diff options
| author | Ingo Molnar <mingo@kernel.org> | 2020-07-31 00:15:53 +0200 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2020-07-31 00:15:53 +0200 |
| commit | c1cc4784ce6e8cceff1013709abd74bcbf7fbf24 (patch) | |
| tree | 5eaacf62240ec85a6ad9c7594e8ad8f7f783afc2 | |
| parent | 92ed301919932f777713b9172e525674157e983d (diff) | |
| parent | 13625c0a4074d3bab61b1dc70a828b574255f339 (diff) | |
Merge branch 'for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/rcucore-rcu-2020-08-03
Pull the v5.9 RCU bits from Paul E. McKenney:
- Documentation updates
- Miscellaneous fixes
- kfree_rcu updates
- RCU tasks updates
- Read-side scalability tests
- SRCU updates
- Torture-test updates
Signed-off-by: Ingo Molnar <mingo@kernel.org>
61 files changed, 2395 insertions, 680 deletions
diff --git a/Documentation/RCU/Design/Requirements/Requirements.rst b/Documentation/RCU/Design/Requirements/Requirements.rst index 75b8ca007a11..a69b5c43a10c 100644 --- a/Documentation/RCU/Design/Requirements/Requirements.rst +++ b/Documentation/RCU/Design/Requirements/Requirements.rst @@ -2583,7 +2583,12 @@ not work to have these markers in the trampoline itself, because there would need to be instructions following ``rcu_read_unlock()``. Although ``synchronize_rcu()`` would guarantee that execution reached the ``rcu_read_unlock()``, it would not be able to guarantee that execution -had completely left the trampoline. +had completely left the trampoline. Worse yet, in some situations +the trampoline's protection must extend a few instructions *prior* to +execution reaching the trampoline. For example, these few instructions +might calculate the address of the trampoline, so that entering the +trampoline would be pre-ordained a surprisingly long time before execution +actually reached the trampoline itself. The solution, in the form of `Tasks RCU <https://lwn.net/Articles/607117/>`__, is to have implicit read-side diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.rst index e98ff261a438..2efed9926c3f 100644 --- a/Documentation/RCU/checklist.txt +++ b/Documentation/RCU/checklist.rst @@ -1,4 +1,8 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================ Review Checklist for RCU Patches +================================ This document contains a checklist for producing and reviewing patches @@ -411,18 +415,21 @@ over a rather long period of time, but improvements are always welcome! __rcu sparse checks to validate your RCU code. These can help find problems as follows: - CONFIG_PROVE_LOCKING: check that accesses to RCU-protected data + CONFIG_PROVE_LOCKING: + check that accesses to RCU-protected data structures are carried out under the proper RCU read-side critical section, while holding the right combination of locks, or whatever other conditions are appropriate. - CONFIG_DEBUG_OBJECTS_RCU_HEAD: check that you don't pass the + CONFIG_DEBUG_OBJECTS_RCU_HEAD: + check that you don't pass the same object to call_rcu() (or friends) before an RCU grace period has elapsed since the last time that you passed that same object to call_rcu() (or friends). - __rcu sparse checks: tag the pointer to the RCU-protected data + __rcu sparse checks: + tag the pointer to the RCU-protected data structure with __rcu, and sparse will warn you if you access that pointer without the services of one of the variants of rcu_dereference(). @@ -442,8 +449,8 @@ over a rather long period of time, but improvements are always welcome! You instead need to use one of the barrier functions: - o call_rcu() -> rcu_barrier() - o call_srcu() -> srcu_barrier() + - call_rcu() -> rcu_barrier() + - call_srcu() -> srcu_barrier() However, these barrier functions are absolutely -not- guaranteed to wait for a grace period. In fact, if there are no call_rcu() diff --git a/Documentation/RCU/index.rst b/Documentation/RCU/index.rst index 81a0a1e5f767..e703d3dbe60c 100644 --- a/Documentation/RCU/index.rst +++ b/Documentation/RCU/index.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: GPL-2.0 + .. _rcu_concepts: ============ @@ -8,10 +10,17 @@ RCU concepts :maxdepth: 3 arrayRCU + checklist + lockdep + lockdep-splat rcubarrier rcu_dereference whatisRCU rcu + rculist_nulls + rcuref + torture + stallwarn listRCU NMI-RCU UP diff --git a/Documentation/RCU/lockdep-splat.txt b/Documentation/RCU/lockdep-splat.rst index b8096316fd11..2a5c79db57dc 100644 --- a/Documentation/RCU/lockdep-splat.txt +++ b/Documentation/RCU/lockdep-splat.rst @@ -1,3 +1,9 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================= +Lockdep-RCU Splat +================= + Lockdep-RCU was added to the Linux kernel in early 2010 (http://lwn.net/Articles/371986/). This facility checks for some common misuses of the RCU API, most notably using one of the rcu_dereference() @@ -12,55 +18,54 @@ overwriting or worse. There can of course be false positives, this being the real world and all that. So let's look at an example RCU lockdep splat from 3.0-rc5, one that -has long since been fixed: - -============================= -WARNING: suspicious RCU usage ------------------------------ -block/cfq-iosched.c:2776 suspicious rcu_dereference_protected() usage! - -other info that might help us debug this: - - -rcu_scheduler_active = 1, debug_locks = 0 -3 locks held by scsi_scan_6/1552: - #0: (&shost->scan_mutex){+.+.}, at: [<ffffffff8145efca>] -scsi_scan_host_selected+0x5a/0x150 - #1: (&eq->sysfs_lock){+.+.}, at: [<ffffffff812a5032>] -elevator_exit+0x22/0x60 - #2: (&(&q->__queue_lock)->rlock){-.-.}, at: [<ffffffff812b6233>] -cfq_exit_queue+0x43/0x190 - -stack backtrace: -Pid: 1552, comm: scsi_scan_6 Not tainted 3.0.0-rc5 #17 -Call Trace: - [<ffffffff810abb9b>] lockdep_rcu_dereference+0xbb/0xc0 - [<ffffffff812b6139>] __cfq_exit_single_io_context+0xe9/0x120 - [<ffffffff812b626c>] cfq_exit_queue+0x7c/0x190 - [<ffffffff812a5046>] elevator_exit+0x36/0x60 - [<ffffffff812a802a>] blk_cleanup_queue+0x4a/0x60 - [<ffffffff8145cc09>] scsi_free_queue+0x9/0x10 - [<ffffffff81460944>] __scsi_remove_device+0x84/0xd0 - [<ffffffff8145dca3>] scsi_probe_and_add_lun+0x353/0xb10 - [<ffffffff817da069>] ? error_exit+0x29/0xb0 - [<ffffffff817d98ed>] ? _raw_spin_unlock_irqrestore+0x3d/0x80 - [<ffffffff8145e722>] __scsi_scan_target+0x112/0x680 - [<ffffffff812c690d>] ? trace_hardirqs_off_thunk+0x3a/0x3c - [<ffffffff817da069>] ? error_exit+0x29/0xb0 - [<ffffffff812bcc60>] ? kobject_del+0x40/0x40 - [<ffffffff8145ed16>] scsi_scan_channel+0x86/0xb0 - [<ffffffff8145f0b0>] scsi_scan_host_selected+0x140/0x150 - [<ffffffff8145f149>] do_scsi_scan_host+0x89/0x90 - [<ffffffff8145f170>] do_scan_async+0x20/0x160 - [<ffffffff8145f150>] ? do_scsi_scan_host+0x90/0x90 - [<ffffffff810975b6>] kthread+0xa6/0xb0 - [<ffffffff817db154>] kernel_thread_helper+0x4/0x10 - [<ffffffff81066430>] ? finish_task_switch+0x80/0x110 - [<ffffffff817d9c04>] ? retint_restore_args+0xe/0xe - [<ffffffff81097510>] ? __kthread_init_worker+0x70/0x70 - [<ffffffff817db150>] ? gs_change+0xb/0xb - -Line 2776 of block/cfq-iosched.c in v3.0-rc5 is as follows: +has long since been fixed:: + + ============================= + WARNING: suspicious RCU usage + ----------------------------- + block/cfq-iosched.c:2776 suspicious rcu_dereference_protected() usage! + +other info that might help us debug this:: + + rcu_scheduler_active = 1, debug_locks = 0 + 3 locks held by scsi_scan_6/1552: + #0: (&shost->scan_mutex){+.+.}, at: [<ffffffff8145efca>] + scsi_scan_host_selected+0x5a/0x150 + #1: (&eq->sysfs_lock){+.+.}, at: [<ffffffff812a5032>] + elevator_exit+0x22/0x60 + #2: (&(&q->__queue_lock)->rlock){-.-.}, at: [<ffffffff812b6233>] + cfq_exit_queue+0x43/0x190 + + stack backtrace: + Pid: 1552, comm: scsi_scan_6 Not tainted 3.0.0-rc5 #17 + Call Trace: + [<ffffffff810abb9b>] lockdep_rcu_dereference+0xbb/0xc0 + [<ffffffff812b6139>] __cfq_exit_single_io_context+0xe9/0x120 + [<ffffffff812b626c>] cfq_exit_queue+0x7c/0x190 + [<ffffffff812a5046>] elevator_exit+0x36/0x60 + [<ffffffff812a802a>] blk_cleanup_queue+0x4a/0x60 + [<ffffffff8145cc09>] scsi_free_queue+0x9/0x10 + [<ffffffff81460944>] __scsi_remove_device+0x84/0xd0 + [<ffffffff8145dca3>] scsi_probe_and_add_lun+0x353/0xb10 + [<ffffffff817da069>] ? error_exit+0x29/0xb0 + [<ffffffff817d98ed>] ? _raw_spin_unlock_irqrestore+0x3d/0x80 + [<ffffffff8145e722>] __scsi_scan_target+0x112/0x680 + [<ffffffff812c690d>] ? trace_hardirqs_off_thunk+0x3a/0x3c + [<ffffffff817da069>] ? error_exit+0x29/0xb0 + [<ffffffff812bcc60>] ? kobject_del+0x40/0x40 + [<ffffffff8145ed16>] scsi_scan_channel+0x86/0xb0 + [<ffffffff8145f0b0>] scsi_scan_host_selected+0x140/0x150 + [<ffffffff8145f149>] do_scsi_scan_host+0x89/0x90 + [<ffffffff8145f170>] do_scan_async+0x20/0x160 + [<ffffffff8145f150>] ? do_scsi_scan_host+0x90/0x90 + [<ffffffff810975b6>] kthread+0xa6/0xb0 + [<ffffffff817db154>] kernel_thread_helper+0x4/0x10 + [<ffffffff81066430>] ? finish_task_switch+0x80/0x110 + [<ffffffff817d9c04>] ? retint_restore_args+0xe/0xe + [<ffffffff81097510>] ? __kthread_init_worker+0x70/0x70 + [<ffffffff817db150>] ? gs_change+0xb/0xb + +Line 2776 of block/cfq-iosched.c in v3.0-rc5 is as follows:: if (rcu_dereference(ioc->ioc_data) == cic) { @@ -70,7 +75,7 @@ case. Instead, we hold three locks, one of which might be RCU related. And maybe that lock really does protect this reference. If so, the fix is to inform RCU, perhaps by changing __cfq_exit_single_io_context() to take the struct request_queue "q" from cfq_exit_queue() as an argument, -which would permit us to invoke rcu_dereference_protected as follows: +which would permit us to invoke rcu_dereference_protected as follows:: if (rcu_dereference_protected(ioc->ioc_data, lockdep_is_held(&q->queue_lock)) == cic) { @@ -85,7 +90,7 @@ On the other hand, perhaps we really do need an RCU read-side critical section. In this case, the critical section must span the use of the return value from rcu_dereference(), or at least until there is some reference count incremented or some such. One way to handle this is to -add rcu_read_lock() and rcu_read_unlock() as follows: +add rcu_read_lock() and rcu_read_unlock() as follows:: rcu_read_lock(); if (rcu_dereference(ioc->ioc_data) == cic) { @@ -102,7 +107,7 @@ above lockdep-RCU splat. But in this particular case, we don't actually dereference the pointer returned from rcu_dereference(). Instead, that pointer is just compared to the cic pointer, which means that the rcu_dereference() can be replaced -by rcu_access_pointer() as follows: +by rcu_access_pointer() as follows:: if (rcu_access_pointer(ioc->ioc_data) == cic) { diff --git a/Documentation/RCU/lockdep.txt b/Documentation/RCU/lockdep.rst index 89db949eeca0..f1fc8ae3846a 100644 --- a/Documentation/RCU/lockdep.txt +++ b/Documentation/RCU/lockdep.rst @@ -1,4 +1,8 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================== RCU and lockdep checking +======================== All flavors of RCU have lockdep checking available, so that lockdep is aware of when each task enters and leaves any flavor of RCU read-side @@ -8,7 +12,7 @@ tracking to include RCU state, which can sometimes help when debugging deadlocks and the like. In addition, RCU provides the following primitives that check lockdep's -state: +state:: rcu_read_lock_held() for normal RCU. rcu_read_lock_bh_held() for RCU-bh. @@ -63,7 +67,7 @@ checking of rcu_dereference() primitives: The rcu_dereference_check() check expression can be any boolean expression, but would normally include a lockdep expression. However, any boolean expression can be used. For a moderately ornate example, -consider the following: +consider the following:: file = rcu_dereference_check(fdt->fd[fd], lockdep_is_held(&files->file_lock) || @@ -82,7 +86,7 @@ RCU read-side critical sections, in case (2) the ->file_lock prevents any change from taking place, and finally, in case (3) the current task is the only task accessing the file_struct, again preventing any change from taking place. If the above statement was invoked only from updater -code, it could instead be written as follows: +code, it could instead be written as follows:: file = rcu_dereference_protected(fdt->fd[fd], lockdep_is_held(&files->file_lock) || @@ -105,7 +109,7 @@ false and they are called from outside any RCU read-side critical section. For example, the workqueue for_each_pwq() macro is intended to be used either within an RCU read-side critical section or with wq->mutex held. -It is thus implemented as follows: +It is thus implemented as follows:: #define for_each_pwq(pwq, wq) list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node, diff --git a/Documentation/RCU/rculist_nulls.rst b/Documentation/RCU/rculist_nulls.rst new file mode 100644 index 000000000000..a9fc774bc400 --- /dev/null +++ b/Documentation/RCU/rculist_nulls.rst @@ -0,0 +1,200 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================================= +Using RCU hlist_nulls to protect list and objects +================================================= + +This section describes how to use hlist_nulls to +protect read-mostly linked lists and +objects using SLAB_TYPESAFE_BY_RCU allocations. + +Please read the basics in Documentation/RCU/listRCU.rst + +Using 'nulls' +============= + +Using special makers (called 'nulls') is a convenient way +to solve following problem : + +A typical RCU linked list managing objects which are +allocated with SLAB_TYPESAFE_BY_RCU kmem_cache can +use following algos : + +1) Lookup algo +-------------- + +:: + + rcu_read_lock() + begin: + obj = lockless_lookup(key); + if (obj) { + if (!try_get_ref(obj)) // might fail for free objects + goto begin; + /* + * Because a writer could delete object, and a writer could + * reuse these object before the RCU grace period, we + * must check key after getting the reference on object + */ + if (obj->key != key) { // not the object we expected + put_ref(obj); + goto begin; + } + } + rcu_read_unlock(); + +Beware that lockless_lookup(key) cannot use traditional hlist_for_each_entry_rcu() +but a version with an additional memory barrier (smp_rmb()) + +:: + + lockless_lookup(key) + { + struct hlist_node *node, *next; + for (pos = rcu_dereference((head)->first); + pos && ({ next = pos->next; smp_rmb(); prefetch(next); 1; }) && + ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); + pos = rcu_dereference(next)) + if (obj->key == key) + return obj; + return NULL; + } + +And note the traditional hlist_for_each_entry_rcu() misses this smp_rmb():: + + struct hlist_node *node; + for (pos = rcu_dereference((head)->first); + pos && ({ prefetch(pos->next); 1; }) && + ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); + pos = rcu_dereference(pos->next)) + if (obj->key == key) + return obj; + return NULL; + +Quoting Corey Minyard:: + + "If the object is moved from one list to another list in-between the + time the hash is calculated and the next field is accessed, and the + object has moved to the end of a new list, the traversal will not + complete properly on the list it should have, since the object will + be on the end of the new list and there's not a way to tell it's on a + new list and restart the list traversal. I think that this can be + solved by pre-fetching the "next" field (with proper barriers) before + checking the key." + +2) Insert algo +-------------- + +We need to make sure a reader cannot read the new 'obj->obj_next' value +and previous value of 'obj->key'. Or else, an item could be deleted +from a chain, and inserted into another chain. If new chain was empty +before the move, 'next' pointer is NULL, and lockless reader can +not detect it missed following items in original chain. + +:: + + /* + * Please note that new inserts are done at the head of list, + * not in the middle or end. + */ + obj = kmem_cache_alloc(...); + lock_chain(); // typically a spin_lock() + obj->key = key; + /* + * we need to make sure obj->key is updated before obj->next + * or obj->refcnt + */ + smp_wmb(); + atomic_set(&obj->refcnt, 1); + hlist_add_head_rcu(&obj->obj_node, list); + unlock_chain(); // typically a spin_unlock() + + +3) Remove algo +-------------- +Nothing special here, we can use a standard RCU hlist deletion. +But thanks to SLAB_TYPESAFE_BY_RCU, beware a deleted object can be reused +very very fast (before the end of RCU grace period) + +:: + + if (put_last_reference_on(obj) { + lock_chain(); // typically a spin_lock() + hlist_del_init_rcu(&obj->obj_node); + unlock_chain(); // typically a spin_unlock() + kmem_cache_free(cachep, obj); + } + + + +-------------------------------------------------------------------------- + +Avoiding extra smp_rmb() +======================== + +With hlist_nulls we can avoid extra smp_rmb() in lockless_lookup() +and extra smp_wmb() in insert function. + +For example, if we choose to store the slot number as the 'nulls' +end-of-list marker for each slot of the hash table, we can detect +a race (some writer did a delete and/or a move of an object +to another chain) checking the final 'nulls' value if +the lookup met the end of chain. If final 'nulls' value +is not the slot number, then we must restart the lookup at +the beginning. If the object was moved to the same chain, +then the reader doesn't care : It might eventually +scan the list again without harm. + + +1) lookup algo +-------------- + +:: + + head = &table[slot]; + rcu_read_lock(); + begin: + hlist_nulls_for_each_entry_rcu(obj, node, head, member) { + if (obj->key == key) { + if (!try_get_ref(obj)) // might fail for free objects + goto begin; + if (obj->key != key) { // not the object we expected + put_ref(obj); + goto begin; + } + goto out; + } + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != