diff --git a/debian/changelog b/debian/changelog index 788618767..f6f9004dc 100644 --- a/debian/changelog +++ b/debian/changelog @@ -7,6 +7,7 @@ linux (4.1.3-1~exp1) UNRELEASED; urgency=medium * [armel/kirkwood] ubi: Change UBIFS_FS and MTD_UBI from built-in to modules, to reduce kernel image size (fixes FTBFS) * debian/rules.real: Use dpkg-parsechangelog -S + * [rt] Update to 4.1.3-rt3 and re-enable [ Ian Campbell ] * [armhf] Set CONFIG_ARM_TEGRA_CPUFREQ as builtin. diff --git a/debian/config/defines b/debian/config/defines index c5a2fe805..c0a09318d 100644 --- a/debian/config/defines +++ b/debian/config/defines @@ -33,7 +33,7 @@ featuresets: rt [featureset-rt_base] -enabled: false +enabled: true [description] part-long-up: This kernel is not suitable for SMP (multi-processor, diff --git a/debian/patches/features/all/rt/0001-arm64-Mark-PMU-interrupt-IRQF_NO_THREAD.patch b/debian/patches/features/all/rt/0001-arm64-Mark-PMU-interrupt-IRQF_NO_THREAD.patch new file mode 100644 index 000000000..1134f8a49 --- /dev/null +++ b/debian/patches/features/all/rt/0001-arm64-Mark-PMU-interrupt-IRQF_NO_THREAD.patch @@ -0,0 +1,27 @@ +From: Anders Roxell +Date: Mon, 27 Apr 2015 22:53:08 +0200 +Subject: arm64: Mark PMU interrupt IRQF_NO_THREAD +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Mark the PMU interrupts as non-threadable, as is the case with +arch/arm: d9c3365 ARM: 7813/1: Mark pmu interupt IRQF_NO_THREAD + +[ upstream commit: 96045ed486b0 ] + +Suggested-by: Sebastian Andrzej Siewior +Signed-off-by: Anders Roxell +--- + arch/arm64/kernel/perf_event.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/arch/arm64/kernel/perf_event.c ++++ b/arch/arm64/kernel/perf_event.c +@@ -488,7 +488,7 @@ armpmu_reserve_hardware(struct arm_pmu * + } + + err = request_irq(irq, armpmu->handle_irq, +- IRQF_NOBALANCING, ++ IRQF_NOBALANCING | IRQF_NO_THREAD, + "arm-pmu", armpmu); + if (err) { + pr_err("unable to request IRQ%d for ARM PMU counters\n", diff --git a/debian/patches/features/all/rt/0001-sched-Implement-lockless-wake-queues.patch b/debian/patches/features/all/rt/0001-sched-Implement-lockless-wake-queues.patch new file mode 100644 index 000000000..fcab2d592 --- /dev/null +++ b/debian/patches/features/all/rt/0001-sched-Implement-lockless-wake-queues.patch @@ -0,0 +1,167 @@ +From: Peter Zijlstra +Date: Fri, 1 May 2015 08:27:50 -0700 +Subject: sched: Implement lockless wake-queues +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +This is useful for locking primitives that can effect multiple +wakeups per operation and want to avoid lock internal lock contention +by delaying the wakeups until we've released the lock internal locks. + +Alternatively it can be used to avoid issuing multiple wakeups, and +thus save a few cycles, in packet processing. Queue all target tasks +and wakeup once you've processed all packets. That way you avoid +waking the target task multiple times if there were multiple packets +for the same task. + +Properties of a wake_q are: +- Lockless, as queue head must reside on the stack. +- Being a queue, maintains wakeup order passed by the callers. This can + be important for otherwise, in scenarios where highly contended locks + could affect any reliance on lock fairness. +- A queued task cannot be added again until it is woken up. + +This patch adds the needed infrastructure into the scheduler code +and uses the new wake_list to delay the futex wakeups until +after we've released the hash bucket locks. + +[upstream commit 7675104990ed255b9315a82ae827ff312a2a88a2] + +Signed-off-by: Peter Zijlstra (Intel) +[tweaks, adjustments, comments, etc.] +Signed-off-by: Davidlohr Bueso +Signed-off-by: Peter Zijlstra (Intel) +Acked-by: Thomas Gleixner +Cc: Borislav Petkov +Cc: Chris Mason +Cc: Davidlohr Bueso +Cc: George Spelvin +Cc: H. Peter Anvin +Cc: Linus Torvalds +Cc: Manfred Spraul +Cc: Sebastian Andrzej Siewior +Cc: Steven Rostedt +Link: http://lkml.kernel.org/r/1430494072-30283-2-git-send-email-dave@stgolabs.net +Signed-off-by: Ingo Molnar +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/sched.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ + kernel/sched/core.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ + 2 files changed, 92 insertions(+) + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -900,6 +900,50 @@ enum cpu_idle_type { + #define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) + + /* ++ * Wake-queues are lists of tasks with a pending wakeup, whose ++ * callers have already marked the task as woken internally, ++ * and can thus carry on. A common use case is being able to ++ * do the wakeups once the corresponding user lock as been ++ * released. ++ * ++ * We hold reference to each task in the list across the wakeup, ++ * thus guaranteeing that the memory is still valid by the time ++ * the actual wakeups are performed in wake_up_q(). ++ * ++ * One per task suffices, because there's never a need for a task to be ++ * in two wake queues simultaneously; it is forbidden to abandon a task ++ * in a wake queue (a call to wake_up_q() _must_ follow), so if a task is ++ * already in a wake queue, the wakeup will happen soon and the second ++ * waker can just skip it. ++ * ++ * The WAKE_Q macro declares and initializes the list head. ++ * wake_up_q() does NOT reinitialize the list; it's expected to be ++ * called near the end of a function, where the fact that the queue is ++ * not used again will be easy to see by inspection. ++ * ++ * Note that this can cause spurious wakeups. schedule() callers ++ * must ensure the call is done inside a loop, confirming that the ++ * wakeup condition has in fact occurred. ++ */ ++struct wake_q_node { ++ struct wake_q_node *next; ++}; ++ ++struct wake_q_head { ++ struct wake_q_node *first; ++ struct wake_q_node **lastp; ++}; ++ ++#define WAKE_Q_TAIL ((struct wake_q_node *) 0x01) ++ ++#define WAKE_Q(name) \ ++ struct wake_q_head name = { WAKE_Q_TAIL, &name.first } ++ ++extern void wake_q_add(struct wake_q_head *head, ++ struct task_struct *task); ++extern void wake_up_q(struct wake_q_head *head); ++ ++/* + * sched-domains (multiprocessor balancing) declarations: + */ + #ifdef CONFIG_SMP +@@ -1511,6 +1555,8 @@ struct task_struct { + /* Protection of the PI data structures: */ + raw_spinlock_t pi_lock; + ++ struct wake_q_node wake_q; ++ + #ifdef CONFIG_RT_MUTEXES + /* PI waiters blocked on a rt_mutex held by this task */ + struct rb_root pi_waiters; +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -541,6 +541,52 @@ static bool set_nr_if_polling(struct tas + #endif + #endif + ++void wake_q_add(struct wake_q_head *head, struct task_struct *task) ++{ ++ struct wake_q_node *node = &task->wake_q; ++ ++ /* ++ * Atomically grab the task, if ->wake_q is !nil already it means ++ * its already queued (either by us or someone else) and will get the ++ * wakeup due to that. ++ * ++ * This cmpxchg() implies a full barrier, which pairs with the write ++ * barrier implied by the wakeup in wake_up_list(). ++ */ ++ if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL)) ++ return; ++ ++ get_task_struct(task); ++ ++ /* ++ * The head is context local, there can be no concurrency. ++ */ ++ *head->lastp = node; ++ head->lastp = &node->next; ++} ++ ++void wake_up_q(struct wake_q_head *head) ++{ ++ struct wake_q_node *node = head->first; ++ ++ while (node != WAKE_Q_TAIL) { ++ struct task_struct *task; ++ ++ task = container_of(node, struct task_struct, wake_q); ++ BUG_ON(!task); ++ /* task can safely be re-inserted now */ ++ node = node->next; ++ task->wake_q.next = NULL; ++ ++ /* ++ * wake_up_process() implies a wmb() to pair with the queueing ++ * in wake_q_add() so as not to miss wakeups. ++ */ ++ wake_up_process(task); ++ put_task_struct(task); ++ } ++} ++ + /* + * resched_curr - mark rq's current task 'to be rescheduled now'. + * diff --git a/debian/patches/features/all/rt/0001-uaccess-count-pagefault_disable-levels-in-pagefault_.patch b/debian/patches/features/all/rt/0001-uaccess-count-pagefault_disable-levels-in-pagefault_.patch new file mode 100644 index 000000000..8dbd516e8 --- /dev/null +++ b/debian/patches/features/all/rt/0001-uaccess-count-pagefault_disable-levels-in-pagefault_.patch @@ -0,0 +1,120 @@ +From: David Hildenbrand +Date: Mon, 11 May 2015 17:52:06 +0200 +Subject: sched/preempt, mm/fault: Count pagefault_disable() levels in pagefault_disabled +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Until now, pagefault_disable()/pagefault_enabled() used the preempt +count to track whether in an environment with pagefaults disabled (can +be queried via in_atomic()). + +This patch introduces a separate counter in task_struct to count the +level of pagefault_disable() calls. We'll keep manipulating the preempt +count to retain compatibility to existing pagefault handlers. + +It is now possible to verify whether in a pagefault_disable() envionment +by calling pagefault_disabled(). In contrast to in_atomic() it will not +be influenced by preempt_enable()/preempt_disable(). + +This patch is based on a patch from Ingo Molnar. + +[upstream commit 8bcbde5480f9777f8b74d71493722c663e22c21b] +Signed-off-by: David Hildenbrand +--- + include/linux/sched.h | 1 + + include/linux/uaccess.h | 36 +++++++++++++++++++++++++++++------- + kernel/fork.c | 3 +++ + 3 files changed, 33 insertions(+), 7 deletions(-) + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -1724,6 +1724,7 @@ struct task_struct { + #ifdef CONFIG_DEBUG_ATOMIC_SLEEP + unsigned long task_state_change; + #endif ++ int pagefault_disabled; + }; + + /* Future-safe accessor for struct task_struct's cpus_allowed. */ +--- a/include/linux/uaccess.h ++++ b/include/linux/uaccess.h +@@ -2,20 +2,36 @@ + #define __LINUX_UACCESS_H__ + + #include ++#include + #include + ++static __always_inline void pagefault_disabled_inc(void) ++{ ++ current->pagefault_disabled++; ++} ++ ++static __always_inline void pagefault_disabled_dec(void) ++{ ++ current->pagefault_disabled--; ++ WARN_ON(current->pagefault_disabled < 0); ++} ++ + /* +- * These routines enable/disable the pagefault handler in that +- * it will not take any locks and go straight to the fixup table. ++ * These routines enable/disable the pagefault handler. If disabled, it will ++ * not take any locks and go straight to the fixup table. ++ * ++ * We increase the preempt and the pagefault count, to be able to distinguish ++ * whether we run in simple atomic context or in a real pagefault_disable() ++ * context. ++ * ++ * For now, after pagefault_disabled() has been called, we run in atomic ++ * context. User access methods will not sleep. + * +- * They have great resemblance to the preempt_disable/enable calls +- * and in fact they are identical; this is because currently there is +- * no other way to make the pagefault handlers do this. So we do +- * disable preemption but we don't necessarily care about that. + */ + static inline void pagefault_disable(void) + { + preempt_count_inc(); ++ pagefault_disabled_inc(); + /* + * make sure to have issued the store before a pagefault + * can hit. +@@ -25,18 +41,24 @@ static inline void pagefault_disable(voi + + static inline void pagefault_enable(void) + { +-#ifndef CONFIG_PREEMPT + /* + * make sure to issue those last loads/stores before enabling + * the pagefault handler again. + */ + barrier(); ++ pagefault_disabled_dec(); ++#ifndef CONFIG_PREEMPT + preempt_count_dec(); + #else + preempt_enable(); + #endif + } + ++/* ++ * Is the pagefault handler disabled? If so, user access methods will not sleep. ++ */ ++#define pagefault_disabled() (current->pagefault_disabled != 0) ++ + #ifndef ARCH_HAS_NOCACHE_UACCESS + + static inline unsigned long __copy_from_user_inatomic_nocache(void *to, +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -1396,6 +1396,9 @@ static struct task_struct *copy_process( + p->hardirq_context = 0; + p->softirq_context = 0; + #endif ++ ++ p->pagefault_disabled = 0; ++ + #ifdef CONFIG_LOCKDEP + p->lockdep_depth = 0; /* no locks held yet */ + p->curr_chain_key = 0; diff --git a/debian/patches/features/all/rt/0002-arm64-Allow-forced-irq-threading.patch b/debian/patches/features/all/rt/0002-arm64-Allow-forced-irq-threading.patch new file mode 100644 index 000000000..0c3acd56b --- /dev/null +++ b/debian/patches/features/all/rt/0002-arm64-Allow-forced-irq-threading.patch @@ -0,0 +1,27 @@ +From: Anders Roxell +Date: Mon, 27 Apr 2015 22:53:09 +0200 +Subject: arm64: Allow forced irq threading +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Now its safe to allow forced interrupt threading for arm64, +all timer interrupts and the perf interrupt are marked NO_THREAD, as is +the case with arch/arm: da0ec6f ARM: 7814/2: Allow forced irq threading + +[ upstream commit: e8557d1f0c4d ] + +Suggested-by: Sebastian Andrzej Siewior +Signed-off-by: Anders Roxell +--- + arch/arm64/Kconfig | 1 + + 1 file changed, 1 insertion(+) + +--- a/arch/arm64/Kconfig ++++ b/arch/arm64/Kconfig +@@ -71,6 +71,7 @@ config ARM64 + select HAVE_RCU_TABLE_FREE + select HAVE_SYSCALL_TRACEPOINTS + select IRQ_DOMAIN ++ select IRQ_FORCED_THREADING + select MODULES_USE_ELF_RELA + select NO_BOOTMEM + select OF diff --git a/debian/patches/features/all/rt/0002-futex-Implement-lockless-wakeups.patch b/debian/patches/features/all/rt/0002-futex-Implement-lockless-wakeups.patch new file mode 100644 index 000000000..2966f9439 --- /dev/null +++ b/debian/patches/features/all/rt/0002-futex-Implement-lockless-wakeups.patch @@ -0,0 +1,182 @@ +From: Davidlohr Bueso +Date: Fri, 1 May 2015 08:27:51 -0700 +Subject: futex: Implement lockless wakeups +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Given the overall futex architecture, any chance of reducing +hb->lock contention is welcome. In this particular case, using +wake-queues to enable lockless wakeups addresses very much real +world performance concerns, even cases of soft-lockups in cases +of large amounts of blocked tasks (which is not hard to find in +large boxes, using but just a handful of futex). + +At the lowest level, this patch can reduce latency of a single thread +attempting to acquire hb->lock in highly contended scenarios by a +up to 2x. At lower counts of nr_wake there are no regressions, +confirming, of course, that the wake_q handling overhead is practically +non existent. For instance, while a fair amount of variation, +the extended pef-bench wakeup benchmark shows for a 20 core machine +the following avg per-thread time to wakeup its share of tasks: + + nr_thr ms-before ms-after + 16 0.0590 0.0215 + 32 0.0396 0.0220 + 48 0.0417 0.0182 + 64 0.0536 0.0236 + 80 0.0414 0.0097 + 96 0.0672 0.0152 + +Naturally, this can cause spurious wakeups. However there is no core code +that cannot handle them afaict, and furthermore tglx does have the point +that other events can already trigger them anyway. + +[upstream commit 1d0dcb3ad9d336e6d6ee020a750a7f8d907e28de] + +Signed-off-by: Davidlohr Bueso +Signed-off-by: Peter Zijlstra (Intel) +Acked-by: Thomas Gleixner +Cc: Andrew Morton +Cc: Borislav Petkov +Cc: Chris Mason +Cc: Davidlohr Bueso +Cc: George Spelvin +Cc: H. Peter Anvin +Cc: Linus Torvalds +Cc: Manfred Spraul +Cc: Peter Zijlstra +Cc: Sebastian Andrzej Siewior +Cc: Steven Rostedt +Link: http://lkml.kernel.org/r/1430494072-30283-3-git-send-email-dave@stgolabs.net +Signed-off-by: Ingo Molnar +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/futex.c | 33 +++++++++++++++++---------------- + 1 file changed, 17 insertions(+), 16 deletions(-) + +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -1090,9 +1090,11 @@ static void __unqueue_futex(struct futex + + /* + * The hash bucket lock must be held when this is called. +- * Afterwards, the futex_q must not be accessed. ++ * Afterwards, the futex_q must not be accessed. Callers ++ * must ensure to later call wake_up_q() for the actual ++ * wakeups to occur. + */ +-static void wake_futex(struct futex_q *q) ++static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q) + { + struct task_struct *p = q->task; + +@@ -1100,14 +1102,10 @@ static void wake_futex(struct futex_q *q + return; + + /* +- * We set q->lock_ptr = NULL _before_ we wake up the task. If +- * a non-futex wake up happens on another CPU then the task +- * might exit and p would dereference a non-existing task +- * struct. Prevent this by holding a reference on p across the +- * wake up. ++ * Queue the task for later wakeup for after we've released ++ * the hb->lock. wake_q_add() grabs reference to p. + */ +- get_task_struct(p); +- ++ wake_q_add(wake_q, p); + __unqueue_futex(q); + /* + * The waiting task can free the futex_q as soon as +@@ -1117,9 +1115,6 @@ static void wake_futex(struct futex_q *q + */ + smp_wmb(); + q->lock_ptr = NULL; +- +- wake_up_state(p, TASK_NORMAL); +- put_task_struct(p); + } + + static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) +@@ -1217,6 +1212,7 @@ futex_wake(u32 __user *uaddr, unsigned i + struct futex_q *this, *next; + union futex_key key = FUTEX_KEY_INIT; + int ret; ++ WAKE_Q(wake_q); + + if (!bitset) + return -EINVAL; +@@ -1244,13 +1240,14 @@ futex_wake(u32 __user *uaddr, unsigned i + if (!(this->bitset & bitset)) + continue; + +- wake_futex(this); ++ mark_wake_futex(&wake_q, this); + if (++ret >= nr_wake) + break; + } + } + + spin_unlock(&hb->lock); ++ wake_up_q(&wake_q); + out_put_key: + put_futex_key(&key); + out: +@@ -1269,6 +1266,7 @@ futex_wake_op(u32 __user *uaddr1, unsign + struct futex_hash_bucket *hb1, *hb2; + struct futex_q *this, *next; + int ret, op_ret; ++ WAKE_Q(wake_q); + + retry: + ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ); +@@ -1320,7 +1318,7 @@ futex_wake_op(u32 __user *uaddr1, unsign + ret = -EINVAL; + goto out_unlock; + } +- wake_futex(this); ++ mark_wake_futex(&wake_q, this); + if (++ret >= nr_wake) + break; + } +@@ -1334,7 +1332,7 @@ futex_wake_op(u32 __user *uaddr1, unsign + ret = -EINVAL; + goto out_unlock; + } +- wake_futex(this); ++ mark_wake_futex(&wake_q, this); + if (++op_ret >= nr_wake2) + break; + } +@@ -1344,6 +1342,7 @@ futex_wake_op(u32 __user *uaddr1, unsign + + out_unlock: + double_unlock_hb(hb1, hb2); ++ wake_up_q(&wake_q); + out_put_keys: + put_futex_key(&key2); + out_put_key1: +@@ -1503,6 +1502,7 @@ static int futex_requeue(u32 __user *uad + struct futex_pi_state *pi_state = NULL; + struct futex_hash_bucket *hb1, *hb2; + struct futex_q *this, *next; ++ WAKE_Q(wake_q); + + if (requeue_pi) { + /* +@@ -1679,7 +1679,7 @@ static int futex_requeue(u32 __user *uad + * woken by futex_unlock_pi(). + */ + if (++task_count <= nr_wake && !requeue_pi) { +- wake_futex(this); ++ mark_wake_futex(&wake_q, this); + continue; + } + +@@ -1719,6 +1719,7 @@ static int futex_requeue(u32 __user *uad + out_unlock: + free_pi_state(pi_state); + double_unlock_hb(hb1, hb2); ++ wake_up_q(&wake_q); + hb_waiters_dec(hb2); + + /* diff --git a/debian/patches/features/all/rt/0002-mm-uaccess-trigger-might_sleep-in-might_fault-with-d.patch b/debian/patches/features/all/rt/0002-mm-uaccess-trigger-might_sleep-in-might_fault-with-d.patch new file mode 100644 index 000000000..0cee8b93a --- /dev/null +++ b/debian/patches/features/all/rt/0002-mm-uaccess-trigger-might_sleep-in-might_fault-with-d.patch @@ -0,0 +1,101 @@ +From: David Hildenbrand +Date: Mon, 11 May 2015 17:52:07 +0200 +Subject: mm, uaccess: trigger might_sleep() in might_fault() with disabled pagefaults +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Commit 662bbcb2747c ("mm, sched: Allow uaccess in atomic with +pagefault_disable()") removed might_sleep() checks for all user access +code (that uses might_fault()). + +The reason was to disable wrong "sleep in atomic" warnings in the +following scenario: + pagefault_disable() + rc = copy_to_user(...) + pagefault_enable() + +Which is valid, as pagefault_disable() increments the preempt counter +and therefore disables the pagefault handler. copy_to_user() will not +sleep and return an error code if a page is not available. + +However, as all might_sleep() checks are removed, +CONFIG_DEBUG_ATOMIC_SLEEP would no longer detect the following scenario: + spin_lock(&lock); + rc = copy_to_user(...) + spin_unlock(&lock) + +If the kernel is compiled with preemption turned on, preempt_disable() +will make in_atomic() detect disabled preemption. The fault handler would +correctly never sleep on user access. +However, with preemption turned off, preempt_disable() is usually a NOP +(with !CONFIG_PREEMPT_COUNT), therefore in_atomic() will not be able to +detect disabled preemption nor disabled pagefaults. The fault handler +could sleep. +We really want to enable CONFIG_DEBUG_ATOMIC_SLEEP checks for user access +functions again, otherwise we can end up with horrible deadlocks. + +Root of all evil is that pagefault_disable() acts almost as +preempt_disable(), depending on preemption being turned on/off. + +As we now have pagefault_disabled(), we can use it to distinguish +whether user acces functions might sleep. + +Convert might_fault() into a makro that calls __might_fault(), to +allow proper file + line messages in case of a might_sleep() warning. + +[upstream commit 9ec23531fd48031d1b6ca5366f5f967d17a8bc28] +Signed-off-by: David Hildenbrand +--- + include/linux/kernel.h | 3 ++- + mm/memory.c | 18 ++++++------------ + 2 files changed, 8 insertions(+), 13 deletions(-) + +--- a/include/linux/kernel.h ++++ b/include/linux/kernel.h +@@ -244,7 +244,8 @@ static inline u32 reciprocal_scale(u32 v + + #if defined(CONFIG_MMU) && \ + (defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP)) +-void might_fault(void); ++#define might_fault() __might_fault(__FILE__, __LINE__) ++void __might_fault(const char *file, int line); + #else + static inline void might_fault(void) { } + #endif +--- a/mm/memory.c ++++ b/mm/memory.c +@@ -3737,7 +3737,7 @@ void print_vma_addr(char *prefix, unsign + } + + #if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP) +-void might_fault(void) ++void __might_fault(const char *file, int line) + { + /* + * Some code (nfs/sunrpc) uses socket ops on kernel memory while +@@ -3747,21 +3747,15 @@ void might_fault(void) + */ + if (segment_eq(get_fs(), KERNEL_DS)) + return; +- +- /* +- * it would be nicer only to annotate paths which are not under +- * pagefault_disable, however that requires a larger audit and +- * providing helpers like get_user_atomic. +- */ +- if (in_atomic()) ++ if (pagefault_disabled()) + return; +- +- __might_sleep(__FILE__, __LINE__, 0); +- ++ __might_sleep(file, line, 0); ++#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) + if (current->mm) + might_lock_read(¤t->mm->mmap_sem); ++#endif + } +-EXPORT_SYMBOL(might_fault); ++EXPORT_SYMBOL(__might_fault); + #endif + + #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) diff --git a/debian/patches/features/all/rt/0003-uaccess-clarify-that-uaccess-may-only-sleep-if-pagef.patch b/debian/patches/features/all/rt/0003-uaccess-clarify-that-uaccess-may-only-sleep-if-pagef.patch new file mode 100644 index 000000000..395e6afb0 --- /dev/null +++ b/debian/patches/features/all/rt/0003-uaccess-clarify-that-uaccess-may-only-sleep-if-pagef.patch @@ -0,0 +1,642 @@ +From: David Hildenbrand +Date: Mon, 11 May 2015 17:52:08 +0200 +Subject: [PATCH] sched/preempt, futex: Update comments to clarify that preemption doesn't have to be disabled +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +In general, non-atomic variants of user access functions must not sleep +if pagefaults are disabled. + +Let's update all relevant comments in uaccess code. This also reflects +the might_sleep() checks in might_fault(). + +[upstream commit 2f09b227eeed4b3a072fe818c82a4c773b778cde] +Signed-off-by: David Hildenbrand +--- + arch/avr32/include/asm/uaccess.h | 12 ++++++--- + arch/hexagon/include/asm/uaccess.h | 3 +- + arch/m32r/include/asm/uaccess.h | 30 +++++++++++++++------- + arch/microblaze/include/asm/uaccess.h | 6 +++- + arch/mips/include/asm/uaccess.h | 45 ++++++++++++++++++++++------------ + arch/s390/include/asm/uaccess.h | 15 +++++++---- + arch/score/include/asm/uaccess.h | 15 +++++++---- + arch/tile/include/asm/uaccess.h | 18 +++++++++---- + arch/x86/include/asm/uaccess.h | 15 +++++++---- + arch/x86/include/asm/uaccess_32.h | 6 +++- + arch/x86/lib/usercopy_32.c | 6 +++- + lib/strnlen_user.c | 6 +++- + 12 files changed, 118 insertions(+), 59 deletions(-) + +--- a/arch/avr32/include/asm/uaccess.h ++++ b/arch/avr32/include/asm/uaccess.h +@@ -97,7 +97,8 @@ static inline __kernel_size_t __copy_fro + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -116,7 +117,8 @@ static inline __kernel_size_t __copy_fro + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -136,7 +138,8 @@ static inline __kernel_size_t __copy_fro + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -158,7 +161,8 @@ static inline __kernel_size_t __copy_fro + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +--- a/arch/hexagon/include/asm/uaccess.h ++++ b/arch/hexagon/include/asm/uaccess.h +@@ -36,7 +36,8 @@ + * @addr: User space pointer to start of block to check + * @size: Size of block to check + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Checks if a pointer to a block of memory in user space is valid. + * +--- a/arch/m32r/include/asm/uaccess.h ++++ b/arch/m32r/include/asm/uaccess.h +@@ -91,7 +91,8 @@ static inline void set_fs(mm_segment_t s + * @addr: User space pointer to start of block to check + * @size: Size of block to check + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Checks if a pointer to a block of memory in user space is valid. + * +@@ -155,7 +156,8 @@ extern int fixup_exception(struct pt_reg + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -175,7 +177,8 @@ extern int fixup_exception(struct pt_reg + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -194,7 +197,8 @@ extern int fixup_exception(struct pt_reg + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -274,7 +278,8 @@ do { \ + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -568,7 +573,8 @@ unsigned long __generic_copy_from_user(v + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from kernel space to user space. Caller must check + * the specified block with access_ok() before calling this function. +@@ -588,7 +594,8 @@ unsigned long __generic_copy_from_user(v + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from kernel space to user space. + * +@@ -606,7 +613,8 @@ unsigned long __generic_copy_from_user(v + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to kernel space. Caller must check + * the specified block with access_ok() before calling this function. +@@ -626,7 +634,8 @@ unsigned long __generic_copy_from_user(v + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to kernel space. + * +@@ -677,7 +686,8 @@ unsigned long clear_user(void __user *me + * strlen_user: - Get the size of a string in user space. + * @str: The string to measure. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Get the size of a NUL-terminated string in user space. + * +--- a/arch/microblaze/include/asm/uaccess.h ++++ b/arch/microblaze/include/asm/uaccess.h +@@ -178,7 +178,8 @@ extern long __user_bad(void); + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -290,7 +291,8 @@ extern long __user_bad(void); + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +--- a/arch/mips/include/asm/uaccess.h ++++ b/arch/mips/include/asm/uaccess.h +@@ -103,7 +103,8 @@ extern u64 __ua_limit; + * @addr: User space pointer to start of block to check + * @size: Size of block to check + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Checks if a pointer to a block of memory in user space is valid. + * +@@ -138,7 +139,8 @@ extern u64 __ua_limit; + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -157,7 +159,8 @@ extern u64 __ua_limit; + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -177,7 +180,8 @@ extern u64 __ua_limit; + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -199,7 +203,8 @@ extern u64 __ua_limit; + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -498,7 +503,8 @@ extern void __put_user_unknown(void); + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -517,7 +523,8 @@ extern void __put_user_unknown(void); + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -537,7 +544,8 @@ extern void __put_user_unknown(void); + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -559,7 +567,8 @@ extern void __put_user_unknown(void); + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -815,7 +824,8 @@ extern size_t __copy_user(void *__to, co + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from kernel space to user space. Caller must check + * the specified block with access_ok() before calling this function. +@@ -888,7 +898,8 @@ extern size_t __copy_user_inatomic(void + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from kernel space to user space. + * +@@ -1075,7 +1086,8 @@ extern size_t __copy_in_user_eva(void *_ + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to kernel space. Caller must check + * the specified block with access_ok() before calling this function. +@@ -1107,7 +1119,8 @@ extern size_t __copy_in_user_eva(void *_ + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to kernel space. + * +@@ -1329,7 +1342,8 @@ strncpy_from_user(char *__to, const char + * strlen_user: - Get the size of a string in user space. + * @str: The string to measure. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Get the size of a NUL-terminated string in user space. + * +@@ -1398,7 +1412,8 @@ static inline long __strnlen_user(const + * strnlen_user: - Get the size of a string in user space. + * @str: The string to measure. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Get the size of a NUL-terminated string in user space. + * +--- a/arch/s390/include/asm/uaccess.h ++++ b/arch/s390/include/asm/uaccess.h +@@ -98,7 +98,8 @@ static inline unsigned long extable_fixu + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to kernel space. Caller must check + * the specified block with access_ok() before calling this function. +@@ -118,7 +119,8 @@ unsigned long __must_check __copy_from_u + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from kernel space to user space. Caller must check + * the specified block with access_ok() before calling this function. +@@ -264,7 +266,8 @@ int __get_user_bad(void) __attribute__(( + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from kernel space to user space. + * +@@ -290,7 +293,8 @@ void copy_from_user_overflow(void) + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to kernel space. + * +@@ -348,7 +352,8 @@ static inline unsigned long strnlen_user + * strlen_user: - Get the size of a string in user space. + * @str: The string to measure. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Get the size of a NUL-terminated string in user space. + * +--- a/arch/score/include/asm/uaccess.h ++++ b/arch/score/include/asm/uaccess.h +@@ -36,7 +36,8 @@ + * @addr: User space pointer to start of block to check + * @size: Size of block to check + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Checks if a pointer to a block of memory in user space is valid. + * +@@ -61,7 +62,8 @@ + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -79,7 +81,8 @@ + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -98,7 +101,8 @@ + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -119,7 +123,8 @@ + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +--- a/arch/tile/include/asm/uaccess.h ++++ b/arch/tile/include/asm/uaccess.h +@@ -78,7 +78,8 @@ int __range_ok(unsigned long addr, unsig + * @addr: User space pointer to start of block to check + * @size: Size of block to check + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Checks if a pointer to a block of memory in user space is valid. + * +@@ -192,7 +193,8 @@ extern int __get_user_bad(void) + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -274,7 +276,8 @@ extern int __put_user_bad(void) + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -330,7 +333,8 @@ extern int __put_user_bad(void) + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from kernel space to user space. Caller must check + * the specified block with access_ok() before calling this function. +@@ -366,7 +370,8 @@ copy_to_user(void __user *to, const void + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to kernel space. Caller must check + * the specified block with access_ok() before calling this function. +@@ -437,7 +442,8 @@ static inline unsigned long __must_check + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to user space. Caller must check + * the specified blocks with access_ok() before calling this function. +--- a/arch/x86/include/asm/uaccess.h ++++ b/arch/x86/include/asm/uaccess.h +@@ -74,7 +74,8 @@ static inline bool __chk_range_not_ok(un + * @addr: User space pointer to start of block to check + * @size: Size of block to check + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Checks if a pointer to a block of memory in user space is valid. + * +@@ -145,7 +146,8 @@ extern int __get_user_bad(void); + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -240,7 +242,8 @@ extern void __put_user_8(void); + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +@@ -455,7 +458,8 @@ struct __large_struct { unsigned long bu + * @x: Variable to store result. + * @ptr: Source address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger +@@ -479,7 +483,8 @@ struct __large_struct { unsigned long bu + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger +--- a/arch/x86/include/asm/uaccess_32.h ++++ b/arch/x86/include/asm/uaccess_32.h +@@ -70,7 +70,8 @@ static __always_inline unsigned long __m + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from kernel space to user space. Caller must check + * the specified block with access_ok() before calling this function. +@@ -117,7 +118,8 @@ static __always_inline unsigned long + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to kernel space. Caller must check + * the specified block with access_ok() before calling this function. +--- a/arch/x86/lib/usercopy_32.c ++++ b/arch/x86/lib/usercopy_32.c +@@ -647,7 +647,8 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocach + * @from: Source address, in kernel space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from kernel space to user space. + * +@@ -668,7 +669,8 @@ EXPORT_SYMBOL(_copy_to_user); + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Copy data from user space to kernel space. + * +--- a/lib/strnlen_user.c ++++ b/lib/strnlen_user.c +@@ -85,7 +85,8 @@ static inline long do_strnlen_user(const + * @str: The string to measure. + * @count: Maximum count (including NUL character) + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Get the size of a NUL-terminated string in user space. + * +@@ -121,7 +122,8 @@ EXPORT_SYMBOL(strnlen_user); + * strlen_user: - Get the size of a user string INCLUDING final NUL. + * @str: The string to measure. + * +- * Context: User context only. This function may sleep. ++ * Context: User context only. This function may sleep if pagefaults are ++ * enabled. + * + * Get the size of a NUL-terminated string in user space. + * diff --git a/debian/patches/features/all/rt/0004-ipc-mqueue-Implement-lockless-pipelined-wakeups.patch b/debian/patches/features/all/rt/0004-ipc-mqueue-Implement-lockless-pipelined-wakeups.patch new file mode 100644 index 000000000..a5d6b3bd4 --- /dev/null +++ b/debian/patches/features/all/rt/0004-ipc-mqueue-Implement-lockless-pipelined-wakeups.patch @@ -0,0 +1,184 @@ +From: Davidlohr Bueso +Date: Mon, 4 May 2015 07:02:46 -0700 +Subject: ipc/mqueue: Implement lockless pipelined wakeups +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +This patch moves the wakeup_process() invocation so it is not done under +the info->lock by making use of a lockless wake_q. With this change, the +waiter is woken up once it is STATE_READY and it does not need to loop +on SMP if it is still in STATE_PENDING. In the timeout case we still need +to grab the info->lock to verify the state. + +This change should also avoid the introduction of preempt_disable() in -rt +which avoids a busy-loop which pools for the STATE_PENDING -> STATE_READY +change if the waiter has a higher priority compared to the waker. + +Additionally, this patch micro-optimizes wq_sleep by using the cheaper +cousin of set_current_state(TASK_INTERRUPTABLE) as we will block no +matter what, thus get rid of the implied barrier. + +[upstream commit fa6004ad4528153b699a4d5ce5ea6b33acce74cc] + +Signed-off-by: Davidlohr Bueso +Signed-off-by: Peter Zijlstra (Intel) +Acked-by: George Spelvin +Acked-by: Thomas Gleixner +Cc: Andrew Morton +Cc: Borislav Petkov +Cc: Chris Mason +Cc: H. Peter Anvin +Cc: Linus Torvalds +Cc: Manfred Spraul +Cc: Peter Zijlstra +Cc: Sebastian Andrzej Siewior +Cc: Steven Rostedt +Cc: dave@stgolabs.net +Link: http://lkml.kernel.org/r/1430748166.1940.17.camel@stgolabs.net +Signed-off-by: Ingo Molnar +Signed-off-by: Sebastian Andrzej Siewior +--- + ipc/mqueue.c | 54 +++++++++++++++++++++++++++++++++--------------------- + 1 file changed, 33 insertions(+), 21 deletions(-) + +--- a/ipc/mqueue.c ++++ b/ipc/mqueue.c +@@ -47,8 +47,7 @@ + #define RECV 1 + + #define STATE_NONE 0 +-#define STATE_PENDING 1 +-#define STATE_READY 2 ++#define STATE_READY 1 + + struct posix_msg_tree_node { + struct rb_node rb_node; +@@ -571,15 +570,12 @@ static int wq_sleep(struct mqueue_inode_ + wq_add(info, sr, ewp); + + for (;;) { +- set_current_state(TASK_INTERRUPTIBLE); ++ __set_current_state(TASK_INTERRUPTIBLE); + + spin_unlock(&info->lock); + time = schedule_hrtimeout_range_clock(timeout, 0, + HRTIMER_MODE_ABS, CLOCK_REALTIME); + +- while (ewp->state == STATE_PENDING) +- cpu_relax(); +- + if (ewp->state == STATE_READY) { + retval = 0; + goto out; +@@ -907,11 +903,15 @@ SYSCALL_DEFINE1(mq_unlink, const char __ + * list of waiting receivers. A sender checks that list before adding the new + * message into the message array. If there is a waiting receiver, then it + * bypasses the message array and directly hands the message over to the +- * receiver. +- * The receiver accepts the message and returns without grabbing the queue +- * spinlock. Therefore an intermediate STATE_PENDING state and memory barriers +- * are necessary. The same algorithm is used for sysv semaphores, see +- * ipc/sem.c for more details. ++ * receiver. The receiver accepts the message and returns without grabbing the ++ * queue spinlock: ++ * ++ * - Set pointer to message. ++ * - Queue the receiver task for later wakeup (without the info->lock). ++ * - Update its state to STATE_READY. Now the receiver can continue. ++ * - Wake up the process after the lock is dropped. Should the process wake up ++ * before this wakeup (due to a timeout or a signal) it will either see ++ * STATE_READY and continue or acquire the lock to check the state again. + * + * The same algorithm is used for senders. + */ +@@ -919,21 +919,29 @@ SYSCALL_DEFINE1(mq_unlink, const char __ + /* pipelined_send() - send a message directly to the task waiting in + * sys_mq_timedreceive() (without inserting message into a queue). + */ +-static inline void pipelined_send(struct mqueue_inode_info *info, ++static inline void pipelined_send(struct wake_q_head *wake_q, ++ struct mqueue_inode_info *info, + struct msg_msg *message, + struct ext_wait_queue *receiver) + { + receiver->msg = message; + list_del(&receiver->list); +- receiver->state = STATE_PENDING; +- wake_up_process(receiver->task); +- smp_wmb(); ++ wake_q_add(wake_q, receiver->task); ++ /* ++ * Rely on the implicit cmpxchg barrier from wake_q_add such ++ * that we can ensure that updating receiver->state is the last ++ * write operation: As once set, the receiver can continue, ++ * and if we don't have the reference count from the wake_q, ++ * yet, at that point we can later have a use-after-free ++ * condition and bogus wakeup. ++ */ + receiver->state = STATE_READY; + } + + /* pipelined_receive() - if there is task waiting in sys_mq_timedsend() + * gets its message and put to the queue (we have one free place for sure). */ +-static inline void pipelined_receive(struct mqueue_inode_info *info) ++static inline void pipelined_receive(struct wake_q_head *wake_q, ++ struct mqueue_inode_info *info) + { + struct ext_wait_queue *sender = wq_get_first_waiter(info, SEND); + +@@ -944,10 +952,9 @@ static inline void pipelined_receive(str + } + if (msg_insert(sender->msg, info)) + return; ++ + list_del(&sender->list); +- sender->state = STATE_PENDING; +- wake_up_process(sender->task); +- smp_wmb(); ++ wake_q_add(wake_q, sender->task); + sender->state = STATE_READY; + } + +@@ -965,6 +972,7 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqd + struct timespec ts; + struct posix_msg_tree_node *new_leaf = NULL; + int ret = 0; ++ WAKE_Q(wake_q); + + if (u_abs_timeout) { + int res = prepare_timeout(u_abs_timeout, &expires, &ts); +@@ -1049,7 +1057,7 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqd + } else { + receiver = wq_get_first_waiter(info, RECV); + if (receiver) { +- pipelined_send(info, msg_ptr, receiver); ++ pipelined_send(&wake_q, info, msg_ptr, receiver); + } else { + /* adds message to the queue */ + ret = msg_insert(msg_ptr, info); +@@ -1062,6 +1070,7 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqd + } + out_unlock: + spin_unlock(&info->lock); ++ wake_up_q(&wake_q); + out_free: + if (ret) + free_msg(msg_ptr); +@@ -1149,14 +1158,17 @@ SYSCALL_DEFINE5(mq_timedreceive, mqd_t, + msg_ptr = wait.msg; + } + } else { ++ WAKE_Q(wake_q); ++ + msg_ptr = msg_get(info); + + inode->i_atime = inode->i_mtime = inode->i_ctime = + CURRENT_TIME; + + /* There is now free space in queue. */ +- pipelined_receive(info); ++ pipelined_receive(&wake_q, info); + spin_unlock(&info->lock); ++ wake_up_q(&wake_q); + ret = 0; + } + if (ret == 0) { diff --git a/debian/patches/features/all/rt/0004-mm-explicitly-disable-enable-preemption-in-kmap_atom.patch b/debian/patches/features/all/rt/0004-mm-explicitly-disable-enable-preemption-in-kmap_atom.patch new file mode 100644 index 000000000..32856545a --- /dev/null +++ b/debian/patches/features/all/rt/0004-mm-explicitly-disable-enable-preemption-in-kmap_atom.patch @@ -0,0 +1,368 @@ +From: David Hildenbrand +Date: Mon, 11 May 2015 17:52:09 +0200 +Subject: sched/preempt, mm/kmap: Explicitly disable/enable preemption in kmap_atomic_* +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The existing code relies on pagefault_disable() implicitly disabling +preemption, so that no schedule will happen between kmap_atomic() and +kunmap_atomic(). + +Let's make this explicit, to prepare for pagefault_disable() not +touching preemption anymore. + +[uptream commit 2cb7c9cb426660b5ed58b643d9e7dd5d50ba901f] +Signed-off-by: David Hildenbrand +--- + arch/arm/mm/highmem.c | 3 +++ + arch/frv/mm/highmem.c | 2 ++ + arch/metag/mm/highmem.c | 4 +++- + arch/microblaze/mm/highmem.c | 4 +++- + arch/mips/mm/highmem.c | 5 ++++- + arch/mn10300/include/asm/highmem.h | 3 +++ + arch/parisc/include/asm/cacheflush.h | 2 ++ + arch/powerpc/mm/highmem.c | 4 +++- + arch/sparc/mm/highmem.c | 4 +++- + arch/tile/mm/highmem.c | 3 ++- + arch/x86/mm/highmem_32.c | 3 ++- + arch/x86/mm/iomap_32.c | 2 ++ + arch/xtensa/mm/highmem.c | 2 ++ + include/linux/highmem.h | 2 ++ + include/linux/io-mapping.h | 2 ++ + 15 files changed, 38 insertions(+), 7 deletions(-) + +--- a/arch/arm/mm/highmem.c ++++ b/arch/arm/mm/highmem.c +@@ -59,6 +59,7 @@ void *kmap_atomic(struct page *page) + void *kmap; + int type; + ++ preempt_disable(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -121,6 +122,7 @@ void __kunmap_atomic(void *kvaddr) + kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)])); + } + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(__kunmap_atomic); + +@@ -130,6 +132,7 @@ void *kmap_atomic_pfn(unsigned long pfn) + int idx, type; + struct page *page = pfn_to_page(pfn); + ++ preempt_disable(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +--- a/arch/frv/mm/highmem.c ++++ b/arch/frv/mm/highmem.c +@@ -42,6 +42,7 @@ void *kmap_atomic(struct page *page) + unsigned long paddr; + int type; + ++ preempt_disable(); + pagefault_disable(); + type = kmap_atomic_idx_push(); + paddr = page_to_phys(page); +@@ -85,5 +86,6 @@ void __kunmap_atomic(void *kvaddr) + } + kmap_atomic_idx_pop(); + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(__kunmap_atomic); +--- a/arch/metag/mm/highmem.c ++++ b/arch/metag/mm/highmem.c +@@ -43,7 +43,7 @@ void *kmap_atomic(struct page *page) + unsigned long vaddr; + int type; + +- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ ++ preempt_disable(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -82,6 +82,7 @@ void __kunmap_atomic(void *kvaddr) + } + + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(__kunmap_atomic); + +@@ -95,6 +96,7 @@ void *kmap_atomic_pfn(unsigned long pfn) + unsigned long vaddr; + int type; + ++ preempt_disable(); + pagefault_disable(); + + type = kmap_atomic_idx_push(); +--- a/arch/microblaze/mm/highmem.c ++++ b/arch/microblaze/mm/highmem.c +@@ -37,7 +37,7 @@ void *kmap_atomic_prot(struct page *page + unsigned long vaddr; + int idx, type; + +- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ ++ preempt_disable(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -63,6 +63,7 @@ void __kunmap_atomic(void *kvaddr) + + if (vaddr < __fix_to_virt(FIX_KMAP_END)) { + pagefault_enable(); ++ preempt_enable(); + return; + } + +@@ -84,5 +85,6 @@ void __kunmap_atomic(void *kvaddr) + #endif + kmap_atomic_idx_pop(); + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(__kunmap_atomic); +--- a/arch/mips/mm/highmem.c ++++ b/arch/mips/mm/highmem.c +@@ -47,7 +47,7 @@ void *kmap_atomic(struct page *page) + unsigned long vaddr; + int idx, type; + +- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ ++ preempt_disable(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -72,6 +72,7 @@ void __kunmap_atomic(void *kvaddr) + + if (vaddr < FIXADDR_START) { // FIXME + pagefault_enable(); ++ preempt_enable(); + return; + } + +@@ -92,6 +93,7 @@ void __kunmap_atomic(void *kvaddr) + #endif + kmap_atomic_idx_pop(); + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(__kunmap_atomic); + +@@ -104,6 +106,7 @@ void *kmap_atomic_pfn(unsigned long pfn) + unsigned long vaddr; + int idx, type; + ++ preempt_disable(); + pagefault_disable(); + + type = kmap_atomic_idx_push(); +--- a/arch/mn10300/include/asm/highmem.h ++++ b/arch/mn10300/include/asm/highmem.h +@@ -75,6 +75,7 @@ static inline void *kmap_atomic(struct p + unsigned long vaddr; + int idx, type; + ++ preempt_disable(); + pagefault_disable(); + if (page < highmem_start_page) + return page_address(page); +@@ -98,6 +99,7 @@ static inline void __kunmap_atomic(unsig + + if (vaddr < FIXADDR_START) { /* FIXME */ + pagefault_enable(); ++ preempt_enable(); + return; + } + +@@ -122,6 +124,7 @@ static inline void __kunmap_atomic(unsig + + kmap_atomic_idx_pop(); + pagefault_enable(); ++ preempt_enable(); + } + #endif /* __KERNEL__ */ + +--- a/arch/parisc/include/asm/cacheflush.h ++++ b/arch/parisc/include/asm/cacheflush.h +@@ -142,6 +142,7 @@ static inline void kunmap(struct page *p + + static inline void *kmap_atomic(struct page *page) + { ++ preempt_disable(); + pagefault_disable(); + return page_address(page); + } +@@ -150,6 +151,7 @@ static inline void __kunmap_atomic(void + { + flush_kernel_dcache_page_addr(addr); + pagefault_enable(); ++ preempt_enable(); + } + + #define kmap_atomic_prot(page, prot) kmap_atomic(page) +--- a/arch/powerpc/mm/highmem.c ++++ b/arch/powerpc/mm/highmem.c +@@ -34,7 +34,7 @@ void *kmap_atomic_prot(struct page *page + unsigned long vaddr; + int idx, type; + +- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ ++ preempt_disable(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -59,6 +59,7 @@ void __kunmap_atomic(void *kvaddr) + + if (vaddr < __fix_to_virt(FIX_KMAP_END)) { + pagefault_enable(); ++ preempt_enable(); + return; + } + +@@ -82,5 +83,6 @@ void __kunmap_atomic(void *kvaddr) + + kmap_atomic_idx_pop(); + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(__kunmap_atomic); +--- a/arch/sparc/mm/highmem.c ++++ b/arch/sparc/mm/highmem.c +@@ -53,7 +53,7 @@ void *kmap_atomic(struct page *page) + unsigned long vaddr; + long idx, type; + +- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ ++ preempt_disable(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -91,6 +91,7 @@ void __kunmap_atomic(void *kvaddr) + + if (vaddr < FIXADDR_START) { // FIXME + pagefault_enable(); ++ preempt_enable(); + return; + } + +@@ -126,5 +127,6 @@ void __kunmap_atomic(void *kvaddr) + + kmap_atomic_idx_pop(); + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(__kunmap_atomic); +--- a/arch/tile/mm/highmem.c ++++ b/arch/tile/mm/highmem.c +@@ -201,7 +201,7 @@ void *kmap_atomic_prot(struct page *page + int idx, type; + pte_t *pte; + +- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ ++ preempt_disable(); + pagefault_disable(); + + /* Avoid icache flushes by disallowing atomic executable mappings. */ +@@ -259,6 +259,7 @@ void __kunmap_atomic(void *kvaddr) + } + + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(__kunmap_atomic); + +--- a/arch/x86/mm/highmem_32.c ++++ b/arch/x86/mm/highmem_32.c +@@ -35,7 +35,7 @@ void *kmap_atomic_prot(struct page *page + unsigned long vaddr; + int idx, type; + +- /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ ++ preempt_disable(); + pagefault_disable(); + + if (!PageHighMem(page)) +@@ -100,6 +100,7 @@ void __kunmap_atomic(void *kvaddr) + #endif + + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(__kunmap_atomic); + +--- a/arch/x86/mm/iomap_32.c ++++ b/arch/x86/mm/iomap_32.c +@@ -59,6 +59,7 @@ void *kmap_atomic_prot_pfn(unsigned long + unsigned long vaddr; + int idx, type; + ++ preempt_disable(); + pagefault_disable(); + + type = kmap_atomic_idx_push(); +@@ -117,5 +118,6 @@ iounmap_atomic(void __iomem *kvaddr) + } + + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL_GPL(iounmap_atomic); +--- a/arch/xtensa/mm/highmem.c ++++ b/arch/xtensa/mm/highmem.c +@@ -42,6 +42,7 @@ void *kmap_atomic(struct page *page) + enum fixed_addresses idx; + unsigned long vaddr; + ++ preempt_disable(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -79,6 +80,7 @@ void __kunmap_atomic(void *kvaddr) + } + + pagefault_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(__kunmap_atomic); + +--- a/include/linux/highmem.h ++++ b/include/linux/highmem.h +@@ -65,6 +65,7 @@ static inline void kunmap(struct page *p + + static inline void *kmap_atomic(struct page *page) + { ++ preempt_disable(); + pagefault_disable(); + return page_address(page); + } +@@ -73,6 +74,7 @@ static inline void *kmap_atomic(struct p + static inline void __kunmap_atomic(void *addr) + { + pagefault_enable(); ++ preempt_enable(); + } + + #define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn)) +--- a/include/linux/io-mapping.h ++++ b/include/linux/io-mapping.h +@@ -141,6 +141,7 @@ static inline void __iomem * + io_mapping_map_atomic_wc(struct io_mapping *mapping, + unsigned long offset) + { ++ preempt_disable(); + pagefault_disable(); + return ((char __force __iomem *) mapping) + offset; + } +@@ -149,6 +150,7 @@ static inline void + io_mapping_unmap_atomic(void __iomem *vaddr) + { + pagefault_enable(); ++ preempt_enable(); + } + + /* Non-atomic map/unmap */ diff --git a/debian/patches/features/all/rt/0005-futex-Ensure-lock-unlock-symetry-versus-pi_lock-and-.patch b/debian/patches/features/all/rt/0005-futex-Ensure-lock-unlock-symetry-versus-pi_lock-and-.patch new file mode 100644 index 000000000..833f01f36 --- /dev/null +++ b/debian/patches/features/all/rt/0005-futex-Ensure-lock-unlock-symetry-versus-pi_lock-and-.patch @@ -0,0 +1,43 @@ +From: Thomas Gleixner +Date: Fri, 1 Mar 2013 11:17:42 +0100 +Subject: futex: Ensure lock/unlock symetry versus pi_lock and hash bucket lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +In exit_pi_state_list() we have the following locking construct: + + spin_lock(&hb->lock); + raw_spin_lock_irq(&curr->pi_lock); + + ... + spin_unlock(&hb->lock); + +In !RT this works, but on RT the migrate_enable() function which is +called from spin_unlock() sees atomic context due to the held pi_lock +and just decrements the migrate_disable_atomic counter of the +task. Now the next call to migrate_disable() sees the counter being +negative and issues a warning. That check should be in +migrate_enable() already. + +Fix this by dropping pi_lock before unlocking hb->lock and reaquire +pi_lock after that again. This is safe as the loop code reevaluates +head again under the pi_lock. + +Reported-by: Yong Zhang +Signed-off-by: Thomas Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/futex.c | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -738,7 +738,9 @@ void exit_pi_state_list(struct task_stru + * task still owns the PI-state: + */ + if (head->next != next) { ++ raw_spin_unlock_irq(&curr->pi_lock); + spin_unlock(&hb->lock); ++ raw_spin_lock_irq(&curr->pi_lock); + continue; + } + diff --git a/debian/patches/features/all/rt/0005-mips-kmap_coherent-relies-on-disabled-preemption.patch b/debian/patches/features/all/rt/0005-mips-kmap_coherent-relies-on-disabled-preemption.patch new file mode 100644 index 000000000..647765e21 --- /dev/null +++ b/debian/patches/features/all/rt/0005-mips-kmap_coherent-relies-on-disabled-preemption.patch @@ -0,0 +1,41 @@ +From: David Hildenbrand +Date: Mon, 11 May 2015 17:52:10 +0200 +Subject: sched/preempt, mm/kmap, MIPS: Disable preemption in kmap_coherent() explicitly +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +k(un)map_coherent relies on pagefault_disable() to also disable +preemption. + +Let's make this explicit, to prepare for pagefault_disable() not +touching preemption anymore. + +This patch is based on a patch by Yang Shi on the -rt tree: +"k{un}map_coherent are just called when cpu_has_dc_aliases == 1 with VIPT +cache. However, actually, the most modern MIPS processors have PIPT dcache +without dcache alias issue. In such case, k{un}map_atomic will be called +with preempt enabled." + +[upstream commit ce01948eb85da733558fa77c2a554144a57ab0fb] +Signed-off-by: David Hildenbrand +--- + arch/mips/mm/init.c | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/arch/mips/mm/init.c ++++ b/arch/mips/mm/init.c +@@ -90,6 +90,7 @@ static void *__kmap_pgprot(struct page * + + BUG_ON(Page_dcache_dirty(page)); + ++ preempt_disable(); + pagefault_disable(); + idx = (addr >> PAGE_SHIFT) & (FIX_N_COLOURS - 1); + idx += in_interrupt() ? FIX_N_COLOURS : 0; +@@ -152,6 +153,7 @@ void kunmap_coherent(void) + write_c0_entryhi(old_ctx); + local_irq_restore(flags); + pagefault_enable(); ++ preempt_enable(); + } + + void copy_user_highpage(struct page *to, struct page *from, diff --git a/debian/patches/features/all/rt/0006-mm-use-pagefault_disable-to-check-for-disabled-pagef.patch b/debian/patches/features/all/rt/0006-mm-use-pagefault_disable-to-check-for-disabled-pagef.patch new file mode 100644 index 000000000..0b829707e --- /dev/null +++ b/debian/patches/features/all/rt/0006-mm-use-pagefault_disable-to-check-for-disabled-pagef.patch @@ -0,0 +1,647 @@ +From: David Hildenbrand +Date: Mon, 11 May 2015 17:52:11 +0200 +Subject: mm/fault, arch: Use pagefault_disable() to check for disabled pagefaults in the handler +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Introduce faulthandler_disabled() and use it to check for irq context and +disabled pagefaults (via pagefault_disable()) in the pagefault handlers. + +Please note that we keep the in_atomic() checks in place - to detect +whether in irq context (in which case preemption is always properly +disabled). + +In contrast, preempt_disable() should never be used to disable pagefaults. +With !CONFIG_PREEMPT_COUNT, preempt_disable() doesn't modify the preempt +counter, and therefore the result of in_atomic() differs. +We validate that condition by using might_fault() checks when calling +might_sleep(). + +Therefore, add a comment to faulthandler_disabled(), describing why this +is needed. + +faulthandler_disabled() and pagefault_disable() are defined in +linux/uaccess.h, so let's properly add that include to all relevant files. + +This patch is based on a patch from Thomas Gleixner. + +[upstream commit 70ffdb9393a7264a069265edded729078dcf0425] +Signed-off-by: David Hildenbrand +--- + arch/alpha/mm/fault.c | 5 ++--- + arch/arc/mm/fault.c | 2 +- + arch/arm/mm/fault.c | 2 +- + arch/arm64/mm/fault.c | 2 +- + arch/avr32/mm/fault.c | 4 ++-- + arch/cris/mm/fault.c | 6 +++--- + arch/frv/mm/fault.c | 4 ++-- + arch/ia64/mm/fault.c | 4 ++-- + arch/m32r/mm/fault.c | 8 ++++---- + arch/m68k/mm/fault.c | 4 ++-- + arch/metag/mm/fault.c | 2 +- + arch/microblaze/mm/fault.c | 8 ++++---- + arch/mips/mm/fault.c | 4 ++-- + arch/mn10300/mm/fault.c | 4 ++-- + arch/nios2/mm/fault.c | 2 +- + arch/parisc/kernel/traps.c | 4 ++-- + arch/parisc/mm/fault.c | 4 ++-- + arch/powerpc/mm/fault.c | 9 +++++---- + arch/s390/mm/fault.c | 2 +- + arch/score/mm/fault.c | 3 ++- + arch/sh/mm/fault.c | 5 +++-- + arch/sparc/mm/fault_32.c | 4 ++-- + arch/sparc/mm/fault_64.c | 4 ++-- + arch/sparc/mm/init_64.c | 2 +- + arch/tile/mm/fault.c | 4 ++-- + arch/um/kernel/trap.c | 4 ++-- + arch/unicore32/mm/fault.c | 2 +- + arch/x86/mm/fault.c | 5 +++-- + arch/xtensa/mm/fault.c | 4 ++-- + include/linux/uaccess.h | 12 ++++++++++++ + 30 files changed, 72 insertions(+), 57 deletions(-) + +--- a/arch/alpha/mm/fault.c ++++ b/arch/alpha/mm/fault.c +@@ -23,8 +23,7 @@ + #include + #include + #include +- +-#include ++#include + + extern void die_if_kernel(char *,struct pt_regs *,long, unsigned long *); + +@@ -107,7 +106,7 @@ do_page_fault(unsigned long address, uns + + /* If we're in an interrupt context, or have no user context, + we must not take the fault. */ +- if (!mm || in_atomic()) ++ if (!mm || faulthandler_disabled()) + goto no_context; + + #ifdef CONFIG_ALPHA_LARGE_VMALLOC +--- a/arch/arc/mm/fault.c ++++ b/arch/arc/mm/fault.c +@@ -86,7 +86,7 @@ void do_page_fault(unsigned long address + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + if (user_mode(regs)) +--- a/arch/arm/mm/fault.c ++++ b/arch/arm/mm/fault.c +@@ -276,7 +276,7 @@ do_page_fault(unsigned long addr, unsign + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + if (user_mode(regs)) +--- a/arch/arm64/mm/fault.c ++++ b/arch/arm64/mm/fault.c +@@ -211,7 +211,7 @@ static int __kprobes do_page_fault(unsig + * If we're in an interrupt or have no user context, we must not take + * the fault. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + if (user_mode(regs)) +--- a/arch/avr32/mm/fault.c ++++ b/arch/avr32/mm/fault.c +@@ -14,11 +14,11 @@ + #include + #include + #include ++#include + + #include + #include + #include +-#include + + #ifdef CONFIG_KPROBES + static inline int notify_page_fault(struct pt_regs *regs, int trap) +@@ -81,7 +81,7 @@ asmlinkage void do_page_fault(unsigned l + * If we're in an interrupt or have no user context, we must + * not take the fault... + */ +- if (in_atomic() || !mm || regs->sr & SYSREG_BIT(GM)) ++ if (faulthandler_disabled() || !mm || regs->sr & SYSREG_BIT(GM)) + goto no_context; + + local_irq_enable(); +--- a/arch/cris/mm/fault.c ++++ b/arch/cris/mm/fault.c +@@ -8,7 +8,7 @@ + #include + #include + #include +-#include ++#include + #include + + extern int find_fixup_code(struct pt_regs *); +@@ -109,11 +109,11 @@ do_page_fault(unsigned long address, str + info.si_code = SEGV_MAPERR; + + /* +- * If we're in an interrupt or "atomic" operation or have no ++ * If we're in an interrupt, have pagefaults disabled or have no + * user context, we must not take the fault. + */ + +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + if (user_mode(regs)) +--- a/arch/frv/mm/fault.c ++++ b/arch/frv/mm/fault.c +@@ -19,9 +19,9 @@ + #include + #include + #include ++#include + + #include +-#include + #include + + /*****************************************************************************/ +@@ -78,7 +78,7 @@ asmlinkage void do_page_fault(int datamm + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + if (user_mode(__frame)) +--- a/arch/ia64/mm/fault.c ++++ b/arch/ia64/mm/fault.c +@@ -11,10 +11,10 @@ + #include + #include + #include ++#include + + #include + #include +-#include + + extern int die(char *, struct pt_regs *, long); + +@@ -96,7 +96,7 @@ ia64_do_page_fault (unsigned long addres + /* + * If we're in an interrupt or have no user context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + #ifdef CONFIG_VIRTUAL_MEM_MAP +--- a/arch/m32r/mm/fault.c ++++ b/arch/m32r/mm/fault.c +@@ -24,9 +24,9 @@ + #include /* For unblank_screen() */ + #include + #include ++#include + + #include +-#include + #include + #include + #include +@@ -111,10 +111,10 @@ asmlinkage void do_page_fault(struct pt_ + mm = tsk->mm; + + /* +- * If we're in an interrupt or have no user context or are running in an +- * atomic region then we must not take the fault.. ++ * If we're in an interrupt or have no user context or have pagefaults ++ * disabled then we must not take the fault. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto bad_area_nosemaphore; + + if (error_code & ACE_USERMODE) +--- a/arch/m68k/mm/fault.c ++++ b/arch/m68k/mm/fault.c +@@ -10,10 +10,10 @@ + #include + #include + #include ++#include + + #include + #include +-#include + #include + + extern void die_if_kernel(char *, struct pt_regs *, long); +@@ -81,7 +81,7 @@ int do_page_fault(struct pt_regs *regs, + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + if (user_mode(regs)) +--- a/arch/metag/mm/fault.c ++++ b/arch/metag/mm/fault.c +@@ -105,7 +105,7 @@ int do_page_fault(struct pt_regs *regs, + + mm = tsk->mm; + +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + if (user_mode(regs)) +--- a/arch/microblaze/mm/fault.c ++++ b/arch/microblaze/mm/fault.c +@@ -107,14 +107,14 @@ void do_page_fault(struct pt_regs *regs, + if ((error_code & 0x13) == 0x13 || (error_code & 0x11) == 0x11) + is_write = 0; + +- if (unlikely(in_atomic() || !mm)) { ++ if (unlikely(faulthandler_disabled() || !mm)) { + if (kernel_mode(regs)) + goto bad_area_nosemaphore; + +- /* in_atomic() in user mode is really bad, ++ /* faulthandler_disabled() in user mode is really bad, + as is current->mm == NULL. */ +- pr_emerg("Page fault in user mode with in_atomic(), mm = %p\n", +- mm); ++ pr_emerg("Page fault in user mode with faulthandler_disabled(), mm = %p\n", ++ mm); + pr_emerg("r15 = %lx MSR = %lx\n", + regs->r15, regs->msr); + die("Weird page fault", regs, SIGSEGV); +--- a/arch/mips/mm/fault.c ++++ b/arch/mips/mm/fault.c +@@ -21,10 +21,10 @@ + #include + #include + #include ++#include + + #include + #include +-#include + #include + #include /* For VMALLOC_END */ + #include +@@ -94,7 +94,7 @@ static void __kprobes __do_page_fault(st + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto bad_area_nosemaphore; + + if (user_mode(regs)) +--- a/arch/mn10300/mm/fault.c ++++ b/arch/mn10300/mm/fault.c +@@ -23,8 +23,8 @@ + #include + #include + #include /* For unblank_screen() */ ++#include + +-#include + #include + #include + #include +@@ -168,7 +168,7 @@ asmlinkage void do_page_fault(struct pt_ + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR) +--- a/arch/nios2/mm/fault.c ++++ b/arch/nios2/mm/fault.c +@@ -77,7 +77,7 @@ asmlinkage void do_page_fault(struct pt_ + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto bad_area_nosemaphore; + + if (user_mode(regs)) +--- a/arch/parisc/kernel/traps.c ++++ b/arch/parisc/kernel/traps.c +@@ -26,9 +26,9 @@ + #include + #include + #include ++#include + + #include +-#include + #include + #include + #include +@@ -800,7 +800,7 @@ void notrace handle_interruption(int cod + * unless pagefault_disable() was called before. + */ + +- if (fault_space == 0 && !in_atomic()) ++ if (fault_space == 0 && !faulthandler_disabled()) + { + pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC); + parisc_terminate("Kernel Fault", regs, code, fault_address); +--- a/arch/parisc/mm/fault.c ++++ b/arch/parisc/mm/fault.c +@@ -15,8 +15,8 @@ + #include + #include + #include ++#include + +-#include + #include + + /* Various important other fields */ +@@ -207,7 +207,7 @@ void do_page_fault(struct pt_regs *regs, + int fault; + unsigned int flags; + +- if (in_atomic()) ++ if (pagefault_disabled()) + goto no_context; + + tsk = current; +--- a/arch/powerpc/mm/fault.c ++++ b/arch/powerpc/mm/fault.c +@@ -33,13 +33,13 @@ + #include + #include + #include ++#include + + #include + #include + #include + #include + #include +-#include + #include + #include + #include +@@ -272,15 +272,16 @@ int __kprobes do_page_fault(struct pt_re + if (!arch_irq_disabled_regs(regs)) + local_irq_enable(); + +- if (in_atomic() || mm == NULL) { ++ if (faulthandler_disabled() || mm == NULL) { + if (!user_mode(regs)) { + rc = SIGSEGV; + goto bail; + } +- /* in_atomic() in user mode is really bad, ++ /* faulthandler_disabled() in user mode is really bad, + as is current->mm == NULL. */ + printk(KERN_EMERG "Page fault in user mode with " +- "in_atomic() = %d mm = %p\n", in_atomic(), mm); ++ "faulthandler_disabled() = %d mm = %p\n", ++ faulthandler_disabled(), mm); + printk(KERN_EMERG "NIP = %lx MSR = %lx\n", + regs->nip, regs->msr); + die("Weird page fault", regs, SIGSEGV); +--- a/arch/s390/mm/fault.c ++++ b/arch/s390/mm/fault.c +@@ -399,7 +399,7 @@ static inline int do_exception(struct pt + * user context. + */ + fault = VM_FAULT_BADCONTEXT; +- if (unlikely(!user_space_fault(regs) || in_atomic() || !mm)) ++ if (unlikely(!user_space_fault(regs) || faulthandler_disabled() || !mm)) + goto out; + + address = trans_exc_code & __FAIL_ADDR_MASK; +--- a/arch/score/mm/fault.c ++++ b/arch/score/mm/fault.c +@@ -34,6 +34,7 @@ + #include + #include + #include ++#include + + /* + * This routine handles page faults. It determines the address, +@@ -73,7 +74,7 @@ asmlinkage void do_page_fault(struct pt_ + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (pagefault_disabled() || !mm) + goto bad_area_nosemaphore; + + if (user_mode(regs)) +--- a/arch/sh/mm/fault.c ++++ b/arch/sh/mm/fault.c +@@ -17,6 +17,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -438,9 +439,9 @@ asmlinkage void __kprobes do_page_fault( + + /* + * If we're in an interrupt, have no user context or are running +- * in an atomic region then we must not take the fault: ++ * with pagefaults disabled then we must not take the fault: + */ +- if (unlikely(in_atomic() || !mm)) { ++ if (unlikely(faulthandler_disabled() || !mm)) { + bad_area_nosemaphore(regs, error_code, address); + return; + } +--- a/arch/sparc/mm/fault_32.c ++++ b/arch/sparc/mm/fault_32.c +@@ -21,6 +21,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -29,7 +30,6 @@ + #include + #include + #include +-#include + + #include "mm_32.h" + +@@ -196,7 +196,7 @@ asmlinkage void do_sparc_fault(struct pt + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (pagefault_disabled() || !mm) + goto no_context; + + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); +--- a/arch/sparc/mm/fault_64.c ++++ b/arch/sparc/mm/fault_64.c +@@ -22,12 +22,12 @@ + #include + #include + #include ++#include + + #include + #include + #include + #include +-#include + #include + #include + #include +@@ -330,7 +330,7 @@ asmlinkage void __kprobes do_sparc64_fau + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto intr_or_no_mm; + + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); +--- a/arch/sparc/mm/init_64.c ++++ b/arch/sparc/mm/init_64.c +@@ -2738,7 +2738,7 @@ void hugetlb_setup(struct pt_regs *regs) + struct mm_struct *mm = current->mm; + struct tsb_config *tp; + +- if (in_atomic() || !mm) { ++ if (faulthandler_disabled() || !mm) { + const struct exception_table_entry *entry; + + entry = search_exception_tables(regs->tpc); +--- a/arch/tile/mm/fault.c ++++ b/arch/tile/mm/fault.c +@@ -354,9 +354,9 @@ static int handle_page_fault(struct pt_r + + /* + * If we're in an interrupt, have no user context or are running in an +- * atomic region then we must not take the fault. ++ * region with pagefaults disabled then we must not take the fault. + */ +- if (in_atomic() || !mm) { ++ if (pagefault_disabled() || !mm) { + vma = NULL; /* happy compiler */ + goto bad_area_nosemaphore; + } +--- a/arch/um/kernel/trap.c ++++ b/arch/um/kernel/trap.c +@@ -35,10 +35,10 @@ int handle_page_fault(unsigned long addr + *code_out = SEGV_MAPERR; + + /* +- * If the fault was during atomic operation, don't take the fault, just ++ * If the fault was with pagefaults disabled, don't take the fault, just + * fail. + */ +- if (in_atomic()) ++ if (faulthandler_disabled()) + goto out_nosemaphore; + + if (is_user) +--- a/arch/unicore32/mm/fault.c ++++ b/arch/unicore32/mm/fault.c +@@ -218,7 +218,7 @@ static int do_pf(unsigned long addr, uns + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) ++ if (faulthandler_disabled() || !mm) + goto no_context; + + if (user_mode(regs)) +--- a/arch/x86/mm/fault.c ++++ b/arch/x86/mm/fault.c +@@ -13,6 +13,7 @@ + #include /* hstate_index_to_shift */ + #include /* prefetchw */ + #include /* exception_enter(), ... */ ++#include /* faulthandler_disabled() */ + + #include /* dotraplinkage, ... */ + #include /* pgd_*(), ... */ +@@ -1126,9 +1127,9 @@ static noinline void + + /* + * If we're in an interrupt, have no user context or are running +- * in an atomic region then we must not take the fault: ++ * in a region with pagefaults disabled then we must not take the fault + */ +- if (unlikely(in_atomic() || !mm)) { ++ if (unlikely(faulthandler_disabled() || !mm)) { + bad_area_nosemaphore(regs, error_code, address); + return; + } +--- a/arch/xtensa/mm/fault.c ++++ b/arch/xtensa/mm/fault.c +@@ -15,10 +15,10 @@ + #include + #include + #include ++#include + #include + #include + #include +-#include + #include + + DEFINE_PER_CPU(unsigned long, asid_cache) = ASID_USER_FIRST; +@@ -57,7 +57,7 @@ void do_page_fault(struct pt_regs *regs) + /* If we're in an interrupt or have no user + * context, we must not take the fault.. + */ +- if (in_atomic() || !mm) { ++ if (faulthandler_disabled() || !mm) { + bad_page_fault(regs, address, SIGSEGV); + return; + } +--- a/include/linux/uaccess.h ++++ b/include/linux/uaccess.h +@@ -59,6 +59,18 @@ static inline void pagefault_enable(void + */ + #define pagefault_disabled() (current->pagefault_disabled != 0) + ++/* ++ * The pagefault handler is in general disabled by pagefault_disable() or ++ * when in irq context (via in_atomic()). ++ * ++ * This function should only be used by the fault handlers. Other users should ++ * stick to pagefault_disabled(). ++ * Please NEVER use preempt_disable() to disable the fault handler. With ++ * !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled. ++ * in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT. ++ */ ++#define faulthandler_disabled() (pagefault_disabled() || in_atomic()) ++ + #ifndef ARCH_HAS_NOCACHE_UACCESS + + static inline unsigned long __copy_from_user_inatomic_nocache(void *to, diff --git a/debian/patches/features/all/rt/0007-drm-i915-use-pagefault_disabled-to-check-for-disable.patch b/debian/patches/features/all/rt/0007-drm-i915-use-pagefault_disabled-to-check-for-disable.patch new file mode 100644 index 000000000..58852ff82 --- /dev/null +++ b/debian/patches/features/all/rt/0007-drm-i915-use-pagefault_disabled-to-check-for-disable.patch @@ -0,0 +1,33 @@ +From: David Hildenbrand +Date: Mon, 11 May 2015 17:52:12 +0200 +Subject: mm/fault, drm/i915: Use pagefault_disabled() to check for disabled pagefaults +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Now that the pagefault disabled counter is in place, we can replace +the in_atomic() check by a pagefault_disabled() checks. + +[upstream commit 32d8206725bcf6e3ce7832ac39e61a6ecfd558db] +Signed-off-by: David Hildenbrand +--- + drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c ++++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c +@@ -32,6 +32,7 @@ + #include "i915_trace.h" + #include "intel_drv.h" + #include ++#include + + #define __EXEC_OBJECT_HAS_PIN (1<<31) + #define __EXEC_OBJECT_HAS_FENCE (1<<30) +@@ -465,7 +466,7 @@ i915_gem_execbuffer_relocate_entry(struc + } + + /* We can't wait for rendering with pagefaults disabled */ +- if (obj->active && in_atomic()) ++ if (obj->active && pagefault_disabled()) + return -EFAULT; + + if (use_cpu_reloc(obj)) diff --git a/debian/patches/features/all/rt/0008-futex-UP-futex_atomic_op_inuser-relies-on-disabled-p.patch b/debian/patches/features/all/rt/0008-futex-UP-futex_atomic_op_inuser-relies-on-disabled-p.patch new file mode 100644 index 000000000..4bc942060 --- /dev/null +++ b/debian/patches/features/all/rt/0008-futex-UP-futex_atomic_op_inuser-relies-on-disabled-p.patch @@ -0,0 +1,46 @@ +From: David Hildenbrand +Date: Mon, 11 May 2015 17:52:13 +0200 +Subject: sched/preempt, futex: Disable preemption in UP futex_atomic_op_inuser() explicitly +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Let's explicitly disable/enable preemption in the !CONFIG_SMP version +of futex_atomic_op_inuser, to prepare for pagefault_disable() not +touching preemption anymore. + +Otherwise we might break mutual exclusion when relying on a get_user()/ +put_user() implementation. + +[upstream commit f3dae07e442a8131a5485b6a38db2aa22a7a48cf] +Signed-off-by: David Hildenbrand +--- + include/asm-generic/futex.h | 5 +++-- + 1 file changed, 3 insertions(+), 2 deletions(-) + +--- a/include/asm-generic/futex.h ++++ b/include/asm-generic/futex.h +@@ -8,8 +8,7 @@ + #ifndef CONFIG_SMP + /* + * The following implementation only for uniprocessor machines. +- * For UP, it's relies on the fact that pagefault_disable() also disables +- * preemption to ensure mutual exclusion. ++ * It relies on preempt_disable() ensuring mutual exclusion. + * + */ + +@@ -38,6 +37,7 @@ futex_atomic_op_inuser(int encoded_op, u + if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) + oparg = 1 << oparg; + ++ preempt_disable(); + pagefault_disable(); + + ret = -EFAULT; +@@ -72,6 +72,7 @@ futex_atomic_op_inuser(int encoded_op, u + + out_pagefault_enable: + pagefault_enable(); ++ preempt_enable(); + + if (ret == 0) { + switch (cmp) { diff --git a/debian/patches/features/all/rt/0009-futex-UP-futex_atomic_cmpxchg_inatomic-relies-on-dis.patch b/debian/patches/features/all/rt/0009-futex-UP-futex_atomic_cmpxchg_inatomic-relies-on-dis.patch new file mode 100644 index 000000000..8ba63d59e --- /dev/null +++ b/debian/patches/features/all/rt/0009-futex-UP-futex_atomic_cmpxchg_inatomic-relies-on-dis.patch @@ -0,0 +1,37 @@ +From: David Hildenbrand +Date: Mon, 11 May 2015 17:52:14 +0200 +Subject: sched/preempt, futex: Disable preemption in UP futex_atomic_op_inuser() explicitly +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Let's explicitly disable/enable preemption in the !CONFIG_SMP version +of futex_atomic_cmpxchg_inatomic, to prepare for pagefault_disable() not +touching preemption anymore. This is needed for this function to be +callable from both, atomic and non-atomic context. + +Otherwise we might break mutual exclusion when relying on a get_user()/ +put_user() implementation. + +[upstream commit f3dae07e442a8131a5485b6a38db2aa22a7a48cf] +Signed-off-by: David Hildenbrand +--- + include/asm-generic/futex.h | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/include/asm-generic/futex.h ++++ b/include/asm-generic/futex.h +@@ -107,6 +107,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, + { + u32 val; + ++ preempt_disable(); + if (unlikely(get_user(val, uaddr) != 0)) + return -EFAULT; + +@@ -114,6 +115,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, + return -EFAULT; + + *uval = val; ++ preempt_enable(); + + return 0; + } diff --git a/debian/patches/features/all/rt/0010-arm-futex-UP-futex_atomic_cmpxchg_inatomic-relies-on.patch b/debian/patches/features/all/rt/0010-arm-futex-UP-futex_atomic_cmpxchg_inatomic-relies-on.patch new file mode 100644 index 000000000..9e5f27550 --- /dev/null +++ b/debian/patches/features/all/rt/0010-arm-futex-UP-futex_atomic_cmpxchg_inatomic-relies-on.patch @@ -0,0 +1,37 @@ +From: David Hildenbrand +Date: Mon, 11 May 2015 17:52:15 +0200 +Subject: sched/preempt, arm/futex: Disable preemption in UP futex_atomic_cmpxchg_inatomic() explicitly +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The !CONFIG_SMP implementation of futex_atomic_cmpxchg_inatomic() +requires preemption to be disabled to guarantee mutual exclusion. +Let's make this explicit. + +This patch is based on a patch by Sebastian Andrzej Siewior on the +-rt branch. + +[upstream commit 39919b01ae4c1949736b40b79e27178d0c0bc406] +Signed-off-by: David Hildenbrand +--- + arch/arm/include/asm/futex.h | 3 +++ + 1 file changed, 3 insertions(+) + +--- a/arch/arm/include/asm/futex.h ++++ b/arch/arm/include/asm/futex.h +@@ -93,6 +93,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) + return -EFAULT; + ++ preempt_disable(); + __asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n" + "1: " TUSER(ldr) " %1, [%4]\n" + " teq %1, %2\n" +@@ -104,6 +105,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, + : "cc", "memory"); + + *uval = val; ++ preempt_enable(); ++ + return ret; + } + diff --git a/debian/patches/features/all/rt/0011-arm-futex-UP-futex_atomic_op_inuser-relies-on-disabl.patch b/debian/patches/features/all/rt/0011-arm-futex-UP-futex_atomic_op_inuser-relies-on-disabl.patch new file mode 100644 index 000000000..0a68a5458 --- /dev/null +++ b/debian/patches/features/all/rt/0011-arm-futex-UP-futex_atomic_op_inuser-relies-on-disabl.patch @@ -0,0 +1,48 @@ +From: David Hildenbrand +Date: Mon, 11 May 2015 17:52:16 +0200 +Subject: sched/preempt, arm/futex: Disable preemption in UP futex_atomic_op_inuser() explicitly +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The !CONFIG_SMP implementation of futex_atomic_op_inuser() seems to rely +on disabled preemption to guarantee mutual exclusion. + +From commit e589ed23dd27: + "For UP it's enough to disable preemption to ensure mutual exclusion..." +From the code itself: + "!SMP, we can work around lack of atomic ops by disabling preemption" + +Let's make this explicit, to prepare for pagefault_disable() not +touching preemption anymore. + +[upstream commit 388b0e0adbc98a1b12a077dc92851a3ce016db42] +Signed-off-by: David Hildenbrand +--- + arch/arm/include/asm/futex.h | 10 ++++++++-- + 1 file changed, 8 insertions(+), 2 deletions(-) + +--- a/arch/arm/include/asm/futex.h ++++ b/arch/arm/include/asm/futex.h +@@ -127,7 +127,10 @@ futex_atomic_op_inuser (int encoded_op, + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) + return -EFAULT; + +- pagefault_disable(); /* implies preempt_disable() */ ++#ifndef CONFIG_SMP ++ preempt_disable(); ++#endif ++ pagefault_disable(); + + switch (op) { + case FUTEX_OP_SET: +@@ -149,7 +152,10 @@ futex_atomic_op_inuser (int encoded_op, + ret = -ENOSYS; + } + +- pagefault_enable(); /* subsumes preempt_enable() */ ++ pagefault_enable(); ++#ifndef CONFIG_SMP ++ preempt_enable(); ++#endif + + if (!ret) { + switch (cmp) { diff --git a/debian/patches/features/all/rt/0012-futex-clarify-that-preemption-doesn-t-have-to-be-dis.patch b/debian/patches/features/all/rt/0012-futex-clarify-that-preemption-doesn-t-have-to-be-dis.patch new file mode 100644 index 000000000..07991ede2 --- /dev/null +++ b/debian/patches/features/all/rt/0012-futex-clarify-that-preemption-doesn-t-have-to-be-dis.patch @@ -0,0 +1,86 @@ +From: David Hildenbrand +Date: Mon, 11 May 2015 17:52:17 +0200 +Subject: sched/preempt, futex: Update comments to clarify that preemption doesn't have to be disabled +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +As arm64 and arc have no special implementations for !CONFIG_SMP, mutual +exclusion doesn't seem to rely on preemption. + +Let's make it clear in the comments that preemption doesn't have to be +disabled when accessing user space in the futex code, so we can remove +preempt_disable() from pagefault_disable(). + +[upstream commit 2f09b227eeed4b3a072fe818c82a4c773b778cde] +Signed-off-by: David Hildenbrand +--- + arch/arc/include/asm/futex.h | 10 +++++----- + arch/arm64/include/asm/futex.h | 4 ++-- + 2 files changed, 7 insertions(+), 7 deletions(-) + +--- a/arch/arc/include/asm/futex.h ++++ b/arch/arc/include/asm/futex.h +@@ -53,7 +53,7 @@ static inline int futex_atomic_op_inuser + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + return -EFAULT; + +- pagefault_disable(); /* implies preempt_disable() */ ++ pagefault_disable(); + + switch (op) { + case FUTEX_OP_SET: +@@ -75,7 +75,7 @@ static inline int futex_atomic_op_inuser + ret = -ENOSYS; + } + +- pagefault_enable(); /* subsumes preempt_enable() */ ++ pagefault_enable(); + + if (!ret) { + switch (cmp) { +@@ -104,7 +104,7 @@ static inline int futex_atomic_op_inuser + return ret; + } + +-/* Compare-xchg with preemption disabled. ++/* Compare-xchg with pagefaults disabled. + * Notes: + * -Best-Effort: Exchg happens only if compare succeeds. + * If compare fails, returns; leaving retry/looping to upper layers +@@ -121,7 +121,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + return -EFAULT; + +- pagefault_disable(); /* implies preempt_disable() */ ++ pagefault_disable(); + + /* TBD : can use llock/scond */ + __asm__ __volatile__( +@@ -142,7 +142,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, + : "r"(oldval), "r"(newval), "r"(uaddr), "ir"(-EFAULT) + : "cc", "memory"); + +- pagefault_enable(); /* subsumes preempt_enable() */ ++ pagefault_enable(); + + *uval = val; + return val; +--- a/arch/arm64/include/asm/futex.h ++++ b/arch/arm64/include/asm/futex.h +@@ -58,7 +58,7 @@ futex_atomic_op_inuser (int encoded_op, + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) + return -EFAULT; + +- pagefault_disable(); /* implies preempt_disable() */ ++ pagefault_disable(); + + switch (op) { + case FUTEX_OP_SET: +@@ -85,7 +85,7 @@ futex_atomic_op_inuser (int encoded_op, + ret = -ENOSYS; + } + +- pagefault_enable(); /* subsumes preempt_enable() */ ++ pagefault_enable(); + + if (!ret) { + switch (cmp) { diff --git a/debian/patches/features/all/rt/0013-mips-properly-lock-access-to-the-fpu.patch b/debian/patches/features/all/rt/0013-mips-properly-lock-access-to-the-fpu.patch new file mode 100644 index 000000000..dd580ccf4 --- /dev/null +++ b/debian/patches/features/all/rt/0013-mips-properly-lock-access-to-the-fpu.patch @@ -0,0 +1,34 @@ +From: David Hildenbrand +Date: Mon, 11 May 2015 17:52:19 +0200 +Subject: sched/preempt, MIPS: Properly lock access to the FPU +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Let's always disable preemption and pagefaults when locking the fpu, +so we can be sure that the owner won't change in between. + +This is a preparation for pagefault_disable() not touching preemption +anymore. + +[upstream commit 76deabd1867d6d2895152f31fdec819e3505738b] +Signed-off-by: David Hildenbrand +--- + arch/mips/kernel/signal-common.h | 9 ++------- + 1 file changed, 2 insertions(+), 7 deletions(-) + +--- a/arch/mips/kernel/signal-common.h ++++ b/arch/mips/kernel/signal-common.h +@@ -28,12 +28,7 @@ extern void __user *get_sigframe(struct + extern int fpcsr_pending(unsigned int __user *fpcsr); + + /* Make sure we will not lose FPU ownership */ +-#ifdef CONFIG_PREEMPT +-#define lock_fpu_owner() preempt_disable() +-#define unlock_fpu_owner() preempt_enable() +-#else +-#define lock_fpu_owner() pagefault_disable() +-#define unlock_fpu_owner() pagefault_enable() +-#endif ++#define lock_fpu_owner() ({ preempt_disable(); pagefault_disable(); }) ++#define unlock_fpu_owner() ({ pagefault_enable(); preempt_enable(); }) + + #endif /* __SIGNAL_COMMON_H */ diff --git a/debian/patches/features/all/rt/0014-uaccess-decouple-preemption-from-the-pagefault-logic.patch b/debian/patches/features/all/rt/0014-uaccess-decouple-preemption-from-the-pagefault-logic.patch new file mode 100644 index 000000000..63acd3c2a --- /dev/null +++ b/debian/patches/features/all/rt/0014-uaccess-decouple-preemption-from-the-pagefault-logic.patch @@ -0,0 +1,61 @@ +From: David Hildenbrand +Date: Mon, 11 May 2015 17:52:20 +0200 +Subject: sched/preempt, mm/fault: Decouple preemption from the page fault logic +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +As the fault handlers now all rely on the pagefault_disabled() checks +and implicit preempt_disable() calls by pagefault_disable() have been +made explicit, we can completely rely on the pagefault_disableD counter. + +So let's no longer touch the preempt count when disabling/enabling +pagefaults. After a call to pagefault_disable(), pagefault_disabled() +will return true, but in_atomic() won't. + +[upstream commit 8222dbe21e79338de92d5e1956cd1e3994cc9f93] +Signed-off-by: David Hildenbrand +--- + include/linux/uaccess.h | 16 ++-------------- + 1 file changed, 2 insertions(+), 14 deletions(-) + +--- a/include/linux/uaccess.h ++++ b/include/linux/uaccess.h +@@ -1,7 +1,6 @@ + #ifndef __LINUX_UACCESS_H__ + #define __LINUX_UACCESS_H__ + +-#include + #include + #include + +@@ -20,17 +19,11 @@ static __always_inline void pagefault_di + * These routines enable/disable the pagefault handler. If disabled, it will + * not take any locks and go straight to the fixup table. + * +- * We increase the preempt and the pagefault count, to be able to distinguish +- * whether we run in simple atomic context or in a real pagefault_disable() +- * context. +- * +- * For now, after pagefault_disabled() has been called, we run in atomic +- * context. User access methods will not sleep. +- * ++ * User access methods will not sleep when called from a pagefault_disabled() ++ * environment. + */ + static inline void pagefault_disable(void) + { +- preempt_count_inc(); + pagefault_disabled_inc(); + /* + * make sure to have issued the store before a pagefault +@@ -47,11 +40,6 @@ static inline void pagefault_enable(void + */ + barrier(); + pagefault_disabled_dec(); +-#ifndef CONFIG_PREEMPT +- preempt_count_dec(); +-#else +- preempt_enable(); +-#endif + } + + /* diff --git a/debian/patches/features/all/rt/ARM-cmpxchg-define-__HAVE_ARCH_CMPXCHG-for-armv6-and.patch b/debian/patches/features/all/rt/ARM-cmpxchg-define-__HAVE_ARCH_CMPXCHG-for-armv6-and.patch new file mode 100644 index 000000000..860195159 --- /dev/null +++ b/debian/patches/features/all/rt/ARM-cmpxchg-define-__HAVE_ARCH_CMPXCHG-for-armv6-and.patch @@ -0,0 +1,40 @@ +From: Yong Zhang +Date: Thu, 29 Jan 2015 12:56:18 -0600 +Subject: ARM: cmpxchg: define __HAVE_ARCH_CMPXCHG for armv6 and later +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Both pi_stress and sigwaittest in rt-test show performance gain with +__HAVE_ARCH_CMPXCHG. Testing result on coretile_express_a9x4: + +pi_stress -p 99 --duration=300 (on linux-3.4-rc5; bigger is better) + vanilla: Total inversion performed: 5493381 + patched: Total inversion performed: 5621746 + +sigwaittest -p 99 -l 100000 (on linux-3.4-rc5-rt6; less is better) + 3.4-rc5-rt6: Min 24, Cur 27, Avg 30, Max 98 + patched: Min 19, Cur 21, Avg 23, Max 96 + +Signed-off-by: Yong Zhang +Cc: Russell King +Cc: Nicolas Pitre +Cc: Will Deacon +Cc: Catalin Marinas +Cc: Thomas Gleixner +Cc: linux-arm-kernel at lists.infradead.org + +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/arm/include/asm/cmpxchg.h | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/arch/arm/include/asm/cmpxchg.h ++++ b/arch/arm/include/asm/cmpxchg.h +@@ -129,6 +129,8 @@ static inline unsigned long __xchg(unsig + + #else /* min ARCH >= ARMv6 */ + ++#define __HAVE_ARCH_CMPXCHG 1 ++ + extern void __bad_cmpxchg(volatile void *ptr, int size); + + /* diff --git a/debian/patches/features/all/rt/ARM-enable-irq-in-translation-section-permission-fau.patch b/debian/patches/features/all/rt/ARM-enable-irq-in-translation-section-permission-fau.patch new file mode 100644 index 000000000..4e6142c68 --- /dev/null +++ b/debian/patches/features/all/rt/ARM-enable-irq-in-translation-section-permission-fau.patch @@ -0,0 +1,86 @@ +From: "Yadi.hu" +Date: Wed, 10 Dec 2014 10:32:09 +0800 +Subject: ARM: enable irq in translation/section permission fault handlers +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Probably happens on all ARM, with +CONFIG_PREEMPT_RT_FULL +CONFIG_DEBUG_ATOMIC_SLEEP + +This simple program.... + +int main() { + *((char*)0xc0001000) = 0; +}; + +[ 512.742724] BUG: sleeping function called from invalid context at kernel/rtmutex.c:658 +[ 512.743000] in_atomic(): 0, irqs_disabled(): 128, pid: 994, name: a +[ 512.743217] INFO: lockdep is turned off. +[ 512.743360] irq event stamp: 0 +[ 512.743482] hardirqs last enabled at (0): [< (null)>] (null) +[ 512.743714] hardirqs last disabled at (0): [] copy_process+0x3b0/0x11c0 +[ 512.744013] softirqs last enabled at (0): [] copy_process+0x3b0/0x11c0 +[ 512.744303] softirqs last disabled at (0): [< (null)>] (null) +[ 512.744631] [] (unwind_backtrace+0x0/0x104) +[ 512.745001] [] (dump_stack+0x20/0x24) +[ 512.745355] [] (__might_sleep+0x1dc/0x1e0) +[ 512.745717] [] (rt_spin_lock+0x34/0x6c) +[ 512.746073] [] (do_force_sig_info+0x34/0xf0) +[ 512.746457] [] (force_sig_info+0x18/0x1c) +[ 512.746829] [] (__do_user_fault+0x9c/0xd8) +[ 512.747185] [] (do_bad_area+0x7c/0x94) +[ 512.747536] [] (do_sect_fault+0x40/0x48) +[ 512.747898] [] (do_DataAbort+0x40/0xa0) +[ 512.748181] Exception stack(0xecaa1fb0 to 0xecaa1ff8) + +Oxc0000000 belongs to kernel address space, user task can not be +allowed to access it. For above condition, correct result is that +test case should receive a “segment fault” and exits but not stacks. + +the root cause is commit 02fe2845d6a8 ("avoid enabling interrupts in +prefetch/data abort handlers"),it deletes irq enable block in Data +abort assemble code and move them into page/breakpiont/alignment fault +handlers instead. But author does not enable irq in translation/section +permission fault handlers. ARM disables irq when it enters exception/ +interrupt mode, if kernel doesn't enable irq, it would be still disabled +during translation/section permission fault. + +We see the above splat because do_force_sig_info is still called with +IRQs off, and that code eventually does a: + + spin_lock_irqsave(&t->sighand->siglock, flags); + +As this is architecture independent code, and we've not seen any other +need for other arch to have the siglock converted to raw lock, we can +conclude that we should enable irq for ARM translation/section +permission exception. + + +Signed-off-by: Yadi.hu +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/arm/mm/fault.c | 6 ++++++ + 1 file changed, 6 insertions(+) + +--- a/arch/arm/mm/fault.c ++++ b/arch/arm/mm/fault.c +@@ -430,6 +430,9 @@ do_translation_fault(unsigned long addr, + if (addr < TASK_SIZE) + return do_page_fault(addr, fsr, regs); + ++ if (interrupts_enabled(regs)) ++ local_irq_enable(); ++ + if (user_mode(regs)) + goto bad_area; + +@@ -497,6 +500,9 @@ do_translation_fault(unsigned long addr, + static int + do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) + { ++ if (interrupts_enabled(regs)) ++ local_irq_enable(); ++ + do_bad_area(addr, fsr, regs); + return 0; + } diff --git a/debian/patches/features/all/rt/ASoC-Intel-sst-use-instead-of-at-the-of-a-C-statemen.patch b/debian/patches/features/all/rt/ASoC-Intel-sst-use-instead-of-at-the-of-a-C-statemen.patch new file mode 100644 index 000000000..8b4c95aa9 --- /dev/null +++ b/debian/patches/features/all/rt/ASoC-Intel-sst-use-instead-of-at-the-of-a-C-statemen.patch @@ -0,0 +1,27 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 11 Jun 2015 14:17:06 +0200 +Subject: ASoC: Intel: sst: use ; instead of , at the of a C statement +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +This was spotted by Fernando Lopez-Lezcano +while he tried to compile a -RT kernel with this driver enabled. +"make C=2" would also warn about this. This is is based on his patch. + +Signed-off-by: Sebastian Andrzej Siewior +--- + sound/soc/intel/atom/sst/sst.