_timer_function_assignment depends on change_timer_function_usage && (change_callback_handle_cast || change_callback_handle_cast_no_arg || change_callback_handle_arg)@ expression change_timer_function_usage._E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type _cast_func; typedef TIMER_FUNC_TYPE; @@ ( _E->_timer.function = -_callback +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -&_callback +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -(_cast_func)_callback; +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -(_cast_func)&_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -&_callback; +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -(_cast_func)_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -(_cast_func)&_callback +(TIMER_FUNC_TYPE)_callback ; ) // Sometimes timer functions are called directly. Replace matched args. @change_timer_function_calls depends on change_timer_function_usage && (change_callback_handle_cast || change_callback_handle_cast_no_arg || change_callback_handle_arg)@ expression _E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type _cast_data; @@ _callback( ( -(_cast_data)_E +&_E->_timer | -(_cast_data)&_E +&_E._timer | -_E +&_E->_timer ) ) // If a timer has been configured without a data argument, it can be // converted without regard to the callback argument, since it is unused. @match_timer_function_unused_data@ expression _E; identifier _timer; identifier _callback; @@ ( -setup_timer(&_E->_timer, _callback, 0); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, 0L); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, 0UL); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0L); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0UL); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_timer, _callback, 0); +timer_setup(&_timer, _callback, 0); | -setup_timer(&_timer, _callback, 0L); +timer_setup(&_timer, _callback, 0); | -setup_timer(&_timer, _callback, 0UL); +timer_setup(&_timer, _callback, 0); | -setup_timer(_timer, _callback, 0); +timer_setup(_timer, _callback, 0); | -setup_timer(_timer, _callback, 0L); +timer_setup(_timer, _callback, 0); | -setup_timer(_timer, _callback, 0UL); +timer_setup(_timer, _callback, 0); ) @change_callback_unused_data depends on match_timer_function_unused_data@ identifier match_timer_function_unused_data._callback; type _origtype; identifier _origarg; @@ void _callback( -_origtype _origarg +struct timer_list *unused ) { ... when != _origarg } Signed-off-by: Kees Cook --- kernel/padata.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/padata.c') diff --git a/kernel/padata.c b/kernel/padata.c index f262c9a4e70a..57c0074d50cc 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -288,9 +288,9 @@ static void invoke_padata_reorder(struct work_struct *work) local_bh_enable(); } -static void padata_reorder_timer(unsigned long arg) +static void padata_reorder_timer(struct timer_list *t) { - struct parallel_data *pd = (struct parallel_data *)arg; + struct parallel_data *pd = from_timer(pd, t, timer); unsigned int weight; int target_cpu, cpu; @@ -485,7 +485,7 @@ static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst, padata_init_pqueues(pd); padata_init_squeues(pd); - setup_timer(&pd->timer, padata_reorder_timer, (unsigned long)pd); + timer_setup(&pd->timer, padata_reorder_timer, 0); atomic_set(&pd->seq_nr, -1); atomic_set(&pd->reorder_objects, 0); atomic_set(&pd->refcnt, 0); -- cgit v1.2.3