slot) + goto begin; + obj = NULL; + + out: + rcu_read_unlock(); + +2) Insert function +------------------ + +:: + + /* + * Please note that new inserts are done at the head of list, + * not in the middle or end. + */ + obj = kmem_cache_alloc(cachep); + lock_chain(); // typically a spin_lock() + obj->key = key; + /* + * changes to obj->key must be visible before refcnt one + */ + smp_wmb(); + atomic_set(&obj->refcnt, 1); + /* + * insert obj in RCU way (readers might be traversing chain) + */ + hlist_nulls_add_head_rcu(&obj->obj_node, list); + unlock_chain(); // typically a spin_unlock() diff --git a/Documentation/RCU/rculist_nulls.txt b/Documentation/RCU/rculist_nulls.txt deleted file mode 100644 index 23f115dc87cf..000000000000 --- a/Documentation/RCU/rculist_nulls.txt +++ /dev/null @@ -1,172 +0,0 @@ -Using hlist_nulls to protect read-mostly linked lists and -objects using SLAB_TYPESAFE_BY_RCU allocations. - -Please read the basics in Documentation/RCU/listRCU.rst - -Using special makers (called 'nulls') is a convenient way -to solve following problem : - -A typical RCU linked list managing objects which are -allocated with SLAB_TYPESAFE_BY_RCU kmem_cache can -use following algos : - -1) Lookup algo --------------- -rcu_read_lock() -begin: -obj = lockless_lookup(key); -if (obj) { - if (!try_get_ref(obj)) // might fail for free objects - goto begin; - /* - * Because a writer could delete object, and a writer could - * reuse these object before the RCU grace period, we - * must check key after getting the reference on object - */ - if (obj->key != key) { // not the object we expected - put_ref(obj); - goto begin; - } -} -rcu_read_unlock(); - -Beware that lockless_lookup(key) cannot use traditional hlist_for_each_entry_rcu() -but a version with an additional memory barrier (smp_rmb()) - -lockless_lookup(key) -{ - struct hlist_node *node, *next; - for (pos = rcu_dereference((head)->first); - pos && ({ next = pos->next; smp_rmb(); prefetch(next); 1; }) && - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); - pos = rcu_dereference(next)) - if (obj->key == key) - return obj; - return NULL; - -And note the traditional hlist_for_each_entry_rcu() misses this smp_rmb() : - - struct hlist_node *node; - for (pos = rcu_dereference((head)->first); - pos && ({ prefetch(pos->next); 1; }) && - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); - pos = rcu_dereference(pos->next)) - if (obj->key == key) - return obj; - return NULL; -} - -Quoting Corey Minyard : - -"If the object is moved from one list to another list in-between the - time the hash is calculated and the next field is accessed, and the - object has moved to the end of a new list, the traversal will not - complete properly on the list it should have, since the object will - be on the end of the new list and there's not a way to tell it's on a - new list and restart the list traversal. I think that this can be - solved by pre-fetching the "next" field (with proper barriers) before - checking the key." - -2) Insert algo : ----------------- - -We need to make sure a reader cannot read the new 'obj->obj_next' value -and previous value of 'obj->key'. Or else, an item could be deleted -from a chain, and inserted into another chain. If new chain was empty -before the move, 'next' pointer is NULL, and lockless reader can -not detect it missed following items in original chain. - -/* - * Please note that new inserts are done at the head of list, - * not in the middle or end. - */ -obj = kmem_cache_alloc(...); -lock_chain(); // typically a spin_lock() -obj->key = key; -/* - * we need to make sure obj->key is updated before obj->next - * or obj->refcnt - */ -smp_wmb(); -atomic_set(&obj->refcnt, 1); -hlist_add_head_rcu(&obj->obj_node, list); -unlock_chain(); // typically a spin_unlock() - - -3) Remove algo --------------- -Nothing special here, we can use a standard RCU hlist deletion. -But thanks to SLAB_TYPESAFE_BY_RCU, beware a deleted object can be reused -very very fast (before the end of RCU grace period) - -if (put_last_reference_on(obj) { - lock_chain(); // typically a spin_lock() - hlist_del_init_rcu(&obj->obj_node); - unlock_chain(); // typically a spin_unlock() - kmem_cache_free(cachep, obj); -} - - - --------------------------------------------------------------------------- -With hlist_nulls we can avoid extra smp_rmb() in lockless_lookup() -and extra smp_wmb() in insert function. - -For example, if we choose to store the slot number as the 'nulls' -end-of-list marker for each slot of the hash table, we can detect -a race (some writer did a delete and/or a move of an object -to another chain) checking the final 'nulls' value if -the lookup met the end of chain. If final 'nulls' value -is not the slot number, then we must restart the lookup at -the beginning. If the object was moved to the same chain, -then the reader doesn't care : It might eventually -scan the list again without harm. - - -1) lookup algo - - head = &table[slot]; - rcu_read_lock(); -begin: - hlist_nulls_for_each_entry_rcu(obj, node, head, member) { - if (obj->key == key) { - if (!try_get_ref(obj)) // might fail for free objects - goto begin; - if (obj->key != key) { // not the object we expected - put_ref(obj); - goto begin; - } - goto out; - } -/* - * if the nulls value we got at the end of this lookup is - * not the expected one, we must restart lookup. - * We probably met an item that was moved to another chain. - */ - if (get_nulls_value(node) != slot) - goto begin; - obj = NULL; - -out: - rcu_read_unlock(); - -2) Insert function : --------------------- - -/* - * Please note that new inserts are done at the head of list, - * not in the middle or end. - */ -obj = kmem_cache_alloc(cachep); -lock_chain(); // typically a spin_lock() -obj->key = key; -/* - * changes to obj->key must be visible before refcnt one - */ -smp_wmb(); -atomic_set(&obj->refcnt, 1); -/* - * insert obj in RCU way (readers might be traversing chain) - */ -hlist_nulls_add_head_rcu(&obj->obj_node, list); -unlock_chain(); // typically a spin_unlock() diff --git a/Documentation/RCU/rcuref.txt b/Documentation/RCU/rcuref.rst index 5e6429d66c24..b33aeb14fde3 100644 --- a/Documentation/RCU/rcuref.txt +++ b/Documentation/RCU/rcuref.rst @@ -1,4 +1,8 @@ -Reference-count design for elements of lists/arrays protected by RCU. +.. SPDX-License-Identifier: GPL-2.0 + +==================================================================== +Reference-count design for elements of lists/arrays protected by RCU +==================================================================== Please note that the percpu-ref feature is likely your first @@ -12,32 +16,33 @@ please read on. Reference counting on elements of lists which are protected by traditional reader/writer spinlocks or semaphores are straightforward: -CODE LISTING A: -1. 2. -add() search_and_reference() -{ { - alloc_object read_lock(&list_lock); - ... search_for_element - atomic_set(&el->rc, 1); atomic_inc(&el->rc); - write_lock(&list_lock); ... - add_element read_unlock(&list_lock); - ... ... - write_unlock(&list_lock); } -} - -3. 4. -release_referenced() delete() -{ { - ... write_lock(&list_lock); - if(atomic_dec_and_test(&el->rc)) ... - kfree(el); - ... remove_element -} write_unlock(&list_lock); - ... - if (atomic_dec_and_test(&el->rc)) - kfree(el); - ... - } +CODE LISTING A:: + + 1. 2. + add() search_and_reference() + { { + alloc_object read_lock(&list_lock); + ... search_for_element + atomic_set(&el->rc, 1); atomic_inc(&el->rc); + write_lock(&list_lock); ... + add_element read_unlock(&list_lock); + ... ... + write_unlock(&list_lock); } + } + + 3. 4. + release_referenced() delete() + { { + ... write_lock(&list_lock); + if(atomic_dec_and_test(&el->rc)) ... + kfree(el); + ... remove_element + } write_unlock(&list_lock); + ... + if (atomic_dec_and_test(&el->rc)) + kfree(el); + ... + } If this list/array is made lock free using RCU as in changing the write_lock() in add() and delete() to spin_lock() and changing read_lock() @@ -46,34 +51,35 @@ search_and_reference() could potentially hold reference to an element which has already been deleted from the list/array. Use atomic_inc_not_zero() in this scenario as follows: -CODE LISTING B: -1. 2. -add() search_and_reference() -{ { - alloc_object rcu_read_lock(); - ... search_for_element - atomic_set(&el->rc, 1); if (!atomic_inc_not_zero(&el->rc)) { - spin_lock(&list_lock); rcu_read_unlock(); - return FAIL; - add_element } - ... ... - spin_unlock(&list_lock); rcu_read_unlock(); -} } -3. 4. -release_referenced() delete() -{ { - ... spin_lock(&list_lock); - if (atomic_dec_and_test(&el->rc)) ... - call_rcu(&el->head, el_free); remove_element - ... spin_unlock(&list_lock); -} ... - if (atomic_dec_and_test(&el->rc)) - call_rcu(&el->head, el_free); - ... - } +CODE LISTING B:: + + 1. 2. + add() search_and_reference() + { { + alloc_object rcu_read_lock(); + ... search_for_element + atomic_set(&el->rc, 1); if (!atomic_inc_not_zero(&el->rc)) { + spin_lock(&list_lock); rcu_read_unlock(); + return FAIL; + add_element } + ... ... + spin_unlock(&list_lock); rcu_read_unlock(); + } } + 3. 4. + release_referenced() delete() + { { + ... spin_lock(&list_lock); + if (atomic_dec_and_test(&el->rc)) ... + call_rcu(&el->head, el_free); remove_element + ... spin_unlock(&list_lock); + } ... + if (atomic_dec_and_test(&el->rc)) + call_rcu(&el->head, el_free); + ... + } Sometimes, a reference to the element needs to be obtained in the -update (write) stream. In such cases, atomic_inc_not_zero() might be +update (write) stream. In such cases, atomic_inc_not_zero() might be overkill, since we hold the update-side spinlock. One might instead use atomic_inc() in such cases. @@ -82,39 +88,40 @@ search_and_reference() code path. In such cases, the atomic_dec_and_test() may be moved from delete() to el_free() as follows: -CODE LISTING C: -1. 2. -add() search_and_reference() -{ { - alloc_object rcu_read_lock(); - ... search_for_element - atomic_set(&el->rc, 1); atomic_inc(&el->rc); - spin_lock(&list_lock); ... - - add_element rcu_read_unlock(); - ... } - spin_unlock(&list_lock); 4. -} delete() -3. { -release_referenced() spin_lock(&list_lock); -{ ... - ... remove_element - if (atomic_dec_and_test(&el->rc)) spin_unlock(&list_lock); - kfree(el); ... - ... call_rcu(&el->head, el_free); -} ... -5. } -void el_free(struct rcu_head *rhp) -{ - release_referenced(); -} +CODE LISTING C:: + + 1. 2. + add() search_and_reference() + { { + alloc_object rcu_read_lock(); + ... search_for_element + atomic_set(&el->rc, 1); atomic_inc(&el->rc); + spin_lock(&list_lock); ... + + add_element rcu_read_unlock(); + ... } + spin_unlock(&list_lock); 4. + } delete() + 3. { + release_referenced() spin_lock(&list_lock); + { ... + ... remove_element + if (atomic_dec_and_test(&el->rc)) spin_unlock(&list_lock); + kfree(el); ... + ... call_rcu(&el->head, el_free); + } ... + 5. } + void el_free(struct rcu_head *rhp) + { + release_referenced(); + } The key point is that the initial reference added by add() is not removed until after a grace period has elapsed following removal. This means that search_and_reference() cannot find this element, which means that the value of el->rc cannot increase. Thus, once it reaches zero, there are no -readers that can or ever will be able to reference the element. The -element can therefore safely be freed. This in turn guarantees that if +readers that can or ever will be able to reference the element. The +element can therefore safely be freed. This in turn guarantees that if any reader finds the element, that reader may safely acquire a reference without checking the value of the reference counter. @@ -130,21 +137,21 @@ the eventual invocation of kfree(), which is usually not a problem on modern computer systems, even the small ones. In cases where delete() can sleep, synchronize_rcu() can be called from -delete(), so that el_free() can be subsumed into delete as follows: - -4. -delete() -{ - spin_lock(&list_lock); - ... - remove_element - spin_unlock(&list_lock); - ... - synchronize_rcu(); - if (atomic_dec_and_test(&el->rc)) - kfree(el); - ... -} +delete(), so that el_free() can be subsumed into delete as follows:: + + 4. + delete() + { + spin_lock(&list_lock); + ... + remove_element + spin_unlock(&list_lock); + ... + synchronize_rcu(); + if (atomic_dec_and_test(&el->rc)) + kfree(el); + ... + } As additional examples in the kernel, the pattern in listing C is used by reference counting of struct pid, while the pattern in listing B is used by diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.rst index a360a8796710..c9ab6af4d3be 100644 --- a/Documentation/RCU/stallwarn.txt +++ b/Documentation/RCU/stallwarn.rst @@ -1,4 +1,8 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================== Using RCU's CPU Stall Detector +============================== This document first discusses what sorts of issues RCU's CPU stall detector can locate, and then discusses kernel parameters and Kconfig @@ -7,39 +11,40 @@ this document explains the stall detector's "splat" format. What Causes RCU CPU Stall Warnings? +=================================== So your kernel printed an RCU CPU stall warning. The next question is "What caused it?" The following problems can result in RCU CPU stall warnings: -o A CPU looping in an RCU read-side critical section. +- A CPU looping in an RCU read-side critical section. -o A CPU looping with interrupts disabled. +- A CPU looping with interrupts disabled. -o A CPU looping with preemption disabled. +- A CPU looping with preemption disabled. -o A CPU looping with bottom halves disabled. +- A CPU looping with bottom halves disabled. -o For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel +- For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel without invoking schedule(). If the looping in the kernel is really expected and desirable behavior, you might need to add some calls to cond_resched(). -o Booting Linux using a console connection that is too slow to +- Booting Linux using a console connection that is too slow to keep up with the boot-time console-message rate. For example, a 115Kbaud serial console can be -way- too slow to keep up with boot-time message rates, and will frequently result in RCU CPU stall warning messages. Especially if you have added debug printk()s. -o Anything that prevents RCU's grace-period kthreads from running. +- Anything that prevents RCU's grace-period kthreads from running. This can result in the "All QSes seen" console-log message. This message will include information on when the kthread last ran and how often it should be expected to run. It can also - result in the "rcu_.*kthread starved for" console-log message, + result in the ``rcu_.*kthread starved for`` console-log message, which will include additional debugging information. -o A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might +- A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might happen to preempt a low-priority task in the middle of an RCU read-side critical section. This is especially damaging if that low-priority task is not permitted to run on any other CPU, @@ -48,7 +53,7 @@ o A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might While the system is in the process of running itself out of memory, you might see stall-warning messages. -o A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that +- A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that is running at a higher priority than the RCU softirq threads. This will prevent RCU callbacks from ever being invoked, and in a CONFIG_PREEMPT_RCU kernel will further prevent @@ -63,7 +68,7 @@ o A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that can increase your system's context-switch rate and thus degrade performance. -o A periodic interrupt whose handler takes longer than the time +- A periodic interrupt whose handler takes longer than the time interval between successive pairs of interrupts. This can prevent RCU's kthreads and softirq handlers from running. Note that certain high-overhead debugging options, for example @@ -71,20 +76,27 @@ o A periodic interrupt whose handler takes longer than the time considerably longer than normal, which can in turn result in RCU CPU stall warnings. -o Testing a workload on a fast system, tuning the stall-warning +- Testing a workload on a fast system, tuning the stall-warning timeout down to just barely avoid RCU CPU stall warnings, and then running the same workload with the same stall-warning timeout on a slow system. Note that thermal throttling and on-demand governors can cause a single system to be sometimes fast and sometimes slow! -o A hardware or software issue shuts off the scheduler-clock +- A hardware or software issue shuts off the scheduler-clock interrupt on a CPU that is not in dyntick-idle mode. This problem really has happened, and seems to be most likely to result in RCU CPU stall warnings for CONFIG_NO_HZ_COMMON=n kernels. -o A bug in the RCU implementation. +- A hardware or software issue that prevents time-based wakeups + from occurring. These issues can range from misconfigured or + buggy timer hardware through bugs in the interrupt or exception + path (whether hardware, firmware, or software) through bugs + in Linux's timer subsystem through bugs in the scheduler, and, + yes, even including bugs in RCU itself. + +- A bug in the RCU implementation. -o A hardware failure. This is quite unlikely, but has occurred +- A hardware failure. This is quite unlikely, but has occurred at least once in real life. A CPU failed in a running system, becoming unresponsive, but not causing an immediate crash. This resulted in a series of RCU CPU stall warnings, eventually @@ -109,6 +121,7 @@ see include/trace/events/rcu.h. Fine-Tuning the RCU CPU Stall Detector +====================================== The rcuupdate.rcu_cpu_stall_suppress module parameter disables RCU's CPU stall detector, which detects conditions that unduly delay RCU grace @@ -118,6 +131,7 @@ The stall detector's idea of what constitutes "unduly delayed" is controlled by a set of kernel configuration variables and cpp macros: CONFIG_RCU_CPU_STALL_TIMEOUT +---------------------------- This kernel configuration parameter defines the period of time that RCU will wait from the beginning of a grace period until it @@ -137,6 +151,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT /sys/module/rcupdate/parameters/rcu_cpu_stall_suppress. RCU_STALL_DELAY_DELTA +--------------------- Although the lockdep facility is extremely useful, it does add some overhead. Therefore, under CONFIG_PROVE_RCU, the @@ -145,6 +160,7 @@ RCU_STALL_DELAY_DELTA macro, not a kernel configuration parameter.) RCU_STALL_RAT_DELAY +------------------- The CPU stall detector tries to make the offending CPU print its own warnings, as this often gives better-quality stack traces. @@ -155,6 +171,7 @@ RCU_STALL_RAT_DELAY parameter.) rcupdate.rcu_task_stall_timeout +------------------------------- This boot/sysfs parameter controls the RCU-tasks stall warning interval. A value of zero or less suppresses RCU-tasks stall @@ -168,9 +185,10 @@ rcupdate.rcu_task_stall_timeout Interpreting RCU's CPU Stall-Detector "Splats" +============================================== For non-RCU-tasks flavors of RCU, when a CPU detects that it is stalling, -it will print a message similar to the following: +it will print a message similar to the following:: INFO: rcu_sched detected stalls on CPUs/tasks: 2-...: (3 GPs behind) idle=06c/0/0 softirq=1453/1455 fqs=0 @@ -223,7 +241,7 @@ an estimate of the total number of RCU callbacks queued across all CPUs (625 in this case). In kernels with CONFIG_RCU_FAST_NO_HZ, more information is printed -for each CPU: +for each CPU:: 0: (64628 ticks this GP) idle=dd5/3fffffffffffffff/0 softirq=82/543 last_accelerate: a345/d342 dyntick_enabled: 1 @@ -235,7 +253,7 @@ processing is enabled. If the grace period ends just as the stall warning starts printing, there will be a spurious stall-warning message, which will include -the following: +the following:: INFO: Stall ended before state dump start @@ -248,7 +266,7 @@ which is overkill for this sort of problem. If all CPUs and tasks have passed through quiescent states, but the grace period has nevertheless failed to end, the stall-warning splat -will include something like the following: +will include something like the following:: All QSes seen, last rcu_preempt kthread activity 23807 (4297905177-4297881370), jiffies_till_next_fqs=3, root ->qsmask 0x0 @@ -261,7 +279,7 @@ which is way less than 23807. Finally, the root rcu_node structure's If the relevant grace-period kthread has been unable to run prior to the stall warning, as was the case in the "All QSes seen" line above, -the following additional line is printed: +the following additional line is printed:: kthread starved for 23807 jiffies! g7075 f0x0 RCU_GP_WAIT_FQS(3) ->state=0x1 ->cpu=5 @@ -276,6 +294,7 @@ kthread last ran on CPU 5. Multiple Warnings From One Stall +================================ If a stall lasts long enough, multiple stall-warning messages will be printed for it. The second and subsequent messages are printed at @@ -285,9 +304,10 @@ of the stall and the first message. Stall Warnings for Expedited Grace Periods +========================================== If an expedited grace period detects a stall, it will place a message -like the following in dmesg: +like the following in dmesg:: INFO: rcu_sched detected expedited stalls on CPUs/tasks: { 7-... } 21119 jiffies s: 73 root: 0x2/. diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.rst index af712a3c5b6a..a90147713062 100644 --- a/Documentation/RCU/torture.txt +++ b/Documentation/RCU/torture.rst @@ -1,7 +1,12 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================== RCU Torture Test Operation +========================== CONFIG_RCU_TORTURE_TEST +======================= The CONFIG_RCU_TORTURE_TEST config option is available for all RCU implementations. It creates an rcutorture kernel module that can @@ -13,9 +18,10 @@ when the module is loaded, and stops when the module is unloaded. Module parameters are prefixed by "rcutorture." in Documentation/admin-guide/kernel-parameters.txt. -OUTPUT +Output +====== -The statistics output is as follows: +The statistics output is as follows:: rcu-torture:--- Start of test: nreaders=16 nfakewriters=4 stat_interval=30 verbose=0 test_no_idle_hz=1 shuffle_interval=3 stutter=5 irqreader=1 fqs_duration=0 fqs_holdoff=0 fqs_stutter=3 test_boost=1/0 test_boost_interval=7 test_boost_duration=4 rcu-torture: rtc: (null) ver: 155441 tfle: 0 rta: 155441 rtaf: 8884 rtf: 155440 rtmbe: 0 rtbe: 0 rtbke: 0 rtbre: 0 rtbf: 0 rtb: 0 nt: 3055767 @@ -36,53 +42,53 @@ automatic determination as to whether RCU operated correctly. The entries are as follows: -o "rtc": The hexadecimal address of the structure currently visible +* "rtc": The hexadecimal address of the structure currently visible to readers. -o "ver": The number of times since boot that the RCU writer task +* "ver": The number of times since boot that the RCU