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/sound/soc/intel/atom/sst/sst.c ++++ b/sound/soc/intel/atom/sst/sst.c +@@ -368,8 +368,8 @@ static inline void sst_restore_shim64(st + * initialize by FW or driver when firmware is loaded + */ + spin_lock_irqsave(&ctx->ipc_spin_lock, irq_flags); +- sst_shim_write64(shim, SST_IMRX, shim_regs->imrx), +- sst_shim_write64(shim, SST_CSR, shim_regs->csr), ++ sst_shim_write64(shim, SST_IMRX, shim_regs->imrx); ++ sst_shim_write64(shim, SST_CSR, shim_regs->csr); + spin_unlock_irqrestore(&ctx->ipc_spin_lock, irq_flags); + } + diff --git a/debian/patches/features/all/rt/HACK-printk-drop-the-logbuf_lock-more-often.patch b/debian/patches/features/all/rt/HACK-printk-drop-the-logbuf_lock-more-often.patch new file mode 100644 index 000000000..6d50d98d9 --- /dev/null +++ b/debian/patches/features/all/rt/HACK-printk-drop-the-logbuf_lock-more-often.patch @@ -0,0 +1,77 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 21 Mar 2013 19:01:05 +0100 +Subject: printk: Drop the logbuf_lock more often +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The lock is hold with irgs off. The latency drops 500us+ on my arm bugs +with a "full" buffer after executing "dmesg" on the shell. + +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/printk/printk.c | 27 ++++++++++++++++++++++++++- + 1 file changed, 26 insertions(+), 1 deletion(-) + +--- a/kernel/printk/printk.c ++++ b/kernel/printk/printk.c +@@ -1162,6 +1162,7 @@ static int syslog_print_all(char __user + { + char *text; + int len = 0; ++ int attempts = 0; + + text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); + if (!text) +@@ -1173,7 +1174,14 @@ static int syslog_print_all(char __user + u64 seq; + u32 idx; + enum log_flags prev; +- ++ int num_msg; ++try_again: ++ attempts++; ++ if (attempts > 10) { ++ len = -EBUSY; ++ goto out; ++ } ++ num_msg = 0; + if (clear_seq < log_first_seq) { + /* messages are gone, move to first available one */ + clear_seq = log_first_seq; +@@ -1194,6 +1202,14 @@ static int syslog_print_all(char __user + prev = msg->flags; + idx = log_next(idx); + seq++; ++ num_msg++; ++ if (num_msg > 5) { ++ num_msg = 0; ++ raw_spin_unlock_irq(&logbuf_lock); ++ raw_spin_lock_irq(&logbuf_lock); ++ if (clear_seq < log_first_seq) ++ goto try_again; ++ } + } + + /* move first record forward until length fits into the buffer */ +@@ -1207,6 +1223,14 @@ static int syslog_print_all(char __user + prev = msg->flags; + idx = log_next(idx); + seq++; ++ num_msg++; ++ if (num_msg > 5) { ++ num_msg = 0; ++ raw_spin_unlock_irq(&logbuf_lock); ++ raw_spin_lock_irq(&logbuf_lock); ++ if (clear_seq < log_first_seq) ++ goto try_again; ++ } + } + + /* last message fitting into this dump */ +@@ -1247,6 +1271,7 @@ static int syslog_print_all(char __user + clear_seq = log_next_seq; + clear_idx = log_next_idx; + } ++out: + raw_spin_unlock_irq(&logbuf_lock); + + kfree(text); diff --git a/debian/patches/features/all/rt/KVM-lapic-mark-LAPIC-timer-handler-as-irqsafe.patch b/debian/patches/features/all/rt/KVM-lapic-mark-LAPIC-timer-handler-as-irqsafe.patch new file mode 100644 index 000000000..a817481fb --- /dev/null +++ b/debian/patches/features/all/rt/KVM-lapic-mark-LAPIC-timer-handler-as-irqsafe.patch @@ -0,0 +1,101 @@ +From: Marcelo Tosatti +Date: Wed, 8 Apr 2015 20:33:25 -0300 +Subject: KVM: lapic: mark LAPIC timer handler as irqsafe +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Since lapic timer handler only wakes up a simple waitqueue, +it can be executed from hardirq context. + +Also handle the case where hrtimer_start_expires fails due to -ETIME, +by injecting the interrupt to the guest immediately. + +Reduces average cyclictest latency by 3us. + +Signed-off-by: Marcelo Tosatti +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/x86/kvm/lapic.c | 40 +++++++++++++++++++++++++++++++++++++--- + 1 file changed, 37 insertions(+), 3 deletions(-) + +--- a/arch/x86/kvm/lapic.c ++++ b/arch/x86/kvm/lapic.c +@@ -1167,8 +1167,36 @@ void wait_lapic_expire(struct kvm_vcpu * + __delay(tsc_deadline - guest_tsc); + } + ++static enum hrtimer_restart apic_timer_fn(struct hrtimer *data); ++ ++static void __apic_timer_expired(struct hrtimer *data) ++{ ++ int ret, i = 0; ++ enum hrtimer_restart r; ++ struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer); ++ ++ r = apic_timer_fn(data); ++ ++ if (r == HRTIMER_RESTART) { ++ do { ++ ret = hrtimer_start_expires(data, HRTIMER_MODE_ABS); ++ if (ret == -ETIME) ++ hrtimer_add_expires_ns(&ktimer->timer, ++ ktimer->period); ++ i++; ++ } while (ret == -ETIME && i < 10); ++ ++ if (ret == -ETIME) { ++ printk_once(KERN_ERR "%s: failed to reprogram timer\n", ++ __func__); ++ WARN_ON_ONCE(1); ++ } ++ } ++} ++ + static void start_apic_timer(struct kvm_lapic *apic) + { ++ int ret; + ktime_t now; + + atomic_set(&apic->lapic_timer.pending, 0); +@@ -1199,9 +1227,11 @@ static void start_apic_timer(struct kvm_ + } + } + +- hrtimer_start(&apic->lapic_timer.timer, ++ ret = hrtimer_start(&apic->lapic_timer.timer, + ktime_add_ns(now, apic->lapic_timer.period), + HRTIMER_MODE_ABS); ++ if (ret == -ETIME) ++ __apic_timer_expired(&apic->lapic_timer.timer); + + apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016" + PRIx64 ", " +@@ -1233,8 +1263,10 @@ static void start_apic_timer(struct kvm_ + do_div(ns, this_tsc_khz); + expire = ktime_add_ns(now, ns); + expire = ktime_sub_ns(expire, lapic_timer_advance_ns); +- hrtimer_start(&apic->lapic_timer.timer, ++ ret = hrtimer_start(&apic->lapic_timer.timer, + expire, HRTIMER_MODE_ABS); ++ if (ret == -ETIME) ++ __apic_timer_expired(&apic->lapic_timer.timer); + } else + apic_timer_expired(apic); + +@@ -1707,6 +1739,7 @@ int kvm_create_lapic(struct kvm_vcpu *vc + hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS); + apic->lapic_timer.timer.function = apic_timer_fn; ++ apic->lapic_timer.timer.irqsafe = 1; + + /* + * APIC is created enabled. This will prevent kvm_lapic_set_base from +@@ -1834,7 +1867,8 @@ void __kvm_migrate_apic_timer(struct kvm + + timer = &vcpu->arch.apic->lapic_timer.timer; + if (hrtimer_cancel(timer)) +- hrtimer_start_expires(timer, HRTIMER_MODE_ABS); ++ if (hrtimer_start_expires(timer, HRTIMER_MODE_ABS) == -ETIME) ++ __apic_timer_expired(timer); + } + + /* diff --git a/debian/patches/features/all/rt/KVM-use-simple-waitqueue-for-vcpu-wq.patch b/debian/patches/features/all/rt/KVM-use-simple-waitqueue-for-vcpu-wq.patch new file mode 100644 index 000000000..805cb1d04 --- /dev/null +++ b/debian/patches/features/all/rt/KVM-use-simple-waitqueue-for-vcpu-wq.patch @@ -0,0 +1,342 @@ +From: Marcelo Tosatti +Date: Wed, 8 Apr 2015 20:33:24 -0300 +Subject: KVM: use simple waitqueue for vcpu->wq +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The problem: + +On -RT, an emulated LAPIC timer instances has the following path: + +1) hard interrupt +2) ksoftirqd is scheduled +3) ksoftirqd wakes up vcpu thread +4) vcpu thread is scheduled + +This extra context switch introduces unnecessary latency in the +LAPIC path for a KVM guest. + +The solution: + +Allow waking up vcpu thread from hardirq context, +thus avoiding the need for ksoftirqd to be scheduled. + +Normal waitqueues make use of spinlocks, which on -RT +are sleepable locks. Therefore, waking up a waitqueue +waiter involves locking a sleeping lock, which +is not allowed from hard interrupt context. + +cyclictest command line: +# cyclictest -m -n -q -p99 -l 1000000 -h60 -D 1m + +This patch reduces the average latency in my tests from 14us to 11us. + +Signed-off-by: Marcelo Tosatti +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/arm/kvm/arm.c | 4 ++-- + arch/arm/kvm/psci.c | 4 ++-- + arch/powerpc/include/asm/kvm_host.h | 4 ++-- + arch/powerpc/kvm/book3s_hv.c | 23 +++++++++++------------ + arch/s390/include/asm/kvm_host.h | 2 +- + arch/s390/kvm/interrupt.c | 8 ++++---- + arch/x86/kvm/lapic.c | 6 +++--- + include/linux/kvm_host.h | 4 ++-- + virt/kvm/async_pf.c | 4 ++-- + virt/kvm/kvm_main.c | 16 ++++++++-------- + 10 files changed, 37 insertions(+), 38 deletions(-) + +--- a/arch/arm/kvm/arm.c ++++ b/arch/arm/kvm/arm.c +@@ -474,9 +474,9 @@ bool kvm_arch_intc_initialized(struct kv + + static void vcpu_pause(struct kvm_vcpu *vcpu) + { +- wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu); ++ struct swait_head *wq = kvm_arch_vcpu_wq(vcpu); + +- wait_event_interruptible(*wq, !vcpu->arch.pause); ++ swait_event_interruptible(*wq, !vcpu->arch.pause); + } + + static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu) +--- a/arch/arm/kvm/psci.c ++++ b/arch/arm/kvm/psci.c +@@ -68,7 +68,7 @@ static unsigned long kvm_psci_vcpu_on(st + { + struct kvm *kvm = source_vcpu->kvm; + struct kvm_vcpu *vcpu = NULL; +- wait_queue_head_t *wq; ++ struct swait_head *wq; + unsigned long cpu_id; + unsigned long context_id; + phys_addr_t target_pc; +@@ -117,7 +117,7 @@ static unsigned long kvm_psci_vcpu_on(st + smp_mb(); /* Make sure the above is visible */ + + wq = kvm_arch_vcpu_wq(vcpu); +- wake_up_interruptible(wq); ++ swait_wake_interruptible(wq); + + return PSCI_RET_SUCCESS; + } +--- a/arch/powerpc/include/asm/kvm_host.h ++++ b/arch/powerpc/include/asm/kvm_host.h +@@ -280,7 +280,7 @@ struct kvmppc_vcore { + u8 in_guest; + struct list_head runnable_threads; + spinlock_t lock; +- wait_queue_head_t wq; ++ struct swait_head wq; + spinlock_t stoltb_lock; /* protects stolen_tb and preempt_tb */ + u64 stolen_tb; + u64 preempt_tb; +@@ -613,7 +613,7 @@ struct kvm_vcpu_arch { + u8 prodded; + u32 last_inst; + +- wait_queue_head_t *wqp; ++ struct swait_head *wqp; + struct kvmppc_vcore *vcore; + int ret; + int trap; +--- a/arch/powerpc/kvm/book3s_hv.c ++++ b/arch/powerpc/kvm/book3s_hv.c +@@ -115,11 +115,11 @@ static bool kvmppc_ipi_thread(int cpu) + static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) + { + int cpu = vcpu->cpu; +- wait_queue_head_t *wqp; ++ struct swait_head *wqp; + + wqp = kvm_arch_vcpu_wq(vcpu); +- if (waitqueue_active(wqp)) { +- wake_up_interruptible(wqp); ++ if (swaitqueue_active(wqp)) { ++ swait_wake_interruptible(wqp); + ++vcpu->stat.halt_wakeup; + } + +@@ -686,8 +686,8 @@ int kvmppc_pseries_do_hcall(struct kvm_v + tvcpu->arch.prodded = 1; + smp_mb(); + if (vcpu->arch.ceded) { +- if (waitqueue_active(&vcpu->wq)) { +- wake_up_interruptible(&vcpu->wq); ++ if (swaitqueue_active(&vcpu->wq)) { ++ swait_wake_interruptible(&vcpu->wq); + vcpu->stat.halt_wakeup++; + } + } +@@ -1426,7 +1426,7 @@ static struct kvmppc_vcore *kvmppc_vcore + INIT_LIST_HEAD(&vcore->runnable_threads); + spin_lock_init(&vcore->lock); + spin_lock_init(&vcore->stoltb_lock); +- init_waitqueue_head(&vcore->wq); ++ init_swait_head(&vcore->wq); + vcore->preempt_tb = TB_NIL; + vcore->lpcr = kvm->arch.lpcr; + vcore->first_vcpuid = core * threads_per_subcore; +@@ -2073,10 +2073,9 @@ static void kvmppc_vcore_blocked(struct + { + struct kvm_vcpu *vcpu; + int do_sleep = 1; ++ DEFINE_SWAITER(wait); + +- DEFINE_WAIT(wait); +- +- prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE); ++ swait_prepare(&vc->wq, &wait, TASK_INTERRUPTIBLE); + + /* + * Check one last time for pending exceptions and ceded state after +@@ -2090,7 +2089,7 @@ static void kvmppc_vcore_blocked(struct + } + + if (!do_sleep) { +- finish_wait(&vc->wq, &wait); ++ swait_finish(&vc->wq, &wait); + return; + } + +@@ -2098,7 +2097,7 @@ static void kvmppc_vcore_blocked(struct + trace_kvmppc_vcore_blocked(vc, 0); + spin_unlock(&vc->lock); + schedule(); +- finish_wait(&vc->wq, &wait); ++ swait_finish(&vc->wq, &wait); + spin_lock(&vc->lock); + vc->vcore_state = VCORE_INACTIVE; + trace_kvmppc_vcore_blocked(vc, 1); +@@ -2142,7 +2141,7 @@ static int kvmppc_run_vcpu(struct kvm_ru + kvmppc_start_thread(vcpu); + trace_kvm_guest_enter(vcpu); + } else if (vc->vcore_state == VCORE_SLEEPING) { +- wake_up(&vc->wq); ++ swait_wake(&vc->wq); + } + + } +--- a/arch/s390/include/asm/kvm_host.h ++++ b/arch/s390/include/asm/kvm_host.h +@@ -419,7 +419,7 @@ struct kvm_s390_irq_payload { + struct kvm_s390_local_interrupt { + spinlock_t lock; + struct kvm_s390_float_interrupt *float_int; +- wait_queue_head_t *wq; ++ struct swait_head *wq; + atomic_t *cpuflags; + DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS); + struct kvm_s390_irq_payload irq; +--- a/arch/s390/kvm/interrupt.c ++++ b/arch/s390/kvm/interrupt.c +@@ -875,13 +875,13 @@ int kvm_s390_handle_wait(struct kvm_vcpu + + void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu) + { +- if (waitqueue_active(&vcpu->wq)) { ++ if (swaitqueue_active(&vcpu->wq)) { + /* + * The vcpu gave up the cpu voluntarily, mark it as a good + * yield-candidate. + */ + vcpu->preempted = true; +- wake_up_interruptible(&vcpu->wq); ++ swait_wake_interruptible(&vcpu->wq); + vcpu->stat.halt_wakeup++; + } + } +@@ -987,7 +987,7 @@ int kvm_s390_inject_program_int(struct k + spin_lock(&li->lock); + irq.u.pgm.code = code; + __inject_prog(vcpu, &irq); +- BUG_ON(waitqueue_active(li->wq)); ++ BUG_ON(swaitqueue_active(li->wq)); + spin_unlock(&li->lock); + return 0; + } +@@ -1006,7 +1006,7 @@ int kvm_s390_inject_prog_irq(struct kvm_ + spin_lock(&li->lock); + irq.u.pgm = *pgm_info; + rc = __inject_prog(vcpu, &irq); +- BUG_ON(waitqueue_active(li->wq)); ++ BUG_ON(swaitqueue_active(li->wq)); + spin_unlock(&li->lock); + return rc; + } +--- a/arch/x86/kvm/lapic.c ++++ b/arch/x86/kvm/lapic.c +@@ -1104,7 +1104,7 @@ static void apic_update_lvtt(struct kvm_ + static void apic_timer_expired(struct kvm_lapic *apic) + { + struct kvm_vcpu *vcpu = apic->vcpu; +- wait_queue_head_t *q = &vcpu->wq; ++ struct swait_head *q = &vcpu->wq; + struct kvm_timer *ktimer = &apic->lapic_timer; + + if (atomic_read(&apic->lapic_timer.pending)) +@@ -1113,8 +1113,8 @@ static void apic_timer_expired(struct kv + atomic_inc(&apic->lapic_timer.pending); + kvm_set_pending_timer(vcpu); + +- if (waitqueue_active(q)) +- wake_up_interruptible(q); ++ if (swaitqueue_active(q)) ++ swait_wake_interruptible(q); + + if (apic_lvtt_tscdeadline(apic)) + ktimer->expired_tscdeadline = ktimer->tscdeadline; +--- a/include/linux/kvm_host.h ++++ b/include/linux/kvm_host.h +@@ -230,7 +230,7 @@ struct kvm_vcpu { + + int fpu_active; + int guest_fpu_loaded, guest_xcr0_loaded; +- wait_queue_head_t wq; ++ struct swait_head wq; + struct pid *pid; + int sigset_active; + sigset_t sigset; +@@ -690,7 +690,7 @@ static inline bool kvm_arch_has_noncoher + } + #endif + +-static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) ++static inline struct swait_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) + { + #ifdef __KVM_HAVE_ARCH_WQP + return vcpu->arch.wqp; +--- a/virt/kvm/async_pf.c ++++ b/virt/kvm/async_pf.c +@@ -94,8 +94,8 @@ static void async_pf_execute(struct work + + trace_kvm_async_pf_completed(addr, gva); + +- if (waitqueue_active(&vcpu->wq)) +- wake_up_interruptible(&vcpu->wq); ++ if (swaitqueue_active(&vcpu->wq)) ++ swait_wake_interruptible(&vcpu->wq); + + mmput(mm); + kvm_put_kvm(vcpu->kvm); +--- a/virt/kvm/kvm_main.c ++++ b/virt/kvm/kvm_main.c +@@ -218,7 +218,7 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, + vcpu->kvm = kvm; + vcpu->vcpu_id = id; + vcpu->pid = NULL; +- init_waitqueue_head(&vcpu->wq); ++ init_swait_head(&vcpu->wq); + kvm_async_pf_vcpu_init(vcpu); + + page = alloc_page(GFP_KERNEL | __GFP_ZERO); +@@ -1779,7 +1779,7 @@ static int kvm_vcpu_check_block(struct k + void kvm_vcpu_block(struct kvm_vcpu *vcpu) + { + ktime_t start, cur; +- DEFINE_WAIT(wait); ++ DEFINE_SWAITER(wait); + bool waited = false; + + start = cur = ktime_get(); +@@ -1800,7 +1800,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcp + } + + for (;;) { +- prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); ++ swait_prepare(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); + + if (kvm_vcpu_check_block(vcpu) < 0) + break; +@@ -1809,7 +1809,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcp + schedule(); + } + +- finish_wait(&vcpu->wq, &wait); ++ swait_finish(&vcpu->wq, &wait); + cur = ktime_get(); + + out: +@@ -1825,11 +1825,11 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu + { + int me; + int cpu = vcpu->cpu; +- wait_queue_head_t *wqp; ++ struct swait_head *wqp; + + wqp = kvm_arch_vcpu_wq(vcpu); +- if (waitqueue_active(wqp)) { +- wake_up_interruptible(wqp); ++ if (swaitqueue_active(wqp)) { ++ swait_wake_interruptible(wqp); + ++vcpu->stat.halt_wakeup; + } + +@@ -1930,7 +1930,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *m + continue; + if (vcpu == me) + continue; +- if (waitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu)) ++ if (swaitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu)) + continue; + if (!kvm_vcpu_eligible_for_directed_yield(vcpu)) + continue; diff --git a/debian/patches/features/all/rt/acpi-rt-Convert-acpi_gbl_hardware-lock-back-to-a-raw.patch b/debian/patches/features/all/rt/acpi-rt-Convert-acpi_gbl_hardware-lock-back-to-a-raw.patch new file mode 100644 index 000000000..ef3fa5836 --- /dev/null +++ b/debian/patches/features/all/rt/acpi-rt-Convert-acpi_gbl_hardware-lock-back-to-a-raw.patch @@ -0,0 +1,174 @@ +From: Steven Rostedt +Date: Wed, 13 Feb 2013 09:26:05 -0500 +Subject: acpi/rt: Convert acpi_gbl_hardware lock back to a raw_spinlock_t +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +We hit the following bug with 3.6-rt: + +[ 5.898990] BUG: scheduling while atomic: swapper/3/0/0x00000002 +[ 5.898991] no locks held by swapper/3/0. +[ 5.898993] Modules linked in: +[ 5.898996] Pid: 0, comm: swapper/3 Not tainted 3.6.11-rt28.19.el6rt.x86_64.debug #1 +[ 5.898997] Call Trace: +[ 5.899011] [] __schedule_bug+0x67/0x90 +[ 5.899028] [] __schedule+0x793/0x7a0 +[ 5.899032] [] ? debug_rt_mutex_print_deadlock+0x50/0x200 +[ 5.899034] [] schedule+0x29/0x70 +[ 5.899036] BUG: scheduling while atomic: swapper/7/0/0x00000002 +[ 5.899037] no locks held by swapper/7/0. +[ 5.899039] [] rt_spin_lock_slowlock+0xe5/0x2f0 +[ 5.899040] Modules linked in: +[ 5.899041] +[ 5.899045] [] ? _raw_spin_unlock_irqrestore+0x38/0x90 +[ 5.899046] Pid: 0, comm: swapper/7 Not tainted 3.6.11-rt28.19.el6rt.x86_64.debug #1 +[ 5.899047] Call Trace: +[ 5.899049] [] rt_spin_lock+0x16/0x40 +[ 5.899052] [] __schedule_bug+0x67/0x90 +[ 5.899054] [] ? notifier_call_chain+0x80/0x80 +[ 5.899056] [] __schedule+0x793/0x7a0 +[ 5.899059] [] acpi_os_acquire_lock+0x1f/0x23 +[ 5.899062] [] ? debug_rt_mutex_print_deadlock+0x50/0x200 +[ 5.899068] [] acpi_write_bit_register+0x33/0xb0 +[ 5.899071] [] schedule+0x29/0x70 +[ 5.899072] [] ? acpi_read_bit_register+0x33/0x51 +[ 5.899074] [] rt_spin_lock_slowlock+0xe5/0x2f0 +[ 5.899077] [] acpi_idle_enter_bm+0x8a/0x28e +[ 5.899079] [] ? _raw_spin_unlock_irqrestore+0x38/0x90 +[ 5.899081] [] ? this_cpu_load+0x1a/0x30 +[ 5.899083] [] rt_spin_lock+0x16/0x40 +[ 5.899087] [] cpuidle_enter+0x19/0x20 +[ 5.899088] [] ? notifier_call_chain+0x80/0x80 +[ 5.899090] [] cpuidle_enter_state+0x17/0x50 +[ 5.899092] [] acpi_os_acquire_lock+0x1f/0x23 +[ 5.899094] [] cpuidle899101] [] ? + +As the acpi code disables interrupts in acpi_idle_enter_bm, and calls +code that grabs the acpi lock, it causes issues as the lock is currently +in RT a sleeping lock. + +The lock was converted from a raw to a sleeping lock due to some +previous issues, and tests that showed it didn't seem to matter. +Unfortunately, it did matter for one of our boxes. + +This patch converts the lock back to a raw lock. I've run this code on a +few of my own machines, one being my laptop that uses the acpi quite +extensively. I've been able to suspend and resume without issues. + +[ tglx: Made the change exclusive for acpi_gbl_hardware_lock ] + +Signed-off-by: Steven Rostedt +Cc: John Kacur +Cc: Clark Williams +Link: http://lkml.kernel.org/r/1360765565.23152.5.camel@gandalf.local.home + +Signed-off-by: Thomas Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/acpi/acpica/acglobal.h | 2 +- + drivers/acpi/acpica/hwregs.c | 4 ++-- + drivers/acpi/acpica/hwxface.c | 4 ++-- + drivers/acpi/acpica/utmutex.c | 4 ++-- + include/acpi/platform/aclinux.h | 15 +++++++++++++++ + 5 files changed, 22 insertions(+), 7 deletions(-) + +--- a/drivers/acpi/acpica/acglobal.h ++++ b/drivers/acpi/acpica/acglobal.h +@@ -112,7 +112,7 @@ ACPI_GLOBAL(u8, acpi_gbl_global_lock_pen + * interrupt level + */ + ACPI_GLOBAL(acpi_spinlock, acpi_gbl_gpe_lock); /* For GPE data structs and registers */ +-ACPI_GLOBAL(acpi_spinlock, acpi_gbl_hardware_lock); /* For ACPI H/W except GPE registers */ ++ACPI_GLOBAL(acpi_raw_spinlock, acpi_gbl_hardware_lock); /* For ACPI H/W except GPE registers */ + ACPI_GLOBAL(acpi_spinlock, acpi_gbl_reference_count_lock); + + /* Mutex for _OSI support */ +--- a/drivers/acpi/acpica/hwregs.c ++++ b/drivers/acpi/acpica/hwregs.c +@@ -269,14 +269,14 @@ acpi_status acpi_hw_clear_acpi_status(vo + ACPI_BITMASK_ALL_FIXED_STATUS, + ACPI_FORMAT_UINT64(acpi_gbl_xpm1a_status.address))); + +- lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock); ++ raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags); + + /* Clear the fixed events in PM1 A/B */ + + status = acpi_hw_register_write(ACPI_REGISTER_PM1_STATUS, + ACPI_BITMASK_ALL_FIXED_STATUS); + +- acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags); ++ raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags); + + if (ACPI_FAILURE(status)) { + goto exit; +--- a/drivers/acpi/acpica/hwxface.c ++++ b/drivers/acpi/acpica/hwxface.c +@@ -374,7 +374,7 @@ acpi_status acpi_write_bit_register(u32 + return_ACPI_STATUS(AE_BAD_PARAMETER); + } + +- lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock); ++ raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags); + + /* + * At this point, we know that the parent register is one of the +@@ -435,7 +435,7 @@ acpi_status acpi_write_bit_register(u32 + + unlock_and_exit: + +- acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags); ++ raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags); + return_ACPI_STATUS(status); + } + +--- a/drivers/acpi/acpica/utmutex.c ++++ b/drivers/acpi/acpica/utmutex.c +@@ -88,7 +88,7 @@ acpi_status acpi_ut_mutex_initialize(voi + return_ACPI_STATUS (status); + } + +- status = acpi_os_create_lock (&acpi_gbl_hardware_lock); ++ status = acpi_os_create_raw_lock (&acpi_gbl_hardware_lock); + if (ACPI_FAILURE (status)) { + return_ACPI_STATUS (status); + } +@@ -141,7 +141,7 @@ void acpi_ut_mutex_terminate(void) + /* Delete the spinlocks */ + + acpi_os_delete_lock(acpi_gbl_gpe_lock); +- acpi_os_delete_lock(acpi_gbl_hardware_lock); ++ acpi_os_delete_raw_lock(acpi_gbl_hardware_lock); + acpi_os_delete_lock(acpi_gbl_reference_count_lock); + + /* Delete the reader/writer lock */ +--- a/include/acpi/platform/aclinux.h ++++ b/include/acpi/platform/aclinux.h +@@ -123,6 +123,7 @@ + + #define acpi_cache_t struct kmem_cache + #define acpi_spinlock spinlock_t * ++#define acpi_raw_spinlock raw_spinlock_t * + #define acpi_cpu_flags unsigned long + + /* Use native linux version of acpi_os_allocate_zeroed */ +@@ -141,6 +142,20 @@ + #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_thread_id + #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_lock + ++#define acpi_os_create_raw_lock(__handle) \ ++({ \ ++ raw_spinlock_t *lock = ACPI_ALLOCATE(sizeof(*lock)); \ ++ \ ++ if (lock) { \ ++ *(__handle) = lock; \ ++ raw_spin_lock_init(*(__handle)); \ ++ } \ ++ lock ? AE_OK : AE_NO_MEMORY; \ ++ }) ++ ++#define acpi_os_delete_raw_lock(__handle) kfree(__handle) ++ ++ + /* + * OSL interfaces used by debugger/disassembler + */ diff --git a/debian/patches/features/all/rt/arch-arm64-Add-lazy-preempt-support.patch b/debian/patches/features/all/rt/arch-arm64-Add-lazy-preempt-support.patch new file mode 100644 index 000000000..24ae7af63 --- /dev/null +++ b/debian/patches/features/all/rt/arch-arm64-Add-lazy-preempt-support.patch @@ -0,0 +1,104 @@ +From: Anders Roxell +Date: Thu, 14 May 2015 17:52:17 +0200 +Subject: arch/arm64: Add lazy preempt support +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +arm64 is missing support for PREEMPT_RT. The main feature which is +lacking is support for lazy preemption. The arch-specific entry code, +thread information structure definitions, and associated data tables +have to be extended to provide this support. Then the Kconfig file has +to be extended to indicate the support is available, and also to +indicate that support for full RT preemption is now available. + +Signed-off-by: Anders Roxell +--- + arch/arm64/Kconfig | 1 + + arch/arm64/include/asm/thread_info.h | 3 +++ + arch/arm64/kernel/asm-offsets.c | 1 + + arch/arm64/kernel/entry.S | 13 ++++++++++--- + 4 files changed, 15 insertions(+), 3 deletions(-) + +--- a/arch/arm64/Kconfig ++++ b/arch/arm64/Kconfig +@@ -69,6 +69,7 @@ config ARM64 + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP + select HAVE_RCU_TABLE_FREE ++ select HAVE_PREEMPT_LAZY + select HAVE_SYSCALL_TRACEPOINTS + select IRQ_DOMAIN + select IRQ_FORCED_THREADING +--- a/arch/arm64/include/asm/thread_info.h ++++ b/arch/arm64/include/asm/thread_info.h +@@ -47,6 +47,7 @@ struct thread_info { + mm_segment_t addr_limit; /* address limit */ + struct task_struct *task; /* main task structure */ + int preempt_count; /* 0 => preemptable, <0 => bug */ ++ int preempt_lazy_count; /* 0 => preemptable, <0 => bug */ + int cpu; /* cpu */ + }; + +@@ -101,6 +102,7 @@ static inline struct thread_info *curren + #define TIF_NEED_RESCHED 1 + #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ + #define TIF_FOREIGN_FPSTATE 3 /* CPU's FP state is not current's */ ++#define TIF_NEED_RESCHED_LAZY 4 + #define TIF_NOHZ 7 + #define TIF_SYSCALL_TRACE 8 + #define TIF_SYSCALL_AUDIT 9 +@@ -117,6 +119,7 @@ static inline struct thread_info *curren + #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) + #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) + #define _TIF_FOREIGN_FPSTATE (1 << TIF_FOREIGN_FPSTATE) ++#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) + #define _TIF_NOHZ (1 << TIF_NOHZ) + #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) + #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +--- a/arch/arm64/kernel/asm-offsets.c ++++ b/arch/arm64/kernel/asm-offsets.c +@@ -35,6 +35,7 @@ int main(void) + BLANK(); + DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); + DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count)); ++ DEFINE(TI_PREEMPT_LAZY, offsetof(struct thread_info, preempt_lazy_count)); + DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit)); + DEFINE(TI_TASK, offsetof(struct thread_info, task)); + DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); +--- a/arch/arm64/kernel/entry.S ++++ b/arch/arm64/kernel/entry.S +@@ -367,11 +367,16 @@ ENDPROC(el1_sync) + #ifdef CONFIG_PREEMPT + get_thread_info tsk + ldr w24, [tsk, #TI_PREEMPT] // get preempt count +- cbnz w24, 1f // preempt count != 0 ++ cbnz w24, 2f // preempt count != 0 + ldr x0, [tsk, #TI_FLAGS] // get flags +- tbz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling? +- bl el1_preempt ++ tbnz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling? ++ ++ ldr w24, [tsk, #TI_PREEMPT_LAZY] // get preempt lazy count ++ cbnz w24, 2f // preempt lazy count != 0 ++ tbz x0, #TIF_NEED_RESCHED_LAZY, 2f // needs rescheduling? + 1: ++ bl el1_preempt ++2: + #endif + #ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_on +@@ -385,6 +390,7 @@ ENDPROC(el1_irq) + 1: bl preempt_schedule_irq // irq en/disable is done inside + ldr x0, [tsk, #TI_FLAGS] // get new tasks TI_FLAGS + tbnz x0, #TIF_NEED_RESCHED, 1b // needs rescheduling? ++ tbnz x0, #TIF_NEED_RESCHED_LAZY, 1b // needs rescheduling? + ret x24 + #endif + +@@ -622,6 +628,7 @@ ENDPROC(cpu_switch_to) + str x0, [sp, #S_X0] // returned x0 + work_pending: + tbnz x1, #TIF_NEED_RESCHED, work_resched ++ tbnz x1, #TIF_NEED_RESCHED_LAZY, work_resched + /* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */ + ldr x2, [sp, #S_PSTATE] + mov x0, sp // 'regs' diff --git a/debian/patches/features/all/rt/arm-at91-pit-remove-irq-handler-when-clock-is-unused.patch b/debian/patches/features/all/rt/arm-at91-pit-remove-irq-handler-when-clock-is-unused.patch new file mode 100644 index 000000000..30b6cf55f --- /dev/null +++ b/debian/patches/features/all/rt/arm-at91-pit-remove-irq-handler-when-clock-is-unused.patch @@ -0,0 +1,57 @@ +From: Benedikt Spranger +Date: Sat, 6 Mar 2010 17:47:10 +0100 +Subject: ARM: AT91: PIT: Remove irq handler when clock event is unused +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Setup and remove the interrupt handler in clock event mode selection. +This avoids calling the (shared) interrupt handler when the device is +not used. + +Signed-off-by: Benedikt Spranger +Signed-off-by: Thomas Gleixner +[bigeasy: redo the patch with NR_IRQS_LEGACY which is probably required since +commit 8fe82a55 ("ARM: at91: sparse irq support") which is included since v3.6. +Patch based on what Sami Pietikäinen suggested]. +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/clocksource/timer-atmel-pit.c | 4 ++++ + drivers/clocksource/timer-atmel-st.c | 1 + + 2 files changed, 5 insertions(+) + +--- a/drivers/clocksource/timer-atmel-pit.c ++++ b/drivers/clocksource/timer-atmel-pit.c +@@ -90,6 +90,7 @@ static cycle_t read_pit_clk(struct clock + return elapsed; + } + ++static struct irqaction at91sam926x_pit_irq; + /* + * Clockevent device: interrupts every 1/HZ (== pit_cycles * MCK/16) + */ +@@ -100,6 +101,8 @@ pit_clkevt_mode(enum clock_event_mode mo + + switch (mode) { + case CLOCK_EVT_MODE_PERIODIC: ++ /* Set up irq handler */ ++ setup_irq(at91sam926x_pit_irq.irq, &at91sam926x_pit_irq); + /* update clocksource counter */ + data->cnt += data->cycle * PIT_PICNT(pit_read(data->base, AT91_PIT_PIVR)); + pit_write(data->base, AT91_PIT_MR, +@@ -113,6 +116,7 @@ pit_clkevt_mode(enum clock_event_mode mo + /* disable irq, leaving the clocksource active */ + pit_write(data->base, AT91_PIT_MR, + (data->cycle - 1) | AT91_PIT_PITEN); ++ remove_irq(at91sam926x_pit_irq.irq, &at91sam926x_pit_irq); + break; + case CLOCK_EVT_MODE_RESUME: + break; +--- a/drivers/clocksource/timer-atmel-st.c ++++ b/drivers/clocksource/timer-atmel-st.c +@@ -131,6 +131,7 @@ clkevt32k_mode(enum clock_event_mode mod + break; + case CLOCK_EVT_MODE_SHUTDOWN: + case CLOCK_EVT_MODE_UNUSED: ++ remove_irq(NR_IRQS_LEGACY + AT91_ID_SYS, &at91rm9200_timer_irq); + case CLOCK_EVT_MODE_RESUME: + irqmask = 0; + break; diff --git a/debian/patches/features/all/rt/arm-at91-tclib-default-to-tclib-timer-for-rt.patch b/debian/patches/features/all/rt/arm-at91-tclib-default-to-tclib-timer-for-rt.patch new file mode 100644 index 000000000..1435a36ec --- /dev/null +++ b/debian/patches/features/all/rt/arm-at91-tclib-default-to-tclib-timer-for-rt.patch @@ -0,0 +1,33 @@ +From: Thomas Gleixner +Date: Sat, 1 May 2010 18:29:35 +0200 +Subject: ARM: at91: tclib: Default to tclib timer for RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +RT is not too happy about the shared timer interrupt in AT91 +devices. Default to tclib timer for RT. + +Signed-off-by: Thomas Gleixner + +--- + drivers/misc/Kconfig | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +--- a/drivers/misc/Kconfig ++++ b/drivers/misc/Kconfig +@@ -54,6 +54,7 @@ config AD525X_DPOT_SPI + config ATMEL_TCLIB + bool "Atmel AT32/AT91 Timer/Counter Library" + depends on (AVR32 || ARCH_AT91) ++ default y if PREEMPT_RT_FULL + help + Select this if you want a library to allocate the Timer/Counter + blocks found on many Atmel processors. This facilitates using +@@ -86,7 +87,7 @@ config ATMEL_TCB_CLKSRC_BLOCK + config ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK + bool "TC Block use 32 KiHz clock" + depends on ATMEL_TCB_CLKSRC +- default y ++ default y if !PREEMPT_RT_FULL + help + Select this to use 32 KiHz base clock rate as TC block clock + source for clock events. diff --git a/debian/patches/features/all/rt/arm-convert-boot-lock-to-raw.patch b/debian/patches/features/all/rt/arm-convert-boot-lock-to-raw.patch new file mode 100644 index 000000000..e05ea12ef --- /dev/null +++ b/debian/patches/features/all/rt/arm-convert-boot-lock-to-raw.patch @@ -0,0 +1,466 @@ +From: Frank Rowand +Date: Mon, 19 Sep 2011 14:51:14 -0700 +Subject: arm: Convert arm boot_lock to raw +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The arm boot_lock is used by the secondary processor startup code. The locking +task is the idle thread, which has idle->sched_class == &idle_sched_class. +idle_sched_class->enqueue_task == NULL, so if the idle task blocks on the +lock, the attempt to wake it when the lock becomes available will fail: + +try_to_wake_up() + ... + activate_task() + enqueue_task() + p->sched_class->enqueue_task(rq, p, flags) + +Fix by converting boot_lock to a raw spin lock. + +Signed-off-by: Frank Rowand +Link: http://lkml.kernel.org/r/4E77B952.3010606@am.sony.com +Signed-off-by: Thomas Gleixner +--- + arch/arm/mach-exynos/platsmp.c | 12 ++++++------ + arch/arm/mach-hisi/platmcpm.c | 26 +++++++++++++------------- + arch/arm/mach-omap2/omap-smp.c | 10 +++++----- + arch/arm/mach-prima2/platsmp.c | 10 +++++----- + arch/arm/mach-qcom/platsmp.c | 10 +++++----- + arch/arm/mach-spear/platsmp.c | 10 +++++----- + arch/arm/mach-sti/platsmp.c | 10 +++++----- + arch/arm/mach-ux500/platsmp.c | 10 +++++----- + arch/arm/plat-versatile/platsmp.c | 10 +++++----- + 9 files changed, 54 insertions(+), 54 deletions(-) + +--- a/arch/arm/mach-exynos/platsmp.c ++++ b/arch/arm/mach-exynos/platsmp.c +@@ -231,7 +231,7 @@ static void __iomem *scu_base_addr(void) + return (void __iomem *)(S5P_VA_SCU); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void exynos_secondary_init(unsigned int cpu) + { +@@ -244,8 +244,8 @@ static void exynos_secondary_init(unsign + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -259,7 +259,7 @@ static int exynos_boot_secondary(unsigne + * Set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -286,7 +286,7 @@ static int exynos_boot_secondary(unsigne + + if (timeout == 0) { + printk(KERN_ERR "cpu1 power enable failed"); +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + return -ETIMEDOUT; + } + } +@@ -342,7 +342,7 @@ static int exynos_boot_secondary(unsigne + * calibrations, then wait for it to finish + */ + fail: +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? ret : 0; + } +--- a/arch/arm/mach-hisi/platmcpm.c ++++ b/arch/arm/mach-hisi/platmcpm.c +@@ -57,7 +57,7 @@ + + static void __iomem *sysctrl, *fabric; + static int hip04_cpu_table[HIP04_MAX_CLUSTERS][HIP04_MAX_CPUS_PER_CLUSTER]; +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + static u32 fabric_phys_addr; + /* + * [0]: bootwrapper physical address +@@ -104,7 +104,7 @@ static int hip04_mcpm_power_up(unsigned + if (cluster >= HIP04_MAX_CLUSTERS || cpu >= HIP04_MAX_CPUS_PER_CLUSTER) + return -EINVAL; + +- spin_lock_irq(&boot_lock); ++ raw_spin_lock_irq(&boot_lock); + + if (hip04_cpu_table[cluster][cpu]) + goto out; +@@ -133,7 +133,7 @@ static int hip04_mcpm_power_up(unsigned + udelay(20); + out: + hip04_cpu_table[cluster][cpu]++; +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + + return 0; + } +@@ -149,7 +149,7 @@ static void hip04_mcpm_power_down(void) + + __mcpm_cpu_going_down(cpu, cluster); + +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP); + hip04_cpu_table[cluster][cpu]--; + if (hip04_cpu_table[cluster][cpu] == 1) { +@@ -162,7 +162,7 @@ static void hip04_mcpm_power_down(void) + + last_man = hip04_cluster_is_down(cluster); + if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) { +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + /* Since it's Cortex A15, disable L2 prefetching. */ + asm volatile( + "mcr p15, 1, %0, c15, c0, 3 \n\t" +@@ -173,7 +173,7 @@ static void hip04_mcpm_power_down(void) + hip04_set_snoop_filter(cluster, 0); + __mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN); + } else { +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + v7_exit_coherency_flush(louis); + } + +@@ -192,7 +192,7 @@ static int hip04_mcpm_wait_for_powerdown + cpu >= HIP04_MAX_CPUS_PER_CLUSTER); + + count = TIMEOUT_MSEC / POLL_MSEC; +- spin_lock_irq(&boot_lock); ++ raw_spin_lock_irq(&boot_lock); + for (tries = 0; tries < count; tries++) { + if (hip04_cpu_table[cluster][cpu]) { + ret = -EBUSY; +@@ -202,10 +202,10 @@ static int hip04_mcpm_wait_for_powerdown + data = readl_relaxed(sysctrl + SC_CPU_RESET_STATUS(cluster)); + if (data & CORE_WFI_STATUS(cpu)) + break; +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + /* Wait for clean L2 when the whole cluster is down. */ + msleep(POLL_MSEC); +- spin_lock_irq(&boot_lock); ++ raw_spin_lock_irq(&boot_lock); + } + if (tries >= count) + goto err; +@@ -220,10 +220,10 @@ static int hip04_mcpm_wait_for_powerdown + } + if (tries >= count) + goto err; +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + return 0; + err: +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + return ret; + } + +@@ -235,10 +235,10 @@ static void hip04_mcpm_powered_up(void) + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + if (!hip04_cpu_table[cluster][cpu]) + hip04_cpu_table[cluster][cpu] = 1; +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static void __naked hip04_mcpm_power_up_setup(unsigned int affinity_level) +--- a/arch/arm/mach-omap2/omap-smp.c ++++ b/arch/arm/mach-omap2/omap-smp.c +@@ -43,7 +43,7 @@ + /* SCU base address */ + static void __iomem *scu_base; + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + void __iomem *omap4_get_scu_base(void) + { +@@ -74,8 +74,8 @@ static void omap4_secondary_init(unsigne + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -89,7 +89,7 @@ static int omap4_boot_secondary(unsigned + * Set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * Update the AuxCoreBoot0 with boot state for secondary core. +@@ -166,7 +166,7 @@ static int omap4_boot_secondary(unsigned + * Now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return 0; + } +--- a/arch/arm/mach-prima2/platsmp.c ++++ b/arch/arm/mach-prima2/platsmp.c +@@ -22,7 +22,7 @@ + + static void __iomem *clk_base; + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void sirfsoc_secondary_init(unsigned int cpu) + { +@@ -36,8 +36,8 @@ static void sirfsoc_secondary_init(unsig + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static const struct of_device_id clk_ids[] = { +@@ -75,7 +75,7 @@ static int sirfsoc_boot_secondary(unsign + /* make sure write buffer is drained */ + mb(); + +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -107,7 +107,7 @@ static int sirfsoc_boot_secondary(unsign + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } +--- a/arch/arm/mach-qcom/platsmp.c ++++ b/arch/arm/mach-qcom/platsmp.c +@@ -46,7 +46,7 @@ + + extern void secondary_startup_arm(void); + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + #ifdef CONFIG_HOTPLUG_CPU + static void __ref qcom_cpu_die(unsigned int cpu) +@@ -60,8 +60,8 @@ static void qcom_secondary_init(unsigned + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int scss_release_secondary(unsigned int cpu) +@@ -284,7 +284,7 @@ static int qcom_boot_secondary(unsigned + * set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * Send the secondary CPU a soft interrupt, thereby causing +@@ -297,7 +297,7 @@ static int qcom_boot_secondary(unsigned + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return ret; + } +--- a/arch/arm/mach-spear/platsmp.c ++++ b/arch/arm/mach-spear/platsmp.c +@@ -32,7 +32,7 @@ static void write_pen_release(int val) + sync_cache_w(&pen_release); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void __iomem *scu_base = IOMEM(VA_SCU_BASE); + +@@ -47,8 +47,8 @@ static void spear13xx_secondary_init(uns + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -59,7 +59,7 @@ static int spear13xx_boot_secondary(unsi + * set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -84,7 +84,7 @@ static int spear13xx_boot_secondary(unsi + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } +--- a/arch/arm/mach-sti/platsmp.c ++++ b/arch/arm/mach-sti/platsmp.c +@@ -34,7 +34,7 @@ static void write_pen_release(int val) + sync_cache_w(&pen_release); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void sti_secondary_init(unsigned int cpu) + { +@@ -49,8 +49,8 @@ static void sti_secondary_init(unsigned + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int sti_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -61,7 +61,7 @@ static int sti_boot_secondary(unsigned i + * set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -92,7 +92,7 @@ static int sti_boot_secondary(unsigned i + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } +--- a/arch/arm/mach-ux500/platsmp.c ++++ b/arch/arm/mach-ux500/platsmp.c +@@ -51,7 +51,7 @@ static void __iomem *scu_base_addr(void) + return NULL; + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void ux500_secondary_init(unsigned int cpu) + { +@@ -64,8 +64,8 @@ static void ux500_secondary_init(unsigne + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int ux500_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -76,7 +76,7 @@ static int ux500_boot_secondary(unsigned + * set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -97,7 +97,7 @@ static int ux500_boot_secondary(unsigned + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } +--- a/arch/arm/plat-versatile/platsmp.c ++++ b/arch/arm/plat-versatile/platsmp.c +@@ -30,7 +30,7 @@ static void write_pen_release(int val) + sync_cache_w(&pen_release); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + void versatile_secondary_init(unsigned int cpu) + { +@@ -43,8 +43,8 @@ void versatile_secondary_init(unsigned i + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -55,7 +55,7 @@ int versatile_boot_secondary(unsigned in + * Set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * This is really belt and braces; we hold unintended secondary +@@ -85,7 +85,7 @@ int versatile_boot_secondary(unsigned in + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } diff --git a/debian/patches/features/all/rt/arm-enable-highmem-for-rt.patch b/debian/patches/features/all/rt/arm-enable-highmem-for-rt.patch new file mode 100644 index 000000000..f646cba64 --- /dev/null +++ b/debian/patches/features/all/rt/arm-enable-highmem-for-rt.patch @@ -0,0 +1,149 @@ +Subject: arm: Enable highmem for rt +From: Thomas Gleixner +Date: Wed, 13 Feb 2013 11:03:11 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +fixup highmem for ARM. + +Signed-off-by: Thomas Gleixner +--- + arch/arm/include/asm/switch_to.h | 8 ++++++ + arch/arm/mm/highmem.c | 46 ++++++++++++++++++++++++++++++++++----- + include/linux/highmem.h | 1 + 3 files changed, 50 insertions(+), 5 deletions(-) + +--- a/arch/arm/include/asm/switch_to.h ++++ b/arch/arm/include/asm/switch_to.h +@@ -3,6 +3,13 @@ + + #include + ++#if defined CONFIG_PREEMPT_RT_FULL && defined CONFIG_HIGHMEM ++void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p); ++#else ++static inline void ++switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { } ++#endif ++ + /* + * For v7 SMP cores running a preemptible kernel we may be pre-empted + * during a TLB maintenance operation, so execute an inner-shareable dsb +@@ -22,6 +29,7 @@ extern struct task_struct *__switch_to(s + + #define switch_to(prev,next,last) \ + do { \ ++ switch_kmaps(prev, next); \ + last = __switch_to(prev,task_thread_info(prev), task_thread_info(next)); \ + } while (0) + +--- a/arch/arm/mm/highmem.c ++++ b/arch/arm/mm/highmem.c +@@ -54,12 +54,13 @@ EXPORT_SYMBOL(kunmap); + + void *kmap_atomic(struct page *page) + { ++ pte_t pte = mk_pte(page, kmap_prot); + unsigned int idx; + unsigned long vaddr; + void *kmap; + int type; + +- preempt_disable(); ++ preempt_disable_nort(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -93,7 +94,10 @@ void *kmap_atomic(struct page *page) + * in place, so the contained TLB flush ensures the TLB is updated + * with the new mapping. + */ +- set_fixmap_pte(idx, mk_pte(page, kmap_prot)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_fixmap_pte(idx, pte); + + return (void *)vaddr; + } +@@ -110,6 +114,9 @@ void __kunmap_atomic(void *kvaddr) + + if (cache_is_vivt()) + __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = __pte(0); ++#endif + #ifdef CONFIG_DEBUG_HIGHMEM + BUG_ON(vaddr != __fix_to_virt(idx)); + #else +@@ -122,17 +129,18 @@ void __kunmap_atomic(void *kvaddr) + kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)])); + } + pagefault_enable(); +- preempt_enable(); ++ preempt_enable_nort(); + } + EXPORT_SYMBOL(__kunmap_atomic); + + void *kmap_atomic_pfn(unsigned long pfn) + { ++ pte_t pte = pfn_pte(pfn, kmap_prot); + unsigned long vaddr; + int idx, type; + struct page *page = pfn_to_page(pfn); + +- preempt_disable(); ++ preempt_disable_nort(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -143,7 +151,10 @@ void *kmap_atomic_pfn(unsigned long pfn) + #ifdef CONFIG_DEBUG_HIGHMEM + BUG_ON(!pte_none(get_fixmap_pte(vaddr))); + #endif +- set_fixmap_pte(idx, pfn_pte(pfn, kmap_prot)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_fixmap_pte(idx, pte); + + return (void *)vaddr; + } +@@ -157,3 +168,28 @@ struct page *kmap_atomic_to_page(const v + + return pte_page(get_fixmap_pte(vaddr)); + } ++ ++#if defined CONFIG_PREEMPT_RT_FULL ++void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) ++{ ++ int i; ++ ++ /* ++ * Clear @prev's kmap_atomic mappings ++ */ ++ for (i = 0; i < prev_p->kmap_idx; i++) { ++ int idx = i + KM_TYPE_NR * smp_processor_id(); ++ ++ set_fixmap_pte(idx, __pte(0)); ++ } ++ /* ++ * Restore @next_p's kmap_atomic mappings ++ */ ++ for (i = 0; i < next_p->kmap_idx; i++) { ++ int idx = i + KM_TYPE_NR * smp_processor_id(); ++ ++ if (!pte_none(next_p->kmap_pte[i])) ++ set_fixmap_pte(idx, next_p->kmap_pte[i]); ++ } ++} ++#endif +--- a/include/linux/highmem.h ++++ b/include/linux/highmem.h +@@ -7,6 +7,7 @@ + #include + #include + #include ++#include + + #include + diff --git a/debian/patches/features/all/rt/arm-highmem-flush-tlb-on-unmap.patch b/debian/patches/features/all/rt/arm-highmem-flush-tlb-on-unmap.patch new file mode 100644 index 000000000..6b95f4432 --- /dev/null +++ b/debian/patches/features/all/rt/arm-highmem-flush-tlb-on-unmap.patch @@ -0,0 +1,28 @@ +From: Sebastian Andrzej Siewior +Date: Mon, 11 Mar 2013 21:37:27 +0100 +Subject: arm/highmem: Flush tlb on unmap +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The tlb should be flushed on unmap and thus make the mapping entry +invalid. This is only done in the non-debug case which does not look +right. + +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/arm/mm/highmem.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/arch/arm/mm/highmem.c ++++ b/arch/arm/mm/highmem.c +@@ -112,10 +112,10 @@ void __kunmap_atomic(void *kvaddr) + __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE); + #ifdef CONFIG_DEBUG_HIGHMEM + BUG_ON(vaddr != __fix_to_virt(idx)); +- set_fixmap_pte(idx, __pte(0)); + #else + (void) idx; /* to kill a warning */ + #endif ++ set_fixmap_pte(idx, __pte(0)); + kmap_atomic_idx_pop(); + } else if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) { + /* this address was obtained through kmap_high_get() */ diff --git a/debian/patches/features/all/rt/arm-preempt-lazy-support.patch b/debian/patches/features/all/rt/arm-preempt-lazy-support.patch new file mode 100644 index 000000000..a8bb3ec7b --- /dev/null +++ b/debian/patches/features/all/rt/arm-preempt-lazy-support.patch @@ -0,0 +1,106 @@ +Subject: arm: Add support for lazy preemption +From: Thomas Gleixner +Date: Wed, 31 Oct 2012 12:04:11 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Implement the arm pieces for lazy preempt. + +Signed-off-by: Thomas Gleixner +--- + arch/arm/Kconfig | 1 + + arch/arm/include/asm/thread_info.h | 3 +++ + arch/arm/kernel/asm-offsets.c | 1 + + arch/arm/kernel/entry-armv.S | 13 +++++++++++-- + arch/arm/kernel/signal.c | 3 ++- + 5 files changed, 18 insertions(+), 3 deletions(-) + +--- a/arch/arm/Kconfig ++++ b/arch/arm/Kconfig +@@ -66,6 +66,7 @@ config ARM + select HAVE_PERF_EVENTS + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP ++ select HAVE_PREEMPT_LAZY + select HAVE_RCU_TABLE_FREE if (SMP && ARM_LPAE) + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_SYSCALL_TRACEPOINTS +--- a/arch/arm/include/asm/thread_info.h ++++ b/arch/arm/include/asm/thread_info.h +@@ -50,6 +50,7 @@ struct cpu_context_save { + struct thread_info { + unsigned long flags; /* low level flags */ + int preempt_count; /* 0 => preemptable, <0 => bug */ ++ int preempt_lazy_count; /* 0 => preemptable, <0 => bug */ + mm_segment_t addr_limit; /* address limit */ + struct task_struct *task; /* main task structure */ + __u32 cpu; /* cpu */ +@@ -147,6 +148,7 @@ extern int vfp_restore_user_hwstate(stru + #define TIF_SIGPENDING 0 + #define TIF_NEED_RESCHED 1 + #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ ++#define TIF_NEED_RESCHED_LAZY 3 + #define TIF_UPROBE 7 + #define TIF_SYSCALL_TRACE 8 + #define TIF_SYSCALL_AUDIT 9 +@@ -160,6 +162,7 @@ extern int vfp_restore_user_hwstate(stru + #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) + #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) + #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) ++#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) + #define _TIF_UPROBE (1 << TIF_UPROBE) + #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) + #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +--- a/arch/arm/kernel/asm-offsets.c ++++ b/arch/arm/kernel/asm-offsets.c +@@ -65,6 +65,7 @@ int main(void) + BLANK(); + DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); + DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count)); ++ DEFINE(TI_PREEMPT_LAZY, offsetof(struct thread_info, preempt_lazy_count)); + DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit)); + DEFINE(TI_TASK, offsetof(struct thread_info, task)); + DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); +--- a/arch/arm/kernel/entry-armv.S ++++ b/arch/arm/kernel/entry-armv.S +@@ -208,11 +208,18 @@ ENDPROC(__dabt_svc) + #ifdef CONFIG_PREEMPT + get_thread_info tsk + ldr r8, [tsk, #TI_PREEMPT] @ get preempt count +- ldr r0, [tsk, #TI_FLAGS] @ get flags + teq r8, #0 @ if preempt count != 0 ++ bne 1f @ return from exeption ++ ldr r0, [tsk, #TI_FLAGS] @ get flags ++ tst r0, #_TIF_NEED_RESCHED @ if NEED_RESCHED is set ++ blne svc_preempt @ preempt! ++ ++ ldr r8, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count ++ teq r8, #0 @ if preempt lazy count != 0 + movne r0, #0 @ force flags to 0 +- tst r0, #_TIF_NEED_RESCHED ++ tst r0, #_TIF_NEED_RESCHED_LAZY + blne svc_preempt ++1: + #endif + + svc_exit r5, irq = 1 @ return from exception +@@ -227,6 +234,8 @@ ENDPROC(__irq_svc) + 1: bl preempt_schedule_irq @ irq en/disable is done inside + ldr r0, [tsk, #TI_FLAGS] @ get new tasks TI_FLAGS + tst r0, #_TIF_NEED_RESCHED ++ bne 1b ++ tst r0, #_TIF_NEED_RESCHED_LAZY + reteq r8 @ go again + b 1b + #endif +--- a/arch/arm/kernel/signal.c ++++ b/arch/arm/kernel/signal.c +@@ -563,7 +563,8 @@ asmlinkage int + do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) + { + do { +- if (likely(thread_flags & _TIF_NEED_RESCHED)) { ++ if (likely(thread_flags & (_TIF_NEED_RESCHED | ++ _TIF_NEED_RESCHED_LAZY))) { + schedule(); + } else { + if (unlikely(!user_mode(regs))) diff --git a/debian/patches/features/all/rt/arm-unwind-use_raw_lock.patch b/debian/patches/features/all/rt/arm-unwind-use_raw_lock.patch new file mode 100644 index 000000000..47b9ef946 --- /dev/null +++ b/debian/patches/features/all/rt/arm-unwind-use_raw_lock.patch @@ -0,0 +1,84 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 20 Sep 2013 14:31:54 +0200 +Subject: arm/unwind: use a raw_spin_lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Mostly unwind is done with irqs enabled however SLUB may call it with +irqs disabled while creating a new SLUB cache. + +I had system freeze while loading a module which called +kmem_cache_create() on init. That means SLUB's __slab_alloc() disabled +interrupts and then + +->new_slab_objects() + ->new_slab() + ->setup_object() + ->setup_object_debug() + ->init_tracking() + ->set_track() + ->save_stack_trace() + ->save_stack_trace_tsk() + ->walk_stackframe() + ->unwind_frame() + ->unwind_find_idx() + =>spin_lock_irqsave(&unwind_lock); + + +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/arm/kernel/unwind.c | 14 +++++++------- + 1 file changed, 7 insertions(+), 7 deletions(-) + +--- a/arch/arm/kernel/unwind.c ++++ b/arch/arm/kernel/unwind.c +@@ -93,7 +93,7 @@ extern const struct unwind_idx __start_u + static const struct unwind_idx *__origin_unwind_idx; + extern const struct unwind_idx __stop_unwind_idx[]; + +-static DEFINE_SPINLOCK(unwind_lock); ++static DEFINE_RAW_SPINLOCK(unwind_lock); + static LIST_HEAD(unwind_tables); + + /* Convert a prel31 symbol to an absolute address */ +@@ -201,7 +201,7 @@ static const struct unwind_idx *unwind_f + /* module unwind tables */ + struct unwind_table *table; + +- spin_lock_irqsave(&unwind_lock, flags); ++ raw_spin_lock_irqsave(&unwind_lock, flags); + list_for_each_entry(table, &unwind_tables, list) { + if (addr >= table->begin_addr && + addr < table->end_addr) { +@@ -213,7 +213,7 @@ static const struct unwind_idx *unwind_f + break; + } + } +- spin_unlock_irqrestore(&unwind_lock, flags); ++ raw_spin_unlock_irqrestore(&unwind_lock, flags); + } + + pr_debug("%s: idx = %p\n", __func__, idx); +@@ -529,9 +529,9 @@ struct unwind_table *unwind_table_add(un + tab->begin_addr = text_addr; + tab->end_addr = text_addr + text_size; + +- spin_lock_irqsave(&unwind_lock, flags); ++ raw_spin_lock_irqsave(&unwind_lock, flags); + list_add_tail(&tab->list, &unwind_tables); +- spin_unlock_irqrestore(&unwind_lock, flags); ++ raw_spin_unlock_irqrestore(&unwind_lock, flags); + + return tab; + } +@@ -543,9 +543,9 @@ void unwind_table_del(struct unwind_tabl + if (!tab) + return; + +- spin_lock_irqsave(&unwind_lock, flags); ++ raw_spin_lock_irqsave(&unwind_lock, flags); + list_del(&tab->list); +- spin_unlock_irqrestore(&unwind_lock, flags); ++ raw_spin_unlock_irqrestore(&unwind_lock, flags); + + kfree(tab); + } diff --git a/debian/patches/features/all/rt/ata-disable-interrupts-if-non-rt.patch b/debian/patches/features/all/rt/ata-disable-interrupts-if-non-rt.patch new file mode 100644 index 000000000..41c0c9907 --- /dev/null +++ b/debian/patches/features/all/rt/ata-disable-interrupts-if-non-rt.patch @@ -0,0 +1,65 @@ +From: Steven Rostedt +Date: Fri, 3 Jul 2009 08:44:29 -0500 +Subject: ata: Do not disable interrupts in ide code for preempt-rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Use the local_irq_*_nort variants. + +Signed-off-by: Steven Rostedt +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + drivers/ata/libata-sff.c | 12 ++++++------ + 1 file changed, 6 insertions(+), 6 deletions(-) + +--- a/drivers/ata/libata-sff.c ++++ b/drivers/ata/libata-sff.c +@@ -678,9 +678,9 @@ unsigned int ata_sff_data_xfer_noirq(str + unsigned long flags; + unsigned int consumed; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + consumed = ata_sff_data_xfer32(dev, buf, buflen, rw); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + return consumed; + } +@@ -719,7 +719,7 @@ static void ata_pio_sector(struct ata_qu + unsigned long flags; + + /* FIXME: use a bounce buffer */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + buf = kmap_atomic(page); + + /* do the actual data transfer */ +@@ -727,7 +727,7 @@ static void ata_pio_sector(struct ata_qu + do_write); + + kunmap_atomic(buf); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } else { + buf = page_address(page); + ap->ops->sff_data_xfer(qc->dev, buf + offset, qc->sect_size, +@@ -864,7 +864,7 @@ static int __atapi_pio_bytes(struct ata_ + unsigned long flags; + + /* FIXME: use bounce buffer */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + buf = kmap_atomic(page); + + /* do the actual data transfer */ +@@ -872,7 +872,7 @@ static int __atapi_pio_bytes(struct ata_ + count, rw); + + kunmap_atomic(buf); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } else { + buf = page_address(page); + consumed = ap->ops->sff_data_xfer(dev, buf + offset, diff --git a/debian/patches/features/all/rt/blk-mq-revert-raw-locks-post-pone-notifier-to-POST_D.patchto-POST_D.patch b/debian/patches/features/all/rt/blk-mq-revert-raw-locks-post-pone-notifier-to-POST_D.patchto-POST_D.patch new file mode 100644 index 000000000..0fd88f008 --- /dev/null +++ b/debian/patches/features/all/rt/blk-mq-revert-raw-locks-post-pone-notifier-to-POST_D.patchto-POST_D.patch @@ -0,0 +1,84 @@ +From: Sebastian Andrzej Siewior +Date: Sat, 3 May 2014 11:00:29 +0200 +Subject: blk-mq: revert raw locks, post pone notifier to POST_DEAD +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The blk_mq_cpu_notify_lock should be raw because some CPU down levels +are called with interrupts off. The notifier itself calls currently one +function that is blk_mq_hctx_notify(). +That function acquires the ctx->lock lock which is sleeping and I would +prefer to keep it that way. That function only moves IO-requests from +the CPU that is going offline to another CPU and it is currently the +only one. Therefore I revert the list lock back to sleeping spinlocks +and let the notifier run at POST_DEAD time. + +Signed-off-by: Sebastian Andrzej Siewior +--- + block/blk-mq-cpu.c | 17 ++++++++++------- + block/blk-mq.c | 2 +- + 2 files changed, 11 insertions(+), 8 deletions(-) + +--- a/block/blk-mq-cpu.c ++++ b/block/blk-mq-cpu.c +@@ -16,7 +16,7 @@ + #include "blk-mq.h" + + static LIST_HEAD(blk_mq_cpu_notify_list); +-static DEFINE_RAW_SPINLOCK(blk_mq_cpu_notify_lock); ++static DEFINE_SPINLOCK(blk_mq_cpu_notify_lock); + + static int blk_mq_main_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +@@ -25,7 +25,10 @@ static int blk_mq_main_cpu_notify(struct + struct blk_mq_cpu_notifier *notify; + int ret = NOTIFY_OK; + +- raw_spin_lock(&blk_mq_cpu_notify_lock); ++ if (action != CPU_POST_DEAD) ++ return NOTIFY_OK; ++ ++ spin_lock(&blk_mq_cpu_notify_lock); + + list_for_each_entry(notify, &blk_mq_cpu_notify_list, list) { + ret = notify->notify(notify->data, action, cpu); +@@ -33,7 +36,7 @@ static int blk_mq_main_cpu_notify(struct + break; + } + +- raw_spin_unlock(&blk_mq_cpu_notify_lock); ++ spin_unlock(&blk_mq_cpu_notify_lock); + return ret; + } + +@@ -41,16 +44,16 @@ void blk_mq_register_cpu_notifier(struct + { + BUG_ON(!notifier->notify); + +- raw_spin_lock(&blk_mq_cpu_notify_lock); ++ spin_lock(&blk_mq_cpu_notify_lock); + list_add_tail(¬ifier->list, &blk_mq_cpu_notify_list); +- raw_spin_unlock(&blk_mq_cpu_notify_lock); ++ spin_unlock(&blk_mq_cpu_notify_lock); + } + + void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier) + { +- raw_spin_lock(&blk_mq_cpu_notify_lock); ++ spin_lock(&blk_mq_cpu_notify_lock); + list_del(¬ifier->list); +- raw_spin_unlock(&blk_mq_cpu_notify_lock); ++ spin_unlock(&blk_mq_cpu_notify_lock); + } + + void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier, +--- a/block/blk-mq.c ++++ b/block/blk-mq.c +@@ -1612,7 +1612,7 @@ static int blk_mq_hctx_notify(void *data + { + struct blk_mq_hw_ctx *hctx = data; + +- if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) ++ if (action == CPU_POST_DEAD) + return blk_mq_hctx_cpu_offline(hctx, cpu); + + /* diff --git a/debian/patches/features/all/rt/block-blk-mq-use-swait.patch b/debian/patches/features/all/rt/block-blk-mq-use-swait.patch new file mode 100644 index 000000000..878d8ec69 --- /dev/null +++ b/debian/patches/features/all/rt/block-blk-mq-use-swait.patch @@ -0,0 +1,115 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 13 Feb 2015 11:01:26 +0100 +Subject: block: blk-mq: Use swait +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +| BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:914 +| in_atomic(): 1, irqs_disabled(): 0, pid: 255, name: kworker/u257:6 +| 5 locks held by kworker/u257:6/255: +| #0: ("events_unbound"){.+.+.+}, at: [] process_one_work+0x171/0x5e0 +| #1: ((&entry->work)){+.+.+.}, at: [] process_one_work+0x171/0x5e0 +| #2: (&shost->scan_mutex){+.+.+.}, at: [] __scsi_add_device+0xa3/0x130 [scsi_mod] +| #3: (&set->tag_list_lock){+.+...}, at: [] blk_mq_init_queue+0x96a/0xa50 +| #4: (rcu_read_lock_sched){......}, at: [] percpu_ref_kill_and_confirm+0x1d/0x120 +| Preemption disabled at:[] blk_mq_freeze_queue_start+0x56/0x70 +| +| CPU: 2 PID: 255 Comm: kworker/u257:6 Not tainted 3.18.7-rt0+ #1 +| Workqueue: events_unbound async_run_entry_fn +| 0000000000000003 ffff8800bc29f998 ffffffff815b3a12 0000000000000000 +| 0000000000000000 ffff8800bc29f9b8 ffffffff8109aa16 ffff8800bc29fa28 +| ffff8800bc5d1bc8 ffff8800bc29f9e8 ffffffff815b8dd4 ffff880000000000 +| Call Trace: +| [] dump_stack+0x4f/0x7c +| [] __might_sleep+0x116/0x190 +| [] rt_spin_lock+0x24/0x60 +| [] __wake_up+0x29/0x60 +| [] blk_mq_usage_counter_release+0x1e/0x20 +| [] percpu_ref_kill_and_confirm+0x106/0x120 +| [] blk_mq_freeze_queue_start+0x56/0x70 +| [] blk_mq_update_tag_set_depth+0x40/0xd0 +| [] blk_mq_init_queue+0x98c/0xa50 +| [] scsi_mq_alloc_queue+0x20/0x60 [scsi_mod] +| [] scsi_alloc_sdev+0x2f5/0x370 [scsi_mod] +| [] scsi_probe_and_add_lun+0x9e4/0xdd0 [scsi_mod] +| [] __scsi_add_device+0x126/0x130 [scsi_mod] +| [] ata_scsi_scan_host+0xaf/0x200 [libata] +| [] async_port_probe+0x46/0x60 [libata] +| [] async_run_entry_fn+0x3b/0xf0 +| [] process_one_work+0x201/0x5e0 + +Signed-off-by: Sebastian Andrzej Siewior +--- + block/blk-core.c | 2 +- + block/blk-mq.c | 10 +++++----- + include/linux/blkdev.h | 2 +- + 3 files changed, 7 insertions(+), 7 deletions(-) + +--- a/block/blk-core.c ++++ b/block/blk-core.c +@@ -664,7 +664,7 @@ struct request_queue *blk_alloc_queue_no + q->bypass_depth = 1; + __set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags); + +- init_waitqueue_head(&q->mq_freeze_wq); ++ init_swait_head(&q->mq_freeze_wq); + + if (blkcg_init_queue(q)) + goto fail_bdi; +--- a/block/blk-mq.c ++++ b/block/blk-mq.c +@@ -88,7 +88,7 @@ static int blk_mq_queue_enter(struct req + if (!(gfp & __GFP_WAIT)) + return -EBUSY; + +- ret = wait_event_interruptible(q->mq_freeze_wq, ++ ret = swait_event_interruptible(q->mq_freeze_wq, + !q->mq_freeze_depth || blk_queue_dying(q)); + if (blk_queue_dying(q)) + return -ENODEV; +@@ -107,7 +107,7 @@ static void blk_mq_usage_counter_release + struct request_queue *q = + container_of(ref, struct request_queue, mq_usage_counter); + +- wake_up_all(&q->mq_freeze_wq); ++ swait_wake_all(&q->mq_freeze_wq); + } + + void blk_mq_freeze_queue_start(struct request_queue *q) +@@ -127,7 +127,7 @@ EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_st + + static void blk_mq_freeze_queue_wait(struct request_queue *q) + { +- wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->mq_usage_counter)); ++ swait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->mq_usage_counter)); + } + + /* +@@ -151,7 +151,7 @@ void blk_mq_unfreeze_queue(struct reques + spin_unlock_irq(q->queue_lock); + if (wake) { + percpu_ref_reinit(&q->mq_usage_counter); +- wake_up_all(&q->mq_freeze_wq); ++ swait_wake_all(&q->mq_freeze_wq); + } + } + EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue); +@@ -170,7 +170,7 @@ void blk_mq_wake_waiters(struct request_ + * dying, we need to ensure that processes currently waiting on + * the queue are notified as well. + */ +- wake_up_all(&q->mq_freeze_wq); ++ swait_wake_all(&q->mq_freeze_wq); + } + + bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx) +--- a/include/linux/blkdev.h ++++ b/include/linux/blkdev.h +@@ -483,7 +483,7 @@ struct request_queue { + struct throtl_data *td; + #endif + struct rcu_head rcu_head; +- wait_queue_head_t mq_freeze_wq; ++ struct swait_head mq_freeze_wq; + struct percpu_ref mq_usage_counter; + struct list_head all_q_node; + diff --git a/debian/patches/features/all/rt/block-mq-don-t-complete-requests-via-IPI.patch b/debian/patches/features/all/rt/block-mq-don-t-complete-requests-via-IPI.patch new file mode 100644 index 000000000..42dbf6104 --- /dev/null +++ b/debian/patches/features/all/rt/block-mq-don-t-complete-requests-via-IPI.patch @@ -0,0 +1,102 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 29 Jan 2015 15:10:08 +0100 +Subject: block/mq: don't complete requests via IPI +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The IPI runs in hardirq context and there are sleeping locks. This patch +moves the completion into a workqueue. + +Signed-off-by: Sebastian Andrzej Siewior +--- + block/blk-core.c | 3 +++ + block/blk-mq.c | 20 ++++++++++++++++++++ + include/linux/blk-mq.h | 1 + + include/linux/blkdev.h | 1 + + 4 files changed, 25 insertions(+) + +--- a/block/blk-core.c ++++ b/block/blk-core.c +@@ -100,6 +100,9 @@ void blk_rq_init(struct request_queue *q + + INIT_LIST_HEAD(&rq->queuelist); + INIT_LIST_HEAD(&rq->timeout_list); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work); ++#endif + rq->cpu = -1; + rq->q = q; + rq->__sector = (sector_t) -1; +--- a/block/blk-mq.c ++++ b/block/blk-mq.c +@@ -217,6 +217,9 @@ static void blk_mq_rq_ctx_init(struct re + rq->resid_len = 0; + rq->sense = NULL; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work); ++#endif + INIT_LIST_HEAD(&rq->timeout_list); + rq->timeout = 0; + +@@ -346,6 +349,17 @@ void blk_mq_end_request(struct request * + } + EXPORT_SYMBOL(blk_mq_end_request); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++void __blk_mq_complete_request_remote_work(struct work_struct *work) ++{ ++ struct request *rq = container_of(work, struct request, work); ++ ++ rq->q->softirq_done_fn(rq); ++} ++ ++#else ++ + static void __blk_mq_complete_request_remote(void *data) + { + struct request *rq = data; +@@ -353,6 +367,8 @@ static void __blk_mq_complete_request_re + rq->q->softirq_done_fn(rq); + } + ++#endif ++ + static void blk_mq_ipi_complete_request(struct request *rq) + { + struct blk_mq_ctx *ctx = rq->mq_ctx; +@@ -369,10 +385,14 @@ static void blk_mq_ipi_complete_request( + shared = cpus_share_cache(cpu, ctx->cpu); + + if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ schedule_work_on(ctx->cpu, &rq->work); ++#else + rq->csd.func = __blk_mq_complete_request_remote; + rq->csd.info = rq; + rq->csd.flags = 0; + smp_call_function_single_async(ctx->cpu, &rq->csd); ++#endif + } else { + rq->q->softirq_done_fn(rq); + } +--- a/include/linux/blk-mq.h ++++ b/include/linux/blk-mq.h +@@ -202,6 +202,7 @@ static inline u16 blk_mq_unique_tag_to_t + + struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index); + struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_tag_set *, unsigned int, int); ++void __blk_mq_complete_request_remote_work(struct work_struct *work); + + int blk_mq_request_started(struct request *rq); + void blk_mq_start_request(struct request *rq); +--- a/include/linux/blkdev.h ++++ b/include/linux/blkdev.h +@@ -101,6 +101,7 @@ struct request { + struct list_head queuelist; + union { + struct call_single_data csd; ++ struct work_struct work; + unsigned long fifo_time; + }; + diff --git a/debian/patches/features/all/rt/block-mq-drop-per-ctx-cpu_lock.patch b/debian/patches/features/all/rt/block-mq-drop-per-ctx-cpu_lock.patch new file mode 100644 index 000000000..405329158 --- /dev/null +++ b/debian/patches/features/all/rt/block-mq-drop-per-ctx-cpu_lock.patch @@ -0,0 +1,125 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 18 Feb 2015 18:37:26 +0100 +Subject: block/mq: drop per ctx cpu_lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +While converting the get_cpu() to get_cpu_light() I added a cpu lock to +ensure the same code is not invoked twice on the same CPU. And now I run +into this: + +| kernel BUG at kernel/locking/rtmutex.c:996! +| invalid opcode: 0000 [#1] PREEMPT SMP +| CPU0: 13 PID: 75 Comm: kworker/u258:0 Tainted: G I 3.18.7-rt1.5+ #12 +| Workqueue: writeback bdi_writeback_workfn (flush-8:0) +| task: ffff88023742a620 ti: ffff88023743c000 task.ti: ffff88023743c000 +| RIP: 0010:[] [] rt_spin_lock_slowlock+0x280/0x2d0 +| Call Trace: +| [] rt_spin_lock+0x27/0x60 +taking the same lock again +| +| [] blk_mq_insert_requests+0x51/0x130 +| [] blk_mq_flush_plug_list+0x129/0x140 +| [] blk_flush_plug_list+0xd1/0x250 +| [] schedule+0x75/0xa0 +| [] do_nanosleep+0xdd/0x180 +| [] __hrtimer_nanosleep+0xd2/0x1c0 +| [] cpu_chill+0x56/0x80 +| [] try_to_grab_pending+0x1bd/0x390 +| [] cancel_delayed_work+0x21/0x170 +| [] blk_mq_stop_hw_queue+0x18/0x40 +| [] scsi_queue_rq+0x7f/0x830 [scsi_mod] +| [] __blk_mq_run_hw_queue+0x1ee/0x360 +| [] blk_mq_map_request+0x108/0x190 +take the lock ^^^ +| +| [] blk_sq_make_request+0x82/0x350 +| [] generic_make_request+0xd0/0x120 +| [] submit_bio+0x78/0x190 +| [] _submit_bh+0x117/0x180 +| [] __block_write_full_page.constprop.38+0x138/0x3f0 +| [] block_write_full_page+0xa0/0xe0 +| [] blkdev_writepage+0x13/0x20 +| [] __writepage+0x15/0x40 +| [] write_cache_pages+0x1fb/0x440 +| [] generic_writepages+0x3e/0x60 +| [] do_writepages+0x1c/0x30 +| [] __writeback_single_inode+0x33/0x140 +| [] writeback_sb_inodes+0x2bd/0x490 +| [] __writeback_inodes_wb+0x97/0xd0 +| [] wb_writeback+0x1cb/0x210 +| [] bdi_writeback_workfn+0x25b/0x380 +| [] process_one_work+0x1bb/0x490 +| [] worker_thread+0x6b/0x4f0 +| [] kthread+0xe3/0x100 +| [] ret_from_fork+0x7c/0xb0 + +After looking at this for a while it seems that it is save if blk_mq_ctx is +used multiple times, the in struct lock protects the access. + +Signed-off-by: Sebastian Andrzej Siewior +--- + block/blk-mq.c | 4 ---- + block/blk-mq.h | 8 -------- + 2 files changed, 12 deletions(-) + +--- a/block/blk-mq.c ++++ b/block/blk-mq.c +@@ -1386,9 +1386,7 @@ static void blk_sq_make_request(struct r + if (list_empty(&plug->mq_list)) + trace_block_plug(q); + else if (request_count >= BLK_MAX_REQUEST_COUNT) { +- spin_unlock(&data.ctx->cpu_lock); + blk_flush_plug_list(plug, false); +- spin_lock(&data.ctx->cpu_lock); + trace_block_plug(q); + } + list_add_tail(&rq->queuelist, &plug->mq_list); +@@ -1581,7 +1579,6 @@ static int blk_mq_hctx_cpu_offline(struc + blk_mq_hctx_clear_pending(hctx, ctx); + } + spin_unlock(&ctx->lock); +- __blk_mq_put_ctx(ctx); + + if (list_empty(&tmp)) + return NOTIFY_OK; +@@ -1775,7 +1772,6 @@ static void blk_mq_init_cpu_queues(struc + memset(__ctx, 0, sizeof(*__ctx)); + __ctx->cpu = i; + spin_lock_init(&__ctx->lock); +- spin_lock_init(&__ctx->cpu_lock); + INIT_LIST_HEAD(&__ctx->rq_list); + __ctx->queue = q; + +--- a/block/blk-mq.h ++++ b/block/blk-mq.h +@@ -9,7 +9,6 @@ struct blk_mq_ctx { + struct list_head rq_list; + } ____cacheline_aligned_in_smp; + +- spinlock_t cpu_lock; + unsigned int cpu; + unsigned int index_hw; + +@@ -80,7 +79,6 @@ static inline struct blk_mq_ctx *__blk_m + struct blk_mq_ctx *ctx; + + ctx = per_cpu_ptr(q->queue_ctx, cpu); +- spin_lock(&ctx->cpu_lock); + return ctx; + } + +@@ -95,14 +93,8 @@ static inline struct blk_mq_ctx *blk_mq_ + return __blk_mq_get_ctx(q, get_cpu_light()); + } + +-static void __blk_mq_put_ctx(struct blk_mq_ctx *ctx) +-{ +- spin_unlock(&ctx->cpu_lock); +-} +- + static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx) + { +- __blk_mq_put_ctx(ctx); + put_cpu_light(); + } + diff --git a/debian/patches/features/all/rt/block-mq-drop-preempt-disable.patch b/debian/patches/features/all/rt/block-mq-drop-preempt-disable.patch new file mode 100644 index 000000000..6d3612f6f --- /dev/null +++ b/debian/patches/features/all/rt/block-mq-drop-preempt-disable.patch @@ -0,0 +1,52 @@ +From: Sebastian Andrzej Siewior +Date: Tue, 14 Jul 2015 14:26:34 +0200 +Subject: block/mq: do not invoke preempt_disable() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +preempt_disable() and get_cpu() don't play well together with the sleeping +locks it tries to allocate later. +It seems to be enough to replace it with get_cpu_light() and migrate_disable(). + +Signed-off-by: Sebastian Andrzej Siewior +--- + block/blk-mq.c | 10 +++++----- + 1 file changed, 5 insertions(+), 5 deletions(-) + +--- a/block/blk-mq.c ++++ b/block/blk-mq.c +@@ -364,7 +364,7 @@ static void blk_mq_ipi_complete_request( + return; + } + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + if (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags)) + shared = cpus_share_cache(cpu, ctx->cpu); + +@@ -376,7 +376,7 @@ static void blk_mq_ipi_complete_request( + } else { + rq->q->softirq_done_fn(rq); + } +- put_cpu(); ++ put_cpu_light(); + } + + void __blk_mq_complete_request(struct request *rq) +@@ -905,14 +905,14 @@ void blk_mq_run_hw_queue(struct blk_mq_h + return; + + if (!async) { +- int cpu = get_cpu(); ++ int cpu = get_cpu_light(); + if (cpumask_test_cpu(cpu, hctx->cpumask)) { + __blk_mq_run_hw_queue(hctx); +- put_cpu(); ++ put_cpu_light(); + return; + } + +- put_cpu(); ++ put_cpu_light(); + } + + kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx), diff --git a/debian/patches/features/all/rt/block-mq-use-cpu_light.patch b/debian/patches/features/all/rt/block-mq-use-cpu_light.patch new file mode 100644 index 000000000..dc34d58d1 --- /dev/null +++ b/debian/patches/features/all/rt/block-mq-use-cpu_light.patch @@ -0,0 +1,90 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 9 Apr 2014 10:37:23 +0200 +Subject: block: mq: use cpu_light() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +there is a might sleep splat because get_cpu() disables preemption and +later we grab a lock. As a workaround for this we use get_cpu_light() +and an additional lock to prevent taking the same ctx. + +There is a lock member in the ctx already but there some functions which do ++ +on the member and this works with irq off but on RT we would need the extra lock. + +Signed-off-by: Sebastian Andrzej Siewior +--- + block/blk-mq.c | 4 ++++ + block/blk-mq.h | 17 ++++++++++++++--- + 2 files changed, 18 insertions(+), 3 deletions(-) + +--- a/block/blk-mq.c ++++ b/block/blk-mq.c +@@ -1366,7 +1366,9 @@ static void blk_sq_make_request(struct r + if (list_empty(&plug->mq_list)) + trace_block_plug(q); + else if (request_count >= BLK_MAX_REQUEST_COUNT) { ++ spin_unlock(&data.ctx->cpu_lock); + blk_flush_plug_list(plug, false); ++ spin_lock(&data.ctx->cpu_lock); + trace_block_plug(q); + } + list_add_tail(&rq->queuelist, &plug->mq_list); +@@ -1559,6 +1561,7 @@ static int blk_mq_hctx_cpu_offline(struc + blk_mq_hctx_clear_pending(hctx, ctx); + } + spin_unlock(&ctx->lock); ++ __blk_mq_put_ctx(ctx); + + if (list_empty(&tmp)) + return NOTIFY_OK; +@@ -1752,6 +1755,7 @@ static void blk_mq_init_cpu_queues(struc + memset(__ctx, 0, sizeof(*__ctx)); + __ctx->cpu = i; + spin_lock_init(&__ctx->lock); ++ spin_lock_init(&__ctx->cpu_lock); + INIT_LIST_HEAD(&__ctx->rq_list); + __ctx->queue = q; + +--- a/block/blk-mq.h ++++ b/block/blk-mq.h +@@ -9,6 +9,7 @@ struct blk_mq_ctx { + struct list_head rq_list; + } ____cacheline_aligned_in_smp; + ++ spinlock_t cpu_lock; + unsigned int cpu; + unsigned int index_hw; + +@@ -76,7 +77,11 @@ struct blk_align_bitmap { + static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q, + unsigned int cpu) + { +- return per_cpu_ptr(q->queue_ctx, cpu); ++ struct blk_mq_ctx *ctx; ++ ++ ctx = per_cpu_ptr(q->queue_ctx, cpu); ++ spin_lock(&ctx->cpu_lock); ++ return ctx; + } + + /* +@@ -87,12 +92,18 @@ static inline struct blk_mq_ctx *__blk_m + */ + static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q) + { +- return __blk_mq_get_ctx(q, get_cpu()); ++ return __blk_mq_get_ctx(q, get_cpu_light()); ++} ++ ++static void __blk_mq_put_ctx(struct blk_mq_ctx *ctx) ++{ ++ spin_unlock(&ctx->cpu_lock); + } + + static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx) + { +- put_cpu(); ++ __blk_mq_put_ctx(ctx); ++ put_cpu_light(); + } + + struct blk_mq_alloc_data { diff --git a/debian/patches/features/all/rt/block-shorten-interrupt-disabled-regions.patch b/debian/patches/features/all/rt/block-shorten-interrupt-disabled-regions.patch new file mode 100644 index 000000000..90b6f26c4 --- /dev/null +++ b/debian/patches/features/all/rt/block-shorten-interrupt-disabled-regions.patch @@ -0,0 +1,97 @@ +Subject: block: Shorten interrupt disabled regions +From: Thomas Gleixner +Date: Wed, 22 Jun 2011 19:47:02 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Moving the blk_sched_flush_plug() call out of the interrupt/preempt +disabled region in the scheduler allows us to replace +local_irq_save/restore(flags) by local_irq_disable/enable() in +blk_flush_plug(). + +Now instead of doing this we disable interrupts explicitely when we +lock the request_queue and reenable them when we drop the lock. That +allows interrupts to be handled when the plug list contains requests +for more than one queue. + +Aside of that this change makes the scope of the irq disabled region +more obvious. The current code confused the hell out of me when +looking at: + + local_irq_save(flags); + spin_lock(q->queue_lock); + ... + queue_unplugged(q...); + scsi_request_fn(); + spin_unlock(q->queue_lock); + spin_lock(shost->host_lock); + spin_unlock_irq(shost->host_lock); + +-------------------^^^ ???? + + spin_lock_irq(q->queue_lock); + spin_unlock(q->lock); + local_irq_restore(flags); + +Also add a comment to __blk_run_queue() documenting that +q->request_fn() can drop q->queue_lock and reenable interrupts, but +must return with q->queue_lock held and interrupts disabled. + +Signed-off-by: Thomas Gleixner +Cc: Peter Zijlstra +Cc: Tejun Heo +Cc: Jens Axboe +Cc: Linus Torvalds +Link: http://lkml.kernel.org/r/20110622174919.025446432@linutronix.de +--- + block/blk-core.c | 12 ++---------- + 1 file changed, 2 insertions(+), 10 deletions(-) + +--- a/block/blk-core.c ++++ b/block/blk-core.c +@@ -3077,7 +3077,7 @@ static void queue_unplugged(struct reque + blk_run_queue_async(q); + else + __blk_run_queue(q); +- spin_unlock(q->queue_lock); ++ spin_unlock_irq(q->queue_lock); + } + + static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule) +@@ -3125,7 +3125,6 @@ EXPORT_SYMBOL(blk_check_plugged); + void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) + { + struct request_queue *q; +- unsigned long flags; + struct request *rq; + LIST_HEAD(list); + unsigned int depth; +@@ -3145,11 +3144,6 @@ void blk_flush_plug_list(struct blk_plug + q = NULL; + depth = 0; + +- /* +- * Save and disable interrupts here, to avoid doing it for every +- * queue lock we have to take. +- */ +- local_irq_save(flags); + while (!list_empty(&list)) { + rq = list_entry_rq(list.next); + list_del_init(&rq->queuelist); +@@ -3162,7 +3156,7 @@ void blk_flush_plug_list(struct blk_plug + queue_unplugged(q, depth, from_schedule); + q = rq->q; + depth = 0; +- spin_lock(q->queue_lock); ++ spin_lock_irq(q->queue_lock); + } + + /* +@@ -3189,8 +3183,6 @@ void blk_flush_plug_list(struct blk_plug + */ + if (q) + queue_unplugged(q, depth, from_schedule); +- +- local_irq_restore(flags); + } + + void blk_finish_plug(struct blk_plug *plug) diff --git a/debian/patches/features/all/rt/block-use-cpu-chill.patch b/debian/patches/features/all/rt/block-use-cpu-chill.patch new file mode 100644 index 000000000..c648116f5 --- /dev/null +++ b/debian/patches/features/all/rt/block-use-cpu-chill.patch @@ -0,0 +1,46 @@ +Subject: block: Use cpu_chill() for retry loops +From: Thomas Gleixner +Date: Thu, 20 Dec 2012 18:28:26 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Retry loops on RT might loop forever when the modifying side was +preempted. Steven also observed a live lock when there was a +concurrent priority boosting going on. + +Use cpu_chill() instead of cpu_relax() to let the system +make progress. + +Signed-off-by: Thomas Gleixner + +--- + block/blk-ioc.c | 5 +++-- + 1 file changed, 3 insertions(+), 2 deletions(-) + +--- a/block/blk-ioc.c ++++ b/block/blk-ioc.c +@@ -7,6 +7,7 @@ + #include + #include + #include ++#include + + #include "blk.h" + +@@ -109,7 +110,7 @@ static void ioc_release_fn(struct work_s + spin_unlock(q->queue_lock); + } else { + spin_unlock_irqrestore(&ioc->lock, flags); +- cpu_relax(); ++ cpu_chill(); + spin_lock_irqsave_nested(&ioc->lock, flags, 1); + } + } +@@ -187,7 +188,7 @@ void put_io_context_active(struct io_con + spin_unlock(icq->q->queue_lock); + } else { + spin_unlock_irqrestore(&ioc->lock, flags); +- cpu_relax(); ++ cpu_chill(); + goto retry; + } + } diff --git a/debian/patches/features/all/rt/bug-rt-dependend-variants.patch b/debian/patches/features/all/rt/bug-rt-dependend-variants.patch new file mode 100644 index 000000000..d54502867 --- /dev/null +++ b/debian/patches/features/all/rt/bug-rt-dependend-variants.patch @@ -0,0 +1,37 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:29:58 -0500 +Subject: bug: BUG_ON/WARN_ON variants dependend on RT/!RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Introduce RT/NON-RT WARN/BUG statements to avoid ifdefs in the code. + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + include/asm-generic/bug.h | 14 ++++++++++++++ + 1 file changed, 14 insertions(+) + +--- a/include/asm-generic/bug.h ++++ b/include/asm-generic/bug.h +@@ -206,6 +206,20 @@ extern void warn_slowpath_null(const cha + # define WARN_ON_SMP(x) ({0;}) + #endif + ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define BUG_ON_RT(c) BUG_ON(c) ++# define BUG_ON_NONRT(c) do { } while (0) ++# define WARN_ON_RT(condition) WARN_ON(condition) ++# define WARN_ON_NONRT(condition) do { } while (0) ++# define WARN_ON_ONCE_NONRT(condition) do { } while (0) ++#else ++# define BUG_ON_RT(c) do { } while (0) ++# define BUG_ON_NONRT(c) BUG_ON(c) ++# define WARN_ON_RT(condition) do { } while (0) ++# define WARN_ON_NONRT(condition) WARN_ON(condition) ++# define WARN_ON_ONCE_NONRT(condition) WARN_ON_ONCE(condition) ++#endif ++ + #endif /* __ASSEMBLY__ */ + + #endif diff --git a/debian/patches/features/all/rt/cgroups-scheduling-while-atomic-in-cgroup-code.patch b/debian/patches/features/all/rt/cgroups-scheduling-while-atomic-in-cgroup-code.patch new file mode 100644 index 000000000..48f9a928d --- /dev/null +++ b/debian/patches/features/all/rt/cgroups-scheduling-while-atomic-in-cgroup-code.patch @@ -0,0 +1,65 @@ +From: Mike Galbraith +Date: Sat, 21 Jun 2014 10:09:48 +0200 +Subject: memcontrol: Prevent scheduling while atomic in cgroup code +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +mm, memcg: make refill_stock() use get_cpu_light() + +Nikita reported the following memcg scheduling while atomic bug: + +Call Trace: +[e22d5a90] [c0007ea8] show_stack+0x4c/0x168 (unreliable) +[e22d5ad0] [c0618c04] __schedule_bug+0x94/0xb0 +[e22d5ae0] [c060b9ec] __schedule+0x530/0x550 +[e22d5bf0] [c060bacc] schedule+0x30/0xbc +[e22d5c00] [c060ca24] rt_spin_lock_slowlock+0x180/0x27c +[e22d5c70] [c00b39dc] res_counter_uncharge_until+0x40/0xc4 +[e22d5ca0] [c013ca88] drain_stock.isra.20+0x54/0x98 +[e22d5cc0] [c01402ac] __mem_cgroup_try_charge+0x2e8/0xbac +[e22d5d70] [c01410d4] mem_cgroup_charge_common+0x3c/0x70 +[e22d5d90] [c0117284] __do_fault+0x38c/0x510 +[e22d5df0] [c011a5f4] handle_pte_fault+0x98/0x858 +[e22d5e50] [c060ed08] do_page_fault+0x42c/0x6fc +[e22d5f40] [c000f5b4] handle_page_fault+0xc/0x80 + +What happens: + + refill_stock() + get_cpu_var() + drain_stock() + res_counter_uncharge() + res_counter_uncharge_until() + spin_lock() <== boom + +Fix it by replacing get/put_cpu_var() with get/put_cpu_light(). + + +Reported-by: Nikita Yushchenko +Signed-off-by: Mike Galbraith +Signed-off-by: Sebastian Andrzej Siewior +--- + mm/memcontrol.c | 7 +++++-- + 1 file changed, 5 insertions(+), 2 deletions(-) + +--- a/mm/memcontrol.c ++++ b/mm/memcontrol.c +@@ -2127,14 +2127,17 @@ static void drain_local_stock(struct wor + */ + static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages) + { +- struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock); ++ struct memcg_stock_pcp *stock; ++ int cpu = get_cpu_light(); ++ ++ stock = &per_cpu(memcg_stock, cpu); + + if (stock->cached != memcg) { /* reset if necessary */ + drain_stock(stock); + stock->cached = memcg; + } + stock->nr_pages += nr_pages; +- put_cpu_var(memcg_stock); ++ put_cpu_light(); + } + + /* diff --git a/debian/patches/features/all/rt/cgroups-use-simple-wait-in-css_release.patch b/debian/patches/features/all/rt/cgroups-use-simple-wait-in-css_release.patch new file mode 100644 index 000000000..5d4e83157 --- /dev/null +++ b/debian/patches/features/all/rt/cgroups-use-simple-wait-in-css_release.patch @@ -0,0 +1,87 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 13 Feb 2015 15:52:24 +0100 +Subject: cgroups: use simple wait in css_release() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +To avoid: +|BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:914 +|in_atomic(): 1, irqs_disabled(): 0, pid: 92, name: rcuc/11 +|2 locks held by rcuc/11/92: +| #0: (rcu_callback){......