writer task has changed the structure visible to readers. -o "tfle": If non-zero, indicates that the "torture freelist" +* "tfle": If non-zero, indicates that the "torture freelist" containing structures to be placed into the "rtc" area is empty. This condition is important, since it can fool you into thinking that RCU is working when it is not. :-/ -o "rta": Number of structures allocated from the torture freelist. +* "rta": Number of structures allocated from the torture freelist. -o "rtaf": Number of allocations from the torture freelist that have +* "rtaf": Number of allocations from the torture freelist that have failed due to the list being empty. It is not unusual for this to be non-zero, but it is bad for it to be a large fraction of the value indicated by "rta". -o "rtf": Number of frees into the torture freelist. +* "rtf": Number of frees into the torture freelist. -o "rtmbe": A non-zero value indicates that rcutorture believes that +* "rtmbe": A non-zero value indicates that rcutorture believes that rcu_assign_pointer() and rcu_dereference() are not working correctly. This value should be zero. -o "rtbe": A non-zero value indicates that one of the rcu_barrier() +* "rtbe": A non-zero value indicates that one of the rcu_barrier() family of functions is not working correctly. -o "rtbke": rcutorture was unable to create the real-time kthreads +* "rtbke": rcutorture was unable to create the real-time kthreads used to force RCU priority inversion. This value should be zero. -o "rtbre": Although rcutorture successfully created the kthreads +* "rtbre": Although rcutorture successfully created the kthreads used to force RCU priority inversion, it was unable to set them to the real-time priority level of 1. This value should be zero. -o "rtbf": The number of times that RCU priority boosting failed +* "rtbf": The number of times that RCU priority boosting failed to resolve RCU priority inversion. -o "rtb": The number of times that rcutorture attempted to force +* "rtb": The number of times that rcutorture attempted to force an RCU priority inversion condition. If you are testing RCU priority boosting via the "test_boost" module parameter, this value should be non-zero. -o "nt": The number of times rcutorture ran RCU read-side code from +* "nt": The number of times rcutorture ran RCU read-side code from within a timer handler. This value should be non-zero only if you specified the "irqreader" module parameter. -o "Reader Pipe": Histogram of "ages" of structures seen by readers. +* "Reader Pipe": Histogram of "ages" of structures seen by readers. If any entries past the first two are non-zero, RCU is broken. And rcutorture prints the error flag string "!!!" to make sure you notice. The age of a newly allocated structure is zero, @@ -94,14 +100,14 @@ o "Reader Pipe": Histogram of "ages" of structures seen by readers. RCU. If you want to see what it looks like when broken, break it yourself. ;-) -o "Reader Batch": Another histogram of "ages" of structures seen +* "Reader Batch": Another histogram of "ages" of structures seen by readers, but in terms of counter flips (or batches) rather than in terms of grace periods. The legal number of non-zero entries is again two. The reason for this separate view is that it is sometimes easier to get the third entry to show up in the "Reader Batch" list than in the "Reader Pipe" list. -o "Free-Block Circulation": Shows the number of torture structures +* "Free-Block Circulation": Shows the number of torture structures that have reached a given point in the pipeline. The first element should closely correspond to the number of structures allocated, the second to the number that have been removed from reader view, @@ -112,7 +118,7 @@ o "Free-Block Circulation": Shows the number of torture structures Different implementations of RCU can provide implementation-specific additional information. For example, Tree SRCU provides the following -additional line: +additional line:: srcud-torture: Tree SRCU per-CPU(idx=0): 0(35,-21) 1(-4,24) 2(1,1) 3(-26,20) 4(28,-47) 5(-9,4) 6(-10,14) 7(-14,11) T(1,6) @@ -123,15 +129,15 @@ using a dynamically allocated srcu_struct (hence "srcud-" rather than "old" and "current" values to the underlying array, and is useful for debugging. The final "T" entry contains the totals of the counters. - -USAGE ON SPECIFIC KERNEL BUILDS +Usage on Specific Kernel Builds +=============================== It is sometimes desirable to torture RCU on a specific kernel build, for example, when preparing to put that kernel build into production. In that case, the kernel should be built with CONFIG_RCU_TORTURE_TEST=m so that the test can be started using modprobe and terminated using rmmod. -For example, the following script may be used to torture RCU: +For example, the following script may be used to torture RCU:: #!/bin/sh @@ -148,7 +154,8 @@ two are self-explanatory, while the last indicates that while there were no RCU failures, CPU-hotplug problems were detected. -USAGE ON MAINLINE KERNELS +Usage on Mainline Kernels +========================= When using rcutorture to test changes to RCU itself, it is often necessary to build a number of kernels in order to test that change @@ -180,16 +187,16 @@ to Tree SRCU might run only the SRCU-N and SRCU-P scenarios using the --configs argument to kvm.sh as follows: "--configs 'SRCU-N SRCU-P'". Large systems can run multiple copies of of the full set of scenarios, for example, a system with 448 hardware threads can run five instances -of the full set concurrently. To make this happen: +of the full set concurrently. To make this happen:: kvm.sh --cpus 448 --configs '5*CFLIST' Alternatively, such a system can run 56 concurrent instances of a single -eight-CPU scenario: +eight-CPU scenario:: kvm.sh --cpus 448 --configs '56*TREE04' -Or 28 concurrent instances of each of two eight-CPU scenarios: +Or 28 concurrent instances of each of two eight-CPU scenarios:: kvm.sh --cpus 448 --configs '28*TREE03 28*TREE04' @@ -199,14 +206,14 @@ values for memory may require disabling the callback-flooding tests using the --bootargs parameter discussed below. Sometimes additional debugging is useful, and in such cases the --kconfig -parameter to kvm.sh may be used, for example, "--kconfig 'CONFIG_KASAN=y'". +parameter to kvm.sh may be used, for example, ``--kconfig 'CONFIG_KASAN=y'``. Kernel boot arguments can also be supplied, for example, to control rcutorture's module parameters. For example, to test a change to RCU's CPU stall-warning code, use "--bootargs 'rcutorture.stall_cpu=30'". This will of course result in the scripting reporting a failure, namely the resuling RCU CPU stall warning. As noted above, reducing memory may -require disabling rcutorture's callback-flooding tests: +require disabling rcutorture's callback-flooding tests:: kvm.sh --cpus 448 --configs '56*TREE04' --memory 128M \ --bootargs 'rcutorture.fwd_progress=0' @@ -225,7 +232,7 @@ is listed at the end of the kvm.sh output, which you really should redirect to a file. The build products and console output of each run is kept in tools/testing/selftests/rcutorture/res in timestamped directories. A given directory can be supplied to kvm-find-errors.sh in order to have -it cycle you through summaries of errors and full error logs. For example: +it cycle you through summaries of errors and full error logs. For example:: tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh \ tools/testing/selftests/rcutorture/res/2020.01.20-15.54.23 @@ -245,38 +252,42 @@ that was tested and any uncommitted changes in diff format. The most frequently used files in each per-scenario-run directory are: -.config: This file contains the Kconfig options. +.config: + This file contains the Kconfig options. -Make.out: This contains build output for a specific scenario. +Make.out: + This contains build output for a specific scenario. -console.log: This contains the console output for a specific scenario. +console.log: + This contains the console output for a specific scenario. This file may be examined once the kernel has booted, but it might not exist if the build failed. -vmlinux: This contains the kernel, which can be useful with tools like +vmlinux: + This contains the kernel, which can be useful with tools like objdump and gdb. A number of additional files are available, but are less frequently used. Many are intended for debugging of rcutorture itself or of its scripting. As of v5.4, a successful run with the default set of scenarios produces -the following summary at the end of the run on a 12-CPU system: - -SRCU-N ------- 804233 GPs (148.932/s) [srcu: g10008272 f0x0 ] -SRCU-P ------- 202320 GPs (37.4667/s) [srcud: g1809476 f0x0 ] -SRCU-t ------- 1122086 GPs (207.794/s) [srcu: g0 f0x0 ] -SRCU-u ------- 1111285 GPs (205.794/s) [srcud: g1 f0x0 ] -TASKS01 ------- 19666 GPs (3.64185/s) [tasks: g0 f0x0 ] -TASKS02 ------- 20541 GPs (3.80389/s) [tasks: g0 f0x0 ] -TASKS03 ------- 19416 GPs (3.59556/s) [tasks: g0 f0x0 ] -TINY01 ------- 836134 GPs (154.84/s) [rcu: g0 f0x0 ] n_max_cbs: 34198 -TINY02 ------- 850371 GPs (157.476/s) [rcu: g0 f0x0 ] n_max_cbs: 2631 -TREE01 ------- 162625 GPs (30.1157/s) [rcu: g1124169 f0x0 ] -TREE02 ------- 333003 GPs (61.6672/s) [rcu: g2647753 f0x0 ] n_max_cbs: 35844 -TREE03 ------- 306623 GPs (56.782/s) [rcu: g2975325 f0x0 ] n_max_cbs: 1496497 -CPU count limited from 16 to 12 -TREE04 ------- 246149 GPs (45.5831/s) [rcu: g1695737 f0x0 ] n_max_cbs: 434961 -TREE05 ------- 314603 GPs (58.2598/s) [rcu: g2257741 f0x2 ] n_max_cbs: 193997 -TREE07 ------- 167347 GPs (30.9902/s) [rcu: g1079021 f0x0 ] n_max_cbs: 478732 -CPU count limited from 16 to 12 -TREE09 ------- 752238 GPs (139.303/s) [rcu: g13075057 f0x0 ] n_max_cbs: 99011 +the following summary at the end of the run on a 12-CPU system:: + + SRCU-N ------- 804233 GPs (148.932/s) [srcu: g10008272 f0x0 ] + SRCU-P ------- 202320 GPs (37.4667/s) [srcud: g1809476 f0x0 ] + SRCU-t ------- 1122086 GPs (207.794/s) [srcu: g0 f0x0 ] + SRCU-u ------- 1111285 GPs (205.794/s) [srcud: g1 f0x0 ] + TASKS01 ------- 19666 GPs (3.64185/s) [tasks: g0 f0x0 ] + TASKS02 ------- 20541 GPs (3.80389/s) [tasks: g0 f0x0 ] + TASKS03 ------- 19416 GPs (3.59556/s) [tasks: g0 f0x0 ] + TINY01 ------- 836134 GPs (154.84/s) [rcu: g0 f0x0 ] n_max_cbs: 34198 + TINY02 ------- 850371 GPs (157.476/s) [rcu: g0 f0x0 ] n_max_cbs: 2631 + TREE01 ------- 162625 GPs (30.1157/s) [rcu: g1124169 f0x0 ] + TREE02 ------- 333003 GPs (61.6672/s) [rcu: g2647753 f0x0 ] n_max_cbs: 35844 + TREE03 ------- 306623 GPs (56.782/s) [rcu: g2975325 f0x0 ] n_max_cbs: 1496497 + CPU count limited from 16 to 12 + TREE04 ------- 246149 GPs (45.5831/s) [rcu: g1695737 f0x0 ] n_max_cbs: 434961 + TREE05 ------- 314603 GPs (58.2598/s) [rcu: g2257741 f0x2 ] n_max_cbs: 193997 + TREE07 ------- 167347 GPs (30.9902/s) [rcu: g1079021 f0x0 ] n_max_cbs: 478732 + CPU count limited from 16 to 12 + TREE09 ------- 752238 GPs (139.303/s) [rcu: g13075057 f0x0 ] n_max_cbs: 99011 diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index fb95fad81c79..d35fd3ced0db 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4038,6 +4038,14 @@ latencies, which will choose a value aligned with the appropriate hardware boundaries. + rcutree.rcu_min_cached_objs= [KNL] + Minimum number of objects which are cached and + maintained per one CPU. Object size is equal + to PAGE_SIZE. The cache allows to reduce the + pressure to page allocator, also it makes the + whole algorithm to behave better in low memory + condition. + rcutree.jiffies_till_first_fqs= [KNL] Set delay from grace-period initialization to first attempt to force quiescent states. @@ -4258,6 +4266,20 @@ Set time (jiffies) between CPU-hotplug operations, or zero to disable CPU-hotplug testing. + rcutorture.read_exit= [KNL] + Set the number of read-then-exit kthreads used + to test the interaction of RCU updaters and + task-exit processing. + + rcutorture.read_exit_burst= [KNL] + The number of times in a given read-then-exit + episode that a set of read-then-exit kthreads + is spawned. + + rcutorture.read_exit_delay= [KNL] + The delay, in seconds, between successive + read-then-exit testing episodes. + rcutorture.shuffle_interval= [KNL] Set task-shuffle interval (s). Shuffling tasks allows some CPUs to go into dyntick-idle mode @@ -4407,6 +4429,45 @@ reboot_cpu is s[mp]#### with #### being the processor to be used for rebooting. + refscale.holdoff= [KNL] + Set test-start holdoff period. The purpose of + this parameter is to delay the start of the + test until boot completes in order to avoid + interference. + + refscale.loops= [KNL] + Set the number of loops over the synchronization + primitive under test. Increasing this number + reduces noise due to loop start/end overhead, + but the default has already reduced the per-pass + noise to a handful of picoseconds on ca. 2020 + x86 laptops. + + refscale.nreaders= [KNL] + Set number of readers. The default value of -1 + selects N, where N is roughly 75% of the number + of CPUs. A value of zero is an interesting choice. + + refscale.nruns= [KNL] + Set number of runs, each of which is dumped onto + the console log. + + refscale.readdelay= [KNL] + Set the read-side critical-section duration, + measured in microseconds. + + refscale.scale_type= [KNL] + Specify the read-protection implementation to test. + + refscale.shutdown= [KNL] + Shut down the system at the end of the performance + test. This defaults to 1 (shut it down) when + rcuperf is built into the kernel and to 0 (leave + it running) when rcuperf is built as a module. + + refscale.verbose= [KNL] + Enable additional printk() statements. + relax_domain_level= [KNL, SMP] Set scheduler's default relax_domain_level. See Documentation/admin-guide/cgroup-v1/cpusets.rst. @@ -5082,6 +5143,13 @@ Prevent the CPU-hotplug component of torturing until after init has spawned. + torture.ftrace_dump_at_shutdown= [KNL] + Dump the ftrace buffer at torture-test shutdown, + even if there were no errors. This can be a + very costly operation when many torture tests + are running concurrently, especially on systems + with rotating-rust storage. + tp720= [HW,PS2] tpm_suspend_pcr=[HW,TPM] diff --git a/Documentation/locking/locktorture.rst b/Documentation/locking/locktorture.rst index 8012a74555e7..dfaf9fc883f4 100644 --- a/Documentation/locking/locktorture.rst +++ b/Documentation/locking/locktorture.rst @@ -166,4 +166,4 @@ checked for such errors. The "rmmod" command forces a "SUCCESS", two are self-explanatory, while the last indicates that while there were no locking failures, CPU-hotplug problems were detected. -Also see: Documentation/RCU/torture.txt +Also see: Documentation/RCU/torture.rst diff --git a/MAINTAINERS b/MAINTAINERS index f0569cf304ca..18d31f828172 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14449,7 +14449,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev F: Documentation/RCU/ F: include/linux/rcu* F: kernel/rcu/ -X: Documentation/RCU/torture.txt +X: Documentation/RCU/torture.rst X: include/linux/srcu*.h X: kernel/rcu/srcu*.c @@ -17301,7 +17301,7 @@ M: Josh Triplett <josh@joshtriplett.org> L: linux-kernel@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev -F: Documentation/RCU/torture.txt +F: Documentation/RCU/torture.rst F: kernel/locking/locktorture.c F: kernel/rcu/rcuperf.c F: kernel/rcu/rcutorture.c diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 60278e52c37a..eeaee346f5a9 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4516,6 +4516,8 @@ int try_release_extent_mapping(struct page *page, gfp_t mask) /* once for us */ free_extent_map(em); + + cond_resched(); /* Allow large-extent preemption. */ } } return try_release_extent_state(tree, page, mask); diff --git a/include/linux/rculist.h b/include/linux/rculist.h index df587d181844..7eed65b5f713 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -512,7 +512,7 @@ static inline void hlist_replace_rcu(struct hlist_node *old, * @right: The hlist head on the right * * The lists start out as [@left ][node1 ... ] and - [@right ][node2 ... ] + * [@right ][node2 ... ] * The lists end up as [@left ][node2 ... ] * [@right ][node1 ... ] */ diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index 9670b54b484a..ff3e94779e73 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -162,7 +162,7 @@ static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n) * The barrier() is needed to make sure compiler doesn't cache first element [1], * as this loop can be restarted [2] * [1] Documentation/core-api/atomic_ops.rst around line 114 - * [2] Documentation/RCU/rculist_nulls.txt around line 146 + * [2] Documentation/RCU/rculist_nulls.rst around line 146 */ #define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \ for (({barrier();}), \ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 659cbfa7581a..d15d46db61f7 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -828,17 +828,17 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) /* * Does the specified offset indicate that the corresponding rcu_head - * structure can be handled by kfree_rcu()? + * structure can be handled by kvfree_rcu()? */ -#define __is_kfree_rcu_offset(offset) ((offset) < 4096) +#define __is_kvfree_rcu_offset(offset) ((offset) < 4096) /* * Helper macro for kfree_rcu() to prevent argument-expansion eyestrain. */ -#define __kfree_rcu(head, offset) \ +#define __kvfree_rcu(head, offset) \ do { \ - BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); \ - kfree_call_rcu(head, (rcu_callback_t)(unsigned long)(offset)); \ + BUILD_BUG_ON(!