}, at: [] rcu_cpu_kthread+0x3de/0x940 +| #1: (rcu_read_lock_sched){......}, at: [] percpu_ref_call_confirm_rcu+0x0/0xd0 +|Preemption disabled at:[] percpu_ref_switch_to_atomic_rcu+0x82/0xc0 +|CPU: 11 PID: 92 Comm: rcuc/11 Not tainted 3.18.7-rt0+ #1 +| ffff8802398cdf80 ffff880235f0bc28 ffffffff815b3a12 0000000000000000 +| 0000000000000000 ffff880235f0bc48 ffffffff8109aa16 0000000000000000 +| ffff8802398cdf80 ffff880235f0bc78 ffffffff815b8dd4 000000000000df80 +|Call Trace: +| [] dump_stack+0x4f/0x7c +| [] __might_sleep+0x116/0x190 +| [] rt_spin_lock+0x24/0x60 +| [] queue_work_on+0x6d/0x1d0 +| [] css_release+0x81/0x90 +| [] percpu_ref_call_confirm_rcu+0xbe/0xd0 +| [] percpu_ref_switch_to_atomic_rcu+0x82/0xc0 +| [] rcu_cpu_kthread+0x445/0x940 +| [] smpboot_thread_fn+0x18d/0x2d0 +| [] kthread+0xe8/0x100 +| [] ret_from_fork+0x7c/0xb0 + +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/cgroup.h | 2 ++ + kernel/cgroup.c | 9 +++++---- + 2 files changed, 7 insertions(+), 4 deletions(-) + +--- a/include/linux/cgroup.h ++++ b/include/linux/cgroup.h +@@ -22,6 +22,7 @@ + #include + #include + #include ++#include + + #ifdef CONFIG_CGROUPS + +@@ -91,6 +92,7 @@ struct cgroup_subsys_state { + /* percpu_ref killing and RCU release */ + struct rcu_head rcu_head; + struct work_struct destroy_work; ++ struct swork_event destroy_swork; + }; + + /* bits in struct cgroup_subsys_state flags field */ +--- a/kernel/cgroup.c ++++ b/kernel/cgroup.c +@@ -4421,10 +4421,10 @@ static void css_free_rcu_fn(struct rcu_h + queue_work(cgroup_destroy_wq, &css->destroy_work); + } + +-static void css_release_work_fn(struct work_struct *work) ++static void css_release_work_fn(struct swork_event *sev) + { + struct cgroup_subsys_state *css = +- container_of(work, struct cgroup_subsys_state, destroy_work); ++ container_of(sev, struct cgroup_subsys_state, destroy_swork); + struct cgroup_subsys *ss = css->ss; + struct cgroup *cgrp = css->cgroup; + +@@ -4463,8 +4463,8 @@ static void css_release(struct percpu_re + struct cgroup_subsys_state *css = + container_of(ref, struct cgroup_subsys_state, refcnt); + +- INIT_WORK(&css->destroy_work, css_release_work_fn); +- queue_work(cgroup_destroy_wq, &css->destroy_work); ++ INIT_SWORK(&css->destroy_swork, css_release_work_fn); ++ swork_queue(&css->destroy_swork); + } + + static void init_and_link_css(struct cgroup_subsys_state *css, +@@ -5068,6 +5068,7 @@ static int __init cgroup_wq_init(void) + */ + cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); + BUG_ON(!cgroup_destroy_wq); ++ BUG_ON(swork_get()); + + /* + * Used to destroy pidlists and separate to serve as flush domain. diff --git a/debian/patches/features/all/rt/clocksource-tclib-allow-higher-clockrates.patch b/debian/patches/features/all/rt/clocksource-tclib-allow-higher-clockrates.patch new file mode 100644 index 000000000..ec8a0c599 --- /dev/null +++ b/debian/patches/features/all/rt/clocksource-tclib-allow-higher-clockrates.patch @@ -0,0 +1,161 @@ +From: Benedikt Spranger +Date: Mon, 8 Mar 2010 18:57:04 +0100 +Subject: clocksource: TCLIB: Allow higher clock rates for clock events +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +As default the TCLIB uses the 32KiHz base clock rate for clock events. +Add a compile time selection to allow higher clock resulution. + +(fixed up by Sami Pietikäinen ) + +Signed-off-by: Benedikt Spranger +Signed-off-by: Thomas Gleixner +--- + drivers/clocksource/tcb_clksrc.c | 37 ++++++++++++++++++++++--------------- + drivers/misc/Kconfig | 12 ++++++++++-- + 2 files changed, 32 insertions(+), 17 deletions(-) + +--- a/drivers/clocksource/tcb_clksrc.c ++++ b/drivers/clocksource/tcb_clksrc.c +@@ -23,8 +23,7 @@ + * this 32 bit free-running counter. the second channel is not used. + * + * - The third channel may be used to provide a 16-bit clockevent +- * source, used in either periodic or oneshot mode. This runs +- * at 32 KiHZ, and can handle delays of up to two seconds. ++ * source, used in either periodic or oneshot mode. + * + * A boot clocksource and clockevent source are also currently needed, + * unless the relevant platforms (ARM/AT91, AVR32/AT32) are changed so +@@ -74,6 +73,7 @@ static struct clocksource clksrc = { + struct tc_clkevt_device { + struct clock_event_device clkevt; + struct clk *clk; ++ u32 freq; + void __iomem *regs; + }; + +@@ -82,13 +82,6 @@ static struct tc_clkevt_device *to_tc_cl + return container_of(clkevt, struct tc_clkevt_device, clkevt); + } + +-/* For now, we always use the 32K clock ... this optimizes for NO_HZ, +- * because using one of the divided clocks would usually mean the +- * tick rate can never be less than several dozen Hz (vs 0.5 Hz). +- * +- * A divided clock could be good for high resolution timers, since +- * 30.5 usec resolution can seem "low". +- */ + static u32 timer_clock; + + static void tc_mode(enum clock_event_mode m, struct clock_event_device *d) +@@ -111,11 +104,12 @@ static void tc_mode(enum clock_event_mod + case CLOCK_EVT_MODE_PERIODIC: + clk_enable(tcd->clk); + +- /* slow clock, count up to RC, then irq and restart */ ++ /* count up to RC, then irq and restart */ + __raw_writel(timer_clock + | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO, + regs + ATMEL_TC_REG(2, CMR)); +- __raw_writel((32768 + HZ/2) / HZ, tcaddr + ATMEL_TC_REG(2, RC)); ++ __raw_writel((tcd->freq + HZ / 2) / HZ, ++ tcaddr + ATMEL_TC_REG(2, RC)); + + /* Enable clock and interrupts on RC compare */ + __raw_writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER)); +@@ -128,7 +122,7 @@ static void tc_mode(enum clock_event_mod + case CLOCK_EVT_MODE_ONESHOT: + clk_enable(tcd->clk); + +- /* slow clock, count up to RC, then irq and stop */ ++ /* count up to RC, then irq and stop */ + __raw_writel(timer_clock | ATMEL_TC_CPCSTOP + | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO, + regs + ATMEL_TC_REG(2, CMR)); +@@ -157,8 +151,12 @@ static struct tc_clkevt_device clkevt = + .name = "tc_clkevt", + .features = CLOCK_EVT_FEAT_PERIODIC + | CLOCK_EVT_FEAT_ONESHOT, ++#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK + /* Should be lower than at91rm9200's system timer */ + .rating = 125, ++#else ++ .rating = 200, ++#endif + .set_next_event = tc_next_event, + .set_mode = tc_mode, + }, +@@ -178,8 +176,9 @@ static irqreturn_t ch2_irq(int irq, void + return IRQ_NONE; + } + +-static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx) ++static int __init setup_clkevents(struct atmel_tc *tc, int divisor_idx) + { ++ unsigned divisor = atmel_tc_divisors[divisor_idx]; + int ret; + struct clk *t2_clk = tc->clk[2]; + int irq = tc->irq[2]; +@@ -193,7 +192,11 @@ static int __init setup_clkevents(struct + clkevt.regs = tc->regs; + clkevt.clk = t2_clk; + +- timer_clock = clk32k_divisor_idx; ++ timer_clock = divisor_idx; ++ if (!divisor) ++ clkevt.freq = 32768; ++ else ++ clkevt.freq = clk_get_rate(t2_clk) / divisor; + + clkevt.clkevt.cpumask = cpumask_of(0); + +@@ -203,7 +206,7 @@ static int __init setup_clkevents(struct + return ret; + } + +- clockevents_config_and_register(&clkevt.clkevt, 32768, 1, 0xffff); ++ clockevents_config_and_register(&clkevt.clkevt, clkevt.freq, 1, 0xffff); + + return ret; + } +@@ -340,7 +343,11 @@ static int __init tcb_clksrc_init(void) + goto err_disable_t1; + + /* channel 2: periodic and oneshot timer support */ ++#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK + ret = setup_clkevents(tc, clk32k_divisor_idx); ++#else ++ ret = setup_clkevents(tc, best_divisor_idx); ++#endif + if (ret) + goto err_unregister_clksrc; + +--- a/drivers/misc/Kconfig ++++ b/drivers/misc/Kconfig +@@ -69,8 +69,7 @@ config ATMEL_TCB_CLKSRC + are combined to make a single 32-bit timer. + + When GENERIC_CLOCKEVENTS is defined, the third timer channel +- may be used as a clock event device supporting oneshot mode +- (delays of up to two seconds) based on the 32 KiHz clock. ++ may be used as a clock event device supporting oneshot mode. + + config ATMEL_TCB_CLKSRC_BLOCK + int +@@ -84,6 +83,15 @@ config ATMEL_TCB_CLKSRC_BLOCK + TC can be used for other purposes, such as PWM generation and + interval timing. + ++config ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK ++ bool "TC Block use 32 KiHz clock" ++ depends on ATMEL_TCB_CLKSRC ++ default y ++ help ++ Select this to use 32 KiHz base clock rate as TC block clock ++ source for clock events. ++ ++ + config DUMMY_IRQ + tristate "Dummy IRQ handler" + default n diff --git a/debian/patches/features/all/rt/completion-use-simple-wait-queues.patch b/debian/patches/features/all/rt/completion-use-simple-wait-queues.patch new file mode 100644 index 000000000..f9cd7260b --- /dev/null +++ b/debian/patches/features/all/rt/completion-use-simple-wait-queues.patch @@ -0,0 +1,225 @@ +Subject: completion: Use simple wait queues +From: Thomas Gleixner +Date: Fri, 11 Jan 2013 11:23:51 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Completions have no long lasting callbacks and therefor do not need +the complex waitqueue variant. Use simple waitqueues which reduces the +contention on the waitqueue lock. + +Signed-off-by: Thomas Gleixner +--- + drivers/net/wireless/orinoco/orinoco_usb.c | 2 - + drivers/usb/gadget/function/f_fs.c | 2 - + drivers/usb/gadget/legacy/inode.c | 4 +-- + include/linux/completion.h | 9 +++----- + include/linux/uprobes.h | 1 + kernel/sched/completion.c | 32 ++++++++++++++--------------- + kernel/sched/core.c | 10 +++++++-- + 7 files changed, 33 insertions(+), 27 deletions(-) + +--- a/drivers/net/wireless/orinoco/orinoco_usb.c ++++ b/drivers/net/wireless/orinoco/orinoco_usb.c +@@ -697,7 +697,7 @@ static void ezusb_req_ctx_wait(struct ez + while (!ctx->done.done && msecs--) + udelay(1000); + } else { +- wait_event_interruptible(ctx->done.wait, ++ swait_event_interruptible(ctx->done.wait, + ctx->done.done); + } + break; +--- a/drivers/usb/gadget/function/f_fs.c ++++ b/drivers/usb/gadget/function/f_fs.c +@@ -1403,7 +1403,7 @@ static void ffs_data_put(struct ffs_data + pr_info("%s(): freeing\n", __func__); + ffs_data_clear(ffs); + BUG_ON(waitqueue_active(&ffs->ev.waitq) || +- waitqueue_active(&ffs->ep0req_completion.wait)); ++ swaitqueue_active(&ffs->ep0req_completion.wait)); + kfree(ffs->dev_name); + kfree(ffs); + } +--- a/drivers/usb/gadget/legacy/inode.c ++++ b/drivers/usb/gadget/legacy/inode.c +@@ -345,7 +345,7 @@ ep_io (struct ep_data *epdata, void *buf + spin_unlock_irq (&epdata->dev->lock); + + if (likely (value == 0)) { +- value = wait_event_interruptible (done.wait, done.done); ++ value = swait_event_interruptible (done.wait, done.done); + if (value != 0) { + spin_lock_irq (&epdata->dev->lock); + if (likely (epdata->ep != NULL)) { +@@ -354,7 +354,7 @@ ep_io (struct ep_data *epdata, void *buf + usb_ep_dequeue (epdata->ep, epdata->req); + spin_unlock_irq (&epdata->dev->lock); + +- wait_event (done.wait, done.done); ++ swait_event (done.wait, done.done); + if (epdata->status == -ECONNRESET) + epdata->status = -EINTR; + } else { +--- a/include/linux/completion.h ++++ b/include/linux/completion.h +@@ -7,8 +7,7 @@ + * Atomic wait-for-completion handler data structures. + * See kernel/sched/completion.c for details. + */ +- +-#include ++#include + + /* + * struct completion - structure used to maintain state for a "completion" +@@ -24,11 +23,11 @@ + */ + struct completion { + unsigned int done; +- wait_queue_head_t wait; ++ struct swait_head wait; + }; + + #define COMPLETION_INITIALIZER(work) \ +- { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) } ++ { 0, SWAIT_HEAD_INITIALIZER((work).wait) } + + #define COMPLETION_INITIALIZER_ONSTACK(work) \ + ({ init_completion(&work); work; }) +@@ -73,7 +72,7 @@ struct completion { + static inline void init_completion(struct completion *x) + { + x->done = 0; +- init_waitqueue_head(&x->wait); ++ init_swait_head(&x->wait); + } + + /** +--- a/include/linux/uprobes.h ++++ b/include/linux/uprobes.h +@@ -27,6 +27,7 @@ + #include + #include + #include ++#include + + struct vm_area_struct; + struct mm_struct; +--- a/kernel/sched/completion.c ++++ b/kernel/sched/completion.c +@@ -30,10 +30,10 @@ void complete(struct completion *x) + { + unsigned long flags; + +- spin_lock_irqsave(&x->wait.lock, flags); ++ raw_spin_lock_irqsave(&x->wait.lock, flags); + x->done++; +- __wake_up_locked(&x->wait, TASK_NORMAL, 1); +- spin_unlock_irqrestore(&x->wait.lock, flags); ++ __swait_wake_locked(&x->wait, TASK_NORMAL, 1); ++ raw_spin_unlock_irqrestore(&x->wait.lock, flags); + } + EXPORT_SYMBOL(complete); + +@@ -50,10 +50,10 @@ void complete_all(struct completion *x) + { + unsigned long flags; + +- spin_lock_irqsave(&x->wait.lock, flags); ++ raw_spin_lock_irqsave(&x->wait.lock, flags); + x->done += UINT_MAX/2; +- __wake_up_locked(&x->wait, TASK_NORMAL, 0); +- spin_unlock_irqrestore(&x->wait.lock, flags); ++ __swait_wake_locked(&x->wait, TASK_NORMAL, 0); ++ raw_spin_unlock_irqrestore(&x->wait.lock, flags); + } + EXPORT_SYMBOL(complete_all); + +@@ -62,20 +62,20 @@ do_wait_for_common(struct completion *x, + long (*action)(long), long timeout, int state) + { + if (!x->done) { +- DECLARE_WAITQUEUE(wait, current); ++ DEFINE_SWAITER(wait); + +- __add_wait_queue_tail_exclusive(&x->wait, &wait); ++ swait_prepare_locked(&x->wait, &wait); + do { + if (signal_pending_state(state, current)) { + timeout = -ERESTARTSYS; + break; + } + __set_current_state(state); +- spin_unlock_irq(&x->wait.lock); ++ raw_spin_unlock_irq(&x->wait.lock); + timeout = action(timeout); +- spin_lock_irq(&x->wait.lock); ++ raw_spin_lock_irq(&x->wait.lock); + } while (!x->done && timeout); +- __remove_wait_queue(&x->wait, &wait); ++ swait_finish_locked(&x->wait, &wait); + if (!x->done) + return timeout; + } +@@ -89,9 +89,9 @@ static inline long __sched + { + might_sleep(); + +- spin_lock_irq(&x->wait.lock); ++ raw_spin_lock_irq(&x->wait.lock); + timeout = do_wait_for_common(x, action, timeout, state); +- spin_unlock_irq(&x->wait.lock); ++ raw_spin_unlock_irq(&x->wait.lock); + return timeout; + } + +@@ -277,12 +277,12 @@ bool try_wait_for_completion(struct comp + if (!READ_ONCE(x->done)) + return 0; + +- spin_lock_irqsave(&x->wait.lock, flags); ++ raw_spin_lock_irqsave(&x->wait.lock, flags); + if (!x->done) + ret = 0; + else + x->done--; +- spin_unlock_irqrestore(&x->wait.lock, flags); ++ raw_spin_unlock_irqrestore(&x->wait.lock, flags); + return ret; + } + EXPORT_SYMBOL(try_wait_for_completion); +@@ -311,7 +311,7 @@ bool completion_done(struct completion * + * after it's acquired the lock. + */ + smp_rmb(); +- spin_unlock_wait(&x->wait.lock); ++ raw_spin_unlock_wait(&x->wait.lock); + return true; + } + EXPORT_SYMBOL(completion_done); +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -2802,7 +2802,10 @@ void migrate_disable(void) + } + + #ifdef CONFIG_SCHED_DEBUG +- WARN_ON_ONCE(p->migrate_disable_atomic); ++ if (unlikely(p->migrate_disable_atomic)) { ++ tracing_off(); ++ WARN_ON_ONCE(1); ++ } + #endif + + if (p->migrate_disable) { +@@ -2832,7 +2835,10 @@ void migrate_enable(void) + } + + #ifdef CONFIG_SCHED_DEBUG +- WARN_ON_ONCE(p->migrate_disable_atomic); ++ if (unlikely(p->migrate_disable_atomic)) { ++ tracing_off(); ++ WARN_ON_ONCE(1); ++ } + #endif + WARN_ON_ONCE(p->migrate_disable <= 0); + diff --git a/debian/patches/features/all/rt/cond-resched-lock-rt-tweak.patch b/debian/patches/features/all/rt/cond-resched-lock-rt-tweak.patch new file mode 100644 index 000000000..bff404a7a --- /dev/null +++ b/debian/patches/features/all/rt/cond-resched-lock-rt-tweak.patch @@ -0,0 +1,24 @@ +Subject: sched: Use the proper LOCK_OFFSET for cond_resched() +From: Thomas Gleixner +Date: Sun, 17 Jul 2011 22:51:33 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +RT does not increment preempt count when a 'sleeping' spinlock is +locked. Update PREEMPT_LOCK_OFFSET for that case. + +Signed-off-by: Thomas Gleixner +--- + include/linux/sched.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -2926,7 +2926,7 @@ extern int _cond_resched(void); + + extern int __cond_resched_lock(spinlock_t *lock); + +-#ifdef CONFIG_PREEMPT_COUNT ++#if defined(CONFIG_PREEMPT_COUNT) && !defined(CONFIG_PREEMPT_RT_FULL) + #define PREEMPT_LOCK_OFFSET PREEMPT_OFFSET + #else + #define PREEMPT_LOCK_OFFSET 0 diff --git a/debian/patches/features/all/rt/cond-resched-softirq-rt.patch b/debian/patches/features/all/rt/cond-resched-softirq-rt.patch new file mode 100644 index 000000000..9d374aae4 --- /dev/null +++ b/debian/patches/features/all/rt/cond-resched-softirq-rt.patch @@ -0,0 +1,53 @@ +Subject: sched: Take RT softirq semantics into account in cond_resched() +From: Thomas Gleixner +Date: Thu, 14 Jul 2011 09:56:44 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The softirq semantics work different on -RT. There is no SOFTIRQ_MASK in +the preemption counter which leads to the BUG_ON() statement in +__cond_resched_softirq(). As for -RT it is enough to perform a "normal" +schedule. + +Signed-off-by: Thomas Gleixner +--- + include/linux/sched.h | 4 ++++ + kernel/sched/core.c | 2 ++ + 2 files changed, 6 insertions(+) + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -2937,12 +2937,16 @@ extern int __cond_resched_lock(spinlock_ + __cond_resched_lock(lock); \ + }) + ++#ifndef CONFIG_PREEMPT_RT_FULL + extern int __cond_resched_softirq(void); + + #define cond_resched_softirq() ({ \ + ___might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET); \ + __cond_resched_softirq(); \ + }) ++#else ++# define cond_resched_softirq() cond_resched() ++#endif + + static inline void cond_resched_rcu(void) + { +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -4479,6 +4479,7 @@ int __cond_resched_lock(spinlock_t *lock + } + EXPORT_SYMBOL(__cond_resched_lock); + ++#ifndef CONFIG_PREEMPT_RT_FULL + int __sched __cond_resched_softirq(void) + { + BUG_ON(!in_softirq()); +@@ -4492,6 +4493,7 @@ int __sched __cond_resched_softirq(void) + return 0; + } + EXPORT_SYMBOL(__cond_resched_softirq); ++#endif + + /** + * yield - yield the current processor to other threads. diff --git a/debian/patches/features/all/rt/cpu-hotplug-Document-why-PREEMPT_RT-uses-a-spinlock.patch b/debian/patches/features/all/rt/cpu-hotplug-Document-why-PREEMPT_RT-uses-a-spinlock.patch new file mode 100644 index 000000000..dee79d975 --- /dev/null +++ b/debian/patches/features/all/rt/cpu-hotplug-Document-why-PREEMPT_RT-uses-a-spinlock.patch @@ -0,0 +1,56 @@ +From: Steven Rostedt +Date: Thu, 5 Dec 2013 09:16:52 -0500 +Subject: cpu hotplug: Document why PREEMPT_RT uses a spinlock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The patch: + + cpu: Make hotplug.lock a "sleeping" spinlock on RT + + Tasks can block on hotplug.lock in pin_current_cpu(), but their + state might be != RUNNING. So the mutex wakeup will set the state + unconditionally to RUNNING. That might cause spurious unexpected + wakeups. We could provide a state preserving mutex_lock() function, + but this is semantically backwards. So instead we convert the + hotplug.lock() to a spinlock for RT, which has the state preserving + semantics already. + +Fixed a bug where the hotplug lock on PREEMPT_RT can be called after a +task set its state to TASK_UNINTERRUPTIBLE and before it called +schedule. If the hotplug_lock used a mutex, and there was contention, +the current task's state would be turned to TASK_RUNNABLE and the +schedule call will not sleep. This caused unexpected results. + +Although the patch had a description of the change, the code had no +comments about it. This causes confusion to those that review the code, +and as PREEMPT_RT is held in a quilt queue and not git, it's not as easy +to see why a change was made. Even if it was in git, the code should +still have a comment for something as subtle as this. + +Document the rational for using a spinlock on PREEMPT_RT in the hotplug +lock code. + +Reported-by: Nicholas Mc Guire +Signed-off-by: Steven Rostedt +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/cpu.c | 8 ++++++++ + 1 file changed, 8 insertions(+) + +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -109,6 +109,14 @@ struct hotplug_pcp { + int grab_lock; + struct completion synced; + #ifdef CONFIG_PREEMPT_RT_FULL ++ /* ++ * Note, on PREEMPT_RT, the hotplug lock must save the state of ++ * the task, otherwise the mutex will cause the task to fail ++ * to sleep when required. (Because it's called from migrate_disable()) ++ * ++ * The spinlock_t on PREEMPT_RT is a mutex that saves the task's ++ * state. ++ */ + spinlock_t lock; + #else + struct mutex mutex; diff --git a/debian/patches/features/all/rt/cpu-rt-make-hotplug-lock-a-sleeping-spinlock-on-rt.patch b/debian/patches/features/all/rt/cpu-rt-make-hotplug-lock-a-sleeping-spinlock-on-rt.patch new file mode 100644 index 000000000..9691281bb --- /dev/null +++ b/debian/patches/features/all/rt/cpu-rt-make-hotplug-lock-a-sleeping-spinlock-on-rt.patch @@ -0,0 +1,131 @@ +Subject: cpu: Make hotplug.lock a "sleeping" spinlock on RT +From: Steven Rostedt +Date: Fri, 02 Mar 2012 10:36:57 -0500 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Tasks can block on hotplug.lock in pin_current_cpu(), but their state +might be != RUNNING. So the mutex wakeup will set the state +unconditionally to RUNNING. That might cause spurious unexpected +wakeups. We could provide a state preserving mutex_lock() function, +but this is semantically backwards. So instead we convert the +hotplug.lock() to a spinlock for RT, which has the state preserving +semantics already. + +Signed-off-by: Steven Rostedt +Cc: Carsten Emde +Cc: John Kacur +Cc: Peter Zijlstra +Cc: Clark Williams + +Link: http://lkml.kernel.org/r/1330702617.25686.265.camel@gandalf.stny.rr.com +Signed-off-by: Thomas Gleixner +--- + kernel/cpu.c | 38 +++++++++++++++++++++++++++++--------- + 1 file changed, 29 insertions(+), 9 deletions(-) + +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -59,10 +59,16 @@ static int cpu_hotplug_disabled; + + static struct { + struct task_struct *active_writer; ++ + /* wait queue to wake up the active_writer */ + wait_queue_head_t wq; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* Makes the lock keep the task's state */ ++ spinlock_t lock; ++#else + /* verifies that no writer will get active while readers are active */ + struct mutex lock; ++#endif + /* + * Also blocks the new readers during + * an ongoing cpu hotplug operation. +@@ -75,12 +81,26 @@ static struct { + } cpu_hotplug = { + .active_writer = NULL, + .wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq), ++#ifdef CONFIG_PREEMPT_RT_FULL ++ .lock = __SPIN_LOCK_UNLOCKED(cpu_hotplug.lock), ++#else + .lock = __MUTEX_INITIALIZER(cpu_hotplug.lock), ++#endif + #ifdef CONFIG_DEBUG_LOCK_ALLOC + .dep_map = {.name = "cpu_hotplug.lock" }, + #endif + }; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define hotplug_lock() rt_spin_lock(&cpu_hotplug.lock) ++# define hotplug_trylock() rt_spin_trylock(&cpu_hotplug.lock) ++# define hotplug_unlock() rt_spin_unlock(&cpu_hotplug.lock) ++#else ++# define hotplug_lock() mutex_lock(&cpu_hotplug.lock) ++# define hotplug_trylock() mutex_trylock(&cpu_hotplug.lock) ++# define hotplug_unlock() mutex_unlock(&cpu_hotplug.lock) ++#endif ++ + /* Lockdep annotations for get/put_online_cpus() and cpu_hotplug_begin/end() */ + #define cpuhp_lock_acquire_read() lock_map_acquire_read(&cpu_hotplug.dep_map) + #define cpuhp_lock_acquire_tryread() \ +@@ -117,8 +137,8 @@ void pin_current_cpu(void) + return; + } + preempt_enable(); +- mutex_lock(&cpu_hotplug.lock); +- mutex_unlock(&cpu_hotplug.lock); ++ hotplug_lock(); ++ hotplug_unlock(); + preempt_disable(); + goto retry; + } +@@ -191,9 +211,9 @@ void get_online_cpus(void) + if (cpu_hotplug.active_writer == current) + return; + cpuhp_lock_acquire_read(); +- mutex_lock(&cpu_hotplug.lock); ++ hotplug_lock(); + atomic_inc(&cpu_hotplug.refcount); +- mutex_unlock(&cpu_hotplug.lock); ++ hotplug_unlock(); + } + EXPORT_SYMBOL_GPL(get_online_cpus); + +@@ -201,11 +221,11 @@ bool try_get_online_cpus(void) + { + if (cpu_hotplug.active_writer == current) + return true; +- if (!mutex_trylock(&cpu_hotplug.lock)) ++ if (!hotplug_trylock()) + return false; + cpuhp_lock_acquire_tryread(); + atomic_inc(&cpu_hotplug.refcount); +- mutex_unlock(&cpu_hotplug.lock); ++ hotplug_unlock(); + return true; + } + EXPORT_SYMBOL_GPL(try_get_online_cpus); +@@ -259,11 +279,11 @@ void cpu_hotplug_begin(void) + cpuhp_lock_acquire(); + + for (;;) { +- mutex_lock(&cpu_hotplug.lock); ++ hotplug_lock(); + prepare_to_wait(&cpu_hotplug.wq, &wait, TASK_UNINTERRUPTIBLE); + if (likely(!atomic_read(&cpu_hotplug.refcount))) + break; +- mutex_unlock(&cpu_hotplug.lock); ++ hotplug_unlock(); + schedule(); + } + finish_wait(&cpu_hotplug.wq, &wait); +@@ -272,7 +292,7 @@ void cpu_hotplug_begin(void) + void cpu_hotplug_done(void) + { + cpu_hotplug.active_writer = NULL; +- mutex_unlock(&cpu_hotplug.lock); ++ hotplug_unlock(); + cpuhp_lock_release(); + } + diff --git a/debian/patches/features/all/rt/cpu-rt-rework-cpu-down.patch b/debian/patches/features/all/rt/cpu-rt-rework-cpu-down.patch new file mode 100644 index 000000000..a7e9ae284 --- /dev/null +++ b/debian/patches/features/all/rt/cpu-rt-rework-cpu-down.patch @@ -0,0 +1,562 @@ +From: Steven Rostedt +Date: Mon, 16 Jul 2012 08:07:43 +0000 +Subject: cpu/rt: Rework cpu down for PREEMPT_RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Bringing a CPU down is a pain with the PREEMPT_RT kernel because +tasks can be preempted in many more places than in non-RT. In +order to handle per_cpu variables, tasks may be pinned to a CPU +for a while, and even sleep. But these tasks need to be off the CPU +if that CPU is going down. + +Several synchronization methods have been tried, but when stressed +they failed. This is a new approach. + +A sync_tsk thread is still created and tasks may still block on a +lock when the CPU is going down, but how that works is a bit different. +When cpu_down() starts, it will create the sync_tsk and wait on it +to inform that current tasks that are pinned on the CPU are no longer +pinned. But new tasks that are about to be pinned will still be allowed +to do so at this time. + +Then the notifiers are called. Several notifiers will bring down tasks +that will enter these locations. Some of these tasks will take locks +of other tasks that are on the CPU. If we don't let those other tasks +continue, but make them block until CPU down is done, the tasks that +the notifiers are waiting on will never complete as they are waiting +for the locks held by the tasks that are blocked. + +Thus we still let the task pin the CPU until the notifiers are done. +After the notifiers run, we then make new tasks entering the pinned +CPU sections grab a mutex and wait. This mutex is now a per CPU mutex +in the hotplug_pcp descriptor. + +To help things along, a new function in the scheduler code is created +called migrate_me(). This function will try to migrate the current task +off the CPU this is going down if possible. When the sync_tsk is created, +all tasks will then try to migrate off the CPU going down. There are +several cases that this wont work, but it helps in most cases. + +After the notifiers are called and if a task can't migrate off but enters +the pin CPU sections, it will be forced to wait on the hotplug_pcp mutex +until the CPU down is complete. Then the scheduler will force the migration +anyway. + +Also, I found that THREAD_BOUND need to also be accounted for in the +pinned CPU, and the migrate_disable no longer treats them special. +This helps fix issues with ksoftirqd and workqueue that unbind on CPU down. + +Signed-off-by: Steven Rostedt +Signed-off-by: Thomas Gleixner + +--- + include/linux/sched.h | 7 + + kernel/cpu.c | 244 ++++++++++++++++++++++++++++++++++++++++---------- + kernel/sched/core.c | 82 ++++++++++++++++ + 3 files changed, 285 insertions(+), 48 deletions(-) + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -2217,6 +2217,10 @@ extern void do_set_cpus_allowed(struct t + + extern int set_cpus_allowed_ptr(struct task_struct *p, + const struct cpumask *new_mask); ++int migrate_me(void); ++void tell_sched_cpu_down_begin(int cpu); ++void tell_sched_cpu_down_done(int cpu); ++ + #else + static inline void do_set_cpus_allowed(struct task_struct *p, + const struct cpumask *new_mask) +@@ -2229,6 +2233,9 @@ static inline int set_cpus_allowed_ptr(s + return -EINVAL; + return 0; + } ++static inline int migrate_me(void) { return 0; } ++static inline void tell_sched_cpu_down_begin(int cpu) { } ++static inline void tell_sched_cpu_down_done(int cpu) { } + #endif + + #ifdef CONFIG_NO_HZ_COMMON +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -59,16 +59,10 @@ static int cpu_hotplug_disabled; + + static struct { + struct task_struct *active_writer; +- + /* wait queue to wake up the active_writer */ + wait_queue_head_t wq; +-#ifdef CONFIG_PREEMPT_RT_FULL +- /* Makes the lock keep the task's state */ +- spinlock_t lock; +-#else + /* verifies that no writer will get active while readers are active */ + struct mutex lock; +-#endif + /* + * Also blocks the new readers during + * an ongoing cpu hotplug operation. +@@ -80,27 +74,13 @@ static struct { + #endif + } cpu_hotplug = { + .active_writer = NULL, +- .wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq), +-#ifdef CONFIG_PREEMPT_RT_FULL +- .lock = __SPIN_LOCK_UNLOCKED(cpu_hotplug.lock), +-#else + .lock = __MUTEX_INITIALIZER(cpu_hotplug.lock), +-#endif ++ .wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq), + #ifdef CONFIG_DEBUG_LOCK_ALLOC + .dep_map = {.name = "cpu_hotplug.lock" }, + #endif + }; + +-#ifdef CONFIG_PREEMPT_RT_FULL +-# define hotplug_lock() rt_spin_lock(&cpu_hotplug.lock) +-# define hotplug_trylock() rt_spin_trylock(&cpu_hotplug.lock) +-# define hotplug_unlock() rt_spin_unlock(&cpu_hotplug.lock) +-#else +-# define hotplug_lock() mutex_lock(&cpu_hotplug.lock) +-# define hotplug_trylock() mutex_trylock(&cpu_hotplug.lock) +-# define hotplug_unlock() mutex_unlock(&cpu_hotplug.lock) +-#endif +- + /* Lockdep annotations for get/put_online_cpus() and cpu_hotplug_begin/end() */ + #define cpuhp_lock_acquire_read() lock_map_acquire_read(&cpu_hotplug.dep_map) + #define cpuhp_lock_acquire_tryread() \ +@@ -108,12 +88,42 @@ static struct { + #define cpuhp_lock_acquire() lock_map_acquire(&cpu_hotplug.dep_map) + #define cpuhp_lock_release() lock_map_release(&cpu_hotplug.dep_map) + ++/** ++ * hotplug_pcp - per cpu hotplug descriptor ++ * @unplug: set when pin_current_cpu() needs to sync tasks ++ * @sync_tsk: the task that waits for tasks to finish pinned sections ++ * @refcount: counter of tasks in pinned sections ++ * @grab_lock: set when the tasks entering pinned sections should wait ++ * @synced: notifier for @sync_tsk to tell cpu_down it's finished ++ * @mutex: the mutex to make tasks wait (used when @grab_lock is true) ++ * @mutex_init: zero if the mutex hasn't been initialized yet. ++ * ++ * Although @unplug and @sync_tsk may point to the same task, the @unplug ++ * is used as a flag and still exists after @sync_tsk has exited and ++ * @sync_tsk set to NULL. ++ */ + struct hotplug_pcp { + struct task_struct *unplug; ++ struct task_struct *sync_tsk; + int refcount; ++ int grab_lock; + struct completion synced; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ spinlock_t lock; ++#else ++ struct mutex mutex; ++#endif ++ int mutex_init; + }; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define hotplug_lock(hp) rt_spin_lock(&(hp)->lock) ++# define hotplug_unlock(hp) rt_spin_unlock(&(hp)->lock) ++#else ++# define hotplug_lock(hp) mutex_lock(&(hp)->mutex) ++# define hotplug_unlock(hp) mutex_unlock(&(hp)->mutex) ++#endif ++ + static DEFINE_PER_CPU(struct hotplug_pcp, hotplug_pcp); + + /** +@@ -127,18 +137,39 @@ static DEFINE_PER_CPU(struct hotplug_pcp + void pin_current_cpu(void) + { + struct hotplug_pcp *hp; ++ int force = 0; + + retry: + hp = this_cpu_ptr(&hotplug_pcp); + +- if (!hp->unplug || hp->refcount || preempt_count() > 1 || ++ if (!hp->unplug || hp->refcount || force || preempt_count() > 1 || + hp->unplug == current) { + hp->refcount++; + return; + } +- preempt_enable(); +- hotplug_lock(); +- hotplug_unlock(); ++ if (hp->grab_lock) { ++ preempt_enable(); ++ hotplug_lock(hp); ++ hotplug_unlock(hp); ++ } else { ++ preempt_enable(); ++ /* ++ * Try to push this task off of this CPU. ++ */ ++ if (!migrate_me()) { ++ preempt_disable(); ++ hp = this_cpu_ptr(&hotplug_pcp); ++ if (!hp->grab_lock) { ++ /* ++ * Just let it continue it's already pinned ++ * or about to sleep. ++ */ ++ force = 1; ++ goto retry; ++ } ++ preempt_enable(); ++ } ++ } + preempt_disable(); + goto retry; + } +@@ -159,26 +190,84 @@ void unpin_current_cpu(void) + wake_up_process(hp->unplug); + } + +-/* +- * FIXME: Is this really correct under all circumstances ? +- */ ++static void wait_for_pinned_cpus(struct hotplug_pcp *hp) ++{ ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ while (hp->refcount) { ++ schedule_preempt_disabled(); ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ } ++} ++ + static int sync_unplug_thread(void *data) + { + struct hotplug_pcp *hp = data; + + preempt_disable(); + hp->unplug = current; ++ wait_for_pinned_cpus(hp); ++ ++ /* ++ * This thread will synchronize the cpu_down() with threads ++ * that have pinned the CPU. When the pinned CPU count reaches ++ * zero, we inform the cpu_down code to continue to the next step. ++ */ + set_current_state(TASK_UNINTERRUPTIBLE); +- while (hp->refcount) { +- schedule_preempt_disabled(); ++ preempt_enable(); ++ complete(&hp->synced); ++ ++ /* ++ * If all succeeds, the next step will need tasks to wait till ++ * the CPU is offline before continuing. To do this, the grab_lock ++ * is set and tasks going into pin_current_cpu() will block on the ++ * mutex. But we still need to wait for those that are already in ++ * pinned CPU sections. If the cpu_down() failed, the kthread_should_stop() ++ * will kick this thread out. ++ */ ++ while (!hp->grab_lock && !kthread_should_stop()) { ++ schedule(); ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ } ++ ++ /* Make sure grab_lock is seen before we see a stale completion */ ++ smp_mb(); ++ ++ /* ++ * Now just before cpu_down() enters stop machine, we need to make ++ * sure all tasks that are in pinned CPU sections are out, and new ++ * tasks will now grab the lock, keeping them from entering pinned ++ * CPU sections. ++ */ ++ if (!kthread_should_stop()) { ++ preempt_disable(); ++ wait_for_pinned_cpus(hp); ++ preempt_enable(); ++ complete(&hp->synced); ++ } ++ ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ while (!kthread_should_stop()) { ++ schedule(); + set_current_state(TASK_UNINTERRUPTIBLE); + } + set_current_state(TASK_RUNNING); +- preempt_enable(); +- complete(&hp->synced); ++ ++ /* ++ * Force this thread off this CPU as it's going down and ++ * we don't want any more work on this CPU. ++ */ ++ current->flags &= ~PF_NO_SETAFFINITY; ++ do_set_cpus_allowed(current, cpu_present_mask); ++ migrate_me(); + return 0; + } + ++static void __cpu_unplug_sync(struct hotplug_pcp *hp) ++{ ++ wake_up_process(hp->sync_tsk); ++ wait_for_completion(&hp->synced); ++} ++ + /* + * Start the sync_unplug_thread on the target cpu and wait for it to + * complete. +@@ -186,23 +275,83 @@ static int sync_unplug_thread(void *data + static int cpu_unplug_begin(unsigned int cpu) + { + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); +- struct task_struct *tsk; ++ int err; ++ ++ /* Protected by cpu_hotplug.lock */ ++ if (!hp->mutex_init) { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ spin_lock_init(&hp->lock); ++#else ++ mutex_init(&hp->mutex); ++#endif ++ hp->mutex_init = 1; ++ } ++ ++ /* Inform the scheduler to migrate tasks off this CPU */ ++ tell_sched_cpu_down_begin(cpu); + + init_completion(&hp->synced); +- tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu); +- if (IS_ERR(tsk)) +- return (PTR_ERR(tsk)); +- kthread_bind(tsk, cpu); +- wake_up_process(tsk); +- wait_for_completion(&hp->synced); ++ ++ hp->sync_tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu); ++ if (IS_ERR(hp->sync_tsk)) { ++ err = PTR_ERR(hp->sync_tsk); ++ hp->sync_tsk = NULL; ++ return err; ++ } ++ kthread_bind(hp->sync_tsk, cpu); ++ ++ /* ++ * Wait for tasks to get out of the pinned sections, ++ * it's still OK if new tasks enter. Some CPU notifiers will ++ * wait for tasks that are going to enter these sections and ++ * we must not have them block. ++ */ ++ __cpu_unplug_sync(hp); ++ + return 0; + } + ++static void cpu_unplug_sync(unsigned int cpu) ++{ ++ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); ++ ++ init_completion(&hp->synced); ++ /* The completion needs to be initialzied before setting grab_lock */ ++ smp_wmb(); ++ ++ /* Grab the mutex before setting grab_lock */ ++ hotplug_lock(hp); ++ hp->grab_lock = 1; ++ ++ /* ++ * The CPU notifiers have been completed. ++ * Wait for tasks to get out of pinned CPU sections and have new ++ * tasks block until the CPU is completely down. ++ */ ++ __cpu_unplug_sync(hp); ++ ++ /* All done with the sync thread */ ++ kthread_stop(hp->sync_tsk); ++ hp->sync_tsk = NULL; ++} ++ + static void cpu_unplug_done(unsigned int cpu) + { + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + + hp->unplug = NULL; ++ /* Let all tasks know cpu unplug is finished before cleaning up */ ++ smp_wmb(); ++ ++ if (hp->sync_tsk) ++ kthread_stop(hp->sync_tsk); ++ ++ if (hp->grab_lock) { ++ hotplug_unlock(hp); ++ /* protected by cpu_hotplug.lock */ ++ hp->grab_lock = 0; ++ } ++ tell_sched_cpu_down_done(cpu); + } + + void get_online_cpus(void) +@@ -211,9 +360,9 @@ void get_online_cpus(void) + if (cpu_hotplug.active_writer == current) + return; + cpuhp_lock_acquire_read(); +- hotplug_lock(); ++ mutex_lock(&cpu_hotplug.lock); + atomic_inc(&cpu_hotplug.refcount); +- hotplug_unlock(); ++ mutex_unlock(&cpu_hotplug.lock); + } + EXPORT_SYMBOL_GPL(get_online_cpus); + +@@ -221,11 +370,11 @@ bool try_get_online_cpus(void) + { + if (cpu_hotplug.active_writer == current) + return true; +- if (!hotplug_trylock()) ++ if (!mutex_trylock(&cpu_hotplug.lock)) + return false; + cpuhp_lock_acquire_tryread(); + atomic_inc(&cpu_hotplug.refcount); +- hotplug_unlock(); ++ mutex_unlock(&cpu_hotplug.lock); + return true; + } + EXPORT_SYMBOL_GPL(try_get_online_cpus); +@@ -279,11 +428,11 @@ void cpu_hotplug_begin(void) + cpuhp_lock_acquire(); + + for (;;) { +- hotplug_lock(); ++ mutex_lock(&cpu_hotplug.lock); + prepare_to_wait(&cpu_hotplug.wq, &wait, TASK_UNINTERRUPTIBLE); + if (likely(!atomic_read(&cpu_hotplug.refcount))) + break; +- hotplug_unlock(); ++ mutex_unlock(&cpu_hotplug.lock); + schedule(); + } + finish_wait(&cpu_hotplug.wq, &wait); +@@ -292,7 +441,7 @@ void cpu_hotplug_begin(void) + void cpu_hotplug_done(void) + { + cpu_hotplug.active_writer = NULL; +- hotplug_unlock(); ++ mutex_unlock(&cpu_hotplug.lock); + cpuhp_lock_release(); + } + +@@ -527,6 +676,9 @@ static int __ref _cpu_down(unsigned int + + smpboot_park_threads(cpu); + ++ /* Notifiers are done. Don't let any more tasks pin this CPU. */ ++ cpu_unplug_sync(cpu); ++ + /* + * So now all preempt/rcu users must observe !cpu_active(). + */ +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -2754,7 +2754,7 @@ void migrate_disable(void) + { + struct task_struct *p = current; + +- if (in_atomic() || p->flags & PF_NO_SETAFFINITY) { ++ if (in_atomic()) { + #ifdef CONFIG_SCHED_DEBUG + p->migrate_disable_atomic++; + #endif +@@ -2787,7 +2787,7 @@ void migrate_enable(void) + unsigned long flags; + struct rq *rq; + +- if (in_atomic() || p->flags & PF_NO_SETAFFINITY) { ++ if (in_atomic()) { + #ifdef CONFIG_SCHED_DEBUG + p->migrate_disable_atomic--; + #endif +@@ -4960,6 +4960,84 @@ void do_set_cpus_allowed(struct task_str + cpumask_copy(&p->cpus_allowed, new_mask); + } + ++static DEFINE_PER_CPU(struct cpumask, sched_cpumasks); ++static DEFINE_MUTEX(sched_down_mutex); ++static cpumask_t sched_down_cpumask; ++ ++void tell_sched_cpu_down_begin(int cpu) ++{ ++ mutex_lock(&sched_down_mutex); ++ cpumask_set_cpu(cpu, &sched_down_cpumask); ++ mutex_unlock(&sched_down_mutex); ++} ++ ++void tell_sched_cpu_down_done(int cpu) ++{ ++ mutex_lock(&sched_down_mutex); ++ cpumask_clear_cpu(cpu, &sched_down_cpumask); ++ mutex_unlock(&sched_down_mutex); ++} ++ ++/** ++ * migrate_me - try to move the current task off this cpu ++ * ++ * Used by the pin_current_cpu() code to try to get tasks ++ * to move off the current CPU as it is going down. ++ * It will only move the task if the task isn't pinned to ++ * the CPU (with migrate_disable, affinity or NO_SETAFFINITY) ++ * and the task has to be in a RUNNING state. Otherwise the ++ * movement of the task will wake it up (change its state ++ * to running) when the task did not expect it. ++ * ++ * Returns 1 if it succeeded in moving the current task ++ * 0 otherwise. ++ */ ++int migrate_me(void) ++{ ++ struct task_struct *p = current; ++ struct migration_arg arg; ++ struct cpumask *cpumask; ++ struct cpumask *mask; ++ unsigned long flags; ++ unsigned int dest_cpu; ++ struct rq *rq; ++ ++ /* ++ * We can not migrate tasks bounded to a CPU or tasks not ++ * running. The movement of the task will wake it up. ++ */ ++ if (p->flags & PF_NO_SETAFFINITY || p->state) ++ return 0; ++ ++ mutex_lock(&sched_down_mutex); ++ rq = task_rq_lock(p, &flags); ++ ++ cpumask = this_cpu_ptr(&sched_cpumasks); ++ mask = &p->cpus_allowed; ++ ++ cpumask_andnot(cpumask, mask, &sched_down_cpumask); ++ ++ if (!cpumask_weight(cpumask)) { ++ /* It's only on this CPU? */ ++ task_rq_unlock(rq, p, &flags); ++ mutex_unlock(&sched_down_mutex); ++ return 0; ++ } ++ ++ dest_cpu = cpumask_any_and(cpu_active_mask, cpumask); ++ ++ arg.task = p; ++ arg.dest_cpu = dest_cpu; ++ ++ task_rq_unlock(rq, p, &flags); ++ ++ stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); ++ tlb_migrate_finish(p->mm); ++ mutex_unlock(&sched_down_mutex); ++ ++ return 1; ++} ++ + /* + * This is how migration works: + * diff --git a/debian/patches/features/all/rt/cpu_chill-Add-a-UNINTERRUPTIBLE-hrtimer_nanosleep.patch b/debian/patches/features/all/rt/cpu_chill-Add-a-UNINTERRUPTIBLE-hrtimer_nanosleep.patch new file mode 100644 index 000000000..4b00a392a --- /dev/null +++ b/debian/patches/features/all/rt/cpu_chill-Add-a-UNINTERRUPTIBLE-hrtimer_nanosleep.patch @@ -0,0 +1,107 @@ +From: Steven Rostedt +Date: Tue, 4 Mar 2014 12:28:32 -0500 +Subject: cpu_chill: Add a UNINTERRUPTIBLE hrtimer_nanosleep +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +We hit another bug that was caused by switching cpu_chill() from +msleep() to hrtimer_nanosleep(). + +This time it is a livelock. The problem is that hrtimer_nanosleep() +calls schedule with the state == TASK_INTERRUPTIBLE. But these means +that if a signal is pending, the scheduler wont schedule, and will +simply change the current task state back to TASK_RUNNING. This +nullifies the whole point of cpu_chill() in the first place. That is, +if a task is spinning on a try_lock() and it preempted the owner of the +lock, if it has a signal pending, it will never give up the CPU to let +the owner of the lock run. + +I made a static function __hrtimer_nanosleep() that takes a fifth +parameter "state", which determines the task state of that the +nanosleep() will be in. The normal hrtimer_nanosleep() will act the +same, but cpu_chill() will call the __hrtimer_nanosleep() directly with +the TASK_UNINTERRUPTIBLE state. + +cpu_chill() only cares that the first sleep happens, and does not care +about the state of the restart schedule (in hrtimer_nanosleep_restart). + + +Reported-by: Ulrich Obergfell +Signed-off-by: Steven Rostedt +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/time/hrtimer.c | 25 ++++++++++++++++++------- + 1 file changed, 18 insertions(+), 7 deletions(-) + +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -1746,12 +1746,13 @@ void hrtimer_init_sleeper(struct hrtimer + } + EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); + +-static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode) ++static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode, ++ unsigned long state) + { + hrtimer_init_sleeper(t, current); + + do { +- set_current_state(TASK_INTERRUPTIBLE); ++ set_current_state(state); + hrtimer_start_expires(&t->timer, mode); + if (!hrtimer_active(&t->timer)) + t->task = NULL; +@@ -1795,7 +1796,8 @@ long __sched hrtimer_nanosleep_restart(s + HRTIMER_MODE_ABS); + hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); + +- if (do_nanosleep(&t, HRTIMER_MODE_ABS)) ++ /* cpu_chill() does not care about restart state. */ ++ if (do_nanosleep(&t, HRTIMER_MODE_ABS, TASK_INTERRUPTIBLE)) + goto out; + + rmtp = restart->nanosleep.rmtp; +@@ -1812,8 +1814,10 @@ long __sched hrtimer_nanosleep_restart(s + return ret; + } + +-long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, +- const enum hrtimer_mode mode, const clockid_t clockid) ++static long ++__hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, ++ const enum hrtimer_mode mode, const clockid_t clockid, ++ unsigned long state) + { + struct restart_block *restart; + struct hrtimer_sleeper t; +@@ -1826,7 +1830,7 @@ long hrtimer_nanosleep(struct timespec * + + hrtimer_init_on_stack(&t.timer, clockid, mode); + hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack); +- if (do_nanosleep(&t, mode)) ++ if (do_nanosleep(&t, mode, state)) + goto out; + + /* Absolute timers do not update the rmtp value and restart: */ +@@ -1853,6 +1857,12 @@ long hrtimer_nanosleep(struct timespec * + return ret; + } + ++long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, ++ const enum hrtimer_mode mode, const clockid_t clockid) ++{ ++ return __hrtimer_nanosleep(rqtp, rmtp, mode, clockid, TASK_INTERRUPTIBLE); ++} ++ + SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp, + struct timespec __user *, rmtp) + { +@@ -1879,7 +1889,8 @@ void cpu_chill(void) + unsigned int freeze_flag = current->flags & PF_NOFREEZE; + + current->flags |= PF_NOFREEZE; +- hrtimer_nanosleep(&tu, NULL, HRTIMER_MODE_REL, CLOCK_MONOTONIC); ++ __hrtimer_nanosleep(&tu, NULL, HRTIMER_MODE_REL, CLOCK_MONOTONIC, ++ TASK_UNINTERRUPTIBLE); + if (!freeze_flag) + current->flags &= ~PF_NOFREEZE; + } diff --git a/debian/patches/features/all/rt/cpu_down_move_migrate_enable_back.patch b/debian/patches/features/all/rt/cpu_down_move_migrate_enable_back.patch new file mode 100644 index 000000000..e3a67793f --- /dev/null +++ b/debian/patches/features/all/rt/cpu_down_move_migrate_enable_back.patch @@ -0,0 +1,53 @@ +From: Tiejun Chen +Subject: cpu_down: move migrate_enable() back +Date: Thu, 7 Nov 2013 10:06:07 +0800 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Commit 08c1ab68, "hotplug-use-migrate-disable.patch", intends to +use migrate_enable()/migrate_disable() to replace that combination +of preempt_enable() and preempt_disable(), but actually in +!CONFIG_PREEMPT_RT_FULL case, migrate_enable()/migrate_disable() +are still equal to preempt_enable()/preempt_disable(). So that +followed cpu_hotplug_begin()/cpu_unplug_begin(cpu) would go schedule() +to trigger schedule_debug() like this: + +_cpu_down() + | + + migrate_disable() = preempt_disable() + | + + cpu_hotplug_begin() or cpu_unplug_begin() + | + + schedule() + | + + __schedule() + | + + preempt_disable(); + | + + __schedule_bug() is true! + +So we should move migrate_enable() as the original scheme. + + +Signed-off-by: Tiejun Chen +--- + kernel/cpu.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -668,6 +668,7 @@ static int __ref _cpu_down(unsigned int + err = -EBUSY; + goto restore_cpus; + } ++ migrate_enable(); + + cpu_hotplug_begin(); + err = cpu_unplug_begin(cpu); +@@ -744,7 +745,6 @@ static int __ref _cpu_down(unsigned int + out_release: + cpu_unplug_done(cpu); + out_cancel: +- migrate_enable(); + cpu_hotplug_done(); + if (!err) + cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu); diff --git a/debian/patches/features/all/rt/cpufreq-Remove-cpufreq_rwsem.patch b/debian/patches/features/all/rt/cpufreq-Remove-cpufreq_rwsem.patch new file mode 100644 index 000000000..07a01acb0 --- /dev/null +++ b/debian/patches/features/all/rt/cpufreq-Remove-cpufreq_rwsem.patch @@ -0,0 +1,196 @@ +From: Sebastian Andrzej Siewior +Date: Tue, 21 Jul 2015 15:28:49 +0200 +Subject: cpufreq: Remove cpufreq_rwsem +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +cpufreq_rwsem was introduced in commit 6eed9404ab3c4 ("cpufreq: Use +rwsem for protecting critical sections) in order to replace +try_module_get() on the cpu-freq driver. That try_module_get() worked +well until the refcount was so heavily used that module removal became +more or less impossible. + +Though when looking at the various (undocumented) protection +mechanisms in that code, the randomly sprinkeled around cpufreq_rwsem +locking sites are superfluous. + +The policy, which is acquired in cpufreq_cpu_get() and released in +cpufreq_cpu_put() is sufficiently protected already. + + cpufreq_cpu_get(cpu) + /* Protects against concurrent driver removal */ + read_lock_irqsave(&cpufreq_driver_lock, flags); + policy = per_cpu(cpufreq_cpu_data, cpu); + kobject_get(&policy->kobj); + read_unlock_irqrestore(&cpufreq_driver_lock, flags); + +The reference on the policy serializes versus module unload already: + + cpufreq_unregister_driver() + subsys_interface_unregister() + __cpufreq_remove_dev_finish() + per_cpu(cpufreq_cpu_data) = NULL; + cpufreq_policy_put_kobj() + +If there is a reference held on the policy, i.e. obtained prior to the +unregister call, then cpufreq_policy_put_kobj() will wait until that +reference is dropped. So once subsys_interface_unregister() returns +there is no policy pointer in flight and no new reference can be +obtained. So that rwsem protection is useless. + +The other usage of cpufreq_rwsem in show()/store() of the sysfs +interface is redundant as well because sysfs already does the proper +kobject_get()/put() pairs. + +That leaves CPU hotplug versus module removal. The current +down_write() around the write_lock() in cpufreq_unregister_driver() is +silly at best as it protects actually nothing. + +The trivial solution to this is to prevent hotplug across +cpufreq_unregister_driver completely. + +[upstream: rafael/linux-pm 454d3a2500a4eb33be85dde3bfba9e5f6b5efadc] +[fixes: "cpufreq_stat_notifier_trans: No policy found" since v4.0-rt] +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/cpufreq/cpufreq.c | 35 +++-------------------------------- + 1 file changed, 3 insertions(+), 32 deletions(-) + +--- a/drivers/cpufreq/cpufreq.c ++++ b/drivers/cpufreq/cpufreq.c +@@ -64,12 +64,6 @@ static inline bool has_target(void) + return cpufreq_driver->target_index || cpufreq_driver->target; + } + +-/* +- * rwsem to guarantee that cpufreq driver module doesn't unload during critical +- * sections +- */ +-static DECLARE_RWSEM(cpufreq_rwsem); +- + /* internal prototypes */ + static int __cpufreq_governor(struct cpufreq_policy *policy, + unsigned int event); +@@ -215,9 +209,6 @@ struct cpufreq_policy *cpufreq_cpu_get(u + if (cpu >= nr_cpu_ids) + return NULL; + +- if (!down_read_trylock(&cpufreq_rwsem)) +- return NULL; +- + /* get the cpufreq driver */ + read_lock_irqsave(&cpufreq_driver_lock, flags); + +@@ -230,9 +221,6 @@ struct cpufreq_policy *cpufreq_cpu_get(u + + read_unlock_irqrestore(&cpufreq_driver_lock, flags); + +- if (!policy) +- up_read(&cpufreq_rwsem); +- + return policy; + } + EXPORT_SYMBOL_GPL(cpufreq_cpu_get); +@@ -240,7 +228,6 @@ EXPORT_SYMBOL_GPL(cpufreq_cpu_get); + void cpufreq_cpu_put(struct cpufreq_policy *policy) + { + kobject_put(&policy->kobj); +- up_read(&cpufreq_rwsem); + } + EXPORT_SYMBOL_GPL(cpufreq_cpu_put); + +@@ -765,9 +752,6 @@ static ssize_t show(struct kobject *kobj + struct freq_attr *fattr = to_attr(attr); + ssize_t ret; + +- if (!down_read_trylock(&cpufreq_rwsem)) +- return -EINVAL; +- + down_read(&policy->rwsem); + + if (fattr->show) +@@ -776,7 +760,6 @@ static ssize_t show(struct kobject *kobj + ret = -EIO; + + up_read(&policy->rwsem); +- up_read(&cpufreq_rwsem); + + return ret; + } +@@ -793,9 +776,6 @@ static ssize_t store(struct kobject *kob + if (!cpu_online(policy->cpu)) + goto unlock; + +- if (!down_read_trylock(&cpufreq_rwsem)) +- goto unlock; +- + down_write(&policy->rwsem); + + if (fattr->store) +@@ -804,8 +784,6 @@ static ssize_t store(struct kobject *kob + ret = -EIO; + + up_write(&policy->rwsem); +- +- up_read(&cpufreq_rwsem); + unlock: + put_online_cpus(); + +@@ -1117,16 +1095,12 @@ static int __cpufreq_add_dev(struct devi + if (unlikely(policy)) + return 0; + +- if (!down_read_trylock(&cpufreq_rwsem)) +- return 0; +- + /* Check if this cpu was hot-unplugged earlier and has siblings */ + read_lock_irqsave(&cpufreq_driver_lock, flags); + for_each_policy(policy) { + if (cpumask_test_cpu(cpu, policy->related_cpus)) { + read_unlock_irqrestore(&cpufreq_driver_lock, flags); + ret = cpufreq_add_policy_cpu(policy, cpu, dev); +- up_read(&cpufreq_rwsem); + return ret; + } + } +@@ -1269,8 +1243,6 @@ static int __cpufreq_add_dev(struct devi + + kobject_uevent(&policy->kobj, KOBJ_ADD); + +- up_read(&cpufreq_rwsem); +- + /* Callback for handling stuff after policy is ready */ + if (cpufreq_driver->ready) + cpufreq_driver->ready(policy); +@@ -1304,8 +1276,6 @@ static int __cpufreq_add_dev(struct devi + cpufreq_policy_free(policy); + + nomem_out: +- up_read(&cpufreq_rwsem); +- + return ret; + } + +@@ -2499,19 +2469,20 @@ int cpufreq_unregister_driver(struct cpu + + pr_debug("unregistering driver %s\n", driver->name); + ++ /* Protect against concurrent cpu hotplug */ ++ get_online_cpus(); + subsys_interface_unregister(&cpufreq_interface); + if (cpufreq_boost_supported()) + cpufreq_sysfs_remove_file(&boost.attr); + + unregister_hotcpu_notifier(&cpufreq_cpu_notifier); + +- down_write(&cpufreq_rwsem); + write_lock_irqsave(&cpufreq_driver_lock, flags); + + cpufreq_driver = NULL; + + write_unlock_irqrestore(&cpufreq_driver_lock, flags); +- up_write(&cpufreq_rwsem); ++ put_online_cpus(); + + return 0; + } diff --git a/debian/patches/features/all/rt/cpufreq-drop-K8-s-driver-from-beeing-selected.patch b/debian/patches/features/all/rt/cpufreq-drop-K8-s-driver-from-beeing-selected.patch new file mode 100644 index 000000000..2cee2b82b --- /dev/null +++ b/debian/patches/features/all/rt/cpufreq-drop-K8-s-driver-from-beeing-selected.patch @@ -0,0 +1,33 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 9 Apr 2015 15:23:01 +0200 +Subject: cpufreq: drop K8's driver from beeing selected +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Ralf posted a picture of a backtrace from + +| powernowk8_target_fn() -> transition_frequency_fidvid() and then at the +| end: +| 932 policy = cpufreq_cpu_get(smp_processor_id()); +| 933 cpufreq_cpu_put(policy); + +crashing the system on -RT. I assumed that policy was a NULL pointer but +was rulled out. Since Ralf can't do any more investigations on this and +I have no machine with this, I simply switch it off. + +Reported-by: Ralf Mardorf +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/cpufreq/Kconfig.x86 | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/cpufreq/Kconfig.x86 ++++ b/drivers/cpufreq/Kconfig.x86 +@@ -123,7 +123,7 @@ config X86_POWERNOW_K7_ACPI + + config X86_POWERNOW_K8 + tristate "AMD Opteron/Athlon64 PowerNow!" +- depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ ++ depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ && !PREEMPT_RT_BASE + help + This adds the CPUFreq driver for K8/early Opteron/Athlon64 processors. + Support for K10 and newer processors is now in acpi-cpufreq. diff --git a/debian/patches/features/all/rt/cpumask-disable-offstack-on-rt.patch b/debian/patches/features/all/rt/cpumask-disable-offstack-on-rt.patch new file mode 100644 index 000000000..a0a85ddca --- /dev/null +++ b/debian/patches/features/all/rt/cpumask-disable-offstack-on-rt.patch @@ -0,0 +1,35 @@ +Subject: cpumask: Disable CONFIG_CPUMASK_OFFSTACK for RT +From: Thomas Gleixner +Date: Wed, 14 Dec 2011 01:03:49 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +We can't deal with the cpumask allocations which happen in atomic +context (see arch/x86/kernel/apic/io_apic.c) on RT right now. + +Signed-off-by: Thomas Gleixner +--- + arch/x86/Kconfig | 2 +- + lib/Kconfig | 1 + + 2 files changed, 2 insertions(+), 1 deletion(-) + +--- a/arch/x86/Kconfig ++++ b/arch/x86/Kconfig +@@ -841,7 +841,7 @@ config IOMMU_HELPER + config MAXSMP + bool "Enable Maximum number of SMP Processors and NUMA Nodes" + depends on X86_64 && SMP && DEBUG_KERNEL +- select CPUMASK_OFFSTACK ++ select CPUMASK_OFFSTACK if !PREEMPT_RT_FULL + ---help--- + Enable maximum number of CPUS and NUMA Nodes for this architecture. + If unsure, say N. +--- a/lib/Kconfig ++++ b/lib/Kconfig +@@ -391,6 +391,7 @@ config CHECK_SIGNATURE + + config CPUMASK_OFFSTACK + bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS ++ depends on !PREEMPT_RT_FULL + help + Use dynamic allocation for cpumask_var_t, instead of putting + them on the stack. This is a bit more expensive, but avoids diff --git a/debian/patches/features/all/rt/crypto-Reduce-preempt-disabled-regions-more-algos.patch b/debian/patches/features/all/rt/crypto-Reduce-preempt-disabled-regions-more-algos.patch new file mode 100644 index 000000000..396853550 --- /dev/null +++ b/debian/patches/features/all/rt/crypto-Reduce-preempt-disabled-regions-more-algos.patch @@ -0,0 +1,242 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 21 Feb 2014 17:24:04 +0100 +Subject: crypto: Reduce preempt disabled regions, more algos +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Don Estabrook reported +| kernel: WARNING: CPU: 2 PID: 858 at kernel/sched/core.c:2428 migrate_disable+0xed/0x100() +| kernel: WARNING: CPU: 2 PID: 858 at kernel/sched/core.c:2462 migrate_enable+0x17b/0x200() +| kernel: WARNING: CPU: 3 PID: 865 at kernel/sched/core.c:2428 migrate_disable+0xed/0x100() + +and his backtrace showed some crypto functions which looked fine. + +The problem is the following sequence: + +glue_xts_crypt_128bit() +{ + blkcipher_walk_virt(); /* normal migrate_disable() */ + + glue_fpu_begin(); /* get atomic */ + + while (nbytes) { + __glue_xts_crypt_128bit(); + blkcipher_walk_done(); /* with nbytes = 0, migrate_enable() + * while we are atomic */ + }; + glue_fpu_end() /* no longer atomic */ +} + +and this is why the counter get out of sync and the warning is printed. +The other problem is that we are non-preemptible between +glue_fpu_begin() and glue_fpu_end() and the latency grows. To fix this, +I shorten the FPU off region and ensure blkcipher_walk_done() is called +with preemption enabled. This might hurt the performance because we now +enable/disable the FPU state more often but we gain lower latency and +the bug is gone. + + +Reported-by: Don Estabrook +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/x86/crypto/cast5_avx_glue.c | 21 +++++++++------------ + arch/x86/crypto/glue_helper.c | 31 +++++++++++++++---------------- + 2 files changed, 24 insertions(+), 28 deletions(-) + +--- a/arch/x86/crypto/cast5_avx_glue.c ++++ b/arch/x86/crypto/cast5_avx_glue.c +@@ -60,7 +60,7 @@ static inline void cast5_fpu_end(bool fp + static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk, + bool enc) + { +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct cast5_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + const unsigned int bsize = CAST5_BLOCK_SIZE; + unsigned int nbytes; +@@ -76,7 +76,7 @@ static int ecb_crypt(struct blkcipher_de + u8 *wsrc = walk->src.virt.addr; + u8 *wdst = walk->dst.virt.addr; + +- fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes); ++ fpu_enabled = cast5_fpu_begin(false, nbytes); + + /* Process multi-block batch */ + if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) { +@@ -104,10 +104,9 @@ static int ecb_crypt(struct blkcipher_de + } while (nbytes >= bsize); + + done: ++ cast5_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, walk, nbytes); + } +- +- cast5_fpu_end(fpu_enabled); + return err; + } + +@@ -228,7 +227,7 @@ static unsigned int __cbc_decrypt(struct + static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) + { +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct blkcipher_walk walk; + int err; + +@@ -237,12 +236,11 @@ static int cbc_decrypt(struct blkcipher_ + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + + while ((nbytes = walk.nbytes)) { +- fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes); ++ fpu_enabled = cast5_fpu_begin(false, nbytes); + nbytes = __cbc_decrypt(desc, &walk); ++ cast5_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, &walk, nbytes); + } +- +- cast5_fpu_end(fpu_enabled); + return err; + } + +@@ -312,7 +310,7 @@ static unsigned int __ctr_crypt(struct b + static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) + { +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct blkcipher_walk walk; + int err; + +@@ -321,13 +319,12 @@ static int ctr_crypt(struct blkcipher_de + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + + while ((nbytes = walk.nbytes) >= CAST5_BLOCK_SIZE) { +- fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes); ++ fpu_enabled = cast5_fpu_begin(false, nbytes); + nbytes = __ctr_crypt(desc, &walk); ++ cast5_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, &walk, nbytes); + } + +- cast5_fpu_end(fpu_enabled); +- + if (walk.nbytes) { + ctr_crypt_final(desc, &walk); + err = blkcipher_walk_done(desc, &walk, 0); +--- a/arch/x86/crypto/glue_helper.c ++++ b/arch/x86/crypto/glue_helper.c +@@ -39,7 +39,7 @@ static int __glue_ecb_crypt_128bit(const + void *ctx = crypto_blkcipher_ctx(desc->tfm); + const unsigned int bsize = 128 / 8; + unsigned int nbytes, i, func_bytes; +- bool fpu_enabled = false; ++ bool fpu_enabled; + int err; + + err = blkcipher_walk_virt(desc, walk); +@@ -49,7 +49,7 @@ static int __glue_ecb_crypt_128bit(const + u8 *wdst = walk->dst.virt.addr; + + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- desc, fpu_enabled, nbytes); ++ desc, false, nbytes); + + for (i = 0; i < gctx->num_funcs; i++) { + func_bytes = bsize * gctx->funcs[i].num_blocks; +@@ -71,10 +71,10 @@ static int __glue_ecb_crypt_128bit(const + } + + done: ++ glue_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, walk, nbytes); + } + +- glue_fpu_end(fpu_enabled); + return err; + } + +@@ -194,7 +194,7 @@ int glue_cbc_decrypt_128bit(const struct + struct scatterlist *src, unsigned int nbytes) + { + const unsigned int bsize = 128 / 8; +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct blkcipher_walk walk; + int err; + +@@ -203,12 +203,12 @@ int glue_cbc_decrypt_128bit(const struct + + while ((nbytes = walk.nbytes)) { + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- desc, fpu_enabled, nbytes); ++ desc, false, nbytes); + nbytes = __glue_cbc_decrypt_128bit(gctx, desc, &walk); ++ glue_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, &walk, nbytes); + } + +- glue_fpu_end(fpu_enabled); + return err; + } + EXPORT_SYMBOL_GPL(glue_cbc_decrypt_128bit); +@@ -277,7 +277,7 @@ int glue_ctr_crypt_128bit(const struct c + struct scatterlist *src, unsigned int nbytes) + { + const unsigned int bsize = 128 / 8; +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct blkcipher_walk walk; + int err; + +@@ -286,13 +286,12 @@ int glue_ctr_crypt_128bit(const struct c + + while ((nbytes = walk.nbytes) >= bsize) { + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- desc, fpu_enabled, nbytes); ++ desc, false, nbytes); + nbytes = __glue_ctr_crypt_128bit(gctx, desc, &walk); ++ glue_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, &walk, nbytes); + } + +- glue_fpu_end(fpu_enabled); +- + if (walk.nbytes) { + glue_ctr_crypt_final_128bit( + gctx->funcs[gctx->num_funcs - 1].fn_u.ctr, desc, &walk); +@@ -347,7 +346,7 @@ int glue_xts_crypt_128bit(const struct c + void *tweak_ctx, void *crypt_ctx) + { + const unsigned int bsize = 128 / 8; +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct blkcipher_walk walk; + int err; + +@@ -360,21 +359,21 @@ int glue_xts_crypt_128bit(const struct c + + /* set minimum length to bsize, for tweak_fn */ + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- desc, fpu_enabled, ++ desc, false, + nbytes < bsize ? bsize : nbytes); +- + /* calculate first value of T */ + tweak_fn(tweak_ctx, walk.iv, walk.iv); ++ glue_fpu_end(fpu_enabled); + + while (nbytes) { ++ fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, ++ desc, false, nbytes); + nbytes = __glue_xts_crypt_128bit(gctx, crypt_ctx, desc, &walk); + ++ glue_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, &walk, nbytes); + nbytes = walk.nbytes; + } +- +- glue_fpu_end(fpu_enabled); +- + return err; + } + EXPORT_SYMBOL_GPL(glue_xts_crypt_128bit); diff --git a/debian/patches/features/all/rt/debugobjects-rt.patch b/debian/patches/features/all/rt/debugobjects-rt.patch new file mode 100644 index 000000000..c4a3b7dae --- /dev/null +++ b/debian/patches/features/all/rt/debugobjects-rt.patch @@ -0,0 +1,26 @@ +Subject: debugobjects: Make RT aware +From: Thomas Gleixner +Date: Sun, 17 Jul 2011 21:41:35 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Avoid filling the pool / allocating memory with irqs off(). + +Signed-off-by: Thomas Gleixner +--- + lib/debugobjects.c | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +--- a/lib/debugobjects.c ++++ b/lib/debugobjects.c +@@ -309,7 +309,10 @@ static void + struct debug_obj *obj; + unsigned long flags; + +- fill_pool(); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (preempt_count() == 0 && !irqs_disabled()) ++#endif ++ fill_pool(); + + db = get_bucket((unsigned long) addr); + diff --git a/debian/patches/features/all/rt/dm-make-rt-aware.patch b/debian/patches/features/all/rt/dm-make-rt-aware.patch new file mode 100644 index 000000000..4823177d2 --- /dev/null +++ b/debian/patches/features/all/rt/dm-make-rt-aware.patch @@ -0,0 +1,27 @@ +Subject: dm: Make rt aware +From: Thomas Gleixner +Date: Mon, 14 Nov 2011 23:06:09 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Use the BUG_ON_NORT variant for the irq_disabled() checks. RT has +interrupts legitimately enabled here as we cant deadlock against the +irq thread due to the "sleeping spinlocks" conversion. + +Reported-by: Luis Claudio R. Goncalves + +Signed-off-by: Thomas Gleixner +--- + drivers/md/dm.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/md/dm.c ++++ b/drivers/md/dm.c +@@ -2143,7 +2143,7 @@ static void dm_request_fn(struct request + /* Establish tio->ti before queuing work (map_tio_request) */ + tio->ti = ti; + queue_kthread_work(&md->kworker, &tio->work); +- BUG_ON(!irqs_disabled()); ++ BUG_ON_NONRT(!irqs_disabled()); + } + + goto out; diff --git a/debian/patches/features/all/rt/drivers-net-8139-disable-irq-nosync.patch b/debian/patches/features/all/rt/drivers-net-8139-disable-irq-nosync.patch new file mode 100644 index 000000000..d23d5f984 --- /dev/null +++ b/debian/patches/features/all/rt/drivers-net-8139-disable-irq-nosync.patch @@ -0,0 +1,26 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:29:24 -0500 +Subject: drivers/net: Use disable_irq_nosync() in 8139too +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Use disable_irq_nosync() instead of disable_irq() as this might be +called in atomic context with netpoll. + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + drivers/net/ethernet/realtek/8139too.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/net/ethernet/realtek/8139too.c ++++ b/drivers/net/ethernet/realtek/8139too.c +@@ -2229,7 +2229,7 @@ static void rtl8139_poll_controller(stru + struct rtl8139_private *tp = netdev_priv(dev); + const int irq = tp->pci_dev->irq; + +- disable_irq(irq); ++ disable_irq_nosync(irq); + rtl8139_interrupt(irq, dev); + enable_irq(irq); + } diff --git a/debian/patches/features/all/rt/drivers-net-fix-livelock-issues.patch b/debian/patches/features/all/rt/drivers-net-fix-livelock-issues.patch new file mode 100644 index 000000000..3379ba4e0 --- /dev/null +++ b/debian/patches/features/all/rt/drivers-net-fix-livelock-issues.patch @@ -0,0 +1,127 @@ +From: Thomas Gleixner +Date: Sat, 20 Jun 2009 11:36:54 +0200 +Subject: drivers/net: fix livelock issues +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Preempt-RT runs into a live lock issue with the NETDEV_TX_LOCKED micro +optimization. The reason is that the softirq thread is rescheduling +itself on that return value. Depending on priorities it starts to +monoplize the CPU and livelock on UP systems. + +Remove it. + +Signed-off-by: Thomas Gleixner + +--- + drivers/net/ethernet/atheros/atl1c/atl1c_main.c | 6 +----- + drivers/net/ethernet/atheros/atl1e/atl1e_main.c | 3 +-- + drivers/net/ethernet/chelsio/cxgb/sge.c | 3 +-- + drivers/net/ethernet/neterion/s2io.c | 7 +------ + drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c | 6 ++---- + drivers/net/ethernet/tehuti/tehuti.c | 9 ++------- + drivers/net/rionet.c | 6 +----- + 7 files changed, 9 insertions(+), 31 deletions(-) + +--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c ++++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +@@ -2213,11 +2213,7 @@ static netdev_tx_t atl1c_xmit_frame(stru + } + + tpd_req = atl1c_cal_tpd_req(skb); +- if (!spin_trylock_irqsave(&adapter->tx_lock, flags)) { +- if (netif_msg_pktdata(adapter)) +- dev_info(&adapter->pdev->dev, "tx locked\n"); +- return NETDEV_TX_LOCKED; +- } ++ spin_lock_irqsave(&adapter->tx_lock, flags); + + if (atl1c_tpd_avail(adapter, type) < tpd_req) { + /* no enough descriptor, just stop queue */ +--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c ++++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +@@ -1880,8 +1880,7 @@ static netdev_tx_t atl1e_xmit_frame(stru + return NETDEV_TX_OK; + } + tpd_req = atl1e_cal_tdp_req(skb); +- if (!spin_trylock_irqsave(&adapter->tx_lock, flags)) +- return NETDEV_TX_LOCKED; ++ spin_lock_irqsave(&adapter->tx_lock, flags); + + if (atl1e_tpd_avail(adapter) < tpd_req) { + /* no enough descriptor, just stop queue */ +--- a/drivers/net/ethernet/chelsio/cxgb/sge.c ++++ b/drivers/net/ethernet/chelsio/cxgb/sge.c +@@ -1664,8 +1664,7 @@ static int t1_sge_tx(struct sk_buff *skb + struct cmdQ *q = &sge->cmdQ[qid]; + unsigned int credits, pidx, genbit, count, use_sched_skb = 0; + +- if (!spin_trylock(&q->lock)) +- return NETDEV_TX_LOCKED; ++ spin_lock(&q->lock); + + reclaim_completed_tx(sge, q); + +--- a/drivers/net/ethernet/neterion/s2io.c ++++ b/drivers/net/ethernet/neterion/s2io.c +@@ -4084,12 +4084,7 @@ static netdev_tx_t s2io_xmit(struct sk_b + [skb->priority & (MAX_TX_FIFOS - 1)]; + fifo = &mac_control->fifos[queue]; + +- if (do_spin_lock) +- spin_lock_irqsave(&fifo->tx_lock, flags); +- else { +- if (unlikely(!spin_trylock_irqsave(&fifo->tx_lock, flags))) +- return NETDEV_TX_LOCKED; +- } ++ spin_lock_irqsave(&fifo->tx_lock, flags); + + if (sp->config.multiq) { + if (__netif_subqueue_stopped(dev, fifo->fifo_no)) { +--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c ++++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +@@ -2137,10 +2137,8 @@ static int pch_gbe_xmit_frame(struct sk_ + struct pch_gbe_tx_ring *tx_ring = adapter->tx_ring; + unsigned long flags; + +- if (!spin_trylock_irqsave(&tx_ring->tx_lock, flags)) { +- /* Collision - tell upper layer to requeue */ +- return NETDEV_TX_LOCKED; +- } ++ spin_lock_irqsave(&tx_ring->tx_lock, flags); ++ + if (unlikely(!PCH_GBE_DESC_UNUSED(tx_ring))) { + netif_stop_queue(netdev); + spin_unlock_irqrestore(&tx_ring->tx_lock, flags); +--- a/drivers/net/ethernet/tehuti/tehuti.c ++++ b/drivers/net/ethernet/tehuti/tehuti.c +@@ -1629,13 +1629,8 @@ static netdev_tx_t bdx_tx_transmit(struc + unsigned long flags; + + ENTER; +- local_irq_save(flags); +- if (!spin_trylock(&priv->tx_lock)) { +- local_irq_restore(flags); +- DBG("%s[%s]: TX locked, returning NETDEV_TX_LOCKED\n", +- BDX_DRV_NAME, ndev->name); +- return NETDEV_TX_LOCKED; +- } ++ ++ spin_lock_irqsave(&priv->tx_lock, flags); + + /* build tx descriptor */ + BDX_ASSERT(f->m.wptr >= f->m.memsz); /* started with valid wptr */ +--- a/drivers/net/rionet.c ++++ b/drivers/net/rionet.c +@@ -174,11 +174,7 @@ static int rionet_start_xmit(struct sk_b + unsigned long flags; + int add_num = 1; + +- local_irq_save(flags); +- if (!spin_trylock(&rnet->tx_lock)) { +- local_irq_restore(flags); +- return NETDEV_TX_LOCKED; +- } ++ spin_lock_irqsave(&rnet->tx_lock, flags); + + if (is_multicast_ether_addr(eth->h_dest)) + add_num = nets[rnet->mport->id].nact; diff --git a/debian/patches/features/all/rt/drivers-net-vortex-fix-locking-issues.patch b/debian/patches/features/all/rt/drivers-net-vortex-fix-locking-issues.patch new file mode 100644 index 000000000..e508199e4 --- /dev/null +++ b/debian/patches/features/all/rt/drivers-net-vortex-fix-locking-issues.patch @@ -0,0 +1,49 @@ +From: Steven Rostedt +Date: Fri, 3 Jul 2009 08:30:00 -0500 +Subject: drivers/net: vortex fix locking issues +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Argh, cut and paste wasn't enough... + +Use this patch instead. It needs an irq disable. But, believe it or not, +on SMP this is actually better. If the irq is shared (as it is in Mark's +case), we don't stop the irq of other devices from being handled on +another CPU (unfortunately for Mark, he pinned all interrupts to one CPU). + +Signed-off-by: Steven Rostedt +Signed-off-by: Thomas Gleixner + + drivers/net/ethernet/3com/3c59x.c | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +Signed-off-by: Ingo Molnar + +--- a/drivers/net/ethernet/3com/3c59x.c ++++ b/drivers/net/ethernet/3com/3c59x.c +@@ -842,9 +842,9 @@ static void poll_vortex(struct net_devic + { + struct vortex_private *vp = netdev_priv(dev); + unsigned long flags; +- local_irq_save(flags); ++ local_irq_save_nort(flags); + (vp->full_bus_master_rx ? boomerang_interrupt:vortex_interrupt)(dev->irq,dev); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + #endif + +@@ -1916,12 +1916,12 @@ static void vortex_tx_timeout(struct net + * Block interrupts because vortex_interrupt does a bare spin_lock() + */ + unsigned long flags; +- local_irq_save(flags); ++ local_irq_save_nort(flags); + if (vp->full_bus_master_tx) + boomerang_interrupt(dev->irq, dev); + else + vortex_interrupt(dev->irq, dev); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + } + diff --git a/debian/patches/features/all/rt/drivers-random-reduce-preempt-disabled-region.patch b/debian/patches/features/all/rt/drivers-random-reduce-preempt-disabled-region.patch new file mode 100644 index 000000000..dfdc48772 --- /dev/null +++ b/debian/patches/features/all/rt/drivers-random-reduce-preempt-disabled-region.patch @@ -0,0 +1,33 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:29:30 -0500 +Subject: drivers: random: Reduce preempt disabled region +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +No need to keep preemption disabled across the whole function. + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + drivers/char/random.c | 3 --- + 1 file changed, 3 deletions(-) + +--- a/drivers/char/random.c ++++ b/drivers/char/random.c +@@ -776,8 +776,6 @@ static void add_timer_randomness(struct + } sample; + long delta, delta2, delta3; + +- preempt_disable(); +- + sample.jiffies = jiffies; + sample.cycles = random_get_entropy(); + sample.num = num; +@@ -818,7 +816,6 @@ static void add_timer_randomness(struct + */ + credit_entropy_bits(r, min_t(int, fls(delta>>1), 11)); + } +- preempt_enable(); + } + + void add_input_randomness(unsigned int type, unsigned int code, diff --git a/debian/patches/features/all/rt/drivers-tty-fix-omap-lock-crap.patch b/debian/patches/features/all/rt/drivers-tty-fix-omap-lock-crap.patch new file mode 100644 index 000000000..2dde43020 --- /dev/null +++ b/debian/patches/features/all/rt/drivers-tty-fix-omap-lock-crap.patch @@ -0,0 +1,43 @@ +Subject: tty/serial/omap: Make the locking RT aware +From: Thomas Gleixner +Date: Thu, 28 Jul 2011 13:32:57 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The lock is a sleeping lock and local_irq_save() is not the +optimsation we are looking for. Redo it to make it work on -RT and +non-RT. + +Signed-off-by: Thomas Gleixner +--- + drivers/tty/serial/omap-serial.c | 12 ++++-------- + 1 file changed, 4 insertions(+), 8 deletions(-) + +--- a/drivers/tty/serial/omap-serial.c ++++ b/drivers/tty/serial/omap-serial.c +@@ -1282,13 +1282,10 @@ serial_omap_console_write(struct console + + pm_runtime_get_sync(up->dev); + +- local_irq_save(flags); +- if (up->port.sysrq) +- locked = 0; +- else if (oops_in_progress) +- locked = spin_trylock(&up->port.lock); ++ if (up->port.sysrq || oops_in_progress) ++ locked = spin_trylock_irqsave(&up->port.lock, flags); + else +- spin_lock(&up->port.lock); ++ spin_lock_irqsave(&up->port.lock, flags); + + /* + * First save the IER then disable the interrupts +@@ -1317,8 +1314,7 @@ serial_omap_console_write(struct console + pm_runtime_mark_last_busy(up->dev); + pm_runtime_put_autosuspend(up->dev); + if (locked) +- spin_unlock(&up->port.lock); +- local_irq_restore(flags); ++ spin_unlock_irqrestore(&up->port.lock, flags); + } + + static int __init diff --git a/debian/patches/features/all/rt/drivers-tty-pl011-irq-disable-madness.patch b/debian/patches/features/all/rt/drivers-tty-pl011-irq-disable-madness.patch new file mode 100644 index 000000000..98fca9fc3 --- /dev/null +++ b/debian/patches/features/all/rt/drivers-tty-pl011-irq-disable-madness.patch @@ -0,0 +1,48 @@ +Subject: tty/serial/pl011: Make the locking work on RT +From: Thomas Gleixner +Date: Tue, 08 Jan 2013 21:36:51 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The lock is a sleeping lock and local_irq_save() is not the optimsation +we are looking for. Redo it to make it work on -RT and non-RT. + +Signed-off-by: Thomas Gleixner +--- + drivers/tty/serial/amba-pl011.c | 15 ++++++++++----- + 1 file changed, 10 insertions(+), 5 deletions(-) + +--- a/drivers/tty/serial/amba-pl011.c ++++ b/drivers/tty/serial/amba-pl011.c +@@ -2000,13 +2000,19 @@ pl011_console_write(struct console *co, + + clk_enable(uap->clk); + +- local_irq_save(flags); ++ /* ++ * local_irq_save(flags); ++ * ++ * This local_irq_save() is nonsense. If we come in via sysrq ++ * handling then interrupts are already disabled. Aside of ++ * that the port.sysrq check is racy on SMP regardless. ++ */ + if (uap->port.sysrq) + locked = 0; + else if (oops_in_progress) +- locked = spin_trylock(&uap->port.lock); ++ locked = spin_trylock_irqsave(&uap->port.lock, flags); + else +- spin_lock(&uap->port.lock); ++ spin_lock_irqsave(&uap->port.lock, flags); + + /* + * First save the CR then disable the interrupts +@@ -2028,8 +2034,7 @@ pl011_console_write(struct console *co, + writew(old_cr, uap->port.membase + UART011_CR); + + if (locked) +- spin_unlock(&uap->port.lock); +- local_irq_restore(flags); ++ spin_unlock_irqrestore(&uap->port.lock, flags); + + clk_disable(uap->clk); + } diff --git a/debian/patches/features/all/rt/drm-i915-drop-trace_i915_gem_ring_dispatch-onrt.patch b/debian/patches/features/all/rt/drm-i915-drop-trace_i915_gem_ring_dispatch-onrt.patch new file mode 100644 index 000000000..f903a669b --- /dev/null +++ b/debian/patches/features/all/rt/drm-i915-drop-trace_i915_gem_ring_dispatch-onrt.patch @@ -0,0 +1,59 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 25 Apr 2013 18:12:52 +0200 +Subject: drm/i915: drop trace_i915_gem_ring_dispatch on rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +This tracepoint is responsible for: + +|[<814cc358>] __schedule_bug+0x4d/0x59 +|[<814d24cc>] __schedule+0x88c/0x930 +|[<814d3b90>] ? _raw_spin_unlock_irqrestore+0x40/0x50 +|[<814d3b95>] ? _raw_spin_unlock_irqrestore+0x45/0x50 +|[<810b57b5>] ? task_blocks_on_rt_mutex+0x1f5/0x250 +|[<814d27d9>] schedule+0x29/0x70 +|[<814d3423>] rt_spin_lock_slowlock+0x15b/0x278 +|[<814d3786>] rt_spin_lock+0x26/0x30 +|[] gen6_gt_force_wake_get+0x29/0x60 [i915] +|[] gen6_ring_get_irq+0x5f/0x100 [i915] +|[] ftrace_raw_event_i915_gem_ring_dispatch+0xe3/0x100 [i915] +|[] i915_gem_do_execbuffer.isra.13+0xbd3/0x1430 [i915] +|[<810f8943>] ? trace_buffer_unlock_commit+0x43/0x60 +|[<8113e8d2>] ? ftrace_raw_event_kmem_alloc+0xd2/0x180 +|[<8101d063>] ? native_sched_clock+0x13/0x80 +|[] i915_gem_execbuffer2+0x99/0x280 [i915] +|[] drm_ioctl+0x4c3/0x570 [drm] +|[<8101d0d9>] ? sched_clock+0x9/0x10 +|[] ? i915_gem_execbuffer+0x480/0x480 [i915] +|[<810f1c18>] ? rb_commit+0x68/0xa0 +|[<810f1c6c>] ? ring_buffer_unlock_commit+0x1c/0xa0 +|[<81197467>] do_vfs_ioctl+0x97/0x540 +|[<81021318>] ? ftrace_raw_event_sys_enter+0xd8/0x130 +|[<811979a1>] sys_ioctl+0x91/0xb0 +|[<814db931>] tracesys+0xe1/0xe6 + +Chris Wilson does not like to move i915_trace_irq_get() out of the macro + +|No. This enables the IRQ, as well as making a number of +|very expensively serialised read, unconditionally. + +so it is gone now on RT. + + +Reported-by: Joakim Hernberg +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c ++++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c +@@ -1339,7 +1339,9 @@ i915_gem_ringbuffer_submission(struct dr + return ret; + } + ++#ifndef CONFIG_PREEMPT_RT_BASE + trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), dispatch_flags); ++#endif + + i915_gem_execbuffer_move_to_active(vmas, ring); + i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj); diff --git a/debian/patches/features/all/rt/epoll-use-get-cpu-light.patch b/debian/patches/features/all/rt/epoll-use-get-cpu-light.patch new file mode 100644 index 000000000..68f108881 --- /dev/null +++ b/debian/patches/features/all/rt/epoll-use-get-cpu-light.patch @@ -0,0 +1,31 @@ +Subject: fs/epoll: Do not disable preemption on RT +From: Thomas Gleixner +Date: Fri, 08 Jul 2011 16:35:35 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +ep_call_nested() takes a sleeping lock so we can't disable preemption. +The light version is enough since ep_call_nested() doesn't mind beeing +invoked twice on the same CPU. + +Signed-off-by: Thomas Gleixner +--- + fs/eventpoll.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/fs/eventpoll.c ++++ b/fs/eventpoll.c +@@ -505,12 +505,12 @@ static int ep_poll_wakeup_proc(void *pri + */ + static void ep_poll_safewake(wait_queue_head_t *wq) + { +- int this_cpu = get_cpu(); ++ int this_cpu = get_cpu_light(); + + ep_call_nested(&poll_safewake_ncalls, EP_MAX_NESTS, + ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu); + +- put_cpu(); ++ put_cpu_light(); + } + + static void ep_remove_wait_queue(struct eppoll_entry *pwq) diff --git a/debian/patches/features/all/rt/fix-rt-int3-x86_32-3.2-rt.patch b/debian/patches/features/all/rt/fix-rt-int3-x86_32-3.2-rt.patch new file mode 100644 index 000000000..2479b5182 --- /dev/null +++ b/debian/patches/features/all/rt/fix-rt-int3-x86_32-3.2-rt.patch @@ -0,0 +1,102 @@ +From: Steven Rostedt +Date: Tue, 14 Jul 2015 14:26:34 +0200 +Subject: x86: Do not disable preemption in int3 on 32bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Preemption must be disabled before enabling interrupts in do_trap +on x86_64 because the stack in use for int3 and debug is a per CPU +stack set by th IST. But 32bit does not have an IST and the stack +still belongs to the current task and there is no problem in scheduling +out the task. + +Keep preemption enabled on X86_32 when enabling interrupts for +do_trap(). + +The name of the function is changed from preempt_conditional_sti/cli() +to conditional_sti/cli_ist(), to annotate that this function is used +when the stack is on the IST. + + +Signed-off-by: Steven Rostedt +Signed-off-by: Thomas Gleixner + +--- + arch/x86/kernel/traps.c | 28 +++++++++++++++++++++------- + 1 file changed, 21 insertions(+), 7 deletions(-) + +--- a/arch/x86/kernel/traps.c ++++ b/arch/x86/kernel/traps.c +@@ -88,9 +88,21 @@ static inline void conditional_sti(struc + local_irq_enable(); + } + +-static inline void preempt_conditional_sti(struct pt_regs *regs) ++static inline void conditional_sti_ist(struct pt_regs *regs) + { ++#ifdef CONFIG_X86_64 ++ /* ++ * X86_64 uses a per CPU stack on the IST for certain traps ++ * like int3. The task can not be preempted when using one ++ * of these stacks, thus preemption must be disabled, otherwise ++ * the stack can be corrupted if the task is scheduled out, ++ * and another task comes in and uses this stack. ++ * ++ * On x86_32 the task keeps its own stack and it is OK if the ++ * task schedules out. ++ */ + preempt_count_inc(); ++#endif + if (regs->flags & X86_EFLAGS_IF) + local_irq_enable(); + } +@@ -101,11 +113,13 @@ static inline void conditional_cli(struc + local_irq_disable(); + } + +-static inline void preempt_conditional_cli(struct pt_regs *regs) ++static inline void conditional_cli_ist(struct pt_regs *regs) + { + if (regs->flags & X86_EFLAGS_IF) + local_irq_disable(); ++#ifdef CONFIG_X86_64 + preempt_count_dec(); ++#endif + } + + enum ctx_state ist_enter(struct pt_regs *regs) +@@ -536,9 +550,9 @@ dotraplinkage void notrace do_int3(struc + * as we may switch to the interrupt stack. + */ + debug_stack_usage_inc(); +- preempt_conditional_sti(regs); ++ conditional_sti_ist(regs); + do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL); +- preempt_conditional_cli(regs); ++ conditional_cli_ist(regs); + debug_stack_usage_dec(); + exit: + ist_exit(regs, prev_state); +@@ -668,12 +682,12 @@ dotraplinkage void do_debug(struct pt_re + debug_stack_usage_inc(); + + /* It's safe to allow irq's after DR6 has been saved */ +- preempt_conditional_sti(regs); ++ conditional_sti_ist(regs); + + if (v8086_mode(regs)) { + handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, + X86_TRAP_DB); +- preempt_conditional_cli(regs); ++ conditional_cli_ist(regs); + debug_stack_usage_dec(); + goto exit; + } +@@ -693,7 +707,7 @@ dotraplinkage void do_debug(struct pt_re + si_code = get_si_code(tsk->thread.debugreg6); + if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp) + send_sigtrap(tsk, regs, error_code, si_code); +- preempt_conditional_cli(regs); ++ conditional_cli_ist(regs); + debug_stack_usage_dec(); + + exit: diff --git a/debian/patches/features/all/rt/fs-aio-simple-simple-work.patch b/debian/patches/features/all/rt/fs-aio-simple-simple-work.patch new file mode 100644 index 000000000..17f1c02cb --- /dev/null +++ b/debian/patches/features/all/rt/fs-aio-simple-simple-work.patch @@ -0,0 +1,107 @@ +From: Sebastian Andrzej Siewior +Date: Mon, 16 Feb 2015 18:49:10 +0100 +Subject: fs/aio: simple simple work +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +|BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:768 +|in_atomic(): 1, irqs_disabled(): 0, pid: 26, name: rcuos/2 +|2 locks held by rcuos/2/26: +| #0: (rcu_callback){.+.+..}, at: [] rcu_nocb_kthread+0x1e2/0x380 +| #1: (rcu_read_lock_sched){.+.+..}, at: [] percpu_ref_kill_rcu+0xa6/0x1c0 +|Preemption disabled at:[] rcu_nocb_kthread+0x263/0x380 +|Call Trace: +| [] dump_stack+0x4e/0x9c +| [] __might_sleep+0xfb/0x170 +| [] rt_spin_lock+0x24/0x70 +| [] free_ioctx_users+0x30/0x130 +| [] percpu_ref_kill_rcu+0x1b4/0x1c0 +| [] rcu_nocb_kthread+0x263/0x380 +| [] kthread+0xd6/0xf0 +| [] ret_from_fork+0x7c/0xb0 + +replace this preempt_disable() friendly swork. + +Reported-By: Mike Galbraith +Suggested-by: Benjamin LaHaise +Signed-off-by: Sebastian Andrzej Siewior +--- + fs/aio.c | 24 +++++++++++++++++------- + 1 file changed, 17 insertions(+), 7 deletions(-) + +--- a/fs/aio.c ++++ b/fs/aio.c +@@ -40,6 +40,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -115,7 +116,7 @@ struct kioctx { + struct page **ring_pages; + long nr_pages; + +- struct work_struct free_work; ++ struct swork_event free_work; + + /* + * signals when all in-flight requests are done +@@ -253,6 +254,7 @@ static int __init aio_setup(void) + .mount = aio_mount, + .kill_sb = kill_anon_super, + }; ++ BUG_ON(swork_get()); + aio_mnt = kern_mount(&aio_fs); + if (IS_ERR(aio_mnt)) + panic("Failed to create aio fs mount."); +@@ -559,9 +561,9 @@ static int kiocb_cancel(struct aio_kiocb + return cancel(&kiocb->common); + } + +-static void free_ioctx(struct work_struct *work) ++static void free_ioctx(struct swork_event *sev) + { +- struct kioctx *ctx = container_of(work, struct kioctx, free_work); ++ struct kioctx *ctx = container_of(sev, struct kioctx, free_work); + + pr_debug("freeing %p\n", ctx); + +@@ -580,8 +582,8 @@ static void free_ioctx_reqs(struct percp + if (ctx->rq_wait && atomic_dec_and_test(&ctx->rq_wait->count)) + complete(&ctx->rq_wait->comp); + +- INIT_WORK(&ctx->free_work, free_ioctx); +- schedule_work(&ctx->free_work); ++ INIT_SWORK(&ctx->free_work, free_ioctx); ++ swork_queue(&ctx->free_work); + } + + /* +@@ -589,9 +591,9 @@ static void free_ioctx_reqs(struct percp + * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted - + * now it's safe to cancel any that need to be. + */ +-static void free_ioctx_users(struct percpu_ref *ref) ++static void free_ioctx_users_work(struct swork_event *sev) + { +- struct kioctx *ctx = container_of(ref, struct kioctx, users); ++ struct kioctx *ctx = container_of(sev, struct kioctx, free_work); + struct aio_kiocb *req; + + spin_lock_irq(&ctx->ctx_lock); +@@ -610,6 +612,14 @@ static void free_ioctx_users(struct perc + percpu_ref_put(&ctx->reqs); + } + ++static void free_ioctx_users(struct percpu_ref *ref) ++{ ++ struct kioctx *ctx = container_of(ref, struct kioctx, users); ++ ++ INIT_SWORK(&ctx->free_work, free_ioctx_users_work); ++ swork_queue(&ctx->free_work); ++} ++ + static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) + { + unsigned i, new_nr; diff --git a/debian/patches/features/all/rt/fs-block-rt-support.patch b/debian/patches/features/all/rt/fs-block-rt-support.patch new file mode 100644 index 000000000..fa0f2dc0a --- /dev/null +++ b/debian/patches/features/all/rt/fs-block-rt-support.patch @@ -0,0 +1,23 @@ +Subject: block: Turn off warning which is bogus on RT +From: Thomas Gleixner +Date: Tue, 14 Jun 2011 17:05:09 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +On -RT the context is always with IRQs enabled. Ignore this warning on -RT. + +Signed-off-by: Thomas Gleixner +--- + block/blk-core.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/block/blk-core.c ++++ b/block/blk-core.c +@@ -194,7 +194,7 @@ EXPORT_SYMBOL(blk_delay_queue); + **/ + void blk_start_queue(struct request_queue *q) + { +- WARN_ON(!irqs_disabled()); ++ WARN_ON_NONRT(!irqs_disabled()); + + queue_flag_clear(QUEUE_FLAG_STOPPED, q); + __blk_run_queue(q); diff --git a/debian/patches/features/all/rt/fs-dcache-use-cpu-chill-in-trylock-loops.patch b/debian/patches/features/all/rt/fs-dcache-use-cpu-chill-in-trylock-loops.patch new file mode 100644 index 000000000..20dc5f94d --- /dev/null +++ b/debian/patches/features/all/rt/fs-dcache-use-cpu-chill-in-trylock-loops.patch @@ -0,0 +1,86 @@ +Subject: fs: dcache: Use cpu_chill() in trylock loops +From: Thomas Gleixner +Date: Wed, 07 Mar 2012 21:00:34 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Retry loops on RT might loop forever when the modifying side was +preempted. Use cpu_chill() instead of cpu_relax() to let the system +make progress. + +Signed-off-by: Thomas Gleixner + +--- + fs/autofs4/autofs_i.h | 1 + + fs/autofs4/expire.c | 2 +- + fs/dcache.c | 5 +++-- + fs/namespace.c | 3 ++- + 4 files changed, 7 insertions(+), 4 deletions(-) + +--- a/fs/autofs4/autofs_i.h ++++ b/fs/autofs4/autofs_i.h +@@ -34,6 +34,7 @@ + #include + #include + #include ++#include + #include + #include + +--- a/fs/autofs4/expire.c ++++ b/fs/autofs4/expire.c +@@ -150,7 +150,7 @@ static struct dentry *get_next_positive_ + parent = p->d_parent; + if (!spin_trylock(&parent->d_lock)) { + spin_unlock(&p->d_lock); +- cpu_relax(); ++ cpu_chill(); + goto relock; + } + spin_unlock(&p->d_lock); +--- a/fs/dcache.c ++++ b/fs/dcache.c +@@ -19,6 +19,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -589,7 +590,7 @@ static struct dentry *dentry_kill(struct + + failed: + spin_unlock(&dentry->d_lock); +- cpu_relax(); ++ cpu_chill(); + return dentry; /* try again with same dentry */ + } + +@@ -2392,7 +2393,7 @@ void d_delete(struct dentry * dentry) + if (dentry->d_lockref.count == 1) { + if (!spin_trylock(&inode->i_lock)) { + spin_unlock(&dentry->d_lock); +- cpu_relax(); ++ cpu_chill(); + goto again; + } + dentry->d_flags &= ~DCACHE_CANT_MOUNT; +--- a/fs/namespace.c ++++ b/fs/namespace.c +@@ -14,6 +14,7 @@ + #include + #include + #include ++#include + #include + #include + #include /* init_rootfs */ +@@ -355,7 +356,7 @@ int __mnt_want_write(struct vfsmount *m) + smp_mb(); + while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) { + preempt_enable(); +- cpu_relax(); ++ cpu_chill(); + preempt_disable(); + } + /* diff --git a/debian/patches/features/all/rt/fs-jbd-pull-plug-when-waiting-for-space.patch b/debian/patches/features/all/rt/fs-jbd-pull-plug-when-waiting-for-space.patch new file mode 100644 index 000000000..a7e25aa55 --- /dev/null +++ b/debian/patches/features/all/rt/fs-jbd-pull-plug-when-waiting-for-space.patch @@ -0,0 +1,30 @@ +From: Mike Galbraith +Date: Wed, 11 Jul 2012 22:05:20 +0000 +Subject: fs, jbd: pull your plug when waiting for space +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +With an -rt kernel, and a heavy sync IO load, tasks can jam +up on journal locks without unplugging, which can lead to +terminal IO starvation. Unplug and schedule when waiting for space. + +Signed-off-by: Mike Galbraith +Cc: Steven Rostedt +Cc: Theodore Tso +Link: http://lkml.kernel.org/r/1341812414.7370.73.camel@marge.simpson.net +Signed-off-by: Thomas Gleixner + +--- + fs/jbd/checkpoint.c | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/fs/jbd/checkpoint.c ++++ b/fs/jbd/checkpoint.c +@@ -129,6 +129,8 @@ void __log_wait_for_space(journal_t *jou + if (journal->j_flags & JFS_ABORT) + return; + spin_unlock(&journal->j_state_lock); ++ if (current->plug) ++ io_schedule(); + mutex_lock(&journal->j_checkpoint_mutex); + + /* diff --git a/debian/patches/features/all/rt/fs-jbd-replace-bh_state-lock.patch b/debian/patches/features/all/rt/fs-jbd-replace-bh_state-lock.patch new file mode 100644 index 000000000..b938fb867 --- /dev/null +++ b/debian/patches/features/all/rt/fs-jbd-replace-bh_state-lock.patch @@ -0,0 +1,101 @@ +From: Thomas Gleixner +Date: Fri, 18 Mar 2011 10:11:25 +0100 +Subject: fs: jbd/jbd2: Make state lock and journal head lock rt safe +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +bit_spin_locks break under RT. + +Based on a previous patch from Steven Rostedt +Signed-off-by: Thomas Gleixner + +-- + + include/linux/buffer_head.h | 10 ++++++++++ + include/linux/jbd_common.h | 24 ++++++++++++++++++++++++ + 2 files changed, 34 insertions(+) + +--- a/include/linux/buffer_head.h ++++ b/include/linux/buffer_head.h +@@ -77,6 +77,11 @@ struct buffer_head { + atomic_t b_count; /* users using this buffer_head */ + #ifdef CONFIG_PREEMPT_RT_BASE + spinlock_t b_uptodate_lock; ++#if defined(CONFIG_JBD) || defined(CONFIG_JBD_MODULE) || \ ++ defined(CONFIG_JBD2) || defined(CONFIG_JBD2_MODULE) ++ spinlock_t b_state_lock; ++ spinlock_t b_journal_head_lock; ++#endif + #endif + }; + +@@ -108,6 +113,11 @@ static inline void buffer_head_init_lock + { + #ifdef CONFIG_PREEMPT_RT_BASE + spin_lock_init(&bh->b_uptodate_lock); ++#if defined(CONFIG_JBD) || defined(CONFIG_JBD_MODULE) || \ ++ defined(CONFIG_JBD2) || defined(CONFIG_JBD2_MODULE) ++ spin_lock_init(&bh->b_state_lock); ++ spin_lock_init(&bh->b_journal_head_lock); ++#endif + #endif + } + +--- a/include/linux/jbd_common.h ++++ b/include/linux/jbd_common.h +@@ -15,32 +15,56 @@ static inline struct journal_head *bh2jh + + static inline void jbd_lock_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_lock(BH_State, &bh->b_state); ++#else ++ spin_lock(&bh->b_state_lock); ++#endif + } + + static inline int jbd_trylock_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + return bit_spin_trylock(BH_State, &bh->b_state); ++#else ++ return spin_trylock(&bh->b_state_lock); ++#endif + } + + static inline int jbd_is_locked_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + return bit_spin_is_locked(BH_State, &bh->b_state); ++#else ++ return spin_is_locked(&bh->b_state_lock); ++#endif + } + + static inline void jbd_unlock_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_unlock(BH_State, &bh->b_state); ++#else ++ spin_unlock(&bh->b_state_lock); ++#endif + } + + static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_lock(BH_JournalHead, &bh->b_state); ++#else ++ spin_lock(&bh->b_journal_head_lock); ++#endif + } + + static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_unlock(BH_JournalHead, &bh->b_state); ++#else ++ spin_unlock(&bh->b_journal_head_lock); ++#endif + } + + #endif diff --git a/debian/patches/features/all/rt/fs-jbd2-pull-your-plug-when-waiting-for-space.patch b/debian/patches/features/all/rt/fs-jbd2-pull-your-plug-when-waiting-for-space.patch new file mode 100644 index 000000000..1559284b0 --- /dev/null +++ b/debian/patches/features/all/rt/fs-jbd2-pull-your-plug-when-waiting-for-space.patch @@ -0,0 +1,32 @@ +From: Sebastian Andrzej Siewior +Date: Mon, 17 Feb 2014 17:30:03 +0100 +Subject: fs: jbd2: pull your plug when waiting for space +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Two cps in parallel managed to stall the the ext4 fs. It seems that +journal code is either waiting for locks or sleeping waiting for +something to happen. This seems similar to what Mike observed on ext3, +here is his description: + +|With an -rt kernel, and a heavy sync IO load, tasks can jam +|up on journal locks without unplugging, which can lead to +|terminal IO starvation. Unplug and schedule when waiting +|for space. + + +Signed-off-by: Sebastian Andrzej Siewior +--- + fs/jbd2/checkpoint.c | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/fs/jbd2/checkpoint.c ++++ b/fs/jbd2/checkpoint.c +@@ -116,6 +116,8 @@ void __jbd2_log_wait_for_space(journal_t + nblocks = jbd2_space_needed(journal); + while (jbd2_log_space_left(journal) < nblocks) { + write_unlock(&journal->j_state_lock); ++ if (current->plug) ++ io_schedule(); + mutex_lock(&journal->j_checkpoint_mutex); + + /* diff --git a/debian/patches/features/all/rt/fs-namespace-preemption-fix.patch b/debian/patches/features/all/rt/fs-namespace-preemption-fix.patch new file mode 100644 index 000000000..bcf00cc81 --- /dev/null +++ b/debian/patches/features/all/rt/fs-namespace-preemption-fix.patch @@ -0,0 +1,31 @@ +From: Thomas Gleixner +Date: Sun, 19 Jul 2009 08:44:27 -0500 +Subject: fs: namespace preemption fix +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +On RT we cannot loop with preemption disabled here as +mnt_make_readonly() might have been preempted. We can safely enable +preemption while waiting for MNT_WRITE_HOLD to be cleared. Safe on !RT +as well. + +Signed-off-by: Thomas Gleixner + +--- + fs/namespace.c | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +--- a/fs/namespace.c ++++ b/fs/namespace.c +@@ -353,8 +353,11 @@ int __mnt_want_write(struct vfsmount *m) + * incremented count after it has set MNT_WRITE_HOLD. + */ + smp_mb(); +- while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) ++ while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) { ++ preempt_enable(); + cpu_relax(); ++ preempt_disable(); ++ } + /* + * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will + * be set to match its requirements. So we must not load that until diff --git a/debian/patches/features/all/rt/fs-ntfs-disable-interrupt-non-rt.patch b/debian/patches/features/all/rt/fs-ntfs-disable-interrupt-non-rt.patch new file mode 100644 index 000000000..62ec7ff06 --- /dev/null +++ b/debian/patches/features/all/rt/fs-ntfs-disable-interrupt-non-rt.patch @@ -0,0 +1,60 @@ +From: Mike Galbraith +Date: Fri, 3 Jul 2009 08:44:12 -0500 +Subject: fs: ntfs: disable interrupt only on !RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +On Sat, 2007-10-27 at 11:44 +0200, Ingo Molnar wrote: +> * Nick Piggin wrote: +> +> > > [10138.175796] [] show_trace+0x12/0x14 +> > > [10138.180291] [] dump_stack+0x16/0x18 +> > > [10138.184769] [] native_smp_call_function_mask+0x138/0x13d +> > > [10138.191117] [] smp_call_function+0x1e/0x24 +> > > [10138.196210] [] on_each_cpu+0x25/0x50 +> > > [10138.200807] [] flush_tlb_all+0x1e/0x20 +> > > [10138.205553] [] kmap_high+0x1b6/0x417 +> > > [10138.210118] [] kmap+0x4d/0x4f +> > > [10138.214102] [] ntfs_end_buffer_async_read+0x228/0x2f9 +> > > [10138.220163] [] end_bio_bh_io_sync+0x26/0x3f +> > > [10138.225352] [] bio_endio+0x42/0x6d +> > > [10138.229769] [] __end_that_request_first+0x115/0x4ac +> > > [10138.235682] [] end_that_request_chunk+0x8/0xa +> > > [10138.241052] [] ide_end_request+0x55/0x10a +> > > [10138.246058] [] ide_dma_intr+0x6f/0xac +> > > [10138.250727] [] ide_intr+0x93/0x1e0 +> > > [10138.255125] [] handle_IRQ_event+0x5c/0xc9 +> > +> > Looks like ntfs is kmap()ing from interrupt context. Should be using +> > kmap_atomic instead, I think. +> +> it's not atomic interrupt context but irq thread context - and -rt +> remaps kmap_atomic() to kmap() internally. + +Hm. Looking at the change to mm/bounce.c, perhaps I should do this +instead? + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + fs/ntfs/aops.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/fs/ntfs/aops.c ++++ b/fs/ntfs/aops.c +@@ -143,13 +143,13 @@ static void ntfs_end_buffer_async_read(s + recs = PAGE_CACHE_SIZE / rec_size; + /* Should have been verified before we got here... */ + BUG_ON(!recs); +- local_irq_save(flags); ++ local_irq_save_nort(flags); + kaddr = kmap_atomic(page); + for (i = 0; i < recs; i++) + post_read_mst_fixup((NTFS_RECORD*)(kaddr + + i * rec_size), rec_size); + kunmap_atomic(kaddr); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + flush_dcache_page(page); + if (likely(page_uptodate && !PageError(page))) + SetPageUptodate(page); diff --git a/debian/patches/features/all/rt/fs-replace-bh_uptodate_lock-for-rt.patch b/debian/patches/features/all/rt/fs-replace-bh_uptodate_lock-for-rt.patch new file mode 100644 index 000000000..28a032cb6 --- /dev/null +++ b/debian/patches/features/all/rt/fs-replace-bh_uptodate_lock-for-rt.patch @@ -0,0 +1,162 @@ +From: Thomas Gleixner +Date: Fri, 18 Mar 2011 09:18:52 +0100 +Subject: buffer_head: Replace bh_uptodate_lock for -rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Wrap the bit_spin_lock calls into a separate inline and add the RT +replacements with a real spinlock. + +Signed-off-by: Thomas Gleixner +--- + fs/buffer.c | 21 +++++++-------------- + fs/ntfs/aops.c | 10 +++------- + include/linux/buffer_head.h | 34 ++++++++++++++++++++++++++++++++++ + 3 files changed, 44 insertions(+), 21 deletions(-) + +--- a/fs/buffer.c ++++ b/fs/buffer.c +@@ -301,8 +301,7 @@ static void end_buffer_async_read(struct + * decide that the page is now completely done. + */ + first = page_buffers(page); +- local_irq_save(flags); +- bit_spin_lock(BH_Uptodate_Lock, &first->b_state); ++ flags = bh_uptodate_lock_irqsave(first); + clear_buffer_async_read(bh); + unlock_buffer(bh); + tmp = bh; +@@ -315,8 +314,7 @@ static void end_buffer_async_read(struct + } + tmp = tmp->b_this_page; + } while (tmp != bh); +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); ++ bh_uptodate_unlock_irqrestore(first, flags); + + /* + * If none of the buffers had errors and they are all +@@ -328,9 +326,7 @@ static void end_buffer_async_read(struct + return; + + still_busy: +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); +- return; ++ bh_uptodate_unlock_irqrestore(first, flags); + } + + /* +@@ -358,8 +354,7 @@ void end_buffer_async_write(struct buffe + } + + first = page_buffers(page); +- local_irq_save(flags); +- bit_spin_lock(BH_Uptodate_Lock, &first->b_state); ++ flags = bh_uptodate_lock_irqsave(first); + + clear_buffer_async_write(bh); + unlock_buffer(bh); +@@ -371,15 +366,12 @@ void end_buffer_async_write(struct buffe + } + tmp = tmp->b_this_page; + } +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); ++ bh_uptodate_unlock_irqrestore(first, flags); + end_page_writeback(page); + return; + + still_busy: +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); +- return; ++ bh_uptodate_unlock_irqrestore(first, flags); + } + EXPORT_SYMBOL(end_buffer_async_write); + +@@ -3325,6 +3317,7 @@ struct buffer_head *alloc_buffer_head(gf + struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); + if (ret) { + INIT_LIST_HEAD(&ret->b_assoc_buffers); ++ buffer_head_init_locks(ret); + preempt_disable(); + __this_cpu_inc(bh_accounting.nr); + recalc_bh_state(); +--- a/fs/ntfs/aops.c ++++ b/fs/ntfs/aops.c +@@ -107,8 +107,7 @@ static void ntfs_end_buffer_async_read(s + "0x%llx.", (unsigned long long)bh->b_blocknr); + } + first = page_buffers(page); +- local_irq_save(flags); +- bit_spin_lock(BH_Uptodate_Lock, &first->b_state); ++ flags = bh_uptodate_lock_irqsave(first); + clear_buffer_async_read(bh); + unlock_buffer(bh); + tmp = bh; +@@ -123,8 +122,7 @@ static void ntfs_end_buffer_async_read(s + } + tmp = tmp->b_this_page; + } while (tmp != bh); +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); ++ bh_uptodate_unlock_irqrestore(first, flags); + /* + * If none of the buffers had errors then we can set the page uptodate, + * but we first have to perform the post read mst fixups, if the +@@ -159,9 +157,7 @@ static void ntfs_end_buffer_async_read(s + unlock_page(page); + return; + still_busy: +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); +- return; ++ bh_uptodate_unlock_irqrestore(first, flags); + } + + /** +--- a/include/linux/buffer_head.h ++++ b/include/linux/buffer_head.h +@@ -75,8 +75,42 @@ struct buffer_head { + struct address_space *b_assoc_map; /* mapping this buffer is + associated with */ + atomic_t b_count; /* users using this buffer_head */ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ spinlock_t b_uptodate_lock; ++#endif + }; + ++static inline unsigned long bh_uptodate_lock_irqsave(struct buffer_head *bh) ++{ ++ unsigned long flags; ++ ++#ifndef CONFIG_PREEMPT_RT_BASE ++ local_irq_save(flags); ++ bit_spin_lock(BH_Uptodate_Lock, &bh->b_state); ++#else ++ spin_lock_irqsave(&bh->b_uptodate_lock, flags); ++#endif ++ return flags; ++} ++ ++static inline void ++bh_uptodate_unlock_irqrestore(struct buffer_head *bh, unsigned long flags) ++{ ++#ifndef CONFIG_PREEMPT_RT_BASE ++ bit_spin_unlock(BH_Uptodate_Lock, &bh->b_state); ++ local_irq_restore(flags); ++#else ++ spin_unlock_irqrestore(&bh->b_uptodate_lock, flags); ++#endif ++} ++ ++static inline void buffer_head_init_locks(struct buffer_head *bh) ++{ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ spin_lock_init(&bh->b_uptodate_lock); ++#endif ++} ++ + /* + * macro tricks to expand the set_buffer_foo(), clear_buffer_foo() + * and buffer_foo() functions. diff --git a/debian/patches/features/all/rt/ftrace-migrate-disable-tracing.patch b/debian/patches/features/all/rt/ftrace-migrate-disable-tracing.patch new file mode 100644 index 000000000..c18152b62 --- /dev/null +++ b/debian/patches/features/all/rt/ftrace-migrate-disable-tracing.patch @@ -0,0 +1,74 @@ +From: Thomas Gleixner +Date: Sun, 17 Jul 2011 21:56:42 +0200 +Subject: trace: Add migrate-disabled counter to tracing output +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Signed-off-by: Thomas Gleixner +--- + include/linux/ftrace_event.h | 2 ++ + kernel/trace/trace.c | 9 ++++++--- + kernel/trace/trace_events.c | 2 ++ + kernel/trace/trace_output.c | 5 +++++ + 4 files changed, 15 insertions(+), 3 deletions(-) + +--- a/include/linux/ftrace_event.h ++++ b/include/linux/ftrace_event.h +@@ -66,6 +66,8 @@ struct trace_entry { + unsigned char flags; + unsigned char preempt_count; + int pid; ++ unsigned short migrate_disable; ++ unsigned short padding; + }; + + #define FTRACE_MAX_EVENT \ +--- a/kernel/trace/trace.c ++++ b/kernel/trace/trace.c +@@ -1641,6 +1641,8 @@ tracing_generic_entry_update(struct trac + ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | + (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) | + (test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0); ++ ++ entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 0; + } + EXPORT_SYMBOL_GPL(tracing_generic_entry_update); + +@@ -2563,9 +2565,10 @@ static void print_lat_help_header(struct + "# | / _----=> need-resched \n" + "# || / _---=> hardirq/softirq \n" + "# ||| / _--=> preempt-depth \n" +- "# |||| / delay \n" +- "# cmd pid ||||| time | caller \n" +- "# \\ / ||||| \\ | / \n"); ++ "# |||| / _--=> migrate-disable\n" ++ "# ||||| / delay \n" ++ "# cmd pid |||||| time | caller \n" ++ "# \\ / ||||| \\ | / \n"); + } + + static void print_event_info(struct trace_buffer *buf, struct seq_file *m) +--- a/kernel/trace/trace_events.c ++++ b/kernel/trace/trace_events.c +@@ -162,6 +162,8 @@ static int trace_define_common_fields(vo + __common_field(unsigned char, flags); + __common_field(unsigned char, preempt_count); + __common_field(int, pid); ++ __common_field(unsigned short, migrate_disable); ++ __common_field(unsigned short, padding); + + return ret; + } +--- a/kernel/trace/trace_output.c ++++ b/kernel/trace/trace_output.c +@@ -472,6 +472,11 @@ int trace_print_lat_fmt(struct trace_seq + else + trace_seq_putc(s, '.'); + ++ if (entry->migrate_disable) ++ trace_seq_printf(s, "%x", entry->migrate_disable); ++ else ++ trace_seq_putc(s, '.'); ++ + return !trace_seq_has_overflowed(s); + } + diff --git a/debian/patches/features/all/rt/futex-avoid-double-wake-up-in-PI-futex-wait-wake-on-.patch b/debian/patches/features/all/rt/futex-avoid-double-wake-up-in-PI-futex-wait-wake-on-.patch new file mode 100644 index 000000000..79b45a0df --- /dev/null +++ b/debian/patches/features/all/rt/futex-avoid-double-wake-up-in-PI-futex-wait-wake-on-.patch @@ -0,0 +1,224 @@ +From: Thomas Gleixner +Date: Wed, 18 Feb 2015 20:17:31 +0100 +Subject: futex: avoid double wake up in PI futex wait / wake on -RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The boosted priority is reverted after the unlock but before the +futex_hash_bucket (hb) has been accessed. The result is that we boost the +task, deboost the task, boost again for the hb lock, deboost again. +A sched trace of this scenario looks the following: + +| med_prio-93 sched_wakeup: comm=high_prio pid=92 prio=9 success=1 target_cpu=000 +| med_prio-93 sched_switch: prev_comm=med_prio prev_pid=93 prev_prio=29 prev_state=R ==> next_comm=high_prio next_pid=92 next_prio=9 +|high_prio-92 sched_pi_setprio: comm=low_prio pid=91 oldprio=120 newprio=9 +|high_prio-92 sched_switch: prev_comm=high_prio prev_pid=92 prev_prio=9 prev_state=S ==> next_comm=low_prio next_pid=91 next_prio=9 +| low_prio-91 sched_wakeup: comm=high_prio pid=92 prio=9 success=1 target_cpu=000 +| low_prio-91 sched_pi_setprio: comm=low_prio pid=91 oldprio=9 newprio=120 +| low_prio-91 sched_switch: prev_comm=low_prio prev_pid=91 prev_prio=120 prev_state=R+ ==> next_comm=high_prio next_pid=92 next_prio=9 +|high_prio-92 sched_pi_setprio: comm=low_prio pid=91 oldprio=120 newprio=9 +|high_prio-92 sched_switch: prev_comm=high_prio prev_pid=92 prev_prio=9 prev_state=D ==> next_comm=low_prio next_pid=91 next_prio=9 +| low_prio-91 sched_wakeup: comm=high_prio pid=92 prio=9 success=1 target_cpu=000 +| low_prio-91 sched_pi_setprio: comm=low_prio pid=91 oldprio=9 newprio=120 +| low_prio-91 sched_switch: prev_comm=low_prio prev_pid=91 prev_prio=120 prev_state=R+ ==> next_comm=high_prio next_pid=92 next_prio=9 + +We see four sched_pi_setprio() invocation but ideally two would be enough. +The patch tries to avoid the double wakeup by a wake up once the hb lock is +released. The same test case: + +| med_prio-21 sched_wakeup: comm=high_prio pid=20 prio=9 success=1 target_cpu=000 +| med_prio-21 sched_switch: prev_comm=med_prio prev_pid=21 prev_prio=29 prev_state=R ==> next_comm=high_prio next_pid=20 next_prio=9 +|high_prio-20 sched_pi_setprio: comm=low_prio pid=19 oldprio=120 newprio=9 +|high_prio-20 sched_switch: prev_comm=high_prio prev_pid=20 prev_prio=9 prev_state=S ==> next_comm=low_prio next_pid=19 next_prio=9 +| low_prio-19 sched_wakeup: comm=high_prio pid=20 prio=9 success=1 target_cpu=000 +| low_prio-19 sched_pi_setprio: comm=low_prio pid=19 oldprio=9 newprio=120 +| low_prio-19 sched_switch: prev_comm=low_prio prev_pid=19 prev_prio=120 prev_state=R+ ==> next_comm=high_prio next_pid=20 next_prio=9 + +only two sched_pi_setprio() invocations as one would expect and see +without -RT. + +Signed-off-by: Thomas Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/futex.c | 32 +++++++++++++++++++++++++++++--- + kernel/locking/rtmutex.c | 40 +++++++++++++++++++++++++++++----------- + kernel/locking/rtmutex_common.h | 4 ++++ + 3 files changed, 62 insertions(+), 14 deletions(-) + +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -1117,11 +1117,13 @@ static void mark_wake_futex(struct wake_ + q->lock_ptr = NULL; + } + +-static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) ++static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this, ++ struct futex_hash_bucket *hb) + { + struct task_struct *new_owner; + struct futex_pi_state *pi_state = this->pi_state; + u32 uninitialized_var(curval), newval; ++ bool deboost; + int ret = 0; + + if (!pi_state) +@@ -1173,7 +1175,17 @@ static int wake_futex_pi(u32 __user *uad + raw_spin_unlock_irq(&new_owner->pi_lock); + + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); +- rt_mutex_unlock(&pi_state->pi_mutex); ++ ++ deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex); ++ ++ /* ++ * We deboost after dropping hb->lock. That prevents a double ++ * wakeup on RT. ++ */ ++ spin_unlock(&hb->lock); ++ ++ if (deboost) ++ rt_mutex_adjust_prio(current); + + return 0; + } +@@ -2413,13 +2425,26 @@ static int futex_unlock_pi(u32 __user *u + */ + match = futex_top_waiter(hb, &key); + if (match) { +- ret = wake_futex_pi(uaddr, uval, match); ++ ret = wake_futex_pi(uaddr, uval, match, hb); ++ ++ /* ++ * In case of success wake_futex_pi dropped the hash ++ * bucket lock. ++ */ ++ if (!ret) ++ goto out_putkey; ++ + /* + * The atomic access to the futex value generated a + * pagefault, so retry the user-access and the wakeup: + */ + if (ret == -EFAULT) + goto pi_faulted; ++ ++ /* ++ * wake_futex_pi has detected invalid state. Tell user ++ * space. ++ */ + goto out_unlock; + } + +@@ -2440,6 +2465,7 @@ static int futex_unlock_pi(u32 __user *u + + out_unlock: + spin_unlock(&hb->lock); ++out_putkey: + put_futex_key(&key); + return ret; + +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -300,7 +300,7 @@ static void __rt_mutex_adjust_prio(struc + * of task. We do not use the spin_xx_mutex() variants here as we are + * outside of the debug path.) + */ +-static void rt_mutex_adjust_prio(struct task_struct *task) ++void rt_mutex_adjust_prio(struct task_struct *task) + { + unsigned long flags; + +@@ -957,8 +957,9 @@ static int task_blocks_on_rt_mutex(struc + /* + * Wake up the next waiter on the lock. + * +- * Remove the top waiter from the current tasks pi waiter list and +- * wake it up. ++ * Remove the top waiter from the current tasks pi waiter list, ++ * wake it up and return whether the current task needs to undo ++ * a potential priority boosting. + * + * Called with lock->wait_lock held. + */ +@@ -1255,7 +1256,7 @@ static inline int rt_mutex_slowtrylock(s + /* + * Slow path to release a rt-mutex: + */ +-static void __sched ++static bool __sched + rt_mutex_slowunlock(struct rt_mutex *lock) + { + raw_spin_lock(&lock->wait_lock); +@@ -1298,7 +1299,7 @@ rt_mutex_slowunlock(struct rt_mutex *loc + while (!rt_mutex_has_waiters(lock)) { + /* Drops lock->wait_lock ! */ + if (unlock_rt_mutex_safe(lock) == true) +- return; ++ return false; + /* Relock the rtmutex and try again */ + raw_spin_lock(&lock->wait_lock); + } +@@ -1311,8 +1312,7 @@ rt_mutex_slowunlock(struct rt_mutex *loc + + raw_spin_unlock(&lock->wait_lock); + +- /* Undo pi boosting if necessary: */ +- rt_mutex_adjust_prio(current); ++ return true; + } + + /* +@@ -1363,12 +1363,14 @@ rt_mutex_fasttrylock(struct rt_mutex *lo + + static inline void + rt_mutex_fastunlock(struct rt_mutex *lock, +- void (*slowfn)(struct rt_mutex *lock)) ++ bool (*slowfn)(struct rt_mutex *lock)) + { +- if (likely(rt_mutex_cmpxchg(lock, current, NULL))) ++ if (likely(rt_mutex_cmpxchg(lock, current, NULL))) { + rt_mutex_deadlock_account_unlock(current); +- else +- slowfn(lock); ++ } else if (slowfn(lock)) { ++ /* Undo pi boosting if necessary: */ ++ rt_mutex_adjust_prio(current); ++ } + } + + /** +@@ -1463,6 +1465,22 @@ void __sched rt_mutex_unlock(struct rt_m + EXPORT_SYMBOL_GPL(rt_mutex_unlock); + + /** ++ * rt_mutex_futex_unlock - Futex variant of rt_mutex_unlock ++ * @lock: the rt_mutex to be unlocked ++ * ++ * Returns: true/false indicating whether priority adjustment is ++ * required or not. ++ */ ++bool __sched rt_mutex_futex_unlock(struct rt_mutex *lock) ++{ ++ if (likely(rt_mutex_cmpxchg(lock, current, NULL))) { ++ rt_mutex_deadlock_account_unlock(current); ++ return false; ++ } ++ return rt_mutex_slowunlock(lock); ++} ++ ++/** + * rt_mutex_destroy - mark a mutex unusable + * @lock: the mutex to be destroyed + * +--- a/kernel/locking/rtmutex_common.h ++++ b/kernel/locking/rtmutex_common.h +@@ -132,6 +132,10 @@ extern int rt_mutex_finish_proxy_lock(st + struct rt_mutex_waiter *waiter); + extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to); + ++extern bool rt_mutex_futex_unlock(struct rt_mutex *lock); ++ ++extern void rt_mutex_adjust_prio(struct task_struct *task); ++ + #ifdef CONFIG_DEBUG_RT_MUTEXES + # include "rtmutex-debug.h" + #else diff --git a/debian/patches/features/all/rt/futex-requeue-pi-fix.patch b/debian/patches/features/all/rt/futex-requeue-pi-fix.patch new file mode 100644 index 000000000..f9bbe813e --- /dev/null +++ b/debian/patches/features/all/rt/futex-requeue-pi-fix.patch @@ -0,0 +1,114 @@ +From: Steven Rostedt +Date: Tue, 14 Jul 2015 14:26:34 +0200 +Subject: futex: Fix bug on when a requeued RT task times out +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Requeue with timeout causes a bug with PREEMPT_RT_FULL. + +The bug comes from a timed out condition. + + + TASK 1 TASK 2 + ------ ------ + futex_wait_requeue_pi() + futex_wait_queue_me() + + + double_lock_hb(); + + raw_spin_lock(pi_lock); + if (current->pi_blocked_on) { + } else { + current->pi_blocked_on = PI_WAKE_INPROGRESS; + run_spin_unlock(pi_lock); + spin_lock(hb->lock); <-- blocked! + + + plist_for_each_entry_safe(this) { + rt_mutex_start_proxy_lock(); + task_blocks_on_rt_mutex(); + BUG_ON(task->pi_blocked_on)!!!! + +The BUG_ON() actually has a check for PI_WAKE_INPROGRESS, but the +problem is that, after TASK 1 sets PI_WAKE_INPROGRESS, it then tries to +grab the hb->lock, which it fails to do so. As the hb->lock is a mutex, +it will block and set the "pi_blocked_on" to the hb->lock. + +When TASK 2 goes to requeue it, the check for PI_WAKE_INPROGESS fails +because the task1's pi_blocked_on is no longer set to that, but instead, +set to the hb->lock. + +The fix: + +When calling rt_mutex_start_proxy_lock() a check is made to see +if the proxy tasks pi_blocked_on is set. If so, exit out early. +Otherwise set it to a new flag PI_REQUEUE_INPROGRESS, which notifies +the proxy task that it is being requeued, and will handle things +appropriately. + + +Signed-off-by: Steven Rostedt +Signed-off-by: Thomas Gleixner +--- + kernel/locking/rtmutex.c | 32 +++++++++++++++++++++++++++++++- + kernel/locking/rtmutex_common.h | 1 + + 2 files changed, 32 insertions(+), 1 deletion(-) + +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -71,7 +71,8 @@ static void fixup_rt_mutex_waiters(struc + + static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter) + { +- return waiter && waiter != PI_WAKEUP_INPROGRESS; ++ return waiter && waiter != PI_WAKEUP_INPROGRESS && ++ waiter != PI_REQUEUE_INPROGRESS; + } + + /* +@@ -1603,6 +1604,35 @@ int rt_mutex_start_proxy_lock(struct rt_ + return 1; + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* ++ * In PREEMPT_RT there's an added race. ++ * If the task, that we are about to requeue, times out, ++ * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue ++ * to skip this task. But right after the task sets ++ * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then ++ * block on the spin_lock(&hb->lock), which in RT is an rtmutex. ++ * This will replace the PI_WAKEUP_INPROGRESS with the actual ++ * lock that it blocks on. We *must not* place this task ++ * on this proxy lock in that case. ++ * ++ * To prevent this race, we first take the task's pi_lock ++ * and check if it has updated its pi_blocked_on. If it has, ++ * we assume that it woke up and we return -EAGAIN. ++ * Otherwise, we set the task's pi_blocked_on to ++ * PI_REQUEUE_INPROGRESS, so that if the task is waking up ++ * it will know that we are in the process of requeuing it. ++ */ ++ raw_spin_lock_irq(&task->pi_lock); ++ if (task->pi_blocked_on) { ++ raw_spin_unlock_irq(&task->pi_lock); ++ raw_spin_unlock(&lock->wait_lock); ++ return -EAGAIN; ++ } ++ task->pi_blocked_on = PI_REQUEUE_INPROGRESS; ++ raw_spin_unlock_irq(&task->pi_lock); ++#endif ++ + /* We enforce deadlock detection for futexes */ + ret = task_blocks_on_rt_mutex(lock, waiter, task, + RT_MUTEX_FULL_CHAINWALK); +--- a/kernel/locking/rtmutex_common.h ++++ b/kernel/locking/rtmutex_common.h +@@ -120,6 +120,7 @@ enum rtmutex_chainwalk { + * PI-futex support (proxy locking functions, etc.): + */ + #define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1) ++#define PI_REQUEUE_INPROGRESS ((struct rt_mutex_waiter *) 2) + + extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); + extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, diff --git a/debian/patches/features/all/rt/genirq-disable-irqpoll-on-rt.patch b/debian/patches/features/all/rt/genirq-disable-irqpoll-on-rt.patch new file mode 100644 index 000000000..d7e1f9201 --- /dev/null +++ b/debian/patches/features/all/rt/genirq-disable-irqpoll-on-rt.patch @@ -0,0 +1,38 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:29:57 -0500 +Subject: genirq: Disable irqpoll on -rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Creates long latencies for no value + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + kernel/irq/spurious.c | 8 ++++++++ + 1 file changed, 8 insertions(+) + +--- a/kernel/irq/spurious.c ++++ b/kernel/irq/spurious.c +@@ -444,6 +444,10 @@ MODULE_PARM_DESC(noirqdebug, "Disable ir + + static int __init irqfixup_setup(char *str) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ pr_warn("irqfixup boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n"); ++ return 1; ++#endif + irqfixup = 1; + printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n"); + printk(KERN_WARNING "This may impact system performance.\n"); +@@ -456,6 +460,10 @@ module_param(irqfixup, int, 0644); + + static int __init irqpoll_setup(char *str) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ pr_warn("irqpoll boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n"); ++ return 1; ++#endif + irqfixup = 2; + printk(KERN_WARNING "Misrouted IRQ fixup and polling support " + "enabled\n"); diff --git a/debian/patches/features/all/rt/genirq-do-not-invoke-the-affinity-callback-via-a-wor.patch b/debian/patches/features/all/rt/genirq-do-not-invoke-the-affinity-callback-via-a-wor.patch new file mode 100644 index 000000000..307c72feb --- /dev/null +++ b/debian/patches/features/all/rt/genirq-do-not-invoke-the-affinity-callback-via-a-wor.patch @@ -0,0 +1,145 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 21 Aug 2013 17:48:46 +0200 +Subject: genirq: Do not invoke the affinity callback via a workqueue on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Joe Korty reported, that __irq_set_affinity_locked() schedules a +workqueue while holding a rawlock which results in a might_sleep() +warning. +This patch moves the invokation into a process context so that we only +wakeup() a process while holding the lock. + +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/interrupt.h | 1 + kernel/irq/manage.c | 79 ++++++++++++++++++++++++++++++++++++++++++++-- + 2 files changed, 77 insertions(+), 3 deletions(-) + +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -215,6 +215,7 @@ struct irq_affinity_notify { + unsigned int irq; + struct kref kref; + struct work_struct work; ++ struct list_head list; + void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask); + void (*release)(struct kref *ref); + }; +--- a/kernel/irq/manage.c ++++ b/kernel/irq/manage.c +@@ -181,6 +181,62 @@ static inline void + irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { } + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void _irq_affinity_notify(struct irq_affinity_notify *notify); ++static struct task_struct *set_affinity_helper; ++static LIST_HEAD(affinity_list); ++static DEFINE_RAW_SPINLOCK(affinity_list_lock); ++ ++static int set_affinity_thread(void *unused) ++{ ++ while (1) { ++ struct irq_affinity_notify *notify; ++ int empty; ++ ++ set_current_state(TASK_INTERRUPTIBLE); ++ ++ raw_spin_lock_irq(&affinity_list_lock); ++ empty = list_empty(&affinity_list); ++ raw_spin_unlock_irq(&affinity_list_lock); ++ ++ if (empty) ++ schedule(); ++ if (kthread_should_stop()) ++ break; ++ set_current_state(TASK_RUNNING); ++try_next: ++ notify = NULL; ++ ++ raw_spin_lock_irq(&affinity_list_lock); ++ if (!list_empty(&affinity_list)) { ++ notify = list_first_entry(&affinity_list, ++ struct irq_affinity_notify, list); ++ list_del_init(¬ify->list); ++ } ++ raw_spin_unlock_irq(&affinity_list_lock); ++ ++ if (!notify) ++ continue; ++ _irq_affinity_notify(notify); ++ goto try_next; ++ } ++ return 0; ++} ++ ++static void init_helper_thread(void) ++{ ++ if (set_affinity_helper) ++ return; ++ set_affinity_helper = kthread_run(set_affinity_thread, NULL, ++ "affinity-cb"); ++ WARN_ON(IS_ERR(set_affinity_helper)); ++} ++#else ++ ++static inline void init_helper_thread(void) { } ++ ++#endif ++ + int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, + bool force) + { +@@ -220,7 +276,17 @@ int irq_set_affinity_locked(struct irq_d + + if (desc->affinity_notify) { + kref_get(&desc->affinity_notify->kref); ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ raw_spin_lock(&affinity_list_lock); ++ if (list_empty(&desc->affinity_notify->list)) ++ list_add_tail(&affinity_list, ++ &desc->affinity_notify->list); ++ raw_spin_unlock(&affinity_list_lock); ++ wake_up_process(set_affinity_helper); ++#else + schedule_work(&desc->affinity_notify->work); ++#endif + } + irqd_set(data, IRQD_AFFINITY_SET); + +@@ -258,10 +324,8 @@ int irq_set_affinity_hint(unsigned int i + } + EXPORT_SYMBOL_GPL(irq_set_affinity_hint); + +-static void irq_affinity_notify(struct work_struct *work) ++static void _irq_affinity_notify(struct irq_affinity_notify *notify) + { +- struct irq_affinity_notify *notify = +- container_of(work, struct irq_affinity_notify, work); + struct irq_desc *desc = irq_to_desc(notify->irq); + cpumask_var_t cpumask; + unsigned long flags; +@@ -283,6 +347,13 @@ static void irq_affinity_notify(struct w + kref_put(¬ify->kref, notify->release); + } + ++static void irq_affinity_notify(struct work_struct *work) ++{ ++ struct irq_affinity_notify *notify = ++ container_of(work, struct irq_affinity_notify, work); ++ _irq_affinity_notify(notify); ++} ++ + /** + * irq_set_affinity_notifier - control notification of IRQ affinity changes + * @irq: Interrupt for which to enable/disable notification +@@ -312,6 +383,8 @@ irq_set_affinity_notifier(unsigned int i + notify->irq = irq; + kref_init(¬ify->kref); + INIT_WORK(¬ify->work, irq_affinity_notify); ++ INIT_LIST_HEAD(¬ify->list); ++ init_helper_thread(); + } + + raw_spin_lock_irqsave(&desc->lock, flags); diff --git a/debian/patches/features/all/rt/genirq-force-threading.patch b/debian/patches/features/all/rt/genirq-force-threading.patch new file mode 100644 index 000000000..c72244cc2 --- /dev/null +++ b/debian/patches/features/all/rt/genirq-force-threading.patch @@ -0,0 +1,49 @@ +Subject: genirq: Force interrupt thread on RT +From: Thomas Gleixner +Date: Sun, 03 Apr 2011 11:57:29 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Force threaded_irqs and optimize the code (force_irqthreads) in regard +to this. + +Signed-off-by: Thomas Gleixner +--- + include/linux/interrupt.h | 6 +++++- + kernel/irq/manage.c | 2 ++ + 2 files changed, 7 insertions(+), 1 deletion(-) + +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -377,9 +377,13 @@ extern int irq_set_irqchip_state(unsigne + bool state); + + #ifdef CONFIG_IRQ_FORCED_THREADING ++# ifndef CONFIG_PREEMPT_RT_BASE + extern bool force_irqthreads; ++# else ++# define force_irqthreads (true) ++# endif + #else +-#define force_irqthreads (0) ++#define force_irqthreads (false) + #endif + + #ifndef __ARCH_SET_SOFTIRQ_PENDING +--- a/kernel/irq/manage.c ++++ b/kernel/irq/manage.c +@@ -22,6 +22,7 @@ + #include "internals.h" + + #ifdef CONFIG_IRQ_FORCED_THREADING ++# ifndef CONFIG_PREEMPT_RT_BASE + __read_mostly bool force_irqthreads; + + static int __init setup_forced_irqthreads(char *arg) +@@ -30,6 +31,7 @@ static int __init setup_forced_irqthread + return 0; + } + early_param("threadirqs", setup_forced_irqthreads); ++# endif + #endif + + static void __synchronize_hardirq(struct irq_desc *desc) diff --git a/debian/patches/features/all/rt/gpio-omap-use-raw-locks-for-locking.patch b/debian/patches/features/all/rt/gpio-omap-use-raw-locks-for-locking.patch new file mode 100644 index 000000000..7f3cf6eef --- /dev/null +++ b/debian/patches/features/all/rt/gpio-omap-use-raw-locks-for-locking.patch @@ -0,0 +1,317 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 12 Feb 2015 16:01:13 +0100 +Subject: gpio: omap: use raw locks for locking +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +This patch converts gpio_bank.lock from a spin_lock into a +raw_spin_lock. The call path is to access this lock is always under a +raw_spin_lock, for instance +- __setup_irq() holds &desc->lock with irq off + + __irq_set_trigger() + + omap_gpio_irq_type() + +- handle_level_irq() (runs with irqs off therefore raw locks) + + mask_ack_irq() + + omap_gpio_mask_irq() + +This fixes the obvious backtrace on -RT. However the locking vs context +is not and this is not limited to -RT: +- omap_gpio_irq_type() is called with IRQ off and has an conditional + call to pm_runtime_get_sync() which may sleep. Either it may happen or + it may not happen but pm_runtime_get_sync() should not be called with + irqs off. + +- omap_gpio_debounce() is holding the lock with IRQs off. + + omap2_set_gpio_debounce() + + clk_prepare_enable() + + clk_prepare() this one might sleep. + The number of users of gpiod_set_debounce() / gpio_set_debounce() + looks low but still this is not good. + +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/gpio/gpio-omap.c | 78 +++++++++++++++++++++++------------------------ + 1 file changed, 39 insertions(+), 39 deletions(-) + +--- a/drivers/gpio/gpio-omap.c ++++ b/drivers/gpio/gpio-omap.c +@@ -57,7 +57,7 @@ struct gpio_bank { + u32 saved_datain; + u32 level_mask; + u32 toggle_mask; +- spinlock_t lock; ++ raw_spinlock_t lock; + struct gpio_chip chip; + struct clk *dbck; + u32 mod_usage; +@@ -498,14 +498,14 @@ static int omap_gpio_irq_type(struct irq + (type & (IRQ_TYPE_LEVEL_LOW|IRQ_TYPE_LEVEL_HIGH))) + return -EINVAL; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + retval = omap_set_gpio_triggering(bank, offset, type); + omap_gpio_init_irq(bank, offset); + if (!omap_gpio_is_input(bank, offset)) { +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + return -EINVAL; + } +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH)) + __irq_set_handler_locked(d->irq, handle_level_irq); +@@ -626,14 +626,14 @@ static int omap_set_gpio_wakeup(struct g + return -EINVAL; + } + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + if (enable) + bank->context.wake_en |= gpio_bit; + else + bank->context.wake_en &= ~gpio_bit; + + writel_relaxed(bank->context.wake_en, bank->base + bank->regs->wkup_en); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +@@ -668,7 +668,7 @@ static int omap_gpio_request(struct gpio + if (!BANK_USED(bank)) + pm_runtime_get_sync(bank->dev); + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + /* Set trigger to none. You need to enable the desired trigger with + * request_irq() or set_irq_type(). Only do this if the IRQ line has + * not already been requested. +@@ -678,7 +678,7 @@ static int omap_gpio_request(struct gpio + omap_enable_gpio_module(bank, offset); + } + bank->mod_usage |= BIT(offset); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +@@ -688,11 +688,11 @@ static void omap_gpio_free(struct gpio_c + struct gpio_bank *bank = container_of(chip, struct gpio_bank, chip); + unsigned long flags; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + bank->mod_usage &= ~(BIT(offset)); + omap_disable_gpio_module(bank, offset); + omap_reset_gpio(bank, offset); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + /* + * If this is the last gpio to be freed in the bank, +@@ -794,9 +794,9 @@ static unsigned int omap_gpio_irq_startu + if (!BANK_USED(bank)) + pm_runtime_get_sync(bank->dev); + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + omap_gpio_init_irq(bank, offset); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + omap_gpio_unmask_irq(d); + + return 0; +@@ -808,11 +808,11 @@ static void omap_gpio_irq_shutdown(struc + unsigned long flags; + unsigned offset = d->hwirq; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + bank->irq_usage &= ~(BIT(offset)); + omap_disable_gpio_module(bank, offset); + omap_reset_gpio(bank, offset); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + /* + * If this is the last IRQ to be freed in the bank, +@@ -836,10 +836,10 @@ static void omap_gpio_mask_irq(struct ir + unsigned offset = d->hwirq; + unsigned long flags; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + omap_set_gpio_irqenable(bank, offset, 0); + omap_set_gpio_triggering(bank, offset, IRQ_TYPE_NONE); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + } + + static void omap_gpio_unmask_irq(struct irq_data *d) +@@ -849,7 +849,7 @@ static void omap_gpio_unmask_irq(struct + u32 trigger = irqd_get_trigger_type(d); + unsigned long flags; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + if (trigger) + omap_set_gpio_triggering(bank, offset, trigger); + +@@ -861,7 +861,7 @@ static void omap_gpio_unmask_irq(struct + } + + omap_set_gpio_irqenable(bank, offset, 1); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + } + + /*---------------------------------------------------------------------*/ +@@ -874,9 +874,9 @@ static int omap_mpuio_suspend_noirq(stru + OMAP_MPUIO_GPIO_MASKIT / bank->stride; + unsigned long flags; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + writel_relaxed(0xffff & ~bank->context.wake_en, mask_reg); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +@@ -889,9 +889,9 @@ static int omap_mpuio_resume_noirq(struc + OMAP_MPUIO_GPIO_MASKIT / bank->stride; + unsigned long flags; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + writel_relaxed(bank->context.wake_en, mask_reg); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +@@ -937,9 +937,9 @@ static int omap_gpio_get_direction(struc + + bank = container_of(chip, struct gpio_bank, chip); + reg = bank->base + bank->regs->direction; +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + dir = !!(readl_relaxed(reg) & BIT(offset)); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + return dir; + } + +@@ -949,9 +949,9 @@ static int omap_gpio_input(struct gpio_c + unsigned long flags; + + bank = container_of(chip, struct gpio_bank, chip); +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + omap_set_gpio_direction(bank, offset, 1); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + return 0; + } + +@@ -973,10 +973,10 @@ static int omap_gpio_output(struct gpio_ + unsigned long flags; + + bank = container_of(chip, struct gpio_bank, chip); +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + bank->set_dataout(bank, offset, value); + omap_set_gpio_direction(bank, offset, 0); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + return 0; + } + +@@ -988,9 +988,9 @@ static int omap_gpio_debounce(struct gpi + + bank = container_of(chip, struct gpio_bank, chip); + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + omap2_set_gpio_debounce(bank, offset, debounce); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +@@ -1001,9 +1001,9 @@ static void omap_gpio_set(struct gpio_ch + unsigned long flags; + + bank = container_of(chip, struct gpio_bank, chip); +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + bank->set_dataout(bank, offset, value); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + } + + /*---------------------------------------------------------------------*/ +@@ -1199,7 +1199,7 @@ static int omap_gpio_probe(struct platfo + else + bank->set_dataout = omap_set_gpio_dataout_mask; + +- spin_lock_init(&bank->lock); ++ raw_spin_lock_init(&bank->lock); + + /* Static mapping, never released */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); +@@ -1246,7 +1246,7 @@ static int omap_gpio_runtime_suspend(str + unsigned long flags; + u32 wake_low, wake_hi; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + + /* + * Only edges can generate a wakeup event to the PRCM. +@@ -1299,7 +1299,7 @@ static int omap_gpio_runtime_suspend(str + bank->get_context_loss_count(bank->dev); + + omap_gpio_dbck_disable(bank); +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } +@@ -1314,7 +1314,7 @@ static int omap_gpio_runtime_resume(stru + unsigned long flags; + int c; + +- spin_lock_irqsave(&bank->lock, flags); ++ raw_spin_lock_irqsave(&bank->lock, flags); + + /* + * On the first resume during the probe, the context has not +@@ -1350,14 +1350,14 @@ static int omap_gpio_runtime_resume(stru + if (c != bank->context_loss_count) { + omap_gpio_restore_context(bank); + } else { +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + return 0; + } + } + } + + if (!bank->workaround_enabled) { +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + return 0; + } + +@@ -1412,7 +1412,7 @@ static int omap_gpio_runtime_resume(stru + } + + bank->workaround_enabled = false; +- spin_unlock_irqrestore(&bank->lock, flags); ++ raw_spin_unlock_irqrestore(&bank->lock, flags); + + return 0; + } diff --git a/debian/patches/features/all/rt/hotplug-Use-set_cpus_allowed_ptr-in-sync_unplug_thre.patch b/debian/patches/features/all/rt/hotplug-Use-set_cpus_allowed_ptr-in-sync_unplug_thre.patch new file mode 100644 index 000000000..c1fe3a23d --- /dev/null +++ b/debian/patches/features/all/rt/hotplug-Use-set_cpus_allowed_ptr-in-sync_unplug_thre.patch @@ -0,0 +1,47 @@ +From: Mike Galbraith +Date: Tue, 24 Mar 2015 08:14:49 +0100 +Subject: hotplug: Use set_cpus_allowed_ptr() in sync_unplug_thread() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +do_set_cpus_allowed() is not safe vs ->sched_class change. + +crash> bt +PID: 11676 TASK: ffff88026f979da0 CPU: 22 COMMAND: "sync_unplug/22" + #0 [ffff880274d25bc8] machine_kexec at ffffffff8103b41c + #1 [ffff880274d25c18] crash_kexec at ffffffff810d881a + #2 [ffff880274d25cd8] oops_end at ffffffff81525818 + #3 [ffff880274d25cf8] do_invalid_op at ffffffff81003096 + #4 [ffff880274d25d90] invalid_op at ffffffff8152d3de + [exception RIP: set_cpus_allowed_rt+18] + RIP: ffffffff8109e012 RSP: ffff880274d25e48 RFLAGS: 00010202 + RAX: ffffffff8109e000 RBX: ffff88026f979da0 RCX: ffff8802770cb6e8 + RDX: 0000000000000000 RSI: ffffffff81add700 RDI: ffff88026f979da0 + RBP: ffff880274d25e78 R8: ffffffff816112e0 R9: 0000000000000001 + R10: 0000000000000001 R11: 0000000000011940 R12: ffff88026f979da0 + R13: ffff8802770cb6d0 R14: ffff880274d25fd8 R15: 0000000000000000 + ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 + #5 [ffff880274d25e60] do_set_cpus_allowed at ffffffff8108e65f + #6 [ffff880274d25e80] sync_unplug_thread at ffffffff81058c08 + #7 [ffff880274d25ed8] kthread at ffffffff8107cad6 + #8 [ffff880274d25f50] ret_from_fork at ffffffff8152bbbc +crash> task_struct ffff88026f979da0 | grep class + sched_class = 0xffffffff816111e0 , + +Signed-off-by: Mike Galbraith + +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/cpu.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -267,7 +267,7 @@ static int sync_unplug_thread(void *data + * we don't want any more work on this CPU. + */ + current->flags &= ~PF_NO_SETAFFINITY; +- do_set_cpus_allowed(current, cpu_present_mask); ++ set_cpus_allowed_ptr(current, cpu_present_mask); + migrate_me(); + return 0; + } diff --git a/debian/patches/features/all/rt/hotplug-light-get-online-cpus.patch b/debian/patches/features/all/rt/hotplug-light-get-online-cpus.patch new file mode 100644 index 000000000..fd1429577 --- /dev/null +++ b/debian/patches/features/all/rt/hotplug-light-get-online-cpus.patch @@ -0,0 +1,205 @@ +Subject: hotplug: Lightweight get online cpus +From: Thomas Gleixner +Date: Wed, 15 Jun 2011 12:36:06 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +get_online_cpus() is a heavy weight function which involves a global +mutex. migrate_disable() wants a simpler construct which prevents only +a CPU from going doing while a task is in a migrate disabled section. + +Implement a per cpu lockless mechanism, which serializes only in the +real unplug case on a global mutex. That serialization affects only +tasks on the cpu which should be brought down. + +Signed-off-by: Thomas Gleixner +--- + include/linux/cpu.h | 7 +-- + kernel/cpu.c | 119 +++++++++++++++++++++++++++++++++++++++++++++++++++- + 2 files changed, 122 insertions(+), 4 deletions(-) + +--- a/include/linux/cpu.h ++++ b/include/linux/cpu.h +@@ -221,9 +221,6 @@ static inline void smpboot_thread_init(v + #endif /* CONFIG_SMP */ + extern struct bus_type cpu_subsys; + +-static inline void pin_current_cpu(void) { } +-static inline void unpin_current_cpu(void) { } +- + #ifdef CONFIG_HOTPLUG_CPU + /* Stop CPUs going up and down. */ + +@@ -234,6 +231,8 @@ extern bool try_get_online_cpus(void); + extern void put_online_cpus(void); + extern void cpu_hotplug_disable(void); + extern void cpu_hotplug_enable(void); ++extern void pin_current_cpu(void); ++extern void unpin_current_cpu(void); + #define hotcpu_notifier(fn, pri) cpu_notifier(fn, pri) + #define __hotcpu_notifier(fn, pri) __cpu_notifier(fn, pri) + #define register_hotcpu_notifier(nb) register_cpu_notifier(nb) +@@ -252,6 +251,8 @@ static inline void cpu_hotplug_done(void + #define put_online_cpus() do { } while (0) + #define cpu_hotplug_disable() do { } while (0) + #define cpu_hotplug_enable() do { } while (0) ++static inline void pin_current_cpu(void) { } ++static inline void unpin_current_cpu(void) { } + #define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0) + #define __hotcpu_notifier(fn, pri) do { (void)(fn); } while (0) + /* These aren't inline functions due to a GCC bug. */ +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -88,6 +88,100 @@ static struct { + #define cpuhp_lock_acquire() lock_map_acquire(&cpu_hotplug.dep_map) + #define cpuhp_lock_release() lock_map_release(&cpu_hotplug.dep_map) + ++struct hotplug_pcp { ++ struct task_struct *unplug; ++ int refcount; ++ struct completion synced; ++}; ++ ++static DEFINE_PER_CPU(struct hotplug_pcp, hotplug_pcp); ++ ++/** ++ * pin_current_cpu - Prevent the current cpu from being unplugged ++ * ++ * Lightweight version of get_online_cpus() to prevent cpu from being ++ * unplugged when code runs in a migration disabled region. ++ * ++ * Must be called with preemption disabled (preempt_count = 1)! ++ */ ++void pin_current_cpu(void) ++{ ++ struct hotplug_pcp *hp = this_cpu_ptr(&hotplug_pcp); ++ ++retry: ++ if (!hp->unplug || hp->refcount || preempt_count() > 1 || ++ hp->unplug == current) { ++ hp->refcount++; ++ return; ++ } ++ preempt_enable(); ++ mutex_lock(&cpu_hotplug.lock); ++ mutex_unlock(&cpu_hotplug.lock); ++ preempt_disable(); ++ goto retry; ++} ++ ++/** ++ * unpin_current_cpu - Allow unplug of current cpu ++ * ++ * Must be called with preemption or interrupts disabled! ++ */ ++void unpin_current_cpu(void) ++{ ++ struct hotplug_pcp *hp = this_cpu_ptr(&hotplug_pcp); ++ ++ WARN_ON(hp->refcount <= 0); ++ ++ /* This is safe. sync_unplug_thread is pinned to this cpu */ ++ if (!--hp->refcount && hp->unplug && hp->unplug != current) ++ wake_up_process(hp->unplug); ++} ++ ++/* ++ * FIXME: Is this really correct under all circumstances ? ++ */ ++static int sync_unplug_thread(void *data) ++{ ++ struct hotplug_pcp *hp = data; ++ ++ preempt_disable(); ++ hp->unplug = current; ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ while (hp->refcount) { ++ schedule_preempt_disabled(); ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ } ++ set_current_state(TASK_RUNNING); ++ preempt_enable(); ++ complete(&hp->synced); ++ return 0; ++} ++ ++/* ++ * Start the sync_unplug_thread on the target cpu and wait for it to ++ * complete. ++ */ ++static int cpu_unplug_begin(unsigned int cpu) ++{ ++ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); ++ struct task_struct *tsk; ++ ++ init_completion(&hp->synced); ++ tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d\n", cpu); ++ if (IS_ERR(tsk)) ++ return (PTR_ERR(tsk)); ++ kthread_bind(tsk, cpu); ++ wake_up_process(tsk); ++ wait_for_completion(&hp->synced); ++ return 0; ++} ++ ++static void cpu_unplug_done(unsigned int cpu) ++{ ++ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); ++ ++ hp->unplug = NULL; ++} + + void get_online_cpus(void) + { +@@ -349,13 +443,14 @@ static int __ref take_cpu_down(void *_pa + /* Requires cpu_add_remove_lock to be held */ + static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) + { +- int err, nr_calls = 0; ++ int mycpu, err, nr_calls = 0; + void *hcpu = (void *)(long)cpu; + unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; + struct take_cpu_down_param tcd_param = { + .mod = mod, + .hcpu = hcpu, + }; ++ cpumask_var_t cpumask; + + if (num_online_cpus() == 1) + return -EBUSY; +@@ -363,7 +458,27 @@ static int __ref _cpu_down(unsigned int + if (!cpu_online(cpu)) + return -EINVAL; + ++ /* Move the downtaker off the unplug cpu */ ++ if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) ++ return -ENOMEM; ++ cpumask_andnot(cpumask, cpu_online_mask, cpumask_of(cpu)); ++ set_cpus_allowed_ptr(current, cpumask); ++ free_cpumask_var(cpumask); ++ preempt_disable(); ++ mycpu = smp_processor_id(); ++ if (mycpu == cpu) { ++ printk(KERN_ERR "Yuck! Still on unplug CPU\n!"); ++ preempt_enable(); ++ return -EBUSY; ++ } ++ preempt_enable(); ++ + cpu_hotplug_begin(); ++ err = cpu_unplug_begin(cpu); ++ if (err) { ++ printk("cpu_unplug_begin(%d) failed\n", cpu); ++ goto out_cancel; ++ } + + err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls); + if (err) { +@@ -427,6 +542,8 @@ static int __ref _cpu_down(unsigned int + check_for_tasks(cpu); + + out_release: ++ cpu_unplug_done(cpu); ++out_cancel: + cpu_hotplug_done(); + if (!err) + cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu); diff --git a/debian/patches/features/all/rt/hotplug-sync_unplug-no-27-5cn-27-in-task-name.patch b/debian/patches/features/all/rt/hotplug-sync_unplug-no-27-5cn-27-in-task-name.patch new file mode 100644 index 000000000..c2cb6426a --- /dev/null +++ b/debian/patches/features/all/rt/hotplug-sync_unplug-no-27-5cn-27-in-task-name.patch @@ -0,0 +1,25 @@ +Subject: hotplug: sync_unplug: No "\n" in task name +From: Yong Zhang +Date: Sun, 16 Oct 2011 18:56:43 +0800 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Otherwise the output will look a little odd. + +Signed-off-by: Yong Zhang +Link: http://lkml.kernel.org/r/1318762607-2261-2-git-send-email-yong.zhang0@gmail.com +Signed-off-by: Thomas Gleixner +--- + kernel/cpu.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -167,7 +167,7 @@ static int cpu_unplug_begin(unsigned int + struct task_struct *tsk; + + init_completion(&hp->synced); +- tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d\n", cpu); ++ tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu); + if (IS_ERR(tsk)) + return (PTR_ERR(tsk)); + kthread_bind(tsk, cpu); diff --git a/debian/patches/features/all/rt/hotplug-use-migrate-disable.patch b/debian/patches/features/all/rt/hotplug-use-migrate-disable.patch new file mode 100644 index 000000000..541b172b9 --- /dev/null +++ b/debian/patches/features/all/rt/hotplug-use-migrate-disable.patch @@ -0,0 +1,40 @@ +Subject: hotplug: Use migrate disable on unplug +From: Thomas Gleixner +Date: Sun, 17 Jul 2011 19:35:29 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Migration needs to be disabled accross the unplug handling to make +sure that the unplug thread is off the unplugged cpu. + +Signed-off-by: Thomas Gleixner +--- + kernel/cpu.c | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -466,14 +466,13 @@ static int __ref _cpu_down(unsigned int + cpumask_andnot(cpumask, cpu_online_mask, cpumask_of(cpu)); + set_cpus_allowed_ptr(current, cpumask); + free_cpumask_var(cpumask); +- preempt_disable(); ++ migrate_disable(); + mycpu = smp_processor_id(); + if (mycpu == cpu) { + printk(KERN_ERR "Yuck! Still on unplug CPU\n!"); +- preempt_enable(); ++ migrate_enable(); + return -EBUSY; + } +- preempt_enable(); + + cpu_hotplug_begin(); + err = cpu_unplug_begin(cpu); +@@ -546,6 +545,7 @@ static int __ref _cpu_down(unsigned int + out_release: + cpu_unplug_done(cpu); + out_cancel: ++ migrate_enable(); + cpu_hotplug_done(); + if (!err) + cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu); diff --git a/debian/patches/features/all/rt/hrtimer-Move-schedule_work-call-to-helper-thread.patch b/debian/patches/features/all/rt/hrtimer-Move-schedule_work-call-to-helper-thread.patch new file mode 100644 index 000000000..19f04e06f --- /dev/null +++ b/debian/patches/features/all/rt/hrtimer-Move-schedule_work-call-to-helper-thread.patch @@ -0,0 +1,118 @@ +From: Yang Shi +Date: Mon, 16 Sep 2013 14:09:19 -0700 +Subject: hrtimer: Move schedule_work call to helper thread +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +When run ltp leapsec_timer test, the following call trace is caught: + +BUG: sleeping function called from invalid context at kernel/rtmutex.c:659 +in_atomic(): 1, irqs_disabled(): 1, pid: 0, name: swapper/1 +Preemption disabled at:[] cpu_startup_entry+0x133/0x310 + +CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.10.10-rt3 #2 +Hardware name: Intel Corporation Calpella platform/MATXM-CORE-411-B, BIOS 4.6.3 08/18/2010 +ffffffff81c2f800 ffff880076843e40 ffffffff8169918d ffff880076843e58 +ffffffff8106db31 ffff88007684b4a0 ffff880076843e70 ffffffff8169d9c0 +ffff88007684b4a0 ffff880076843eb0 ffffffff81059da1 0000001876851200 +Call Trace: + [] dump_stack+0x19/0x1b +[] __might_sleep+0xf1/0x170 +[] rt_spin_lock+0x20/0x50 +[] queue_work_on+0x61/0x100 +[] clock_was_set_delayed+0x21/0x30 +[] do_timer+0x40e/0x660 +[] tick_do_update_jiffies64+0xf7/0x140 +[] tick_check_idle+0x92/0xc0 +[] irq_enter+0x57/0x70 +[] smp_apic_timer_interrupt+0x3e/0x9b +[] apic_timer_interrupt+0x6a/0x70 + [] ? cpuidle_enter_state+0x4c/0xc0 +[] cpuidle_idle_call+0xd8/0x2d0 +[] arch_cpu_idle+0xe/0x30 +[] cpu_startup_entry+0x19e/0x310 +[] start_secondary+0x1ad/0x1b0 + +The clock_was_set_delayed is called in hard IRQ handler (timer interrupt), which +calls schedule_work. + +Under PREEMPT_RT_FULL, schedule_work calls spinlocks which could sleep, so it's +not safe to call schedule_work in interrupt context. + +Reference upstream commit b68d61c705ef02384c0538b8d9374545097899ca +(rt,ntp: Move call to schedule_delayed_work() to helper thread) +from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-stable-rt.git, which +makes a similar change. + +add a helper thread which does the call to schedule_work and wake up that +thread instead of calling schedule_work directly. + + +Signed-off-by: Yang Shi +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/time/hrtimer.c | 40 ++++++++++++++++++++++++++++++++++++++++ + 1 file changed, 40 insertions(+) + +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -48,6 +48,7 @@ + #include + #include + #include ++#include + #include + + #include +@@ -713,6 +714,44 @@ static void clock_was_set_work(struct wo + + static DECLARE_WORK(hrtimer_work, clock_was_set_work); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * RT can not call schedule_work from real interrupt context. ++ * Need to make a thread to do the real work. ++ */ ++static struct task_struct *clock_set_delay_thread; ++static bool do_clock_set_delay; ++ ++static int run_clock_set_delay(void *ignore) ++{ ++ while (!kthread_should_stop()) { ++ set_current_state(TASK_INTERRUPTIBLE); ++ if (do_clock_set_delay) { ++ do_clock_set_delay = false; ++ schedule_work(&hrtimer_work); ++ } ++ schedule(); ++ } ++ __set_current_state(TASK_RUNNING); ++ return 0; ++} ++ ++void clock_was_set_delayed(void) ++{ ++ do_clock_set_delay = true; ++ /* Make visible before waking up process */ ++ smp_wmb(); ++ wake_up_process(clock_set_delay_thread); ++} ++ ++static __init int create_clock_set_delay_thread(void) ++{ ++ clock_set_delay_thread = kthread_run(run_clock_set_delay, NULL, "kclksetdelayd"); ++ BUG_ON(!clock_set_delay_thread); ++ return 0; ++} ++early_initcall(create_clock_set_delay_thread); ++#else /* PREEMPT_RT_FULL */ + /* + * Called from timekeeping and resume code to reprogramm the hrtimer + * interrupt device on all cpus. +@@ -721,6 +760,7 @@ void clock_was_set_delayed(void) + { + schedule_work(&hrtimer_work); + } ++#endif + + #else + diff --git a/debian/patches/features/all/rt/hrtimer-fixup-hrtimer-callback-changes-for-preempt-r.patch b/debian/patches/features/all/rt/hrtimer-fixup-hrtimer-callback-changes-for-preempt-r.patch new file mode 100644 index 000000000..e51769da2 --- /dev/null +++ b/debian/patches/features/all/rt/hrtimer-fixup-hrtimer-callback-changes-for-preempt-r.patch @@ -0,0 +1,463 @@ +From: Thomas Gleixner +Date: Fri, 3 Jul 2009 08:44:31 -0500 +Subject: hrtimer: Fixup hrtimer callback changes for preempt-rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +In preempt-rt we can not call the callbacks which take sleeping locks +from the timer interrupt context. + +Bring back the softirq split for now, until we fixed the signal +delivery problem for real. + +Signed-off-by: Thomas Gleixner +Signed-off-by: Ingo Molnar + +--- + include/linux/hrtimer.h | 3 + kernel/sched/core.c | 1 + kernel/sched/rt.c | 1 + kernel/time/hrtimer.c | 219 +++++++++++++++++++++++++++++++++++++++++------ + kernel/time/tick-sched.c | 1 + kernel/watchdog.c | 1 + 6 files changed, 200 insertions(+), 26 deletions(-) + +--- a/include/linux/hrtimer.h ++++ b/include/linux/hrtimer.h +@@ -111,6 +111,8 @@ struct hrtimer { + enum hrtimer_restart (*function)(struct hrtimer *); + struct hrtimer_clock_base *base; + unsigned long state; ++ struct list_head cb_entry; ++ int irqsafe; + #ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + ktime_t praecox; + #endif +@@ -150,6 +152,7 @@ struct hrtimer_clock_base { + int index; + clockid_t clockid; + struct timerqueue_head active; ++ struct list_head expired; + ktime_t resolution; + ktime_t (*get_time)(void); + ktime_t softirq_time; +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -461,6 +461,7 @@ static void init_rq_hrtick(struct rq *rq + + hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + rq->hrtick_timer.function = hrtick; ++ rq->hrtick_timer.irqsafe = 1; + } + #else /* CONFIG_SCHED_HRTICK */ + static inline void hrtick_clear(struct rq *rq) +--- a/kernel/sched/rt.c ++++ b/kernel/sched/rt.c +@@ -44,6 +44,7 @@ void init_rt_bandwidth(struct rt_bandwid + + hrtimer_init(&rt_b->rt_period_timer, + CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ rt_b->rt_period_timer.irqsafe = 1; + rt_b->rt_period_timer.function = sched_rt_period_timer; + } + +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -577,8 +577,7 @@ static int hrtimer_reprogram(struct hrti + * When the callback is running, we do not reprogram the clock event + * device. The timer callback is either running on a different CPU or + * the callback is executed in the hrtimer_interrupt context. The +- * reprogramming is handled either by the softirq, which called the +- * callback or at the end of the hrtimer_interrupt. ++ * reprogramming is handled at the end of the hrtimer_interrupt. + */ + if (hrtimer_callback_running(timer)) + return 0; +@@ -622,6 +621,9 @@ static int hrtimer_reprogram(struct hrti + return res; + } + ++static void __run_hrtimer(struct hrtimer *timer, ktime_t *now); ++static int hrtimer_rt_defer(struct hrtimer *timer); ++ + /* + * Initialize the high resolution related parts of cpu_base + */ +@@ -631,6 +633,21 @@ static inline void hrtimer_init_hres(str + base->hres_active = 0; + } + ++static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, ++ struct hrtimer_clock_base *base, ++ int wakeup) ++{ ++ if (!hrtimer_reprogram(timer, base)) ++ return 0; ++ if (!wakeup) ++ return -ETIME; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ if (!hrtimer_rt_defer(timer)) ++ return -ETIME; ++#endif ++ return 1; ++} ++ + static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) + { + ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; +@@ -712,6 +729,13 @@ static inline int hrtimer_is_hres_enable + static inline int hrtimer_switch_to_hres(void) { return 0; } + static inline void + hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { } ++static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, ++ struct hrtimer_clock_base *base, ++ int wakeup) ++{ ++ return 0; ++} ++ + static inline int hrtimer_reprogram(struct hrtimer *timer, + struct hrtimer_clock_base *base) + { +@@ -719,7 +743,6 @@ static inline int hrtimer_reprogram(stru + } + static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { } + static inline void retrigger_next_event(void *arg) { } +- + #endif /* CONFIG_HIGH_RES_TIMERS */ + + /* +@@ -854,9 +877,9 @@ void hrtimer_wait_for_timer(const struct + { + struct hrtimer_clock_base *base = timer->base; + +- if (base && base->cpu_base && !hrtimer_hres_active()) ++ if (base && base->cpu_base && !timer->irqsafe) + wait_event(base->cpu_base->wait, +- !