__is_kvfree_rcu_offset(offset)); \ + kvfree_call_rcu(head, (rcu_callback_t)(unsigned long)(offset)); \ } while (0) /** @@ -857,7 +857,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * Because the functions are not allowed in the low-order 4096 bytes of * kernel virtual memory, offsets up to 4095 bytes can be accommodated. * If the offset is larger than 4095 bytes, a compile-time error will - * be generated in __kfree_rcu(). If this error is triggered, you can + * be generated in __kvfree_rcu(). If this error is triggered, you can * either fall back to use of call_rcu() or rearrange the structure to * position the rcu_head structure into the first 4096 bytes. * @@ -872,7 +872,46 @@ do { \ typeof (ptr) ___p = (ptr); \ \ if (___p) \ - __kfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \ + __kvfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \ +} while (0) + +/** + * kvfree_rcu() - kvfree an object after a grace period. + * + * This macro consists of one or two arguments and it is + * based on whether an object is head-less or not. If it + * has a head then a semantic stays the same as it used + * to be before: + * + * kvfree_rcu(ptr, rhf); + * + * where @ptr is a pointer to kvfree(), @rhf is the name + * of the rcu_head structure within the type of @ptr. + * + * When it comes to head-less variant, only one argument + * is passed and that is just a pointer which has to be + * freed after a grace period. Therefore the semantic is + * + * kvfree_rcu(ptr); + * + * where @ptr is a pointer to kvfree(). + * + * Please note, head-less way of freeing is permitted to + * use from a context that has to follow might_sleep() + * annotation. Otherwise, please switch and embed the + * rcu_head structure within the type of @ptr. + */ +#define kvfree_rcu(...) KVFREE_GET_MACRO(__VA_ARGS__, \ + kvfree_rcu_arg_2, kvfree_rcu_arg_1)(__VA_ARGS__) + +#define KVFREE_GET_MACRO(_1, _2, NAME, ...) NAME +#define kvfree_rcu_arg_2(ptr, rhf) kfree_rcu(ptr, rhf) +#define kvfree_rcu_arg_1(ptr) \ +do { \ + typeof(ptr) ___p = (ptr); \ + \ + if (___p) \ + kvfree_call_rcu(NULL, (rcu_callback_t) (___p)); \ } while (0) /* diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h index 4c25a41f8b27..d9015aac78c6 100644 --- a/include/linux/rcupdate_trace.h +++ b/include/linux/rcupdate_trace.h @@ -36,8 +36,8 @@ void rcu_read_unlock_trace_special(struct task_struct *t, int nesting); /** * rcu_read_lock_trace - mark beginning of RCU-trace read-side critical section * - * When synchronize_rcu_trace() is invoked by one task, then that task - * is guaranteed to block until all other tasks exit their read-side + * When synchronize_rcu_tasks_trace() is invoked by one task, then that + * task is guaranteed to block until all other tasks exit their read-side * critical sections. Similarly, if call_rcu_trace() is invoked on one * task while other tasks are within RCU read-side critical sections, * invocation of the corresponding RCU callback is deferred until after diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 8512caeb7682..5cc9637cac16 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -34,9 +34,25 @@ static inline void synchronize_rcu_expedited(void) synchronize_rcu(); } -static inline void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func) +/* + * Add one more declaration of kvfree() here. It is + * not so straight forward to just include <linux/mm.h> + * where it is defined due to getting many compile + * errors caused by that include. + */ +extern void kvfree(const void *addr); + +static inline void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func) { - call_rcu(head, func); + if (head) { + call_rcu(head, func); + return; + } + + // kvfree_rcu(one_arg) call. + might_sleep(); + synchronize_rcu(); + kvfree((void *) func); } void rcu_qs(void); diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index d5cc9d675987..d2f4064ebd1d 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -33,7 +33,7 @@ static inline void rcu_virt_note_context_switch(int cpu) } void synchronize_rcu_expedited(void); -void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func); +void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier(void); bool rcu_eqs_special_set(int cpu); diff --git a/include/linux/torture.h b/include/linux/torture.h index 629b66e6c161..7f65bd1dd307 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -55,6 +55,11 @@ struct torture_random_state { #define DEFINE_TORTURE_RANDOM_PERCPU(name) \ DEFINE_PER_CPU(struct torture_random_state, name) unsigned long torture_random(struct torture_random_state *trsp); +static inline void torture_random_init(struct torture_random_state *trsp) +{ + trsp->trs_state = 0; + trsp->trs_count = 0; +} /* Task shuffler, which causes CPUs to occasionally go idle. */ void torture_shuffle_task_register(struct task_struct *tp); diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index f9a7811148e2..ced71237b7e4 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -435,11 +435,12 @@ TRACE_EVENT_RCU(rcu_fqs, #endif /* #if defined(CONFIG_TREE_RCU) */ /* - * Tracepoint for dyntick-idle entry/exit events. These take a string - * as argument: "Start" for entering dyntick-idle mode, "Startirq" for - * entering it from irq/NMI, "End" for leaving it, "Endirq" for leaving it - * to irq/NMI, "--=" for events moving towards idle, and "++=" for events - * moving away from idle. + * Tracepoint for dyntick-idle entry/exit events. These take 2 strings + * as argument: + * polarity: "Start", "End", "StillNonIdle" for entering, exiting or still not + * being in dyntick-idle mode. + * context: "USER" or "IDLE" or "IRQ". + * NMIs nested in IRQs are inferred with dynticks_nesting > 1 in IRQ context. * * These events also take a pair of numbers, which indicate the nesting * depth before and after the event of interest, and a third number that is @@ -506,13 +507,13 @@ TRACE_EVENT_RCU(rcu_callback, /* * Tracepoint for the registration of a single RCU callback of the special - * kfree() form. The first argument is the RCU type, the second argument + * kvfree() form. The first argument is the RCU type, the second argument * is a pointer to the RCU callback, the third argument is the offset * of the callback within the enclosing RCU-protected data structure, * the fourth argument is the number of lazy callbacks queued, and the * fifth argument is the total number of callbacks queued. */ -TRACE_EVENT_RCU(rcu_kfree_callback, +TRACE_EVENT_RCU(rcu_kvfree_callback, TP_PROTO(const char *rcuname, struct rcu_head *rhp, unsigned long offset, long qlen), @@ -596,12 +597,12 @@ TRACE_EVENT_RCU(rcu_invoke_callback, /* * Tracepoint for the invocation of a single RCU callback of the special - * kfree() form. The first argument is the RCU flavor, the second + * kvfree() form. The first argument is the RCU flavor, the second * argument is a pointer to the RCU callback, and the third argument * is the offset of the callback within the enclosing RCU-protected * data structure. */ -TRACE_EVENT_RCU(rcu_invoke_kfree_callback, +TRACE_EVENT_RCU(rcu_invoke_kvfree_callback, TP_PROTO(const char *rcuname, struct rcu_head *rhp, unsigned long offset), diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 29a8de4c50b9..0a7549d159ed 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -5851,9 +5851,7 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s) pr_warn("\n%srcu_scheduler_active = %d, debug_locks = %d\n", !rcu_lockdep_current_cpu_online() ? "RCU used illegally from offline CPU!\n" - : !rcu_is_watching() - ? "RCU used illegally from idle CPU!\n" - : "", + : "", rcu_scheduler_active, debug_locks); /* diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 5efbfc68ce99..8ff6f50e06a0 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -631,13 +631,13 @@ static int lock_torture_writer(void *arg) cxt.cur_ops->writelock(); if (WARN_ON_ONCE(lock_is_write_held)) lwsp->n_lock_fail++; - lock_is_write_held = 1; + lock_is_write_held = true; if (WARN_ON_ONCE(lock_is_read_held)) lwsp->n_lock_fail++; /* rare, but... */ lwsp->n_lock_acquired++; cxt.cur_ops->write_delay(&rand); - lock_is_write_held = 0; + lock_is_write_held = false; cxt.cur_ops->writeunlock(); stutter_wait("lock_torture_writer"); @@ -665,13 +665,13 @@ static int lock_torture_reader(void *arg) schedule_timeout_uninterruptible(1); cxt.cur_ops->readlock(); - lock_is_read_held = 1; + lock_is_read_held = true; if (WARN_ON_ONCE(lock_is_write_held)) lrsp->n_lock_fail++; /* rare, but... */ lrsp->n_lock_acquired++; cxt.cur_ops->read_delay(&rand); - lock_is_read_held = 0; + lock_is_read_held = false; cxt.cur_ops->readunlock(); stutter_wait("lock_torture_reader"); @@ -686,7 +686,7 @@ static int lock_torture_reader(void *arg) static void __torture_print_stats(char *page, struct lock_stress_stats *statp, bool write) { - bool fail = 0; + bool fail = false; int i, n_stress; long max = 0, min = statp ? statp[0].n_lock_acquired : 0; long long sum = 0; @@ -904,7 +904,7 @@ static int __init lock_torture_init(void) /* Initialize the statistics so that each run gets its own numbers. */ if (nwriters_stress) { - lock_is_write_held = 0; + lock_is_write_held = false; cxt.lwsa = kmalloc_array(cxt.nrealwriters_stress, sizeof(*cxt.lwsa), GFP_KERNEL); @@ -935,7 +935,7 @@ static int __init lock_torture_init(void) } if (nreaders_stress) { - lock_is_read_held = 0; + lock_is_read_held = false; cxt.lrsa = kmalloc_array(cxt.nrealreaders_stress, sizeof(*cxt.lrsa), GFP_KERNEL); diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug index 452feae8de20..3cf6132a4bb9 100644 --- a/kernel/rcu/Kconfig.debug +++ b/kernel/rcu/Kconfig.debug @@ -61,6 +61,25 @@ config RCU_TORTURE_TEST Say M if you want the RCU torture tests to build as a module. Say N if you are unsure. +config RCU_REF_SCALE_TEST + tristate "Scalability tests for read-side synchronization (RCU and others)" + depends on DEBUG_KERNEL + select TORTURE_TEST + select SRCU + select TASKS_RCU + select TASKS_RUDE_RCU + select TASKS_TRACE_RCU + default n + help + This option provides a kernel module that runs performance tests + useful comparing RCU with various read-side synchronization mechanisms. + The kernel module may be built after the fact on the running kernel to be + tested, if desired. + + Say Y here if you want these performance tests built into the kernel. + Say M if you want to build it as a module instead. + Say N if you are unsure. + config RCU_CPU_STALL_TIMEOUT int "RCU CPU stall timeout in seconds" depends on RCU_STALL_COMMON diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile index f91f2c2cf138..95f5117ef8da 100644 --- a/kernel/rcu/Makefile +++ b/kernel/rcu/Makefile @@ -12,6 +12,7 @@ obj-$(CONFIG_TREE_SRCU) += srcutree.o obj-$(CONFIG_TINY_SRCU) += srcutiny.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o obj-$(CONFIG_RCU_PERF_TEST) += rcuperf.o +obj-$(CONFIG_RCU_REF_SCALE_TEST) += refscale.o obj-$(CONFIG_TREE_RCU) += tree.o obj-$(CONFIG_TINY_RCU) += tiny.o obj-$(CONFIG_RCU_NEED_SEGCBLIST) += rcu_segcblist.o diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c index 9eb39c20082c..ec903d781778 100644 --- a/kernel/rcu/rcuperf.c +++ b/kernel/rcu/rcuperf.c @@ -69,6 +69,11 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>"); * value specified by nr_cpus for a read-only test. * * Various other use cases may of course be specified. + * + * Note that this test's readers are intended only as a test load for + * the writers. The reader performance statistics will be overly + * pessimistic due to the per-critical-section interrupt disabling, + * test-end checks, and the pair of calls through pointers. */ #ifdef MODULE @@ -309,8 +314,10 @@ static void rcu_perf_wait_shutdown(void) } /* - * RCU perf reader kthread. Repeatedly does empty RCU read-side - * critical section, minimizing update-side interference. + * RCU perf reader kthread. Repeatedly does empty RCU read-side critical + * section, minimizing update-side interference. However, the point of + * this test is not to evaluate reader performance, but instead to serve + * as a test load for update-side performance testing. */ static int rcu_perf_reader(void *arg) @@ -576,11 +583,8 @@ static int compute_real(int n) static int rcu_perf_shutdown(void *arg) { - do { - wait_event(shutdown_wq, - atomic_read(&n_rcu_perf_writer_finished) >= - nrealwriters); - } while (atomic_read(&n_rcu_perf_writer_finished) < nrealwriters); + wait_event(shutdown_wq, + atomic_read(&n_rcu_perf_writer_finished) >= nrealwriters); smp_mb(); /* Wake before output. */ rcu_perf_cleanup(); kernel_power_off(); @@ -693,11 +697,8 @@ kfree_perf_cleanup(void) static int kfree_perf_shutdown(void *arg) { - do { - wait_event(shutdown_wq, - atomic_read(&n_kfree_perf_thread_ended) >= - kfree_nrealthreads); - } while (atomic_read(&n_kfree_perf_thread_ended) < kfree_nrealthreads); + wait_event(shutdown_wq, + atomic_read(&n_kfree_perf_thread_ended) >= kfree_nrealthreads); smp_mb(); /* Wake before output. */ diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index efb792e13fca..d0d265304d14 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -7,7 +7,7 @@ * Authors: Paul E. McKenney <paulmck@linux.ibm.com> * Josh Triplett <josh@joshtriplett.org> * - * See also: Documentation/RCU/torture.txt + * See also: Documentation/RCU/torture.rst */ #define pr_fmt(fmt) fmt @@ -109,6 +109,10 @@ torture_param(int, object_debug, 0, torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)"); torture_param(int, onoff_interval, 0, "Time between CPU hotplugs (jiffies), 0=disable"); +torture_param(int, read_exit_delay, 13, + "Delay between read-then-exit episodes (s)"); +torture_param(int, read_exit_burst, 16, + "# of read-then-exit bursts per episode, zero to disable"); torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles"); torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable."); torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable."); @@ -146,6 +150,7 @@ static struct task_struct *stall_task; static struct task_struct *fwd_prog_task; static struct task_struct **barrier_cbs_tasks; static struct task_struct *barrier_task; +static struct task_struct *read_exit_task; #define RCU_TORTURE_PIPE_LEN 10 @@ -177,6 +182,7 @@ static long n_rcu_torture_boosts; static atomic_long_t n_rcu_torture_timers; static long n_barrier_attempts; static long n_barrier_successes; /* did rcu_barrier test succeed? */ +static unsigned long n_read_exits; static struct list_head rcu_torture_removed; static unsigned long shutdown_jiffies; @@ -1166,6 +1172,7 @@ rcu_torture_writer(void *arg) WARN(1, "%s: rtort_pipe_count: %d\n", __func__, rcu_tortures[i].rtort_pipe_count); } } while (!torture_must_stop()); + rcu_torture_current = NULL; // Let stats task know that we are done. /* Reset expediting back to unexpedited. */ if (expediting > 0) expediting = -expediting; @@ -1370,6 +1377,7 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp) struct rt_read_seg *rtrsp1; unsigned long long ts; + WARN_ON_ONCE(!rcu_is_watching()); newstate = rcutorture_extend_mask(readstate, trsp); rcutorture_one_extend(&readstate, newstate, trsp, rtrsp++); started = cur_ops->get_gp_seq(); @@ -1539,10 +1547,11 @@ rcu_torture_stats_print(void) n_rcu_torture_boosts, atomic_long_read(&n_rcu_torture_timers)); torture_onoff_stats(); - pr_cont("barrier: %ld/%ld:%ld\n", + pr_cont("barrier: %ld/%ld:%ld ", data_race(n_barrier_successes), data_race(n_barrier_attempts), data_race(n_rcu_torture_barrier_error)); + pr_cont("read-exits: %ld\n", data_race(n_read_exits)); pr_alert("%s%s ", torture_type, TORTURE_FLAG); if (atomic_read(&n_rcu_torture_mberror) || @@ -1634,7 +1643,8 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag) "stall_cpu=%d stall_cpu_holdoff=%d stall_cpu_irqsoff=%d " "stall_cpu_block=%d " "n_barrier_cbs=%d " - "onoff_interval=%d onoff_holdoff=%d\n", + "onoff_interval=%d onoff_holdoff=%d " + "read_exit_delay=%d read_exit_burst=%d\n", torture_type, tag, nrealreaders, nfakewriters, stat_interval, verbose, test_no_idle_hz, shuffle_interval, stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter, @@ -1643,7 +1653,8 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag) stall_cpu, stall_cpu_holdoff, stall_cpu_irqsoff, stall_cpu_block, n_barrier_cbs, - onoff_interval, onoff_holdoff); + onoff_interval, onoff_holdoff, + read_exit_delay, read_exit_burst); } static int rcutorture_booster_cleanup(unsigned int cpu) @@ -2175,7 +2186,7 @@ static void rcu_torture_barrier1cb(void *rcu_void) static int rcu_torture_barrier_cbs(void *arg) { long myid = (long)arg; - bool lastphase = 0; + bool lastphase = false; bool newphase; struct rcu_head rcu; @@ -2338,6 +2349,99 @@ static bool rcu_torture_can_boost(void) return true; } +static bool read_exit_child_stop; +static bool read_exit_child_stopped; +static wait_queue_head_t read_exit_wq; + +// Child kthread which just does an rcutorture reader and exits. +static int rcu_torture_read_exit_child(void *trsp_in) +{ + struct torture_random_state *trsp = trsp_in; + + set_user_nice(current, MAX_NICE); + // Minimize time between reading and exiting. + while (!kthread_should_stop()) + schedule_timeout_uninterruptible(1); + (void)rcu_torture_one_read(trsp); + return 0; +} + +// Parent kthread which creates and destroys read-exit child kthreads. +static int rcu_torture_read_exit(void *unused) +{ + int count = 0; + bool errexit = false; + int i; + struct task_struct *tsp; + DEFINE_TORTURE_RANDOM(trs); + + // Allocate and initialize. + set_user_nice(current, MAX_NICE); + VERBOSE_TOROUT_STRING("rcu_torture_read_exit: Start of test"); + + // Each pass through this loop does one read-exit episode. + do { + if (++count > read_exit_burst) { + VERBOSE_TOROUT_STRING("rcu_torture_read_exit: End of episode"); + rcu_barrier(); // Wait for task_struct free, avoid OOM. + for (i = 0; i < read_exit_delay; i++) { + schedule_timeout_uninterruptible(HZ); + if (READ_ONCE(read_exit_child_stop)) + break; + } + if (!READ_ONCE(read_exit_child_stop)) + VERBOSE_TOROUT_STRING("rcu_torture_read_exit: Start of episode"); + count = 0; + } + if (READ_ONCE(read_exit_child_stop)) + break; + // Spawn child. + tsp = kthread_run(rcu_torture_read_exit_child, + &trs, "%s", + "rcu_torture_read_exit_child"); + if (IS_ERR(tsp)) { + VERBOSE_TOROUT_ERRSTRING("out of memory"); + errexit = true; + tsp = NULL; + break; + } + cond_resched(); + kthread_stop(tsp); + n_read_exits ++; + stutter_wait("rcu_torture_read_exit"); + } while (!errexit && !READ_ONCE(read_exit_child_stop)); + + // Clean up and exit. + smp_store_release(&read_exit_child_stopped, true); // After reaping. + smp_mb(); // Store before wakeup. + wake_up(&read_exit_wq); + while (!torture_must_stop()) + schedule_timeout_uninterruptible(1); + torture_kthread_stopping("rcu_torture_read_exit"); + return 0; +} + +static int rcu_torture_read_exit_init(void) +{ + if (read_exit_burst <= 0) + return -EINVAL; + init_waitqueue_head(&read_exit_wq); + read_exit_child_stop = false; + read_exit_child_stopped = false; + return torture_create_kthread(rcu_torture_read_exit, NULL, + read_exit_task); +} + +static void rcu_torture_read_exit_cleanup(void) +{ + if (!read_exit_task) + return; + WRITE_ONCE(read_exit_child_stop, true); + smp_mb(); // Above write before wait. + wait_event(read_exit_wq, smp_load_acquire(&read_exit_child_stopped)); + torture_stop_kthread(rcutorture_read_exit, read_exit_task); +} + static enum cpuhp_state rcutor_hp; static void @@ -2359,6 +2463,7 @@ rcu_torture_cleanup(void) } show_rcu_gp_kthreads(); + rcu_torture_read_exit_cleanup(); rcu_torture_barrier_cleanup(); torture_stop_kthread(rcu_torture_fwd_prog, fwd_prog_task); torture_stop_kthread(rcu_torture_stall, stall_task); @@ -2370,7 +2475,6 @@ rcu_torture_cleanup(void) reader_tasks[i]); kfree(reader_tasks); } - rcu_torture_current = NULL; if (fakewriter_tasks) { for (i = 0; i < nfakewriters; i++) { @@ -2682,6 +2786,9 @@ rcu_torture_init(void) firsterr = rcu_torture_barrier_init(); if (firsterr) goto unwind; + firsterr = rcu_torture_read_exit_init(); + if (firsterr) + goto unwind; if (object_debug) rcu_test_debug_objects(); torture_init_end(); diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c new file mode 100644 index 000000000000..d9291f883b54 --- /dev/null +++ b/kernel/rcu/refscale.c @@ -0,0 +1,717 @@ +// SPDX-License-Identifier: GPL-2.0+ +// +// Scalability test comparing RCU vs other mechanisms +// for acquiring references on objects. +// +// Copyright (C) Google, 2020. +// +// Author: Joel Fernandes <joel@joelfernandes.org> + +#define pr_fmt(fmt) fmt + +#include <linux/atomic.h> +#include <linux/bitops.h> +#include <linux/completion.h> +#include <linux/cpu.h> +#include <linux/delay.h> +#include <linux/err.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kthread.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/notifier.h> +#include <linux/percpu.h> +#include <linux/rcupdate.h> +#include <linux/rcupdate_trace.h> +#include <linux/reboot.h> +#include <linux/sched.h> +#include <linux/spinlock.h> +#include <linux/smp.h> +#include <linux/stat.h> +#include <linux/srcu.h> +#include <linux/slab.h> +#include <linux/torture.h> +#include <linux/types.h> + +#include "rcu.h" + +#define SCALE_FLAG "-ref-scale: " + +#define SCALEOUT(s, x...) \ + pr_alert("%s" SCALE_FLAG s, scale_type, ## x) + +#define VERBOSE_SCALEOUT(s, x...) \ + do { if (verbose) pr_alert("%s" SCALE_FLAG s, scale_type, ## x); } while (0) + +#define VERBOSE_SCALEOUT_ERRSTRING(s, x...) \ + do { if (verbose) pr_alert("%s" SCALE_FLAG "!!! " s, scale_type, ## x); } while (0) + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Joel Fernandes (Google) <joel@joelfernandes.org>"); + +static char *scale_type = "rcu"; +module_param(scale_type, charp, 0444); +MODULE_PARM_DESC(scale_type, "Type of test (rcu, srcu, refcnt, rwsem, rwlock."); + +torture_param(int, verbose, 0, "Enable verbose debugging printk()s"); + +// Wait until there are multiple CPUs before starting test. +torture_param(int, holdoff, IS_BUILTIN(CONFIG_RCU_REF_SCALE_TEST) ? 