(timer->state & HRTIMER_STATE_CALLBACK)); ++ !(timer->state & HRTIMER_STATE_CALLBACK)); + } + + #else +@@ -906,6 +929,11 @@ static void __remove_hrtimer(struct hrti + if (!(timer->state & HRTIMER_STATE_ENQUEUED)) + goto out; + ++ if (unlikely(!list_empty(&timer->cb_entry))) { ++ list_del_init(&timer->cb_entry); ++ goto out; ++ } ++ + next_timer = timerqueue_getnext(&base->active); + timerqueue_del(&base->active, &timer->node); + if (&timer->node == next_timer) { +@@ -1016,15 +1044,26 @@ int __hrtimer_start_range_ns(struct hrti + * on dynticks target. + */ + wake_up_nohz_cpu(new_base->cpu_base->cpu); +- } else if (new_base->cpu_base == this_cpu_ptr(&hrtimer_bases) && +- hrtimer_reprogram(timer, new_base)) { ++ } else if (new_base->cpu_base == this_cpu_ptr(&hrtimer_bases)) { ++ ++ ret = hrtimer_enqueue_reprogram(timer, new_base, wakeup); ++ if (ret < 0) { ++ /* ++ * In case we failed to reprogram the timer (mostly ++ * because out current timer is already elapsed), ++ * remove it again and report a failure. This avoids ++ * stale base->first entries. ++ */ ++ debug_deactivate(timer); ++ __remove_hrtimer(timer, new_base, ++ timer->state & HRTIMER_STATE_CALLBACK, 0); ++ } else if (ret > 0) { + /* + * Only allow reprogramming if the new base is on this CPU. + * (it might still be on another CPU if the timer was pending) + * + * XXX send_remote_softirq() ? + */ +- if (wakeup) { + /* + * We need to drop cpu_base->lock to avoid a + * lock ordering issue vs. rq->lock. +@@ -1032,9 +1071,7 @@ int __hrtimer_start_range_ns(struct hrti + raw_spin_unlock(&new_base->cpu_base->lock); + raise_softirq_irqoff(HRTIMER_SOFTIRQ); + local_irq_restore(flags); +- return ret; +- } else { +- __raise_softirq_irqoff(HRTIMER_SOFTIRQ); ++ return 0; + } + } + +@@ -1189,6 +1226,7 @@ static void __hrtimer_init(struct hrtime + + base = hrtimer_clockid_to_base(clock_id); + timer->base = &cpu_base->clock_base[base]; ++ INIT_LIST_HEAD(&timer->cb_entry); + timerqueue_init(&timer->node); + + #ifdef CONFIG_TIMER_STATS +@@ -1272,10 +1310,128 @@ static void __run_hrtimer(struct hrtimer + timer->state &= ~HRTIMER_STATE_CALLBACK; + } + +-#ifdef CONFIG_HIGH_RES_TIMERS +- + static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer); + ++#ifdef CONFIG_PREEMPT_RT_BASE ++static void hrtimer_rt_reprogram(int restart, struct hrtimer *timer, ++ struct hrtimer_clock_base *base) ++{ ++ /* ++ * Note, we clear the callback flag before we requeue the ++ * timer otherwise we trigger the callback_running() check ++ * in hrtimer_reprogram(). ++ */ ++ timer->state &= ~HRTIMER_STATE_CALLBACK; ++ ++ if (restart != HRTIMER_NORESTART) { ++ BUG_ON(hrtimer_active(timer)); ++ /* ++ * Enqueue the timer, if it's the leftmost timer then ++ * we need to reprogram it. ++ */ ++ if (!enqueue_hrtimer(timer, base)) ++ return; ++ ++#ifndef CONFIG_HIGH_RES_TIMERS ++ } ++#else ++ if (base->cpu_base->hres_active && ++ hrtimer_reprogram(timer, base)) ++ goto requeue; ++ ++ } else if (hrtimer_active(timer)) { ++ /* ++ * If the timer was rearmed on another CPU, reprogram ++ * the event device. ++ */ ++ if (&timer->node == base->active.next && ++ base->cpu_base->hres_active && ++ hrtimer_reprogram(timer, base)) ++ goto requeue; ++ } ++ return; ++ ++requeue: ++ /* ++ * Timer is expired. Thus move it from tree to pending list ++ * again. ++ */ ++ __remove_hrtimer(timer, base, timer->state, 0); ++ list_add_tail(&timer->cb_entry, &base->expired); ++#endif ++} ++ ++/* ++ * The changes in mainline which removed the callback modes from ++ * hrtimer are not yet working with -rt. The non wakeup_process() ++ * based callbacks which involve sleeping locks need to be treated ++ * seperately. ++ */ ++static void hrtimer_rt_run_pending(void) ++{ ++ enum hrtimer_restart (*fn)(struct hrtimer *); ++ struct hrtimer_cpu_base *cpu_base; ++ struct hrtimer_clock_base *base; ++ struct hrtimer *timer; ++ int index, restart; ++ ++ local_irq_disable(); ++ cpu_base = &per_cpu(hrtimer_bases, smp_processor_id()); ++ ++ raw_spin_lock(&cpu_base->lock); ++ ++ for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) { ++ base = &cpu_base->clock_base[index]; ++ ++ while (!list_empty(&base->expired)) { ++ timer = list_first_entry(&base->expired, ++ struct hrtimer, cb_entry); ++ ++ /* ++ * Same as the above __run_hrtimer function ++ * just we run with interrupts enabled. ++ */ ++ debug_hrtimer_deactivate(timer); ++ __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0); ++ timer_stats_account_hrtimer(timer); ++ fn = timer->function; ++ ++ raw_spin_unlock_irq(&cpu_base->lock); ++ restart = fn(timer); ++ raw_spin_lock_irq(&cpu_base->lock); ++ ++ hrtimer_rt_reprogram(restart, timer, base); ++ } ++ } ++ ++ raw_spin_unlock_irq(&cpu_base->lock); ++ ++ wake_up_timer_waiters(cpu_base); ++} ++ ++static int hrtimer_rt_defer(struct hrtimer *timer) ++{ ++ if (timer->irqsafe) ++ return 0; ++ ++ __remove_hrtimer(timer, timer->base, timer->state, 0); ++ list_add_tail(&timer->cb_entry, &timer->base->expired); ++ return 1; ++} ++ ++#else ++ ++static inline void hrtimer_rt_run_pending(void) ++{ ++ hrtimer_peek_ahead_timers(); ++} ++ ++static inline int hrtimer_rt_defer(struct hrtimer *timer) { return 0; } ++ ++#endif ++ ++#ifdef CONFIG_HIGH_RES_TIMERS ++ + /* + * High resolution timer interrupt + * Called with interrupts disabled +@@ -1284,7 +1440,7 @@ void hrtimer_interrupt(struct clock_even + { + struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); + ktime_t expires_next, now, entry_time, delta; +- int i, retries = 0; ++ int i, retries = 0, raise = 0; + + BUG_ON(!cpu_base->hres_active); + cpu_base->nr_events++; +@@ -1343,7 +1499,10 @@ void hrtimer_interrupt(struct clock_even + if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) + break; + +- __run_hrtimer(timer, &basenow); ++ if (!hrtimer_rt_defer(timer)) ++ __run_hrtimer(timer, &basenow); ++ else ++ raise = 1; + } + } + /* Reevaluate the clock bases for the next expiry */ +@@ -1360,6 +1519,10 @@ void hrtimer_interrupt(struct clock_even + if (expires_next.tv64 == KTIME_MAX || + !tick_program_event(expires_next, 0)) { + cpu_base->hang_detected = 0; ++ ++ if (raise) ++ raise_softirq_irqoff(HRTIMER_SOFTIRQ); ++ + return; + } + +@@ -1439,18 +1602,18 @@ void hrtimer_peek_ahead_timers(void) + __hrtimer_peek_ahead_timers(); + local_irq_restore(flags); + } +- +-static void run_hrtimer_softirq(struct softirq_action *h) +-{ +- hrtimer_peek_ahead_timers(); +-} +- + #else /* CONFIG_HIGH_RES_TIMERS */ + + static inline void __hrtimer_peek_ahead_timers(void) { } + + #endif /* !CONFIG_HIGH_RES_TIMERS */ + ++ ++static void run_hrtimer_softirq(struct softirq_action *h) ++{ ++ hrtimer_rt_run_pending(); ++} ++ + /* + * Called from timer softirq every jiffy, expire hrtimers: + * +@@ -1483,7 +1646,7 @@ void hrtimer_run_queues(void) + struct timerqueue_node *node; + struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); + struct hrtimer_clock_base *base; +- int index, gettime = 1; ++ int index, gettime = 1, raise = 0; + + if (hrtimer_hres_active()) + return; +@@ -1508,12 +1671,16 @@ void hrtimer_run_queues(void) + hrtimer_get_expires_tv64(timer)) + break; + +- __run_hrtimer(timer, &base->softirq_time); ++ if (!hrtimer_rt_defer(timer)) ++ __run_hrtimer(timer, &base->softirq_time); ++ else ++ raise = 1; + } + raw_spin_unlock(&cpu_base->lock); + } + +- wake_up_timer_waiters(cpu_base); ++ if (raise) ++ raise_softirq_irqoff(HRTIMER_SOFTIRQ); + } + + /* +@@ -1535,6 +1702,7 @@ static enum hrtimer_restart hrtimer_wake + void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task) + { + sl->timer.function = hrtimer_wakeup; ++ sl->timer.irqsafe = 1; + sl->task = task; + } + EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); +@@ -1671,6 +1839,7 @@ static void init_hrtimers_cpu(int cpu) + for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { + cpu_base->clock_base[i].cpu_base = cpu_base; + timerqueue_init_head(&cpu_base->clock_base[i].active); ++ INIT_LIST_HEAD(&cpu_base->clock_base[i].expired); + } + + cpu_base->cpu = cpu; +@@ -1783,9 +1952,7 @@ void __init hrtimers_init(void) + hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE, + (void *)(long)smp_processor_id()); + register_cpu_notifier(&hrtimers_nb); +-#ifdef CONFIG_HIGH_RES_TIMERS + open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq); +-#endif + } + + /** +--- a/kernel/time/tick-sched.c ++++ b/kernel/time/tick-sched.c +@@ -1159,6 +1159,7 @@ void tick_setup_sched_timer(void) + * Emulate tick processing via per-CPU hrtimers: + */ + hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); ++ ts->sched_timer.irqsafe = 1; + ts->sched_timer.function = tick_sched_timer; + + /* Get the next period (per cpu) */ +--- a/kernel/watchdog.c ++++ b/kernel/watchdog.c +@@ -454,6 +454,7 @@ static void watchdog_enable(unsigned int + /* kick off the timer for the hardlockup detector */ + hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer->function = watchdog_timer_fn; ++ hrtimer->irqsafe = 1; + + /* Enable the perf event */ + watchdog_nmi_enable(cpu); diff --git a/debian/patches/features/all/rt/hrtimer-raise-softirq-if-hrtimer-irq-stalled.patch b/debian/patches/features/all/rt/hrtimer-raise-softirq-if-hrtimer-irq-stalled.patch new file mode 100644 index 000000000..a3a170fe8 --- /dev/null +++ b/debian/patches/features/all/rt/hrtimer-raise-softirq-if-hrtimer-irq-stalled.patch @@ -0,0 +1,38 @@ +Subject: hrtimer: Raise softirq if hrtimer irq stalled +From: Watanabe +Date: Sun, 28 Oct 2012 11:13:44 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +When the hrtimer stall detection hits the softirq is not raised. + +Signed-off-by: Thomas Gleixner + +--- + kernel/time/hrtimer.c | 9 ++++----- + 1 file changed, 4 insertions(+), 5 deletions(-) + +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -1519,11 +1519,7 @@ void hrtimer_interrupt(struct clock_even + if (expires_next.tv64 == KTIME_MAX || + !tick_program_event(expires_next, 0)) { + cpu_base->hang_detected = 0; +- +- if (raise) +- raise_softirq_irqoff(HRTIMER_SOFTIRQ); +- +- return; ++ goto out; + } + + /* +@@ -1567,6 +1563,9 @@ void hrtimer_interrupt(struct clock_even + tick_program_event(expires_next, 1); + printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n", + ktime_to_ns(delta)); ++out: ++ if (raise) ++ raise_softirq_irqoff(HRTIMER_SOFTIRQ); + } + + /* diff --git a/debian/patches/features/all/rt/hrtimers-prepare-full-preemption.patch b/debian/patches/features/all/rt/hrtimers-prepare-full-preemption.patch new file mode 100644 index 000000000..2b1cc7386 --- /dev/null +++ b/debian/patches/features/all/rt/hrtimers-prepare-full-preemption.patch @@ -0,0 +1,196 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:29:34 -0500 +Subject: hrtimers: Prepare full preemption +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Make cancellation of a running callback in softirq context safe +against preemption. + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + include/linux/hrtimer.h | 10 ++++++++++ + kernel/time/hrtimer.c | 33 ++++++++++++++++++++++++++++++++- + kernel/time/itimer.c | 1 + + kernel/time/posix-timers.c | 33 +++++++++++++++++++++++++++++++++ + 4 files changed, 76 insertions(+), 1 deletion(-) + +--- a/include/linux/hrtimer.h ++++ b/include/linux/hrtimer.h +@@ -197,6 +197,9 @@ struct hrtimer_cpu_base { + unsigned long nr_hangs; + ktime_t max_hang_time; + #endif ++#ifdef CONFIG_PREEMPT_RT_BASE ++ wait_queue_head_t wait; ++#endif + struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; + }; + +@@ -384,6 +387,13 @@ static inline int hrtimer_restart(struct + return hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + } + ++/* Softirq preemption could deadlock timer removal */ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ extern void hrtimer_wait_for_timer(const struct hrtimer *timer); ++#else ++# define hrtimer_wait_for_timer(timer) do { cpu_relax(); } while (0) ++#endif ++ + /* Query timers: */ + extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer); + extern int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp); +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -837,6 +837,32 @@ u64 hrtimer_forward(struct hrtimer *time + } + EXPORT_SYMBOL_GPL(hrtimer_forward); + ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define wake_up_timer_waiters(b) wake_up(&(b)->wait) ++ ++/** ++ * hrtimer_wait_for_timer - Wait for a running timer ++ * ++ * @timer: timer to wait for ++ * ++ * The function waits in case the timers callback function is ++ * currently executed on the waitqueue of the timer base. The ++ * waitqueue is woken up after the timer callback function has ++ * finished execution. ++ */ ++void hrtimer_wait_for_timer(const struct hrtimer *timer) ++{ ++ struct hrtimer_clock_base *base = timer->base; ++ ++ if (base && base->cpu_base && !hrtimer_hres_active()) ++ wait_event(base->cpu_base->wait, ++ !(timer->state & HRTIMER_STATE_CALLBACK)); ++} ++ ++#else ++# define wake_up_timer_waiters(b) do { } while (0) ++#endif ++ + /* + * enqueue_hrtimer - internal function to (re)start a timer + * +@@ -1099,7 +1125,7 @@ int hrtimer_cancel(struct hrtimer *timer + + if (ret >= 0) + return ret; +- cpu_relax(); ++ hrtimer_wait_for_timer(timer); + } + } + EXPORT_SYMBOL_GPL(hrtimer_cancel); +@@ -1486,6 +1512,8 @@ void hrtimer_run_queues(void) + } + raw_spin_unlock(&cpu_base->lock); + } ++ ++ wake_up_timer_waiters(cpu_base); + } + + /* +@@ -1647,6 +1675,9 @@ static void init_hrtimers_cpu(int cpu) + + cpu_base->cpu = cpu; + hrtimer_init_hres(cpu_base); ++#ifdef CONFIG_PREEMPT_RT_BASE ++ init_waitqueue_head(&cpu_base->wait); ++#endif + } + + #ifdef CONFIG_HOTPLUG_CPU +--- a/kernel/time/itimer.c ++++ b/kernel/time/itimer.c +@@ -213,6 +213,7 @@ int do_setitimer(int which, struct itime + /* We are sharing ->siglock with it_real_fn() */ + if (hrtimer_try_to_cancel(timer) < 0) { + spin_unlock_irq(&tsk->sighand->siglock); ++ hrtimer_wait_for_timer(&tsk->signal->real_timer); + goto again; + } + expires = timeval_to_ktime(value->it_value); +--- a/kernel/time/posix-timers.c ++++ b/kernel/time/posix-timers.c +@@ -821,6 +821,20 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_ + return overrun; + } + ++/* ++ * Protected by RCU! ++ */ ++static void timer_wait_for_callback(struct k_clock *kc, struct k_itimer *timr) ++{ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (kc->timer_set == common_timer_set) ++ hrtimer_wait_for_timer(&timr->it.real.timer); ++ else ++ /* FIXME: Whacky hack for posix-cpu-timers */ ++ schedule_timeout(1); ++#endif ++} ++ + /* Set a POSIX.1b interval timer. */ + /* timr->it_lock is taken. */ + static int +@@ -898,6 +912,7 @@ SYSCALL_DEFINE4(timer_settime, timer_t, + if (!timr) + return -EINVAL; + ++ rcu_read_lock(); + kc = clockid_to_kclock(timr->it_clock); + if (WARN_ON_ONCE(!kc || !kc->timer_set)) + error = -EINVAL; +@@ -906,9 +921,12 @@ SYSCALL_DEFINE4(timer_settime, timer_t, + + unlock_timer(timr, flag); + if (error == TIMER_RETRY) { ++ timer_wait_for_callback(kc, timr); + rtn = NULL; // We already got the old time... ++ rcu_read_unlock(); + goto retry; + } ++ rcu_read_unlock(); + + if (old_setting && !error && + copy_to_user(old_setting, &old_spec, sizeof (old_spec))) +@@ -946,10 +964,15 @@ SYSCALL_DEFINE1(timer_delete, timer_t, t + if (!timer) + return -EINVAL; + ++ rcu_read_lock(); + if (timer_delete_hook(timer) == TIMER_RETRY) { + unlock_timer(timer, flags); ++ timer_wait_for_callback(clockid_to_kclock(timer->it_clock), ++ timer); ++ rcu_read_unlock(); + goto retry_delete; + } ++ rcu_read_unlock(); + + spin_lock(¤t->sighand->siglock); + list_del(&timer->list); +@@ -975,8 +998,18 @@ static void itimer_delete(struct k_itime + retry_delete: + spin_lock_irqsave(&timer->it_lock, flags); + ++ /* On RT we can race with a deletion */ ++ if (!timer->it_signal) { ++ unlock_timer(timer, flags); ++ return; ++ } ++ + if (timer_delete_hook(timer) == TIMER_RETRY) { ++ rcu_read_lock(); + unlock_timer(timer, flags); ++ timer_wait_for_callback(clockid_to_kclock(timer->it_clock), ++ timer); ++ rcu_read_unlock(); + goto retry_delete; + } + list_del(&timer->list); diff --git a/debian/patches/features/all/rt/hwlat-detector-Don-t-ignore-threshold-module-paramet.patch b/debian/patches/features/all/rt/hwlat-detector-Don-t-ignore-threshold-module-paramet.patch new file mode 100644 index 000000000..898a615ea --- /dev/null +++ b/debian/patches/features/all/rt/hwlat-detector-Don-t-ignore-threshold-module-paramet.patch @@ -0,0 +1,26 @@ +From: Mike Galbraith +Date: Fri, 30 Aug 2013 07:57:25 +0200 +Subject: hwlat-detector: Don't ignore threshold module parameter +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +If the user specified a threshold at module load time, use it. + + +Acked-by: Steven Rostedt +Signed-off-by: Mike Galbraith +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/misc/hwlat_detector.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/misc/hwlat_detector.c ++++ b/drivers/misc/hwlat_detector.c +@@ -414,7 +414,7 @@ static int init_stats(void) + goto out; + + __reset_stats(); +- data.threshold = DEFAULT_LAT_THRESHOLD; /* threshold us */ ++ data.threshold = threshold ?: DEFAULT_LAT_THRESHOLD; /* threshold us */ + data.sample_window = DEFAULT_SAMPLE_WINDOW; /* window us */ + data.sample_width = DEFAULT_SAMPLE_WIDTH; /* width us */ + diff --git a/debian/patches/features/all/rt/hwlat-detector-Update-hwlat_detector-to-add-outer-lo.patch b/debian/patches/features/all/rt/hwlat-detector-Update-hwlat_detector-to-add-outer-lo.patch new file mode 100644 index 000000000..fffea2fc0 --- /dev/null +++ b/debian/patches/features/all/rt/hwlat-detector-Update-hwlat_detector-to-add-outer-lo.patch @@ -0,0 +1,126 @@ +From: Steven Rostedt +Date: Mon, 19 Aug 2013 17:33:25 -0400 +Subject: hwlat-detector: Update hwlat_detector to add outer loop detection +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The hwlat_detector reads two timestamps in a row, then reports any +gap between those calls. The problem is, it misses everything between +the second reading of the time stamp to the first reading of the time stamp +in the next loop. That's were most of the time is spent, which means, +chances are likely that it will miss all hardware latencies. This +defeats the purpose. + +By also testing the first time stamp from the previous loop second +time stamp (the outer loop), we are more likely to find a latency. + +Setting the threshold to 1, here's what the report now looks like: + +1347415723.0232202770 0 2 +1347415725.0234202822 0 2 +1347415727.0236202875 0 2 +1347415729.0238202928 0 2 +1347415731.0240202980 0 2 +1347415734.0243203061 0 2 +1347415736.0245203113 0 2 +1347415738.0247203166 2 0 +1347415740.0249203219 0 3 +1347415742.0251203272 0 3 +1347415743.0252203299 0 3 +1347415745.0254203351 0 2 +1347415747.0256203404 0 2 +1347415749.0258203457 0 2 +1347415751.0260203510 0 2 +1347415754.0263203589 0 2 +1347415756.0265203642 0 2 +1347415758.0267203695 0 2 +1347415760.0269203748 0 2 +1347415762.0271203801 0 2 +1347415764.0273203853 2 0 + +There's some hardware latency that takes 2 microseconds to run. + +Signed-off-by: Steven Rostedt +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/misc/hwlat_detector.c | 32 ++++++++++++++++++++++++++------ + 1 file changed, 26 insertions(+), 6 deletions(-) + +--- a/drivers/misc/hwlat_detector.c ++++ b/drivers/misc/hwlat_detector.c +@@ -143,6 +143,7 @@ static void detector_exit(void); + struct sample { + u64 seqnum; /* unique sequence */ + u64 duration; /* ktime delta */ ++ u64 outer_duration; /* ktime delta (outer loop) */ + struct timespec timestamp; /* wall time */ + unsigned long lost; + }; +@@ -219,11 +220,13 @@ static struct sample *buffer_get_sample( + */ + static int get_sample(void *unused) + { +- ktime_t start, t1, t2; ++ ktime_t start, t1, t2, last_t2; + s64 diff, total = 0; + u64 sample = 0; ++ u64 outer_sample = 0; + int ret = 1; + ++ last_t2.tv64 = 0; + start = ktime_get(); /* start timestamp */ + + do { +@@ -231,7 +234,22 @@ static int get_sample(void *unused) + t1 = ktime_get(); /* we'll look for a discontinuity */ + t2 = ktime_get(); + ++ if (last_t2.tv64) { ++ /* Check the delta from outer loop (t2 to next t1) */ ++ diff = ktime_to_us(ktime_sub(t1, last_t2)); ++ /* This shouldn't happen */ ++ if (diff < 0) { ++ pr_err(BANNER "time running backwards\n"); ++ goto out; ++ } ++ if (diff > outer_sample) ++ outer_sample = diff; ++ } ++ last_t2 = t2; ++ + total = ktime_to_us(ktime_sub(t2, start)); /* sample width */ ++ ++ /* This checks the inner loop (t1 to t2) */ + diff = ktime_to_us(ktime_sub(t2, t1)); /* current diff */ + + /* This shouldn't happen */ +@@ -246,12 +264,13 @@ static int get_sample(void *unused) + } while (total <= data.sample_width); + + /* If we exceed the threshold value, we have found a hardware latency */ +- if (sample > data.threshold) { ++ if (sample > data.threshold || outer_sample > data.threshold) { + struct sample s; + + data.count++; + s.seqnum = data.count; + s.duration = sample; ++ s.outer_duration = outer_sample; + s.timestamp = CURRENT_TIME; + __buffer_add_sample(&s); + +@@ -738,10 +757,11 @@ static ssize_t debug_sample_fread(struct + } + } + +- len = snprintf(buf, sizeof(buf), "%010lu.%010lu\t%llu\n", +- sample->timestamp.tv_sec, +- sample->timestamp.tv_nsec, +- sample->duration); ++ len = snprintf(buf, sizeof(buf), "%010lu.%010lu\t%llu\t%llu\n", ++ sample->timestamp.tv_sec, ++ sample->timestamp.tv_nsec, ++ sample->duration, ++ sample->outer_duration); + + + /* handling partial reads is more trouble than it's worth */ diff --git a/debian/patches/features/all/rt/hwlat-detector-Use-thread-instead-of-stop-machine.patch b/debian/patches/features/all/rt/hwlat-detector-Use-thread-instead-of-stop-machine.patch new file mode 100644 index 000000000..e89f187ad --- /dev/null +++ b/debian/patches/features/all/rt/hwlat-detector-Use-thread-instead-of-stop-machine.patch @@ -0,0 +1,184 @@ +From: Steven Rostedt +Date: Mon, 19 Aug 2013 17:33:27 -0400 +Subject: hwlat-detector: Use thread instead of stop machine +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +There's no reason to use stop machine to search for hardware latency. +Simply disabling interrupts while running the loop will do enough to +check if something comes in that wasn't disabled by interrupts being +off, which is exactly what stop machine does. + +Instead of using stop machine, just have the thread disable interrupts +while it checks for hardware latency. + +Signed-off-by: Steven Rostedt +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/misc/hwlat_detector.c | 60 ++++++++++++++++++------------------------ + 1 file changed, 26 insertions(+), 34 deletions(-) + +--- a/drivers/misc/hwlat_detector.c ++++ b/drivers/misc/hwlat_detector.c +@@ -41,7 +41,6 @@ + #include + #include + #include +-#include + #include + #include + #include +@@ -107,7 +106,6 @@ struct data; /* Global state */ + /* Sampling functions */ + static int __buffer_add_sample(struct sample *sample); + static struct sample *buffer_get_sample(struct sample *sample); +-static int get_sample(void *unused); + + /* Threading and state */ + static int kthread_fn(void *unused); +@@ -149,7 +147,7 @@ struct sample { + unsigned long lost; + }; + +-/* keep the global state somewhere. Mostly used under stop_machine. */ ++/* keep the global state somewhere. */ + static struct data { + + struct mutex lock; /* protect changes */ +@@ -172,7 +170,7 @@ static struct data { + * @sample: The new latency sample value + * + * This receives a new latency sample and records it in a global ring buffer. +- * No additional locking is used in this case - suited for stop_machine use. ++ * No additional locking is used in this case. + */ + static int __buffer_add_sample(struct sample *sample) + { +@@ -229,18 +227,18 @@ static struct sample *buffer_get_sample( + #endif + /** + * get_sample - sample the CPU TSC and look for likely hardware latencies +- * @unused: This is not used but is a part of the stop_machine API + * + * Used to repeatedly capture the CPU TSC (or similar), looking for potential +- * hardware-induced latency. Called under stop_machine, with data.lock held. ++ * hardware-induced latency. Called with interrupts disabled and with ++ * data.lock held. + */ +-static int get_sample(void *unused) ++static int get_sample(void) + { + time_type start, t1, t2, last_t2; + s64 diff, total = 0; + u64 sample = 0; + u64 outer_sample = 0; +- int ret = 1; ++ int ret = -1; + + init_time(last_t2, 0); + start = time_get(); /* start timestamp */ +@@ -279,10 +277,14 @@ static int get_sample(void *unused) + + } while (total <= data.sample_width); + ++ ret = 0; ++ + /* If we exceed the threshold value, we have found a hardware latency */ + if (sample > data.threshold || outer_sample > data.threshold) { + struct sample s; + ++ ret = 1; ++ + data.count++; + s.seqnum = data.count; + s.duration = sample; +@@ -295,7 +297,6 @@ static int get_sample(void *unused) + data.max_sample = sample; + } + +- ret = 0; + out: + return ret; + } +@@ -305,32 +306,30 @@ static int get_sample(void *unused) + * @unused: A required part of the kthread API. + * + * Used to periodically sample the CPU TSC via a call to get_sample. We +- * use stop_machine, whith does (intentionally) introduce latency since we ++ * disable interrupts, which does (intentionally) introduce latency since we + * need to ensure nothing else might be running (and thus pre-empting). + * Obviously this should never be used in production environments. + * +- * stop_machine will schedule us typically only on CPU0 which is fine for +- * almost every real-world hardware latency situation - but we might later +- * generalize this if we find there are any actualy systems with alternate +- * SMI delivery or other non CPU0 hardware latencies. ++ * Currently this runs on which ever CPU it was scheduled on, but most ++ * real-worald hardware latency situations occur across several CPUs, ++ * but we might later generalize this if we find there are any actualy ++ * systems with alternate SMI delivery or other hardware latencies. + */ + static int kthread_fn(void *unused) + { +- int err = 0; +- u64 interval = 0; ++ int ret; ++ u64 interval; + + while (!kthread_should_stop()) { + + mutex_lock(&data.lock); + +- err = stop_machine(get_sample, unused, 0); +- if (err) { +- /* Houston, we have a problem */ +- mutex_unlock(&data.lock); +- goto err_out; +- } ++ local_irq_disable(); ++ ret = get_sample(); ++ local_irq_enable(); + +- wake_up(&data.wq); /* wake up reader(s) */ ++ if (ret > 0) ++ wake_up(&data.wq); /* wake up reader(s) */ + + interval = data.sample_window - data.sample_width; + do_div(interval, USEC_PER_MSEC); /* modifies interval value */ +@@ -338,15 +337,10 @@ static int kthread_fn(void *unused) + mutex_unlock(&data.lock); + + if (msleep_interruptible(interval)) +- goto out; ++ break; + } +- goto out; +-err_out: +- pr_err(BANNER "could not call stop_machine, disabling\n"); +- enabled = 0; +-out: +- return err; + ++ return 0; + } + + /** +@@ -442,8 +436,7 @@ static int init_stats(void) + * This function provides a generic read implementation for the global state + * "data" structure debugfs filesystem entries. It would be nice to use + * simple_attr_read directly, but we need to make sure that the data.lock +- * spinlock is held during the actual read (even though we likely won't ever +- * actually race here as the updater runs under a stop_machine context). ++ * is held during the actual read. + */ + static ssize_t simple_data_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos, const u64 *entry) +@@ -478,8 +471,7 @@ static ssize_t simple_data_read(struct f + * This function provides a generic write implementation for the global state + * "data" structure debugfs filesystem entries. It would be nice to use + * simple_attr_write directly, but we need to make sure that the data.lock +- * spinlock is held during the actual write (even though we likely won't ever +- * actually race here as the updater runs under a stop_machine context). ++ * is held during the actual write. + */ + static ssize_t simple_data_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos, u64 *entry) diff --git a/debian/patches/features/all/rt/hwlat-detector-Use-trace_clock_local-if-available.patch b/debian/patches/features/all/rt/hwlat-detector-Use-trace_clock_local-if-available.patch new file mode 100644 index 000000000..c50005449 --- /dev/null +++ b/debian/patches/features/all/rt/hwlat-detector-Use-trace_clock_local-if-available.patch @@ -0,0 +1,93 @@ +From: Steven Rostedt +Date: Mon, 19 Aug 2013 17:33:26 -0400 +Subject: hwlat-detector: Use trace_clock_local if available +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +As ktime_get() calls into the timing code which does a read_seq(), it +may be affected by other CPUS that touch that lock. To remove this +dependency, use the trace_clock_local() which is already exported +for module use. If CONFIG_TRACING is enabled, use that as the clock, +otherwise use ktime_get(). + +Signed-off-by: Steven Rostedt +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/misc/hwlat_detector.c | 34 +++++++++++++++++++++++++--------- + 1 file changed, 25 insertions(+), 9 deletions(-) + +--- a/drivers/misc/hwlat_detector.c ++++ b/drivers/misc/hwlat_detector.c +@@ -51,6 +51,7 @@ + #include + #include + #include ++#include + + #define BUF_SIZE_DEFAULT 262144UL /* 8K*(sizeof(entry)) */ + #define BUF_FLAGS (RB_FL_OVERWRITE) /* no block on full */ +@@ -211,6 +212,21 @@ static struct sample *buffer_get_sample( + return sample; + } + ++#ifndef CONFIG_TRACING ++#define time_type ktime_t ++#define time_get() ktime_get() ++#define time_to_us(x) ktime_to_us(x) ++#define time_sub(a, b) ktime_sub(a, b) ++#define init_time(a, b) (a).tv64 = b ++#define time_u64(a) ((a).tv64) ++#else ++#define time_type u64 ++#define time_get() trace_clock_local() ++#define time_to_us(x) div_u64(x, 1000) ++#define time_sub(a, b) ((a) - (b)) ++#define init_time(a, b) (a = b) ++#define time_u64(a) a ++#endif + /** + * get_sample - sample the CPU TSC and look for likely hardware latencies + * @unused: This is not used but is a part of the stop_machine API +@@ -220,23 +236,23 @@ static struct sample *buffer_get_sample( + */ + static int get_sample(void *unused) + { +- ktime_t start, t1, t2, last_t2; ++ time_type start, t1, t2, last_t2; + s64 diff, total = 0; + u64 sample = 0; + u64 outer_sample = 0; + int ret = 1; + +- last_t2.tv64 = 0; +- start = ktime_get(); /* start timestamp */ ++ init_time(last_t2, 0); ++ start = time_get(); /* start timestamp */ + + do { + +- t1 = ktime_get(); /* we'll look for a discontinuity */ +- t2 = ktime_get(); ++ t1 = time_get(); /* we'll look for a discontinuity */ ++ t2 = time_get(); + +- if (last_t2.tv64) { ++ if (time_u64(last_t2)) { + /* Check the delta from outer loop (t2 to next t1) */ +- diff = ktime_to_us(ktime_sub(t1, last_t2)); ++ diff = time_to_us(time_sub(t1, last_t2)); + /* This shouldn't happen */ + if (diff < 0) { + pr_err(BANNER "time running backwards\n"); +@@ -247,10 +263,10 @@ static int get_sample(void *unused) + } + last_t2 = t2; + +- total = ktime_to_us(ktime_sub(t2, start)); /* sample width */ ++ total = time_to_us(time_sub(t2, start)); /* sample width */ + + /* This checks the inner loop (t1 to t2) */ +- diff = ktime_to_us(ktime_sub(t2, t1)); /* current diff */ ++ diff = time_to_us(time_sub(t2, t1)); /* current diff */ + + /* This shouldn't happen */ + if (diff < 0) { diff --git a/debian/patches/features/all/rt/hwlatdetect.patch b/debian/patches/features/all/rt/hwlatdetect.patch new file mode 100644 index 000000000..d026fb74c --- /dev/null +++ b/debian/patches/features/all/rt/hwlatdetect.patch @@ -0,0 +1,1348 @@ +Subject: hwlatdetect.patch +From: Carsten Emde +Date: Tue, 19 Jul 2011 13:53:12 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Jon Masters developed this wonderful SMI detector. For details please +consult Documentation/hwlat_detector.txt. It could be ported to Linux +3.0 RT without any major change. + +Signed-off-by: Carsten Emde + +--- + Documentation/hwlat_detector.txt | 64 ++ + drivers/misc/Kconfig | 29 + drivers/misc/Makefile | 1 + drivers/misc/hwlat_detector.c | 1212 +++++++++++++++++++++++++++++++++++++++ + 4 files changed, 1306 insertions(+) + +--- /dev/null ++++ b/Documentation/hwlat_detector.txt +@@ -0,0 +1,64 @@ ++Introduction: ++------------- ++ ++The module hwlat_detector is a special purpose kernel module that is used to ++detect large system latencies induced by the behavior of certain underlying ++hardware or firmware, independent of Linux itself. The code was developed ++originally to detect SMIs (System Management Interrupts) on x86 systems, ++however there is nothing x86 specific about this patchset. It was ++originally written for use by the "RT" patch since the Real Time ++kernel is highly latency sensitive. ++ ++SMIs are usually not serviced by the Linux kernel, which typically does not ++even know that they are occuring. SMIs are instead are set up by BIOS code ++and are serviced by BIOS code, usually for "critical" events such as ++management of thermal sensors and fans. Sometimes though, SMIs are used for ++other tasks and those tasks can spend an inordinate amount of time in the ++handler (sometimes measured in milliseconds). Obviously this is a problem if ++you are trying to keep event service latencies down in the microsecond range. ++ ++The hardware latency detector works by hogging all of the cpus for configurable ++amounts of time (by calling stop_machine()), polling the CPU Time Stamp Counter ++for some period, then looking for gaps in the TSC data. Any gap indicates a ++time when the polling was interrupted and since the machine is stopped and ++interrupts turned off the only thing that could do that would be an SMI. ++ ++Note that the SMI detector should *NEVER* be used in a production environment. ++It is intended to be run manually to determine if the hardware platform has a ++problem with long system firmware service routines. ++ ++Usage: ++------ ++ ++Loading the module hwlat_detector passing the parameter "enabled=1" (or by ++setting the "enable" entry in "hwlat_detector" debugfs toggled on) is the only ++step required to start the hwlat_detector. It is possible to redefine the ++threshold in microseconds (us) above which latency spikes will be taken ++into account (parameter "threshold="). ++ ++Example: ++ ++ # modprobe hwlat_detector enabled=1 threshold=100 ++ ++After the module is loaded, it creates a directory named "hwlat_detector" under ++the debugfs mountpoint, "/debug/hwlat_detector" for this text. It is necessary ++to have debugfs mounted, which might be on /sys/debug on your system. ++ ++The /debug/hwlat_detector interface contains the following files: ++ ++count - number of latency spikes observed since last reset ++enable - a global enable/disable toggle (0/1), resets count ++max - maximum hardware latency actually observed (usecs) ++sample - a pipe from which to read current raw sample data ++ in the format ++ (can be opened O_NONBLOCK for a single sample) ++threshold - minimum latency value to be considered (usecs) ++width - time period to sample with CPUs held (usecs) ++ must be less than the total window size (enforced) ++window - total period of sampling, width being inside (usecs) ++ ++By default we will set width to 500,000 and window to 1,000,000, meaning that ++we will sample every 1,000,000 usecs (1s) for 500,000 usecs (0.5s). If we ++observe any latencies that exceed the threshold (initially 100 usecs), ++then we write to a global sample ring buffer of 8K samples, which is ++consumed by reading from the "sample" (pipe) debugfs file interface. +--- a/drivers/misc/Kconfig ++++ b/drivers/misc/Kconfig +@@ -121,6 +121,35 @@ config IBM_ASM + for information on the specific driver level and support statement + for your IBM server. + ++config HWLAT_DETECTOR ++ tristate "Testing module to detect hardware-induced latencies" ++ depends on DEBUG_FS ++ depends on RING_BUFFER ++ default m ++ ---help--- ++ A simple hardware latency detector. Use this module to detect ++ large latencies introduced by the behavior of the underlying ++ system firmware external to Linux. We do this using periodic ++ use of stop_machine to grab all available CPUs and measure ++ for unexplainable gaps in the CPU timestamp counter(s). By ++ default, the module is not enabled until the "enable" file ++ within the "hwlat_detector" debugfs directory is toggled. ++ ++ This module is often used to detect SMI (System Management ++ Interrupts) on x86 systems, though is not x86 specific. To ++ this end, we default to using a sample window of 1 second, ++ during which we will sample for 0.5 seconds. If an SMI or ++ similar event occurs during that time, it is recorded ++ into an 8K samples global ring buffer until retreived. ++ ++ WARNING: This software should never be enabled (it can be built ++ but should not be turned on after it is loaded) in a production ++ environment where high latencies are a concern since the ++ sampling mechanism actually introduces latencies for ++ regular tasks while the CPU(s) are being held. ++ ++ If unsure, say N ++ + config PHANTOM + tristate "Sensable PHANToM (PCI)" + depends on PCI +--- a/drivers/misc/Makefile ++++ b/drivers/misc/Makefile +@@ -38,6 +38,7 @@ obj-$(CONFIG_C2PORT) += c2port/ + obj-$(CONFIG_HMC6352) += hmc6352.o + obj-y += eeprom/ + obj-y += cb710/ ++obj-$(CONFIG_HWLAT_DETECTOR) += hwlat_detector.o + obj-$(CONFIG_SPEAR13XX_PCIE_GADGET) += spear13xx_pcie_gadget.o + obj-$(CONFIG_VMWARE_BALLOON) += vmw_balloon.o + obj-$(CONFIG_ARM_CHARLCD) += arm-charlcd.o +--- /dev/null ++++ b/drivers/misc/hwlat_detector.c +@@ -0,0 +1,1212 @@ ++/* ++ * hwlat_detector.c - A simple Hardware Latency detector. ++ * ++ * Use this module to detect large system latencies induced by the behavior of ++ * certain underlying system hardware or firmware, independent of Linux itself. ++ * The code was developed originally to detect the presence of SMIs on Intel ++ * and AMD systems, although there is no dependency upon x86 herein. ++ * ++ * The classical example usage of this module is in detecting the presence of ++ * SMIs or System Management Interrupts on Intel and AMD systems. An SMI is a ++ * somewhat special form of hardware interrupt spawned from earlier CPU debug ++ * modes in which the (BIOS/EFI/etc.) firmware arranges for the South Bridge ++ * LPC (or other device) to generate a special interrupt under certain ++ * circumstances, for example, upon expiration of a special SMI timer device, ++ * due to certain external thermal readings, on certain I/O address accesses, ++ * and other situations. An SMI hits a special CPU pin, triggers a special ++ * SMI mode (complete with special memory map), and the OS is unaware. ++ * ++ * Although certain hardware-inducing latencies are necessary (for example, ++ * a modern system often requires an SMI handler for correct thermal control ++ * and remote management) they can wreak havoc upon any OS-level performance ++ * guarantees toward low-latency, especially when the OS is not even made ++ * aware of the presence of these interrupts. For this reason, we need a ++ * somewhat brute force mechanism to detect these interrupts. In this case, ++ * we do it by hogging all of the CPU(s) for configurable timer intervals, ++ * sampling the built-in CPU timer, looking for discontiguous readings. ++ * ++ * WARNING: This implementation necessarily introduces latencies. Therefore, ++ * you should NEVER use this module in a production environment ++ * requiring any kind of low-latency performance guarantee(s). ++ * ++ * Copyright (C) 2008-2009 Jon Masters, Red Hat, Inc. ++ * ++ * Includes useful feedback from Clark Williams ++ * ++ * This file is licensed under the terms of the GNU General Public ++ * License version 2. This program is licensed "as is" without any ++ * warranty of any kind, whether express or implied. ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++#define BUF_SIZE_DEFAULT 262144UL /* 8K*(sizeof(entry)) */ ++#define BUF_FLAGS (RB_FL_OVERWRITE) /* no block on full */ ++#define U64STR_SIZE 22 /* 20 digits max */ ++ ++#define VERSION "1.0.0" ++#define BANNER "hwlat_detector: " ++#define DRVNAME "hwlat_detector" ++#define DEFAULT_SAMPLE_WINDOW 1000000 /* 1s */ ++#define DEFAULT_SAMPLE_WIDTH 500000 /* 0.5s */ ++#define DEFAULT_LAT_THRESHOLD 10 /* 10us */ ++ ++/* Module metadata */ ++ ++MODULE_LICENSE("GPL"); ++MODULE_AUTHOR("Jon Masters "); ++MODULE_DESCRIPTION("A simple hardware latency detector"); ++MODULE_VERSION(VERSION); ++ ++/* Module parameters */ ++ ++static int debug; ++static int enabled; ++static int threshold; ++ ++module_param(debug, int, 0); /* enable debug */ ++module_param(enabled, int, 0); /* enable detector */ ++module_param(threshold, int, 0); /* latency threshold */ ++ ++/* Buffering and sampling */ ++ ++static struct ring_buffer *ring_buffer; /* sample buffer */ ++static DEFINE_MUTEX(ring_buffer_mutex); /* lock changes */ ++static unsigned long buf_size = BUF_SIZE_DEFAULT; ++static struct task_struct *kthread; /* sampling thread */ ++ ++/* DebugFS filesystem entries */ ++ ++static struct dentry *debug_dir; /* debugfs directory */ ++static struct dentry *debug_max; /* maximum TSC delta */ ++static struct dentry *debug_count; /* total detect count */ ++static struct dentry *debug_sample_width; /* sample width us */ ++static struct dentry *debug_sample_window; /* sample window us */ ++static struct dentry *debug_sample; /* raw samples us */ ++static struct dentry *debug_threshold; /* threshold us */ ++static struct dentry *debug_enable; /* enable/disable */ ++ ++/* Individual samples and global state */ ++ ++struct sample; /* latency sample */ ++struct data; /* Global state */ ++ ++/* Sampling functions */ ++static int __buffer_add_sample(struct sample *sample); ++static struct sample *buffer_get_sample(struct sample *sample); ++static int get_sample(void *unused); ++ ++/* Threading and state */ ++static int kthread_fn(void *unused); ++static int start_kthread(void); ++static int stop_kthread(void); ++static void __reset_stats(void); ++static int init_stats(void); ++ ++/* Debugfs interface */ ++static ssize_t simple_data_read(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos, const u64 *entry); ++static ssize_t simple_data_write(struct file *filp, const char __user *ubuf, ++ size_t cnt, loff_t *ppos, u64 *entry); ++static int debug_sample_fopen(struct inode *inode, struct file *filp); ++static ssize_t debug_sample_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos); ++static int debug_sample_release(struct inode *inode, struct file *filp); ++static int debug_enable_fopen(struct inode *inode, struct file *filp); ++static ssize_t debug_enable_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos); ++static ssize_t debug_enable_fwrite(struct file *file, ++ const char __user *user_buffer, ++ size_t user_size, loff_t *offset); ++ ++/* Initialization functions */ ++static int init_debugfs(void); ++static void free_debugfs(void); ++static int detector_init(void); ++static void detector_exit(void); ++ ++/* Individual latency samples are stored here when detected and packed into ++ * the ring_buffer circular buffer, where they are overwritten when ++ * more than buf_size/sizeof(sample) samples are received. */ ++struct sample { ++ u64 seqnum; /* unique sequence */ ++ u64 duration; /* ktime delta */ ++ struct timespec timestamp; /* wall time */ ++ unsigned long lost; ++}; ++ ++/* keep the global state somewhere. Mostly used under stop_machine. */ ++static struct data { ++ ++ struct mutex lock; /* protect changes */ ++ ++ u64 count; /* total since reset */ ++ u64 max_sample; /* max hardware latency */ ++ u64 threshold; /* sample threshold level */ ++ ++ u64 sample_window; /* total sampling window (on+off) */ ++ u64 sample_width; /* active sampling portion of window */ ++ ++ atomic_t sample_open; /* whether the sample file is open */ ++ ++ wait_queue_head_t wq; /* waitqeue for new sample values */ ++ ++} data; ++ ++/** ++ * __buffer_add_sample - add a new latency sample recording to the ring buffer ++ * @sample: The new latency sample value ++ * ++ * This receives a new latency sample and records it in a global ring buffer. ++ * No additional locking is used in this case - suited for stop_machine use. ++ */ ++static int __buffer_add_sample(struct sample *sample) ++{ ++ return ring_buffer_write(ring_buffer, ++ sizeof(struct sample), sample); ++} ++ ++/** ++ * buffer_get_sample - remove a hardware latency sample from the ring buffer ++ * @sample: Pre-allocated storage for the sample ++ * ++ * This retrieves a hardware latency sample from the global circular buffer ++ */ ++static struct sample *buffer_get_sample(struct sample *sample) ++{ ++ struct ring_buffer_event *e = NULL; ++ struct sample *s = NULL; ++ unsigned int cpu = 0; ++ ++ if (!sample) ++ return NULL; ++ ++ mutex_lock(&ring_buffer_mutex); ++ for_each_online_cpu(cpu) { ++ e = ring_buffer_consume(ring_buffer, cpu, NULL, &sample->lost); ++ if (e) ++ break; ++ } ++ ++ if (e) { ++ s = ring_buffer_event_data(e); ++ memcpy(sample, s, sizeof(struct sample)); ++ } else ++ sample = NULL; ++ mutex_unlock(&ring_buffer_mutex); ++ ++ return sample; ++} ++ ++/** ++ * get_sample - sample the CPU TSC and look for likely hardware latencies ++ * @unused: This is not used but is a part of the stop_machine API ++ * ++ * Used to repeatedly capture the CPU TSC (or similar), looking for potential ++ * hardware-induced latency. Called under stop_machine, with data.lock held. ++ */ ++static int get_sample(void *unused) ++{ ++ ktime_t start, t1, t2; ++ s64 diff, total = 0; ++ u64 sample = 0; ++ int ret = 1; ++ ++ start = ktime_get(); /* start timestamp */ ++ ++ do { ++ ++ t1 = ktime_get(); /* we'll look for a discontinuity */ ++ t2 = ktime_get(); ++ ++ total = ktime_to_us(ktime_sub(t2, start)); /* sample width */ ++ diff = ktime_to_us(ktime_sub(t2, t1)); /* current diff */ ++ ++ /* This shouldn't happen */ ++ if (diff < 0) { ++ pr_err(BANNER "time running backwards\n"); ++ goto out; ++ } ++ ++ if (diff > sample) ++ sample = diff; /* only want highest value */ ++ ++ } while (total <= data.sample_width); ++ ++ /* If we exceed the threshold value, we have found a hardware latency */ ++ if (sample > data.threshold) { ++ struct sample s; ++ ++ data.count++; ++ s.seqnum = data.count; ++ s.duration = sample; ++ s.timestamp = CURRENT_TIME; ++ __buffer_add_sample(&s); ++ ++ /* Keep a running maximum ever recorded hardware latency */ ++ if (sample > data.max_sample) ++ data.max_sample = sample; ++ } ++ ++ ret = 0; ++out: ++ return ret; ++} ++ ++/* ++ * kthread_fn - The CPU time sampling/hardware latency detection kernel thread ++ * @unused: A required part of the kthread API. ++ * ++ * Used to periodically sample the CPU TSC via a call to get_sample. We ++ * use stop_machine, whith does (intentionally) introduce latency since we ++ * need to ensure nothing else might be running (and thus pre-empting). ++ * Obviously this should never be used in production environments. ++ * ++ * stop_machine will schedule us typically only on CPU0 which is fine for ++ * almost every real-world hardware latency situation - but we might later ++ * generalize this if we find there are any actualy systems with alternate ++ * SMI delivery or other non CPU0 hardware latencies. ++ */ ++static int kthread_fn(void *unused) ++{ ++ int err = 0; ++ u64 interval = 0; ++ ++ while (!kthread_should_stop()) { ++ ++ mutex_lock(&data.lock); ++ ++ err = stop_machine(get_sample, unused, 0); ++ if (err) { ++ /* Houston, we have a problem */ ++ mutex_unlock(&data.lock); ++ goto err_out; ++ } ++ ++ wake_up(&data.wq); /* wake up reader(s) */ ++ ++ interval = data.sample_window - data.sample_width; ++ do_div(interval, USEC_PER_MSEC); /* modifies interval value */ ++ ++ mutex_unlock(&data.lock); ++ ++ if (msleep_interruptible(interval)) ++ goto out; ++ } ++ goto out; ++err_out: ++ pr_err(BANNER "could not call stop_machine, disabling\n"); ++ enabled = 0; ++out: ++ return err; ++ ++} ++ ++/** ++ * start_kthread - Kick off the hardware latency sampling/detector kthread ++ * ++ * This starts a kernel thread that will sit and sample the CPU timestamp ++ * counter (TSC or similar) and look for potential hardware latencies. ++ */ ++static int start_kthread(void) ++{ ++ kthread = kthread_run(kthread_fn, NULL, ++ DRVNAME); ++ if (IS_ERR(kthread)) { ++ pr_err(BANNER "could not start sampling thread\n"); ++ enabled = 0; ++ return -ENOMEM; ++ } ++ ++ return 0; ++} ++ ++/** ++ * stop_kthread - Inform the hardware latency samping/detector kthread to stop ++ * ++ * This kicks the running hardware latency sampling/detector kernel thread and ++ * tells it to stop sampling now. Use this on unload and at system shutdown. ++ */ ++static int stop_kthread(void) ++{ ++ int ret; ++ ++ ret = kthread_stop(kthread); ++ ++ return ret; ++} ++ ++/** ++ * __reset_stats - Reset statistics for the hardware latency detector ++ * ++ * We use data to store various statistics and global state. We call this ++ * function in order to reset those when "enable" is toggled on or off, and ++ * also at initialization. Should be called with data.lock held. ++ */ ++static void __reset_stats(void) ++{ ++ data.count = 0; ++ data.max_sample = 0; ++ ring_buffer_reset(ring_buffer); /* flush out old sample entries */ ++} ++ ++/** ++ * init_stats - Setup global state statistics for the hardware latency detector ++ * ++ * We use data to store various statistics and global state. We also use ++ * a global ring buffer (ring_buffer) to keep raw samples of detected hardware ++ * induced system latencies. This function initializes these structures and ++ * allocates the global ring buffer also. ++ */ ++static int init_stats(void) ++{ ++ int ret = -ENOMEM; ++ ++ mutex_init(&data.lock); ++ init_waitqueue_head(&data.wq); ++ atomic_set(&data.sample_open, 0); ++ ++ ring_buffer = ring_buffer_alloc(buf_size, BUF_FLAGS); ++ ++ if (WARN(!ring_buffer, KERN_ERR BANNER ++ "failed to allocate ring buffer!\n")) ++ goto out; ++ ++ __reset_stats(); ++ data.threshold = DEFAULT_LAT_THRESHOLD; /* threshold us */ ++ data.sample_window = DEFAULT_SAMPLE_WINDOW; /* window us */ ++ data.sample_width = DEFAULT_SAMPLE_WIDTH; /* width us */ ++ ++ ret = 0; ++ ++out: ++ return ret; ++ ++} ++ ++/* ++ * simple_data_read - Wrapper read function for global state debugfs entries ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * @entry: The entry to read from ++ * ++ * This function provides a generic read implementation for the global state ++ * "data" structure debugfs filesystem entries. It would be nice to use ++ * simple_attr_read directly, but we need to make sure that the data.lock ++ * spinlock is held during the actual read (even though we likely won't ever ++ * actually race here as the updater runs under a stop_machine context). ++ */ ++static ssize_t simple_data_read(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos, const u64 *entry) ++{ ++ char buf[U64STR_SIZE]; ++ u64 val = 0; ++ int len = 0; ++ ++ memset(buf, 0, sizeof(buf)); ++ ++ if (!entry) ++ return -EFAULT; ++ ++ mutex_lock(&data.lock); ++ val = *entry; ++ mutex_unlock(&data.lock); ++ ++ len = snprintf(buf, sizeof(buf), "%llu\n", (unsigned long long)val); ++ ++ return simple_read_from_buffer(ubuf, cnt, ppos, buf, len); ++ ++} ++ ++/* ++ * simple_data_write - Wrapper write function for global state debugfs entries ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to write value from ++ * @cnt: The maximum number of bytes to write ++ * @ppos: The current "file" position ++ * @entry: The entry to write to ++ * ++ * This function provides a generic write implementation for the global state ++ * "data" structure debugfs filesystem entries. It would be nice to use ++ * simple_attr_write directly, but we need to make sure that the data.lock ++ * spinlock is held during the actual write (even though we likely won't ever ++ * actually race here as the updater runs under a stop_machine context). ++ */ ++static ssize_t simple_data_write(struct file *filp, const char __user *ubuf, ++ size_t cnt, loff_t *ppos, u64 *entry) ++{ ++ char buf[U64STR_SIZE]; ++ int csize = min(cnt, sizeof(buf)); ++ u64 val = 0; ++ int err = 0; ++ ++ memset(buf, '\0', sizeof(buf)); ++ if (copy_from_user(buf, ubuf, csize)) ++ return -EFAULT; ++ ++ buf[U64STR_SIZE-1] = '\0'; /* just in case */ ++ err = kstrtoull(buf, 10, &val); ++ if (err) ++ return -EINVAL; ++ ++ mutex_lock(&data.lock); ++ *entry = val; ++ mutex_unlock(&data.lock); ++ ++ return csize; ++} ++ ++/** ++ * debug_count_fopen - Open function for "count" debugfs entry ++ * @inode: The in-kernel inode representation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function provides an open implementation for the "count" debugfs ++ * interface to the hardware latency detector. ++ */ ++static int debug_count_fopen(struct inode *inode, struct file *filp) ++{ ++ return 0; ++} ++ ++/** ++ * debug_count_fread - Read function for "count" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * ++ * This function provides a read implementation for the "count" debugfs ++ * interface to the hardware latency detector. Can be used to read the ++ * number of latency readings exceeding the configured threshold since ++ * the detector was last reset (e.g. by writing a zero into "count"). ++ */ ++static ssize_t debug_count_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ return simple_data_read(filp, ubuf, cnt, ppos, &data.count); ++} ++ ++/** ++ * debug_count_fwrite - Write function for "count" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that contains the value to write ++ * @cnt: The maximum number of bytes to write to "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function provides a write implementation for the "count" debugfs ++ * interface to the hardware latency detector. Can be used to write a ++ * desired value, especially to zero the total count. ++ */ ++static ssize_t debug_count_fwrite(struct file *filp, ++ const char __user *ubuf, ++ size_t cnt, ++ loff_t *ppos) ++{ ++ return simple_data_write(filp, ubuf, cnt, ppos, &data.count); ++} ++ ++/** ++ * debug_enable_fopen - Dummy open function for "enable" debugfs interface ++ * @inode: The in-kernel inode representation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function provides an open implementation for the "enable" debugfs ++ * interface to the hardware latency detector. ++ */ ++static int debug_enable_fopen(struct inode *inode, struct file *filp) ++{ ++ return 0; ++} ++ ++/** ++ * debug_enable_fread - Read function for "enable" debugfs interface ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * ++ * This function provides a read implementation for the "enable" debugfs ++ * interface to the hardware latency detector. Can be used to determine ++ * whether the detector is currently enabled ("0\n" or "1\n" returned). ++ */ ++static ssize_t debug_enable_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ char buf[4]; ++ ++ if ((cnt < sizeof(buf)) || (*ppos)) ++ return 0; ++ ++ buf[0] = enabled ? '1' : '0'; ++ buf[1] = '\n'; ++ buf[2] = '\0'; ++ if (copy_to_user(ubuf, buf, strlen(buf))) ++ return -EFAULT; ++ return *ppos = strlen(buf); ++} ++ ++/** ++ * debug_enable_fwrite - Write function for "enable" debugfs interface ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that contains the value to write ++ * @cnt: The maximum number of bytes to write to "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function provides a write implementation for the "enable" debugfs ++ * interface to the hardware latency detector. Can be used to enable or ++ * disable the detector, which will have the side-effect of possibly ++ * also resetting the global stats and kicking off the measuring ++ * kthread (on an enable) or the converse (upon a disable). ++ */ ++static ssize_t debug_enable_fwrite(struct file *filp, ++ const char __user *ubuf, ++ size_t cnt, ++ loff_t *ppos) ++{ ++ char buf[4]; ++ int csize = min(cnt, sizeof(buf)); ++ long val = 0; ++ int err = 0; ++ ++ memset(buf, '\0', sizeof(buf)); ++ if (copy_from_user(buf, ubuf, csize)) ++ return -EFAULT; ++ ++ buf[sizeof(buf)-1] = '\0'; /* just in case */ ++ err = kstrtoul(buf, 10, &val); ++ if (0 != err) ++ return -EINVAL; ++ ++ if (val) { ++ if (enabled) ++ goto unlock; ++ enabled = 1; ++ __reset_stats(); ++ if (start_kthread()) ++ return -EFAULT; ++ } else { ++ if (!enabled) ++ goto unlock; ++ enabled = 0; ++ err = stop_kthread(); ++ if (err) { ++ pr_err(BANNER "cannot stop kthread\n"); ++ return -EFAULT; ++ } ++ wake_up(&data.wq); /* reader(s) should return */ ++ } ++unlock: ++ return csize; ++} ++ ++/** ++ * debug_max_fopen - Open function for "max" debugfs entry ++ * @inode: The in-kernel inode representation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function provides an open implementation for the "max" debugfs ++ * interface to the hardware latency detector. ++ */ ++static int debug_max_fopen(struct inode *inode, struct file *filp) ++{ ++ return 0; ++} ++ ++/** ++ * debug_max_fread - Read function for "max" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * ++ * This function provides a read implementation for the "max" debugfs ++ * interface to the hardware latency detector. Can be used to determine ++ * the maximum latency value observed since it was last reset. ++ */ ++static ssize_t debug_max_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ return simple_data_read(filp, ubuf, cnt, ppos, &data.max_sample); ++} ++ ++/** ++ * debug_max_fwrite - Write function for "max" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that contains the value to write ++ * @cnt: The maximum number of bytes to write to "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function provides a write implementation for the "max" debugfs ++ * interface to the hardware latency detector. Can be used to reset the ++ * maximum or set it to some other desired value - if, then, subsequent ++ * measurements exceed this value, the maximum will be updated. ++ */ ++static ssize_t debug_max_fwrite(struct file *filp, ++ const char __user *ubuf, ++ size_t cnt, ++ loff_t *ppos) ++{ ++ return simple_data_write(filp, ubuf, cnt, ppos, &data.max_sample); ++} ++ ++ ++/** ++ * debug_sample_fopen - An open function for "sample" debugfs interface ++ * @inode: The in-kernel inode representation of this debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function handles opening the "sample" file within the hardware ++ * latency detector debugfs directory interface. This file is used to read ++ * raw samples from the global ring_buffer and allows the user to see a ++ * running latency history. Can be opened blocking or non-blocking, ++ * affecting whether it behaves as a buffer read pipe, or does not. ++ * Implements simple locking to prevent multiple simultaneous use. ++ */ ++static int debug_sample_fopen(struct inode *inode, struct file *filp) ++{ ++ if (!atomic_add_unless(&data.sample_open, 1, 1)) ++ return -EBUSY; ++ else ++ return 0; ++} ++ ++/** ++ * debug_sample_fread - A read function for "sample" debugfs interface ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that will contain the samples read ++ * @cnt: The maximum bytes to read from the debugfs "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function handles reading from the "sample" file within the hardware ++ * latency detector debugfs directory interface. This file is used to read ++ * raw samples from the global ring_buffer and allows the user to see a ++ * running latency history. By default this will block pending a new ++ * value written into the sample buffer, unless there are already a ++ * number of value(s) waiting in the buffer, or the sample file was ++ * previously opened in a non-blocking mode of operation. ++ */ ++static ssize_t debug_sample_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ int len = 0; ++ char buf[64]; ++ struct sample *sample = NULL; ++ ++ if (!enabled) ++ return 0; ++ ++ sample = kzalloc(sizeof(struct sample), GFP_KERNEL); ++ if (!sample) ++ return -ENOMEM; ++ ++ while (!buffer_get_sample(sample)) { ++ ++ DEFINE_WAIT(wait); ++ ++ if (filp->f_flags & O_NONBLOCK) { ++ len = -EAGAIN; ++ goto out; ++ } ++ ++ prepare_to_wait(&data.wq, &wait, TASK_INTERRUPTIBLE); ++ schedule(); ++ finish_wait(&data.wq, &wait); ++ ++ if (signal_pending(current)) { ++ len = -EINTR; ++ goto out; ++ } ++ ++ if (!enabled) { /* enable was toggled */ ++ len = 0; ++ goto out; ++ } ++ } ++ ++ len = snprintf(buf, sizeof(buf), "%010lu.%010lu\t%llu\n", ++ sample->timestamp.tv_sec, ++ sample->timestamp.tv_nsec, ++ sample->duration); ++ ++ ++ /* handling partial reads is more trouble than it's worth */ ++ if (len > cnt) ++ goto out; ++ ++ if (copy_to_user(ubuf, buf, len)) ++ len = -EFAULT; ++ ++out: ++ kfree(sample); ++ return len; ++} ++ ++/** ++ * debug_sample_release - Release function for "sample" debugfs interface ++ * @inode: The in-kernel inode represenation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function completes the close of the debugfs interface "sample" file. ++ * Frees the sample_open "lock" so that other users may open the interface. ++ */ ++static int debug_sample_release(struct inode *inode, struct file *filp) ++{ ++ atomic_dec(&data.sample_open); ++ ++ return 0; ++} ++ ++/** ++ * debug_threshold_fopen - Open function for "threshold" debugfs entry ++ * @inode: The in-kernel inode representation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function provides an open implementation for the "threshold" debugfs ++ * interface to the hardware latency detector. ++ */ ++static int debug_threshold_fopen(struct inode *inode, struct file *filp) ++{ ++ return 0; ++} ++ ++/** ++ * debug_threshold_fread - Read function for "threshold" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * ++ * This function provides a read implementation for the "threshold" debugfs ++ * interface to the hardware latency detector. It can be used to determine ++ * the current threshold level at which a latency will be recorded in the ++ * global ring buffer, typically on the order of 10us. ++ */ ++static ssize_t debug_threshold_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ return simple_data_read(filp, ubuf, cnt, ppos, &data.threshold); ++} ++ ++/** ++ * debug_threshold_fwrite - Write function for "threshold" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that contains the value to write ++ * @cnt: The maximum number of bytes to write to "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function provides a write implementation for the "threshold" debugfs ++ * interface to the hardware latency detector. It can be used to configure ++ * the threshold level at which any subsequently detected latencies will ++ * be recorded into the global ring buffer. ++ */ ++static ssize_t debug_threshold_fwrite(struct file *filp, ++ const char __user *ubuf, ++ size_t cnt, ++ loff_t *ppos) ++{ ++ int ret; ++ ++ ret = simple_data_write(filp, ubuf, cnt, ppos, &data.threshold); ++ ++ if (enabled) ++ wake_up_process(kthread); ++ ++ return ret; ++} ++ ++/** ++ * debug_width_fopen - Open function for "width" debugfs entry ++ * @inode: The in-kernel inode representation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function provides an open implementation for the "width" debugfs ++ * interface to the hardware latency detector. ++ */ ++static int debug_width_fopen(struct inode *inode, struct file *filp) ++{ ++ return 0; ++} ++ ++/** ++ * debug_width_fread - Read function for "width" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * ++ * This function provides a read implementation for the "width" debugfs ++ * interface to the hardware latency detector. It can be used to determine ++ * for how many us of the total window us we will actively sample for any ++ * hardware-induced latecy periods. Obviously, it is not possible to ++ * sample constantly and have the system respond to a sample reader, or, ++ * worse, without having the system appear to have gone out to lunch. ++ */ ++static ssize_t debug_width_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ return simple_data_read(filp, ubuf, cnt, ppos, &data.sample_width); ++} ++ ++/** ++ * debug_width_fwrite - Write function for "width" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that contains the value to write ++ * @cnt: The maximum number of bytes to write to "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function provides a write implementation for the "width" debugfs ++ * interface to the hardware latency detector. It can be used to configure ++ * for how many us of the total window us we will actively sample for any ++ * hardware-induced latency periods. Obviously, it is not possible to ++ * sample constantly and have the system respond to a sample reader, or, ++ * worse, without having the system appear to have gone out to lunch. It ++ * is enforced that width is less that the total window size. ++ */ ++static ssize_t debug_width_fwrite(struct file *filp, ++ const char __user *ubuf, ++ size_t cnt, ++ loff_t *ppos) ++{ ++ char buf[U64STR_SIZE]; ++ int csize = min(cnt, sizeof(buf)); ++ u64 val = 0; ++ int err = 0; ++ ++ memset(buf, '\0', sizeof(buf)); ++ if (copy_from_user(buf, ubuf, csize)) ++ return -EFAULT; ++ ++ buf[U64STR_SIZE-1] = '\0'; /* just in case */ ++ err = kstrtoull(buf, 10, &val); ++ if (0 != err) ++ return -EINVAL; ++ ++ mutex_lock(&data.lock); ++ if (val < data.sample_window) ++ data.sample_width = val; ++ else { ++ mutex_unlock(&data.lock); ++ return -EINVAL; ++ } ++ mutex_unlock(&data.lock); ++ ++ if (enabled) ++ wake_up_process(kthread); ++ ++ return csize; ++} ++ ++/** ++ * debug_window_fopen - Open function for "window" debugfs entry ++ * @inode: The in-kernel inode representation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function provides an open implementation for the "window" debugfs ++ * interface to the hardware latency detector. The window is the total time ++ * in us that will be considered one sample period. Conceptually, windows ++ * occur back-to-back and contain a sample width period during which ++ * actual sampling occurs. ++ */ ++static int debug_window_fopen(struct inode *inode, struct file *filp) ++{ ++ return 0; ++} ++ ++/** ++ * debug_window_fread - Read function for "window" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * ++ * This function provides a read implementation for the "window" debugfs ++ * interface to the hardware latency detector. The window is the total time ++ * in us that will be considered one sample period. Conceptually, windows ++ * occur back-to-back and contain a sample width period during which ++ * actual sampling occurs. Can be used to read the total window size. ++ */ ++static ssize_t debug_window_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ return simple_data_read(filp, ubuf, cnt, ppos, &data.sample_window); ++} ++ ++/** ++ * debug_window_fwrite - Write function for "window" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that contains the value to write ++ * @cnt: The maximum number of bytes to write to "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function provides a write implementation for the "window" debufds ++ * interface to the hardware latency detetector. The window is the total time ++ * in us that will be considered one sample period. Conceptually, windows ++ * occur back-to-back and contain a sample width period during which ++ * actual sampling occurs. Can be used to write a new total window size. It ++ * is enfoced that any value written must be greater than the sample width ++ * size, or an error results. ++ */ ++static ssize_t debug_window_fwrite(struct file *filp, ++ const char __user *ubuf, ++ size_t cnt, ++ loff_t *ppos) ++{ ++ char buf[U64STR_SIZE]; ++ int csize = min(cnt, sizeof(buf)); ++ u64 val = 0; ++ int err = 0; ++ ++ memset(buf, '\0', sizeof(buf)); ++ if (copy_from_user(buf, ubuf, csize)) ++ return -EFAULT; ++ ++ buf[U64STR_SIZE-1] = '\0'; /* just in case */ ++ err = kstrtoull(buf, 10, &val); ++ if (0 != err) ++ return -EINVAL; ++ ++ mutex_lock(&data.lock); ++ if (data.sample_width < val) ++ data.sample_window = val; ++ else { ++ mutex_unlock(&data.lock); ++ return -EINVAL; ++ } ++ mutex_unlock(&data.lock); ++ ++ return csize; ++} ++ ++/* ++ * Function pointers for the "count" debugfs file operations ++ */ ++static const struct file_operations count_fops = { ++ .open = debug_count_fopen, ++ .read = debug_count_fread, ++ .write = debug_count_fwrite, ++ .owner = THIS_MODULE, ++}; ++ ++/* ++ * Function pointers for the "enable" debugfs file operations ++ */ ++static const struct file_operations enable_fops = { ++ .open = debug_enable_fopen, ++ .read = debug_enable_fread, ++ .write = debug_enable_fwrite, ++ .owner = THIS_MODULE, ++}; ++ ++/* ++ * Function pointers for the "max" debugfs file operations ++ */ ++static const struct file_operations max_fops = { ++ .open = debug_max_fopen, ++ .read = debug_max_fread, ++ .write = debug_max_fwrite, ++ .owner = THIS_MODULE, ++}; ++ ++/* ++ * Function pointers for the "sample" debugfs file operations ++ */ ++static const struct file_operations sample_fops = { ++ .open = debug_sample_fopen, ++ .read = debug_sample_fread, ++ .release = debug_sample_release, ++ .owner = THIS_MODULE, ++}; ++ ++/* ++ * Function pointers for the "threshold" debugfs file operations ++ */ ++static const struct file_operations threshold_fops = { ++ .open = debug_threshold_fopen, ++ .read = debug_threshold_fread, ++ .write = debug_threshold_fwrite, ++ .owner = THIS_MODULE, ++}; ++ ++/* ++ * Function pointers for the "width" debugfs file operations ++ */ ++static const struct file_operations width_fops = { ++ .open = debug_width_fopen, ++ .read = debug_width_fread, ++ .write = debug_width_fwrite, ++ .owner = THIS_MODULE, ++}; ++ ++/* ++ * Function pointers for the "window" debugfs file operations ++ */ ++static const struct file_operations window_fops = { ++ .open = debug_window_fopen, ++ .read = debug_window_fread, ++ .write = debug_window_fwrite, ++ .owner = THIS_MODULE, ++}; ++ ++/** ++ * init_debugfs - A function to initialize the debugfs interface files ++ * ++ * This function creates entries in debugfs for "hwlat_detector", including ++ * files to read values from the detector, current samples, and the ++ * maximum sample that has been captured since the hardware latency ++ * dectector was started. ++ */ ++static int init_debugfs(void) ++{ ++ int ret = -ENOMEM; ++ ++ debug_dir = debugfs_create_dir(DRVNAME, NULL); ++ if (!debug_dir) ++ goto err_debug_dir; ++ ++ debug_sample = debugfs_create_file("sample", 0444, ++ debug_dir, NULL, ++ &sample_fops); ++ if (!debug_sample) ++ goto err_sample; ++ ++ debug_count = debugfs_create_file("count", 0444, ++ debug_dir, NULL, ++ &count_fops); ++ if (!debug_count) ++ goto err_count; ++ ++ debug_max = debugfs_create_file("max", 0444, ++ debug_dir, NULL, ++ &max_fops); ++ if (!debug_max) ++ goto err_max; ++ ++ debug_sample_window = debugfs_create_file("window", 0644, ++ debug_dir, NULL, ++ &window_fops); ++ if (!debug_sample_window) ++ goto err_window; ++ ++ debug_sample_width = debugfs_create_file("width", 0644, ++ debug_dir, NULL, ++ &width_fops); ++ if (!debug_sample_width) ++ goto err_width; ++ ++ debug_threshold = debugfs_create_file("threshold", 0644, ++ debug_dir, NULL, ++ &threshold_fops); ++ if (!debug_threshold) ++ goto err_threshold; ++ ++ debug_enable = debugfs_create_file("enable", 0644, ++ debug_dir, &enabled, ++ &enable_fops); ++ if (!debug_enable) ++ goto err_enable; ++ ++ else { ++ ret = 0; ++ goto out; ++ } ++ ++err_enable: ++ debugfs_remove(debug_threshold); ++err_threshold: ++ debugfs_remove(debug_sample_width); ++err_width: ++ debugfs_remove(debug_sample_window); ++err_window: ++ debugfs_remove(debug_max); ++err_max: ++ debugfs_remove(debug_count); ++err_count: ++ debugfs_remove(debug_sample); ++err_sample: ++ debugfs_remove(debug_dir); ++err_debug_dir: ++out: ++ return ret; ++} ++ ++/** ++ * free_debugfs - A function to cleanup the debugfs file interface ++ */ ++static void free_debugfs(void) ++{ ++ /* could also use a debugfs_remove_recursive */ ++ debugfs_remove(debug_enable); ++ debugfs_remove(debug_threshold); ++ debugfs_remove(debug_sample_width); ++ debugfs_remove(debug_sample_window); ++ debugfs_remove(debug_max); ++ debugfs_remove(debug_count); ++ debugfs_remove(debug_sample); ++ debugfs_remove(debug_dir); ++} ++ ++/** ++ * detector_init - Standard module initialization code ++ */ ++static int detector_init(void) ++{ ++ int ret = -ENOMEM; ++ ++ pr_info(BANNER "version %s\n", VERSION); ++ ++ ret = init_stats(); ++ if (0 != ret) ++ goto out; ++ ++ ret = init_debugfs(); ++ if (0 != ret) ++ goto err_stats; ++ ++ if (enabled) ++ ret = start_kthread(); ++ ++ goto out; ++ ++err_stats: ++ ring_buffer_free(ring_buffer); ++out: ++ return ret; ++ ++} ++ ++/** ++ * detector_exit - Standard module cleanup code ++ */ ++static void detector_exit(void) ++{ ++ int err; ++ ++ if (enabled) { ++ enabled = 0; ++ err = stop_kthread(); ++ if (err) ++ pr_err(BANNER "cannot stop kthread\n"); ++ } ++ ++ free_debugfs(); ++ ring_buffer_free(ring_buffer); /* free up the ring buffer */ ++ ++} ++ ++module_init(detector_init); ++module_exit(detector_exit); diff --git a/debian/patches/features/all/rt/i2c-omap-drop-the-lock-hard-irq-context.patch b/debian/patches/features/all/rt/i2c-omap-drop-the-lock-hard-irq-context.patch new file mode 100644 index 000000000..bb63eb0ae --- /dev/null +++ b/debian/patches/features/all/rt/i2c-omap-drop-the-lock-hard-irq-context.patch @@ -0,0 +1,34 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 21 Mar 2013 11:35:49 +0100 +Subject: i2c/omap: drop the lock hard irq context +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The lock is taken while reading two registers. On RT the first lock is +taken in hard irq where it might sleep and in the threaded irq. +The threaded irq runs in oneshot mode so the hard irq does not run until +the thread the completes so there is no reason to grab the lock. + +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/i2c/busses/i2c-omap.c | 5 +---- + 1 file changed, 1 insertion(+), 4 deletions(-) + +--- a/drivers/i2c/busses/i2c-omap.c ++++ b/drivers/i2c/busses/i2c-omap.c +@@ -996,15 +996,12 @@ omap_i2c_isr(int irq, void *dev_id) + u16 mask; + u16 stat; + +- spin_lock(&dev->lock); +- mask = omap_i2c_read_reg(dev, OMAP_I2C_IE_REG); + stat = omap_i2c_read_reg(dev, OMAP_I2C_STAT_REG); ++ mask = omap_i2c_read_reg(dev, OMAP_I2C_IE_REG); + + if (stat & mask) + ret = IRQ_WAKE_THREAD; + +- spin_unlock(&dev->lock); +- + return ret; + } + diff --git a/debian/patches/features/all/rt/i915-bogus-warning-from-i915-when-running-on-PREEMPT.patch b/debian/patches/features/all/rt/i915-bogus-warning-from-i915-when-running-on-PREEMPT.patch new file mode 100644 index 000000000..831d1c3d7 --- /dev/null +++ b/debian/patches/features/all/rt/i915-bogus-warning-from-i915-when-running-on-PREEMPT.patch @@ -0,0 +1,30 @@ +From: Clark Williams +Date: Tue, 26 May 2015 10:43:43 -0500 +Subject: i915: bogus warning from i915 when running on PREEMPT_RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The i915 driver has a 'WARN_ON(!in_interrupt())' in the display +handler, which whines constanly on the RT kernel (since the interrupt +is actually handled in a threaded handler and not actual interrupt +context). + +Change the WARN_ON to WARN_ON_NORT + +Tested-by: Joakim Hernberg +Signed-off-by: Clark Williams +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/gpu/drm/i915/intel_display.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/gpu/drm/i915/intel_display.c ++++ b/drivers/gpu/drm/i915/intel_display.c +@@ -10086,7 +10086,7 @@ void intel_check_page_flip(struct drm_de + struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe]; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + +- WARN_ON(!in_interrupt()); ++ WARN_ON_NONRT(!in_interrupt()); + + if (crtc == NULL) + return; diff --git a/debian/patches/features/all/rt/i915_compile_fix.patch b/debian/patches/features/all/rt/i915_compile_fix.patch new file mode 100644 index 000000000..9d6153f62 --- /dev/null +++ b/debian/patches/features/all/rt/i915_compile_fix.patch @@ -0,0 +1,24 @@ +From: Sebastian Andrzej Siewior +Date: Tue, 14 Jul 2015 14:26:34 +0200 +Subject: gpu/i915: don't open code these things +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The opencode part is gone in 1f83fee0 ("drm/i915: clear up wedged transitions") +the owner check is still there. + +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/gpu/drm/i915/i915_gem_shrinker.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c ++++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c +@@ -39,7 +39,7 @@ static bool mutex_is_locked_by(struct mu + if (!mutex_is_locked(mutex)) + return false; + +-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES) ++#if (defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES)) && !defined(CONFIG_PREEMPT_RT_BASE) + return mutex->owner == task; + #else + /* Since UP may be pre-empted, we cannot assume that we own the lock */ diff --git a/debian/patches/features/all/rt/ide-use-nort-local-irq-variants.patch b/debian/patches/features/all/rt/ide-use-nort-local-irq-variants.patch new file mode 100644 index 000000000..90eef3a53 --- /dev/null +++ b/debian/patches/features/all/rt/ide-use-nort-local-irq-variants.patch @@ -0,0 +1,170 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:30:16 -0500 +Subject: ide: Do not disable interrupts for PREEMPT-RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Use the local_irq_*_nort variants. + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + drivers/ide/alim15x3.c | 4 ++-- + drivers/ide/hpt366.c | 4 ++-- + drivers/ide/ide-io-std.c | 8 ++++---- + drivers/ide/ide-io.c | 2 +- + drivers/ide/ide-iops.c | 4 ++-- + drivers/ide/ide-probe.c | 4 ++-- + drivers/ide/ide-taskfile.c | 6 +++--- + 7 files changed, 16 insertions(+), 16 deletions(-) + +--- a/drivers/ide/alim15x3.c ++++ b/drivers/ide/alim15x3.c +@@ -234,7 +234,7 @@ static int init_chipset_ali15x3(struct p + + isa_dev = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, NULL); + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + + if (m5229_revision < 0xC2) { + /* +@@ -325,7 +325,7 @@ static int init_chipset_ali15x3(struct p + } + pci_dev_put(north); + pci_dev_put(isa_dev); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + return 0; + } + +--- a/drivers/ide/hpt366.c ++++ b/drivers/ide/hpt366.c +@@ -1241,7 +1241,7 @@ static int init_dma_hpt366(ide_hwif_t *h + + dma_old = inb(base + 2); + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + + dma_new = dma_old; + pci_read_config_byte(dev, hwif->channel ? 0x4b : 0x43, &masterdma); +@@ -1252,7 +1252,7 @@ static int init_dma_hpt366(ide_hwif_t *h + if (dma_new != dma_old) + outb(dma_new, base + 2); + +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + printk(KERN_INFO " %s: BM-DMA at 0x%04lx-0x%04lx\n", + hwif->name, base, base + 7); +--- a/drivers/ide/ide-io-std.c ++++ b/drivers/ide/ide-io-std.c +@@ -175,7 +175,7 @@ void ide_input_data(ide_drive_t *drive, + unsigned long uninitialized_var(flags); + + if ((io_32bit & 2) && !mmio) { +- local_irq_save(flags); ++ local_irq_save_nort(flags); + ata_vlb_sync(io_ports->nsect_addr); + } + +@@ -186,7 +186,7 @@ void ide_input_data(ide_drive_t *drive, + insl(data_addr, buf, words); + + if ((io_32bit & 2) && !mmio) +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + if (((len + 1) & 3) < 2) + return; +@@ -219,7 +219,7 @@ void ide_output_data(ide_drive_t *drive, + unsigned long uninitialized_var(flags); + + if ((io_32bit & 2) && !mmio) { +- local_irq_save(flags); ++ local_irq_save_nort(flags); + ata_vlb_sync(io_ports->nsect_addr); + } + +@@ -230,7 +230,7 @@ void ide_output_data(ide_drive_t *drive, + outsl(data_addr, buf, words); + + if ((io_32bit & 2) && !mmio) +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + if (((len + 1) & 3) < 2) + return; +--- a/drivers/ide/ide-io.c ++++ b/drivers/ide/ide-io.c +@@ -659,7 +659,7 @@ void ide_timer_expiry (unsigned long dat + /* disable_irq_nosync ?? */ + disable_irq(hwif->irq); + /* local CPU only, as if we were handling an interrupt */ +- local_irq_disable(); ++ local_irq_disable_nort(); + if (hwif->polling) { + startstop = handler(drive); + } else if (drive_is_ready(drive)) { +--- a/drivers/ide/ide-iops.c ++++ b/drivers/ide/ide-iops.c +@@ -129,12 +129,12 @@ int __ide_wait_stat(ide_drive_t *drive, + if ((stat & ATA_BUSY) == 0) + break; + +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + *rstat = stat; + return -EBUSY; + } + } +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + /* + * Allow status to settle, then read it again. +--- a/drivers/ide/ide-probe.c ++++ b/drivers/ide/ide-probe.c +@@ -196,10 +196,10 @@ static void do_identify(ide_drive_t *dri + int bswap = 1; + + /* local CPU only; some systems need this */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + /* read 512 bytes of id info */ + hwif->tp_ops->input_data(drive, NULL, id, SECTOR_SIZE); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + drive->dev_flags |= IDE_DFLAG_ID_READ; + #ifdef DEBUG +--- a/drivers/ide/ide-taskfile.c ++++ b/drivers/ide/ide-taskfile.c +@@ -250,7 +250,7 @@ void ide_pio_bytes(ide_drive_t *drive, s + + page_is_high = PageHighMem(page); + if (page_is_high) +- local_irq_save(flags); ++ local_irq_save_nort(flags); + + buf = kmap_atomic(page) + offset; + +@@ -271,7 +271,7 @@ void ide_pio_bytes(ide_drive_t *drive, s + kunmap_atomic(buf); + + if (page_is_high) +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + len -= nr_bytes; + } +@@ -414,7 +414,7 @@ static ide_startstop_t pre_task_out_intr + } + + if ((drive->dev_flags & IDE_DFLAG_UNMASK) == 0) +- local_irq_disable(); ++ local_irq_disable_nort(); + + ide_set_handler(drive, &task_pio_intr, WAIT_WORSTCASE); + diff --git a/debian/patches/features/all/rt/idr-use-local-lock-for-protection.patch b/debian/patches/features/all/rt/idr-use-local-lock-for-protection.patch new file mode 100644 index 000000000..691538b69 --- /dev/null +++ b/debian/patches/features/all/rt/idr-use-local-lock-for-protection.patch @@ -0,0 +1,97 @@ +From: Thomas Gleixner +Date: Tue, 14 Jul 2015 14:26:34 +0200 +Subject: idr: Use local lock instead of preempt enable/disable +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +We need to protect the per cpu variable and prevent migration. + +Signed-off-by: Thomas Gleixner +--- + include/linux/idr.h | 4 ++++ + lib/idr.c | 36 +++++++++++++++++++++++++++++++++--- + 2 files changed, 37 insertions(+), 3 deletions(-) + +--- a/include/linux/idr.h ++++ b/include/linux/idr.h +@@ -95,10 +95,14 @@ bool idr_is_empty(struct idr *idp); + * Each idr_preload() should be matched with an invocation of this + * function. See idr_preload() for details. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++void idr_preload_end(void); ++#else + static inline void idr_preload_end(void) + { + preempt_enable(); + } ++#endif + + /** + * idr_find - return pointer for given id +--- a/lib/idr.c ++++ b/lib/idr.c +@@ -30,6 +30,7 @@ + #include + #include + #include ++#include + + #define MAX_IDR_SHIFT (sizeof(int) * 8 - 1) + #define MAX_IDR_BIT (1U << MAX_IDR_SHIFT) +@@ -366,6 +367,35 @@ static void idr_fill_slot(struct idr *id + idr_mark_full(pa, id); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static DEFINE_LOCAL_IRQ_LOCK(idr_lock); ++ ++static inline void idr_preload_lock(void) ++{ ++ local_lock(idr_lock); ++} ++ ++static inline void idr_preload_unlock(void) ++{ ++ local_unlock(idr_lock); ++} ++ ++void idr_preload_end(void) ++{ ++ idr_preload_unlock(); ++} ++EXPORT_SYMBOL(idr_preload_end); ++#else ++static inline void idr_preload_lock(void) ++{ ++ preempt_disable(); ++} ++ ++static inline void idr_preload_unlock(void) ++{ ++ preempt_enable(); ++} ++#endif + + /** + * idr_preload - preload for idr_alloc() +@@ -401,7 +431,7 @@ void idr_preload(gfp_t gfp_mask) + WARN_ON_ONCE(in_interrupt()); + might_sleep_if(gfp_mask & __GFP_WAIT); + +- preempt_disable(); ++ idr_preload_lock(); + + /* + * idr_alloc() is likely to succeed w/o full idr_layer buffer and +@@ -413,9 +443,9 @@ void idr_preload(gfp_t gfp_mask) + while (__this_cpu_read(idr_preload_cnt) < MAX_IDR_FREE) { + struct idr_layer *new; + +- preempt_enable(); ++ idr_preload_unlock(); + new = kmem_cache_zalloc(idr_layer_cache, gfp_mask); +- preempt_disable(); ++ idr_preload_lock(); + if (!new) + break; + diff --git a/debian/patches/features/all/rt/infiniband-mellanox-ib-use-nort-irq.patch b/debian/patches/features/all/rt/infiniband-mellanox-ib-use-nort-irq.patch new file mode 100644 index 000000000..dc3cb129c --- /dev/null +++ b/debian/patches/features/all/rt/infiniband-mellanox-ib-use-nort-irq.patch @@ -0,0 +1,41 @@ +From: Sven-Thorsten Dietrich +Date: Fri, 3 Jul 2009 08:30:35 -0500 +Subject: infiniband: Mellanox IB driver patch use _nort() primitives +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Fixes in_atomic stack-dump, when Mellanox module is loaded into the RT +Kernel. + +Michael S. Tsirkin sayeth: +"Basically, if you just make spin_lock_irqsave (and spin_lock_irq) not disable +interrupts for non-raw spinlocks, I think all of infiniband will be fine without +changes." + +Signed-off-by: Sven-Thorsten Dietrich +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c ++++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +@@ -821,7 +821,7 @@ void ipoib_mcast_restart_task(struct wor + + ipoib_dbg_mcast(priv, "restarting multicast task\n"); + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + netif_addr_lock(dev); + spin_lock(&priv->lock); + +@@ -903,7 +903,7 @@ void ipoib_mcast_restart_task(struct wor + + spin_unlock(&priv->lock); + netif_addr_unlock(dev); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + /* + * make sure the in-flight joins have finished before we attempt diff --git a/debian/patches/features/all/rt/inpt-gameport-use-local-irq-nort.patch b/debian/patches/features/all/rt/inpt-gameport-use-local-irq-nort.patch new file mode 100644 index 000000000..887651eba --- /dev/null +++ b/debian/patches/features/all/rt/inpt-gameport-use-local-irq-nort.patch @@ -0,0 +1,45 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:30:16 -0500 +Subject: input: gameport: Do not disable interrupts on PREEMPT_RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Use the _nort() primitives. + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + drivers/input/gameport/gameport.c | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +--- a/drivers/input/gameport/gameport.c ++++ b/drivers/input/gameport/gameport.c +@@ -124,12 +124,12 @@ static int old_gameport_measure_speed(st + tx = 1 << 30; + + for(i = 0; i < 50; i++) { +- local_irq_save(flags); ++ local_irq_save_nort(flags); + GET_TIME(t1); + for (t = 0; t < 50; t++) gameport_read(gameport); + GET_TIME(t2); + GET_TIME(t3); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + udelay(i * 10); + if ((t = DELTA(t2,t1) - DELTA(t3,t2)) < tx) tx = t; + } +@@ -148,11 +148,11 @@ static int old_gameport_measure_speed(st + tx = 1 << 30; + + for(i = 0; i < 50; i++) { +- local_irq_save(flags); ++ local_irq_save_nort(flags); + rdtscl(t1); + for (t = 0; t < 50; t++) gameport_read(gameport); + rdtscl(t2); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + udelay(i * 10); + if (t2 - t1 < tx) tx = t2 - t1; + } diff --git a/debian/patches/features/all/rt/introduce_migrate_disable_cpu_light.patch b/debian/patches/features/all/rt/introduce_migrate_disable_cpu_light.patch new file mode 100644 index 000000000..d394b4592 --- /dev/null +++ b/debian/patches/features/all/rt/introduce_migrate_disable_cpu_light.patch @@ -0,0 +1,341 @@ +Subject: Intrduce migrate_disable() + cpu_light() +From: Thomas Gleixner +Date: Fri, 17 Jun 2011 15:42:38 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Introduce migrate_disable(). The task can't be pushed to another CPU but can +be preempted. + +From: Peter Zijlstra : +|Make migrate_disable() be a preempt_disable() for !rt kernels. This +|allows generic code to use it but still enforces that these code +|sections stay relatively small. +| +|A preemptible migrate_disable() accessible for general use would allow +|people growing arbitrary per-cpu crap instead of clean these things +|up. + +From: Steven Rostedt +| The migrate_disable() can cause a bit of a overhead to the RT kernel, +| as changing the affinity is expensive to do at every lock encountered. +| As a running task can not migrate, the actual disabling of migration +| does not need to occur until the task is about to schedule out. +| +| In most cases, a task that disables migration will enable it before +| it schedules making this change improve performance tremendously. + +On top of this build get/put_cpu_light(). It is similar to get_cpu(): +it uses migrate_disable() instead of preempt_disable(). That means the user +remains on the same CPU but the function using it may be preempted and +invoked again from another caller on the same CPU. + +Signed-off-by: Thomas Gleixner +--- + include/linux/cpu.h | 3 + + include/linux/preempt.h | 9 +++ + include/linux/sched.h | 29 +++++++++- + include/linux/smp.h | 3 + + kernel/sched/core.c | 131 ++++++++++++++++++++++++++++++++++++++++++++++-- + kernel/sched/debug.c | 7 ++ + lib/smp_processor_id.c | 5 + + 7 files changed, 178 insertions(+), 9 deletions(-) + +--- a/include/linux/cpu.h ++++ b/include/linux/cpu.h +@@ -221,6 +221,9 @@ static inline void smpboot_thread_init(v + #endif /* CONFIG_SMP */ + extern struct bus_type cpu_subsys; + ++static inline void pin_current_cpu(void) { } ++static inline void unpin_current_cpu(void) { } ++ + #ifdef CONFIG_HOTPLUG_CPU + /* Stop CPUs going up and down. */ + +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -153,11 +153,20 @@ do { \ + # define preempt_enable_rt() preempt_enable() + # define preempt_disable_nort() barrier() + # define preempt_enable_nort() barrier() ++# ifdef CONFIG_SMP ++ extern void migrate_disable(void); ++ extern void migrate_enable(void); ++# else /* CONFIG_SMP */ ++# define migrate_disable() barrier() ++# define migrate_enable() barrier() ++# endif /* CONFIG_SMP */ + #else + # define preempt_disable_rt() barrier() + # define preempt_enable_rt() barrier() + # define preempt_disable_nort() preempt_disable() + # define preempt_enable_nort() preempt_enable() ++# define migrate_disable() preempt_disable() ++# define migrate_enable() preempt_enable() + #endif + + #ifdef CONFIG_PREEMPT_NOTIFIERS +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -1371,6 +1371,12 @@ struct task_struct { + #endif + + unsigned int policy; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ int migrate_disable; ++# ifdef CONFIG_SCHED_DEBUG ++ int migrate_disable_atomic; ++# endif ++#endif + int nr_cpus_allowed; + cpumask_t cpus_allowed; + +@@ -1781,9 +1787,6 @@ struct task_struct { + int pagefault_disabled; + }; + +-/* Future-safe accessor for struct task_struct's cpus_allowed. */ +-#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) +- + #define TNF_MIGRATED 0x01 + #define TNF_NO_GROUP 0x02 + #define TNF_SHARED 0x04 +@@ -3072,6 +3075,26 @@ static inline void set_task_cpu(struct t + + #endif /* CONFIG_SMP */ + ++static inline int __migrate_disabled(struct task_struct *p) ++{ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ return p->migrate_disable; ++#else ++ return 0; ++#endif ++} ++ ++/* Future-safe accessor for struct task_struct's cpus_allowed. */ ++static inline const struct cpumask *tsk_cpus_allowed(struct task_struct *p) ++{ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (p->migrate_disable) ++ return cpumask_of(task_cpu(p)); ++#endif ++ ++ return &p->cpus_allowed; ++} ++ + extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); + extern long sched_getaffinity(pid_t pid, struct cpumask *mask); + +--- a/include/linux/smp.h ++++ b/include/linux/smp.h +@@ -185,6 +185,9 @@ static inline void smp_init(void) { } + #define get_cpu() ({ preempt_disable(); smp_processor_id(); }) + #define put_cpu() preempt_enable() + ++#define get_cpu_light() ({ migrate_disable(); smp_processor_id(); }) ++#define put_cpu_light() migrate_enable() ++ + /* + * Callback to arch code if there's nosmp or maxcpus=0 on the + * boot command line: +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -2696,6 +2696,125 @@ static inline void schedule_debug(struct + schedstat_inc(this_rq(), sched_count); + } + ++#if defined(CONFIG_PREEMPT_RT_FULL) && defined(CONFIG_SMP) ++#define MIGRATE_DISABLE_SET_AFFIN (1<<30) /* Can't make a negative */ ++#define migrate_disabled_updated(p) ((p)->migrate_disable & MIGRATE_DISABLE_SET_AFFIN) ++#define migrate_disable_count(p) ((p)->migrate_disable & ~MIGRATE_DISABLE_SET_AFFIN) ++ ++static inline void update_migrate_disable(struct task_struct *p) ++{ ++ const struct cpumask *mask; ++ ++ if (likely(!p->migrate_disable)) ++ return; ++ ++ /* Did we already update affinity? */ ++ if (unlikely(migrate_disabled_updated(p))) ++ return; ++ ++ /* ++ * Since this is always current we can get away with only locking ++ * rq->lock, the ->cpus_allowed value can normally only be changed ++ * while holding both p->pi_lock and rq->lock, but seeing that this ++ * is current, we cannot actually be waking up, so all code that ++ * relies on serialization against p->pi_lock is out of scope. ++ * ++ * Having rq->lock serializes us against things like ++ * set_cpus_allowed_ptr() that can still happen concurrently. ++ */ ++ mask = tsk_cpus_allowed(p); ++ ++ if (p->sched_class->set_cpus_allowed) ++ p->sched_class->set_cpus_allowed(p, mask); ++ /* mask==cpumask_of(task_cpu(p)) which has a cpumask_weight==1 */ ++ p->nr_cpus_allowed = 1; ++ ++ /* Let migrate_enable know to fix things back up */ ++ p->migrate_disable |= MIGRATE_DISABLE_SET_AFFIN; ++} ++ ++void migrate_disable(void) ++{ ++ struct task_struct *p = current; ++ ++ if (in_atomic() || p->flags & PF_NO_SETAFFINITY) { ++#ifdef CONFIG_SCHED_DEBUG ++ p->migrate_disable_atomic++; ++#endif ++ return; ++ } ++ ++#ifdef CONFIG_SCHED_DEBUG ++ WARN_ON_ONCE(p->migrate_disable_atomic); ++#endif ++ ++ if (p->migrate_disable) { ++ p->migrate_disable++; ++ return; ++ } ++ ++ preempt_disable(); ++ pin_current_cpu(); ++ p->migrate_disable = 1; ++ preempt_enable(); ++} ++EXPORT_SYMBOL(migrate_disable); ++ ++void migrate_enable(void) ++{ ++ struct task_struct *p = current; ++ const struct cpumask *mask; ++ unsigned long flags; ++ struct rq *rq; ++ ++ if (in_atomic() || p->flags & PF_NO_SETAFFINITY) { ++#ifdef CONFIG_SCHED_DEBUG ++ p->migrate_disable_atomic--; ++#endif ++ return; ++ } ++ ++#ifdef CONFIG_SCHED_DEBUG ++ WARN_ON_ONCE(p->migrate_disable_atomic); ++#endif ++ WARN_ON_ONCE(p->migrate_disable <= 0); ++ ++ if (migrate_disable_count(p) > 1) { ++ p->migrate_disable--; ++ return; ++ } ++ ++ preempt_disable(); ++ if (unlikely(migrate_disabled_updated(p))) { ++ /* ++ * Undo whatever update_migrate_disable() did, also see there ++ * about locking. ++ */ ++ rq = this_rq(); ++ raw_spin_lock_irqsave(&rq->lock, flags); ++ ++ /* ++ * Clearing migrate_disable causes tsk_cpus_allowed to ++ * show the tasks original cpu affinity. ++ */ ++ p->migrate_disable = 0; ++ mask = tsk_cpus_allowed(p); ++ if (p->sched_class->set_cpus_allowed) ++ p->sched_class->set_cpus_allowed(p, mask); ++ p->nr_cpus_allowed = cpumask_weight(mask); ++ raw_spin_unlock_irqrestore(&rq->lock, flags); ++ } else ++ p->migrate_disable = 0; ++ ++ unpin_current_cpu(); ++ preempt_enable(); ++} ++EXPORT_SYMBOL(migrate_enable); ++#else ++static inline void update_migrate_disable(struct task_struct *p) { } ++#define migrate_disabled_updated(p) 0 ++#endif ++ + /* + * Pick up the highest-prio task: + */ +@@ -2802,6 +2921,8 @@ static void __sched __schedule(void) + smp_mb__before_spinlock(); + raw_spin_lock_irq(&rq->lock); + ++ update_migrate_disable(prev); ++ + rq->clock_skip_update <<= 1; /* promote REQ to ACT */ + + switch_count = &prev->nivcsw; +@@ -4803,11 +4924,13 @@ static struct rq *move_queued_task(struc + + void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) + { +- if (p->sched_class->set_cpus_allowed) +- p->sched_class->set_cpus_allowed(p, new_mask); ++ if (!migrate_disabled_updated(p)) { ++ if (p->sched_class->set_cpus_allowed) ++ p->sched_class->set_cpus_allowed(p, new_mask); ++ p->nr_cpus_allowed = cpumask_weight(new_mask); ++ } + + cpumask_copy(&p->cpus_allowed, new_mask); +- p->nr_cpus_allowed = cpumask_weight(new_mask); + } + + /* +@@ -4853,7 +4976,7 @@ int set_cpus_allowed_ptr(struct task_str + do_set_cpus_allowed(p, new_mask); + + /* Can the task run on the task's current CPU? If so, we're done */ +- if (cpumask_test_cpu(task_cpu(p), new_mask)) ++ if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p)) + goto out; + + dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); +--- a/kernel/sched/debug.c ++++ b/kernel/sched/debug.c +@@ -260,6 +260,9 @@ void print_rt_rq(struct seq_file *m, int + P(rt_throttled); + PN(rt_time); + PN(rt_runtime); ++#ifdef CONFIG_SMP ++ P(rt_nr_migratory); ++#endif + + #undef PN + #undef P +@@ -648,6 +651,10 @@ void proc_sched_show_task(struct task_st + #endif + P(policy); + P(prio); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ P(migrate_disable); ++#endif ++ P(nr_cpus_allowed); + #undef PN + #undef __PN + #undef P +--- a/lib/smp_processor_id.c ++++ b/lib/smp_processor_id.c +@@ -39,8 +39,9 @@ notrace static unsigned int check_preemp + if (!printk_ratelimit()) + goto out_enable; + +- printk(KERN_ERR "BUG: using %s%s() in preemptible [%08x] code: %s/%d\n", +- what1, what2, preempt_count() - 1, current->comm, current->pid); ++ printk(KERN_ERR "BUG: using %s%s() in preemptible [%08x %08x] code: %s/%d\n", ++ what1, what2, preempt_count() - 1, __migrate_disabled(current), ++ current->comm, current->pid); + + print_symbol("caller is %s\n", (long)__builtin_return_address(0)); + dump_stack(); diff --git a/debian/patches/features/all/rt/ipc-make-rt-aware.patch b/debian/patches/features/all/rt/ipc-make-rt-aware.patch new file mode 100644 index 000000000..c3632e51e --- /dev/null +++ b/debian/patches/features/all/rt/ipc-make-rt-aware.patch @@ -0,0 +1,68 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:30:12 -0500 +Subject: ipc: Make the ipc code -rt aware +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +RT serializes the code with the (rt)spinlock but keeps preemption +enabled. Some parts of the code need to be atomic nevertheless. + +Protect it with preempt_disable/enable_rt pairts. + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + ipc/msg.c | 16 +++++++++++++++- + 1 file changed, 15 insertions(+), 1 deletion(-) + +--- a/ipc/msg.c ++++ b/ipc/msg.c +@@ -188,6 +188,12 @@ static void expunge_all(struct msg_queue + struct msg_receiver *msr, *t; + + list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) { ++ /* ++ * Make sure that the wakeup doesnt preempt ++ * this CPU prematurely. (on PREEMPT_RT) ++ */ ++ preempt_disable_rt(); ++ + msr->r_msg = NULL; /* initialize expunge ordering */ + wake_up_process(msr->r_tsk); + /* +@@ -198,6 +204,8 @@ static void expunge_all(struct msg_queue + */ + smp_mb(); + msr->r_msg = ERR_PTR(res); ++ ++ preempt_enable_rt(); + } + } + +@@ -574,6 +582,11 @@ static inline int pipelined_send(struct + if (testmsg(msg, msr->r_msgtype, msr->r_mode) && + !security_msg_queue_msgrcv(msq, msg, msr->r_tsk, + msr->r_msgtype, msr->r_mode)) { ++ /* ++ * Make sure that the wakeup doesnt preempt ++ * this CPU prematurely. (on PREEMPT_RT) ++ */ ++ preempt_disable_rt(); + + list_del(&msr->r_list); + if (msr->r_maxsize < msg->m_ts) { +@@ -595,12 +608,13 @@ static inline int pipelined_send(struct + */ + smp_mb(); + msr->r_msg = msg; ++ preempt_enable_rt(); + + return 1; + } ++ preempt_enable_rt(); + } + } +- + return 0; + } + diff --git a/debian/patches/features/all/rt/ipc-sem-rework-semaphore-wakeups.patch b/debian/patches/features/all/rt/ipc-sem-rework-semaphore-wakeups.patch new file mode 100644 index 000000000..96c9475f6 --- /dev/null +++ b/debian/patches/features/all/rt/ipc-sem-rework-semaphore-wakeups.patch @@ -0,0 +1,70 @@ +Subject: ipc/sem: Rework semaphore wakeups +From: Peter Zijlstra +Date: Wed, 14 Sep 2011 11:57:04 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Current sysv sems have a weird ass wakeup scheme that involves keeping +preemption disabled over a potential O(n^2) loop and busy waiting on +that on other CPUs. + +Kill this and simply wake the task directly from under the sem_lock. + +This was discovered by a migrate_disable() debug feature that +disallows: + + spin_lock(); + preempt_disable(); + spin_unlock() + preempt_enable(); + +Cc: Manfred Spraul +Suggested-by: Thomas Gleixner +Reported-by: Mike Galbraith +Signed-off-by: Peter Zijlstra +Cc: Manfred Spraul +Link: http://lkml.kernel.org/r/1315994224.5040.1.camel@twins +Signed-off-by: Thomas Gleixner +--- + ipc/sem.c | 10 ++++++++++ + 1 file changed, 10 insertions(+) + +--- a/ipc/sem.c ++++ b/ipc/sem.c +@@ -680,6 +680,13 @@ static int perform_atomic_semop(struct s + static void wake_up_sem_queue_prepare(struct list_head *pt, + struct sem_queue *q, int error) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct task_struct *p = q->sleeper; ++ get_task_struct(p); ++ q->status = error; ++ wake_up_process(p); ++ put_task_struct(p); ++#else + if (list_empty(pt)) { + /* + * Hold preempt off so that we don't get preempted and have the +@@ -691,6 +698,7 @@ static void wake_up_sem_queue_prepare(st + q->pid = error; + + list_add_tail(&q->list, pt); ++#endif + } + + /** +@@ -704,6 +712,7 @@ static void wake_up_sem_queue_prepare(st + */ + static void wake_up_sem_queue_do(struct list_head *pt) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + struct sem_queue *q, *t; + int did_something; + +@@ -716,6 +725,7 @@ static void wake_up_sem_queue_do(struct + } + if (did_something) + preempt_enable(); ++#endif + } + + static void unlink_queue(struct sem_array *sma, struct sem_queue *q) diff --git a/debian/patches/features/all/rt/irq-allow-disabling-of-softirq-processing-in-irq-thread-context.patch b/debian/patches/features/all/rt/irq-allow-disabling-of-softirq-processing-in-irq-thread-context.patch new file mode 100644 index 000000000..7ebb929ce --- /dev/null +++ b/debian/patches/features/all/rt/irq-allow-disabling-of-softirq-processing-in-irq-thread-context.patch @@ -0,0 +1,147 @@ +Subject: genirq: Allow disabling of softirq processing in irq thread context +From: Thomas Gleixner +Date: Tue, 31 Jan 2012 13:01:27 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The processing of softirqs in irq thread context is a performance gain +for the non-rt workloads of a system, but it's counterproductive for +interrupts which are explicitely related to the realtime +workload. Allow such interrupts to prevent softirq processing in their +thread context. + +Signed-off-by: Thomas Gleixner + +--- + include/linux/interrupt.h | 2 ++ + include/linux/irq.h | 4 +++- + kernel/irq/manage.c | 13 ++++++++++++- + kernel/irq/settings.h | 12 ++++++++++++ + kernel/softirq.c | 9 +++++++++ + 5 files changed, 38 insertions(+), 2 deletions(-) + +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -61,6 +61,7 @@ + * interrupt handler after suspending interrupts. For system + * wakeup devices users need to implement wakeup detection in + * their interrupt handlers. ++ * IRQF_NO_SOFTIRQ_CALL - Do not process softirqs in the irq thread context (RT) + */ + #define IRQF_SHARED 0x00000080 + #define IRQF_PROBE_SHARED 0x00000100 +@@ -74,6 +75,7 @@ + #define IRQF_NO_THREAD 0x00010000 + #define IRQF_EARLY_RESUME 0x00020000 + #define IRQF_COND_SUSPEND 0x00040000 ++#define IRQF_NO_SOFTIRQ_CALL 0x00080000 + + #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) + +--- a/include/linux/irq.h ++++ b/include/linux/irq.h +@@ -72,6 +72,7 @@ enum irqchip_irq_state; + * IRQ_IS_POLLED - Always polled by another interrupt. Exclude + * it from the spurious interrupt detection + * mechanism and from core side polling. ++ * IRQ_NO_SOFTIRQ_CALL - No softirq processing in the irq thread context (RT) + */ + enum { + IRQ_TYPE_NONE = 0x00000000, +@@ -97,13 +98,14 @@ enum { + IRQ_NOTHREAD = (1 << 16), + IRQ_PER_CPU_DEVID = (1 << 17), + IRQ_IS_POLLED = (1 << 18), ++ IRQ_NO_SOFTIRQ_CALL = (1 << 19), + }; + + #define IRQF_MODIFY_MASK \ + (IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \ + IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \ + IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \ +- IRQ_IS_POLLED) ++ IRQ_IS_POLLED | IRQ_NO_SOFTIRQ_CALL) + + #define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING) + +--- a/kernel/irq/manage.c ++++ b/kernel/irq/manage.c +@@ -900,7 +900,15 @@ irq_forced_thread_fn(struct irq_desc *de + local_bh_disable(); + ret = action->thread_fn(action->irq, action->dev_id); + irq_finalize_oneshot(desc, action); +- local_bh_enable(); ++ /* ++ * Interrupts which have real time requirements can be set up ++ * to avoid softirq processing in the thread handler. This is ++ * safe as these interrupts do not raise soft interrupts. ++ */ ++ if (irq_settings_no_softirq_call(desc)) ++ _local_bh_enable(); ++ else ++ local_bh_enable(); + return ret; + } + +@@ -1296,6 +1304,9 @@ static int + irqd_set(&desc->irq_data, IRQD_NO_BALANCING); + } + ++ if (new->flags & IRQF_NO_SOFTIRQ_CALL) ++ irq_settings_set_no_softirq_call(desc); ++ + /* Set default affinity mask once everything is setup */ + setup_affinity(irq, desc, mask); + +--- a/kernel/irq/settings.h ++++ b/kernel/irq/settings.h +@@ -15,6 +15,7 @@ enum { + _IRQ_NESTED_THREAD = IRQ_NESTED_THREAD, + _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID, + _IRQ_IS_POLLED = IRQ_IS_POLLED, ++ _IRQ_NO_SOFTIRQ_CALL = IRQ_NO_SOFTIRQ_CALL, + _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK, + }; + +@@ -28,6 +29,7 @@ enum { + #define IRQ_NESTED_THREAD GOT_YOU_MORON + #define IRQ_PER_CPU_DEVID GOT_YOU_MORON + #define IRQ_IS_POLLED GOT_YOU_MORON ++#define IRQ_NO_SOFTIRQ_CALL GOT_YOU_MORON + #undef IRQF_MODIFY_MASK + #define IRQF_MODIFY_MASK GOT_YOU_MORON + +@@ -38,6 +40,16 @@ irq_settings_clr_and_set(struct irq_desc + desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK); + } + ++static inline bool irq_settings_no_softirq_call(struct irq_desc *desc) ++{ ++ return desc->status_use_accessors & _IRQ_NO_SOFTIRQ_CALL; ++} ++ ++static inline void irq_settings_set_no_softirq_call(struct irq_desc *desc) ++{ ++ desc->status_use_accessors |= _IRQ_NO_SOFTIRQ_CALL; ++} ++ + static inline bool irq_settings_is_per_cpu(struct irq_desc *desc) + { + return desc->status_use_accessors & _IRQ_PER_CPU; +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -606,6 +606,15 @@ void local_bh_enable_ip(unsigned long ip + } + EXPORT_SYMBOL(local_bh_enable_ip); + ++void _local_bh_enable(void) ++{ ++ if (WARN_ON(current->softirq_nestcnt == 0)) ++ return; ++ if (--current->softirq_nestcnt == 0) ++ migrate_enable(); ++} ++EXPORT_SYMBOL(_local_bh_enable); ++ + int in_serving_softirq(void) + { + return current->flags & PF_IN_SOFTIRQ; diff --git a/debian/patches/features/all/rt/irqwork-push_most_work_into_softirq_context.patch b/debian/patches/features/all/rt/irqwork-push_most_work_into_softirq_context.patch new file mode 100644 index 000000000..cdbb5672b --- /dev/null +++ b/debian/patches/features/all/rt/irqwork-push_most_work_into_softirq_context.patch @@ -0,0 +1,198 @@ +Subject: irqwork: push most work into softirq context +From: Sebastian Andrzej Siewior +Date: Tue, 23 Jun 2015 15:32:51 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Initially we defered all irqwork into softirq because we didn't want the +latency spikes if perf or another user was busy and delayed the RT task. +The NOHZ trigger (nohz_full_kick_work) was the first user that did not work +as expected if it did not run in the original irqwork context so we had to +bring it back somehow for it. push_irq_work_func is the second one that +requires this. + +This patch adds the IRQ_WORK_HARD_IRQ which makes sure the callback runs +in raw-irq context. Everything else is defered into softirq context. Without +-RT we have the orignal behavior. + +This patch incorporates tglx orignal work which revoked a little bringing back +the arch_irq_work_raise() if possible and a few fixes from Steven Rostedt and +Mike Galbraith, + +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/irq_work.h | 1 + + kernel/irq_work.c | 47 ++++++++++++++++++++++++++++++++++------------- + kernel/sched/rt.c | 1 + + kernel/time/tick-sched.c | 6 ++++++ + kernel/time/timer.c | 6 +++++- + 5 files changed, 47 insertions(+), 14 deletions(-) + +--- a/include/linux/irq_work.h ++++ b/include/linux/irq_work.h +@@ -16,6 +16,7 @@ + #define IRQ_WORK_BUSY 2UL + #define IRQ_WORK_FLAGS 3UL + #define IRQ_WORK_LAZY 4UL /* Doesn't want IPI, wait for tick */ ++#define IRQ_WORK_HARD_IRQ 8UL /* Run hard IRQ context, even on RT */ + + struct irq_work { + unsigned long flags; +--- a/kernel/irq_work.c ++++ b/kernel/irq_work.c +@@ -17,6 +17,7 @@ + #include + #include + #include ++#include + #include + + +@@ -65,6 +66,8 @@ void __weak arch_irq_work_raise(void) + */ + bool irq_work_queue_on(struct irq_work *work, int cpu) + { ++ struct llist_head *list; ++ + /* All work should have been flushed before going offline */ + WARN_ON_ONCE(cpu_is_offline(cpu)); + +@@ -75,7 +78,12 @@ bool irq_work_queue_on(struct irq_work * + if (!irq_work_claim(work)) + return false; + +- if (llist_add(&work->llnode, &per_cpu(raised_list, cpu))) ++ if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL) && !(work->flags & IRQ_WORK_HARD_IRQ)) ++ list = &per_cpu(lazy_list, cpu); ++ else ++ list = &per_cpu(raised_list, cpu); ++ ++ if (llist_add(&work->llnode, list)) + arch_send_call_function_single_ipi(cpu); + + return true; +@@ -86,6 +94,9 @@ EXPORT_SYMBOL_GPL(irq_work_queue_on); + /* Enqueue the irq work @work on the current CPU */ + bool irq_work_queue(struct irq_work *work) + { ++ struct llist_head *list; ++ bool lazy_work, realtime = IS_ENABLED(CONFIG_PREEMPT_RT_FULL); ++ + /* Only queue if not already pending */ + if (!irq_work_claim(work)) + return false; +@@ -93,13 +104,15 @@ bool irq_work_queue(struct irq_work *wor + /* Queue the entry and raise the IPI if needed. */ + preempt_disable(); + +- /* If the work is "lazy", handle it from next tick if any */ +- if (work->flags & IRQ_WORK_LAZY) { +- if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) && +- tick_nohz_tick_stopped()) +- arch_irq_work_raise(); +- } else { +- if (llist_add(&work->llnode, this_cpu_ptr(&raised_list))) ++ lazy_work = work->flags & IRQ_WORK_LAZY; ++ ++ if (lazy_work || (realtime && !(work->flags & IRQ_WORK_HARD_IRQ))) ++ list = this_cpu_ptr(&lazy_list); ++ else ++ list = this_cpu_ptr(&raised_list); ++ ++ if (llist_add(&work->llnode, list)) { ++ if (!lazy_work || tick_nohz_tick_stopped()) + arch_irq_work_raise(); + } + +@@ -116,9 +129,8 @@ bool irq_work_needs_cpu(void) + raised = this_cpu_ptr(&raised_list); + lazy = this_cpu_ptr(&lazy_list); + +- if (llist_empty(raised) || arch_irq_work_has_interrupt()) +- if (llist_empty(lazy)) +- return false; ++ if (llist_empty(raised) && llist_empty(lazy)) ++ return false; + + /* All work should have been flushed before going offline */ + WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); +@@ -132,7 +144,7 @@ static void irq_work_run_list(struct lli + struct irq_work *work; + struct llist_node *llnode; + +- BUG_ON(!irqs_disabled()); ++ BUG_ON_NONRT(!irqs_disabled()); + + if (llist_empty(list)) + return; +@@ -169,7 +181,16 @@ static void irq_work_run_list(struct lli + void irq_work_run(void) + { + irq_work_run_list(this_cpu_ptr(&raised_list)); +- irq_work_run_list(this_cpu_ptr(&lazy_list)); ++ if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) { ++ /* ++ * NOTE: we raise softirq via IPI for safety, ++ * and execute in irq_work_tick() to move the ++ * overhead from hard to soft irq context. ++ */ ++ if (!llist_empty(this_cpu_ptr(&lazy_list))) ++ raise_softirq(TIMER_SOFTIRQ); ++ } else ++ irq_work_run_list(this_cpu_ptr(&lazy_list)); + } + EXPORT_SYMBOL_GPL(irq_work_run); + +--- a/kernel/sched/rt.c ++++ b/kernel/sched/rt.c +@@ -90,6 +90,7 @@ void init_rt_rq(struct rt_rq *rt_rq) + rt_rq->push_cpu = nr_cpu_ids; + raw_spin_lock_init(&rt_rq->push_lock); + init_irq_work(&rt_rq->push_work, push_irq_work_func); ++ rt_rq->push_work.flags |= IRQ_WORK_HARD_IRQ; + #endif + #endif /* CONFIG_SMP */ + /* We start is dequeued state, because no RT tasks are queued */ +--- a/kernel/time/tick-sched.c ++++ b/kernel/time/tick-sched.c +@@ -181,6 +181,11 @@ static bool can_stop_full_tick(void) + return false; + } + ++ if (!arch_irq_work_has_interrupt()) { ++ trace_tick_stop(0, "missing irq work interrupt\n"); ++ return false; ++ } ++ + /* sched_clock_tick() needs us? */ + #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK + /* +@@ -227,6 +232,7 @@ static void nohz_full_kick_work_func(str + + static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { + .func = nohz_full_kick_work_func, ++ .flags = IRQ_WORK_HARD_IRQ, + }; + + /* +--- a/kernel/time/timer.c ++++ b/kernel/time/timer.c +@@ -1455,7 +1455,7 @@ void update_process_times(int user_tick) + scheduler_tick(); + run_local_timers(); + rcu_check_callbacks(user_tick); +-#ifdef CONFIG_IRQ_WORK ++#if defined(CONFIG_IRQ_WORK) && !defined(CONFIG_PREEMPT_RT_FULL) + if (in_irq()) + irq_work_tick(); + #endif +@@ -1471,6 +1471,10 @@ static void run_timer_softirq(struct sof + + hrtimer_run_pending(); + ++#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) ++ irq_work_tick(); ++#endif ++ + if (time_after_eq(jiffies, base->timer_jiffies)) + __run_timers(base); + } diff --git a/debian/patches/features/all/rt/jump-label-rt.patch b/debian/patches/features/all/rt/jump-label-rt.patch new file mode 100644 index 000000000..e0056e97a --- /dev/null +++ b/debian/patches/features/all/rt/jump-label-rt.patch @@ -0,0 +1,36 @@ +Subject: jump-label: disable if stop_machine() is used +From: Thomas Gleixner +Date: Wed, 08 Jul 2015 17:14:48 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Some architectures are using stop_machine() while switching the opcode which +leads to latency spikes. +The architectures which use stop_machine() atm: +- ARM stop machine +- s390 stop machine + +The architecures which use other sorcery: +- MIPS +- X86 +- powerpc +- sparc +- arm64 + +Signed-off-by: Thomas Gleixner +[bigeasy: only ARM for now] +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/arm/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/arch/arm/Kconfig ++++ b/arch/arm/Kconfig +@@ -31,7 +31,7 @@ config ARM + select HARDIRQS_SW_RESEND + select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT) + select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6 +- select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL ++ select HAVE_ARCH_JUMP_LABEL if (!XIP_KERNEL && !PREEMPT_RT_BASE) + select HAVE_ARCH_KGDB + select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT) + select HAVE_ARCH_TRACEHOOK diff --git a/debian/patches/features/all/rt/kconfig-disable-a-few-options-rt.patch b/debian/patches/features/all/rt/kconfig-disable-a-few-options-rt.patch new file mode 100644 index 000000000..f19d98334 --- /dev/null +++ b/debian/patches/features/all/rt/kconfig-disable-a-few-options-rt.patch @@ -0,0 +1,34 @@ +Subject: kconfig: Disable config options which are not RT compatible +From: Thomas Gleixner +Date: Sun, 24 Jul 2011 12:11:43 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Disable stuff which is known to have issues on RT + +Signed-off-by: Thomas Gleixner +--- + arch/Kconfig | 1 + + mm/Kconfig | 2 +- + 2 files changed, 2 insertions(+), 1 deletion(-) + +--- a/arch/Kconfig ++++ b/arch/Kconfig +@@ -6,6 +6,7 @@ config OPROFILE + tristate "OProfile system profiling" + depends on PROFILING + depends on HAVE_OPROFILE ++ depends on !PREEMPT_RT_FULL + select RING_BUFFER + select RING_BUFFER_ALLOW_SWAP + help +--- a/mm/Kconfig ++++ b/mm/Kconfig +@@ -409,7 +409,7 @@ config NOMMU_INITIAL_TRIM_EXCESS + + config TRANSPARENT_HUGEPAGE + bool "Transparent Hugepage Support" +- depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE ++ depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT_FULL + select COMPACTION + help + Transparent Hugepages allows the kernel to use huge pages and diff --git a/debian/patches/features/all/rt/kconfig-preempt-rt-full.patch b/debian/patches/features/all/rt/kconfig-preempt-rt-full.patch new file mode 100644 index 000000000..3455c7fc8 --- /dev/null +++ b/debian/patches/features/all/rt/kconfig-preempt-rt-full.patch @@ -0,0 +1,59 @@ +Subject: kconfig: Add PREEMPT_RT_FULL +From: Thomas Gleixner +Date: Wed, 29 Jun 2011 14:58:57 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Introduce the final symbol for PREEMPT_RT_FULL. + +Signed-off-by: Thomas Gleixner +--- + init/Makefile | 2 +- + kernel/Kconfig.preempt | 8 ++++++++ + scripts/mkcompile_h | 4 +++- + 3 files changed, 12 insertions(+), 2 deletions(-) + +--- a/init/Makefile ++++ b/init/Makefile +@@ -33,4 +33,4 @@ mounts-$(CONFIG_BLK_DEV_MD) += do_mounts + include/generated/compile.h: FORCE + @$($(quiet)chk_compile.h) + $(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@ \ +- "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CC) $(KBUILD_CFLAGS)" ++ "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CONFIG_PREEMPT_RT_FULL)" "$(CC) $(KBUILD_CFLAGS)" +--- a/kernel/Kconfig.preempt ++++ b/kernel/Kconfig.preempt +@@ -67,6 +67,14 @@ config PREEMPT_RTB + enables changes which are preliminary for the full preemptible + RT kernel. + ++config PREEMPT_RT_FULL ++ bool "Fully Preemptible Kernel (RT)" ++ depends on IRQ_FORCED_THREADING ++ select PREEMPT_RT_BASE ++ select PREEMPT_RCU ++ help ++ All and everything ++ + endchoice + + config PREEMPT_COUNT +--- a/scripts/mkcompile_h ++++ b/scripts/mkcompile_h +@@ -4,7 +4,8 @@ TARGET=$1 + ARCH=$2 + SMP=$3 + PREEMPT=$4 +-CC=$5 ++RT=$5 ++CC=$6 + + vecho() { [ "${quiet}" = "silent_" ] || echo "$@" ; } + +@@ -57,6 +58,7 @@ UTS_VERSION="#$VERSION" + CONFIG_FLAGS="" + if [ -n "$SMP" ] ; then CONFIG_FLAGS="SMP"; fi + if [ -n "$PREEMPT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT"; fi ++if [ -n "$RT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS RT"; fi + UTS_VERSION="$UTS_VERSION $CONFIG_FLAGS $TIMESTAMP" + + # Truncate to maximum length diff --git a/debian/patches/features/all/rt/kernel-SRCU-provide-a-static-initializer.patch b/debian/patches/features/all/rt/kernel-SRCU-provide-a-static-initializer.patch new file mode 100644 index 000000000..9cc6fefb1 --- /dev/null +++ b/debian/patches/features/all/rt/kernel-SRCU-provide-a-static-initializer.patch @@ -0,0 +1,125 @@ +From: Sebastian Andrzej Siewior +Date: Tue, 19 Mar 2013 14:44:30 +0100 +Subject: [PATCH] kernel/SRCU: provide a static initializer +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +There are macros for static initializer for the three out of four +possible notifier types, that are: + ATOMIC_NOTIFIER_HEAD() + BLOCKING_NOTIFIER_HEAD() + RAW_NOTIFIER_HEAD() + +This patch provides a static initilizer for the forth type to make it +complete. + +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/notifier.h | 34 +++++++++++++++++++++++++--------- + include/linux/srcu.h | 6 +++--- + 2 files changed, 28 insertions(+), 12 deletions(-) + +--- a/include/linux/notifier.h ++++ b/include/linux/notifier.h +@@ -6,7 +6,7 @@ + * + * Alan Cox + */ +- ++ + #ifndef _LINUX_NOTIFIER_H + #define _LINUX_NOTIFIER_H + #include +@@ -42,9 +42,7 @@ + * in srcu_notifier_call_chain(): no cache bounces and no memory barriers. + * As compensation, srcu_notifier_chain_unregister() is rather expensive. + * SRCU notifier chains should be used when the chain will be called very +- * often but notifier_blocks will seldom be removed. Also, SRCU notifier +- * chains are slightly more difficult to use because they require special +- * runtime initialization. ++ * often but notifier_blocks will seldom be removed. + */ + + typedef int (*notifier_fn_t)(struct notifier_block *nb, +@@ -88,7 +86,7 @@ struct srcu_notifier_head { + (name)->head = NULL; \ + } while (0) + +-/* srcu_notifier_heads must be initialized and cleaned up dynamically */ ++/* srcu_notifier_heads must be cleaned up dynamically */ + extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); + #define srcu_cleanup_notifier_head(name) \ + cleanup_srcu_struct(&(name)->srcu); +@@ -101,7 +99,13 @@ extern void srcu_init_notifier_head(stru + .head = NULL } + #define RAW_NOTIFIER_INIT(name) { \ + .head = NULL } +-/* srcu_notifier_heads cannot be initialized statically */ ++ ++#define SRCU_NOTIFIER_INIT(name, pcpu) \ ++ { \ ++ .mutex = __MUTEX_INITIALIZER(name.mutex), \ ++ .head = NULL, \ ++ .srcu = __SRCU_STRUCT_INIT(name.srcu, pcpu), \ ++ } + + #define ATOMIC_NOTIFIER_HEAD(name) \ + struct atomic_notifier_head name = \ +@@ -113,6 +117,18 @@ extern void srcu_init_notifier_head(stru + struct raw_notifier_head name = \ + RAW_NOTIFIER_INIT(name) + ++#define _SRCU_NOTIFIER_HEAD(name, mod) \ ++ static DEFINE_PER_CPU(struct srcu_struct_array, \ ++ name##_head_srcu_array); \ ++ mod struct srcu_notifier_head name = \ ++ SRCU_NOTIFIER_INIT(name, name##_head_srcu_array) ++ ++#define SRCU_NOTIFIER_HEAD(name) \ ++ _SRCU_NOTIFIER_HEAD(name, ) ++ ++#define SRCU_NOTIFIER_HEAD_STATIC(name) \ ++ _SRCU_NOTIFIER_HEAD(name, static) ++ + #ifdef __KERNEL__ + + extern int atomic_notifier_chain_register(struct atomic_notifier_head *nh, +@@ -182,12 +198,12 @@ static inline int notifier_to_errno(int + + /* + * Declared notifiers so far. I can imagine quite a few more chains +- * over time (eg laptop power reset chains, reboot chain (to clean ++ * over time (eg laptop power reset chains, reboot chain (to clean + * device units up), device [un]mount chain, module load/unload chain, +- * low memory chain, screenblank chain (for plug in modular screenblankers) ++ * low memory chain, screenblank chain (for plug in modular screenblankers) + * VC switch chains (for loadable kernel svgalib VC switch helpers) etc... + */ +- ++ + /* CPU notfiers are defined in include/linux/cpu.h. */ + + /* netdevice notifiers are defined in include/linux/netdevice.h */ +--- a/include/linux/srcu.h ++++ b/include/linux/srcu.h +@@ -84,10 +84,10 @@ int init_srcu_struct(struct srcu_struct + + void process_srcu(struct work_struct *work); + +-#define __SRCU_STRUCT_INIT(name) \ ++#define __SRCU_STRUCT_INIT(name, pcpu_name) \ + { \ + .completed = -300, \ +- .per_cpu_ref = &name##_srcu_array, \ ++ .per_cpu_ref = &pcpu_name, \ + .queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock), \ + .running = false, \ + .batch_queue = RCU_BATCH_INIT(name.batch_queue), \ +@@ -104,7 +104,7 @@ void process_srcu(struct work_struct *wo + */ + #define __DEFINE_SRCU(name, is_static) \ + static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\ +- is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name) ++ is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name##_srcu_array) + #define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) + #define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static) + diff --git a/debian/patches/features/all/rt/kernel-cpu-fix-cpu-down-problem-if-kthread-s-cpu-is-.patch b/debian/patches/features/all/rt/kernel-cpu-fix-cpu-down-problem-if-kthread-s-cpu-is-.patch new file mode 100644 index 000000000..613834631 --- /dev/null +++ b/debian/patches/features/all/rt/kernel-cpu-fix-cpu-down-problem-if-kthread-s-cpu-is-.patch @@ -0,0 +1,86 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 7 Jun 2013 22:37:06 +0200 +Subject: kernel/cpu: fix cpu down problem if kthread's cpu is going down +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +If kthread is pinned to CPUx and CPUx is going down then we get into +trouble: +- first the unplug thread is created +- it will set itself to hp->unplug. As a result, every task that is + going to take a lock, has to leave the CPU. +- the CPU_DOWN_PREPARE notifier are started. The worker thread will + start a new process for the "high priority worker". + Now kthread would like to take a lock but since it can't leave the CPU + it will never complete its task. + +We could fire the unplug thread after the notifier but then the cpu is +no longer marked "online" and the unplug thread will run on CPU0 which +was fixed before :) + +So instead the unplug thread is started and kept waiting until the +notfier complete their work. + +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/cpu.c | 15 +++++++++++++-- + 1 file changed, 13 insertions(+), 2 deletions(-) + +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -108,6 +108,7 @@ struct hotplug_pcp { + int refcount; + int grab_lock; + struct completion synced; ++ struct completion unplug_wait; + #ifdef CONFIG_PREEMPT_RT_FULL + /* + * Note, on PREEMPT_RT, the hotplug lock must save the state of +@@ -211,6 +212,7 @@ static int sync_unplug_thread(void *data + { + struct hotplug_pcp *hp = data; + ++ wait_for_completion(&hp->unplug_wait); + preempt_disable(); + hp->unplug = current; + wait_for_pinned_cpus(hp); +@@ -276,6 +278,14 @@ static void __cpu_unplug_sync(struct hot + wait_for_completion(&hp->synced); + } + ++static void __cpu_unplug_wait(unsigned int cpu) ++{ ++ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); ++ ++ complete(&hp->unplug_wait); ++ wait_for_completion(&hp->synced); ++} ++ + /* + * Start the sync_unplug_thread on the target cpu and wait for it to + * complete. +@@ -299,6 +309,7 @@ static int cpu_unplug_begin(unsigned int + tell_sched_cpu_down_begin(cpu); + + init_completion(&hp->synced); ++ init_completion(&hp->unplug_wait); + + hp->sync_tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu); + if (IS_ERR(hp->sync_tsk)) { +@@ -314,8 +325,7 @@ static int cpu_unplug_begin(unsigned int + * wait for tasks that are going to enter these sections and + * we must not have them block. + */ +- __cpu_unplug_sync(hp); +- ++ wake_up_process(hp->sync_tsk); + return 0; + } + +@@ -682,6 +692,7 @@ static int __ref _cpu_down(unsigned int + #endif + synchronize_rcu(); + ++ __cpu_unplug_wait(cpu); + smpboot_park_threads(cpu); + + /* Notifiers are done. Don't let any more tasks pin this CPU. */ diff --git a/debian/patches/features/all/rt/kernel-hotplug-restore-original-cpu-mask-oncpu-down.patch b/debian/patches/features/all/rt/kernel-hotplug-restore-original-cpu-mask-oncpu-down.patch new file mode 100644 index 000000000..bb7e0c699 --- /dev/null +++ b/debian/patches/features/all/rt/kernel-hotplug-restore-original-cpu-mask-oncpu-down.patch @@ -0,0 +1,59 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 14 Jun 2013 17:16:35 +0200 +Subject: kernel/hotplug: restore original cpu mask oncpu/down +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +If a task which is allowed to run only on CPU X puts CPU Y down then it +will be allowed on all CPUs but the on CPU Y after it comes back from +kernel. This patch ensures that we don't lose the initial setting unless +the CPU the task is running is going down. + + +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/cpu.c | 13 ++++++++++++- + 1 file changed, 12 insertions(+), 1 deletion(-) + +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -640,6 +640,7 @@ static int __ref _cpu_down(unsigned int + .hcpu = hcpu, + }; + cpumask_var_t cpumask; ++ cpumask_var_t cpumask_org; + + if (num_online_cpus() == 1) + return -EBUSY; +@@ -650,6 +651,12 @@ static int __ref _cpu_down(unsigned int + /* Move the downtaker off the unplug cpu */ + if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) + return -ENOMEM; ++ if (!alloc_cpumask_var(&cpumask_org, GFP_KERNEL)) { ++ free_cpumask_var(cpumask); ++ return -ENOMEM; ++ } ++ ++ cpumask_copy(cpumask_org, tsk_cpus_allowed(current)); + cpumask_andnot(cpumask, cpu_online_mask, cpumask_of(cpu)); + set_cpus_allowed_ptr(current, cpumask); + free_cpumask_var(cpumask); +@@ -658,7 +665,8 @@ static int __ref _cpu_down(unsigned int + if (mycpu == cpu) { + printk(KERN_ERR "Yuck! Still on unplug CPU\n!"); + migrate_enable(); +- return -EBUSY; ++ err = -EBUSY; ++ goto restore_cpus; + } + + cpu_hotplug_begin(); +@@ -740,6 +748,9 @@ static int __ref _cpu_down(unsigned int + cpu_hotplug_done(); + if (!err) + cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu); ++restore_cpus: ++ set_cpus_allowed_ptr(current, cpumask_org); ++ free_cpumask_var(cpumask_org); + return err; + } + diff --git a/debian/patches/features/all/rt/kgb-serial-hackaround.patch b/debian/patches/features/all/rt/kgb-serial-hackaround.patch new file mode 100644 index 000000000..a7c951e51 --- /dev/null +++ b/debian/patches/features/all/rt/kgb-serial-hackaround.patch @@ -0,0 +1,102 @@ +From: Jason Wessel +Date: Thu, 28 Jul 2011 12:42:23 -0500 +Subject: kgdb/serial: Short term workaround +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +On 07/27/2011 04:37 PM, Thomas Gleixner wrote: +> - KGDB (not yet disabled) is reportedly unusable on -rt right now due +> to missing hacks in the console locking which I dropped on purpose. +> + +To work around this in the short term you can use this patch, in +addition to the clocksource watchdog patch that Thomas brewed up. + +Comments are welcome of course. Ultimately the right solution is to +change separation between the console and the HW to have a polled mode ++ work queue so as not to introduce any kind of latency. + +Thanks, +Jason. + +--- + drivers/tty/serial/8250/8250_core.c | 3 ++- + include/linux/kdb.h | 2 ++ + kernel/debug/kdb/kdb_io.c | 6 ++---- + 3 files changed, 6 insertions(+), 5 deletions(-) + +--- a/drivers/tty/serial/8250/8250_core.c ++++ b/drivers/tty/serial/8250/8250_core.c +@@ -36,6 +36,7 @@ + #include + #include + #include ++#include + #include + #include + #ifdef CONFIG_SPARC +@@ -3373,7 +3374,7 @@ static void serial8250_console_write(str + + if (port->sysrq) + locked = 0; +- else if (oops_in_progress) ++ else if (oops_in_progress || in_kdb_printk()) + locked = spin_trylock_irqsave(&port->lock, flags); + else + spin_lock_irqsave(&port->lock, flags); +--- a/include/linux/kdb.h ++++ b/include/linux/kdb.h +@@ -167,6 +167,7 @@ extern __printf(2, 0) int vkdb_printf(en + extern __printf(1, 2) int kdb_printf(const char *, ...); + typedef __printf(1, 2) int (*kdb_printf_t)(const char *, ...); + ++#define in_kdb_printk() (kdb_trap_printk) + extern void kdb_init(int level); + + /* Access to kdb specific polling devices */ +@@ -201,6 +202,7 @@ extern int kdb_register_flags(char *, kd + extern int kdb_unregister(char *); + #else /* ! CONFIG_KGDB_KDB */ + static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; } ++#define in_kdb_printk() (0) + static inline void kdb_init(int level) {} + static inline int kdb_register(char *cmd, kdb_func_t func, char *usage, + char *help, short minlen) { return 0; } +--- a/kernel/debug/kdb/kdb_io.c ++++ b/kernel/debug/kdb/kdb_io.c +@@ -554,7 +554,6 @@ int vkdb_printf(enum kdb_msgsrc src, con + int linecount; + int colcount; + int logging, saved_loglevel = 0; +- int saved_trap_printk; + int got_printf_lock = 0; + int retlen = 0; + int fnd, len; +@@ -565,8 +564,6 @@ int vkdb_printf(enum kdb_msgsrc src, con + unsigned long uninitialized_var(flags); + + preempt_disable(); +- saved_trap_printk = kdb_trap_printk; +- kdb_trap_printk = 0; + + /* Serialize kdb_printf if multiple cpus try to write at once. + * But if any cpu goes recursive in kdb, just print the output, +@@ -855,7 +852,6 @@ int vkdb_printf(enum kdb_msgsrc src, con + } else { + __release(kdb_printf_lock); + } +- kdb_trap_printk = saved_trap_printk; + preempt_enable(); + return retlen; + } +@@ -865,9 +861,11 @@ int kdb_printf(const char *fmt, ...) + va_list ap; + int r; + ++ kdb_trap_printk++; + va_start(ap, fmt); + r = vkdb_printf(KDB_MSGSRC_INTERNAL, fmt, ap); + va_end(ap); ++ kdb_trap_printk--; + + return r; + } diff --git a/debian/patches/features/all/rt/latency-hist.patch b/debian/patches/features/all/rt/latency-hist.patch new file mode 100644 index 000000000..64c023819 --- /dev/null +++ b/debian/patches/features/all/rt/latency-hist.patch @@ -0,0 +1,1809 @@ +Subject: tracing: Add latency histograms +From: Carsten Emde +Date: Tue, 19 Jul 2011 14:03:41 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +This patch provides a recording mechanism to store data of potential +sources of system latencies. The recordings separately determine the +latency caused by a delayed timer expiration, by a delayed wakeup of the +related user space program and by the sum of both. The histograms can be +enabled and reset individually. The data are accessible via the debug +filesystem. For details please consult Documentation/trace/histograms.txt. + +Signed-off-by: Carsten Emde +Signed-off-by: Thomas Gleixner + +--- + Documentation/trace/histograms.txt | 186 +++++ + include/linux/hrtimer.h | 3 + include/linux/sched.h | 6 + include/trace/events/hist.h | 72 ++ + include/trace/events/latency_hist.h | 29 + kernel/time/hrtimer.c | 21 + kernel/trace/Kconfig | 104 +++ + kernel/trace/Makefile | 4 + kernel/trace/latency_hist.c | 1178 ++++++++++++++++++++++++++++++++++++ + kernel/trace/trace_irqsoff.c | 11 + 10 files changed, 1614 insertions(+) + +--- /dev/null ++++ b/Documentation/trace/histograms.txt +@@ -0,0 +1,186 @@ ++ Using the Linux Kernel Latency Histograms ++ ++ ++This document gives a short explanation how to enable, configure and use ++latency histograms. Latency histograms are primarily relevant in the ++context of real-time enabled kernels (CONFIG_PREEMPT/CONFIG_PREEMPT_RT) ++and are used in the quality management of the Linux real-time ++capabilities. ++ ++ ++* Purpose of latency histograms ++ ++A latency histogram continuously accumulates the frequencies of latency ++data. There are two types of histograms ++- potential sources of latencies ++- effective latencies ++ ++ ++* Potential sources of latencies ++ ++Potential sources of latencies are code segments where interrupts, ++preemption or both are disabled (aka critical sections). To create ++histograms of potential sources of latency, the kernel stores the time ++stamp at the start of a critical section, determines the time elapsed ++when the end of the section is reached, and increments the frequency ++counter of that latency value - irrespective of whether any concurrently ++running process is affected by latency or not. ++- Configuration items (in the Kernel hacking/Tracers submenu) ++ CONFIG_INTERRUPT_OFF_LATENCY ++ CONFIG_PREEMPT_OFF_LATENCY ++ ++ ++* Effective latencies ++ ++Effective latencies are actually occuring during wakeup of a process. To ++determine effective latencies, the kernel stores the time stamp when a ++process is scheduled to be woken up, and determines the duration of the ++wakeup time shortly before control is passed over to this process. Note ++that the apparent latency in user space may be somewhat longer, since the ++process may be interrupted after control is passed over to it but before ++the execution in user space takes place. Simply measuring the interval ++between enqueuing and wakeup may also not appropriate in cases when a ++process is scheduled as a result of a timer expiration. The timer may have ++missed its deadline, e.g. due to disabled interrupts, but this latency ++would not be registered. Therefore, the offsets of missed timers are ++recorded in a separate histogram. If both wakeup latency and missed timer ++offsets are configured and enabled, a third histogram may be enabled that ++records the overall latency as a sum of the timer latency, if any, and the ++wakeup latency. This histogram is called "timerandwakeup". ++- Configuration items (in the Kernel hacking/Tracers submenu) ++ CONFIG_WAKEUP_LATENCY ++ CONFIG_MISSED_TIMER_OFSETS ++ ++ ++* Usage ++ ++The interface to the administration of the latency histograms is located ++in the debugfs file system. To mount it, either enter ++ ++mount -t sysfs nodev /sys ++mount -t debugfs nodev /sys/kernel/debug ++ ++from shell command line level, or add ++ ++nodev /sys sysfs defaults 0 0 ++nodev /sys/kernel/debug debugfs defaults 0 0 ++ ++to the file /etc/fstab. All latency histogram related files are then ++available in the directory /sys/kernel/debug/tracing/latency_hist. A ++particular histogram type is enabled by writing non-zero to the related ++variable in the /sys/kernel/debug/tracing/latency_hist/enable directory. ++Select "preemptirqsoff" for the histograms of potential sources of ++latencies and "wakeup" for histograms of effective latencies etc. The ++histogram data - one per CPU - are available in the files ++ ++/sys/kernel/debug/tracing/latency_hist/preemptoff/CPUx ++/sys/kernel/debug/tracing/latency_hist/irqsoff/CPUx ++/sys/kernel/debug/tracing/latency_hist/preemptirqsoff/CPUx ++/sys/kernel/debug/tracing/latency_hist/wakeup/CPUx ++/sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio/CPUx ++/sys/kernel/debug/tracing/latency_hist/missed_timer_offsets/CPUx ++/sys/kernel/debug/tracing/latency_hist/timerandwakeup/CPUx ++ ++The histograms are reset by writing non-zero to the file "reset" in a ++particular latency directory. To reset all latency data, use ++ ++#!/bin/sh ++ ++TRACINGDIR=/sys/kernel/debug/tracing ++HISTDIR=$TRACINGDIR/latency_hist ++ ++if test -d $HISTDIR ++then ++ cd $HISTDIR ++ for i in `find . | grep /reset$` ++ do ++ echo 1 >$i ++ done ++fi ++ ++ ++* Data format ++ ++Latency data are stored with a resolution of one microsecond. The ++maximum latency is 10,240 microseconds. The data are only valid, if the ++overflow register is empty. Every output line contains the latency in ++microseconds in the first row and the number of samples in the second ++row. To display only lines with a positive latency count, use, for ++example, ++ ++grep -v " 0$" /sys/kernel/debug/tracing/latency_hist/preemptoff/CPU0 ++ ++#Minimum latency: 0 microseconds. ++#Average latency: 0 microseconds. ++#Maximum latency: 25 microseconds. ++#Total samples: 3104770694 ++#There are 0 samples greater or equal than 10240 microseconds ++#usecs samples ++ 0 2984486876 ++ 1 49843506 ++ 2 58219047 ++ 3 5348126 ++ 4 2187960 ++ 5 3388262 ++ 6 959289 ++ 7 208294 ++ 8 40420 ++ 9 4485 ++ 10 14918 ++ 11 18340 ++ 12 25052 ++ 13 19455 ++ 14 5602 ++ 15 969 ++ 16 47 ++ 17 18 ++ 18 14 ++ 19 1 ++ 20 3 ++ 21 2 ++ 22 5 ++ 23 2 ++ 25 1 ++ ++ ++* Wakeup latency of a selected process ++ ++To only collect wakeup latency data of a particular process, write the ++PID of the requested process to ++ ++/sys/kernel/debug/tracing/latency_hist/wakeup/pid ++ ++PIDs are not considered, if this variable is set to 0. ++ ++ ++* Details of the process with the highest wakeup latency so far ++ ++Selected data of the process that suffered from the highest wakeup ++latency that occurred in a particular CPU are available in the file ++ ++/sys/kernel/debug/tracing/latency_hist/wakeup/max_latency-CPUx. ++ ++In addition, other relevant system data at the time when the ++latency occurred are given. ++ ++The format of the data is (all in one line): ++ () \ ++<- ++ ++The value of is only relevant in the combined timer ++and wakeup latency recording. In the wakeup recording, it is ++always 0, in the missed_timer_offsets recording, it is the same ++as . ++ ++When retrospectively searching for the origin of a latency and ++tracing was not enabled, it may be helpful to know the name and ++some basic data of the task that (finally) was switching to the ++late real-tlme task. In addition to the victim's data, also the ++data of the possible culprit are therefore displayed after the ++"<-" symbol. ++ ++Finally, the timestamp of the time when the latency occurred ++in . after the most recent system boot ++is provided. ++ ++These data are also reset when the wakeup histogram is reset. +--- a/include/linux/hrtimer.h ++++ b/include/linux/hrtimer.h +@@ -111,6 +111,9 @@ struct hrtimer { + enum hrtimer_restart (*function)(struct hrtimer *); + struct hrtimer_clock_base *base; + unsigned long state; ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ ktime_t praecox; ++#endif + #ifdef CONFIG_TIMER_STATS + int start_pid; + void *start_site; +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -1753,6 +1753,12 @@ struct task_struct { + unsigned long trace; + /* bitmask and counter of trace recursion */ + unsigned long trace_recursion; ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ u64 preempt_timestamp_hist; ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ long timer_offset; ++#endif ++#endif + #endif /* CONFIG_TRACING */ + #ifdef CONFIG_MEMCG + struct memcg_oom_info { +--- /dev/null ++++ b/include/trace/events/hist.h +@@ -0,0 +1,72 @@ ++#undef TRACE_SYSTEM ++#define TRACE_SYSTEM hist ++ ++#if !defined(_TRACE_HIST_H) || defined(TRACE_HEADER_MULTI_READ) ++#define _TRACE_HIST_H ++ ++#include "latency_hist.h" ++#include ++ ++#if !defined(CONFIG_PREEMPT_OFF_HIST) && !defined(CONFIG_INTERRUPT_OFF_HIST) ++#define trace_preemptirqsoff_hist(a, b) ++#else ++TRACE_EVENT(preemptirqsoff_hist, ++ ++ TP_PROTO(int reason, int starthist), ++ ++ TP_ARGS(reason, starthist), ++ ++ TP_STRUCT__entry( ++ __field(int, reason) ++ __field(int, starthist) ++ ), ++ ++ TP_fast_assign( ++ __entry->reason = reason; ++ __entry->starthist = starthist; ++ ), ++ ++ TP_printk("reason=%s starthist=%s", getaction(__entry->reason), ++ __entry->starthist ? "start" : "stop") ++); ++#endif ++ ++#ifndef CONFIG_MISSED_TIMER_OFFSETS_HIST ++#define trace_hrtimer_interrupt(a, b, c, d) ++#else ++TRACE_EVENT(hrtimer_interrupt, ++ ++ TP_PROTO(int cpu, long long offset, struct task_struct *curr, ++ struct task_struct *task), ++ ++ TP_ARGS(cpu, offset, curr, task), ++ ++ TP_STRUCT__entry( ++ __field(int, cpu) ++ __field(long long, offset) ++ __array(char, ccomm, TASK_COMM_LEN) ++ __field(int, cprio) ++ __array(char, tcomm, TASK_COMM_LEN) ++ __field(int, tprio) ++ ), ++ ++ TP_fast_assign( ++ __entry->cpu = cpu; ++ __entry->offset = offset; ++ memcpy(__entry->ccomm, curr->comm, TASK_COMM_LEN); ++ __entry->cprio = curr->prio; ++ memcpy(__entry->tcomm, task != NULL ? task->comm : "", ++ task != NULL ? TASK_COMM_LEN : 7); ++ __entry->tprio = task != NULL ? task->prio : -1; ++ ), ++ ++ TP_printk("cpu=%d offset=%lld curr=%s[%d] thread=%s[%d]", ++ __entry->cpu, __entry->offset, __entry->ccomm, ++ __entry->cprio, __entry->tcomm, __entry->tprio) ++); ++#endif ++ ++#endif /* _TRACE_HIST_H */ ++ ++/* This part must be outside protection */ ++#include +--- /dev/null ++++ b/include/trace/events/latency_hist.h +@@ -0,0 +1,29 @@ ++#ifndef _LATENCY_HIST_H ++#define _LATENCY_HIST_H ++ ++enum hist_action { ++ IRQS_ON, ++ PREEMPT_ON, ++ TRACE_STOP, ++ IRQS_OFF, ++ PREEMPT_OFF, ++ TRACE_START, ++}; ++ ++static char *actions[] = { ++ "IRQS_ON", ++ "PREEMPT_ON", ++ "TRACE_STOP", ++ "IRQS_OFF", ++ "PREEMPT_OFF", ++ "TRACE_START", ++}; ++ ++static inline char *getaction(int action) ++{ ++ if (action >= 0 && action <= sizeof(actions)/sizeof(actions[0])) ++ return actions[action]; ++ return "unknown"; ++} ++ ++#endif /* _LATENCY_HIST_H */ +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -53,6 +53,7 @@ + #include + + #include ++#include + + #include "tick-internal.h" + +@@ -966,7 +967,16 @@ int __hrtimer_start_range_ns(struct hrti + new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); + + timer_stats_hrtimer_set_start_info(timer); ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ { ++ ktime_t now = new_base->get_time(); + ++ if (ktime_to_ns(tim) < ktime_to_ns(now)) ++ timer->praecox = now; ++ else ++ timer->praecox = ktime_set(0, 0); ++ } ++#endif + leftmost = enqueue_hrtimer(timer, new_base); + + if (!leftmost) { +@@ -1238,6 +1248,8 @@ static void __run_hrtimer(struct hrtimer + + #ifdef CONFIG_HIGH_RES_TIMERS + ++static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer); ++ + /* + * High resolution timer interrupt + * Called with interrupts disabled +@@ -1281,6 +1293,15 @@ void hrtimer_interrupt(struct clock_even + + timer = container_of(node, struct hrtimer, node); + ++ trace_hrtimer_interrupt(raw_smp_processor_id(), ++ ktime_to_ns(ktime_sub(ktime_to_ns(timer->praecox) ? ++ timer->praecox : hrtimer_get_expires(timer), ++ basenow)), ++ current, ++ timer->function == hrtimer_wakeup ? ++ container_of(timer, struct hrtimer_sleeper, ++ timer)->task : NULL); ++ + /* + * The immediate goal for using the softexpires is + * minimizing wakeups, not running timers at the +--- a/kernel/trace/Kconfig ++++ b/kernel/trace/Kconfig +@@ -187,6 +187,24 @@ config IRQSOFF_TRACER + enabled. This option and the preempt-off timing option can be + used together or separately.) + ++config INTERRUPT_OFF_HIST ++ bool "Interrupts-off Latency Histogram" ++ depends on IRQSOFF_TRACER ++ help ++ This option generates continuously updated histograms (one per cpu) ++ of the duration of time periods with interrupts disabled. The ++ histograms are disabled by default. To enable them, write a non-zero ++ number to ++ ++ /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff ++ ++ If PREEMPT_OFF_HIST is also selected, additional histograms (one ++ per cpu) are generated that accumulate the duration of time periods ++ when both interrupts and preemption are disabled. The histogram data ++ will be located in the debug file system at ++ ++ /sys/kernel/debug/tracing/latency_hist/irqsoff ++ + config PREEMPT_TRACER + bool "Preemption-off Latency Tracer" + default n +@@ -211,6 +229,24 @@ config PREEMPT_TRACER + enabled. This option and the irqs-off timing option can be + used together or separately.) + ++config PREEMPT_OFF_HIST ++ bool "Preemption-off Latency Histogram" ++ depends on PREEMPT_TRACER ++ help ++ This option generates continuously updated histograms (one per cpu) ++ of the duration of time periods with preemption disabled. The ++ histograms are disabled by default. To enable them, write a non-zero ++ number to ++ ++ /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff ++ ++ If INTERRUPT_OFF_HIST is also selected, additional histograms (one ++ per cpu) are generated that accumulate the duration of time periods ++ when both interrupts and preemption are disabled. The histogram data ++ will be located in the debug file system at ++ ++ /sys/kernel/debug/tracing/latency_hist/preemptoff ++ + config SCHED_TRACER + bool "Scheduling Latency Tracer" + select GENERIC_TRACER +@@ -221,6 +257,74 @@ config SCHED_TRACER + This tracer tracks the latency of the highest priority task + to be scheduled in, starting from the point it has woken up. + ++config WAKEUP_LATENCY_HIST ++ bool "Scheduling Latency Histogram" ++ depends on SCHED_TRACER ++ help ++ This option generates continuously updated histograms (one per cpu) ++ of the scheduling latency of the highest priority task. ++ The histograms are disabled by default. To enable them, write a ++ non-zero number to ++ ++ /sys/kernel/debug/tracing/latency_hist/enable/wakeup ++ ++ Two different algorithms are used, one to determine the latency of ++ processes that exclusively use the highest priority of the system and ++ another one to determine the latency of processes that share the ++ highest system priority with other processes. The former is used to ++ improve hardware and system software, the latter to optimize the ++ priority design of a given system. The histogram data will be ++ located in the debug file system at ++ ++ /sys/kernel/debug/tracing/latency_hist/wakeup ++ ++ and ++ ++ /sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio ++ ++ If both Scheduling Latency Histogram and Missed Timer Offsets ++ Histogram are selected, additional histogram data will be collected ++ that contain, in addition to the wakeup latency, the timer latency, in ++ case the wakeup was triggered by an expired timer. These histograms ++ are available in the ++ ++ /sys/kernel/debug/tracing/latency_hist/timerandwakeup ++ ++ directory. They reflect the apparent interrupt and scheduling latency ++ and are best suitable to determine the worst-case latency of a given ++ system. To enable these histograms, write a non-zero number to ++ ++ /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup ++ ++config MISSED_TIMER_OFFSETS_HIST ++ depends on HIGH_RES_TIMERS ++ select GENERIC_TRACER ++ bool "Missed Timer Offsets Histogram" ++ help ++ Generate a histogram of missed timer offsets in microseconds. The ++ histograms are disabled by default. To enable them, write a non-zero ++ number to ++ ++ /sys/kernel/debug/tracing/latency_hist/enable/missed_timer_offsets ++ ++ The histogram data will be located in the debug file system at ++ ++ /sys/kernel/debug/tracing/latency_hist/missed_timer_offsets ++ ++ If both Scheduling Latency Histogram and Missed Timer Offsets ++ Histogram are selected, additional histogram data will be collected ++ that contain, in addition to the wakeup latency, the timer latency, in ++ case the wakeup was triggered by an expired timer. These histograms ++ are available in the ++ ++ /sys/kernel/debug/tracing/latency_hist/timerandwakeup ++ ++ directory. They reflect the apparent interrupt and scheduling latency ++ and are best suitable to determine the worst-case latency of a given ++ system. To enable these histograms, write a non-zero number to ++ ++ /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup ++ + config ENABLE_DEFAULT_TRACERS + bool "Trace process context switches and events" + depends on !GENERIC_TRACER +--- a/kernel/trace/Makefile ++++ b/kernel/trace/Makefile +@@ -36,6 +36,10 @@ obj-$(CONFIG_FUNCTION_TRACER) += trace_f + obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o + obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o + obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o ++obj-$(CONFIG_INTERRUPT_OFF_HIST) += latency_hist.o ++obj-$(CONFIG_PREEMPT_OFF_HIST) += latency_hist.o ++obj-$(CONFIG_WAKEUP_LATENCY_HIST) += latency_hist.o ++obj-$(CONFIG_MISSED_TIMER_OFFSETS_HIST) += latency_hist.o + obj-$(CONFIG_NOP_TRACER) += trace_nop.o + obj-$(CONFIG_STACK_TRACER) += trace_stack.o + obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o +--- /dev/null ++++ b/kernel/trace/latency_hist.c +@@ -0,0 +1,1178 @@ ++/* ++ * kernel/trace/latency_hist.c ++ * ++ * Add support for histograms of preemption-off latency and ++ * interrupt-off latency and wakeup latency, it depends on ++ * Real-Time Preemption Support. ++ * ++ * Copyright (C) 2005 MontaVista Software, Inc. ++ * Yi Yang ++ * ++ * Converted to work with the new latency tracer. ++ * Copyright (C) 2008 Red Hat, Inc. ++ * Steven Rostedt ++ * ++ */ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++#include "trace.h" ++#include ++ ++#define NSECS_PER_USECS 1000L ++ ++#define CREATE_TRACE_POINTS ++#include ++ ++enum { ++ IRQSOFF_LATENCY = 0, ++ PREEMPTOFF_LATENCY, ++ PREEMPTIRQSOFF_LATENCY, ++ WAKEUP_LATENCY, ++ WAKEUP_LATENCY_SHAREDPRIO, ++ MISSED_TIMER_OFFSETS, ++ TIMERANDWAKEUP_LATENCY, ++ MAX_LATENCY_TYPE, ++}; ++ ++#define MAX_ENTRY_NUM 10240 ++ ++struct hist_data { ++ atomic_t hist_mode; /* 0 log, 1 don't log */ ++ long offset; /* set it to MAX_ENTRY_NUM/2 for a bipolar scale */ ++ long min_lat; ++ long max_lat; ++ unsigned long long below_hist_bound_samples; ++ unsigned long long above_hist_bound_samples; ++ long long accumulate_lat; ++ unsigned long long total_samples; ++ unsigned long long hist_array[MAX_ENTRY_NUM]; ++}; ++ ++struct enable_data { ++ int latency_type; ++ int enabled; ++}; ++ ++static char *latency_hist_dir_root = "latency_hist"; ++ ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++static DEFINE_PER_CPU(struct hist_data, irqsoff_hist); ++static char *irqsoff_hist_dir = "irqsoff"; ++static DEFINE_PER_CPU(cycles_t, hist_irqsoff_start); ++static DEFINE_PER_CPU(int, hist_irqsoff_counting); ++#endif ++ ++#ifdef CONFIG_PREEMPT_OFF_HIST ++static DEFINE_PER_CPU(struct hist_data, preemptoff_hist); ++static char *preemptoff_hist_dir = "preemptoff"; ++static DEFINE_PER_CPU(cycles_t, hist_preemptoff_start); ++static DEFINE_PER_CPU(int, hist_preemptoff_counting); ++#endif ++ ++#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST) ++static DEFINE_PER_CPU(struct hist_data, preemptirqsoff_hist); ++static char *preemptirqsoff_hist_dir = "preemptirqsoff"; ++static DEFINE_PER_CPU(cycles_t, hist_preemptirqsoff_start); ++static DEFINE_PER_CPU(int, hist_preemptirqsoff_counting); ++#endif ++ ++#if defined(CONFIG_PREEMPT_OFF_HIST) || defined(CONFIG_INTERRUPT_OFF_HIST) ++static notrace void probe_preemptirqsoff_hist(void *v, int reason, int start); ++static struct enable_data preemptirqsoff_enabled_data = { ++ .latency_type = PREEMPTIRQSOFF_LATENCY, ++ .enabled = 0, ++}; ++#endif ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++struct maxlatproc_data { ++ char comm[FIELD_SIZEOF(struct task_struct, comm)]; ++ char current_comm[FIELD_SIZEOF(struct task_struct, comm)]; ++ int pid; ++ int current_pid; ++ int prio; ++ int current_prio; ++ long latency; ++ long timeroffset; ++ cycle_t timestamp; ++}; ++#endif ++ ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist); ++static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist_sharedprio); ++static char *wakeup_latency_hist_dir = "wakeup"; ++static char *wakeup_latency_hist_dir_sharedprio = "sharedprio"; ++static notrace void probe_wakeup_latency_hist_start(void *v, ++ struct task_struct *p, int success); ++static notrace void probe_wakeup_latency_hist_stop(void *v, ++ struct task_struct *prev, struct task_struct *next); ++static notrace void probe_sched_migrate_task(void *, ++ struct task_struct *task, int cpu); ++static struct enable_data wakeup_latency_enabled_data = { ++ .latency_type = WAKEUP_LATENCY, ++ .enabled = 0, ++}; ++static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc); ++static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc_sharedprio); ++static DEFINE_PER_CPU(struct task_struct *, wakeup_task); ++static DEFINE_PER_CPU(int, wakeup_sharedprio); ++static unsigned long wakeup_pid; ++#endif ++ ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++static DEFINE_PER_CPU(struct hist_data, missed_timer_offsets); ++static char *missed_timer_offsets_dir = "missed_timer_offsets"; ++static notrace void probe_hrtimer_interrupt(void *v, int cpu, ++ long long offset, struct task_struct *curr, struct task_struct *task); ++static struct enable_data missed_timer_offsets_enabled_data = { ++ .latency_type = MISSED_TIMER_OFFSETS, ++ .enabled = 0, ++}; ++static DEFINE_PER_CPU(struct maxlatproc_data, missed_timer_offsets_maxlatproc); ++static unsigned long missed_timer_offsets_pid; ++#endif ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++static DEFINE_PER_CPU(struct hist_data, timerandwakeup_latency_hist); ++static char *timerandwakeup_latency_hist_dir = "timerandwakeup"; ++static struct enable_data timerandwakeup_enabled_data = { ++ .latency_type = TIMERANDWAKEUP_LATENCY, ++ .enabled = 0, ++}; ++static DEFINE_PER_CPU(struct maxlatproc_data, timerandwakeup_maxlatproc); ++#endif ++ ++void notrace latency_hist(int latency_type, int cpu, long latency, ++ long timeroffset, cycle_t stop, ++ struct task_struct *p) ++{ ++ struct hist_data *my_hist; ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ struct maxlatproc_data *mp = NULL; ++#endif ++ ++ if (!cpu_possible(cpu) || latency_type < 0 || ++ latency_type >= MAX_LATENCY_TYPE) ++ return; ++ ++ switch (latency_type) { ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++ case IRQSOFF_LATENCY: ++ my_hist = &per_cpu(irqsoff_hist, cpu); ++ break; ++#endif ++#ifdef CONFIG_PREEMPT_OFF_HIST ++ case PREEMPTOFF_LATENCY: ++ my_hist = &per_cpu(preemptoff_hist, cpu); ++ break; ++#endif ++#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST) ++ case PREEMPTIRQSOFF_LATENCY: ++ my_hist = &per_cpu(preemptirqsoff_hist, cpu); ++ break; ++#endif ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ case WAKEUP_LATENCY: ++ my_hist = &per_cpu(wakeup_latency_hist, cpu); ++ mp = &per_cpu(wakeup_maxlatproc, cpu); ++ break; ++ case WAKEUP_LATENCY_SHAREDPRIO: ++ my_hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu); ++ mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu); ++ break; ++#endif ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ case MISSED_TIMER_OFFSETS: ++ my_hist = &per_cpu(missed_timer_offsets, cpu); ++ mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu); ++ break; ++#endif ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ case TIMERANDWAKEUP_LATENCY: ++ my_hist = &per_cpu(timerandwakeup_latency_hist, cpu); ++ mp = &per_cpu(timerandwakeup_maxlatproc, cpu); ++ break; ++#endif ++ ++ default: ++ return; ++ } ++ ++ latency += my_hist->offset; ++ ++ if (atomic_read(&my_hist->hist_mode) == 0) ++ return; ++ ++ if (latency < 0 || latency >= MAX_ENTRY_NUM) { ++ if (latency < 0) ++ my_hist->below_hist_bound_samples++; ++ else ++ my_hist->above_hist_bound_samples++; ++ } else ++ my_hist->hist_array[latency]++; ++ ++ if (unlikely(latency > my_hist->max_lat || ++ my_hist->min_lat == LONG_MAX)) { ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ if (latency_type == WAKEUP_LATENCY || ++ latency_type == WAKEUP_LATENCY_SHAREDPRIO || ++ latency_type == MISSED_TIMER_OFFSETS || ++ latency_type == TIMERANDWAKEUP_LATENCY) { ++ strncpy(mp->comm, p->comm, sizeof(mp->comm)); ++ strncpy(mp->current_comm, current->comm, ++ sizeof(mp->current_comm)); ++ mp->pid = task_pid_nr(p); ++ mp->current_pid = task_pid_nr(current); ++ mp->prio = p->prio; ++ mp->current_prio = current->prio; ++ mp->latency = latency; ++ mp->timeroffset = timeroffset; ++ mp->timestamp = stop; ++ } ++#endif ++ my_hist->max_lat = latency; ++ } ++ if (unlikely(latency < my_hist->min_lat)) ++ my_hist->min_lat = latency; ++ my_hist->total_samples++; ++ my_hist->accumulate_lat += latency; ++} ++ ++static void *l_start(struct seq_file *m, loff_t *pos) ++{ ++ loff_t *index_ptr = NULL; ++ loff_t index = *pos; ++ struct hist_data *my_hist = m->private; ++ ++ if (index == 0) { ++ char minstr[32], avgstr[32], maxstr[32]; ++ ++ atomic_dec(&my_hist->hist_mode); ++ ++ if (likely(my_hist->total_samples)) { ++ long avg = (long) div64_s64(my_hist->accumulate_lat, ++ my_hist->total_samples); ++ snprintf(minstr, sizeof(minstr), "%ld", ++ my_hist->min_lat - my_hist->offset); ++ snprintf(avgstr, sizeof(avgstr), "%ld", ++ avg - my_hist->offset); ++ snprintf(maxstr, sizeof(maxstr), "%ld", ++ my_hist->max_lat - my_hist->offset); ++ } else { ++ strcpy(minstr, ""); ++ strcpy(avgstr, minstr); ++ strcpy(maxstr, minstr); ++ } ++ ++ seq_printf(m, "#Minimum latency: %s microseconds\n" ++ "#Average latency: %s microseconds\n" ++ "#Maximum latency: %s microseconds\n" ++ "#Total samples: %llu\n" ++ "#There are %llu samples lower than %ld" ++ " microseconds.\n" ++ "#There are %llu samples greater or equal" ++ " than %ld microseconds.\n" ++ "#usecs\t%16s\n", ++ minstr, avgstr, maxstr, ++ my_hist->total_samples, ++ my_hist->below_hist_bound_samples, ++ -my_hist->offset, ++ my_hist->above_hist_bound_samples, ++ MAX_ENTRY_NUM - my_hist->offset, ++ "samples"); ++ } ++ if (index < MAX_ENTRY_NUM) { ++ index_ptr = kmalloc(sizeof(loff_t), GFP_KERNEL); ++ if (index_ptr) ++ *index_ptr = index; ++ } ++ ++ return index_ptr; ++} ++ ++static void *l_next(struct seq_file *m, void *p, loff_t *pos) ++{ ++ loff_t *index_ptr = p; ++ struct hist_data *my_hist = m->private; ++ ++ if (++*pos >= MAX_ENTRY_NUM) { ++ atomic_inc(&my_hist->hist_mode); ++ return NULL; ++ } ++ *index_ptr = *pos; ++ return index_ptr; ++} ++ ++static void l_stop(struct seq_file *m, void *p) ++{ ++ kfree(p); ++} ++ ++static int l_show(struct seq_file *m, void *p) ++{ ++ int index = *(loff_t *) p; ++ struct hist_data *my_hist = m->private; ++ ++ seq_printf(m, "%6ld\t%16llu\n", index - my_hist->offset, ++ my_hist->hist_array[index]); ++ return 0; ++} ++ ++static const struct seq_operations latency_hist_seq_op = { ++ .start = l_start, ++ .next = l_next, ++ .stop = l_stop, ++ .show = l_show ++}; ++ ++static int latency_hist_open(struct inode *inode, struct file *file) ++{ ++ int ret; ++ ++ ret = seq_open(file, &latency_hist_seq_op); ++ if (!ret) { ++ struct seq_file *seq = file->private_data; ++ seq->private = inode->i_private; ++ } ++ return ret; ++} ++ ++static const struct file_operations latency_hist_fops = { ++ .open = latency_hist_open, ++ .read = seq_read, ++ .llseek = seq_lseek, ++ .release = seq_release, ++}; ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++static void clear_maxlatprocdata(struct maxlatproc_data *mp) ++{ ++ mp->comm[0] = mp->current_comm[0] = '\0'; ++ mp->prio = mp->current_prio = mp->pid = mp->current_pid = ++ mp->latency = mp->timeroffset = -1; ++ mp->timestamp = 0; ++} ++#endif ++ ++static void hist_reset(struct hist_data *hist) ++{ ++ atomic_dec(&hist->hist_mode); ++ ++ memset(hist->hist_array, 0, sizeof(hist->hist_array)); ++ hist->below_hist_bound_samples = 0ULL; ++ hist->above_hist_bound_samples = 0ULL; ++ hist->min_lat = LONG_MAX; ++ hist->max_lat = LONG_MIN; ++ hist->total_samples = 0ULL; ++ hist->accumulate_lat = 0LL; ++ ++ atomic_inc(&hist->hist_mode); ++} ++ ++static ssize_t ++latency_hist_reset(struct file *file, const char __user *a, ++ size_t size, loff_t *off) ++{ ++ int cpu; ++ struct hist_data *hist = NULL; ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ struct maxlatproc_data *mp = NULL; ++#endif ++ off_t latency_type = (off_t) file->private_data; ++ ++ for_each_online_cpu(cpu) { ++ ++ switch (latency_type) { ++#ifdef CONFIG_PREEMPT_OFF_HIST ++ case PREEMPTOFF_LATENCY: ++ hist = &per_cpu(preemptoff_hist, cpu); ++ break; ++#endif ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++ case IRQSOFF_LATENCY: ++ hist = &per_cpu(irqsoff_hist, cpu); ++ break; ++#endif ++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) ++ case PREEMPTIRQSOFF_LATENCY: ++ hist = &per_cpu(preemptirqsoff_hist, cpu); ++ break; ++#endif ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ case WAKEUP_LATENCY: ++ hist = &per_cpu(wakeup_latency_hist, cpu); ++ mp = &per_cpu(wakeup_maxlatproc, cpu); ++ break; ++ case WAKEUP_LATENCY_SHAREDPRIO: ++ hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu); ++ mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu); ++ break; ++#endif ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ case MISSED_TIMER_OFFSETS: ++ hist = &per_cpu(missed_timer_offsets, cpu); ++ mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu); ++ break; ++#endif ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ case TIMERANDWAKEUP_LATENCY: ++ hist = &per_cpu(timerandwakeup_latency_hist, cpu); ++ mp = &per_cpu(timerandwakeup_maxlatproc, cpu); ++ break; ++#endif ++ } ++ ++ hist_reset(hist); ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ if (latency_type == WAKEUP_LATENCY || ++ latency_type == WAKEUP_LATENCY_SHAREDPRIO || ++ latency_type == MISSED_TIMER_OFFSETS || ++ latency_type == TIMERANDWAKEUP_LATENCY) ++ clear_maxlatprocdata(mp); ++#endif ++ } ++ ++ return size; ++} ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++static ssize_t ++show_pid(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) ++{ ++ char buf[64]; ++ int r; ++ unsigned long *this_pid = file->private_data; ++ ++ r = snprintf(buf, sizeof(buf), "%lu\n", *this_pid); ++ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); ++} ++ ++static ssize_t do_pid(struct file *file, const char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ char buf[64]; ++ unsigned long pid; ++ unsigned long *this_pid = file->private_data; ++ ++ if (cnt >= sizeof(buf)) ++ return -EINVAL; ++ ++ if (copy_from_user(&buf, ubuf, cnt)) ++ return -EFAULT; ++ ++ buf[cnt] = '\0'; ++ ++ if (kstrtoul(buf, 10, &pid)) ++ return -EINVAL; ++ ++ *this_pid = pid; ++ ++ return cnt; ++} ++#endif ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++static ssize_t ++show_maxlatproc(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) ++{ ++ int r; ++ struct maxlatproc_data *mp = file->private_data; ++ int strmaxlen = (TASK_COMM_LEN * 2) + (8 * 8); ++ unsigned long long t; ++ unsigned long usecs, secs; ++ char *buf; ++ ++ if (mp->pid == -1 || mp->current_pid == -1) { ++ buf = "(none)\n"; ++ return simple_read_from_buffer(ubuf, cnt, ppos, buf, ++ strlen(buf)); ++ } ++ ++ buf = kmalloc(strmaxlen, GFP_KERNEL); ++ if (buf == NULL) ++ return -ENOMEM; ++ ++ t = ns2usecs(mp->timestamp); ++ usecs = do_div(t, USEC_PER_SEC); ++ secs = (unsigned long) t; ++ r = snprintf(buf, strmaxlen, ++ "%d %d %ld (%ld) %s <- %d %d %s %lu.