10 : 0, + "Holdoff time before test start (s)"); +// Number of loops per experiment, all readers execute operations concurrently. +torture_param(long, loops, 10000, "Number of loops per experiment."); +// Number of readers, with -1 defaulting to about 75% of the CPUs. +torture_param(int, nreaders, -1, "Number of readers, -1 for 75% of CPUs."); +// Number of runs. +torture_param(int, nruns, 30, "Number of experiments to run."); +// Reader delay in nanoseconds, 0 for no delay. +torture_param(int, readdelay, 0, "Read-side delay in nanoseconds."); + +#ifdef MODULE +# define REFSCALE_SHUTDOWN 0 +#else +# define REFSCALE_SHUTDOWN 1 +#endif + +torture_param(bool, shutdown, REFSCALE_SHUTDOWN, + "Shutdown at end of scalability tests."); + +struct reader_task { + struct task_struct *task; + int start_reader; + wait_queue_head_t wq; + u64 last_duration_ns; +}; + +static struct task_struct *shutdown_task; +static wait_queue_head_t shutdown_wq; + +static struct task_struct *main_task; +static wait_queue_head_t main_wq; +static int shutdown_start; + +static struct reader_task *reader_tasks; + +// Number of readers that are part of the current experiment. +static atomic_t nreaders_exp; + +// Use to wait for all threads to start. +static atomic_t n_init; +static atomic_t n_started; +static atomic_t n_warmedup; +static atomic_t n_cooleddown; + +// Track which experiment is currently running. +static int exp_idx; + +// Operations vector for selecting different types of tests. +struct ref_scale_ops { + void (*init)(void); + void (*cleanup)(void); + void (*readsection)(const int nloops); + void (*delaysection)(const int nloops, const int udl, const int ndl); + const char *name; +}; + +static struct ref_scale_ops *cur_ops; + +static void un_delay(const int udl, const int ndl) +{ + if (udl) + udelay(udl); + if (ndl) + ndelay(ndl); +} + +static void ref_rcu_read_section(const int nloops) +{ + int i; + + for (i = nloops; i >= 0; i--) { + rcu_read_lock(); + rcu_read_unlock(); + } +} + +static void ref_rcu_delay_section(const int nloops, const int udl, const int ndl) +{ + int i; + + for (i = nloops; i >= 0; i--) { + rcu_read_lock(); + un_delay(udl, ndl); + rcu_read_unlock(); + } +} + +static void rcu_sync_scale_init(void) +{ +} + +static struct ref_scale_ops rcu_ops = { + .init = rcu_sync_scale_init, + .readsection = ref_rcu_read_section, + .delaysection = ref_rcu_delay_section, + .name = "rcu" +}; + +// Definitions for SRCU ref scale testing. +DEFINE_STATIC_SRCU(srcu_refctl_scale); +static struct srcu_struct *srcu_ctlp = &srcu_refctl_scale; + +static void srcu_ref_scale_read_section(const int nloops) +{ + int i; + int idx; + + for (i = nloops; i >= 0; i--) { + idx = srcu_read_lock(srcu_ctlp); + srcu_read_unlock(srcu_ctlp, idx); + } +} + +static void srcu_ref_scale_delay_section(const int nloops, const int udl, const int ndl) +{ + int i; + int idx; + + for (i = nloops; i >= 0; i--) { + idx = srcu_read_lock(srcu_ctlp); + un_delay(udl, ndl); + srcu_read_unlock(srcu_ctlp, idx); + } +} + +static struct ref_scale_ops srcu_ops = { + .init = rcu_sync_scale_init, + .readsection = srcu_ref_scale_read_section, + .delaysection = srcu_ref_scale_delay_section, + .name = "srcu" +}; + +// Definitions for RCU Tasks ref scale testing: Empty read markers. +// These definitions also work for RCU Rude readers. +static void rcu_tasks_ref_scale_read_section(const int nloops) +{ + int i; + + for (i = nloops; i >= 0; i--) + continue; +} + +static void rcu_tasks_ref_scale_delay_section(const int nloops, const int udl, const int ndl) +{ + int i; + + for (i = nloops; i >= 0; i--) + un_delay(udl, ndl); +} + +static struct ref_scale_ops rcu_tasks_ops = { + .init = rcu_sync_scale_init, + .readsection = rcu_tasks_ref_scale_read_section, + .delaysection = rcu_tasks_ref_scale_delay_section, + .name = "rcu-tasks" +}; + +// Definitions for RCU Tasks Trace ref scale testing. +static void rcu_trace_ref_scale_read_section(const int nloops) +{ + int i; + + for (i = nloops; i >= 0; i--) { + rcu_read_lock_trace(); + rcu_read_unlock_trace(); + } +} + +static void rcu_trace_ref_scale_delay_section(const int nloops, const int udl, const int ndl) +{ + int i; + + for (i = nloops; i >= 0; i--) { + rcu_read_lock_trace(); + un_delay(udl, ndl); + rcu_read_unlock_trace(); + } +} + +static struct ref_scale_ops rcu_trace_ops = { + .init = rcu_sync_scale_init, + .readsection = rcu_trace_ref_scale_read_section, + .delaysection = rcu_trace_ref_scale_delay_section, + .name = "rcu-trace" +}; + +// Definitions for reference count +static atomic_t refcnt; + +static void ref_refcnt_section(const int nloops) +{ + int i; + + for (i = nloops; i >= 0; i--) { + atomic_inc(&refcnt); + atomic_dec(&refcnt); + } +} + +static void ref_refcnt_delay_section(const int nloops, const int udl, const int ndl) +{ + int i; + + for (i = nloops; i >= 0; i--) { + atomic_inc(&refcnt); + un_delay(udl, ndl); + atomic_dec(&refcnt); + } +} + +static struct ref_scale_ops refcnt_ops = { + .init = rcu_sync_scale_init, + .readsection = ref_refcnt_section, + .delaysection = ref_refcnt_delay_section, + .name = "refcnt" +}; + +// Definitions for rwlock +static rwlock_t test_rwlock; + +static void ref_rwlock_init(void) +{ + rwlock_init(&test_rwlock); +} + +static void ref_rwlock_section(const int nloops) +{ + int i; + + for (i = nloops; i >= 0; i--) { + read_lock(&test_rwlock); + read_unlock(&test_rwlock); + } +} + +static void ref_rwlock_delay_section(const int nloops, const int udl, const int ndl) +{ + int i; + + for (i = nloops; i >= 0; i--) { + read_lock(&test_rwlock); + un_delay(udl, ndl); + read_unlock(&test_rwlock); + } +} + +static struct ref_scale_ops rwlock_ops = { + .init = ref_rwlock_init, + .readsection = ref_rwlock_section, + .delaysection = ref_rwlock_delay_section, + .name = "rwlock" +}; + +// Definitions for rwsem +static struct rw_semaphore test_rwsem; + +static void ref_rwsem_init(void) +{ + init_rwsem(&test_rwsem); +} + +static void ref_rwsem_section(const int nloops) +{ + int i; + + for (i = nloops; i >= 0; i--) { + down_read(&test_rwsem); + up_read(&test_rwsem); + } +} + +static void ref_rwsem_delay_section(const int nloops, const int udl, const int ndl) +{ + int i; + + for (i = nloops; i >= 0; i--) { + down_read(&test_rwsem); + un_delay(udl, ndl); + up_read(&test_rwsem); + } +} + +static struct ref_scale_ops rwsem_ops = { + .init = ref_rwsem_init, + .readsection = ref_rwsem_section, + .delaysection = ref_rwsem_delay_section, + .name = "rwsem" +}; + +static void rcu_scale_one_reader(void) +{ + if (readdelay <= 0) + cur_ops->readsection(loops); + else + cur_ops->delaysection(loops, readdelay / 1000, readdelay % 1000); +} + +// Reader kthread. Repeatedly does empty RCU read-side +// critical section, minimizing update-side interference. +static int +ref_scale_reader(void *arg) +{ + unsigned long flags; + long me = (long)arg; + struct reader_task *rt = &(reader_tasks[me]); + u64 start; + s64 duration; + + VERBOSE_SCALEOUT("ref_scale_reader %ld: task started", me); + set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids)); + set_user_nice(current, MAX_NICE); + atomic_inc(&n_init); + if (holdoff) + schedule_timeout_interruptible(holdoff * HZ); +repeat: + VERBOSE_SCALEOUT("ref_scale_reader %ld: waiting to start next experiment on cpu %d", me, smp_processor_id()); + + // Wait for signal that this reader can start. + wait_event(rt->wq, (atomic_read(&nreaders_exp) && smp_load_acquire(&rt->start_reader)) || + torture_must_stop()); + + if (torture_must_stop()) + goto end; + + // Make sure that the CPU is affinitized appropriately during testing. + WARN_ON_ONCE(smp_processor_id() != me); + + WRITE_ONCE(rt->start_reader, 0); + if (!atomic_dec_return(&n_started)) + while (atomic_read_acquire(&n_started)) + cpu_relax(); + + VERBOSE_SCALEOUT("ref_scale_reader %ld: experiment %d started", me, exp_idx); + + + // To reduce noise, do an initial cache-warming invocation, check + // in, and then keep warming until everyone has checked in. + rcu_scale_one_reader(); + if (!atomic_dec_return(&n_warmedup)) + while (atomic_read_acquire(&n_warmedup)) + rcu_scale_one_reader(); + // Also keep interrupts disabled. This also has the effect + // of preventing entries into slow path for rcu_read_unlock(). + local_irq_save(flags); + start = ktime_get_mono_fast_ns(); + + rcu_scale_one_reader(); + + duration = ktime_get_mono_fast_ns() - start; + local_irq_restore(flags); + + rt->last_duration_ns = WARN_ON_ONCE(duration < 0) ? 0 : duration; + // To reduce runtime-skew noise, do maintain-load invocations until + // everyone is done. + if (!atomic_dec_return(&n_cooleddown)) + while (atomic_read_acquire(&n_cooleddown)) + rcu_scale_one_reader(); + + if (atomic_dec_and_test(&nreaders_exp)) + wake_up(&main_wq); + + VERBOSE_SCALEOUT("ref_scale_reader %ld: experiment %d ended, (readers remaining=%d)", + me, exp_idx, atomic_read(&nreaders_exp)); + + if (!torture_must_stop()) + goto repeat; +end: + torture_kthread_stopping("ref_scale_reader"); + return 0; +} + +static void reset_readers(void) +{ + int i; + struct reader_task *rt; + + for (i = 0; i < nreaders; i++) { + rt = &(reader_tasks[i]); + + rt->last_duration_ns = 0; + } +} + +// Print the results of each reader and return the sum of all their durations. +static u64 process_durations(int n) +{ + int i; + struct reader_task *rt; + char buf1[64]; + char *buf; + u64 sum = 0; + + buf = kmalloc(128 + nreaders * 32, GFP_KERNEL); + if (!buf) + return 0; + buf[0] = 0; + sprintf(buf, "Experiment #%d (Format: <THREAD-NUM>:<Total loop time in ns>)", + exp_idx); + + for (i = 0; i < n && !torture_must_stop(); i++) { + rt = &(reader_tasks[i]); + sprintf(buf1, "%d: %llu\t", i, rt->last_duration_ns); + + if (i % 5 == 0) + strcat(buf, "\n"); + strcat(buf, buf1); + + sum += rt->last_duration_ns; + } + strcat(buf, "\n"); + + SCALEOUT("%s\n", buf); + + kfree(buf); + return sum; +} + +// The main_func is the main orchestrator, it performs a bunch of +// experiments. For every experiment, it orders all the readers +// involved to start and waits for them to finish the experiment. It +// then reads their timestamps and starts the next experiment. Each +// experiment progresses from 1 concurrent reader to N of them at which +// point all the timestamps are printed. +static int main_func(void *arg) +{ + bool errexit = false; + int exp, r; + char buf1[64]; + char *buf; + u64 *result_avg; + + set_cpus_allowed_ptr(current, cpumask_of(nreaders % nr_cpu_ids)); + set_user_nice(current, MAX_NICE); + + VERBOSE_SCALEOUT("main_func task started"); + result_avg = kzalloc(nruns * sizeof(*result_avg), GFP_KERNEL); + buf = kzalloc(64 + nruns * 32, GFP_KERNEL); + if (!result_avg || !buf) { + VERBOSE_SCALEOUT_ERRSTRING("out of memory"); + errexit = true; + } + if (holdoff) + schedule_timeout_interruptible(holdoff * HZ); + + // Wait for all threads to start. + atomic_inc(&n_init); + while (atomic_read(&n_init) < nreaders + 1) + schedule_timeout_uninterruptible(1); + + // Start exp readers up per experiment + for (exp = 0; exp < nruns && !torture_must_stop(); exp++) { + if (errexit) + break; + if (torture_must_stop()) + goto end; + + reset_readers(); + atomic_set(&nreaders_exp, nreaders); + atomic_set(&n_started, nreaders); + atomic_set(&n_warmedup, nreaders); + atomic_set(&n_cooleddown, nreaders); + + exp_idx = exp; + + for (r = 0; r < nreaders; r++) { + smp_store_release(&reader_tasks[r].start_reader, 1); + wake_up(&reader_tasks[r].wq); + } + + VERBOSE_SCALEOUT("main_func: experiment started, waiting for %d readers", + nreaders); + + wait_event(main_wq, + !atomic_read(&nreaders_exp) || torture_must_stop()); + + VERBOSE_SCALEOUT("main_func: experiment ended"); + + if (torture_must_stop()) + goto end; + + result_avg[exp] = div_u64(1000 * process_durations(nreaders), nreaders * loops); + } + + // Print the average of all experiments + SCALEOUT("END OF TEST. Calculating average duration per loop (nanoseconds)...\n"); + + buf[0] = 0; + strcat(buf, "\n"); + strcat(buf, "Runs\tTime(ns)\n"); + + for (exp = 0; exp < nruns; exp++) { + u64 avg; + u32 rem; + + if (errexit) + break; + avg = div_u64_rem(result_avg[exp], 1000, &rem); + sprintf(buf1, "%d\t%llu.%03u\n", exp + 1, avg, rem); + strcat(buf, buf1); + } + + if (!errexit) + SCALEOUT("%s", buf); + + // This will shutdown everything including us. + if (shutdown) { + shutdown_start = 1; + wake_up(&shutdown_wq); + } + + // Wait for torture to stop us + while (!torture_must_stop()) + schedule_timeout_uninterruptible(1); + +end: + torture_kthread_stopping("main_func"); + kfree(result_avg); + kfree(buf); + return 0; +} + +static void +ref_scale_print_module_parms(struct ref_scale_ops *cur_ops, const char *tag) +{ + pr_alert("%s" SCALE_FLAG + "--- %s: verbose=%d shutdown=%d holdoff=%d loops=%ld nreaders=%d nruns=%d readdelay=%d\n", scale_type, tag, + verbose, shutdown, holdoff, loops, nreaders, nruns, readdelay); +} + +static void +ref_scale_cleanup(void) +{ + int i; + + if (torture_cleanup_begin()) + return; + + if (!cur_ops) { + torture_cleanup_end(); + return; + } + + if (reader_tasks) { + for (i = 0; i < nreaders; i++) + torture_stop_kthread("ref_scale_reader", + reader_tasks[i].task); + } + kfree(reader_tasks); + + torture_stop_kthread("main_task", main_task); + kfree(main_task); + + // Do scale-type-specific cleanup operations. + if (cur_ops->cleanup != NULL) + cur_ops->cleanup(); + + torture_cleanup_end(); +} + +// Shutdown kthread. Just waits to be awakened, then shuts down system. +static int +ref_scale_shutdown(void *arg) +{ + wait_event(shutdown_wq, shutdown_start); + + smp_mb(); // Wake before output. + ref_scale_cleanup(); + kernel_power_off(); + + return -EINVAL; +} + +static int __init +ref_scale_init(void) +{ + long i; + int firsterr = 0; + static struct ref_scale_ops *scale_ops[] = { + &rcu_ops, &srcu_ops, &rcu_trace_ops, &rcu_tasks_ops, + &refcnt_ops, &rwlock_ops, &rwsem_ops, + }; + + if (!torture_init_begin(scale_type, verbose)) + return -EBUSY; + + for (i = 0; i < ARRAY_SIZE(scale_ops); i++) { + cur_ops = scale_ops[i]; + if (strcmp(scale_type, cur_ops->name) == 0) + break; + } + if (i == ARRAY_SIZE(scale_ops)) { + pr_alert("rcu-scale: invalid scale type: \"%s\"\n", scale_type); + pr_alert("rcu-scale types:"); + for (i = 0; i < ARRAY_SIZE(scale_ops); i++) + pr_cont(" %s", scale_ops[i]->name); + pr_cont("\n"); + WARN_ON(!IS_MODULE(CONFIG_RCU_REF_SCALE_TEST)); + firsterr = -EINVAL; + cur_ops = NULL; + goto unwind; + } + if (cur_ops->init) + cur_ops->init(); + + ref_scale_print_module_parms(cur_ops, "Start of test"); + + // Shutdown task + if (shutdown) { + init_waitqueue_head(&shutdown_wq); + firsterr = torture_create_kthread(ref_scale_shutdown, NULL, + shutdown_task); + if (firsterr) + goto unwind; + schedule_timeout_uninterruptible(1); + } + + // Reader tasks (default to ~75% of online CPUs). + if (nreaders < 0) + nreaders = (num_online_cpus() >> 1) + (num_online_cpus() >> 2); + reader_tasks = kcalloc(nreaders, sizeof(reader_tasks[0]), + GFP_KERNEL); + if (!reader_tasks) { + VERBOSE_SCALEOUT_ERRSTRING("out of memory"); + firsterr = -ENOMEM; + goto unwind; + } + + VERBOSE_SCALEOUT("Starting %d reader threads\n", nreaders); + + for (i = 0; i < nreaders; i++) { + firsterr = torture_create_kthread(ref_scale_reader, (void *)i, + reader_tasks[i].task); + if (firsterr) + goto unwind; + + init_waitqueue_head(&(reader_tasks[i].wq)); + } + + // Main Task + init_waitqueue_head(&main_wq); + firsterr = torture_create_kthread(main_func, NULL, main_task); + if (firsterr) + goto unwind; + + torture_init_end(); + return 0; + +unwind: + torture_init_end(); + ref_scale_cleanup(); + return firsterr; +} + +module_init(ref_scale_init); +module_exit(ref_scale_cleanup); diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 6d3ef700fb0e..c100acf332ed 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -766,7 +766,7 @@ static void srcu_flip(struct srcu_struct *ssp) * it, if this function was preempted for enough time for the counters * to wrap, it really doesn't matter whether or not we expedite the grace * period. The extra overhead of a needlessly expedited grace period is - * negligible when amoritized over that time period, and the extra latency + * negligible when amortized over that time period, and the extra latency * of a needlessly non-expedited grace period is similarly negligible. */ static bool srcu_might_be_idle(struct srcu_struct *ssp) @@ -777,14 +777,15 @@ static bool srcu_might_be_idle(struct srcu_struct *ssp) unsigned long t; unsigned long tlast; + check_init_srcu_struct(ssp); /* If the local srcu_data structure has callbacks, not idle. */ - local_irq_save(flags); - sdp = this_cpu_ptr(ssp->sda); + sdp = raw_cpu_ptr(ssp->sda); + spin_lock_irqsave_rcu_node(sdp, flags); if (rcu_segcblist_pend_cbs(&sdp->srcu_cblist)) { - local_irq_restore(flags); + spin_unlock_irqrestore_rcu_node(sdp, flags); return false; /* Callbacks already present, so not idle. */ } - local_irq_restore(flags); + spin_unlock_irqrestore_rcu_node(sdp, flags); /* * No local callbacks, so probabalistically probe global state. @@ -864,9 +865,8 @@ static void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp, } rhp->func = func; idx = srcu_read_lock(ssp); - local_irq_save(flags); - sdp = this_cpu_ptr(ssp->sda); - spin_lock_rcu_node(sdp); + sdp = raw_cpu_ptr(ssp->sda); + spin_lock_irqsave_rcu_node(sdp, flags); rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp); rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&ssp->srcu_gp_seq)); diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index ce23f6cc5043..835e2df8590a 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -103,6 +103,7 @@ module_param(rcu_task_stall_timeout, int, 0644); #define RTGS_WAIT_READERS 9 #define RTGS_INVOKE_CBS 10 #define RTGS_WAIT_CBS 11 +#ifndef CONFIG_TINY_RCU static const char * const rcu_tasks_gp_state_names[] = { "RTGS_INIT", "RTGS_WAIT_WAIT_CBS", @@ -117,6 +118,7 @@ static const char * const rcu_tasks_gp_state_names[] = { "RTGS_INVOKE_CBS", "RTGS_WAIT_CBS", }; +#endif /* #ifndef CONFIG_TINY_RCU */ //////////////////////////////////////////////////////////////////////// // @@ -129,6 +131,7 @@ static void set_tasks_gp_state(struct rcu_tasks *rtp, int newstate) rtp->gp_jiffies = jiffies; } +#ifndef CONFIG_TINY_RCU /* Return state name. */ static const char *tasks_gp_state_getname(struct rcu_tasks *rtp) { @@ -139,6 +142,7 @@ static const char *tasks_gp_state_getname(struct rcu_tasks *rtp) return "???"; return rcu_tasks_gp_state_names[j]; } +#endif /* #ifndef CONFIG_TINY_RCU */ // Enqueue a callback for the specified flavor of Tasks RCU. static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func, @@ -205,7 +209,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) if (!rtp->cbs_head) { WARN_ON(signal_pending(current)); set_tasks_gp_state(rtp, RTGS_WAIT_WAIT_CBS); - schedule_timeout_interruptible(HZ/10); + schedule_timeout_idle(HZ/10); } continue; } @@ -227,7 +231,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) cond_resched(); } /* Paranoid sleep to keep this from entering a tight loop */ - schedule_timeout_uninterruptible(HZ/10); + schedule_timeout_idle(HZ/10); set_tasks_gp_state(rtp, RTGS_WAIT_CBS); } @@ -268,6 +272,7 @@ static void __init rcu_tasks_bootup_oddness(void) #endif /* #ifndef CONFIG_TINY_RCU */ +#ifndef CONFIG_TINY_RCU /* Dump out rcutorture-relevant state common to all RCU-tasks flavors. */ static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s) { @@ -281,6 +286,7 @@ static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s) ".C"[!!data_race(rtp->cbs_head)], s); } +#endif /* #ifndef CONFIG_TINY_RCU */ static void exit_tasks_rcu_finish_trace(struct task_struct *t); @@ -336,7 +342,7 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp) /* Slowly back off waiting for holdouts */ set_tasks_gp_state(rtp, RTGS_WAIT_SCAN_HOLDOUTS); - schedule_timeout_interruptible(HZ/fract); + schedule_timeout_idle(HZ/fract); if (fract > 1) fract--; @@ -402,7 +408,7 @@ static void rcu_tasks_pertask(struct task_struct *t, struct list_head *hop) } /* Processing between scanning taskslist and draining the holdout list. */ -void rcu_tasks_postscan(struct list_head *hop) +static void rcu_tasks_postscan(struct list_head *hop) { /* * Wait for tasks that are in the process of exiting. This @@ -557,10 +563,12 @@ static int __init rcu_spawn_tasks_kthread(void) } core_initcall(rcu_spawn_tasks_kthread); +#ifndef CONFIG_TINY_RCU static void show_rcu_tasks_classic_gp_kthread(void) { show_rcu_tasks_generic_gp_kthread(&rcu_tasks, ""); } +#endif /* #ifndef CONFIG_TINY_RCU */ /* Do the srcu_read_lock() for the above synchronize_srcu(). */ void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu) @@ -682,10 +690,12 @@ static int __init rcu_spawn_tasks_rude_kthread(void) } core_initcall(rcu_spawn_tasks_rude_kthread); +#ifndef CONFIG_TINY_RCU static void show_rcu_tasks_rude_gp_kthread(void) { show_rcu_tasks_generic_gp_kthread(&rcu_tasks_rude, ""); } +#endif /* #ifndef CONFIG_TINY_RCU */ #else /* #ifdef CONFIG_TASKS_RUDE_RCU */ static void show_rcu_tasks_rude_gp_kthread(void) {} @@ -727,8 +737,8 @@ EXPORT_SYMBOL_GPL(rcu_trace_lock_map); #ifdef CONFIG_TASKS_TRACE_RCU -atomic_t trc_n_readers_need_end; // Number of waited-for readers. -DECLARE_WAIT_QUEUE_HEAD(trc_wait); // List of holdout tasks. +static atomic_t trc_n_readers_need_end; // Number of waited-for readers. +static DECLARE_WAIT_QUEUE_HEAD(trc_wait); // List of holdout tasks. // Record outstanding IPIs to each CPU. No point in sending two... static DEFINE_PER_CPU(bool, trc_ipi_to_cpu); @@ -835,7 +845,7 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg) bool ofl = cpu_is_offline(cpu); if (task_curr(t)) { - WARN_ON_ONCE(ofl & !is_idle_task(t)); + WARN_ON_ONCE(ofl && !is_idle_task(t)); // If no chance of heavyweight readers, do it the hard way. if (!ofl && !IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) @@ -1118,11 +1128,10 @@ EXPORT_SYMBOL_GPL(call_rcu_tasks_trace); * synchronize_rcu_tasks_trace - wait for a trace rcu-tasks grace period * * Control will return to the caller some time after a trace rcu-tasks - * grace period has elapsed, in other words after all currently - * executing rcu-tasks read-side critical sections have elapsed. These - * read-side critical sections are delimited by calls to schedule(), - * cond_resched_tasks_rcu_qs(), userspace execution, and (in theory, - * anyway) cond_resched(). + * grace period has elapsed, in other words after all currently executing + * rcu-tasks read-side critical sections have elapsed. These read-side + * critical sections are delimited by calls to rcu_read_lock_trace() + * and rcu_read_unlock_trace(). * * This is a very specialized primitive, intended only for a few uses in * tracing and other situations requiring manipulation of function preambles @@ -1164,6 +1173,7 @@ static int __init rcu_spawn_tasks_trace_kthread(void) } core_initcall(rcu_spawn_tasks_trace_kthread); +#ifndef CONFIG_TINY_RCU static void show_rcu_tasks_trace_gp_kthread(void) { char buf[64]; @@ -1174,18 +1184,21 @@ static void show_rcu_tasks_trace_gp_kthread(void) data_race(n_heavy_reader_attempts)); show_rcu_tasks_generic_gp_kthread(&rcu_tasks_trace, buf); } +#endif /* #ifndef CONFIG_TINY_RCU */ #else /* #ifdef CONFIG_TASKS_TRACE_RCU */ static void exit_tasks_rcu_finish_trace(struct task_struct *t) { } static inline void show_rcu_tasks_trace_gp_kthread(void) {} #endif /* #else #ifdef CONFIG_TASKS_TRACE_RCU */ +#ifndef CONFIG_TINY_RCU void show_rcu_tasks_gp_kthreads(void) { show_rcu_tasks_classic_gp_kthread(); show_rcu_tasks_rude_gp_kthread(); show_rcu_tasks_trace_gp_kthread(); } +#endif /* #ifndef CONFIG_TINY_RCU */ #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ static inline void rcu_tasks_bootup_oddness(void) {} diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index dd572ce7c747..aa897c3f2e92 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -23,6 +23,7 @@ #include <linux/cpu.h> #include <linux/prefetch.h> #include <linux/slab.h> +#include <linux/mm.h> #include "rcu.h" @@ -84,9 +85,9 @@ static inline bool rcu_reclaim_tiny(struct rcu_head *head) unsigned long offset = (unsigned long)head->func; rcu_lock_acquire(&rcu_callback_map); - if (__is_kfree_rcu_offset(offset)) { - trace_rcu_invoke_kfree_callback("", head, offset); - kfree((void *)head - offset); + if (__is_kvfree_rcu_offset(offset)) { + trace_rcu_invoke_kvfree_callback("", head, offset); + kvfree((void *)head - offset); rcu_lock_release(&rcu_callback_map); return true; } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 6c6569e0586c..ac7198ed3197 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -57,6 +57,8 @@ #include <linux/slab.h> #include <linux/sched/isolation.h> #include <linux/sched/clock.h> +#include <linux/vmalloc.h> +#include <linux/mm.h> #include "../time/tick-internal.h" #include "tree.h" @@ -175,6 +177,15 @@ module_param(gp_init_delay, int, 0444); static int gp_cleanup_delay; module_param(gp_cleanup_delay, int, 0444); +/* + * This rcu parameter is runtime-read-only. It reflects + * a minimum allowed number of objects which can be cached + * per-CPU. Object size is equal to one page. This value + * can be changed at boot time. + */ +static int rcu_min_cached_objs = 2; +module_param(rcu_min_cached_objs, int, 0444); + /* Retrieve RCU kthreads priority for rcutorture */ int rcu_get_gp_kthreads_prio(void) { @@ -954,7 +965,6 @@ void __rcu_irq_enter_check_tick(void) /** * rcu_nmi_enter - inform RCU of entry to NMI context - * @irq: Is this call from rcu_irq_enter? * * If the CPU was idle from RCU's viewpoint, update rdp->dynticks and * rdp->dynticks_nmi_nesting to let the RCU grace-period handling know @@ -990,8 +1000,11 @@ noinstr void rcu_nmi_enter(void) rcu_dynticks_eqs_exit(); // ... but is watching here. - if (!in_nmi()) + if (!in_nmi()) { + instrumentation_begin(); rcu_cleanup_after_idle(); + instrumentation_end(); + } instrumentation_begin(); // instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs() @@ -1638,7 +1651,7 @@ static void rcu_gp_slow(int delay) if (delay > 0 && !(rcu_seq_ctr(rcu_state.gp_seq) % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay))) - schedule_timeout_uninterruptible(delay); + schedule_timeout_idle(delay); } static unsigned long sleep_duration; @@ -1661,7 +1674,7 @@ static void rcu_gp_torture_wait(void) duration = xchg(&sleep_duration, 0UL); if (duration > 0) { pr_alert("%s: Waiting %lu jiffies\n", __func__, duration); - schedule_timeout_uninterruptible(duration); + schedule_timeout_idle(duration); pr_alert("%s: Wait complete\n", __func__); } } @@ -2443,6 +2456,7 @@ static void rcu_do_batch(struct rcu_data *rdp) local_irq_save(flags); rcu_nocb_lock(rdp); count = -rcl.len; + rdp->n_cbs_invoked += count; trace_rcu_batch_end(rcu_state.name, count, !!rcl.head, need_resched(), is_idle_task(current), rcu_is_callbacks_kthread()); @@ -2726,7 +2740,7 @@ static void rcu_cpu_kthread(unsigned int cpu) } *statusp = RCU_KTHREAD_YIELDING; trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); - schedule_timeout_interruptible(2); + schedule_timeout_idle(2); trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); *statusp = RCU_KTHREAD_WAITING; } @@ -2894,8 +2908,8 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func) return; // Enqueued onto ->nocb_bypass, so just leave. // If no-CBs CPU gets here, rcu_nocb_try_bypass() acquired ->nocb_lock. rcu_segcblist_enqueue(&rdp->cblist, head); - if (__is_kfree_rcu_offset((unsigned long)func)) - trace_rcu_kfree_callback(rcu_state.name, head, + if (__is_kvfree_rcu_offset((unsigned long)func)) + trace_rcu_kvfree_callback(rcu_state.name, head, (unsigned long)func, rcu_segcblist_n_cbs(&rdp->cblist)); else @@ -2957,53 +2971,53 @@ EXPORT_SYMBOL_GPL(call_rcu); /* Maximum number of jiffies to wait before draining a batch. */ #define KFREE_DRAIN_JIFFIES (HZ / 50) #define KFREE_N_BATCHES 2 - -/* - * This macro defines how many entries the "records" array - * will contain. It is based on the fact that the size of - * kfree_rcu_bulk_data structure becomes exactly one page. - */ -#define KFREE_BULK_MAX_ENTR ((PAGE_SIZE / sizeof(void *)) - 3) +#define FREE_N_CHANNELS 2 /** - * struct kfree_rcu_bulk_data - single block to store kfree_rcu() pointers + * struct kvfree_rcu_bulk_data - single block to store kvfree_rcu() pointers * @nr_records: Number of active pointers in the array - * @records: Array of the kfree_rcu() pointers * @next: Next bulk object in the block chain - * @head_free_debug: For debug, when CONFIG_DEBUG_OBJECTS_RCU_HEAD is set + * @records: Array of the kvfree_rcu() pointers */ -struct kfree_rcu_bulk_data { +struct kvfree_rcu_bulk_data { unsigned long nr_records; - void *records[KFREE_BULK_MAX_ENTR]; - struct kfree_rcu_bulk_data *next; - struct rcu_head *head_free_debug; + struct kvfree_rcu_bulk_data *next; + void *records[]; }; +/* + * This macro defines how many entries the "records" array + * will contain. It is based on the fact that the size of + * kvfree_rcu_bulk_data structure becomes exactly one page. + */ +#define KVFREE_BULK_MAX_ENTR \ + ((PAGE_SIZE - sizeof(struct kvfree_rcu_bulk_data)) / sizeof(void *)) + /** * struct kfree_rcu_cpu_work - single batch of kfree_rcu() requests * @rcu_work: Let queue_rcu_work() invoke workqueue handler after grace period * @head_free: List of kfree_rcu() objects waiting for a grace period - * @bhead_free: Bulk-List of kfree_rcu() objects waiting for a grace period + * @bkvhead_free: Bulk-List of kvfree_rcu() objects waiting for a grace period * @krcp: Pointer to @kfree_rcu_cpu structure */ struct kfree_rcu_cpu_work { struct rcu_work rcu_work; struct rcu_head *head_free; - struct kfree_rcu_bulk_data *bhead_free; + struct kvfree_rcu_bulk_data *bkvhead_free[FREE_N_CHANNELS]; struct kfree_rcu_cpu *krcp; }; /** * struct kfree_rcu_cpu - batch up kfree_rcu() requests for RCU grace period * @head: List of kfree_rcu() objects not yet waiting for a grace period - * @bhead: Bulk-List of kfree_rcu() objects not yet waiting for a grace period - * @bcached: Keeps at most one object for later reuse when build chain blocks + * @bkvhead: Bulk-List of kvfree_rcu() objects not yet waiting for a grace period * @krw_arr: Array of batches of kfree_rcu() objects waiting for a grace period * @lock: Synchronize access to this structure * @monitor_work: Promote @head to @head_free after KFREE_DRAIN_JIFFIES * @monitor_todo: Tracks whether a @monitor_work delayed work is pending - * @initialized: The @lock and @rcu_work fields have been initialized + * @initialized: The @rcu_work fields have been initialized + * @count: Number of objects for which GP not started * * This is a per-CPU structure. The reason that it is not included in * the rcu_data structure is to permit this code to be extracted from @@ -3012,28 +3026,84 @@ struct kfree_rcu_cpu_work { */ struct kfree_rcu_cpu { struct rcu_head *head; - struct kfree_rcu_bulk_data *bhead; - struct kfree_rcu_bulk_data *bcached; + struct kvfree_rcu_bulk_data *bkvhead[FREE_N_CHANNELS]; struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES]; - spinlock_t lock; + raw_spinlock_t lock; struct delayed_work monitor_work; bool monitor_todo; bool initialized; - // Number of objects for which GP not started int count; + + /* + * A simple cache list that contains objects for + * reuse purpose. In order to save some per-cpu + * space the list is singular. Even though it is + * lockless an access has to be protected by the + * per-cpu lock. + */ + struct llist_head bkvcache; + int nr_bkv_objs; }; -static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc); +static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc) = { + .lock = __RAW_SPIN_LOCK_UNLOCKED(krc.lock), +}; static __always_inline void -debug_rcu_head_unqueue_bulk(struct rcu_head *head) +debug_rcu_bhead_unqueue(struct kvfree_rcu_bulk_data *bhead) { #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD - for (; head; head = head->next) - debug_rcu_head_unqueue(head); + int i; + + for (i = 0; i < bhead->nr_records; i++) + debug_rcu_head_unqueue((struct rcu_head *)(bhead->records[i])); #endif } +static inline struct kfree_rcu_cpu * +krc_this_cpu_lock(unsigned long *flags) +{ + struct kfree_rcu_cpu *krcp; + + local_irq_save(*flags); // For safely calling this_cpu_ptr(). + krcp = this_cpu_ptr(&krc); + raw_spin_lock(&krcp->lock); + + return krcp; +} + +static inline void +krc_this_cpu_unlock(struct kfree_rcu_cpu *krcp, unsigned long flags) +{ + raw_spin_unlock(&krcp->lock); + local_irq_restore(flags); +} + +static inline struct kvfree_rcu_bulk_data * +get_cached_bnode(struct kfree_rcu_cpu *krcp) +{ + if (!krcp->nr_bkv_objs) + return NULL; + + krcp->nr_bkv_objs--; + return (struct kvfree_rcu_bulk_data *) + llist_del_first(&krcp->bkvcache); +} + +static inline bool +put_cached_bnode(struct kfree_rcu_cpu *krcp, + struct kvfree_rcu_bulk_data *bnode) +{ + // Check the limit. + if (krcp->nr_bkv_objs >= rcu_min_cached_objs) + return false; + + llist_add((struct llist_node *) bnode, &krcp->bkvcache); + krcp->nr_bkv_objs++; + return true; + +} + /* * This function is invoked in workqueue context after a grace period. * It frees all the objects queued on ->bhead_free or ->head_free. @@ -3041,38 +3111,63 @@ debug_rcu_head_unqueue_bulk(struct rcu_head *head) static void kfree_rcu_work(struct work_struct *work) { unsigned long flags; + struct kvfree_rcu_bulk_data *bkvhead[FREE_N_CHANNELS], *bnext; struct rcu_head *head, *next; - struct kfree_rcu_bulk_data *bhead, *bnext; struct kfree_rcu_cpu *krcp; struct kfree_rcu_cpu_work *krwp; + int i, j; krwp = container_of(to_rcu_work(work), struct kfree_rcu_cpu_work, rcu_work); krcp = krwp->krcp; - spin_lock_irqsave(&krcp->lock, flags); - head = krwp->head_free; - krwp->head_free = NULL; - bhead = krwp->bhead_free; - krwp->bhead_free = NULL; - spin_unlock_irqrestore(&krcp->lock, flags); - - /* "bhead" is now private, so traverse locklessly. */ - for (; bhead; bhead = bnext) { - bnext = bhead->next; - debug_rcu_head_unqueue_bulk(bhead->head_free_debug); + raw_spin_lock_irqsave(&krcp->lock, flags); + // Channels 1 and 2. + for (i = 0; i < FREE_N_CHANNELS; i++) { + bkvhead[i] = krwp->bkvhead_free[i]; + krwp->bkvhead_free[i] = NULL; + } - rcu_lock_acquire(&rcu_callback_map); - trace_rcu_invoke_kfree_bulk_callback(rcu_state.name, - bhead->nr_records, bhead->records); + // Channel 3. + head = krwp->head_free; + krwp->head_free = NULL; + raw_spin_unlock_irqrestore(&krcp->lock, flags); + + // Handle two first channels. + for (i = 0; i < FREE_N_CHANNELS; i++) { + for (; bkvhead[i]; bkvhead[i] = bnext) { + bnext = bkvhead[i]->next; + debug_rcu_bhead_unqueue(bkvhead[i]); + + rcu_lock_acquire(&rcu_callback_map); + if (i == 0) { // kmalloc() / kfree(). + trace_rcu_invoke_kfree_bulk_callback( + rcu_state.name, bkvhead[i]->nr_records, + bkvhead[i]->records); + + kfree_bulk(bkvhead[i]->nr_records, + bkvhead[i]->records); + } else { // vmalloc() / vfree(). + for (j = 0; j < bkvhead[i]->nr_records; j++) { + trace_rcu_invoke_kvfree_callback( + rcu_state.name, + bkvhead[i]->records[j], 0); + + vfree(bkvhead[i]->records[j]); + } + } + rcu_lock_release(&rcu_callback_map); - kfree_bulk(bhead->nr_records, bhead->records); - rcu_lock_release(&rcu_callback_map); + krcp = krc_this_cpu_lock(&flags); + if (put_cached_bnode(krcp, bkvhead[i])) + bkvhead[i] = NULL; + krc_this_cpu_unlock(krcp, flags); - if (cmpxchg(&krcp->bcached, NULL, bhead)) - free_page((unsigned long) bhead); + if (bkvhead[i]) + free_page((unsigned long) bkvhead[i]); - cond_resched_tasks_rcu_qs(); + cond_resched_tasks_rcu_qs(); + } } /* @@ -3082,14 +3177,15 @@ static void kfree_rcu_work(struct work_struct *work) */ for (; head; head = next) { unsigned long offset = (unsigned long)head->func; + void *ptr = (void *)head - offset; next = head->next; - debug_rcu_head_unqueue(head); + debug_rcu_head_unqueue((struct rcu_head *)ptr); rcu_lock_acquire(&rcu_callback_map); - trace_rcu_invoke_kfree_callback(rcu_state.name, head, offset); + trace_rcu_invoke_kvfree_callback(rcu_state.name, head, offset); - if (!WARN_ON_ONCE(!__is_kfree_rcu_offset(offset))) - kfree((void *)head - offset); + if (!WARN_ON_ONCE(!__is_kvfree_rcu_offset(offset))) + kvfree(ptr); rcu_lock_release(&rcu_callback_map); cond_resched_tasks_rcu_qs(); @@ -3105,8 +3201,8 @@ static void kfree_rcu_work(struct work_struct *work) static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp) { struct kfree_rcu_cpu_work *krwp; - bool queued = false; - int i; + bool repeat = false; + int i, j; lockdep_assert_held(&krcp->lock); @@ -3114,21 +3210,25 @@ static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp) krwp = &(krcp->krw_arr[i]); /* - * Try to detach bhead or head and attach it over any + * Try to detach bkvhead or head and attach it over any * available corresponding free channel. It can be that * a previous RCU batch is in progress, it means that * immediately to queue another one is not possible so * return false to tell caller to retry. */ - if ((krcp->bhead && !krwp->bhead_free) || + if ((krcp->bkvhead[0] && !krwp->bkvhead_free[0]) || + (krcp->bkvhead[1] && !krwp->bkvhead_free[1]) || (krcp->head && !krwp->head_free)) { - /* Channel 1. */ - if (!krwp->bhead_free) { - krwp->bhead_free = krcp->bhead; - krcp->bhead = NULL; + // Channel 1 corresponds to SLAB ptrs. + // Channel 2 corresponds to vmalloc ptrs. + for (j = 0; j < FREE_N_CHANNELS; j++) { + if (!krwp->bkvhead_free[j]) { + krwp->bkvhead_free[j] = krcp->bkvhead[j]; + krcp->bkvhead[j] = NULL; + } } - /* Channel 2. */ + // Channel 3 corresponds to emergency path. if (!krwp->head_free) { krwp->head_free = krcp->head; krcp->head = NULL; @@ -3137,17 +3237,21 @@ static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp) WRITE_ONCE(krcp->count, 0); /* - * One work is per one batch, so there are two "free channels", - * "bhead_free" and "head_free" the batch can handle. It can be - * that the work is in the pending state when two channels have - * been detached following each other, one by one. + * One work is per one batch, so there are three + * "free channels", the batch can handle. It can + * be that the work is in the pending state when + * channels have been detached following by each + * other. */ queue_rcu_work(system_wq, &krwp->rcu_work); - queued = true; } + + // Repeat if any "free" corresponding channel is still busy. + if (krcp->bkvhead[0] || krcp->bkvhead[1] || krcp->head) + repeat = true; } - return queued; + return !repeat; } static inline void kfree_rcu_drain_unlock(struct kfree_rcu_cpu *krcp, @@ -3157,14 +3261,14 @@ static inline void kfree_rcu_drain_unlock(struct kfree_rcu_cpu *krcp, krcp->monitor_todo = false; if (queue_kfree_rcu_work(krcp)) { // Success! Our job is done here. - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); return; } // Previous RCU batch still in progress, try again later. krcp->monitor_todo = true; schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES); - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); } /* @@ -3177,32 +3281,50 @@ static void kfree_rcu_monitor(struct work_struct *work) struct kfree_rcu_cpu *krcp = container_of(work, struct kfree_rcu_cpu, monitor_work.work); - spin_lock_irqsave(&krcp->lock, flags); + raw_spin_lock_irqsave(&krcp->lock, flags); if (krcp->monitor_todo) kfree_rcu_drain_unlock(krcp, flags); else - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); } static inline bool -kfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, - struct rcu_head *head, rcu_callback_t func) +kvfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, void *ptr) { - struct kfree_rcu_bulk_data *bnode; + struct kvfree_rcu_bulk_data *bnode; + int idx; if (unlikely(!krcp->initialized)) return false; lockdep_assert_held(&krcp->lock); + idx = !!is_vmalloc_addr(ptr); /* Check if a new block is required. */ - if (!krcp->bhead || - krcp->bhead->nr_records == KFREE_BULK_MAX_ENTR) { - bnode = xchg(&krcp->bcached, NULL); + if (!krcp->bkvhead[idx] || + krcp->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) { + bnode = get_cached_bnode(krcp); if (!bnode) { - WARN_ON_ONCE(sizeof(struct kfree_rcu_bulk_data) > PAGE_SIZE); + /* + * To keep this path working on raw non-preemptible + * sections, prevent the optional entry into the + * allocator as it uses sleeping locks. In fact, even + * if the caller of kfree_rcu() is preemptible, this + * path still is not, as krcp->lock is a raw spinlock. + * With additional page pre-allocation in the works, + * hitting this return is going to be much less likely. + */ + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + return false; - bnode = (struct kfree_rcu_bulk_data *) + /* + * NOTE: For one argument of kvfree_rcu() we can + * drop the lock and get the page in sleepable + * context. That would allow to maintain an array + * for the CONFIG_PREEMPT_RT as well if no cached + * pages are available. + */ + bnode = (struct kvfree_rcu_bulk_data *) __get_free_page(GFP_NOWAIT | __GFP_NOWARN); } @@ -3212,53 +3334,62 @@ kfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, /* Initialize the new block. */ bnode->nr_records = 0; - bnode->next = krcp->bhead; - bnode->head_free_debug = NULL; + bnode->next = krcp->bkvhead[idx]; /* Attach it to the head. */ - krcp->bhead = bnode; + krcp->bkvhead[idx] = bnode; } -#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD - head->func = func; - head->next = krcp->bhead->head_free_debug; - krcp->bhead->head_free_debug = head; -#endif - /* Finally insert. */ - krcp->bhead->records[krcp->bhead->nr_records++] = - (void *) head - (unsigned long) func; + krcp->bkvhead[idx]->records + [krcp->bkvhead[idx]->nr_records++] = ptr; return true; } /* - * Queue a request for lazy invocation of kfree_bulk()/kfree() after a grace - * period. Please note there are two paths are maintained, one is the main one - * that uses kfree_bulk() interface and second one is emergency one, that is - * used only when the main path can not be maintained temporary, due to memory - * pressure. + * Queue a request for lazy invocation of appropriate free routine after a + * grace period. Please note there are three paths are maintained, two are the + * main ones that use array of pointers interface and third one is emergency + * one, that is used only when the main path can not be maintained temporary, + * due to memory pressure. * - * Each kfree_call_rcu() request is added to a batch. The batch will be drained + * Each kvfree_call_rcu() request is added to a batch. The batch will be drained * every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch will * be free'd in workqueue context. This allows us to: batch requests together to - * reduce the number of grace periods during heavy kfree_rcu() load. + * reduce the number of grace periods during heavy kfree_rcu()/kvfree_rcu() load. */ -void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func) +void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func) { unsigned long flags; struct kfree_rcu_cpu *krcp; + bool success; + void *ptr; - local_irq_save(flags); // For safely calling this_cpu_ptr(). - krcp = this_cpu_ptr(&krc); - if (krcp->initialized) - spin_lock(&krcp->lock); + if (head) { + ptr = (void *) head - (unsigned long) func; + } else { + /* + * Please note there is a limitation for the head-less + * variant, that is why there is a clear rule for such + * objects: it can be used from might_sleep() context + * only. For other places please embed an rcu_head to + * your data. + */ + might_sleep(); + ptr = (unsigned long *) func; + } + + krcp = krc_this_cpu_lock(&flags); // Queue the object but don't yet schedule the batch. - if (debug_rcu_head_queue(head)) { + if (debug_rcu_head_queue(ptr)) { // Probable double kfree_rcu(), just leak. WARN_ONCE(1, "%s(): Double-freed call. rcu_head %p\n", __func__, head); + + // Mark as success and leave. + success = true; goto unlock_return; } @@ -3266,10 +3397,16 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func) * Under high memory pressure GFP_NOWAIT can fail, * in that case the emergency path is maintained. */ - if (unlikely(!kfree_call_rcu_add_ptr_to_bulk(krcp, head, func))) { + success = kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr); + if (!success) { + if (head == NULL) + // Inline if kvfree_rcu(one_arg) call. + goto unlock_return; + head->func = func; head->next = krcp->head; krcp->head = head; + success = true; } WRITE_ONCE(krcp->count, krcp->count + 1); @@ -3282,11 +3419,20 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func) } unlock_return: - if (krcp->initialized) - spin_unlock(&krcp->lock); - local_irq_restore(flags); + krc_this_cpu_unlock(krcp, flags); + + /* + * Inline kvfree() after synchronize_rcu(). We can do + * it from might_sleep() context only, so the current + * CPU can pass the QS state. + */ + if (!success) { + debug_rcu_head_unqueue((struct rcu_head *) ptr); + synchronize_rcu(); + kvfree(ptr); + } } -EXPORT_SYMBOL_GPL(kfree_call_rcu); +EXPORT_SYMBOL_GPL(kvfree_call_rcu); static unsigned long kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc) @@ -3315,11 +3461,11 @@ kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); count = krcp->count; - spin_lock_irqsave(&krcp->lock, flags); + raw_spin_lock_irqsave(&krcp->lock, flags); if (krcp->monitor_todo) kfree_rcu_drain_unlock(krcp, flags); else - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); sc->nr_to_scan -= count; freed += count; @@ -3328,7 +3474,7 @@ kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) break; } - return freed; + return freed == 0 ? SHRINK_STOP : freed; } static struct shrinker kfree_rcu_shrinker = { @@ -3346,15 +3492,15 @@ void __init kfree_rcu_scheduler_running(void) for_each_online_cpu(cpu) { struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); - spin_lock_irqsave(&krcp->lock, flags); + raw_spin_lock_irqsave(&krcp->lock, flags); if (!krcp->head || krcp->monitor_todo) { - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); continue; } krcp->monitor_todo = true; schedule_delayed_work_on(cpu, &krcp->monitor_work, KFREE_DRAIN_JIFFIES); - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); } } @@ -3842,10 +3988,9 @@ void rcu_cpu_starting(unsigned int cpu) { unsigned long flags; unsigned long mask; - int nbits; - unsigned long oldmask; struct rcu_data *rdp; struct rcu_node *rnp; + bool newcpu; if (per_cpu(rcu_cpu_started, cpu)) return; @@ -3857,12 +4002,10 @@ void rcu_cpu_starting(unsigned int cpu) mask = rdp->grpmask; raw_spin_lock_irqsave_rcu_node(rnp, flags); WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext | mask); - oldmask = rnp->expmaskinitnext; + newcpu = !(rnp->expmaskinitnext & mask); rnp->expmaskinitnext |= mask; - oldmask ^= rnp->expmaskinitnext; - nbits = bitmap_weight(&oldmask, BITS_PER_LONG); /* Allow lockless access for expedited grace periods. */ - smp_store_release(&rcu_state.ncpus, rcu_state.ncpus + nbits); /* ^^^ */ + smp_store_release(&rcu_state.ncpus, rcu_state.ncpus + newcpu); /* ^^^ */ ASSERT_EXCLUSIVE_WRITER(rcu_state.ncpus); rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */ rdp->rcu_onl_gp_seq = READ_ONCE(rcu_state.gp_seq); @@ -4249,13 +4392,23 @@ static void __init kfree_rcu_batch_init(void) for_each_possible_cpu(cpu) { struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); + struct kvfree_rcu_bulk_data *bnode; - spin_lock_init(&krcp->lock); for (i = 0; i < KFREE_N_BATCHES; i++) { INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work); krcp->krw_arr[i].krcp = krcp; } + for (i = 0; i < rcu_min_cached_objs; i++) { + bnode = (struct kvfree_rcu_bulk_data *) + __get_free_page(GFP_NOWAIT | __GFP_NOWARN); + + if (bnode) + put_cached_bnode(krcp, bnode); + else + pr_err("Failed to preallocate for %d CPU!\n", cpu); + } + INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor); krcp->initialized = true; } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 43991a40b084..c96ae351688b 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -41,7 +41,7 @@ struct rcu_node { raw_spinlock_t __private lock; /* Root rcu_node's lock protects */ /* some rcu_state fields as well as */ /* following. */ - unsigned long gp_seq; /* Track rsp->rcu_gp_seq. */ + unsigned long gp_seq; /* Track rsp->gp_seq. */ unsigned long gp_seq_needed; /* Track furthest future GP request. */ unsigned long completedqs; /* All QSes done for this node. */ unsigned long qsmask; /* CPUs or groups that need to switch in */ @@ -73,9 +73,9 @@ struct rcu_node { unsigned long ffmask; /* Fully functional CPUs. */ unsigned long grpmask; /* Mask to apply to parent qsmask. */ /* Only one bit will be set in this mask. */ - int grplo; /* lowest-numbered CPU or group here. */ - int grphi; /* highest-numbered CPU or group here. */ - u8 grpnum; /* CPU/group number for next level up. */ + int grplo; /* lowest-numbered CPU here. */ + int grphi; /* highest-numbered CPU here. */ + u8 grpnum; /* group number for next level up. */ u8 level; /* root is at level 0. */ bool wait_blkd_tasks;/* Necessary to wait for blocked tasks to */ /* exit RCU read-side critical sections */ @@ -149,7 +149,7 @@ union rcu_noqs { /* Per-CPU data for read-copy update. */ struct rcu_data { /* 1) quiescent-state and grace-period handling : */ - unsigned long gp_seq; /* Track rsp->rcu_gp_seq counter. */ + unsigned long gp_seq; /* Track rsp->gp_seq counter. */ unsigned long gp_seq_needed; /* Track furthest future GP request. */ union rcu_noqs cpu_no_qs; /* No QSes yet for this CPU. */ bool core_needs_qs; /* Core waits for quiesc state. */ @@ -171,6 +171,7 @@ struct rcu_data { /* different grace periods. */ long qlen_last_fqs_check; /* qlen at last check for QS forcing */ + unsigned long n_cbs_invoked; /* # callbacks invoked since boot. */ unsigned long n_force_qs_snap; /* did other CPU force QS recently? */ long blimit; /* Upper limit on a processed batch */ @@ -301,6 +302,8 @@ struct rcu_state { u8 boost ____cacheline_internodealigned_in_smp; /* Subject to priority boost. */ unsigned long gp_seq; /* Grace-period sequence #. */ + unsigned long gp_max; /* Maximum GP duration in */ + /* jiffies. */ struct task_struct *gp_kthread; /* Task for grace periods. */ struct swait_queue_head gp_wq; /* Where GP task waits. */ short gp_flags; /* Commands for GP task. */ @@ -346,8 +349,6 @@ struct rcu_state { /* a reluctant CPU. */ unsigned long n_force_qs_gpstart; /* Snapshot of n_force_qs at */ /* GP start. */ - unsigned long gp_max; /* Maximum GP duration in */ - /* jiffies. */ const char *name; /* Name of structure. */ char abbr; /* Abbreviated name. */ diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 72952edad1e4..1888c0eb1216 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -403,7 +403,7 @@ retry_ipi: /* Online, so delay for a bit and try again. */ raw_spin_unlock_irqrestore_rcu_node(rnp, flags); trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("selectofl")); - schedule_timeout_uninterruptible(1); + schedule_timeout_idle(1); goto retry_ipi; } /* CPU really is offline, so we must report its QS. */ diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 352223664ebd..982fc5be5269 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1033,7 +1033,7 @@ static int rcu_boost_kthread(void *arg) if (spincnt > 10) { WRITE_ONCE(rnp->boost_kthread_status, RCU_KTHREAD_YIELDING); trace_rcu_utilization(TPS("End boost kthread@rcu_yield")); - schedule_timeout_interruptible(2); + schedule_timeout_idle(2); trace_rcu_utilization(TPS("Start boost kthread@rcu_yield")); spincnt = 0; } @@ -2005,7 +2005,7 @@ static void nocb_gp_wait(struct rcu_data *my_rdp) /* Polling, so trace if first poll in the series. */ if (gotcbs) trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Poll")); - schedule_timeout_interruptible(1); + schedule_timeout_idle(1); } else if (!needwait_gp) { /* Wait for callbacks to appear. */ trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Sleep")); diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 54a6dba0280d..b5d3b4794db4 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -237,14 +237,12 @@ struct rcu_stall_chk_rdr { */ static bool check_slow_task(struct task_struct *t, void *arg) { - struct rcu_node *rnp; struct rcu_stall_chk_rdr *rscrp = arg; if (task_curr(t)) return false; // It is running, so decline to inspect it. rscrp->nesting = t->rcu_read_lock_nesting; rscrp->rs = t->rcu_read_unlock_special; - rnp = t->rcu_blocked_node; rscrp->on_blkd_list = !list_empty(&t->rcu_node_entry); return true; } @@ -468,7 +466,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps) /* * OK, time to rat on our buddy... - * See Documentation/RCU/stallwarn.txt for info on how to debug + * See Documentation/RCU/stallwarn.rst for info on how to debug * RCU CPU stall warnings. */ pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name); @@ -535,7 +533,7 @@ static void print_cpu_stall(unsigned long gps) /* * OK, time to rat on ourselves... - * See Documentation/RCU/stallwarn.txt for info on how to debug + * See Documentation/RCU/stallwarn.rst for info on how to debug * RCU CPU stall warnings. */ pr_err("INFO: %s self-detected stall on CPU\n", rcu_state.name); @@ -649,6 +647,7 @@ static void check_cpu_stall(struct rcu_data *rdp) */ void show_rcu_gp_kthreads(void) { + unsigned long cbs = 0; int cpu; unsigned long j; unsigned long ja; @@ -690,9 +689,11 @@ void show_rcu_gp_kthreads(void) } for_each_possible_cpu(cpu) { rdp = per_cpu_ptr(&rcu_data, cpu); + cbs += data_race(rdp->n_cbs_invoked); if (rcu_segcblist_is_offloaded(&rdp->cblist)) show_rcu_nocb_state(rdp); } + pr_info("RCU callbacks invoked since boot: %lu\n", cbs); show_rcu_tasks_gp_kthreads(); } EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 84843adfd939..2de49b5d8dd2 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -42,6 +42,7 @@ #include <linux/kprobes.h> #include <linux/slab.h> #include <linux/irq_work.h> +#include <linux/rcupdate_trace.h> #define CREATE_TRACE_POINTS @@ -207,7 +208,7 @@ void rcu_end_inkernel_boot(void) rcu_unexpedite_gp(); if (rcu_normal_after_boot) WRITE_ONCE(rcu_normal, 1); - rcu_boot_ended = 1; + rcu_boot_ended = true; } /* @@ -279,6 +280,7 @@ struct lockdep_map rcu_sched_lock_map = { }; EXPORT_SYMBOL_GPL(rcu_sched_lock_map); +// Tell lockdep when RCU callbacks are being invoked. static struct lock_class_key rcu_callback_key; struct lockdep_map rcu_callback_map = STATIC_LOCKDEP_MAP_INIT("rcu_callback", &rcu_callback_key); @@ -390,13 +392,14 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, might_sleep(); continue; } - init_rcu_head_on_stack(&rs_array[i].head); - init_completion(&rs_array[i].completion); for (j = 0; j < i; j++) if (crcu_array[j] == crcu_array[i]) break; - if (j == i) + if (j == i) { + init_rcu_head_on_stack(&rs_array[i].head); + init_completion(&rs_array[i].completion); (crcu_array[i])(&rs_array[i].head, wakeme_after_rcu); + } } /* Wait for all callbacks to be invoked. */ @@ -407,9 +410,10 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, for (j = 0; j < i; j++) if (crcu_array[j] == crcu_array[i]) break; - if (j == i) + if (j == i) { wait_for_completion(&rs_array[i].completion); - destroy_rcu_head_on_stack(&rs_array[i].head); + destroy_rcu_head_on_stack(&rs_array[i].head); + } } } EXPORT_SYMBOL_GPL(__wait_rcu_gp); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 3e2dc9b8858c..f0199a4ba1ad 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -351,16 +351,24 @@ void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu); /* - * Set a per-task tick dependency. Posix CPU timers need this in order to elapse - * per task timers. + * Set a per-task tick dependency. RCU need this. Also posix CPU timers + * in order to elapse per task timers. */ void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) { - /* - * We could optimize this with just kicking the target running the task - * if that noise matters for nohz full users. - */ - tick_nohz_dep_set_all(&tsk->tick_dep_mask, bit); + if (!atomic_fetch_or(BIT(bit), &tsk->tick_dep_mask)) { + if (tsk == current) { + preempt_disable(); + tick_nohz_full_kick(); + preempt_enable(); + } else { + /* + * Some future tick_nohz_full_kick_task() + * should optimize this. + */ + tick_nohz_full_kick_all(); + } + } } EXPORT_SYMBOL_GPL(tick_nohz_dep_set_task); diff --git a/kernel/torture.c b/kernel/torture.c index a1a41484ff6d..1061492f14bd 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -45,6 +45,9 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>"); static bool disable_onoff_at_boot; module_param(disable_onoff_at_boot, bool, 0444); +static bool ftrace_dump_at_shutdown; +module_param(ftrace_dump_at_shutdown, bool, 0444); + static char *torture_type; static int verbose; @@ -527,7 +530,8 @@ static int torture_shutdown(void *arg) torture_shutdown_hook(); else VERBOSE_TOROUT_STRING("No torture_shutdown_hook(), skipping."); - rcu_ftrace_dump(DUMP_ALL); + if (ftrace_dump_at_shutdown) + rcu_ftrace_dump(DUMP_ALL); kernel_power_off(); /* Shut down the system. */ return 0; } diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c index ddc9685702b1..5cf2fe9aab9e 100644 --- a/lib/test_vmalloc.c +++ b/lib/test_vmalloc.c @@ -15,6 +15,8 @@ #include <linux/delay.h> #include <linux/rwsem.h> #include <linux/mm.h> +#include <linux/rcupdate.h> +#include <linux/slab.h> #define __param(type, name, init, msg) \ static type name = init; \ @@ -35,14 +37,18 @@ __param(int, test_loop_count, 1000000, __param(int, run_test_mask, INT_MAX, "Set tests specified in the mask.\n\n" - "\t\tid: 1, name: fix_size_alloc_test\n" - "\t\tid: 2, name: full_fit_alloc_test\n" - "\t\tid: 4, name: long_busy_list_alloc_test\n" - "\t\tid: 8, name: random_size_alloc_test\n" - "\t\tid: 16, name: fix_align_alloc_test\n" - "\t\tid: 32, name: random_size_align_alloc_test\n" - "\t\tid: 64, name: align_shift_alloc_test\n" - "\t\tid: 128, name: pcpu_alloc_test\n" + "\t\tid: 1, name: fix_size_alloc_test\n" + "\t\tid: 2, name: full_fit_alloc_test\n" + "\t\tid: 4, name: long_busy_list_alloc_test\n" + "\t\tid: 8, name: random_size_alloc_test\n" + "\t\tid: 16, name: fix_align_alloc_test\n" + "\t\tid: 32, name: random_size_align_alloc_test\n" + "\t\tid: 64, name: align_shift_alloc_test\n" + "\t\tid: 128, name: pcpu_alloc_test\n" + "\t\tid: 256, name: kvfree_rcu_1_arg_vmalloc_test\n" + "\t\tid: 512, name: kvfree_rcu_2_arg_vmalloc_test\n" + "\t\tid: 1024, name: kvfree_rcu_1_arg_slab_test\n" + "\t\tid: 2048, name: kvfree_rcu_2_arg_slab_test\n" /* Add a new test case description here. */ ); @@ -316,6 +322,83 @@ pcpu_alloc_test(void) return rv; } +struct test_kvfree_rcu { + struct rcu_head rcu; + unsigned char array[20]; +}; + +static int +kvfree_rcu_1_arg_vmalloc_test(void) +{ + struct test_kvfree_rcu *p; + int i; + + for (i = 0; i < test_loop_count; i++) { + p = vmalloc(1 * PAGE_SIZE); + if (!p) + return -1; + + p->array[0] = 'a'; + kvfree_rcu(p); + } + + return 0; +} + +static int +kvfree_rcu_2_arg_vmalloc_test(void) +{ + struct test_kvfree_rcu *p; + int i; + + for (i = 0; i < test_loop_count; i++) { + p = vmalloc(1 * PAGE_SIZE); + if (!p) + return -1; + + p->array[0] = 'a'; + kvfree_rcu(p, rcu); + } + + return 0; +} + +static int +kvfree_rcu_1_arg_slab_test(void) +{ + struct test_kvfree_rcu *p; + int i; + + for (i = 0; i < test_loop_count; i++) { + p = kmalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return -1; + + p->array[0] = 'a'; + kvfree_rcu(p); + } + + return 0; +} + +static int +kvfree_rcu_2_arg_slab_test(void) +{ + struct test_kvfree_rcu *p; + int i; + + for (i = 0; i < test_loop_count; i++) { + p = kmalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return -1; + + p->array[0] = 'a'; + kvfree_rcu(p, rcu); + } + + return 0; +} + struct test_case_desc { const char *test_name; int (*test_func)(void); @@ -330,6 +413,10 @@ static struct test_case_desc test_case_array[] = { { "random_size_align_alloc_test", random_size_align_alloc_test }, { "align_shift_alloc_test", align_shift_alloc_test }, { "pcpu_alloc_test", pcpu_alloc_test }, + { "kvfree_rcu_1_arg_vmalloc_test", kvfree_rcu_1_arg_vmalloc_test }, + { "kvfree_rcu_2_arg_vmalloc_test", kvfree_rcu_2_arg_vmalloc_test }, + { "kvfree_rcu_1_arg_slab_test", kvfree_rcu_1_arg_slab_test }, + { "kvfree_rcu_2_arg_slab_test", kvfree_rcu_2_arg_slab_test }, /* Add a new test case here. */ }; diff --git a/mm/list_lru.c b/mm/list_lru.c index 9222910ab1cb..e825804b3928 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -373,14 +373,14 @@ static void memcg_destroy_list_lru_node(struct list_lru_node *nlru) struct list_lru_memcg *memcg_lrus; /* * This is called when shrinker has already been unregistered, - * and nobody can use it. So, there is no need to use kvfree_rcu(). + * and nobody can use it. So, there is no need to use kvfree_rcu_local(). */ memcg_lrus = rcu_dereference_protected(nlru->memcg_lrus, true); __memcg_destroy_list_lru_node(memcg_lrus, 0, memcg_nr_cache_ids); kvfree(memcg_lrus); } -static void kvfree_rcu(struct rcu_head *head) +static void kvfree_rcu_local(struct rcu_head *head) { struct list_lru_memcg *mlru; @@ -419,7 +419,7 @@ static int memcg_update_list_lru_node(struct list_lru_node *nlru, rcu_assign_pointer(nlru->memcg_lrus, new); spin_unlock_irq(&nlru->lock); - call_rcu(&old->rcu, kvfree_rcu); + call_rcu(&old->rcu, kvfree_rcu_local); return 0; } diff --git a/mm/mmap.c b/mm/mmap.c index 8c7ca737a19b..dcdab2675a21 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -3171,6 +3171,7 @@ void exit_mmap(struct mm_struct *mm) if (vma->vm_flags & VM_ACCOUNT) nr_accounted += vma_pages(vma); vma = remove_vma(vma); + cond_resched(); } vm_unacct_memory(nr_accounted); } diff --git a/net/core/sock.c b/net/core/sock.c index 2e5b7870e5d3..b8ac834f5386 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1973,7 +1973,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) /* * Before updating sk_refcnt, we must commit prior changes to memory - * (Documentation/RCU/rculist_nulls.txt for details) + * (Documentation/RCU/rculist_nulls.rst for details) */ smp_wmb(); refcount_set(&newsk->sk_refcnt, 2); @@ -3035,7 +3035,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk_rx_queue_clear(sk); /* * Before updating sk_refcnt, we must commit prior changes to memory - * (Documentation/RCU/rculist_nulls.txt for details) + * (Documentation/RCU/rculist_nulls.rst for details) */ smp_wmb(); refcount_set(&sk->sk_refcnt, 1); diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh index 93e80a42249a..d6e5ce084b1c 100755 --- a/tools/testing/selftests/rcutorture/bin/configinit.sh +++ b/tools/testing/selftests/rcutorture/bin/configinit.sh @@ -32,11 +32,11 @@ if test -z "$TORTURE_TRUST_MAKE" then make clean > $resdir/Make.clean 2>&1 fi -make $TORTURE_DEFCONFIG > $resdir/Make.defconfig.out 2>&1 +make $TORTURE_KMAKE_ARG $TORTURE_DEFCONFIG > $resdir/Make.defconfig.out 2>&1 mv .config .config.sav sh $T/upd.sh < .config.sav > .config cp .config .config.new -yes '' | make oldconfig > $resdir/Make.oldconfig.out 2> $resdir/Make.oldconfig.err +yes '' | make $TORTURE_KMAKE_ARG oldconfig > $resdir/Make.oldconfig.out 2> $resdir/Make.oldconfig.err # verify new config matches specification. configcheck.sh .config $c diff --git a/tools/testing/selftests/rcutorture/bin/console-badness.sh b/tools/testing/selftests/rcutorture/bin/console-badness.sh new file mode 100755 index 000000000000..0e4c0b2eb7f0 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/console-badness.sh @@ -0,0 +1,16 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Scan standard input for error messages, dumping any found to standard +# output. +# +# Usage: console-badness.sh +# +# Copyright (C) 2020 Facebook, Inc. +# +# Authors: Paul E. McKenney <paulmck@kernel.org> + +egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' | +grep -v 'ODEBUG: ' | +grep -v 'This means that this is a DEBUG kernel and it is' | +grep -v 'Warning: unable to open an initial console' diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh index 12810229fddc..51f3464b96d3 100644 --- a/tools/testing/selftests/rcutorture/bin/functions.sh +++ b/tools/testing/selftests/rcutorture/bin/functions.sh @@ -215,9 +215,6 @@ identify_qemu_args () { then echo -device spapr-vlan,netdev=net0,mac=$TORTURE_QEMU_MAC echo -netdev bridge,br=br0,id=net0 - elif test -n "$TORTURE_QEMU_INTERACTIVE" - then - echo -net nic -net user fi ;; esac @@ -234,7 +231,7 @@ identify_qemu_args () { # Returns the number of virtual CPUs available to the aggregate of the # guest OSes. identify_qemu_vcpus () { - lscpu | grep '^CPU(s):' | sed -e 's/CPU(s)://' + lscpu | grep '^CPU(s):' | sed -e 's/CPU(s)://' -e 's/[ ]*//g' } # print_bug @@ -275,3 +272,21 @@ specify_qemu_cpus () { esac fi } + +# specify_qemu_net qemu-args +# +# Appends a string containing "-net none" to qemu-args, unless the incoming +# qemu-args already contains "-smp" or unless the TORTURE_QEMU_INTERACTIVE +# environment variable is set, in which case the string that is be added is +# instead "-net nic -net user". +specify_qemu_net () { + if echo $1 | grep -q -e -net + then + echo $1 + elif test -n "$TORTURE_QEMU_INTERACTIVE" + then + echo $1 -net nic -net user + else + echo $1 -net none + fi +} diff --git a/tools/testing/selftests/rcutorture/bin/jitter.sh b/tools/testing/selftests/rcutorture/bin/jitter.sh index 30cb5b27d32e..188b864bc4bf 100755 --- a/tools/testing/selftests/rcutorture/bin/jitter.sh +++ b/tools/testing/selftests/rcutorture/bin/jitter.sh @@ -46,6 +46,12 @@ do exit 0; fi + # Check for stop request. + if test -f "$TORTURE_STOPFILE" + then + exit 1; + fi + # Set affinity to randomly selected online CPU if cpus=`grep 1 /sys/devices/system/cpu/*/online 2>&1 | sed -e 's,/[^/]*$,,' -e 's/^[^0-9]*//'` diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh index 18d6518504ee..115e1822b26f 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh @@ -9,6 +9,12 @@ # # Authors: Paul E. McKenney <paulmck@linux.ibm.com> +if test -f "$TORTURE_STOPFILE" +then + echo "kvm-build.sh early exit due to run STOP request" + exit 1 +fi + config_template=${1} if test -z "$config_template" -o ! -f "$config_template" -o ! -r "$config_template" then diff --git a/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh new file mode 100755 index 000000000000..6e65c134e5f1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh @@ -0,0 +1,108 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0+ +# +# Run a group of kvm.sh tests on the specified commits. This currently +# unconditionally does three-minute runs on each scenario in CFLIST, +# taking advantage of all available CPUs and trusting the "make" utility. +# In the short term, adjustments can be made by editing this script and +# CFLIST. If some adjustments appear to have ongoing value, this script +# might grow some command-line arguments. +# +# Usage: kvm-check-branches.sh commit1 commit2..commit3 commit4 ... +# +# This script considers its arguments one at a time. If more elaborate +# specification of commits is needed, please use "git rev-list" to +# produce something that this simple script can understand. The reason +# for retaining the simplicity is that it allows the user to more easily +# see which commit came from which branch. +# +# This script creates a yyyy.mm.dd-hh.mm.ss-group entry in the "res" +# directory. The calls to kvm.sh create the usual entries, but this script +# moves them under the yyyy.mm.dd-hh.mm.ss-group entry, each in its own +# directory numbered in run order, that is, "0001", "0002", and so on. +# For successful runs, the large build artifacts are removed. Doing this +# reduces the disk space required by about two orders of magnitude for +# successful runs. +# +# Copyright (C) Facebook, 2020 +# +# Authors: Paul E. McKenney <paulmck@kernel.org> + +if ! git status > /dev/null 2>&1 +then + echo '!!!' This script needs to run in a git archive. 1>&2 + echo '!!!' Giving up. 1>&2 + exit 1 +fi + +# Remember where we started so that we can get back and the end. +curcommit="`git status | head -1 | awk '{ print $NF }'`" + +nfail=0 +ntry=0 +resdir="tools/testing/selftests/rcutorture/res" +ds="`date +%Y.%m.%d-%H.%M.%S`-group" +if ! test -e $resdir +then + mkdir $resdir || : +fi +mkdir $resdir/$ds +echo Results directory: $resdir/$ds + +KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM +PATH=${KVM}/bin:$PATH; export PATH +. functions.sh +cpus="`identify_qemu_vcpus`" +echo Using up to $cpus CPUs. + +# Each pass through this loop does one command-line argument. +for gitbr in $@ +do + echo ' --- git branch ' $gitbr + + # Each pass through this loop tests one commit. + for i in `git rev-list "$gitbr"` + do + ntry=`expr $ntry + 1` + idir=`awk -v ntry="$ntry" 'END { printf "%04d", ntry; }' < /dev/null` + echo ' --- commit ' $i from branch $gitbr + date + mkdir $resdir/$ds/$idir + echo $gitbr > $resdir/$ds/$idir/gitbr + echo $i >> $resdir/$ds/$idir/gitbr + + # Test the specified commit. + git checkout $i > $resdir/$ds/$idir/git-checkout.out 2>&1 + echo git checkout return code: $? "(Commit $ntry: $i)" + kvm.sh --cpus $cpus --duration 3 --trust-make > $resdir/$ds/$idir/kvm.sh.out 2>&1 + ret=$? + echo kvm.sh return code $ret for commit $i from branch $gitbr + + # Move the build products to their resting place. + runresdir="`grep -m 1 '^Results directory:' < $resdir/$ds/$idir/kvm.sh.out | sed -e 's/^Results directory://'`" + mv $runresdir $resdir/$ds/$idir + rrd="`echo $runresdir | sed -e 's,^.*/,,'`" + echo Run results: $resdir/$ds/$idir/$rrd + if test "$ret" -ne 0 + then + # Failure, so leave all evidence intact. + nfail=`expr $nfail + 1` + else + # Success, so remove large files to save about 1GB. + ( cd $resdir/$ds/$idir/$rrd; rm -f */vmlinux */bzImage */System.map */Module.symvers ) + fi + done +done +date + +# Go back to the original commit. +git checkout "$curcommit" + +if test $nfail -ne 0 +then + echo '!!! ' $nfail failures in $ntry 'runs!!!' + exit 1 +else + echo No failures in $ntry runs. + exit 0 +fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-refscale.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-refscale.sh new file mode 100755 index 000000000000..35a463dddffe --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-refscale.sh @@ -0,0 +1,71 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Analyze a given results directory for refscale performance measurements. +# +# Usage: kvm-recheck-refscale.sh resdir +# +# Copyright (C) IBM Corporation, 2016 +# +# Authors: Paul E. McKenney <paulmck@linux.ibm.com> + +i="$1" +if test -d "$i" -a -r "$i" +then + : +else + echo Unreadable results directory: $i + exit 1 +fi +PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH +. functions.sh + +configfile=`echo $i | sed -e 's/^.*\///'` + +sed -e 's/^\[[^]]*]//' < $i/console.log | tr -d '\015' | +awk -v configfile="$configfile" ' +/^[ ]*Runs Time\(ns\) *$/ { + if (dataphase + 0 == 0) { + dataphase = 1; + # print configfile, $0; + } + next; +} + +/[^ ]*[0-9][0-9]* [0-9][0-9]*\.[0-9][0-9]*$/ { + if (dataphase == 1) { + # print $0; + readertimes[++n] = $2; + sum += $2; + } + next; +} + +{ + if (dataphase == 1) + dataphase == 2; + next; +} + +END { + print configfile " results:"; + newNR = asort(readertimes); + if (newNR <= 0) { + print "No refscale records found???" + exit; + } + medianidx = int(newNR / 2); + if (newNR == medianidx * 2) + medianvalue = (readertimes[medianidx - 1] + readertimes[medianidx]) / 2; + else + medianvalue = readertimes[medianidx]; + points = "Points:"; + for (i = 1; i <= newNR; i++) + points = points " " readertimes[i]; + print points; + print "Average reader duration: " sum / newNR " nanoseconds"; + print "Minimum reader duration: " readertimes[1]; + print "Median reader duration: " medianvalue; + print "Maximum reader duration: " readertimes[newNR]; + print "Computed from refscale printk output."; +}' diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index 736f04749b90..840a4679a0d7 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -31,6 +31,7 @@ do head -1 $resdir/log fi TORTURE_SUITE="`cat $i/../TORTURE_SUITE`" + configfile=`echo $i | sed -e 's,^.*/,,'` rm -f $i/console.log.*.diags kvm-recheck-${TORTURE_SUITE}.sh $i if test -f "$i/qemu-retval" && test "`cat $i/qemu-retval`" -ne 0 && test "`cat $i/qemu-retval`" -ne 137 @@ -43,7 +44,8 @@ do then echo QEMU killed fi - configcheck.sh $i/.config $i/ConfigFragment + configcheck.sh $i/.config $i/ConfigFragment > $T 2>&1 + cat $T if test -r $i/Make.oldconfig.err then cat $i/Make.oldconfig.err @@ -55,15 +57,15 @@ do cat $i/Warnings fi else - if test -f "$i/qemu-cmd" - then - print_bug qemu failed - echo " $i" - elif test -f "$i/buildonly" + if test -f "$i/buildonly" then echo Build-only run, no boot/test configcheck.sh $i/.config $i/ConfigFragment parse-build.sh $i/Make.out $configfile + elif test -f "$i/qemu-cmd" + then + print_bug qemu failed + echo " $i" else print_bug Build failed echo " $i" @@ -72,7 +74,11 @@ do done if test -f "$rd/kcsan.sum" then - if test -s "$rd/kcsan.sum" + if grep -q CONFIG_KCSAN=y $T + then + echo "Compiler or architecture does not support KCSAN!" + echo Did you forget to switch your compiler with '--kmake-arg CC=<cc-that-supports-kcsan>'? + elif test -s "$rd/kcsan.sum" then echo KCSAN summary in $rd/kcsan.sum else diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index 6ff611c630d1..e07779a62634 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -124,7 +124,6 @@ seconds=$4 qemu_args=$5 boot_args=$6 -cd $KVM kstarttime=`gawk 'BEGIN { print systime() }' < /dev/null` if test -z "$TORTURE_BUILDONLY" then @@ -141,6 +140,7 @@ then cpu_count=$TORTURE_ALLOTED_CPUS fi qemu_args="`specify_qemu_cpus "$QEMU" "$qemu_args" "$cpu_count"`" +qemu_args="`specify_qemu_net "$qemu_args"`" # Generate architecture-specific and interaction-specific qemu arguments qemu_args="$qemu_args `identify_qemu_args "$QEMU" "$resdir/console.log"`" @@ -152,6 +152,7 @@ qemu_append="`identify_qemu_append "$QEMU"`" boot_args="`configfrag_boot_params "$boot_args" "$config_template"`" # Generate kernel-version-specific boot parameters boot_args="`per_version_boot_params "$boot_args" $resdir/.config $seconds`" +echo $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd if test -n "$TORTURE_BUILDONLY" then @@ -159,9 +160,16 @@ then touch $resdir/buildonly exit 0 fi + +# Decorate qemu-cmd with redirection, backgrounding, and PID capture +sed -e 's/$/ 2>\&1 \&/' < $resdir/qemu-cmd > $T/qemu-cmd +echo 'echo $! > $resdir/qemu_pid' >> $T/qemu-cmd + +# In case qemu refuses to run... echo "NOTE: $QEMU either did not run or was interactive" > $resdir/console.log -echo $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd -( $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append "$qemu_append $boot_args" > $resdir/qemu-output 2>&1 & echo $! > $resdir/qemu_pid; wait `cat $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) & + +# Attempt to run qemu +( . $T/qemu-cmd; wait `cat $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) & commandcompleted=0 sleep 10 # Give qemu's pid a chance to reach the file if test -s "$resdir/qemu_pid" @@ -181,7 +189,7 @@ do kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null` if test -z "$qemu_pid" || kill -0 "$qemu_pid" > /dev/null 2>&1 then - if test $kruntime -ge $seconds + if test $kruntime -ge $seconds -o -f "$TORTURE_STOPFILE" then break; fi @@ -210,10 +218,19 @@ then fi if test $commandcompleted -eq 0 -a -n "$qemu_pid" then - echo Grace period for qemu job at pid $qemu_pid + if ! test -f "$TORTURE_STOPFILE" + then + echo Grace period for qemu job at pid $qemu_pid + fi oldline="`tail $resdir/console.log`" while : do + if test -f "$TORTURE_STOPFILE" + then + echo "PID $qemu_pid killed due to run STOP request" >> $resdir/Warnings 2>&1 + kill -KILL $qemu_pid + break + fi kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null` if kill -0 $qemu_pid > /dev/null 2>&1 then diff --git a/tools/testing/selftests/rcutorture/bin/kvm-transform.sh b/tools/testing/selftests/rcutorture/bin/kvm-transform.sh new file mode 100755 index 000000000000..c45a953ef393 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-transform.sh @@ -0,0 +1,51 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Transform a qemu-cmd file to allow reuse. +# +# Usage: kvm-transform.sh bzImage console.log < qemu-cmd-in > qemu-cmd-out +# +# bzImage: Kernel and initrd from the same prior kvm.sh run. +# console.log: File into which to place console output. +# +# The original qemu-cmd file is provided on standard input. +# The transformed qemu-cmd file is on standard output. +# The transformation assumes that the qemu command is confined to a +# single line. It also assumes no whitespace in filenames. +# +# Copyright (C) 2020 Facebook, Inc. +# +# Authors: Paul E. McKenney <paulmck@kernel.org> + +image="$1" +if test -z "$image" +then + echo Need kernel image file. + exit 1 +fi +consolelog="$2" +if test -z "$consolelog" +then + echo "Need console log file name." + exit 1 +fi + +awk -v image="$image" -v consolelog="$consolelog" ' +{ + line = ""; + for (i = 1; i <= NF; i++) { + if (line == "") + line = $i; + else + line = line " " $i; + if ($i == "-serial") { + i++; + line = line " file:" consolelog; + } + if ($i == "-kernel") { + i++; + line = line " " image; + } + } + print line; +}' diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index c279cf9cb010..e655983b7429 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -73,6 +73,10 @@ usage () { while test $# -gt 0 do case "$1" in + --allcpus) + cpus=$TORTURE_ALLOTED_CPUS + max_cpus=$TORTURE_ALLOTED_CPUS + ;; --bootargs|--bootarg) checkarg --bootargs "(list of kernel boot arguments)" "$#" "$2" '.*' '^--' TORTURE_BOOTARGS="$2" @@ -180,13 +184,14 @@ do shift ;; --torture) - checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuperf\)$' '^--' + checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuperf\|refscale\)$' '^--' TORTURE_SUITE=$2 shift - if test "$TORTURE_SUITE" = rcuperf + if test "$TORTURE_SUITE" = rcuperf || test "$TORTURE_SUITE" = refscale then - # If you really want jitter for rcuperf, specify - # it after specifying rcuperf. (But why?) + # If you really want jitter for refscale or + # rcuperf, specify it after specifying the rcuperf + # or the refscale. (But why jitter in these cases?) jitter=0 fi ;; @@ -333,6 +338,8 @@ then mkdir -p "$resdir" || : fi mkdir $resdir/$ds +TORTURE_RESDIR="$resdir/$ds"; export TORTURE_RESDIR +TORTURE_STOPFILE="$resdir/$ds/STOP"; export TORTURE_STOPFILE echo Results directory: $resdir/$ds echo $scriptname $args touch $resdir/$ds/log @@ -497,3 +504,7 @@ fi # Tracing: trace_event=rcu:rcu_grace_period,rcu:rcu_future_grace_period,rcu:rcu_grace_period_init,rcu:rcu_nocb_wake,rcu:rcu_preempt_task,rcu:rcu_unlock_preempted_task,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_kfree_callback,rcu:rcu_batch_start,rcu:rcu_invoke_callback,rcu:rcu_invoke_kfree_callback,rcu:rcu_batch_end,rcu:rcu_torture_read,rcu:rcu_barrier # Function-graph tracing: ftrace=function_graph ftrace_graph_filter=sched_setaffinity,migration_cpu_stop # Also --kconfig "CONFIG_FUNCTION_TRACER=y CONFIG_FUNCTION_GRAPH_TRACER=y" +# Control buffer size: --bootargs trace_buf_size=3k +# Get trace-buffer dumps on all oopses: --bootargs ftrace_dump_on_oops +# Ditto, but dump only the oopsing CPU: --bootargs ftrace_dump_on_oops=orig_cpu +# Heavy-handed way to also dump on warnings: --bootargs panic_on_warn diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index 4bf62d7b1cbc..71a9f43a3918 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -33,8 +33,8 @@ then fi cat /dev/null > $file.diags -# Check for proper termination, except that rcuperf runs don't indicate this. -if test "$TORTURE_SUITE" != rcuperf +# Check for proper termination, except for rcuperf and refscale. +if test "$TORTURE_SUITE" != rcuperf && test "$TORTURE_SUITE" != refscale then # check for abject failure @@ -44,11 +44,23 @@ then tail -1 | awk ' { - for (i=NF-8;i<=NF;i++) + normalexit = 1; + for (i=NF-8;i<=NF;i++) { + if (i <= 0 || i !~ /^[0-9]*$/) { + bangstring = $0; + gsub(/^\[[^]]*] /, "", bangstring); + print bangstring; + normalexit = 0; + exit 0; + } sum+=$i; + } } - END { print sum }'` - print_bug $title FAILURE, $nerrs instances + END { + if (normalexit) + print sum " instances" + }'` + print_bug $title FAILURE, $nerrs exit fi @@ -104,10 +116,7 @@ then fi fi | tee -a $file.diags -egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for' < $file | -grep -v 'ODEBUG: ' | -grep -v 'This means that this is a DEBUG kernel and it is' | -grep -v 'Warning: unable to open an initial console' > $T.diags +console-badness.sh < $file > $T.diags if test -s $T.diags then print_warning "Assertion failure in $file $title" diff --git a/tools/testing/selftests/rcutorture/configs/refscale/CFLIST b/tools/testing/selftests/rcutorture/configs/refscale/CFLIST new file mode 100644 index 000000000000..4d62eb4a39f9 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/CFLIST @@ -0,0 +1,2 @@ +NOPREEMPT +PREEMPT diff --git a/tools/testing/selftests/rcutorture/configs/refscale/CFcommon b/tools/testing/selftests/rcutorture/configs/refscale/CFcommon new file mode 100644 index 000000000000..a98b58b54bb1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/CFcommon @@ -0,0 +1,2 @@ +CONFIG_RCU_REF_SCALE_TEST=y +CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT new file mode 100644 index 000000000000..1cd25b7314e3 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT @@ -0,0 +1,18 @@ +CONFIG_SMP=y +CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=n +#CHECK#CONFIG_PREEMPT_RCU=n +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=y +CONFIG_NO_HZ_FULL=n +CONFIG_RCU_FAST_NO_HZ=n +CONFIG_HOTPLUG_CPU=n +CONFIG_SUSPEND=n +CONFIG_HIBERNATION=n +CONFIG_RCU_NOCB_CPU=n +CONFIG_DEBUG_LOCK_ALLOC=n +CONFIG_PROVE_LOCKING=n +CONFIG_RCU_BOOST=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT new file mode 100644 index 000000000000..d10bc694f42c --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT @@ -0,0 +1,18 @@ +CONFIG_SMP=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y +#CHECK#CONFIG_PREEMPT_RCU=y +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=y +CONFIG_NO_HZ_FULL=n +CONFIG_RCU_FAST_NO_HZ=n +CONFIG_HOTPLUG_CPU=n +CONFIG_SUSPEND=n +CONFIG_HIBERNATION=n +CONFIG_RCU_NOCB_CPU=n +CONFIG_DEBUG_LOCK_ALLOC=n +CONFIG_PROVE_LOCKING=n +CONFIG_RCU_BOOST=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh new file mode 100644 index 000000000000..321e82641287 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh @@ -0,0 +1,16 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Torture-suite-dependent shell functions for the rest of the scripts. +# +# Copyright (C) IBM Corporation, 2015 +# +# Authors: Paul E. McKenney <paulmck@linux.ibm.com> + +# per_version_boot_params bootparam-string config-file seconds +# +# Adds per-version torture-module parameters to kernels supporting them. +per_version_boot_params () { + echo $1 refscale.shutdown=1 \ + refscale.verbose=1 +} |