%06lu\n", mp->pid, ++ MAX_RT_PRIO-1 - mp->prio, mp->latency, mp->timeroffset, mp->comm, ++ mp->current_pid, MAX_RT_PRIO-1 - mp->current_prio, mp->current_comm, ++ secs, usecs); ++ r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); ++ kfree(buf); ++ return r; ++} ++#endif ++ ++static ssize_t ++show_enable(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) ++{ ++ char buf[64]; ++ struct enable_data *ed = file->private_data; ++ int r; ++ ++ r = snprintf(buf, sizeof(buf), "%d\n", ed->enabled); ++ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); ++} ++ ++static ssize_t ++do_enable(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) ++{ ++ char buf[64]; ++ long enable; ++ struct enable_data *ed = file->private_data; ++ ++ if (cnt >= sizeof(buf)) ++ return -EINVAL; ++ ++ if (copy_from_user(&buf, ubuf, cnt)) ++ return -EFAULT; ++ ++ buf[cnt] = 0; ++ ++ if (kstrtoul(buf, 10, &enable)) ++ return -EINVAL; ++ ++ if ((enable && ed->enabled) || (!enable && !ed->enabled)) ++ return cnt; ++ ++ if (enable) { ++ int ret; ++ ++ switch (ed->latency_type) { ++#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) ++ case PREEMPTIRQSOFF_LATENCY: ++ ret = register_trace_preemptirqsoff_hist( ++ probe_preemptirqsoff_hist, NULL); ++ if (ret) { ++ pr_info("wakeup trace: Couldn't assign " ++ "probe_preemptirqsoff_hist " ++ "to trace_preemptirqsoff_hist\n"); ++ return ret; ++ } ++ break; ++#endif ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ case WAKEUP_LATENCY: ++ ret = register_trace_sched_wakeup( ++ probe_wakeup_latency_hist_start, NULL); ++ if (ret) { ++ pr_info("wakeup trace: Couldn't assign " ++ "probe_wakeup_latency_hist_start " ++ "to trace_sched_wakeup\n"); ++ return ret; ++ } ++ ret = register_trace_sched_wakeup_new( ++ probe_wakeup_latency_hist_start, NULL); ++ if (ret) { ++ pr_info("wakeup trace: Couldn't assign " ++ "probe_wakeup_latency_hist_start " ++ "to trace_sched_wakeup_new\n"); ++ unregister_trace_sched_wakeup( ++ probe_wakeup_latency_hist_start, NULL); ++ return ret; ++ } ++ ret = register_trace_sched_switch( ++ probe_wakeup_latency_hist_stop, NULL); ++ if (ret) { ++ pr_info("wakeup trace: Couldn't assign " ++ "probe_wakeup_latency_hist_stop " ++ "to trace_sched_switch\n"); ++ unregister_trace_sched_wakeup( ++ probe_wakeup_latency_hist_start, NULL); ++ unregister_trace_sched_wakeup_new( ++ probe_wakeup_latency_hist_start, NULL); ++ return ret; ++ } ++ ret = register_trace_sched_migrate_task( ++ probe_sched_migrate_task, NULL); ++ if (ret) { ++ pr_info("wakeup trace: Couldn't assign " ++ "probe_sched_migrate_task " ++ "to trace_sched_migrate_task\n"); ++ unregister_trace_sched_wakeup( ++ probe_wakeup_latency_hist_start, NULL); ++ unregister_trace_sched_wakeup_new( ++ probe_wakeup_latency_hist_start, NULL); ++ unregister_trace_sched_switch( ++ probe_wakeup_latency_hist_stop, NULL); ++ return ret; ++ } ++ break; ++#endif ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ case MISSED_TIMER_OFFSETS: ++ ret = register_trace_hrtimer_interrupt( ++ probe_hrtimer_interrupt, NULL); ++ if (ret) { ++ pr_info("wakeup trace: Couldn't assign " ++ "probe_hrtimer_interrupt " ++ "to trace_hrtimer_interrupt\n"); ++ return ret; ++ } ++ break; ++#endif ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ case TIMERANDWAKEUP_LATENCY: ++ if (!wakeup_latency_enabled_data.enabled || ++ !missed_timer_offsets_enabled_data.enabled) ++ return -EINVAL; ++ break; ++#endif ++ default: ++ break; ++ } ++ } else { ++ switch (ed->latency_type) { ++#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) ++ case PREEMPTIRQSOFF_LATENCY: ++ { ++ int cpu; ++ ++ unregister_trace_preemptirqsoff_hist( ++ probe_preemptirqsoff_hist, NULL); ++ for_each_online_cpu(cpu) { ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++ per_cpu(hist_irqsoff_counting, ++ cpu) = 0; ++#endif ++#ifdef CONFIG_PREEMPT_OFF_HIST ++ per_cpu(hist_preemptoff_counting, ++ cpu) = 0; ++#endif ++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) ++ per_cpu(hist_preemptirqsoff_counting, ++ cpu) = 0; ++#endif ++ } ++ } ++ break; ++#endif ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ case WAKEUP_LATENCY: ++ { ++ int cpu; ++ ++ unregister_trace_sched_wakeup( ++ probe_wakeup_latency_hist_start, NULL); ++ unregister_trace_sched_wakeup_new( ++ probe_wakeup_latency_hist_start, NULL); ++ unregister_trace_sched_switch( ++ probe_wakeup_latency_hist_stop, NULL); ++ unregister_trace_sched_migrate_task( ++ probe_sched_migrate_task, NULL); ++ ++ for_each_online_cpu(cpu) { ++ per_cpu(wakeup_task, cpu) = NULL; ++ per_cpu(wakeup_sharedprio, cpu) = 0; ++ } ++ } ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ timerandwakeup_enabled_data.enabled = 0; ++#endif ++ break; ++#endif ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ case MISSED_TIMER_OFFSETS: ++ unregister_trace_hrtimer_interrupt( ++ probe_hrtimer_interrupt, NULL); ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ timerandwakeup_enabled_data.enabled = 0; ++#endif ++ break; ++#endif ++ default: ++ break; ++ } ++ } ++ ed->enabled = enable; ++ return cnt; ++} ++ ++static const struct file_operations latency_hist_reset_fops = { ++ .open = tracing_open_generic, ++ .write = latency_hist_reset, ++}; ++ ++static const struct file_operations enable_fops = { ++ .open = tracing_open_generic, ++ .read = show_enable, ++ .write = do_enable, ++}; ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++static const struct file_operations pid_fops = { ++ .open = tracing_open_generic, ++ .read = show_pid, ++ .write = do_pid, ++}; ++ ++static const struct file_operations maxlatproc_fops = { ++ .open = tracing_open_generic, ++ .read = show_maxlatproc, ++}; ++#endif ++ ++#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) ++static notrace void probe_preemptirqsoff_hist(void *v, int reason, ++ int starthist) ++{ ++ int cpu = raw_smp_processor_id(); ++ int time_set = 0; ++ ++ if (starthist) { ++ cycle_t uninitialized_var(start); ++ ++ if (!preempt_count() && !irqs_disabled()) ++ return; ++ ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++ if ((reason == IRQS_OFF || reason == TRACE_START) && ++ !per_cpu(hist_irqsoff_counting, cpu)) { ++ per_cpu(hist_irqsoff_counting, cpu) = 1; ++ start = ftrace_now(cpu); ++ time_set++; ++ per_cpu(hist_irqsoff_start, cpu) = start; ++ } ++#endif ++ ++#ifdef CONFIG_PREEMPT_OFF_HIST ++ if ((reason == PREEMPT_OFF || reason == TRACE_START) && ++ !per_cpu(hist_preemptoff_counting, cpu)) { ++ per_cpu(hist_preemptoff_counting, cpu) = 1; ++ if (!(time_set++)) ++ start = ftrace_now(cpu); ++ per_cpu(hist_preemptoff_start, cpu) = start; ++ } ++#endif ++ ++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) ++ if (per_cpu(hist_irqsoff_counting, cpu) && ++ per_cpu(hist_preemptoff_counting, cpu) && ++ !per_cpu(hist_preemptirqsoff_counting, cpu)) { ++ per_cpu(hist_preemptirqsoff_counting, cpu) = 1; ++ if (!time_set) ++ start = ftrace_now(cpu); ++ per_cpu(hist_preemptirqsoff_start, cpu) = start; ++ } ++#endif ++ } else { ++ cycle_t uninitialized_var(stop); ++ ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++ if ((reason == IRQS_ON || reason == TRACE_STOP) && ++ per_cpu(hist_irqsoff_counting, cpu)) { ++ cycle_t start = per_cpu(hist_irqsoff_start, cpu); ++ ++ stop = ftrace_now(cpu); ++ time_set++; ++ if (start) { ++ long latency = ((long) (stop - start)) / ++ NSECS_PER_USECS; ++ ++ latency_hist(IRQSOFF_LATENCY, cpu, latency, 0, ++ stop, NULL); ++ } ++ per_cpu(hist_irqsoff_counting, cpu) = 0; ++ } ++#endif ++ ++#ifdef CONFIG_PREEMPT_OFF_HIST ++ if ((reason == PREEMPT_ON || reason == TRACE_STOP) && ++ per_cpu(hist_preemptoff_counting, cpu)) { ++ cycle_t start = per_cpu(hist_preemptoff_start, cpu); ++ ++ if (!(time_set++)) ++ stop = ftrace_now(cpu); ++ if (start) { ++ long latency = ((long) (stop - start)) / ++ NSECS_PER_USECS; ++ ++ latency_hist(PREEMPTOFF_LATENCY, cpu, latency, ++ 0, stop, NULL); ++ } ++ per_cpu(hist_preemptoff_counting, cpu) = 0; ++ } ++#endif ++ ++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) ++ if ((!per_cpu(hist_irqsoff_counting, cpu) || ++ !per_cpu(hist_preemptoff_counting, cpu)) && ++ per_cpu(hist_preemptirqsoff_counting, cpu)) { ++ cycle_t start = per_cpu(hist_preemptirqsoff_start, cpu); ++ ++ if (!time_set) ++ stop = ftrace_now(cpu); ++ if (start) { ++ long latency = ((long) (stop - start)) / ++ NSECS_PER_USECS; ++ ++ latency_hist(PREEMPTIRQSOFF_LATENCY, cpu, ++ latency, 0, stop, NULL); ++ } ++ per_cpu(hist_preemptirqsoff_counting, cpu) = 0; ++ } ++#endif ++ } ++} ++#endif ++ ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++static DEFINE_RAW_SPINLOCK(wakeup_lock); ++static notrace void probe_sched_migrate_task(void *v, struct task_struct *task, ++ int cpu) ++{ ++ int old_cpu = task_cpu(task); ++ ++ if (cpu != old_cpu) { ++ unsigned long flags; ++ struct task_struct *cpu_wakeup_task; ++ ++ raw_spin_lock_irqsave(&wakeup_lock, flags); ++ ++ cpu_wakeup_task = per_cpu(wakeup_task, old_cpu); ++ if (task == cpu_wakeup_task) { ++ put_task_struct(cpu_wakeup_task); ++ per_cpu(wakeup_task, old_cpu) = NULL; ++ cpu_wakeup_task = per_cpu(wakeup_task, cpu) = task; ++ get_task_struct(cpu_wakeup_task); ++ } ++ ++ raw_spin_unlock_irqrestore(&wakeup_lock, flags); ++ } ++} ++ ++static notrace void probe_wakeup_latency_hist_start(void *v, ++ struct task_struct *p, int success) ++{ ++ unsigned long flags; ++ struct task_struct *curr = current; ++ int cpu = task_cpu(p); ++ struct task_struct *cpu_wakeup_task; ++ ++ raw_spin_lock_irqsave(&wakeup_lock, flags); ++ ++ cpu_wakeup_task = per_cpu(wakeup_task, cpu); ++ ++ if (wakeup_pid) { ++ if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) || ++ p->prio == curr->prio) ++ per_cpu(wakeup_sharedprio, cpu) = 1; ++ if (likely(wakeup_pid != task_pid_nr(p))) ++ goto out; ++ } else { ++ if (likely(!rt_task(p)) || ++ (cpu_wakeup_task && p->prio > cpu_wakeup_task->prio) || ++ p->prio > curr->prio) ++ goto out; ++ if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) || ++ p->prio == curr->prio) ++ per_cpu(wakeup_sharedprio, cpu) = 1; ++ } ++ ++ if (cpu_wakeup_task) ++ put_task_struct(cpu_wakeup_task); ++ cpu_wakeup_task = per_cpu(wakeup_task, cpu) = p; ++ get_task_struct(cpu_wakeup_task); ++ cpu_wakeup_task->preempt_timestamp_hist = ++ ftrace_now(raw_smp_processor_id()); ++out: ++ raw_spin_unlock_irqrestore(&wakeup_lock, flags); ++} ++ ++static notrace void probe_wakeup_latency_hist_stop(void *v, ++ struct task_struct *prev, struct task_struct *next) ++{ ++ unsigned long flags; ++ int cpu = task_cpu(next); ++ long latency; ++ cycle_t stop; ++ struct task_struct *cpu_wakeup_task; ++ ++ raw_spin_lock_irqsave(&wakeup_lock, flags); ++ ++ cpu_wakeup_task = per_cpu(wakeup_task, cpu); ++ ++ if (cpu_wakeup_task == NULL) ++ goto out; ++ ++ /* Already running? */ ++ if (unlikely(current == cpu_wakeup_task)) ++ goto out_reset; ++ ++ if (next != cpu_wakeup_task) { ++ if (next->prio < cpu_wakeup_task->prio) ++ goto out_reset; ++ ++ if (next->prio == cpu_wakeup_task->prio) ++ per_cpu(wakeup_sharedprio, cpu) = 1; ++ ++ goto out; ++ } ++ ++ if (current->prio == cpu_wakeup_task->prio) ++ per_cpu(wakeup_sharedprio, cpu) = 1; ++ ++ /* ++ * The task we are waiting for is about to be switched to. ++ * Calculate latency and store it in histogram. ++ */ ++ stop = ftrace_now(raw_smp_processor_id()); ++ ++ latency = ((long) (stop - next->preempt_timestamp_hist)) / ++ NSECS_PER_USECS; ++ ++ if (per_cpu(wakeup_sharedprio, cpu)) { ++ latency_hist(WAKEUP_LATENCY_SHAREDPRIO, cpu, latency, 0, stop, ++ next); ++ per_cpu(wakeup_sharedprio, cpu) = 0; ++ } else { ++ latency_hist(WAKEUP_LATENCY, cpu, latency, 0, stop, next); ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ if (timerandwakeup_enabled_data.enabled) { ++ latency_hist(TIMERANDWAKEUP_LATENCY, cpu, ++ next->timer_offset + latency, next->timer_offset, ++ stop, next); ++ } ++#endif ++ } ++ ++out_reset: ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ next->timer_offset = 0; ++#endif ++ put_task_struct(cpu_wakeup_task); ++ per_cpu(wakeup_task, cpu) = NULL; ++out: ++ raw_spin_unlock_irqrestore(&wakeup_lock, flags); ++} ++#endif ++ ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++static notrace void probe_hrtimer_interrupt(void *v, int cpu, ++ long long latency_ns, struct task_struct *curr, ++ struct task_struct *task) ++{ ++ if (latency_ns <= 0 && task != NULL && rt_task(task) && ++ (task->prio < curr->prio || ++ (task->prio == curr->prio && ++ !cpumask_test_cpu(cpu, &task->cpus_allowed)))) { ++ long latency; ++ cycle_t now; ++ ++ if (missed_timer_offsets_pid) { ++ if (likely(missed_timer_offsets_pid != ++ task_pid_nr(task))) ++ return; ++ } ++ ++ now = ftrace_now(cpu); ++ latency = (long) div_s64(-latency_ns, NSECS_PER_USECS); ++ latency_hist(MISSED_TIMER_OFFSETS, cpu, latency, latency, now, ++ task); ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ task->timer_offset = latency; ++#endif ++ } ++} ++#endif ++ ++static __init int latency_hist_init(void) ++{ ++ struct dentry *latency_hist_root = NULL; ++ struct dentry *dentry; ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ struct dentry *dentry_sharedprio; ++#endif ++ struct dentry *entry; ++ struct dentry *enable_root; ++ int i = 0; ++ struct hist_data *my_hist; ++ char name[64]; ++ char *cpufmt = "CPU%d"; ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ char *cpufmt_maxlatproc = "max_latency-CPU%d"; ++ struct maxlatproc_data *mp = NULL; ++#endif ++ ++ dentry = tracing_init_dentry(); ++ latency_hist_root = debugfs_create_dir(latency_hist_dir_root, dentry); ++ enable_root = debugfs_create_dir("enable", latency_hist_root); ++ ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++ dentry = debugfs_create_dir(irqsoff_hist_dir, latency_hist_root); ++ for_each_possible_cpu(i) { ++ sprintf(name, cpufmt, i); ++ entry = debugfs_create_file(name, 0444, dentry, ++ &per_cpu(irqsoff_hist, i), &latency_hist_fops); ++ my_hist = &per_cpu(irqsoff_hist, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ } ++ entry = debugfs_create_file("reset", 0644, dentry, ++ (void *)IRQSOFF_LATENCY, &latency_hist_reset_fops); ++#endif ++ ++#ifdef CONFIG_PREEMPT_OFF_HIST ++ dentry = debugfs_create_dir(preemptoff_hist_dir, ++ latency_hist_root); ++ for_each_possible_cpu(i) { ++ sprintf(name, cpufmt, i); ++ entry = debugfs_create_file(name, 0444, dentry, ++ &per_cpu(preemptoff_hist, i), &latency_hist_fops); ++ my_hist = &per_cpu(preemptoff_hist, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ } ++ entry = debugfs_create_file("reset", 0644, dentry, ++ (void *)PREEMPTOFF_LATENCY, &latency_hist_reset_fops); ++#endif ++ ++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) ++ dentry = debugfs_create_dir(preemptirqsoff_hist_dir, ++ latency_hist_root); ++ for_each_possible_cpu(i) { ++ sprintf(name, cpufmt, i); ++ entry = debugfs_create_file(name, 0444, dentry, ++ &per_cpu(preemptirqsoff_hist, i), &latency_hist_fops); ++ my_hist = &per_cpu(preemptirqsoff_hist, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ } ++ entry = debugfs_create_file("reset", 0644, dentry, ++ (void *)PREEMPTIRQSOFF_LATENCY, &latency_hist_reset_fops); ++#endif ++ ++#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) ++ entry = debugfs_create_file("preemptirqsoff", 0644, ++ enable_root, (void *)&preemptirqsoff_enabled_data, ++ &enable_fops); ++#endif ++ ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ dentry = debugfs_create_dir(wakeup_latency_hist_dir, ++ latency_hist_root); ++ dentry_sharedprio = debugfs_create_dir( ++ wakeup_latency_hist_dir_sharedprio, dentry); ++ for_each_possible_cpu(i) { ++ sprintf(name, cpufmt, i); ++ ++ entry = debugfs_create_file(name, 0444, dentry, ++ &per_cpu(wakeup_latency_hist, i), ++ &latency_hist_fops); ++ my_hist = &per_cpu(wakeup_latency_hist, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ ++ entry = debugfs_create_file(name, 0444, dentry_sharedprio, ++ &per_cpu(wakeup_latency_hist_sharedprio, i), ++ &latency_hist_fops); ++ my_hist = &per_cpu(wakeup_latency_hist_sharedprio, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ ++ sprintf(name, cpufmt_maxlatproc, i); ++ ++ mp = &per_cpu(wakeup_maxlatproc, i); ++ entry = debugfs_create_file(name, 0444, dentry, mp, ++ &maxlatproc_fops); ++ clear_maxlatprocdata(mp); ++ ++ mp = &per_cpu(wakeup_maxlatproc_sharedprio, i); ++ entry = debugfs_create_file(name, 0444, dentry_sharedprio, mp, ++ &maxlatproc_fops); ++ clear_maxlatprocdata(mp); ++ } ++ entry = debugfs_create_file("pid", 0644, dentry, ++ (void *)&wakeup_pid, &pid_fops); ++ entry = debugfs_create_file("reset", 0644, dentry, ++ (void *)WAKEUP_LATENCY, &latency_hist_reset_fops); ++ entry = debugfs_create_file("reset", 0644, dentry_sharedprio, ++ (void *)WAKEUP_LATENCY_SHAREDPRIO, &latency_hist_reset_fops); ++ entry = debugfs_create_file("wakeup", 0644, ++ enable_root, (void *)&wakeup_latency_enabled_data, ++ &enable_fops); ++#endif ++ ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ dentry = debugfs_create_dir(missed_timer_offsets_dir, ++ latency_hist_root); ++ for_each_possible_cpu(i) { ++ sprintf(name, cpufmt, i); ++ entry = debugfs_create_file(name, 0444, dentry, ++ &per_cpu(missed_timer_offsets, i), &latency_hist_fops); ++ my_hist = &per_cpu(missed_timer_offsets, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ ++ sprintf(name, cpufmt_maxlatproc, i); ++ mp = &per_cpu(missed_timer_offsets_maxlatproc, i); ++ entry = debugfs_create_file(name, 0444, dentry, mp, ++ &maxlatproc_fops); ++ clear_maxlatprocdata(mp); ++ } ++ entry = debugfs_create_file("pid", 0644, dentry, ++ (void *)&missed_timer_offsets_pid, &pid_fops); ++ entry = debugfs_create_file("reset", 0644, dentry, ++ (void *)MISSED_TIMER_OFFSETS, &latency_hist_reset_fops); ++ entry = debugfs_create_file("missed_timer_offsets", 0644, ++ enable_root, (void *)&missed_timer_offsets_enabled_data, ++ &enable_fops); ++#endif ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ dentry = debugfs_create_dir(timerandwakeup_latency_hist_dir, ++ latency_hist_root); ++ for_each_possible_cpu(i) { ++ sprintf(name, cpufmt, i); ++ entry = debugfs_create_file(name, 0444, dentry, ++ &per_cpu(timerandwakeup_latency_hist, i), ++ &latency_hist_fops); ++ my_hist = &per_cpu(timerandwakeup_latency_hist, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ ++ sprintf(name, cpufmt_maxlatproc, i); ++ mp = &per_cpu(timerandwakeup_maxlatproc, i); ++ entry = debugfs_create_file(name, 0444, dentry, mp, ++ &maxlatproc_fops); ++ clear_maxlatprocdata(mp); ++ } ++ entry = debugfs_create_file("reset", 0644, dentry, ++ (void *)TIMERANDWAKEUP_LATENCY, &latency_hist_reset_fops); ++ entry = debugfs_create_file("timerandwakeup", 0644, ++ enable_root, (void *)&timerandwakeup_enabled_data, ++ &enable_fops); ++#endif ++ return 0; ++} ++ ++device_initcall(latency_hist_init); +--- a/kernel/trace/trace_irqsoff.c ++++ b/kernel/trace/trace_irqsoff.c +@@ -13,6 +13,7 @@ + #include + #include + #include ++#include + + #include "trace.h" + +@@ -433,11 +434,13 @@ void start_critical_timings(void) + { + if (preempt_trace() || irq_trace()) + start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); ++ trace_preemptirqsoff_hist(TRACE_START, 1); + } + EXPORT_SYMBOL_GPL(start_critical_timings); + + void stop_critical_timings(void) + { ++ trace_preemptirqsoff_hist(TRACE_STOP, 0); + if (preempt_trace() || irq_trace()) + stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); + } +@@ -447,6 +450,7 @@ EXPORT_SYMBOL_GPL(stop_critical_timings) + #ifdef CONFIG_PROVE_LOCKING + void time_hardirqs_on(unsigned long a0, unsigned long a1) + { ++ trace_preemptirqsoff_hist(IRQS_ON, 0); + if (!preempt_trace() && irq_trace()) + stop_critical_timing(a0, a1); + } +@@ -455,6 +459,7 @@ void time_hardirqs_off(unsigned long a0, + { + if (!preempt_trace() && irq_trace()) + start_critical_timing(a0, a1); ++ trace_preemptirqsoff_hist(IRQS_OFF, 1); + } + + #else /* !CONFIG_PROVE_LOCKING */ +@@ -480,6 +485,7 @@ inline void print_irqtrace_events(struct + */ + void trace_hardirqs_on(void) + { ++ trace_preemptirqsoff_hist(IRQS_ON, 0); + if (!preempt_trace() && irq_trace()) + stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); + } +@@ -489,11 +495,13 @@ void trace_hardirqs_off(void) + { + if (!preempt_trace() && irq_trace()) + start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); ++ trace_preemptirqsoff_hist(IRQS_OFF, 1); + } + EXPORT_SYMBOL(trace_hardirqs_off); + + __visible void trace_hardirqs_on_caller(unsigned long caller_addr) + { ++ trace_preemptirqsoff_hist(IRQS_ON, 0); + if (!preempt_trace() && irq_trace()) + stop_critical_timing(CALLER_ADDR0, caller_addr); + } +@@ -503,6 +511,7 @@ EXPORT_SYMBOL(trace_hardirqs_on_caller); + { + if (!preempt_trace() && irq_trace()) + start_critical_timing(CALLER_ADDR0, caller_addr); ++ trace_preemptirqsoff_hist(IRQS_OFF, 1); + } + EXPORT_SYMBOL(trace_hardirqs_off_caller); + +@@ -512,12 +521,14 @@ EXPORT_SYMBOL(trace_hardirqs_off_caller) + #ifdef CONFIG_PREEMPT_TRACER + void trace_preempt_on(unsigned long a0, unsigned long a1) + { ++ trace_preemptirqsoff_hist(PREEMPT_ON, 0); + if (preempt_trace() && !irq_trace()) + stop_critical_timing(a0, a1); + } + + void trace_preempt_off(unsigned long a0, unsigned long a1) + { ++ trace_preemptirqsoff_hist(PREEMPT_ON, 1); + if (preempt_trace() && !irq_trace()) + start_critical_timing(a0, a1); + } diff --git a/debian/patches/features/all/rt/leds-trigger-disable-CPU-trigger-on-RT.patch b/debian/patches/features/all/rt/leds-trigger-disable-CPU-trigger-on-RT.patch new file mode 100644 index 000000000..dec3a42ce --- /dev/null +++ b/debian/patches/features/all/rt/leds-trigger-disable-CPU-trigger-on-RT.patch @@ -0,0 +1,36 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 23 Jan 2014 14:45:59 +0100 +Subject: leds: trigger: disable CPU trigger on -RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +as it triggers: +|CPU: 0 PID: 0 Comm: swapper Not tainted 3.12.8-rt10 #141 +|[] (unwind_backtrace+0x0/0xf8) from [] (show_stack+0x1c/0x20) +|[] (show_stack+0x1c/0x20) from [] (dump_stack+0x20/0x2c) +|[] (dump_stack+0x20/0x2c) from [] (__might_sleep+0x13c/0x170) +|[] (__might_sleep+0x13c/0x170) from [] (__rt_spin_lock+0x28/0x38) +|[] (__rt_spin_lock+0x28/0x38) from [] (rt_read_lock+0x68/0x7c) +|[] (rt_read_lock+0x68/0x7c) from [] (led_trigger_event+0x2c/0x5c) +|[] (led_trigger_event+0x2c/0x5c) from [] (ledtrig_cpu+0x54/0x5c) +|[] (ledtrig_cpu+0x54/0x5c) from [] (arch_cpu_idle_exit+0x18/0x1c) +|[] (arch_cpu_idle_exit+0x18/0x1c) from [] (cpu_startup_entry+0xa8/0x234) +|[] (cpu_startup_entry+0xa8/0x234) from [] (rest_init+0xb8/0xe0) +|[] (rest_init+0xb8/0xe0) from [] (start_kernel+0x2c4/0x380) + + +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/leds/trigger/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/leds/trigger/Kconfig ++++ b/drivers/leds/trigger/Kconfig +@@ -61,7 +61,7 @@ config LEDS_TRIGGER_BACKLIGHT + + config LEDS_TRIGGER_CPU + bool "LED CPU Trigger" +- depends on LEDS_TRIGGERS ++ depends on LEDS_TRIGGERS && !PREEMPT_RT_BASE + help + This allows LEDs to be controlled by active CPUs. This shows + the active CPUs across an array of LEDs so you can see which diff --git a/debian/patches/features/all/rt/lglocks-rt.patch b/debian/patches/features/all/rt/lglocks-rt.patch new file mode 100644 index 000000000..b11890624 --- /dev/null +++ b/debian/patches/features/all/rt/lglocks-rt.patch @@ -0,0 +1,183 @@ +Subject: lglocks: Provide a RT safe variant +From: Thomas Gleixner +Date: Wed, 15 Jun 2011 11:02:21 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +lglocks by itself will spin in order to get the lock. This will end up +badly if a task with the highest priority keeps spinning while a task +with the lowest priority owns the lock. + +Lets replace them with rt_mutex based locks so they can sleep, track +owner and boost if needed. + +Signed-off-by: Thomas Gleixner +--- + include/linux/lglock.h | 21 ++++++++++++++++-- + kernel/locking/lglock.c | 54 ++++++++++++++++++++++++++++++++---------------- + 2 files changed, 55 insertions(+), 20 deletions(-) + +--- a/include/linux/lglock.h ++++ b/include/linux/lglock.h +@@ -34,22 +34,39 @@ + #endif + + struct lglock { ++#ifndef CONFIG_PREEMPT_RT_FULL + arch_spinlock_t __percpu *lock; ++#else ++ struct rt_mutex __percpu *lock; ++#endif + #ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lock_class_key lock_key; + struct lockdep_map lock_dep_map; + #endif + }; + +-#define DEFINE_LGLOCK(name) \ ++#ifndef CONFIG_PREEMPT_RT_FULL ++# define DEFINE_LGLOCK(name) \ + static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \ + = __ARCH_SPIN_LOCK_UNLOCKED; \ + struct lglock name = { .lock = &name ## _lock } + +-#define DEFINE_STATIC_LGLOCK(name) \ ++# define DEFINE_STATIC_LGLOCK(name) \ + static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \ + = __ARCH_SPIN_LOCK_UNLOCKED; \ + static struct lglock name = { .lock = &name ## _lock } ++#else ++ ++# define DEFINE_LGLOCK(name) \ ++ static DEFINE_PER_CPU(struct rt_mutex, name ## _lock) \ ++ = __RT_MUTEX_INITIALIZER( name ## _lock); \ ++ struct lglock name = { .lock = &name ## _lock } ++ ++# define DEFINE_STATIC_LGLOCK(name) \ ++ static DEFINE_PER_CPU(struct rt_mutex, name ## _lock) \ ++ = __RT_MUTEX_INITIALIZER( name ## _lock); \ ++ static struct lglock name = { .lock = &name ## _lock } ++#endif + + void lg_lock_init(struct lglock *lg, char *name); + void lg_local_lock(struct lglock *lg); +--- a/kernel/locking/lglock.c ++++ b/kernel/locking/lglock.c +@@ -4,6 +4,15 @@ + #include + #include + ++#ifndef CONFIG_PREEMPT_RT_FULL ++# define lg_lock_ptr arch_spinlock_t ++# define lg_do_lock(l) arch_spin_lock(l) ++# define lg_do_unlock(l) arch_spin_unlock(l) ++#else ++# define lg_lock_ptr struct rt_mutex ++# define lg_do_lock(l) __rt_spin_lock(l) ++# define lg_do_unlock(l) __rt_spin_unlock(l) ++#endif + /* + * Note there is no uninit, so lglocks cannot be defined in + * modules (but it's fine to use them from there) +@@ -12,51 +21,60 @@ + + void lg_lock_init(struct lglock *lg, char *name) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ int i; ++ ++ for_each_possible_cpu(i) { ++ struct rt_mutex *lock = per_cpu_ptr(lg->lock, i); ++ ++ rt_mutex_init(lock); ++ } ++#endif + LOCKDEP_INIT_MAP(&lg->lock_dep_map, name, &lg->lock_key, 0); + } + EXPORT_SYMBOL(lg_lock_init); + + void lg_local_lock(struct lglock *lg) + { +- arch_spinlock_t *lock; ++ lg_lock_ptr *lock; + +- preempt_disable(); ++ migrate_disable(); + lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); + lock = this_cpu_ptr(lg->lock); +- arch_spin_lock(lock); ++ lg_do_lock(lock); + } + EXPORT_SYMBOL(lg_local_lock); + + void lg_local_unlock(struct lglock *lg) + { +- arch_spinlock_t *lock; ++ lg_lock_ptr *lock; + + lock_release(&lg->lock_dep_map, 1, _RET_IP_); + lock = this_cpu_ptr(lg->lock); +- arch_spin_unlock(lock); +- preempt_enable(); ++ lg_do_unlock(lock); ++ migrate_enable(); + } + EXPORT_SYMBOL(lg_local_unlock); + + void lg_local_lock_cpu(struct lglock *lg, int cpu) + { +- arch_spinlock_t *lock; ++ lg_lock_ptr *lock; + +- preempt_disable(); ++ preempt_disable_nort(); + lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); + lock = per_cpu_ptr(lg->lock, cpu); +- arch_spin_lock(lock); ++ lg_do_lock(lock); + } + EXPORT_SYMBOL(lg_local_lock_cpu); + + void lg_local_unlock_cpu(struct lglock *lg, int cpu) + { +- arch_spinlock_t *lock; ++ lg_lock_ptr *lock; + + lock_release(&lg->lock_dep_map, 1, _RET_IP_); + lock = per_cpu_ptr(lg->lock, cpu); +- arch_spin_unlock(lock); +- preempt_enable(); ++ lg_do_unlock(lock); ++ preempt_enable_nort(); + } + EXPORT_SYMBOL(lg_local_unlock_cpu); + +@@ -64,12 +82,12 @@ void lg_global_lock(struct lglock *lg) + { + int i; + +- preempt_disable(); ++ preempt_disable_nort(); + lock_acquire_exclusive(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); + for_each_possible_cpu(i) { +- arch_spinlock_t *lock; ++ lg_lock_ptr *lock; + lock = per_cpu_ptr(lg->lock, i); +- arch_spin_lock(lock); ++ lg_do_lock(lock); + } + } + EXPORT_SYMBOL(lg_global_lock); +@@ -80,10 +98,10 @@ void lg_global_unlock(struct lglock *lg) + + lock_release(&lg->lock_dep_map, 1, _RET_IP_); + for_each_possible_cpu(i) { +- arch_spinlock_t *lock; ++ lg_lock_ptr *lock; + lock = per_cpu_ptr(lg->lock, i); +- arch_spin_unlock(lock); ++ lg_do_unlock(lock); + } +- preempt_enable(); ++ preempt_enable_nort(); + } + EXPORT_SYMBOL(lg_global_unlock); diff --git a/debian/patches/features/all/rt/list_bl.h-make-list-head-locking-RT-safe.patch b/debian/patches/features/all/rt/list_bl.h-make-list-head-locking-RT-safe.patch new file mode 100644 index 000000000..0fcbf6274 --- /dev/null +++ b/debian/patches/features/all/rt/list_bl.h-make-list-head-locking-RT-safe.patch @@ -0,0 +1,115 @@ +From: Paul Gortmaker +Date: Fri, 21 Jun 2013 15:07:25 -0400 +Subject: list_bl: Make list head locking RT safe +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +As per changes in include/linux/jbd_common.h for avoiding the +bit_spin_locks on RT ("fs: jbd/jbd2: Make state lock and journal +head lock rt safe") we do the same thing here. + +We use the non atomic __set_bit and __clear_bit inside the scope of +the lock to preserve the ability of the existing LIST_DEBUG code to +use the zero'th bit in the sanity checks. + +As a bit spinlock, we had no lockdep visibility into the usage +of the list head locking. Now, if we were to implement it as a +standard non-raw spinlock, we would see: + +BUG: sleeping function called from invalid context at kernel/rtmutex.c:658 +in_atomic(): 1, irqs_disabled(): 0, pid: 122, name: udevd +5 locks held by udevd/122: + #0: (&sb->s_type->i_mutex_key#7/1){+.+.+.}, at: [] lock_rename+0xe8/0xf0 + #1: (rename_lock){+.+...}, at: [] d_move+0x2c/0x60 + #2: (&dentry->d_lock){+.+...}, at: [] dentry_lock_for_move+0xf3/0x130 + #3: (&dentry->d_lock/2){+.+...}, at: [] dentry_lock_for_move+0xc4/0x130 + #4: (&dentry->d_lock/3){+.+...}, at: [] dentry_lock_for_move+0xd7/0x130 +Pid: 122, comm: udevd Not tainted 3.4.47-rt62 #7 +Call Trace: + [] __might_sleep+0x134/0x1f0 + [] rt_spin_lock+0x24/0x60 + [] __d_shrink+0x5c/0xa0 + [] __d_drop+0x1d/0x40 + [] __d_move+0x8e/0x320 + [] d_move+0x3e/0x60 + [] vfs_rename+0x198/0x4c0 + [] sys_renameat+0x213/0x240 + [] ? _raw_spin_unlock+0x35/0x60 + [] ? do_page_fault+0x1ec/0x4b0 + [] ? retint_swapgs+0xe/0x13 + [] ? trace_hardirqs_on_thunk+0x3a/0x3f + [] sys_rename+0x1b/0x20 + [] system_call_fastpath+0x1a/0x1f + +Since we are only taking the lock during short lived list operations, +lets assume for now that it being raw won't be a significant latency +concern. + + +Signed-off-by: Paul Gortmaker +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/list_bl.h | 28 ++++++++++++++++++++++++++-- + 1 file changed, 26 insertions(+), 2 deletions(-) + +--- a/include/linux/list_bl.h ++++ b/include/linux/list_bl.h +@@ -2,6 +2,7 @@ + #define _LINUX_LIST_BL_H + + #include ++#include + #include + + /* +@@ -32,13 +33,22 @@ + + struct hlist_bl_head { + struct hlist_bl_node *first; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ raw_spinlock_t lock; ++#endif + }; + + struct hlist_bl_node { + struct hlist_bl_node *next, **pprev; + }; +-#define INIT_HLIST_BL_HEAD(ptr) \ +- ((ptr)->first = NULL) ++ ++static inline void INIT_HLIST_BL_HEAD(struct hlist_bl_head *h) ++{ ++ h->first = NULL; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ raw_spin_lock_init(&h->lock); ++#endif ++} + + static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) + { +@@ -117,12 +127,26 @@ static inline void hlist_bl_del_init(str + + static inline void hlist_bl_lock(struct hlist_bl_head *b) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_lock(0, (unsigned long *)b); ++#else ++ raw_spin_lock(&b->lock); ++#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) ++ __set_bit(0, (unsigned long *)b); ++#endif ++#endif + } + + static inline void hlist_bl_unlock(struct hlist_bl_head *b) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + __bit_spin_unlock(0, (unsigned long *)b); ++#else ++#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) ++ __clear_bit(0, (unsigned long *)b); ++#endif ++ raw_spin_unlock(&b->lock); ++#endif + } + + static inline bool hlist_bl_is_locked(struct hlist_bl_head *b) diff --git a/debian/patches/features/all/rt/local-irq-rt-depending-variants.patch b/debian/patches/features/all/rt/local-irq-rt-depending-variants.patch new file mode 100644 index 000000000..c8bfb4d65 --- /dev/null +++ b/debian/patches/features/all/rt/local-irq-rt-depending-variants.patch @@ -0,0 +1,53 @@ +From: Thomas Gleixner +Date: Tue, 21 Jul 2009 22:34:14 +0200 +Subject: rt: local_irq_* variants depending on RT/!RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Add local_irq_*_(no)rt variant which are mainly used to break +interrupt disabled sections on PREEMPT_RT or to explicitely disable +interrupts on PREEMPT_RT. + +Signed-off-by: Thomas Gleixner + +--- + include/linux/interrupt.h | 2 +- + include/linux/irqflags.h | 19 +++++++++++++++++++ + 2 files changed, 20 insertions(+), 1 deletion(-) + +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -184,7 +184,7 @@ extern void devm_free_irq(struct device + #ifdef CONFIG_LOCKDEP + # define local_irq_enable_in_hardirq() do { } while (0) + #else +-# define local_irq_enable_in_hardirq() local_irq_enable() ++# define local_irq_enable_in_hardirq() local_irq_enable_nort() + #endif + + extern void disable_irq_nosync(unsigned int irq); +--- a/include/linux/irqflags.h ++++ b/include/linux/irqflags.h +@@ -148,4 +148,23 @@ + + #define irqs_disabled_flags(flags) raw_irqs_disabled_flags(flags) + ++/* ++ * local_irq* variants depending on RT/!RT ++ */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define local_irq_disable_nort() do { } while (0) ++# define local_irq_enable_nort() do { } while (0) ++# define local_irq_save_nort(flags) local_save_flags(flags) ++# define local_irq_restore_nort(flags) (void)(flags) ++# define local_irq_disable_rt() local_irq_disable() ++# define local_irq_enable_rt() local_irq_enable() ++#else ++# define local_irq_disable_nort() local_irq_disable() ++# define local_irq_enable_nort() local_irq_enable() ++# define local_irq_save_nort(flags) local_irq_save(flags) ++# define local_irq_restore_nort(flags) local_irq_restore(flags) ++# define local_irq_disable_rt() do { } while (0) ++# define local_irq_enable_rt() do { } while (0) ++#endif ++ + #endif diff --git a/debian/patches/features/all/rt/localversion.patch b/debian/patches/features/all/rt/localversion.patch new file mode 100644 index 000000000..18553d148 --- /dev/null +++ b/debian/patches/features/all/rt/localversion.patch @@ -0,0 +1,16 @@ +Subject: localversion: Add RT specific localversion file +From: Thomas Gleixner +Date: Fri, 08 Jul 2011 20:25:16 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Signed-off-by: Thomas Gleixner +Signed-off-by: Peter Zijlstra +Link: http://lkml.kernel.org/n/tip-8vdw4bfcsds27cvox6rpb334@git.kernel.org +--- + localversion-rt | 1 + + 1 file changed, 1 insertion(+) + +--- /dev/null ++++ b/localversion-rt +@@ -0,0 +1 @@ ++-rt3 diff --git a/debian/patches/features/all/rt/lockdep-no-softirq-accounting-on-rt.patch b/debian/patches/features/all/rt/lockdep-no-softirq-accounting-on-rt.patch new file mode 100644 index 000000000..f247a89f3 --- /dev/null +++ b/debian/patches/features/all/rt/lockdep-no-softirq-accounting-on-rt.patch @@ -0,0 +1,59 @@ +Subject: lockdep: Make it RT aware +From: Thomas Gleixner +Date: Sun, 17 Jul 2011 18:51:23 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +teach lockdep that we don't really do softirqs on -RT. + +Signed-off-by: Thomas Gleixner +--- + include/linux/irqflags.h | 10 +++++++--- + kernel/locking/lockdep.c | 2 ++ + 2 files changed, 9 insertions(+), 3 deletions(-) + +--- a/include/linux/irqflags.h ++++ b/include/linux/irqflags.h +@@ -25,8 +25,6 @@ + # define trace_softirqs_enabled(p) ((p)->softirqs_enabled) + # define trace_hardirq_enter() do { current->hardirq_context++; } while (0) + # define trace_hardirq_exit() do { current->hardirq_context--; } while (0) +-# define lockdep_softirq_enter() do { current->softirq_context++; } while (0) +-# define lockdep_softirq_exit() do { current->softirq_context--; } while (0) + # define INIT_TRACE_IRQFLAGS .softirqs_enabled = 1, + #else + # define trace_hardirqs_on() do { } while (0) +@@ -39,9 +37,15 @@ + # define trace_softirqs_enabled(p) 0 + # define trace_hardirq_enter() do { } while (0) + # define trace_hardirq_exit() do { } while (0) ++# define INIT_TRACE_IRQFLAGS ++#endif ++ ++#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT_FULL) ++# define lockdep_softirq_enter() do { current->softirq_context++; } while (0) ++# define lockdep_softirq_exit() do { current->softirq_context--; } while (0) ++#else + # define lockdep_softirq_enter() do { } while (0) + # define lockdep_softirq_exit() do { } while (0) +-# define INIT_TRACE_IRQFLAGS + #endif + + #if defined(CONFIG_IRQSOFF_TRACER) || \ +--- a/kernel/locking/lockdep.c ++++ b/kernel/locking/lockdep.c +@@ -3563,6 +3563,7 @@ static void check_flags(unsigned long fl + } + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * We dont accurately track softirq state in e.g. + * hardirq contexts (such as on 4KSTACKS), so only +@@ -3577,6 +3578,7 @@ static void check_flags(unsigned long fl + DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled); + } + } ++#endif + + if (!debug_locks) + print_irqtrace_events(current); diff --git a/debian/patches/features/all/rt/lockdep-selftest-fix-warnings-due-to-missing-PREEMPT.patch b/debian/patches/features/all/rt/lockdep-selftest-fix-warnings-due-to-missing-PREEMPT.patch new file mode 100644 index 000000000..3a87fc183 --- /dev/null +++ b/debian/patches/features/all/rt/lockdep-selftest-fix-warnings-due-to-missing-PREEMPT.patch @@ -0,0 +1,142 @@ +From: Josh Cartwright +Date: Wed, 28 Jan 2015 13:08:45 -0600 +Subject: lockdep: selftest: fix warnings due to missing PREEMPT_RT conditionals +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +"lockdep: Selftest: Only do hardirq context test for raw spinlock" +disabled the execution of certain tests with PREEMPT_RT_FULL, but did +not prevent the tests from still being defined. This leads to warnings +like: + + ./linux/lib/locking-selftest.c:574:1: warning: 'irqsafe1_hard_rlock_12' defined but not used [-Wunused-function] + ./linux/lib/locking-selftest.c:574:1: warning: 'irqsafe1_hard_rlock_21' defined but not used [-Wunused-function] + ./linux/lib/locking-selftest.c:577:1: warning: 'irqsafe1_hard_wlock_12' defined but not used [-Wunused-function] + ./linux/lib/locking-selftest.c:577:1: warning: 'irqsafe1_hard_wlock_21' defined but not used [-Wunused-function] + ./linux/lib/locking-selftest.c:580:1: warning: 'irqsafe1_soft_spin_12' defined but not used [-Wunused-function] + ... + +Fixed by wrapping the test definitions in #ifndef CONFIG_PREEMPT_RT_FULL +conditionals. + + +Signed-off-by: Josh Cartwright +Signed-off-by: Xander Huff +Acked-by: Gratian Crisan +Signed-off-by: Sebastian Andrzej Siewior +--- + lib/locking-selftest.c | 27 +++++++++++++++++++++++++++ + 1 file changed, 27 insertions(+) + +--- a/lib/locking-selftest.c ++++ b/lib/locking-selftest.c +@@ -590,6 +590,8 @@ GENERATE_TESTCASE(init_held_rsem) + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_rlock) + +@@ -605,9 +607,12 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_ + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Enabling hardirqs with a softirq-safe lock held: + */ +@@ -640,6 +645,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A + #undef E1 + #undef E2 + ++#endif ++ + /* + * Enabling irqs with an irq-safe lock held: + */ +@@ -663,6 +670,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_rlock) + +@@ -678,6 +687,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + +@@ -709,6 +720,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_rlock) + +@@ -724,6 +737,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_ + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + #undef E3 +@@ -757,6 +772,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_ + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_rlock) + +@@ -772,10 +789,14 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_ + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + #undef E3 + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + /* + * read-lock / write-lock irq inversion. + * +@@ -838,6 +859,10 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_inver + #undef E2 + #undef E3 + ++#endif ++ ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + /* + * read-lock / write-lock recursion that is actually safe. + */ +@@ -876,6 +901,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_ + #undef E2 + #undef E3 + ++#endif ++ + /* + * read-lock / write-lock recursion that is unsafe. + */ diff --git a/debian/patches/features/all/rt/lockdep-selftest-only-do-hardirq-context-test-for-raw-spinlock.patch b/debian/patches/features/all/rt/lockdep-selftest-only-do-hardirq-context-test-for-raw-spinlock.patch new file mode 100644 index 000000000..55aaec382 --- /dev/null +++ b/debian/patches/features/all/rt/lockdep-selftest-only-do-hardirq-context-test-for-raw-spinlock.patch @@ -0,0 +1,57 @@ +Subject: lockdep: selftest: Only do hardirq context test for raw spinlock +From: Yong Zhang +Date: Mon, 16 Apr 2012 15:01:56 +0800 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +From: Yong Zhang + +On -rt there is no softirq context any more and rwlock is sleepable, +disable softirq context test and rwlock+irq test. + +Signed-off-by: Yong Zhang +Cc: Yong Zhang +Link: http://lkml.kernel.org/r/1334559716-18447-3-git-send-email-yong.zhang0@gmail.com +Signed-off-by: Thomas Gleixner +--- + lib/locking-selftest.c | 23 +++++++++++++++++++++++ + 1 file changed, 23 insertions(+) + +--- a/lib/locking-selftest.c ++++ b/lib/locking-selftest.c +@@ -1858,6 +1858,7 @@ void locking_selftest(void) + + printk(" --------------------------------------------------------------------------\n"); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * irq-context testcases: + */ +@@ -1870,6 +1871,28 @@ void locking_selftest(void) + + DO_TESTCASE_6x2("irq read-recursion", irq_read_recursion); + // DO_TESTCASE_6x2B("irq read-recursion #2", irq_read_recursion2); ++#else ++ /* On -rt, we only do hardirq context test for raw spinlock */ ++ DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 12); ++ DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 21); ++ ++ DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 12); ++ DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 21); ++ ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 123); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 132); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 213); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 231); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 312); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 321); ++ ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 123); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 132); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 213); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 231); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 312); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 321); ++#endif + + ww_tests(); + diff --git a/debian/patches/features/all/rt/locking-locktorture-Do-NOT-include-rwlock.h-directly.patch b/debian/patches/features/all/rt/locking-locktorture-Do-NOT-include-rwlock.h-directly.patch new file mode 100644 index 000000000..f11ea481e --- /dev/null +++ b/debian/patches/features/all/rt/locking-locktorture-Do-NOT-include-rwlock.h-directly.patch @@ -0,0 +1,27 @@ +From: "Wolfgang M. Reimer" +Date: Tue, 21 Jul 2015 16:20:07 +0200 +Subject: locking: locktorture: Do NOT include rwlock.h directly +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Including rwlock.h directly will cause kernel builds to fail +if CONFIG_PREEMPT_RT_FULL is defined. The correct header file +(rwlock_rt.h OR rwlock.h) will be included by spinlock.h which +is included by locktorture.c anyway. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Wolfgang M. Reimer +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/locking/locktorture.c | 1 - + 1 file changed, 1 deletion(-) + +--- a/kernel/locking/locktorture.c ++++ b/kernel/locking/locktorture.c +@@ -24,7 +24,6 @@ + #include + #include + #include +-#include + #include + #include + #include diff --git a/debian/patches/features/all/rt/md-disable-bcache.patch b/debian/patches/features/all/rt/md-disable-bcache.patch new file mode 100644 index 000000000..1027aa894 --- /dev/null +++ b/debian/patches/features/all/rt/md-disable-bcache.patch @@ -0,0 +1,32 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 29 Aug 2013 11:48:57 +0200 +Subject: md: disable bcache +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +It uses anon semaphores +|drivers/md/bcache/request.c: In function ‘cached_dev_write_complete’: +|drivers/md/bcache/request.c:1007:2: error: implicit declaration of function ‘up_read_non_owner’ [-Werror=implicit-function-declaration] +| up_read_non_owner(&dc->writeback_lock); +| ^ +|drivers/md/bcache/request.c: In function ‘request_write’: +|drivers/md/bcache/request.c:1033:2: error: implicit declaration of function ‘down_read_non_owner’ [-Werror=implicit-function-declaration] +| down_read_non_owner(&dc->writeback_lock); +| ^ + +either we get rid of those or we have to introduce them… + +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/md/bcache/Kconfig | 1 + + 1 file changed, 1 insertion(+) + +--- a/drivers/md/bcache/Kconfig ++++ b/drivers/md/bcache/Kconfig +@@ -1,6 +1,7 @@ + + config BCACHE + tristate "Block device as cache" ++ depends on !PREEMPT_RT_FULL + ---help--- + Allows a block device to be used as cache for other devices; uses + a btree for indexing and the layout is optimized for SSDs. diff --git a/debian/patches/features/all/rt/md-raid5-percpu-handling-rt-aware.patch b/debian/patches/features/all/rt/md-raid5-percpu-handling-rt-aware.patch new file mode 100644 index 000000000..7b54209d6 --- /dev/null +++ b/debian/patches/features/all/rt/md-raid5-percpu-handling-rt-aware.patch @@ -0,0 +1,62 @@ +From: Thomas Gleixner +Date: Tue, 6 Apr 2010 16:51:31 +0200 +Subject: md: raid5: Make raid5_percpu handling RT aware +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +__raid_run_ops() disables preemption with get_cpu() around the access +to the raid5_percpu variables. That causes scheduling while atomic +spews on RT. + +Serialize the access to the percpu data with a lock and keep the code +preemptible. + +Reported-by: Udo van den Heuvel +Signed-off-by: Thomas Gleixner +Tested-by: Udo van den Heuvel + +--- + drivers/md/raid5.c | 7 +++++-- + drivers/md/raid5.h | 1 + + 2 files changed, 6 insertions(+), 2 deletions(-) + +--- a/drivers/md/raid5.c ++++ b/drivers/md/raid5.c +@@ -1918,8 +1918,9 @@ static void raid_run_ops(struct stripe_h + struct raid5_percpu *percpu; + unsigned long cpu; + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + percpu = per_cpu_ptr(conf->percpu, cpu); ++ spin_lock(&percpu->lock); + if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) { + ops_run_biofill(sh); + overlap_clear++; +@@ -1975,7 +1976,8 @@ static void raid_run_ops(struct stripe_h + if (test_and_clear_bit(R5_Overlap, &dev->flags)) + wake_up(&sh->raid_conf->wait_for_overlap); + } +- put_cpu(); ++ spin_unlock(&percpu->lock); ++ put_cpu_light(); + } + + static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp) +@@ -6350,6 +6352,7 @@ static int raid5_alloc_percpu(struct r5c + __func__, cpu); + break; + } ++ spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock); + } + put_online_cpus(); + +--- a/drivers/md/raid5.h ++++ b/drivers/md/raid5.h +@@ -494,6 +494,7 @@ struct r5conf { + int recovery_disabled; + /* per cpu variables */ + struct raid5_percpu { ++ spinlock_t lock; /* Protection for -RT */ + struct page *spare_page; /* Used when checking P/Q in raid6 */ + struct flex_array *scribble; /* space for constructing buffer + * lists and performing address diff --git a/debian/patches/features/all/rt/mips-disable-highmem-on-rt.patch b/debian/patches/features/all/rt/mips-disable-highmem-on-rt.patch new file mode 100644 index 000000000..c4798d0c2 --- /dev/null +++ b/debian/patches/features/all/rt/mips-disable-highmem-on-rt.patch @@ -0,0 +1,23 @@ +Subject: mips: Disable highmem on RT +From: Thomas Gleixner +Date: Mon, 18 Jul 2011 17:10:12 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The current highmem handling on -RT is not compatible and needs fixups. + +Signed-off-by: Thomas Gleixner +--- + arch/mips/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/arch/mips/Kconfig ++++ b/arch/mips/Kconfig +@@ -2365,7 +2365,7 @@ config CPU_R4400_WORKAROUNDS + # + config HIGHMEM + bool "High Memory Support" +- depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA ++ depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA && !PREEMPT_RT_FULL + + config CPU_SUPPORTS_HIGHMEM + bool diff --git a/debian/patches/features/all/rt/mm-bounce-local-irq-save-nort.patch b/debian/patches/features/all/rt/mm-bounce-local-irq-save-nort.patch new file mode 100644 index 000000000..41282ed1f --- /dev/null +++ b/debian/patches/features/all/rt/mm-bounce-local-irq-save-nort.patch @@ -0,0 +1,28 @@ +Subject: mm: bounce: Use local_irq_save_nort +From: Thomas Gleixner +Date: Wed, 09 Jan 2013 10:33:09 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +kmap_atomic() is preemptible on RT. + +Signed-off-by: Thomas Gleixner +--- + block/bounce.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/block/bounce.c ++++ b/block/bounce.c +@@ -54,11 +54,11 @@ static void bounce_copy_vec(struct bio_v + unsigned long flags; + unsigned char *vto; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + vto = kmap_atomic(to->bv_page); + memcpy(vto + to->bv_offset, vfrom, to->bv_len); + kunmap_atomic(vto); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + + #else /* CONFIG_HIGHMEM */ diff --git a/debian/patches/features/all/rt/mm-convert-swap-to-percpu-locked.patch b/debian/patches/features/all/rt/mm-convert-swap-to-percpu-locked.patch new file mode 100644 index 000000000..8f3e23e8a --- /dev/null +++ b/debian/patches/features/all/rt/mm-convert-swap-to-percpu-locked.patch @@ -0,0 +1,135 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:29:51 -0500 +Subject: mm/swap: Convert to percpu locked +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Replace global locks (get_cpu + local_irq_save) with "local_locks()". +Currently there is one of for "rotate" and one for "swap". + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + mm/swap.c | 34 ++++++++++++++++++++-------------- + 1 file changed, 20 insertions(+), 14 deletions(-) + +--- a/mm/swap.c ++++ b/mm/swap.c +@@ -32,6 +32,7 @@ + #include + #include + #include ++#include + + #include "internal.h" + +@@ -45,6 +46,9 @@ static DEFINE_PER_CPU(struct pagevec, lr + static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs); + static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs); + ++static DEFINE_LOCAL_IRQ_LOCK(rotate_lock); ++static DEFINE_LOCAL_IRQ_LOCK(swapvec_lock); ++ + /* + * This path almost never happens for VM activity - pages are normally + * freed via pagevecs. But it gets used by networking. +@@ -481,11 +485,11 @@ void rotate_reclaimable_page(struct page + unsigned long flags; + + page_cache_get(page); +- local_irq_save(flags); ++ local_lock_irqsave(rotate_lock, flags); + pvec = this_cpu_ptr(&lru_rotate_pvecs); + if (!pagevec_add(pvec, page)) + pagevec_move_tail(pvec); +- local_irq_restore(flags); ++ local_unlock_irqrestore(rotate_lock, flags); + } + } + +@@ -536,12 +540,13 @@ static bool need_activate_page_drain(int + void activate_page(struct page *page) + { + if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { +- struct pagevec *pvec = &get_cpu_var(activate_page_pvecs); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, ++ activate_page_pvecs); + + page_cache_get(page); + if (!pagevec_add(pvec, page)) + pagevec_lru_move_fn(pvec, __activate_page, NULL); +- put_cpu_var(activate_page_pvecs); ++ put_locked_var(swapvec_lock, activate_page_pvecs); + } + } + +@@ -567,7 +572,7 @@ void activate_page(struct page *page) + + static void __lru_cache_activate_page(struct page *page) + { +- struct pagevec *pvec = &get_cpu_var(lru_add_pvec); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec); + int i; + + /* +@@ -589,7 +594,7 @@ static void __lru_cache_activate_page(st + } + } + +- put_cpu_var(lru_add_pvec); ++ put_locked_var(swapvec_lock, lru_add_pvec); + } + + /* +@@ -628,13 +633,13 @@ EXPORT_SYMBOL(mark_page_accessed); + + static void __lru_cache_add(struct page *page) + { +- struct pagevec *pvec = &get_cpu_var(lru_add_pvec); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec); + + page_cache_get(page); + if (!pagevec_space(pvec)) + __pagevec_lru_add(pvec); + pagevec_add(pvec, page); +- put_cpu_var(lru_add_pvec); ++ put_locked_var(swapvec_lock, lru_add_pvec); + } + + /** +@@ -814,9 +819,9 @@ void lru_add_drain_cpu(int cpu) + unsigned long flags; + + /* No harm done if a racing interrupt already did this */ +- local_irq_save(flags); ++ local_lock_irqsave(rotate_lock, flags); + pagevec_move_tail(pvec); +- local_irq_restore(flags); ++ local_unlock_irqrestore(rotate_lock, flags); + } + + pvec = &per_cpu(lru_deactivate_file_pvecs, cpu); +@@ -844,18 +849,19 @@ void deactivate_file_page(struct page *p + return; + + if (likely(get_page_unless_zero(page))) { +- struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, ++ lru_deactivate_file_pvecs); + + if (!pagevec_add(pvec, page)) + pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); +- put_cpu_var(lru_deactivate_file_pvecs); ++ put_locked_var(swapvec_lock, lru_deactivate_file_pvecs); + } + } + + void lru_add_drain(void) + { +- lru_add_drain_cpu(get_cpu()); +- put_cpu(); ++ lru_add_drain_cpu(local_lock_cpu(swapvec_lock)); ++ local_unlock_cpu(swapvec_lock); + } + + static void lru_add_drain_per_cpu(struct work_struct *dummy) diff --git a/debian/patches/features/all/rt/mm-disable-sloub-rt.patch b/debian/patches/features/all/rt/mm-disable-sloub-rt.patch new file mode 100644 index 000000000..6f34fe1a9 --- /dev/null +++ b/debian/patches/features/all/rt/mm-disable-sloub-rt.patch @@ -0,0 +1,32 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:44:03 -0500 +Subject: mm: Allow only slub on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Disable SLAB and SLOB on -RT. Only SLUB is adopted to -RT needs. + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + init/Kconfig | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/init/Kconfig ++++ b/init/Kconfig +@@ -1688,6 +1688,7 @@ choice + + config SLAB + bool "SLAB" ++ depends on !PREEMPT_RT_FULL + help + The regular slab allocator that is established and known to work + well in all environments. It organizes cache hot objects in +@@ -1706,6 +1707,7 @@ config SLUB + config SLOB + depends on EXPERT + bool "SLOB (Simple Allocator)" ++ depends on !PREEMPT_RT_FULL + help + SLOB replaces the stock allocator with a drastically simpler + allocator. SLOB is generally more space efficient but diff --git a/debian/patches/features/all/rt/mm-enable-slub.patch b/debian/patches/features/all/rt/mm-enable-slub.patch new file mode 100644 index 000000000..84f27ece8 --- /dev/null +++ b/debian/patches/features/all/rt/mm-enable-slub.patch @@ -0,0 +1,395 @@ +Subject: mm: Enable SLUB for RT +From: Thomas Gleixner +Date: Thu, 25 Oct 2012 10:32:35 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Make SLUB RT aware by converting locks to raw and using free lists to +move the freeing out of the lock held region. + +Signed-off-by: Thomas Gleixner +--- + mm/slab.h | 4 ++ + mm/slub.c | 118 +++++++++++++++++++++++++++++++++++++++++++++++--------------- + 2 files changed, 95 insertions(+), 27 deletions(-) + +--- a/mm/slab.h ++++ b/mm/slab.h +@@ -330,7 +330,11 @@ static inline struct kmem_cache *cache_f + * The slab lists for all objects. + */ + struct kmem_cache_node { ++#ifdef CONFIG_SLUB ++ raw_spinlock_t list_lock; ++#else + spinlock_t list_lock; ++#endif + + #ifdef CONFIG_SLAB + struct list_head slabs_partial; /* partial list first, better asm code */ +--- a/mm/slub.c ++++ b/mm/slub.c +@@ -1069,7 +1069,7 @@ static noinline struct kmem_cache_node * + { + struct kmem_cache_node *n = get_node(s, page_to_nid(page)); + +- spin_lock_irqsave(&n->list_lock, *flags); ++ raw_spin_lock_irqsave(&n->list_lock, *flags); + slab_lock(page); + + if (!check_slab(s, page)) +@@ -1116,7 +1116,7 @@ static noinline struct kmem_cache_node * + + fail: + slab_unlock(page); +- spin_unlock_irqrestore(&n->list_lock, *flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, *flags); + slab_fix(s, "Object at 0x%p not freed", object); + return NULL; + } +@@ -1242,6 +1242,12 @@ static inline void dec_slabs_node(struct + + #endif /* CONFIG_SLUB_DEBUG */ + ++struct slub_free_list { ++ raw_spinlock_t lock; ++ struct list_head list; ++}; ++static DEFINE_PER_CPU(struct slub_free_list, slub_free_list); ++ + /* + * Hooks for other subsystems that check memory allocations. In a typical + * production configuration these hooks all should produce no code at all. +@@ -1352,7 +1358,11 @@ static struct page *allocate_slab(struct + + flags &= gfp_allowed_mask; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (system_state == SYSTEM_RUNNING) ++#else + if (flags & __GFP_WAIT) ++#endif + local_irq_enable(); + + flags |= s->allocflags; +@@ -1421,7 +1431,11 @@ static struct page *allocate_slab(struct + page->frozen = 1; + + out: ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (system_state == SYSTEM_RUNNING) ++#else + if (flags & __GFP_WAIT) ++#endif + local_irq_disable(); + if (!page) + return NULL; +@@ -1478,6 +1492,16 @@ static void __free_slab(struct kmem_cach + memcg_uncharge_slab(s, order); + } + ++static void free_delayed(struct list_head *h) ++{ ++ while(!list_empty(h)) { ++ struct page *page = list_first_entry(h, struct page, lru); ++ ++ list_del(&page->lru); ++ __free_slab(page->slab_cache, page); ++ } ++} ++ + #define need_reserve_slab_rcu \ + (sizeof(((struct page *)NULL)->lru) < sizeof(struct rcu_head)) + +@@ -1512,6 +1536,12 @@ static void free_slab(struct kmem_cache + } + + call_rcu(head, rcu_free_slab); ++ } else if (irqs_disabled()) { ++ struct slub_free_list *f = this_cpu_ptr(&slub_free_list); ++ ++ raw_spin_lock(&f->lock); ++ list_add(&page->lru, &f->list); ++ raw_spin_unlock(&f->lock); + } else + __free_slab(s, page); + } +@@ -1625,7 +1655,7 @@ static void *get_partial_node(struct kme + if (!n || !n->nr_partial) + return NULL; + +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + list_for_each_entry_safe(page, page2, &n->partial, lru) { + void *t; + +@@ -1650,7 +1680,7 @@ static void *get_partial_node(struct kme + break; + + } +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + return object; + } + +@@ -1896,7 +1926,7 @@ static void deactivate_slab(struct kmem_ + * that acquire_slab() will see a slab page that + * is frozen + */ +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + } + } else { + m = M_FULL; +@@ -1907,7 +1937,7 @@ static void deactivate_slab(struct kmem_ + * slabs from diagnostic functions will not see + * any frozen slabs. + */ +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + } + } + +@@ -1942,7 +1972,7 @@ static void deactivate_slab(struct kmem_ + goto redo; + + if (lock) +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + + if (m == M_FREE) { + stat(s, DEACTIVATE_EMPTY); +@@ -1974,10 +2004,10 @@ static void unfreeze_partials(struct kme + n2 = get_node(s, page_to_nid(page)); + if (n != n2) { + if (n) +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + + n = n2; +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + } + + do { +@@ -2006,7 +2036,7 @@ static void unfreeze_partials(struct kme + } + + if (n) +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + + while (discard_page) { + page = discard_page; +@@ -2045,14 +2075,21 @@ static void put_cpu_partial(struct kmem_ + pobjects = oldpage->pobjects; + pages = oldpage->pages; + if (drain && pobjects > s->cpu_partial) { ++ struct slub_free_list *f; + unsigned long flags; ++ LIST_HEAD(tofree); + /* + * partial array is full. Move the existing + * set to the per node partial list. + */ + local_irq_save(flags); + unfreeze_partials(s, this_cpu_ptr(s->cpu_slab)); ++ f = this_cpu_ptr(&slub_free_list); ++ raw_spin_lock(&f->lock); ++ list_splice_init(&f->list, &tofree); ++ raw_spin_unlock(&f->lock); + local_irq_restore(flags); ++ free_delayed(&tofree); + oldpage = NULL; + pobjects = 0; + pages = 0; +@@ -2124,7 +2161,22 @@ static bool has_cpu_slab(int cpu, void * + + static void flush_all(struct kmem_cache *s) + { ++ LIST_HEAD(tofree); ++ int cpu; ++ + on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1, GFP_ATOMIC); ++ for_each_online_cpu(cpu) { ++ struct slub_free_list *f; ++ ++ if (!has_cpu_slab(cpu, s)) ++ continue; ++ ++ f = &per_cpu(slub_free_list, cpu); ++ raw_spin_lock_irq(&f->lock); ++ list_splice_init(&f->list, &tofree); ++ raw_spin_unlock_irq(&f->lock); ++ free_delayed(&tofree); ++ } + } + + /* +@@ -2160,10 +2212,10 @@ static unsigned long count_partial(struc + unsigned long x = 0; + struct page *page; + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + list_for_each_entry(page, &n->partial, lru) + x += get_count(page); +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + return x; + } + #endif /* CONFIG_SLUB_DEBUG || CONFIG_SYSFS */ +@@ -2300,9 +2352,11 @@ static inline void *get_freelist(struct + static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, + unsigned long addr, struct kmem_cache_cpu *c) + { ++ struct slub_free_list *f; + void *freelist; + struct page *page; + unsigned long flags; ++ LIST_HEAD(tofree); + + local_irq_save(flags); + #ifdef CONFIG_PREEMPT +@@ -2370,7 +2424,13 @@ static void *__slab_alloc(struct kmem_ca + VM_BUG_ON(!c->page->frozen); + c->freelist = get_freepointer(s, freelist); + c->tid = next_tid(c->tid); ++out: ++ f = this_cpu_ptr(&slub_free_list); ++ raw_spin_lock(&f->lock); ++ list_splice_init(&f->list, &tofree); ++ raw_spin_unlock(&f->lock); + local_irq_restore(flags); ++ free_delayed(&tofree); + return freelist; + + new_slab: +@@ -2387,8 +2447,7 @@ static void *__slab_alloc(struct kmem_ca + + if (unlikely(!freelist)) { + slab_out_of_memory(s, gfpflags, node); +- local_irq_restore(flags); +- return NULL; ++ goto out; + } + + page = c->page; +@@ -2403,8 +2462,7 @@ static void *__slab_alloc(struct kmem_ca + deactivate_slab(s, page, get_freepointer(s, freelist)); + c->page = NULL; + c->freelist = NULL; +- local_irq_restore(flags); +- return freelist; ++ goto out; + } + + /* +@@ -2588,7 +2646,7 @@ static void __slab_free(struct kmem_cach + + do { + if (unlikely(n)) { +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + n = NULL; + } + prior = page->freelist; +@@ -2620,7 +2678,7 @@ static void __slab_free(struct kmem_cach + * Otherwise the list_lock will synchronize with + * other processors updating the list of slabs. + */ +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + + } + } +@@ -2662,7 +2720,7 @@ static void __slab_free(struct kmem_cach + add_partial(n, page, DEACTIVATE_TO_TAIL); + stat(s, FREE_ADD_PARTIAL); + } +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + return; + + slab_empty: +@@ -2677,7 +2735,7 @@ static void __slab_free(struct kmem_cach + remove_full(s, n, page); + } + +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + stat(s, FREE_SLAB); + discard_slab(s, page); + } +@@ -2876,7 +2934,7 @@ static void + init_kmem_cache_node(struct kmem_cache_node *n) + { + n->nr_partial = 0; +- spin_lock_init(&n->list_lock); ++ raw_spin_lock_init(&n->list_lock); + INIT_LIST_HEAD(&n->partial); + #ifdef CONFIG_SLUB_DEBUG + atomic_long_set(&n->nr_slabs, 0); +@@ -3458,7 +3516,7 @@ int __kmem_cache_shrink(struct kmem_cach + for (i = 0; i < SHRINK_PROMOTE_MAX; i++) + INIT_LIST_HEAD(promote + i); + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + + /* + * Build lists of slabs to discard or promote. +@@ -3489,7 +3547,7 @@ int __kmem_cache_shrink(struct kmem_cach + for (i = SHRINK_PROMOTE_MAX - 1; i >= 0; i--) + list_splice(promote + i, &n->partial); + +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + + /* Release empty slabs */ + list_for_each_entry_safe(page, t, &discard, lru) +@@ -3665,6 +3723,12 @@ void __init kmem_cache_init(void) + { + static __initdata struct kmem_cache boot_kmem_cache, + boot_kmem_cache_node; ++ int cpu; ++ ++ for_each_possible_cpu(cpu) { ++ raw_spin_lock_init(&per_cpu(slub_free_list, cpu).lock); ++ INIT_LIST_HEAD(&per_cpu(slub_free_list, cpu).list); ++ } + + if (debug_guardpage_minorder()) + slub_max_order = 0; +@@ -3907,7 +3971,7 @@ static int validate_slab_node(struct kme + struct page *page; + unsigned long flags; + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + + list_for_each_entry(page, &n->partial, lru) { + validate_slab_slab(s, page, map); +@@ -3929,7 +3993,7 @@ static int validate_slab_node(struct kme + s->name, count, atomic_long_read(&n->nr_slabs)); + + out: +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + return count; + } + +@@ -4117,12 +4181,12 @@ static int list_locations(struct kmem_ca + if (!atomic_long_read(&n->nr_slabs)) + continue; + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + list_for_each_entry(page, &n->partial, lru) + process_slab(&t, s, page, alloc, map); + list_for_each_entry(page, &n->full, lru) + process_slab(&t, s, page, alloc, map); +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + } + + for (i = 0; i < t.count; i++) { diff --git a/debian/patches/features/all/rt/mm-make-vmstat-rt-aware.patch b/debian/patches/features/all/rt/mm-make-vmstat-rt-aware.patch new file mode 100644 index 000000000..fdd4f592e --- /dev/null +++ b/debian/patches/features/all/rt/mm-make-vmstat-rt-aware.patch @@ -0,0 +1,89 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:30:13 -0500 +Subject: mm/vmstat: Protect per cpu variables with preempt disable on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Disable preemption on -RT for the vmstat code. On vanila the code runs in +IRQ-off regions while on -RT it is not. "preempt_disable" ensures that the +same ressources is not updated in parallel due to preemption. + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + include/linux/vmstat.h | 4 ++++ + mm/vmstat.c | 6 ++++++ + 2 files changed, 10 insertions(+) + +--- a/include/linux/vmstat.h ++++ b/include/linux/vmstat.h +@@ -33,7 +33,9 @@ DECLARE_PER_CPU(struct vm_event_state, v + */ + static inline void __count_vm_event(enum vm_event_item item) + { ++ preempt_disable_rt(); + raw_cpu_inc(vm_event_states.event[item]); ++ preempt_enable_rt(); + } + + static inline void count_vm_event(enum vm_event_item item) +@@ -43,7 +45,9 @@ static inline void count_vm_event(enum v + + static inline void __count_vm_events(enum vm_event_item item, long delta) + { ++ preempt_disable_rt(); + raw_cpu_add(vm_event_states.event[item], delta); ++ preempt_enable_rt(); + } + + static inline void count_vm_events(enum vm_event_item item, long delta) +--- a/mm/vmstat.c ++++ b/mm/vmstat.c +@@ -226,6 +226,7 @@ void __mod_zone_page_state(struct zone * + long x; + long t; + ++ preempt_disable_rt(); + x = delta + __this_cpu_read(*p); + + t = __this_cpu_read(pcp->stat_threshold); +@@ -235,6 +236,7 @@ void __mod_zone_page_state(struct zone * + x = 0; + } + __this_cpu_write(*p, x); ++ preempt_enable_rt(); + } + EXPORT_SYMBOL(__mod_zone_page_state); + +@@ -267,6 +269,7 @@ void __inc_zone_state(struct zone *zone, + s8 __percpu *p = pcp->vm_stat_diff + item; + s8 v, t; + ++ preempt_disable_rt(); + v = __this_cpu_inc_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v > t)) { +@@ -275,6 +278,7 @@ void __inc_zone_state(struct zone *zone, + zone_page_state_add(v + overstep, zone, item); + __this_cpu_write(*p, -overstep); + } ++ preempt_enable_rt(); + } + + void __inc_zone_page_state(struct page *page, enum zone_stat_item item) +@@ -289,6 +293,7 @@ void __dec_zone_state(struct zone *zone, + s8 __percpu *p = pcp->vm_stat_diff + item; + s8 v, t; + ++ preempt_disable_rt(); + v = __this_cpu_dec_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v < - t)) { +@@ -297,6 +302,7 @@ void __dec_zone_state(struct zone *zone, + zone_page_state_add(v - overstep, zone, item); + __this_cpu_write(*p, overstep); + } ++ preempt_enable_rt(); + } + + void __dec_zone_page_state(struct page *page, enum zone_stat_item item) diff --git a/debian/patches/features/all/rt/mm-memcontrol-Don-t-call-schedule_work_on-in-preempt.patch b/debian/patches/features/all/rt/mm-memcontrol-Don-t-call-schedule_work_on-in-preempt.patch new file mode 100644 index 000000000..7757f7176 --- /dev/null +++ b/debian/patches/features/all/rt/mm-memcontrol-Don-t-call-schedule_work_on-in-preempt.patch @@ -0,0 +1,69 @@ +From: Yang Shi +Subject: mm/memcontrol: Don't call schedule_work_on in preemption disabled context +Date: Wed, 30 Oct 2013 11:48:33 -0700 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The following trace is triggered when running ltp oom test cases: + +BUG: sleeping function called from invalid context at kernel/rtmutex.c:659 +in_atomic(): 1, irqs_disabled(): 0, pid: 17188, name: oom03 +Preemption disabled at:[] mem_cgroup_reclaim+0x90/0xe0 + +CPU: 2 PID: 17188 Comm: oom03 Not tainted 3.10.10-rt3 #2 +Hardware name: Intel Corporation Calpella platform/MATXM-CORE-411-B, BIOS 4.6.3 08/18/2010 +ffff88007684d730 ffff880070df9b58 ffffffff8169918d ffff880070df9b70 +ffffffff8106db31 ffff88007688b4a0 ffff880070df9b88 ffffffff8169d9c0 +ffff88007688b4a0 ffff880070df9bc8 ffffffff81059da1 0000000170df9bb0 +Call Trace: +[] dump_stack+0x19/0x1b +[] __might_sleep+0xf1/0x170 +[] rt_spin_lock+0x20/0x50 +[] queue_work_on+0x61/0x100 +[] drain_all_stock+0xe1/0x1c0 +[] mem_cgroup_reclaim+0x90/0xe0 +[] __mem_cgroup_try_charge+0x41a/0xc40 +[] ? release_pages+0x1b1/0x1f0 +[] ? sched_exec+0x40/0xb0 +[] mem_cgroup_charge_common+0x37/0x70 +[] mem_cgroup_newpage_charge+0x26/0x30 +[] handle_pte_fault+0x618/0x840 +[] ? unpin_current_cpu+0x16/0x70 +[] ? migrate_enable+0xd4/0x200 +[] handle_mm_fault+0x145/0x1e0 +[] __do_page_fault+0x1a1/0x4c0 +[] ? preempt_schedule_irq+0x4b/0x70 +[] ? retint_kernel+0x37/0x40 +[] do_page_fault+0xe/0x10 +[] page_fault+0x22/0x30 + +So, to prevent schedule_work_on from being called in preempt disabled context, +replace the pair of get/put_cpu() to get/put_cpu_light(). + + +Signed-off-by: Yang Shi +Signed-off-by: Sebastian Andrzej Siewior +--- + + mm/memcontrol.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/mm/memcontrol.c ++++ b/mm/memcontrol.c +@@ -2147,7 +2147,7 @@ static void drain_all_stock(struct mem_c + return; + /* Notify other cpus that system-wide "drain" is running */ + get_online_cpus(); +- curcpu = get_cpu(); ++ curcpu = get_cpu_light(); + for_each_online_cpu(cpu) { + struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); + struct mem_cgroup *memcg; +@@ -2164,7 +2164,7 @@ static void drain_all_stock(struct mem_c + schedule_work_on(cpu, &stock->work); + } + } +- put_cpu(); ++ put_cpu_light(); + put_online_cpus(); + mutex_unlock(&percpu_charge_mutex); + } diff --git a/debian/patches/features/all/rt/mm-memcontrol-do_not_disable_irq.patch b/debian/patches/features/all/rt/mm-memcontrol-do_not_disable_irq.patch new file mode 100644 index 000000000..3db8a67e6 --- /dev/null +++ b/debian/patches/features/all/rt/mm-memcontrol-do_not_disable_irq.patch @@ -0,0 +1,138 @@ +From: Sebastian Andrzej Siewior +Subject: mm/memcontrol: Replace local_irq_disable with local locks +Date: Wed, 28 Jan 2015 17:14:16 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +There are a few local_irq_disable() which then take sleeping locks. This +patch converts them local locks. + +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/swap.h | 1 + + mm/compaction.c | 6 ++++-- + mm/memcontrol.c | 18 ++++++++++++------ + mm/swap.c | 2 +- + 4 files changed, 18 insertions(+), 9 deletions(-) + +--- a/include/linux/swap.h ++++ b/include/linux/swap.h +@@ -298,6 +298,7 @@ extern unsigned long nr_free_pagecache_p + + + /* linux/mm/swap.c */ ++DECLARE_LOCAL_IRQ_LOCK(swapvec_lock); + extern void lru_cache_add(struct page *); + extern void lru_cache_add_anon(struct page *page); + extern void lru_cache_add_file(struct page *page); +--- a/mm/compaction.c ++++ b/mm/compaction.c +@@ -1406,10 +1406,12 @@ static int compact_zone(struct zone *zon + cc->migrate_pfn & ~((1UL << cc->order) - 1); + + if (last_migrated_pfn < current_block_start) { +- cpu = get_cpu(); ++ cpu = get_cpu_light(); ++ local_lock_irq(swapvec_lock); + lru_add_drain_cpu(cpu); ++ local_unlock_irq(swapvec_lock); + drain_local_pages(zone); +- put_cpu(); ++ put_cpu_light(); + /* No more flushing until we migrate again */ + last_migrated_pfn = 0; + } +--- a/mm/memcontrol.c ++++ b/mm/memcontrol.c +@@ -66,6 +66,8 @@ + #include + #include + #include ++#include ++ + #include "slab.h" + + #include +@@ -85,6 +87,7 @@ int do_swap_account __read_mostly; + #define do_swap_account 0 + #endif + ++static DEFINE_LOCAL_IRQ_LOCK(event_lock); + static const char * const mem_cgroup_stat_names[] = { + "cache", + "rss", +@@ -4801,12 +4804,12 @@ static int mem_cgroup_move_account(struc + + ret = 0; + +- local_irq_disable(); ++ local_lock_irq(event_lock); + mem_cgroup_charge_statistics(to, page, nr_pages); + memcg_check_events(to, page); + mem_cgroup_charge_statistics(from, page, -nr_pages); + memcg_check_events(from, page); +- local_irq_enable(); ++ local_unlock_irq(event_lock); + out_unlock: + unlock_page(page); + out: +@@ -5543,10 +5546,10 @@ void mem_cgroup_commit_charge(struct pag + VM_BUG_ON_PAGE(!PageTransHuge(page), page); + } + +- local_irq_disable(); ++ local_lock_irq(event_lock); + mem_cgroup_charge_statistics(memcg, page, nr_pages); + memcg_check_events(memcg, page); +- local_irq_enable(); ++ local_unlock_irq(event_lock); + + if (do_swap_account && PageSwapCache(page)) { + swp_entry_t entry = { .val = page_private(page) }; +@@ -5602,14 +5605,14 @@ static void uncharge_batch(struct mem_cg + memcg_oom_recover(memcg); + } + +- local_irq_save(flags); ++ local_lock_irqsave(event_lock, flags); + __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS], nr_anon); + __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_CACHE], nr_file); + __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE], nr_huge); + __this_cpu_add(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGOUT], pgpgout); + __this_cpu_add(memcg->stat->nr_page_events, nr_pages); + memcg_check_events(memcg, dummy_page); +- local_irq_restore(flags); ++ local_unlock_irqrestore(event_lock, flags); + + if (!mem_cgroup_is_root(memcg)) + css_put_many(&memcg->css, nr_pages); +@@ -5813,6 +5816,7 @@ void mem_cgroup_swapout(struct page *pag + { + struct mem_cgroup *memcg; + unsigned short oldid; ++ unsigned long flags; + + VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_PAGE(page_count(page), page); +@@ -5835,9 +5839,11 @@ void mem_cgroup_swapout(struct page *pag + if (!mem_cgroup_is_root(memcg)) + page_counter_uncharge(&memcg->memory, 1); + ++ local_lock_irqsave(event_lock, flags); + /* Caller disabled preemption with mapping->tree_lock */ + mem_cgroup_charge_statistics(memcg, page, -1); + memcg_check_events(memcg, page); ++ local_unlock_irqrestore(event_lock, flags); + } + + /** +--- a/mm/swap.c ++++ b/mm/swap.c +@@ -47,7 +47,7 @@ static DEFINE_PER_CPU(struct pagevec, lr + static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs); + + static DEFINE_LOCAL_IRQ_LOCK(rotate_lock); +-static DEFINE_LOCAL_IRQ_LOCK(swapvec_lock); ++DEFINE_LOCAL_IRQ_LOCK(swapvec_lock); + + /* + * This path almost never happens for VM activity - pages are normally diff --git a/debian/patches/features/all/rt/mm-page-alloc-use-local-lock-on-target-cpu.patch b/debian/patches/features/all/rt/mm-page-alloc-use-local-lock-on-target-cpu.patch new file mode 100644 index 000000000..d0c8ecaef --- /dev/null +++ b/debian/patches/features/all/rt/mm-page-alloc-use-local-lock-on-target-cpu.patch @@ -0,0 +1,28 @@ +Subject: mm: page_alloc: Use local_lock_on() instead of plain spinlock +From: Thomas Gleixner +Date: Thu, 27 Sep 2012 11:11:46 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The plain spinlock while sufficient does not update the local_lock +internals. Use a proper local_lock function instead to ease debugging. + +Signed-off-by: Thomas Gleixner + +--- + mm/page_alloc.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/mm/page_alloc.c ++++ b/mm/page_alloc.c +@@ -238,9 +238,9 @@ static DEFINE_LOCAL_IRQ_LOCK(pa_lock); + + #ifdef CONFIG_PREEMPT_RT_BASE + # define cpu_lock_irqsave(cpu, flags) \ +- spin_lock_irqsave(&per_cpu(pa_lock, cpu).lock, flags) ++ local_lock_irqsave_on(pa_lock, flags, cpu) + # define cpu_unlock_irqrestore(cpu, flags) \ +- spin_unlock_irqrestore(&per_cpu(pa_lock, cpu).lock, flags) ++ local_unlock_irqrestore_on(pa_lock, flags, cpu) + #else + # define cpu_lock_irqsave(cpu, flags) local_irq_save(flags) + # define cpu_unlock_irqrestore(cpu, flags) local_irq_restore(flags) diff --git a/debian/patches/features/all/rt/mm-page_alloc-reduce-lock-sections-further.patch b/debian/patches/features/all/rt/mm-page_alloc-reduce-lock-sections-further.patch new file mode 100644 index 000000000..7b80e0f6d --- /dev/null +++ b/debian/patches/features/all/rt/mm-page_alloc-reduce-lock-sections-further.patch @@ -0,0 +1,193 @@ +From: Peter Zijlstra +Date: Fri Jul 3 08:44:37 2009 -0500 +Subject: mm: page_alloc: Reduce lock sections further +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Split out the pages which are to be freed into a separate list and +call free_pages_bulk() outside of the percpu page allocator locks. + +Signed-off-by: Peter Zijlstra +Signed-off-by: Thomas Gleixner +--- + mm/page_alloc.c | 85 ++++++++++++++++++++++++++++++++++++++++---------------- + 1 file changed, 61 insertions(+), 24 deletions(-) + +--- a/mm/page_alloc.c ++++ b/mm/page_alloc.c +@@ -694,7 +694,7 @@ static inline int free_pages_check(struc + } + + /* +- * Frees a number of pages from the PCP lists ++ * Frees a number of pages which have been collected from the pcp lists. + * Assumes all pages on list are in same zone, and of same order. + * count is the number of pages to free. + * +@@ -705,18 +705,51 @@ static inline int free_pages_check(struc + * pinned" detection logic. + */ + static void free_pcppages_bulk(struct zone *zone, int count, +- struct per_cpu_pages *pcp) ++ struct list_head *list) + { +- int migratetype = 0; +- int batch_free = 0; + int to_free = count; + unsigned long nr_scanned; ++ unsigned long flags; ++ ++ spin_lock_irqsave(&zone->lock, flags); + +- spin_lock(&zone->lock); + nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); + if (nr_scanned) + __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); + ++ while (!list_empty(list)) { ++ struct page *page = list_first_entry(list, struct page, lru); ++ int mt; /* migratetype of the to-be-freed page */ ++ ++ /* must delete as __free_one_page list manipulates */ ++ list_del(&page->lru); ++ ++ mt = get_freepage_migratetype(page); ++ if (unlikely(has_isolate_pageblock(zone))) ++ mt = get_pageblock_migratetype(page); ++ ++ /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ ++ __free_one_page(page, page_to_pfn(page), zone, 0, mt); ++ trace_mm_page_pcpu_drain(page, 0, mt); ++ to_free--; ++ } ++ WARN_ON(to_free != 0); ++ spin_unlock_irqrestore(&zone->lock, flags); ++} ++ ++/* ++ * Moves a number of pages from the PCP lists to free list which ++ * is freed outside of the locked region. ++ * ++ * Assumes all pages on list are in same zone, and of same order. ++ * count is the number of pages to free. ++ */ ++static void isolate_pcp_pages(int to_free, struct per_cpu_pages *src, ++ struct list_head *dst) ++{ ++ int migratetype = 0; ++ int batch_free = 0; ++ + while (to_free) { + struct page *page; + struct list_head *list; +@@ -732,7 +765,7 @@ static void free_pcppages_bulk(struct zo + batch_free++; + if (++migratetype == MIGRATE_PCPTYPES) + migratetype = 0; +- list = &pcp->lists[migratetype]; ++ list = &src->lists[migratetype]; + } while (list_empty(list)); + + /* This is the only non-empty list. Free them all. */ +@@ -740,21 +773,11 @@ static void free_pcppages_bulk(struct zo + batch_free = to_free; + + do { +- int mt; /* migratetype of the to-be-freed page */ +- +- page = list_entry(list->prev, struct page, lru); +- /* must delete as __free_one_page list manipulates */ ++ page = list_last_entry(list, struct page, lru); + list_del(&page->lru); +- mt = get_freepage_migratetype(page); +- if (unlikely(has_isolate_pageblock(zone))) +- mt = get_pageblock_migratetype(page); +- +- /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ +- __free_one_page(page, page_to_pfn(page), zone, 0, mt); +- trace_mm_page_pcpu_drain(page, 0, mt); ++ list_add(&page->lru, dst); + } while (--to_free && --batch_free && !list_empty(list)); + } +- spin_unlock(&zone->lock); + } + + static void free_one_page(struct zone *zone, +@@ -763,7 +786,9 @@ static void free_one_page(struct zone *z + int migratetype) + { + unsigned long nr_scanned; +- spin_lock(&zone->lock); ++ unsigned long flags; ++ ++ spin_lock_irqsave(&zone->lock, flags); + nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); + if (nr_scanned) + __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); +@@ -773,7 +798,7 @@ static void free_one_page(struct zone *z + migratetype = get_pfnblock_migratetype(page, pfn); + } + __free_one_page(page, pfn, zone, order, migratetype); +- spin_unlock(&zone->lock); ++ spin_unlock_irqrestore(&zone->lock, flags); + } + + static int free_tail_pages_check(struct page *head_page, struct page *page) +@@ -1381,16 +1406,18 @@ static int rmqueue_bulk(struct zone *zon + void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) + { + unsigned long flags; ++ LIST_HEAD(dst); + int to_drain, batch; + + local_lock_irqsave(pa_lock, flags); + batch = READ_ONCE(pcp->batch); + to_drain = min(pcp->count, batch); + if (to_drain > 0) { +- free_pcppages_bulk(zone, to_drain, pcp); ++ isolate_pcp_pages(to_drain, pcp, &dst); + pcp->count -= to_drain; + } + local_unlock_irqrestore(pa_lock, flags); ++ free_pcppages_bulk(zone, to_drain, &dst); + } + #endif + +@@ -1406,16 +1433,21 @@ static void drain_pages_zone(unsigned in + unsigned long flags; + struct per_cpu_pageset *pset; + struct per_cpu_pages *pcp; ++ LIST_HEAD(dst); ++ int count; + + cpu_lock_irqsave(cpu, flags); + pset = per_cpu_ptr(zone->pageset, cpu); + + pcp = &pset->pcp; +- if (pcp->count) { +- free_pcppages_bulk(zone, pcp->count, pcp); ++ count = pcp->count; ++ if (count) { ++ isolate_pcp_pages(count, pcp, &dst); + pcp->count = 0; + } + cpu_unlock_irqrestore(cpu, flags); ++ if (count) ++ free_pcppages_bulk(zone, count, &dst); + } + + /* +@@ -1593,8 +1625,13 @@ void free_hot_cold_page(struct page *pag + pcp->count++; + if (pcp->count >= pcp->high) { + unsigned long batch = READ_ONCE(pcp->batch); +- free_pcppages_bulk(zone, batch, pcp); ++ LIST_HEAD(dst); ++ ++ isolate_pcp_pages(batch, pcp, &dst); + pcp->count -= batch; ++ local_unlock_irqrestore(pa_lock, flags); ++ free_pcppages_bulk(zone, batch, &dst); ++ return; + } + + out: diff --git a/debian/patches/features/all/rt/mm-page_alloc-rt-friendly-per-cpu-pages.patch b/debian/patches/features/all/rt/mm-page_alloc-rt-friendly-per-cpu-pages.patch new file mode 100644 index 000000000..e81fededb --- /dev/null +++ b/debian/patches/features/all/rt/mm-page_alloc-rt-friendly-per-cpu-pages.patch @@ -0,0 +1,202 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:29:37 -0500 +Subject: mm: page_alloc: rt-friendly per-cpu pages +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +rt-friendly per-cpu pages: convert the irqs-off per-cpu locking +method into a preemptible, explicit-per-cpu-locks method. + +Contains fixes from: + Peter Zijlstra + Thomas Gleixner + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner +--- + mm/page_alloc.c | 57 ++++++++++++++++++++++++++++++++++++++++---------------- + 1 file changed, 41 insertions(+), 16 deletions(-) + +--- a/mm/page_alloc.c ++++ b/mm/page_alloc.c +@@ -60,6 +60,7 @@ + #include + #include + #include ++#include + #include + + #include +@@ -233,6 +234,18 @@ EXPORT_SYMBOL(nr_node_ids); + EXPORT_SYMBOL(nr_online_nodes); + #endif + ++static DEFINE_LOCAL_IRQ_LOCK(pa_lock); ++ ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define cpu_lock_irqsave(cpu, flags) \ ++ spin_lock_irqsave(&per_cpu(pa_lock, cpu).lock, flags) ++# define cpu_unlock_irqrestore(cpu, flags) \ ++ spin_unlock_irqrestore(&per_cpu(pa_lock, cpu).lock, flags) ++#else ++# define cpu_lock_irqsave(cpu, flags) local_irq_save(flags) ++# define cpu_unlock_irqrestore(cpu, flags) local_irq_restore(flags) ++#endif ++ + int page_group_by_mobility_disabled __read_mostly; + + void set_pageblock_migratetype(struct page *page, int migratetype) +@@ -825,11 +838,11 @@ static void __free_pages_ok(struct page + return; + + migratetype = get_pfnblock_migratetype(page, pfn); +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + __count_vm_events(PGFREE, 1 << order); + set_freepage_migratetype(page, migratetype); + free_one_page(page_zone(page), page, pfn, order, migratetype); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + } + + void __init __free_pages_bootmem(struct page *page, unsigned int order) +@@ -1370,14 +1383,14 @@ void drain_zone_pages(struct zone *zone, + unsigned long flags; + int to_drain, batch; + +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + batch = READ_ONCE(pcp->batch); + to_drain = min(pcp->count, batch); + if (to_drain > 0) { + free_pcppages_bulk(zone, to_drain, pcp); + pcp->count -= to_drain; + } +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + } + #endif + +@@ -1394,7 +1407,7 @@ static void drain_pages_zone(unsigned in + struct per_cpu_pageset *pset; + struct per_cpu_pages *pcp; + +- local_irq_save(flags); ++ cpu_lock_irqsave(cpu, flags); + pset = per_cpu_ptr(zone->pageset, cpu); + + pcp = &pset->pcp; +@@ -1402,7 +1415,7 @@ static void drain_pages_zone(unsigned in + free_pcppages_bulk(zone, pcp->count, pcp); + pcp->count = 0; + } +- local_irq_restore(flags); ++ cpu_unlock_irqrestore(cpu, flags); + } + + /* +@@ -1488,8 +1501,17 @@ void drain_all_pages(struct zone *zone) + else + cpumask_clear_cpu(cpu, &cpus_with_pcps); + } ++#ifndef CONFIG_PREEMPT_RT_BASE + on_each_cpu_mask(&cpus_with_pcps, (smp_call_func_t) drain_local_pages, + zone, 1); ++#else ++ for_each_cpu(cpu, &cpus_with_pcps) { ++ if (zone) ++ drain_pages_zone(cpu, zone); ++ else ++ drain_pages(cpu); ++ } ++#endif + } + + #ifdef CONFIG_HIBERNATION +@@ -1545,7 +1567,7 @@ void free_hot_cold_page(struct page *pag + + migratetype = get_pfnblock_migratetype(page, pfn); + set_freepage_migratetype(page, migratetype); +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + __count_vm_event(PGFREE); + + /* +@@ -1576,7 +1598,7 @@ void free_hot_cold_page(struct page *pag + } + + out: +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + } + + /* +@@ -1707,7 +1729,7 @@ struct page *buffered_rmqueue(struct zon + struct per_cpu_pages *pcp; + struct list_head *list; + +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + pcp = &this_cpu_ptr(zone->pageset)->pcp; + list = &pcp->lists[migratetype]; + if (list_empty(list)) { +@@ -1739,13 +1761,15 @@ struct page *buffered_rmqueue(struct zon + */ + WARN_ON_ONCE(order > 1); + } +- spin_lock_irqsave(&zone->lock, flags); ++ local_spin_lock_irqsave(pa_lock, &zone->lock, flags); + page = __rmqueue(zone, order, migratetype); +- spin_unlock(&zone->lock); +- if (!page) ++ if (!page) { ++ spin_unlock(&zone->lock); + goto failed; ++ } + __mod_zone_freepage_state(zone, -(1 << order), + get_freepage_migratetype(page)); ++ spin_unlock(&zone->lock); + } + + __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); +@@ -1755,13 +1779,13 @@ struct page *buffered_rmqueue(struct zon + + __count_zone_vm_events(PGALLOC, zone, 1 << order); + zone_statistics(preferred_zone, zone, gfp_flags); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + + VM_BUG_ON_PAGE(bad_range(zone, page), page); + return page; + + failed: +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + return NULL; + } + +@@ -5650,6 +5674,7 @@ static int page_alloc_cpu_notify(struct + void __init page_alloc_init(void) + { + hotcpu_notifier(page_alloc_cpu_notify, 0); ++ local_irq_lock_init(pa_lock); + } + + /* +@@ -6544,7 +6569,7 @@ void zone_pcp_reset(struct zone *zone) + struct per_cpu_pageset *pset; + + /* avoid races with drain_pages() */ +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + if (zone->pageset != &boot_pageset) { + for_each_online_cpu(cpu) { + pset = per_cpu_ptr(zone->pageset, cpu); +@@ -6553,7 +6578,7 @@ void zone_pcp_reset(struct zone *zone) + free_percpu(zone->pageset); + zone->pageset = &boot_pageset; + } +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + } + + #ifdef CONFIG_MEMORY_HOTREMOVE diff --git a/debian/patches/features/all/rt/mm-protect-activate-switch-mm.patch b/debian/patches/features/all/rt/mm-protect-activate-switch-mm.patch new file mode 100644 index 000000000..5d91c0f61 --- /dev/null +++ b/debian/patches/features/all/rt/mm-protect-activate-switch-mm.patch @@ -0,0 +1,72 @@ +From: Yong Zhang +Date: Tue, 15 May 2012 13:53:56 +0800 +Subject: mm: Protect activate_mm() by preempt_[disable&enable]_rt() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +User preempt_*_rt instead of local_irq_*_rt or otherwise there will be +warning on ARM like below: + +WARNING: at build/linux/kernel/smp.c:459 smp_call_function_many+0x98/0x264() +Modules linked in: +[] (unwind_backtrace+0x0/0xe4) from [] (warn_slowpath_common+0x4c/0x64) +[] (warn_slowpath_common+0x4c/0x64) from [] (warn_slowpath_null+0x18/0x1c) +[] (warn_slowpath_null+0x18/0x1c) from [](smp_call_function_many+0x98/0x264) +[] (smp_call_function_many+0x98/0x264) from [] (smp_call_function+0x44/0x6c) +[] (smp_call_function+0x44/0x6c) from [] (__new_context+0xbc/0x124) +[] (__new_context+0xbc/0x124) from [] (flush_old_exec+0x460/0x5e4) +[] (flush_old_exec+0x460/0x5e4) from [] (load_elf_binary+0x2e0/0x11ac) +[] (load_elf_binary+0x2e0/0x11ac) from [] (search_binary_handler+0x94/0x2a4) +[] (search_binary_handler+0x94/0x2a4) from [] (do_execve+0x254/0x364) +[] (do_execve+0x254/0x364) from [] (sys_execve+0x34/0x54) +[] (sys_execve+0x34/0x54) from [] (ret_fast_syscall+0x0/0x30) +---[ end trace 0000000000000002 ]--- + +The reason is that ARM need irq enabled when doing activate_mm(). +According to mm-protect-activate-switch-mm.patch, actually +preempt_[disable|enable]_rt() is sufficient. + +Inspired-by: Steven Rostedt +Signed-off-by: Yong Zhang +Cc: Steven Rostedt +Link: http://lkml.kernel.org/r/1337061236-1766-1-git-send-email-yong.zhang0@gmail.com +Signed-off-by: Thomas Gleixner +--- + fs/exec.c | 2 ++ + mm/mmu_context.c | 2 ++ + 2 files changed, 4 insertions(+) + +--- a/fs/exec.c ++++ b/fs/exec.c +@@ -859,12 +859,14 @@ static int exec_mmap(struct mm_struct *m + } + } + task_lock(tsk); ++ preempt_disable_rt(); + active_mm = tsk->active_mm; + tsk->mm = mm; + tsk->active_mm = mm; + activate_mm(active_mm, mm); + tsk->mm->vmacache_seqnum = 0; + vmacache_flush(tsk); ++ preempt_enable_rt(); + task_unlock(tsk); + if (old_mm) { + up_read(&old_mm->mmap_sem); +--- a/mm/mmu_context.c ++++ b/mm/mmu_context.c +@@ -23,6 +23,7 @@ void use_mm(struct mm_struct *mm) + struct task_struct *tsk = current; + + task_lock(tsk); ++ preempt_disable_rt(); + active_mm = tsk->active_mm; + if (active_mm != mm) { + atomic_inc(&mm->mm_count); +@@ -30,6 +31,7 @@ void use_mm(struct mm_struct *mm) + } + tsk->mm = mm; + switch_mm(active_mm, mm, tsk); ++ preempt_enable_rt(); + task_unlock(tsk); + #ifdef finish_arch_post_lock_switch + finish_arch_post_lock_switch(); diff --git a/debian/patches/features/all/rt/mm-rt-kmap-atomic-scheduling.patch b/debian/patches/features/all/rt/mm-rt-kmap-atomic-scheduling.patch new file mode 100644 index 000000000..62557854d --- /dev/null +++ b/debian/patches/features/all/rt/mm-rt-kmap-atomic-scheduling.patch @@ -0,0 +1,289 @@ +Subject: mm, rt: kmap_atomic scheduling +From: Peter Zijlstra +Date: Thu, 28 Jul 2011 10:43:51 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +In fact, with migrate_disable() existing one could play games with +kmap_atomic. You could save/restore the kmap_atomic slots on context +switch (if there are any in use of course), this should be esp easy now +that we have a kmap_atomic stack. + +Something like the below.. it wants replacing all the preempt_disable() +stuff with pagefault_disable() && migrate_disable() of course, but then +you can flip kmaps around like below. + +Signed-off-by: Peter Zijlstra +[dvhart@linux.intel.com: build fix] +Link: http://lkml.kernel.org/r/1311842631.5890.208.camel@twins + +[tglx@linutronix.de: Get rid of the per cpu variable and store the idx + and the pte content right away in the task struct. + Shortens the context switch code. ] +--- + arch/x86/kernel/process_32.c | 32 ++++++++++++++++++++++++++++++++ + arch/x86/mm/highmem_32.c | 13 ++++++++++--- + arch/x86/mm/iomap_32.c | 9 ++++++++- + include/linux/highmem.h | 27 +++++++++++++++++++++++---- + include/linux/sched.h | 7 +++++++ + include/linux/uaccess.h | 2 ++ + mm/highmem.c | 6 ++++-- + 7 files changed, 86 insertions(+), 10 deletions(-) + +--- a/arch/x86/kernel/process_32.c ++++ b/arch/x86/kernel/process_32.c +@@ -35,6 +35,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -210,6 +211,35 @@ start_thread(struct pt_regs *regs, unsig + } + EXPORT_SYMBOL_GPL(start_thread); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) ++{ ++ int i; ++ ++ /* ++ * Clear @prev's kmap_atomic mappings ++ */ ++ for (i = 0; i < prev_p->kmap_idx; i++) { ++ int idx = i + KM_TYPE_NR * smp_processor_id(); ++ pte_t *ptep = kmap_pte - idx; ++ ++ kpte_clear_flush(ptep, __fix_to_virt(FIX_KMAP_BEGIN + idx)); ++ } ++ /* ++ * Restore @next_p's kmap_atomic mappings ++ */ ++ for (i = 0; i < next_p->kmap_idx; i++) { ++ int idx = i + KM_TYPE_NR * smp_processor_id(); ++ ++ if (!pte_none(next_p->kmap_pte[i])) ++ set_pte(kmap_pte - idx, next_p->kmap_pte[i]); ++ } ++} ++#else ++static inline void ++switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { } ++#endif ++ + + /* + * switch_to(x,y) should switch tasks from x to y. +@@ -292,6 +322,8 @@ EXPORT_SYMBOL_GPL(start_thread); + task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT)) + __switch_to_xtra(prev_p, next_p, tss); + ++ switch_kmaps(prev_p, next_p); ++ + /* + * Leave lazy mode, flushing any hypercalls made here. + * This must be done before restoring TLS segments so +--- a/arch/x86/mm/highmem_32.c ++++ b/arch/x86/mm/highmem_32.c +@@ -32,10 +32,11 @@ EXPORT_SYMBOL(kunmap); + */ + void *kmap_atomic_prot(struct page *page, pgprot_t prot) + { ++ pte_t pte = mk_pte(page, prot); + unsigned long vaddr; + int idx, type; + +- preempt_disable(); ++ preempt_disable_nort(); + pagefault_disable(); + + if (!PageHighMem(page)) +@@ -45,7 +46,10 @@ void *kmap_atomic_prot(struct page *page + idx = type + KM_TYPE_NR*smp_processor_id(); + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); + BUG_ON(!pte_none(*(kmap_pte-idx))); +- set_pte(kmap_pte-idx, mk_pte(page, prot)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_pte(kmap_pte-idx, pte); + arch_flush_lazy_mmu_mode(); + + return (void *)vaddr; +@@ -88,6 +92,9 @@ void __kunmap_atomic(void *kvaddr) + * is a bad idea also, in case the page changes cacheability + * attributes or becomes a protected page in a hypervisor. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = __pte(0); ++#endif + kpte_clear_flush(kmap_pte-idx, vaddr); + kmap_atomic_idx_pop(); + arch_flush_lazy_mmu_mode(); +@@ -100,7 +107,7 @@ void __kunmap_atomic(void *kvaddr) + #endif + + pagefault_enable(); +- preempt_enable(); ++ preempt_enable_nort(); + } + EXPORT_SYMBOL(__kunmap_atomic); + +--- a/arch/x86/mm/iomap_32.c ++++ b/arch/x86/mm/iomap_32.c +@@ -56,6 +56,7 @@ EXPORT_SYMBOL_GPL(iomap_free); + + void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) + { ++ pte_t pte = pfn_pte(pfn, prot); + unsigned long vaddr; + int idx, type; + +@@ -65,7 +66,10 @@ void *kmap_atomic_prot_pfn(unsigned long + type = kmap_atomic_idx_push(); + idx = type + KM_TYPE_NR * smp_processor_id(); + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); +- set_pte(kmap_pte - idx, pfn_pte(pfn, prot)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_pte(kmap_pte - idx, pte); + arch_flush_lazy_mmu_mode(); + + return (void *)vaddr; +@@ -113,6 +117,9 @@ iounmap_atomic(void __iomem *kvaddr) + * is a bad idea also, in case the page changes cacheability + * attributes or becomes a protected page in a hypervisor. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = __pte(0); ++#endif + kpte_clear_flush(kmap_pte-idx, vaddr); + kmap_atomic_idx_pop(); + } +--- a/include/linux/highmem.h ++++ b/include/linux/highmem.h +@@ -87,32 +87,51 @@ static inline void __kunmap_atomic(void + + #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32) + ++#ifndef CONFIG_PREEMPT_RT_FULL + DECLARE_PER_CPU(int, __kmap_atomic_idx); ++#endif + + static inline int kmap_atomic_idx_push(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + int idx = __this_cpu_inc_return(__kmap_atomic_idx) - 1; + +-#ifdef CONFIG_DEBUG_HIGHMEM ++# ifdef CONFIG_DEBUG_HIGHMEM + WARN_ON_ONCE(in_irq() && !irqs_disabled()); + BUG_ON(idx >= KM_TYPE_NR); +-#endif ++# endif + return idx; ++#else ++ current->kmap_idx++; ++ BUG_ON(current->kmap_idx > KM_TYPE_NR); ++ return current->kmap_idx - 1; ++#endif + } + + static inline int kmap_atomic_idx(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + return __this_cpu_read(__kmap_atomic_idx) - 1; ++#else ++ return current->kmap_idx - 1; ++#endif + } + + static inline void kmap_atomic_idx_pop(void) + { +-#ifdef CONFIG_DEBUG_HIGHMEM ++#ifndef CONFIG_PREEMPT_RT_FULL ++# ifdef CONFIG_DEBUG_HIGHMEM + int idx = __this_cpu_dec_return(__kmap_atomic_idx); + + BUG_ON(idx < 0); +-#else ++# else + __this_cpu_dec(__kmap_atomic_idx); ++# endif ++#else ++ current->kmap_idx--; ++# ifdef CONFIG_DEBUG_HIGHMEM ++ BUG_ON(current->kmap_idx < 0); ++# endif + #endif + } + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -26,6 +26,7 @@ struct sched_param { + #include + #include + #include ++#include + + #include + #include +@@ -1796,6 +1797,12 @@ struct task_struct { + int softirq_nestcnt; + unsigned int softirqs_raised; + #endif ++#ifdef CONFIG_PREEMPT_RT_FULL ++# if defined CONFIG_HIGHMEM || defined CONFIG_X86_32 ++ int kmap_idx; ++ pte_t kmap_pte[KM_TYPE_NR]; ++# endif ++#endif + #ifdef CONFIG_DEBUG_ATOMIC_SLEEP + unsigned long task_state_change; + #endif +--- a/include/linux/uaccess.h ++++ b/include/linux/uaccess.h +@@ -24,6 +24,7 @@ static __always_inline void pagefault_di + */ + static inline void pagefault_disable(void) + { ++ migrate_disable(); + pagefault_disabled_inc(); + /* + * make sure to have issued the store before a pagefault +@@ -40,6 +41,7 @@ static inline void pagefault_enable(void + */ + barrier(); + pagefault_disabled_dec(); ++ migrate_enable(); + } + + /* +--- a/mm/highmem.c ++++ b/mm/highmem.c +@@ -29,10 +29,11 @@ + #include + #include + +- ++#ifndef CONFIG_PREEMPT_RT_FULL + #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32) + DEFINE_PER_CPU(int, __kmap_atomic_idx); + #endif ++#endif + + /* + * Virtual_count is not a pure "count". +@@ -107,8 +108,9 @@ static inline wait_queue_head_t *get_pkm + unsigned long totalhigh_pages __read_mostly; + EXPORT_SYMBOL(totalhigh_pages); + +- ++#ifndef CONFIG_PREEMPT_RT_FULL + EXPORT_PER_CPU_SYMBOL(__kmap_atomic_idx); ++#endif + + unsigned int nr_free_highpages (void) + { diff --git a/debian/patches/features/all/rt/mm-scatterlist-dont-disable-irqs-on-RT.patch b/debian/patches/features/all/rt/mm-scatterlist-dont-disable-irqs-on-RT.patch new file mode 100644 index 000000000..92a12305a --- /dev/null +++ b/debian/patches/features/all/rt/mm-scatterlist-dont-disable-irqs-on-RT.patch @@ -0,0 +1,44 @@ +From: Thomas Gleixner +Date: Fri, 3 Jul 2009 08:44:34 -0500 +Subject: mm/scatterlist: Do not disable irqs on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The local_irq_save() is not only used to get things done "fast" but +also to ensure that in case of SG_MITER_ATOMIC we are in "atomic" +context for kmap_atomic(). For -RT it is enough to keep pagefault +disabled (which is currently handled by kmap_atomic()). + +Signed-off-by: Thomas Gleixner +--- + lib/scatterlist.c | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +--- a/lib/scatterlist.c ++++ b/lib/scatterlist.c +@@ -592,7 +592,7 @@ void sg_miter_stop(struct sg_mapping_ite + flush_kernel_dcache_page(miter->page); + + if (miter->__flags & SG_MITER_ATOMIC) { +- WARN_ON_ONCE(preemptible()); ++ WARN_ON_ONCE(!pagefault_disabled()); + kunmap_atomic(miter->addr); + } else + kunmap(miter->page); +@@ -637,7 +637,7 @@ static size_t sg_copy_buffer(struct scat + if (!sg_miter_skip(&miter, skip)) + return false; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + + while (sg_miter_next(&miter) && offset < buflen) { + unsigned int len; +@@ -654,7 +654,7 @@ static size_t sg_copy_buffer(struct scat + + sg_miter_stop(&miter); + +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + return offset; + } + diff --git a/debian/patches/features/all/rt/mm-slub-move-slab-initialization-into-irq-enabled-region.patch b/debian/patches/features/all/rt/mm-slub-move-slab-initialization-into-irq-enabled-region.patch new file mode 100644 index 000000000..bf349fe69 --- /dev/null +++ b/debian/patches/features/all/rt/mm-slub-move-slab-initialization-into-irq-enabled-region.patch @@ -0,0 +1,163 @@ +From: Thomas Gleixner +Date: Tue, 14 Jul 2015 14:26:34 +0200 +Subject: mm/slub: move slab initialization into irq enabled region +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Initializing a new slab can introduce rather large latencies because most +of the initialization runs always with interrupts disabled. + +There is no point in doing so. The newly allocated slab is not visible +yet, so there is no reason to protect it against concurrent alloc/free. + +Move the expensive parts of the initialization into allocate_slab(), so +for all allocations with GFP_WAIT set, interrupts are enabled. + +Signed-off-by: Thomas Gleixner +Acked-by: Christoph Lameter +Cc: Pekka Enberg +Cc: David Rientjes +Cc: Joonsoo Kim +Cc: Sebastian Andrzej Siewior +Cc: Steven Rostedt +Cc: Peter Zijlstra +Signed-off-by: Andrew Morton +--- + + mm/slub.c | 89 +++++++++++++++++++++++++++++--------------------------------- + 1 file changed, 42 insertions(+), 47 deletions(-) + +--- a/mm/slub.c ++++ b/mm/slub.c +@@ -1306,6 +1306,17 @@ static inline void slab_free_hook(struct + kasan_slab_free(s, x); + } + ++static void setup_object(struct kmem_cache *s, struct page *page, ++ void *object) ++{ ++ setup_object_debug(s, page, object); ++ if (unlikely(s->ctor)) { ++ kasan_unpoison_object_data(s, object); ++ s->ctor(object); ++ kasan_poison_object_data(s, object); ++ } ++} ++ + /* + * Slab allocation and freeing + */ +@@ -1336,6 +1347,8 @@ static struct page *allocate_slab(struct + struct page *page; + struct kmem_cache_order_objects oo = s->oo; + gfp_t alloc_gfp; ++ void *start, *p; ++ int idx, order; + + flags &= gfp_allowed_mask; + +@@ -1359,13 +1372,13 @@ static struct page *allocate_slab(struct + * Try a lower order alloc if possible + */ + page = alloc_slab_page(s, alloc_gfp, node, oo); +- +- if (page) +- stat(s, ORDER_FALLBACK); ++ if (unlikely(!page)) ++ goto out; ++ stat(s, ORDER_FALLBACK); + } + +- if (kmemcheck_enabled && page +- && !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) { ++ if (kmemcheck_enabled && ++ !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) { + int pages = 1 << oo_order(oo); + + kmemcheck_alloc_shadow(page, oo_order(oo), alloc_gfp, node); +@@ -1380,51 +1393,9 @@ static struct page *allocate_slab(struct + kmemcheck_mark_unallocated_pages(page, pages); + } + +- if (flags & __GFP_WAIT) +- local_irq_disable(); +- if (!page) +- return NULL; +- + page->objects = oo_objects(oo); +- mod_zone_page_state(page_zone(page), +- (s->flags & SLAB_RECLAIM_ACCOUNT) ? +- NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE, +- 1 << oo_order(oo)); +- +- return page; +-} +- +-static void setup_object(struct kmem_cache *s, struct page *page, +- void *object) +-{ +- setup_object_debug(s, page, object); +- if (unlikely(s->ctor)) { +- kasan_unpoison_object_data(s, object); +- s->ctor(object); +- kasan_poison_object_data(s, object); +- } +-} +- +-static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) +-{ +- struct page *page; +- void *start; +- void *p; +- int order; +- int idx; +- +- if (unlikely(flags & GFP_SLAB_BUG_MASK)) { +- pr_emerg("gfp: %u\n", flags & GFP_SLAB_BUG_MASK); +- BUG(); +- } +- +- page = allocate_slab(s, +- flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node); +- if (!page) +- goto out; + + order = compound_order(page); +- inc_slabs_node(s, page_to_nid(page), page->objects); + page->slab_cache = s; + __SetPageSlab(page); + if (page->pfmemalloc) +@@ -1448,10 +1419,34 @@ static struct page *new_slab(struct kmem + page->freelist = start; + page->inuse = page->objects; + page->frozen = 1; ++ + out: ++ if (flags & __GFP_WAIT) ++ local_irq_disable(); ++ if (!page) ++ return NULL; ++ ++ mod_zone_page_state(page_zone(page), ++ (s->flags & SLAB_RECLAIM_ACCOUNT) ? ++ NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE, ++ 1 << oo_order(oo)); ++ ++ inc_slabs_node(s, page_to_nid(page), page->objects); ++ + return page; + } + ++static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) ++{ ++ if (unlikely(flags & GFP_SLAB_BUG_MASK)) { ++ pr_emerg("gfp: %u\n", flags & GFP_SLAB_BUG_MASK); ++ BUG(); ++ } ++ ++ return allocate_slab(s, ++ flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node); ++} ++ + static void __free_slab(struct kmem_cache *s, struct page *page) + { + int order = compound_order(page); diff --git a/debian/patches/features/all/rt/mm-vmalloc-use-get-cpu-light.patch b/debian/patches/features/all/rt/mm-vmalloc-use-get-cpu-light.patch new file mode 100644 index 000000000..53a88d430 --- /dev/null +++ b/debian/patches/features/all/rt/mm-vmalloc-use-get-cpu-light.patch @@ -0,0 +1,66 @@ +Subject: mm/vmalloc: Another preempt disable region which sucks +From: Thomas Gleixner +Date: Tue, 12 Jul 2011 11:39:36 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Avoid the preempt disable version of get_cpu_var(). The inner-lock should +provide enough serialisation. + +Signed-off-by: Thomas Gleixner +--- + mm/vmalloc.c | 13 ++++++++----- + 1 file changed, 8 insertions(+), 5 deletions(-) + +--- a/mm/vmalloc.c ++++ b/mm/vmalloc.c +@@ -819,7 +819,7 @@ static void *new_vmap_block(unsigned int + struct vmap_block *vb; + struct vmap_area *va; + unsigned long vb_idx; +- int node, err; ++ int node, err, cpu; + void *vaddr; + + node = numa_node_id(); +@@ -862,11 +862,12 @@ static void *new_vmap_block(unsigned int + BUG_ON(err); + radix_tree_preload_end(); + +- vbq = &get_cpu_var(vmap_block_queue); ++ cpu = get_cpu_light(); ++ vbq = this_cpu_ptr(&vmap_block_queue); + spin_lock(&vbq->lock); + list_add_tail_rcu(&vb->free_list, &vbq->free); + spin_unlock(&vbq->lock); +- put_cpu_var(vmap_block_queue); ++ put_cpu_light(); + + return vaddr; + } +@@ -935,6 +936,7 @@ static void *vb_alloc(unsigned long size + struct vmap_block *vb; + void *vaddr = NULL; + unsigned int order; ++ int cpu; + + BUG_ON(size & ~PAGE_MASK); + BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); +@@ -949,7 +951,8 @@ static void *vb_alloc(unsigned long size + order = get_order(size); + + rcu_read_lock(); +- vbq = &get_cpu_var(vmap_block_queue); ++ cpu = get_cpu_light(); ++ vbq = this_cpu_ptr(&vmap_block_queue); + list_for_each_entry_rcu(vb, &vbq->free, free_list) { + unsigned long pages_off; + +@@ -972,7 +975,7 @@ static void *vb_alloc(unsigned long size + break; + } + +- put_cpu_var(vmap_block_queue); ++ put_cpu_light(); + rcu_read_unlock(); + + /* Allocate new block if nothing was found */ diff --git a/debian/patches/features/all/rt/mm-workingset-do-not-protect-workingset_shadow_nodes.patch b/debian/patches/features/all/rt/mm-workingset-do-not-protect-workingset_shadow_nodes.patch new file mode 100644 index 000000000..aef2a3a12 --- /dev/null +++ b/debian/patches/features/all/rt/mm-workingset-do-not-protect-workingset_shadow_nodes.patch @@ -0,0 +1,151 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 29 Jan 2015 17:19:44 +0100 +Subject: mm/workingset: Do not protect workingset_shadow_nodes with irq off +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +workingset_shadow_nodes is protected by local_irq_disable(). Some users +use spin_lock_irq(). +Replace the irq/on with a local_lock(). Rename workingset_shadow_nodes +so I catch users of it which will be introduced later. + +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/swap.h | 4 +++- + mm/filemap.c | 11 ++++++++--- + mm/truncate.c | 7 +++++-- + mm/workingset.c | 23 ++++++++++++----------- + 4 files changed, 28 insertions(+), 17 deletions(-) + +--- a/include/linux/swap.h ++++ b/include/linux/swap.h +@@ -11,6 +11,7 @@ + #include + #include + #include ++#include + #include + + struct notifier_block; +@@ -252,7 +253,8 @@ struct swap_info_struct { + void *workingset_eviction(struct address_space *mapping, struct page *page); + bool workingset_refault(void *shadow); + void workingset_activation(struct page *page); +-extern struct list_lru workingset_shadow_nodes; ++extern struct list_lru __workingset_shadow_nodes; ++DECLARE_LOCAL_IRQ_LOCK(workingset_shadow_lock); + + static inline unsigned int workingset_node_pages(struct radix_tree_node *node) + { +--- a/mm/filemap.c ++++ b/mm/filemap.c +@@ -167,7 +167,9 @@ static void page_cache_tree_delete(struc + if (!workingset_node_pages(node) && + list_empty(&node->private_list)) { + node->private_data = mapping; +- list_lru_add(&workingset_shadow_nodes, &node->private_list); ++ local_lock(workingset_shadow_lock); ++ list_lru_add(&__workingset_shadow_nodes, &node->private_list); ++ local_unlock(workingset_shadow_lock); + } + } + +@@ -533,9 +535,12 @@ static int page_cache_tree_insert(struct + * node->private_list is protected by + * mapping->tree_lock. + */ +- if (!list_empty(&node->private_list)) +- list_lru_del(&workingset_shadow_nodes, ++ if (!list_empty(&node->private_list)) { ++ local_lock(workingset_shadow_lock); ++ list_lru_del(&__workingset_shadow_nodes, + &node->private_list); ++ local_unlock(workingset_shadow_lock); ++ } + } + return 0; + } +--- a/mm/truncate.c ++++ b/mm/truncate.c +@@ -56,8 +56,11 @@ static void clear_exceptional_entry(stru + * protected by mapping->tree_lock. + */ + if (!workingset_node_shadows(node) && +- !list_empty(&node->private_list)) +- list_lru_del(&workingset_shadow_nodes, &node->private_list); ++ !list_empty(&node->private_list)) { ++ local_lock(workingset_shadow_lock); ++ list_lru_del(&__workingset_shadow_nodes, &node->private_list); ++ local_unlock(workingset_shadow_lock); ++ } + __radix_tree_delete_node(&mapping->page_tree, node); + unlock: + spin_unlock_irq(&mapping->tree_lock); +--- a/mm/workingset.c ++++ b/mm/workingset.c +@@ -264,7 +264,8 @@ void workingset_activation(struct page * + * point where they would still be useful. + */ + +-struct list_lru workingset_shadow_nodes; ++struct list_lru __workingset_shadow_nodes; ++DEFINE_LOCAL_IRQ_LOCK(workingset_shadow_lock); + + static unsigned long count_shadow_nodes(struct shrinker *shrinker, + struct shrink_control *sc) +@@ -274,9 +275,9 @@ static unsigned long count_shadow_nodes( + unsigned long pages; + + /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ +- local_irq_disable(); +- shadow_nodes = list_lru_shrink_count(&workingset_shadow_nodes, sc); +- local_irq_enable(); ++ local_lock_irq(workingset_shadow_lock); ++ shadow_nodes = list_lru_shrink_count(&__workingset_shadow_nodes, sc); ++ local_unlock_irq(workingset_shadow_lock); + + pages = node_present_pages(sc->nid); + /* +@@ -363,9 +364,9 @@ static enum lru_status shadow_lru_isolat + spin_unlock(&mapping->tree_lock); + ret = LRU_REMOVED_RETRY; + out: +- local_irq_enable(); ++ local_unlock_irq(workingset_shadow_lock); + cond_resched(); +- local_irq_disable(); ++ local_lock_irq(workingset_shadow_lock); + spin_lock(lru_lock); + return ret; + } +@@ -376,10 +377,10 @@ static unsigned long scan_shadow_nodes(s + unsigned long ret; + + /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ +- local_irq_disable(); +- ret = list_lru_shrink_walk(&workingset_shadow_nodes, sc, ++ local_lock_irq(workingset_shadow_lock); ++ ret = list_lru_shrink_walk(&__workingset_shadow_nodes, sc, + shadow_lru_isolate, NULL); +- local_irq_enable(); ++ local_unlock_irq(workingset_shadow_lock); + return ret; + } + +@@ -400,7 +401,7 @@ static int __init workingset_init(void) + { + int ret; + +- ret = list_lru_init_key(&workingset_shadow_nodes, &shadow_nodes_key); ++ ret = list_lru_init_key(&__workingset_shadow_nodes, &shadow_nodes_key); + if (ret) + goto err; + ret = register_shrinker(&workingset_shadow_shrinker); +@@ -408,7 +409,7 @@ static int __init workingset_init(void) + goto err_list_lru; + return 0; + err_list_lru: +- list_lru_destroy(&workingset_shadow_nodes); ++ list_lru_destroy(&__workingset_shadow_nodes); + err: + return ret; + } diff --git a/debian/patches/features/all/rt/mmc-sdhci-don-t-provide-hard-irq-handler.patch b/debian/patches/features/all/rt/mmc-sdhci-don-t-provide-hard-irq-handler.patch new file mode 100644 index 000000000..96f36dc78 --- /dev/null +++ b/debian/patches/features/all/rt/mmc-sdhci-don-t-provide-hard-irq-handler.patch @@ -0,0 +1,74 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 26 Feb 2015 12:13:36 +0100 +Subject: mmc: sdhci: don't provide hard irq handler +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +the sdhci code provides both irq handlers: the primary and the thread +handler. Initially it was meant for the primary handler to be very +short. +The result is not that on -RT we have the primrary handler grabing locks +and this isn't really working. As a hack for now I just push both +handler into the threaded mode. + + +Reported-By: Michal Šmucr +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/mmc/host/sdhci.c | 32 +++++++++++++++++++++++++++----- + 1 file changed, 27 insertions(+), 5 deletions(-) + +--- a/drivers/mmc/host/sdhci.c ++++ b/drivers/mmc/host/sdhci.c +@@ -2691,6 +2691,31 @@ static irqreturn_t sdhci_thread_irq(int + return isr ? IRQ_HANDLED : IRQ_NONE; + } + ++#ifdef CONFIG_PREEMPT_RT_BASE ++static irqreturn_t sdhci_rt_irq(int irq, void *dev_id) ++{ ++ irqreturn_t ret; ++ ++ local_bh_disable(); ++ ret = sdhci_irq(irq, dev_id); ++ local_bh_enable(); ++ if (ret == IRQ_WAKE_THREAD) ++ ret = sdhci_thread_irq(irq, dev_id); ++ return ret; ++} ++#endif ++ ++static int sdhci_req_irq(struct sdhci_host *host) ++{ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ return request_threaded_irq(host->irq, NULL, sdhci_rt_irq, ++ IRQF_SHARED, mmc_hostname(host->mmc), host); ++#else ++ return request_threaded_irq(host->irq, sdhci_irq, sdhci_thread_irq, ++ IRQF_SHARED, mmc_hostname(host->mmc), host); ++#endif ++} ++ + /*****************************************************************************\ + * * + * Suspend/resume * +@@ -2758,9 +2783,7 @@ int sdhci_resume_host(struct sdhci_host + } + + if (!device_may_wakeup(mmc_dev(host->mmc))) { +- ret = request_threaded_irq(host->irq, sdhci_irq, +- sdhci_thread_irq, IRQF_SHARED, +- mmc_hostname(host->mmc), host); ++ ret = sdhci_req_irq(host); + if (ret) + return ret; + } else { +@@ -3417,8 +3440,7 @@ int sdhci_add_host(struct sdhci_host *ho + + sdhci_init(host, 0); + +- ret = request_threaded_irq(host->irq, sdhci_irq, sdhci_thread_irq, +- IRQF_SHARED, mmc_hostname(mmc), host); ++ ret = sdhci_req_irq(host); + if (ret) { + pr_err("%s: Failed to request IRQ %d: %d\n", + mmc_hostname(mmc), host->irq, ret); diff --git a/debian/patches/features/all/rt/mmci-remove-bogus-irq-save.patch b/debian/patches/features/all/rt/mmci-remove-bogus-irq-save.patch new file mode 100644 index 000000000..b563c9bb2 --- /dev/null +++ b/debian/patches/features/all/rt/mmci-remove-bogus-irq-save.patch @@ -0,0 +1,40 @@ +Subject: mmci: Remove bogus local_irq_save() +From: Thomas Gleixner +Date: Wed, 09 Jan 2013 12:11:12 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +On !RT interrupt runs with interrupts disabled. On RT it's in a +thread, so no need to disable interrupts at all. + +Signed-off-by: Thomas Gleixner +--- + drivers/mmc/host/mmci.c | 5 ----- + 1 file changed, 5 deletions(-) + +--- a/drivers/mmc/host/mmci.c ++++ b/drivers/mmc/host/mmci.c +@@ -1155,15 +1155,12 @@ static irqreturn_t mmci_pio_irq(int irq, + struct sg_mapping_iter *sg_miter = &host->sg_miter; + struct variant_data *variant = host->variant; + void __iomem *base = host->base; +- unsigned long flags; + u32 status; + + status = readl(base + MMCISTATUS); + + dev_dbg(mmc_dev(host->mmc), "irq1 (pio) %08x\n", status); + +- local_irq_save(flags); +- + do { + unsigned int remain, len; + char *buffer; +@@ -1203,8 +1200,6 @@ static irqreturn_t mmci_pio_irq(int irq, + + sg_miter_stop(sg_miter); + +- local_irq_restore(flags); +- + /* + * If we have less than the fifo 'half-full' threshold to transfer, + * trigger a PIO interrupt as soon as any data is available. diff --git a/debian/patches/features/all/rt/move_sched_delayed_work_to_helper.patch b/debian/patches/features/all/rt/move_sched_delayed_work_to_helper.patch new file mode 100644 index 000000000..8e750efce --- /dev/null +++ b/debian/patches/features/all/rt/move_sched_delayed_work_to_helper.patch @@ -0,0 +1,89 @@ +Date: Wed, 26 Jun 2013 15:28:11 -0400 +From: Steven Rostedt +Subject: rt,ntp: Move call to schedule_delayed_work() to helper thread +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The ntp code for notify_cmos_timer() is called from a hard interrupt +context. schedule_delayed_work() under PREEMPT_RT_FULL calls spinlocks +that have been converted to mutexes, thus calling schedule_delayed_work() +from interrupt is not safe. + +Add a helper thread that does the call to schedule_delayed_work and wake +up that thread instead of calling schedule_delayed_work() directly. +This is only for CONFIG_PREEMPT_RT_FULL, otherwise the code still calls +schedule_delayed_work() directly in irq context. + +Note: There's a few places in the kernel that do this. Perhaps the RT +code should have a dedicated thread that does the checks. Just register +a notifier on boot up for your check and wake up the thread when +needed. This will be a todo. + +Signed-off-by: Steven Rostedt + +--- + kernel/time/ntp.c | 43 +++++++++++++++++++++++++++++++++++++++++++ + 1 file changed, 43 insertions(+) + +--- a/kernel/time/ntp.c ++++ b/kernel/time/ntp.c +@@ -10,6 +10,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -529,10 +530,52 @@ static void sync_cmos_clock(struct work_ + &sync_cmos_work, timespec_to_jiffies(&next)); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * RT can not call schedule_delayed_work from real interrupt context. ++ * Need to make a thread to do the real work. ++ */ ++static struct task_struct *cmos_delay_thread; ++static bool do_cmos_delay; ++ ++static int run_cmos_delay(void *ignore) ++{ ++ while (!kthread_should_stop()) { ++ set_current_state(TASK_INTERRUPTIBLE); ++ if (do_cmos_delay) { ++ do_cmos_delay = false; ++ queue_delayed_work(system_power_efficient_wq, ++ &sync_cmos_work, 0); ++ } ++ schedule(); ++ } ++ __set_current_state(TASK_RUNNING); ++ return 0; ++} ++ ++void ntp_notify_cmos_timer(void) ++{ ++ do_cmos_delay = true; ++ /* Make visible before waking up process */ ++ smp_wmb(); ++ wake_up_process(cmos_delay_thread); ++} ++ ++static __init int create_cmos_delay_thread(void) ++{ ++ cmos_delay_thread = kthread_run(run_cmos_delay, NULL, "kcmosdelayd"); ++ BUG_ON(!cmos_delay_thread); ++ return 0; ++} ++early_initcall(create_cmos_delay_thread); ++ ++#else ++ + void ntp_notify_cmos_timer(void) + { + queue_delayed_work(system_power_efficient_wq, &sync_cmos_work, 0); + } ++#endif /* CONFIG_PREEMPT_RT_FULL */ + + #else + void ntp_notify_cmos_timer(void) { } diff --git a/debian/patches/features/all/rt/mutex-no-spin-on-rt.patch b/debian/patches/features/all/rt/mutex-no-spin-on-rt.patch new file mode 100644 index 000000000..0860700e6 --- /dev/null +++ b/debian/patches/features/all/rt/mutex-no-spin-on-rt.patch @@ -0,0 +1,29 @@ +From: Thomas Gleixner +Date: Sun, 17 Jul 2011 21:51:45 +0200 +Subject: locking: Disable spin on owner for RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Drop spin on owner for mutex / rwsem. We are most likely not using it +but… + +Signed-off-by: Thomas Gleixner +--- + kernel/Kconfig.locks | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/kernel/Kconfig.locks ++++ b/kernel/Kconfig.locks +@@ -225,11 +225,11 @@ config ARCH_SUPPORTS_ATOMIC_RMW + + config MUTEX_SPIN_ON_OWNER + def_bool y +- depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW ++ depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL + + config RWSEM_SPIN_ON_OWNER + def_bool y +- depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW ++ depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL + + config LOCK_SPIN_ON_OWNER + def_bool y diff --git a/debian/patches/features/all/rt/net-another-local-irq-disable-alloc-atomic-headache.patch b/debian/patches/features/all/rt/net-another-local-irq-disable-alloc-atomic-headache.patch new file mode 100644 index 000000000..05432e24c --- /dev/null +++ b/debian/patches/features/all/rt/net-another-local-irq-disable-alloc-atomic-headache.patch @@ -0,0 +1,42 @@ +From: Thomas Gleixner +Date: Wed, 26 Sep 2012 16:21:08 +0200 +Subject: net: Another local_irq_disable/kmalloc headache +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Replace it by a local lock. Though that's pretty inefficient :( + +Signed-off-by: Thomas Gleixner +--- + net/core/skbuff.c | 6 ++++-- + 1 file changed, 4 insertions(+), 2 deletions(-) + +--- a/net/core/skbuff.c ++++ b/net/core/skbuff.c +@@ -63,6 +63,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -356,6 +357,7 @@ struct netdev_alloc_cache { + }; + static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache); + static DEFINE_PER_CPU(struct netdev_alloc_cache, napi_alloc_cache); ++static DEFINE_LOCAL_IRQ_LOCK(netdev_alloc_lock); + + static struct page *__page_frag_refill(struct netdev_alloc_cache *nc, + gfp_t gfp_mask) +@@ -433,9 +435,9 @@ static void *__netdev_alloc_frag(unsigne + unsigned long flags; + void *data; + +- local_irq_save(flags); ++ local_lock_irqsave(netdev_alloc_lock, flags); + data = __alloc_page_frag(&netdev_alloc_cache, fragsz, gfp_mask); +- local_irq_restore(flags); ++ local_unlock_irqrestore(netdev_alloc_lock, flags); + return data; + } + diff --git a/debian/patches/features/all/rt/net-fix-iptable-xt-write-recseq-begin-rt-fallout.patch b/debian/patches/features/all/rt/net-fix-iptable-xt-write-recseq-begin-rt-fallout.patch new file mode 100644 index 000000000..2a1e853e2 --- /dev/null +++ b/debian/patches/features/all/rt/net-fix-iptable-xt-write-recseq-begin-rt-fallout.patch @@ -0,0 +1,74 @@ +Subject: net: netfilter: Serialize xt_write_recseq sections on RT +From: Thomas Gleixner +Date: Sun, 28 Oct 2012 11:18:08 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The netfilter code relies only on the implicit semantics of +local_bh_disable() for serializing wt_write_recseq sections. RT breaks +that and needs explicit serialization here. + +Reported-by: Peter LaDow +Signed-off-by: Thomas Gleixner + +--- + include/linux/netfilter/x_tables.h | 7 +++++++ + net/netfilter/core.c | 6 ++++++ + 2 files changed, 13 insertions(+) + +--- a/include/linux/netfilter/x_tables.h ++++ b/include/linux/netfilter/x_tables.h +@@ -3,6 +3,7 @@ + + + #include ++#include + #include + + /** +@@ -282,6 +283,8 @@ void xt_free_table_info(struct xt_table_ + */ + DECLARE_PER_CPU(seqcount_t, xt_recseq); + ++DECLARE_LOCAL_IRQ_LOCK(xt_write_lock); ++ + /** + * xt_write_recseq_begin - start of a write section + * +@@ -296,6 +299,9 @@ static inline unsigned int xt_write_recs + { + unsigned int addend; + ++ /* RT protection */ ++ local_lock(xt_write_lock); ++ + /* + * Low order bit of sequence is set if we already + * called xt_write_recseq_begin(). +@@ -326,6 +332,7 @@ static inline void xt_write_recseq_end(u + /* this is kind of a write_seqcount_end(), but addend is 0 or 1 */ + smp_wmb(); + __this_cpu_add(xt_recseq.sequence, addend); ++ local_unlock(xt_write_lock); + } + + /* +--- a/net/netfilter/core.c ++++ b/net/netfilter/core.c +@@ -22,11 +22,17 @@ + #include + #include + #include ++#include + #include + #include + + #include "nf_internals.h" + ++#ifdef CONFIG_PREEMPT_RT_BASE ++DEFINE_LOCAL_IRQ_LOCK(xt_write_lock); ++EXPORT_PER_CPU_SYMBOL(xt_write_lock); ++#endif ++ + static DEFINE_MUTEX(afinfo_mutex); + + const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly; diff --git a/debian/patches/features/all/rt/net-gianfar-do-not-disable-interrupts.patch b/debian/patches/features/all/rt/net-gianfar-do-not-disable-interrupts.patch new file mode 100644 index 000000000..74838c952 --- /dev/null +++ b/debian/patches/features/all/rt/net-gianfar-do-not-disable-interrupts.patch @@ -0,0 +1,77 @@ +From: Sebastian Andrzej Siewior +Date: Tue, 25 Mar 2014 18:34:20 +0100 +Subject: net: gianfar: Do not disable interrupts +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +each per-queue lock is taken with spin_lock_irqsave() except in the case +where all of them are taken for some kind of serialisation. As an +optimisation local_irq_save() is used so that lock_tx_qs() and +lock_rx_qs() can use just the spin_lock() variant instead. +On RT local_irq_save() behaves differently so we use the nort() +variant. +Lockdep screems easily by "ethtool -K eth0 rx off tx off" + +What remains is missing lockdep annotation that makes lockdep think +lock_tx_qs() may cause a dead lock. + + +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/net/ethernet/freescale/gianfar.c | 12 ++++++------ + 1 file changed, 6 insertions(+), 6 deletions(-) + +--- a/drivers/net/ethernet/freescale/gianfar.c ++++ b/drivers/net/ethernet/freescale/gianfar.c +@@ -1540,7 +1540,7 @@ static int gfar_suspend(struct device *d + + if (netif_running(ndev)) { + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + lock_tx_qs(priv); + + gfar_halt_nodisable(priv); +@@ -1556,7 +1556,7 @@ static int gfar_suspend(struct device *d + gfar_write(®s->maccfg1, tempval); + + unlock_tx_qs(priv); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + disable_napi(priv); + +@@ -1598,7 +1598,7 @@ static int gfar_resume(struct device *de + /* Disable Magic Packet mode, in case something + * else woke us up. + */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + lock_tx_qs(priv); + + tempval = gfar_read(®s->maccfg2); +@@ -1608,7 +1608,7 @@ static int gfar_resume(struct device *de + gfar_start(priv); + + unlock_tx_qs(priv); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + netif_device_attach(ndev); + +@@ -3418,14 +3418,14 @@ static irqreturn_t gfar_error(int irq, v + dev->stats.tx_dropped++; + atomic64_inc(&priv->extra_stats.tx_underrun); + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + lock_tx_qs(priv); + + /* Reactivate the Tx Queues */ + gfar_write(®s->tstat, gfargrp->tstat); + + unlock_tx_qs(priv); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + netif_dbg(priv, tx_err, dev, "Transmit Error\n"); + } diff --git a/debian/patches/features/all/rt/net-make-devnet_rename_seq-a-mutex.patch b/debian/patches/features/all/rt/net-make-devnet_rename_seq-a-mutex.patch new file mode 100644 index 000000000..699679ce4 --- /dev/null +++ b/debian/patches/features/all/rt/net-make-devnet_rename_seq-a-mutex.patch @@ -0,0 +1,107 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 20 Mar 2013 18:06:20 +0100 +Subject: net: Add a mutex around devnet_rename_seq +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +On RT write_seqcount_begin() disables preemption and device_rename() +allocates memory with GFP_KERNEL and grabs later the sysfs_mutex +mutex. Serialize with a mutex and add use the non preemption disabling +__write_seqcount_begin(). + +To avoid writer starvation, let the reader grab the mutex and release +it when it detects a writer in progress. This keeps the normal case +(no reader on the fly) fast. + +[ tglx: Instead of replacing the seqcount by a mutex, add the mutex ] + +Signed-off-by: Sebastian Andrzej Siewior +Signed-off-by: Thomas Gleixner +--- + net/core/dev.c | 34 ++++++++++++++++++++-------------- + 1 file changed, 20 insertions(+), 14 deletions(-) + +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -184,6 +184,7 @@ static unsigned int napi_gen_id; + static DEFINE_HASHTABLE(napi_hash, 8); + + static seqcount_t devnet_rename_seq; ++static DEFINE_MUTEX(devnet_rename_mutex); + + static inline void dev_base_seq_inc(struct net *net) + { +@@ -856,7 +857,8 @@ int netdev_get_name(struct net *net, cha + strcpy(name, dev->name); + rcu_read_unlock(); + if (read_seqcount_retry(&devnet_rename_seq, seq)) { +- cond_resched(); ++ mutex_lock(&devnet_rename_mutex); ++ mutex_unlock(&devnet_rename_mutex); + goto retry; + } + +@@ -1125,20 +1127,17 @@ int dev_change_name(struct net_device *d + if (dev->flags & IFF_UP) + return -EBUSY; + +- write_seqcount_begin(&devnet_rename_seq); ++ mutex_lock(&devnet_rename_mutex); ++ __raw_write_seqcount_begin(&devnet_rename_seq); + +- if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { +- write_seqcount_end(&devnet_rename_seq); +- return 0; +- } ++ if (strncmp(newname, dev->name, IFNAMSIZ) == 0) ++ goto outunlock; + + memcpy(oldname, dev->name, IFNAMSIZ); + + err = dev_get_valid_name(net, dev, newname); +- if (err < 0) { +- write_seqcount_end(&devnet_rename_seq); +- return err; +- } ++ if (err < 0) ++ goto outunlock; + + if (oldname[0] && !strchr(oldname, '%')) + netdev_info(dev, "renamed from %s\n", oldname); +@@ -1151,11 +1150,12 @@ int dev_change_name(struct net_device *d + if (ret) { + memcpy(dev->name, oldname, IFNAMSIZ); + dev->name_assign_type = old_assign_type; +- write_seqcount_end(&devnet_rename_seq); +- return ret; ++ err = ret; ++ goto outunlock; + } + +- write_seqcount_end(&devnet_rename_seq); ++ __raw_write_seqcount_end(&devnet_rename_seq); ++ mutex_unlock(&devnet_rename_mutex); + + netdev_adjacent_rename_links(dev, oldname); + +@@ -1176,7 +1176,8 @@ int dev_change_name(struct net_device *d + /* err >= 0 after dev_alloc_name() or stores the first errno */ + if (err >= 0) { + err = ret; +- write_seqcount_begin(&devnet_rename_seq); ++ mutex_lock(&devnet_rename_mutex); ++ __raw_write_seqcount_begin(&devnet_rename_seq); + memcpy(dev->name, oldname, IFNAMSIZ); + memcpy(oldname, newname, IFNAMSIZ); + dev->name_assign_type = old_assign_type; +@@ -1189,6 +1190,11 @@ int dev_change_name(struct net_device *d + } + + return err; ++ ++outunlock: ++ __raw_write_seqcount_end(&devnet_rename_seq); ++ mutex_unlock(&devnet_rename_mutex); ++ return err; + } + + /** diff --git a/debian/patches/features/all/rt/net-prevent-abba-deadlock.patch b/debian/patches/features/all/rt/net-prevent-abba-deadlock.patch new file mode 100644 index 000000000..46a6316c3 --- /dev/null +++ b/debian/patches/features/all/rt/net-prevent-abba-deadlock.patch @@ -0,0 +1,112 @@ +Subject: net-flip-lock-dep-thingy.patch +From: Thomas Gleixner +Date: Tue, 28 Jun 2011 10:59:58 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +======================================================= +[ INFO: possible circular locking dependency detected ] +3.0.0-rc3+ #26 +------------------------------------------------------- +ip/1104 is trying to acquire lock: + (local_softirq_lock){+.+...}, at: [] __local_lock+0x25/0x68 + +but task is already holding lock: + (sk_lock-AF_INET){+.+...}, at: [] lock_sock+0x10/0x12 + +which lock already depends on the new lock. + + +the existing dependency chain (in reverse order) is: + +-> #1 (sk_lock-AF_INET){+.+...}: + [] lock_acquire+0x103/0x12e + [] lock_sock_nested+0x82/0x92 + [] lock_sock+0x10/0x12 + [] tcp_close+0x1b/0x355 + [] inet_release+0xc3/0xcd + [] sock_release+0x1f/0x74 + [] sock_close+0x27/0x2b + [] fput+0x11d/0x1e3 + [] filp_close+0x70/0x7b + [] sys_close+0xf8/0x13d + [] system_call_fastpath+0x16/0x1b + +-> #0 (local_softirq_lock){+.+...}: + [] __lock_acquire+0xacc/0xdc8 + [] lock_acquire+0x103/0x12e + [] _raw_spin_lock+0x3b/0x4a + [] __local_lock+0x25/0x68 + [] local_bh_disable+0x36/0x3b + [] _raw_write_lock_bh+0x16/0x4f + [] tcp_close+0x159/0x355 + [] inet_release+0xc3/0xcd + [] sock_release+0x1f/0x74 + [] sock_close+0x27/0x2b + [] fput+0x11d/0x1e3 + [] filp_close+0x70/0x7b + [] sys_close+0xf8/0x13d + [] system_call_fastpath+0x16/0x1b + +other info that might help us debug this: + + Possible unsafe locking scenario: + + CPU0 CPU1 + ---- ---- + lock(sk_lock-AF_INET); + lock(local_softirq_lock); + lock(sk_lock-AF_INET); + lock(local_softirq_lock); + + *** DEADLOCK *** + +1 lock held by ip/1104: + #0: (sk_lock-AF_INET){+.+...}, at: [] lock_sock+0x10/0x12 + +stack backtrace: +Pid: 1104, comm: ip Not tainted 3.0.0-rc3+ #26 +Call Trace: + [] print_circular_bug+0x1f8/0x209 + [] __lock_acquire+0xacc/0xdc8 + [] ? __local_lock+0x25/0x68 + [] lock_acquire+0x103/0x12e + [] ? __local_lock+0x25/0x68 + [] ? get_parent_ip+0x11/0x41 + [] _raw_spin_lock+0x3b/0x4a + [] ? __local_lock+0x25/0x68 + [] ? get_parent_ip+0x28/0x41 + [] __local_lock+0x25/0x68 + [] local_bh_disable+0x36/0x3b + [] ? lock_sock+0x10/0x12 + [] _raw_write_lock_bh+0x16/0x4f + [] tcp_close+0x159/0x355 + [] inet_release+0xc3/0xcd + [] sock_release+0x1f/0x74 + [] sock_close+0x27/0x2b + [] fput+0x11d/0x1e3 + [] filp_close+0x70/0x7b + [] sys_close+0xf8/0x13d + [] system_call_fastpath+0x16/0x1b + + +Signed-off-by: Thomas Gleixner +--- + net/core/sock.c | 3 +-- + 1 file changed, 1 insertion(+), 2 deletions(-) + +--- a/net/core/sock.c ++++ b/net/core/sock.c +@@ -2370,12 +2370,11 @@ void lock_sock_nested(struct sock *sk, i + if (sk->sk_lock.owned) + __lock_sock(sk); + sk->sk_lock.owned = 1; +- spin_unlock(&sk->sk_lock.slock); ++ spin_unlock_bh(&sk->sk_lock.slock); + /* + * The sk_lock has mutex_lock() semantics here: + */ + mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); +- local_bh_enable(); + } + EXPORT_SYMBOL(lock_sock_nested); + diff --git a/debian/patches/features/all/rt/net-sched-dev_deactivate_many-use-msleep-1-instead-o.patch b/debian/patches/features/all/rt/net-sched-dev_deactivate_many-use-msleep-1-instead-o.patch new file mode 100644 index 000000000..5dc6111ae --- /dev/null +++ b/debian/patches/features/all/rt/net-sched-dev_deactivate_many-use-msleep-1-instead-o.patch @@ -0,0 +1,58 @@ +From: Marc Kleine-Budde +Date: Wed, 5 Mar 2014 00:49:47 +0100 +Subject: net: sched: Use msleep() instead of yield() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +On PREEMPT_RT enabled systems the interrupt handler run as threads at prio 50 +(by default). If a high priority userspace process tries to shut down a busy +network interface it might spin in a yield loop waiting for the device to +become idle. With the interrupt thread having a lower priority than the +looping process it might never be scheduled and so result in a deadlock on UP +systems. + +With Magic SysRq the following backtrace can be produced: + +> test_app R running 0 174 168 0x00000000 +> [] (__schedule+0x220/0x3fc) from [] (preempt_schedule_irq+0x48/0x80) +> [] (preempt_schedule_irq+0x48/0x80) from [] (svc_preempt+0x8/0x20) +> [] (svc_preempt+0x8/0x20) from [] (local_bh_enable+0x18/0x88) +> [] (local_bh_enable+0x18/0x88) from [] (dev_deactivate_many+0x220/0x264) +> [] (dev_deactivate_many+0x220/0x264) from [] (__dev_close_many+0x64/0xd4) +> [] (__dev_close_many+0x64/0xd4) from [] (__dev_close+0x28/0x3c) +> [] (__dev_close+0x28/0x3c) from [] (__dev_change_flags+0x88/0x130) +> [] (__dev_change_flags+0x88/0x130) from [] (dev_change_flags+0x10/0x48) +> [] (dev_change_flags+0x10/0x48) from [] (do_setlink+0x370/0x7ec) +> [] (do_setlink+0x370/0x7ec) from [] (rtnl_newlink+0x2b4/0x450) +> [] (rtnl_newlink+0x2b4/0x450) from [] (rtnetlink_rcv_msg+0x158/0x1f4) +> [] (rtnetlink_rcv_msg+0x158/0x1f4) from [] (netlink_rcv_skb+0xac/0xc0) +> [] (netlink_rcv_skb+0xac/0xc0) from [] (rtnetlink_rcv+0x18/0x24) +> [] (rtnetlink_rcv+0x18/0x24) from [] (netlink_unicast+0x13c/0x198) +> [] (netlink_unicast+0x13c/0x198) from [] (netlink_sendmsg+0x264/0x2e0) +> [] (netlink_sendmsg+0x264/0x2e0) from [] (sock_sendmsg+0x78/0x98) +> [] (sock_sendmsg+0x78/0x98) from [] (___sys_sendmsg.part.25+0x268/0x278) +> [] (___sys_sendmsg.part.25+0x268/0x278) from [] (__sys_sendmsg+0x48/0x78) +> [] (__sys_sendmsg+0x48/0x78) from [] (ret_fast_syscall+0x0/0x2c) + +This patch works around the problem by replacing yield() by msleep(1), giving +the interrupt thread time to finish, similar to other changes contained in the +rt patch set. Using wait_for_completion() instead would probably be a better +solution. + + +Signed-off-by: Marc Kleine-Budde +Signed-off-by: Sebastian Andrzej Siewior +--- + net/sched/sch_generic.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/net/sched/sch_generic.c ++++ b/net/sched/sch_generic.c +@@ -894,7 +894,7 @@ void dev_deactivate_many(struct list_hea + /* Wait for outstanding qdisc_run calls. */ + list_for_each_entry(dev, head, close_list) + while (some_qdisc_is_busy(dev)) +- yield(); ++ msleep(1); + } + + void dev_deactivate(struct net_device *dev) diff --git a/debian/patches/features/all/rt/net-tx-action-avoid-livelock-on-rt.patch b/debian/patches/features/all/rt/net-tx-action-avoid-livelock-on-rt.patch new file mode 100644 index 000000000..365a6bd33 --- /dev/null +++ b/debian/patches/features/all/rt/net-tx-action-avoid-livelock-on-rt.patch @@ -0,0 +1,93 @@ +Subject: net: Avoid livelock in net_tx_action() on RT +From: Steven Rostedt +Date: Thu, 06 Oct 2011 10:48:39 -0400 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +qdisc_lock is taken w/o disabling interrupts or bottom halfs. So code +holding a qdisc_lock() can be interrupted and softirqs can run on the +return of interrupt in !RT. + +The spin_trylock() in net_tx_action() makes sure, that the softirq +does not deadlock. When the lock can't be acquired q is requeued and +the NET_TX softirq is raised. That causes the softirq to run over and +over. + +That works in mainline as do_softirq() has a retry loop limit and +leaves the softirq processing in the interrupt return path and +schedules ksoftirqd. The task which holds qdisc_lock cannot be +preempted, so the lock is released and either ksoftirqd or the next +softirq in the return from interrupt path can proceed. Though it's a +bit strange to actually run MAX_SOFTIRQ_RESTART (10) loops before it +decides to bail out even if it's clear in the first iteration :) + +On RT all softirq processing is done in a FIFO thread and we don't +have a loop limit, so ksoftirqd preempts the lock holder forever and +unqueues and requeues until the reset button is hit. + +Due to the forced threading of ksoftirqd on RT we actually cannot +deadlock on qdisc_lock because it's a "sleeping lock". So it's safe to +replace the spin_trylock() with a spin_lock(). When contended, +ksoftirqd is scheduled out and the lock holder can proceed. + +[ tglx: Massaged changelog and code comments ] + +Solved-by: Thomas Gleixner +Signed-off-by: Steven Rostedt +Tested-by: Carsten Emde +Cc: Clark Williams +Cc: John Kacur +Cc: Luis Claudio R. Goncalves +Signed-off-by: Thomas Gleixner + +--- + net/core/dev.c | 32 +++++++++++++++++++++++++++++++- + 1 file changed, 31 insertions(+), 1 deletion(-) + +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -3445,6 +3445,36 @@ int netif_rx_ni(struct sk_buff *skb) + } + EXPORT_SYMBOL(netif_rx_ni); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * RT runs ksoftirqd as a real time thread and the root_lock is a ++ * "sleeping spinlock". If the trylock fails then we can go into an ++ * infinite loop when ksoftirqd preempted the task which actually ++ * holds the lock, because we requeue q and raise NET_TX softirq ++ * causing ksoftirqd to loop forever. ++ * ++ * It's safe to use spin_lock on RT here as softirqs run in thread ++ * context and cannot deadlock against the thread which is holding ++ * root_lock. ++ * ++ * On !RT the trylock might fail, but there we bail out from the ++ * softirq loop after 10 attempts which we can't do on RT. And the ++ * task holding root_lock cannot be preempted, so the only downside of ++ * that trylock is that we need 10 loops to decide that we should have ++ * given up in the first one :) ++ */ ++static inline int take_root_lock(spinlock_t *lock) ++{ ++ spin_lock(lock); ++ return 1; ++} ++#else ++static inline int take_root_lock(spinlock_t *lock) ++{ ++ return spin_trylock(lock); ++} ++#endif ++ + static void net_tx_action(struct softirq_action *h) + { + struct softnet_data *sd = this_cpu_ptr(&softnet_data); +@@ -3486,7 +3516,7 @@ static void net_tx_action(struct softirq + head = head->next_sched; + + root_lock = qdisc_lock(q); +- if (spin_trylock(root_lock)) { ++ if (take_root_lock(root_lock)) { + smp_mb__before_atomic(); + clear_bit(__QDISC_STATE_SCHED, + &q->state); diff --git a/debian/patches/features/all/rt/net-use-cpu-chill.patch b/debian/patches/features/all/rt/net-use-cpu-chill.patch new file mode 100644 index 000000000..0f85db295 --- /dev/null +++ b/debian/patches/features/all/rt/net-use-cpu-chill.patch @@ -0,0 +1,63 @@ +Subject: net: Use cpu_chill() instead of cpu_relax() +From: Thomas Gleixner +Date: Wed, 07 Mar 2012 21:10:04 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Retry loops on RT might loop forever when the modifying side was +preempted. Use cpu_chill() instead of cpu_relax() to let the system +make progress. + +Signed-off-by: Thomas Gleixner + +--- + net/packet/af_packet.c | 5 +++-- + net/rds/ib_rdma.c | 3 ++- + 2 files changed, 5 insertions(+), 3 deletions(-) + +--- a/net/packet/af_packet.c ++++ b/net/packet/af_packet.c +@@ -63,6 +63,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -698,7 +699,7 @@ static void prb_retire_rx_blk_timer_expi + if (BLOCK_NUM_PKTS(pbd)) { + while (atomic_read(&pkc->blk_fill_in_prog)) { + /* Waiting for skb_copy_bits to finish... */ +- cpu_relax(); ++ cpu_chill(); + } + } + +@@ -960,7 +961,7 @@ static void prb_retire_current_block(str + if (!(status & TP_STATUS_BLK_TMO)) { + while (atomic_read(&pkc->blk_fill_in_prog)) { + /* Waiting for skb_copy_bits to finish... */ +- cpu_relax(); ++ cpu_chill(); + } + } + prb_close_block(pkc, pbd, po, status); +--- a/net/rds/ib_rdma.c ++++ b/net/rds/ib_rdma.c +@@ -34,6 +34,7 @@ + #include + #include + #include ++#include + + #include "rds.h" + #include "ib.h" +@@ -286,7 +287,7 @@ static inline void wait_clean_list_grace + for_each_online_cpu(cpu) { + flag = &per_cpu(clean_list_grace, cpu); + while (test_bit(CLEAN_LIST_BUSY_BIT, flag)) +- cpu_relax(); ++ cpu_chill(); + } + } + diff --git a/debian/patches/features/all/rt/net-wireless-warn-nort.patch b/debian/patches/features/all/rt/net-wireless-warn-nort.patch new file mode 100644 index 000000000..74b661660 --- /dev/null +++ b/debian/patches/features/all/rt/net-wireless-warn-nort.patch @@ -0,0 +1,24 @@ +Subject: net/wireless: Use WARN_ON_NORT() +From: Thomas Gleixner +Date: Thu, 21 Jul 2011 21:05:33 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The softirq counter is meaningless on RT, so the check triggers a +false positive. + +Signed-off-by: Thomas Gleixner +--- + net/mac80211/rx.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/net/mac80211/rx.c ++++ b/net/mac80211/rx.c +@@ -3554,7 +3554,7 @@ void ieee80211_rx(struct ieee80211_hw *h + struct ieee80211_supported_band *sband; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); + +- WARN_ON_ONCE(softirq_count() == 0); ++ WARN_ON_ONCE_NONRT(softirq_count() == 0); + + if (WARN_ON(status->band >= IEEE80211_NUM_BANDS)) + goto drop; diff --git a/debian/patches/features/all/rt/oleg-signal-rt-fix.patch b/debian/patches/features/all/rt/oleg-signal-rt-fix.patch new file mode 100644 index 000000000..97de9c3e4 --- /dev/null +++ b/debian/patches/features/all/rt/oleg-signal-rt-fix.patch @@ -0,0 +1,144 @@ +From: Oleg Nesterov +Date: Tue, 14 Jul 2015 14:26:34 +0200 +Subject: signal/x86: Delay calling signals in atomic +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +On x86_64 we must disable preemption before we enable interrupts +for stack faults, int3 and debugging, because the current task is using +a per CPU debug stack defined by the IST. If we schedule out, another task +can come in and use the same stack and cause the stack to be corrupted +and crash the kernel on return. + +When CONFIG_PREEMPT_RT_FULL is enabled, spin_locks become mutexes, and +one of these is the spin lock used in signal handling. + +Some of the debug code (int3) causes do_trap() to send a signal. +This function calls a spin lock that has been converted to a mutex +and has the possibility to sleep. If this happens, the above issues with +the corrupted stack is possible. + +Instead of calling the signal right away, for PREEMPT_RT and x86_64, +the signal information is stored on the stacks task_struct and +TIF_NOTIFY_RESUME is set. Then on exit of the trap, the signal resume +code will send the signal when preemption is enabled. + +[ rostedt: Switched from #ifdef CONFIG_PREEMPT_RT_FULL to + ARCH_RT_DELAYS_SIGNAL_SEND and added comments to the code. ] + + +Signed-off-by: Oleg Nesterov +Signed-off-by: Steven Rostedt +Signed-off-by: Thomas Gleixner +--- + + arch/x86/include/asm/signal.h | 13 +++++++++++++ + arch/x86/kernel/signal.c | 8 ++++++++ + include/linux/sched.h | 4 ++++ + kernel/signal.c | 37 +++++++++++++++++++++++++++++++++++-- + 4 files changed, 60 insertions(+), 2 deletions(-) + +--- a/arch/x86/include/asm/signal.h ++++ b/arch/x86/include/asm/signal.h +@@ -23,6 +23,19 @@ typedef struct { + unsigned long sig[_NSIG_WORDS]; + } sigset_t; + ++/* ++ * Because some traps use the IST stack, we must keep preemption ++ * disabled while calling do_trap(), but do_trap() may call ++ * force_sig_info() which will grab the signal spin_locks for the ++ * task, which in PREEMPT_RT_FULL are mutexes. By defining ++ * ARCH_RT_DELAYS_SIGNAL_SEND the force_sig_info() will set ++ * TIF_NOTIFY_RESUME and set up the signal to be sent on exit of the ++ * trap. ++ */ ++#if defined(CONFIG_PREEMPT_RT_FULL) && defined(CONFIG_X86_64) ++#define ARCH_RT_DELAYS_SIGNAL_SEND ++#endif ++ + #ifndef CONFIG_COMPAT + typedef sigset_t compat_sigset_t; + #endif +--- a/arch/x86/kernel/signal.c ++++ b/arch/x86/kernel/signal.c +@@ -727,6 +727,14 @@ do_notify_resume(struct pt_regs *regs, v + { + user_exit(); + ++#ifdef ARCH_RT_DELAYS_SIGNAL_SEND ++ if (unlikely(current->forced_info.si_signo)) { ++ struct task_struct *t = current; ++ force_sig_info(t->forced_info.si_signo, &t->forced_info, t); ++ t->forced_info.si_signo = 0; ++ } ++#endif ++ + if (thread_info_flags & _TIF_UPROBE) + uprobe_notify_resume(regs); + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -1538,6 +1538,10 @@ struct task_struct { + sigset_t blocked, real_blocked; + sigset_t saved_sigmask; /* restored if set_restore_sigmask() was used */ + struct sigpending pending; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* TODO: move me into ->restart_block ? */ ++ struct siginfo forced_info; ++#endif + + unsigned long sas_ss_sp; + size_t sas_ss_size; +--- a/kernel/signal.c ++++ b/kernel/signal.c +@@ -1282,8 +1282,8 @@ int do_send_sig_info(int sig, struct sig + * We don't want to have recursive SIGSEGV's etc, for example, + * that is why we also clear SIGNAL_UNKILLABLE. + */ +-int +-force_sig_info(int sig, struct siginfo *info, struct task_struct *t) ++static int ++do_force_sig_info(int sig, struct siginfo *info, struct task_struct *t) + { + unsigned long int flags; + int ret, blocked, ignored; +@@ -1308,6 +1308,39 @@ force_sig_info(int sig, struct siginfo * + return ret; + } + ++int force_sig_info(int sig, struct siginfo *info, struct task_struct *t) ++{ ++/* ++ * On some archs, PREEMPT_RT has to delay sending a signal from a trap ++ * since it can not enable preemption, and the signal code's spin_locks ++ * turn into mutexes. Instead, it must set TIF_NOTIFY_RESUME which will ++ * send the signal on exit of the trap. ++ */ ++#ifdef ARCH_RT_DELAYS_SIGNAL_SEND ++ if (in_atomic()) { ++ if (WARN_ON_ONCE(t != current)) ++ return 0; ++ if (WARN_ON_ONCE(t->forced_info.si_signo)) ++ return 0; ++ ++ if (is_si_special(info)) { ++ WARN_ON_ONCE(info != SEND_SIG_PRIV); ++ t->forced_info.si_signo = sig; ++ t->forced_info.si_errno = 0; ++ t->forced_info.si_code = SI_KERNEL; ++ t->forced_info.si_pid = 0; ++ t->forced_info.si_uid = 0; ++ } else { ++ t->forced_info = *info; ++ } ++ ++ set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); ++ return 0; ++ } ++#endif ++ return do_force_sig_info(sig, info, t); ++} ++ + /* + * Nuke all other threads in the group. + */ diff --git a/debian/patches/features/all/rt/panic-disable-random-on-rt.patch b/debian/patches/features/all/rt/panic-disable-random-on-rt.patch new file mode 100644 index 000000000..3a49239fc --- /dev/null +++ b/debian/patches/features/all/rt/panic-disable-random-on-rt.patch @@ -0,0 +1,27 @@ +From: Thomas Gleixner +Date: Tue, 14 Jul 2015 14:26:34 +0200 +Subject: panic: skip get_random_bytes for RT_FULL in init_oops_id +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Disable on -RT. If this is invoked from irq-context we will have problems +to acquire the sleeping lock. + +Signed-off-by: Thomas Gleixner +--- + kernel/panic.c | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/kernel/panic.c ++++ b/kernel/panic.c +@@ -387,9 +387,11 @@ static u64 oops_id; + + static int init_oops_id(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + if (!oops_id) + get_random_bytes(&oops_id, sizeof(oops_id)); + else ++#endif + oops_id++; + + return 0; diff --git a/debian/patches/features/all/rt/patch-to-introduce-rcu-bh-qs-where-safe-from-softirq.patch b/debian/patches/features/all/rt/patch-to-introduce-rcu-bh-qs-where-safe-from-softirq.patch new file mode 100644 index 000000000..2883a4759 --- /dev/null +++ b/debian/patches/features/all/rt/patch-to-introduce-rcu-bh-qs-where-safe-from-softirq.patch @@ -0,0 +1,112 @@ +Subject: rcu: Make ksoftirqd do RCU quiescent states +From: "Paul E. McKenney" +Date: Wed, 5 Oct 2011 11:45:18 -0700 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Implementing RCU-bh in terms of RCU-preempt makes the system vulnerable +to network-based denial-of-service attacks. This patch therefore +makes __do_softirq() invoke rcu_bh_qs(), but only when __do_softirq() +is running in ksoftirqd context. A wrapper layer in interposed so that +other calls to __do_softirq() avoid invoking rcu_bh_qs(). The underlying +function __do_softirq_common() does the actual work. + +The reason that rcu_bh_qs() is bad in these non-ksoftirqd contexts is +that there might be a local_bh_enable() inside an RCU-preempt read-side +critical section. This local_bh_enable() can invoke __do_softirq() +directly, so if __do_softirq() were to invoke rcu_bh_qs() (which just +calls rcu_preempt_qs() in the PREEMPT_RT_FULL case), there would be +an illegal RCU-preempt quiescent state in the middle of an RCU-preempt +read-side critical section. Therefore, quiescent states can only happen +in cases where __do_softirq() is invoked directly from ksoftirqd. + +Signed-off-by: Paul E. McKenney +Link: http://lkml.kernel.org/r/20111005184518.GA21601@linux.vnet.ibm.com +Signed-off-by: Thomas Gleixner + +--- + include/linux/rcupdate.h | 6 ------ + kernel/rcu/tree.c | 9 ++++++++- + kernel/rcu/tree_plugin.h | 9 +++++++-- + 3 files changed, 15 insertions(+), 9 deletions(-) + +--- a/include/linux/rcupdate.h ++++ b/include/linux/rcupdate.h +@@ -300,13 +300,7 @@ static inline int rcu_preempt_depth(void + void rcu_init(void); + void rcu_end_inkernel_boot(void); + void rcu_sched_qs(void); +- +-#ifdef CONFIG_PREEMPT_RT_FULL +-static inline void rcu_bh_qs(void) { } +-#else + void rcu_bh_qs(void); +-#endif +- + void rcu_check_callbacks(int user); + struct notifier_block; + void rcu_idle_enter(void); +--- a/kernel/rcu/tree.c ++++ b/kernel/rcu/tree.c +@@ -220,7 +220,14 @@ void rcu_sched_qs(void) + } + } + +-#ifndef CONFIG_PREEMPT_RT_FULL ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void rcu_preempt_qs(void); ++ ++void rcu_bh_qs(void) ++{ ++ rcu_preempt_qs(); ++} ++#else + void rcu_bh_qs(void) + { + if (!__this_cpu_read(rcu_bh_data.passed_quiesce)) { +--- a/kernel/rcu/tree_plugin.h ++++ b/kernel/rcu/tree_plugin.h +@@ -28,6 +28,7 @@ + #include + #include + #include ++#include + #include "../time/tick-internal.h" + + #ifdef CONFIG_RCU_BOOST +@@ -1356,7 +1357,7 @@ static void rcu_prepare_kthreads(int cpu + + #endif /* #else #ifdef CONFIG_RCU_BOOST */ + +-#if !defined(CONFIG_RCU_FAST_NO_HZ) ++#if !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) + + /* + * Check to see if any future RCU-related work will need to be done +@@ -1374,7 +1375,9 @@ int rcu_needs_cpu(unsigned long *delta_j + return rcu_cpu_has_callbacks(NULL); + } + #endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ ++#endif /* !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) */ + ++#if !defined(CONFIG_RCU_FAST_NO_HZ) + /* + * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up + * after it. +@@ -1472,6 +1475,8 @@ static bool __maybe_unused rcu_try_advan + return cbs_ready; + } + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + /* + * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready + * to invoke. If the CPU has callbacks, try to advance them. Tell the +@@ -1512,7 +1517,7 @@ int rcu_needs_cpu(unsigned long *dj) + return 0; + } + #endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ +- ++#endif /* #ifndef CONFIG_PREEMPT_RT_FULL */ + /* + * Prepare a CPU for idle from an RCU perspective. The first major task + * is to sense whether nohz mode has been enabled or disabled via sysfs. diff --git a/debian/patches/features/all/rt/pci-access-use-__wake_up_all_locked.patch b/debian/patches/features/all/rt/pci-access-use-__wake_up_all_locked.patch new file mode 100644 index 000000000..556fc1ece --- /dev/null +++ b/debian/patches/features/all/rt/pci-access-use-__wake_up_all_locked.patch @@ -0,0 +1,26 @@ +Subject: pci: Use __wake_up_all_locked in pci_unblock_user_cfg_access() +From: Thomas Gleixner +Date: Thu, 01 Dec 2011 00:07:16 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The waitqueue is protected by the pci_lock, so we can just avoid to +lock the waitqueue lock itself. That prevents the +might_sleep()/scheduling while atomic problem on RT + +Signed-off-by: Thomas Gleixner + +--- + drivers/pci/access.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/pci/access.c ++++ b/drivers/pci/access.c +@@ -521,7 +521,7 @@ void pci_cfg_access_unlock(struct pci_de + WARN_ON(!dev->block_cfg_access); + + dev->block_cfg_access = 0; +- wake_up_all(&pci_cfg_wait); ++ wake_up_all_locked(&pci_cfg_wait); + raw_spin_unlock_irqrestore(&pci_lock, flags); + } + EXPORT_SYMBOL_GPL(pci_cfg_access_unlock); diff --git a/debian/patches/features/all/rt/percpu_ida-use-locklocks.patch b/debian/patches/features/all/rt/percpu_ida-use-locklocks.patch new file mode 100644 index 000000000..6151f0cc6 --- /dev/null +++ b/debian/patches/features/all/rt/percpu_ida-use-locklocks.patch @@ -0,0 +1,102 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 9 Apr 2014 11:58:17 +0200 +Subject: percpu_ida: Use local locks +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +the local_irq_save() + spin_lock() does not work that well on -RT + +Signed-off-by: Sebastian Andrzej Siewior +--- + lib/percpu_ida.c | 20 ++++++++++++-------- + 1 file changed, 12 insertions(+), 8 deletions(-) + +--- a/lib/percpu_ida.c ++++ b/lib/percpu_ida.c +@@ -26,6 +26,9 @@ + #include + #include + #include ++#include ++ ++static DEFINE_LOCAL_IRQ_LOCK(irq_off_lock); + + struct percpu_ida_cpu { + /* +@@ -148,13 +151,13 @@ int percpu_ida_alloc(struct percpu_ida * + unsigned long flags; + int tag; + +- local_irq_save(flags); ++ local_lock_irqsave(irq_off_lock, flags); + tags = this_cpu_ptr(pool->tag_cpu); + + /* Fastpath */ + tag = alloc_local_tag(tags); + if (likely(tag >= 0)) { +- local_irq_restore(flags); ++ local_unlock_irqrestore(irq_off_lock, flags); + return tag; + } + +@@ -173,6 +176,7 @@ int percpu_ida_alloc(struct percpu_ida * + + if (!tags->nr_free) + alloc_global_tags(pool, tags); ++ + if (!tags->nr_free) + steal_tags(pool, tags); + +@@ -184,7 +188,7 @@ int percpu_ida_alloc(struct percpu_ida * + } + + spin_unlock(&pool->lock); +- local_irq_restore(flags); ++ local_unlock_irqrestore(irq_off_lock, flags); + + if (tag >= 0 || state == TASK_RUNNING) + break; +@@ -196,7 +200,7 @@ int percpu_ida_alloc(struct percpu_ida * + + schedule(); + +- local_irq_save(flags); ++ local_lock_irqsave(irq_off_lock, flags); + tags = this_cpu_ptr(pool->tag_cpu); + } + if (state != TASK_RUNNING) +@@ -221,7 +225,7 @@ void percpu_ida_free(struct percpu_ida * + + BUG_ON(tag >= pool->nr_tags); + +- local_irq_save(flags); ++ local_lock_irqsave(irq_off_lock, flags); + tags = this_cpu_ptr(pool->tag_cpu); + + spin_lock(&tags->lock); +@@ -253,7 +257,7 @@ void percpu_ida_free(struct percpu_ida * + spin_unlock(&pool->lock); + } + +- local_irq_restore(flags); ++ local_unlock_irqrestore(irq_off_lock, flags); + } + EXPORT_SYMBOL_GPL(percpu_ida_free); + +@@ -345,7 +349,7 @@ int percpu_ida_for_each_free(struct perc + struct percpu_ida_cpu *remote; + unsigned cpu, i, err = 0; + +- local_irq_save(flags); ++ local_lock_irqsave(irq_off_lock, flags); + for_each_possible_cpu(cpu) { + remote = per_cpu_ptr(pool->tag_cpu, cpu); + spin_lock(&remote->lock); +@@ -367,7 +371,7 @@ int percpu_ida_for_each_free(struct perc + } + spin_unlock(&pool->lock); + out: +- local_irq_restore(flags); ++ local_unlock_irqrestore(irq_off_lock, flags); + return err; + } + EXPORT_SYMBOL_GPL(percpu_ida_for_each_free); diff --git a/debian/patches/features/all/rt/perf-make-swevent-hrtimer-irqsafe.patch b/debian/patches/features/all/rt/perf-make-swevent-hrtimer-irqsafe.patch new file mode 100644 index 000000000..f474fbf16 --- /dev/null +++ b/debian/patches/features/all/rt/perf-make-swevent-hrtimer-irqsafe.patch @@ -0,0 +1,69 @@ +From: Yong Zhang +Date: Wed, 11 Jul 2012 22:05:21 +0000 +Subject: perf: Make swevent hrtimer run in irq instead of softirq +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Otherwise we get a deadlock like below: + +[ 1044.042749] BUG: scheduling while atomic: ksoftirqd/21/141/0x00010003 +[ 1044.042752] INFO: lockdep is turned off. +[ 1044.042754] Modules linked in: +[ 1044.042757] Pid: 141, comm: ksoftirqd/21 Tainted: G W 3.4.0-rc2-rt3-23676-ga723175-dirty #29 +[ 1044.042759] Call Trace: +[ 1044.042761] [] __schedule_bug+0x65/0x80 +[ 1044.042770] [] __schedule+0x83c/0xa70 +[ 1044.042775] [] ? prepare_to_wait+0x32/0xb0 +[ 1044.042779] [] schedule+0x2e/0xa0 +[ 1044.042782] [] hrtimer_wait_for_timer+0x6d/0xb0 +[ 1044.042786] [] ? wake_up_bit+0x40/0x40 +[ 1044.042790] [] hrtimer_cancel+0x20/0x40 +[ 1044.042794] [] perf_swevent_cancel_hrtimer+0x3c/0x50 +[ 1044.042798] [] task_clock_event_stop+0x11/0x40 +[ 1044.042802] [] task_clock_event_del+0xe/0x10 +[ 1044.042805] [] event_sched_out+0x118/0x1d0 +[ 1044.042809] [] group_sched_out+0x29/0x90 +[ 1044.042813] [] __perf_event_disable+0x18e/0x200 +[ 1044.042817] [] remote_function+0x63/0x70 +[ 1044.042821] [] generic_smp_call_function_single_interrupt+0xce/0x120 +[ 1044.042826] [] smp_call_function_single_interrupt+0x27/0x40 +[ 1044.042831] [] call_function_single_interrupt+0x6c/0x80 +[ 1044.042833] [] ? perf_event_overflow+0x20/0x20 +[ 1044.042840] [] ? _raw_spin_unlock_irq+0x30/0x70 +[ 1044.042844] [] ? _raw_spin_unlock_irq+0x36/0x70 +[ 1044.042848] [] run_hrtimer_softirq+0xc2/0x200 +[ 1044.042853] [] ? perf_event_overflow+0x20/0x20 +[ 1044.042857] [] __do_softirq_common+0xf5/0x3a0 +[ 1044.042862] [] __thread_do_softirq+0x15d/0x200 +[ 1044.042865] [] run_ksoftirqd+0xfa/0x210 +[ 1044.042869] [] ? __thread_do_softirq+0x200/0x200 +[ 1044.042873] [] ? __thread_do_softirq+0x200/0x200 +[ 1044.042877] [] kthread+0xb6/0xc0 +[ 1044.042881] [] ? _raw_spin_unlock_irq+0x3b/0x70 +[ 1044.042886] [] kernel_thread_helper+0x4/0x10 +[ 1044.042889] [] ? finish_task_switch+0x8c/0x110 +[ 1044.042894] [] ? _raw_spin_unlock_irq+0x3b/0x70 +[ 1044.042897] [] ? retint_restore_args+0xe/0xe +[ 1044.042900] [] ? kthreadd+0x1e0/0x1e0 +[ 1044.042902] [] ? gs_change+0xb/0xb + +Signed-off-by: Yong Zhang +Cc: Peter Zijlstra +Cc: Steven Rostedt +Link: http://lkml.kernel.org/r/1341476476-5666-1-git-send-email-yong.zhang0@gmail.com +Signed-off-by: Thomas Gleixner +Signed-off-by: Steven Rostedt + +--- + kernel/events/core.c | 1 + + 1 file changed, 1 insertion(+) + +--- a/kernel/events/core.c ++++ b/kernel/events/core.c +@@ -6890,6 +6890,7 @@ static void perf_swevent_init_hrtimer(st + + hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hwc->hrtimer.function = perf_swevent_hrtimer; ++ hwc->hrtimer.irqsafe = 1; + + /* + * Since hrtimers have a fixed rate, we can do a static freq->period diff --git a/debian/patches/features/all/rt/peter_zijlstra-frob-rcu.patch b/debian/patches/features/all/rt/peter_zijlstra-frob-rcu.patch new file mode 100644 index 000000000..785974b52 --- /dev/null +++ b/debian/patches/features/all/rt/peter_zijlstra-frob-rcu.patch @@ -0,0 +1,167 @@ +Subject: rcu: Frob softirq test +From: Peter Zijlstra +Date: Sat Aug 13 00:23:17 CEST 2011 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +With RT_FULL we get the below wreckage: + +[ 126.060484] ======================================================= +[ 126.060486] [ INFO: possible circular locking dependency detected ] +[ 126.060489] 3.0.1-rt10+ #30 +[ 126.060490] ------------------------------------------------------- +[ 126.060492] irq/24-eth0/1235 is trying to acquire lock: +[ 126.060495] (&(lock)->wait_lock#2){+.+...}, at: [] rt_mutex_slowunlock+0x16/0x55 +[ 126.060503] +[ 126.060504] but task is already holding lock: +[ 126.060506] (&p->pi_lock){-...-.}, at: [] try_to_wake_up+0x35/0x429 +[ 126.060511] +[ 126.060511] which lock already depends on the new lock. +[ 126.060513] +[ 126.060514] +[ 126.060514] the existing dependency chain (in reverse order) is: +[ 126.060516] +[ 126.060516] -> #1 (&p->pi_lock){-...-.}: +[ 126.060519] [] lock_acquire+0x145/0x18a +[ 126.060524] [] _raw_spin_lock_irqsave+0x4b/0x85 +[ 126.060527] [] task_blocks_on_rt_mutex+0x36/0x20f +[ 126.060531] [] rt_mutex_slowlock+0xd1/0x15a +[ 126.060534] [] rt_mutex_lock+0x2d/0x2f +[ 126.060537] [] rcu_boost+0xad/0xde +[ 126.060541] [] rcu_boost_kthread+0x7d/0x9b +[ 126.060544] [] kthread+0x99/0xa1 +[ 126.060547] [] kernel_thread_helper+0x4/0x10 +[ 126.060551] +[ 126.060552] -> #0 (&(lock)->wait_lock#2){+.+...}: +[ 126.060555] [] __lock_acquire+0x1157/0x1816 +[ 126.060558] [] lock_acquire+0x145/0x18a +[ 126.060561] [] _raw_spin_lock+0x40/0x73 +[ 126.060564] [] rt_mutex_slowunlock+0x16/0x55 +[ 126.060566] [] rt_mutex_unlock+0x27/0x29 +[ 126.060569] [] rcu_read_unlock_special+0x17e/0x1c4 +[ 126.060573] [] __rcu_read_unlock+0x48/0x89 +[ 126.060576] [] select_task_rq_rt+0xc7/0xd5 +[ 126.060580] [] try_to_wake_up+0x175/0x429 +[ 126.060583] [] wake_up_process+0x15/0x17 +[ 126.060585] [] wakeup_softirqd+0x24/0x26 +[ 126.060590] [] irq_exit+0x49/0x55 +[ 126.060593] [] smp_apic_timer_interrupt+0x8a/0x98 +[ 126.060597] [] apic_timer_interrupt+0x13/0x20 +[ 126.060600] [] irq_forced_thread_fn+0x1b/0x44 +[ 126.060603] [] irq_thread+0xde/0x1af +[ 126.060606] [] kthread+0x99/0xa1 +[ 126.060608] [] kernel_thread_helper+0x4/0x10 +[ 126.060611] +[ 126.060612] other info that might help us debug this: +[ 126.060614] +[ 126.060615] Possible unsafe locking scenario: +[ 126.060616] +[ 126.060617] CPU0 CPU1 +[ 126.060619] ---- ---- +[ 126.060620] lock(&p->pi_lock); +[ 126.060623] lock(&(lock)->wait_lock); +[ 126.060625] lock(&p->pi_lock); +[ 126.060627] lock(&(lock)->wait_lock); +[ 126.060629] +[ 126.060629] *** DEADLOCK *** +[ 126.060630] +[ 126.060632] 1 lock held by irq/24-eth0/1235: +[ 126.060633] #0: (&p->pi_lock){-...-.}, at: [] try_to_wake_up+0x35/0x429 +[ 126.060638] +[ 126.060638] stack backtrace: +[ 126.060641] Pid: 1235, comm: irq/24-eth0 Not tainted 3.0.1-rt10+ #30 +[ 126.060643] Call Trace: +[ 126.060644] [] print_circular_bug+0x289/0x29a +[ 126.060651] [] __lock_acquire+0x1157/0x1816 +[ 126.060655] [] ? trace_hardirqs_off_caller+0x1f/0x99 +[ 126.060658] [] ? rt_mutex_slowunlock+0x16/0x55 +[ 126.060661] [] lock_acquire+0x145/0x18a +[ 126.060664] [] ? rt_mutex_slowunlock+0x16/0x55 +[ 126.060668] [] _raw_spin_lock+0x40/0x73 +[ 126.060671] [] ? rt_mutex_slowunlock+0x16/0x55 +[ 126.060674] [] ? rcu_report_qs_rsp+0x87/0x8c +[ 126.060677] [] rt_mutex_slowunlock+0x16/0x55 +[ 126.060680] [] ? rcu_read_unlock_special+0x9b/0x1c4 +[ 126.060683] [] rt_mutex_unlock+0x27/0x29 +[ 126.060687] [] rcu_read_unlock_special+0x17e/0x1c4 +[ 126.060690] [] __rcu_read_unlock+0x48/0x89 +[ 126.060693] [] select_task_rq_rt+0xc7/0xd5 +[ 126.060696] [] ? select_task_rq_rt+0x27/0xd5 +[ 126.060701] [] ? clockevents_program_event+0x8e/0x90 +[ 126.060704] [] try_to_wake_up+0x175/0x429 +[ 126.060708] [] ? tick_program_event+0x1f/0x21 +[ 126.060711] [] wake_up_process+0x15/0x17 +[ 126.060715] [] wakeup_softirqd+0x24/0x26 +[ 126.060718] [] irq_exit+0x49/0x55 +[ 126.060721] [] smp_apic_timer_interrupt+0x8a/0x98 +[ 126.060724] [] apic_timer_interrupt+0x13/0x20 +[ 126.060726] [] ? migrate_disable+0x75/0x12d +[ 126.060733] [] ? local_bh_disable+0xe/0x1f +[ 126.060736] [] ? local_bh_disable+0x1d/0x1f +[ 126.060739] [] irq_forced_thread_fn+0x1b/0x44 +[ 126.060742] [] ? _raw_spin_unlock_irq+0x3b/0x59 +[ 126.060745] [] irq_thread+0xde/0x1af +[ 126.060748] [] ? irq_thread_fn+0x3a/0x3a +[ 126.060751] [] ? irq_finalize_oneshot+0xd1/0xd1 +[ 126.060754] [] ? irq_finalize_oneshot+0xd1/0xd1 +[ 126.060757] [] kthread+0x99/0xa1 +[ 126.060761] [] kernel_thread_helper+0x4/0x10 +[ 126.060764] [] ? finish_task_switch+0x87/0x10a +[ 126.060768] [] ? retint_restore_args+0xe/0xe +[ 126.060771] [] ? __init_kthread_worker+0x8c/0x8c +[ 126.060774] [] ? gs_change+0xb/0xb + +Because irq_exit() does: + +void irq_exit(void) +{ + account_system_vtime(current); + trace_hardirq_exit(); + sub_preempt_count(IRQ_EXIT_OFFSET); + if (!in_interrupt() && local_softirq_pending()) + invoke_softirq(); + + ... +} + +Which triggers a wakeup, which uses RCU, now if the interrupted task has +t->rcu_read_unlock_special set, the rcu usage from the wakeup will end +up in rcu_read_unlock_special(). rcu_read_unlock_special() will test +for in_irq(), which will fail as we just decremented preempt_count +with IRQ_EXIT_OFFSET, and in_sering_softirq(), which for +PREEMPT_RT_FULL reads: + +int in_serving_softirq(void) +{ + int res; + + preempt_disable(); + res = __get_cpu_var(local_softirq_runner) == current; + preempt_enable(); + return res; +} + +Which will thus also fail, resulting in the above wreckage. + +The 'somewhat' ugly solution is to open-code the preempt_count() test +in rcu_read_unlock_special(). + +Also, we're not at all sure how ->rcu_read_unlock_special gets set +here... so this is very likely a bandaid and more thought is required. + +Cc: Paul E. McKenney +Signed-off-by: Peter Zijlstra +--- + kernel/rcu/tree_plugin.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/kernel/rcu/tree_plugin.h ++++ b/kernel/rcu/tree_plugin.h +@@ -291,7 +291,7 @@ void rcu_read_unlock_special(struct task + } + + /* Hardware IRQ handlers cannot block, complain if they get here. */ +- if (in_irq() || in_serving_softirq()) { ++ if (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET)) { + lockdep_rcu_suspicious(__FILE__, __LINE__, + "rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n"); + pr_alert("->rcu_read_unlock_special: %#x (b: %d, nq: %d)\n", diff --git a/debian/patches/features/all/rt/peterz-srcu-crypto-chain.patch b/debian/patches/features/all/rt/peterz-srcu-crypto-chain.patch new file mode 100644 index 000000000..a305f6496 --- /dev/null +++ b/debian/patches/features/all/rt/peterz-srcu-crypto-chain.patch @@ -0,0 +1,183 @@ +Subject: crypto: Convert crypto notifier chain to SRCU +From: Peter Zijlstra +Date: Fri, 05 Oct 2012 09:03:24 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The crypto notifier deadlocks on RT. Though this can be a real deadlock +on mainline as well due to fifo fair rwsems. + +The involved parties here are: + +[ 82.172678] swapper/0 S 0000000000000001 0 1 0 0x00000000 +[ 82.172682] ffff88042f18fcf0 0000000000000046 ffff88042f18fc80 ffffffff81491238 +[ 82.172685] 0000000000011cc0 0000000000011cc0 ffff88042f18c040 ffff88042f18ffd8 +[ 82.172688] 0000000000011cc0 0000000000011cc0 ffff88042f18ffd8 0000000000011cc0 +[ 82.172689] Call Trace: +[ 82.172697] [] ? _raw_spin_unlock_irqrestore+0x6c/0x7a +[ 82.172701] [] schedule+0x64/0x66 +[ 82.172704] [] schedule_timeout+0x27/0xd0 +[ 82.172708] [] ? unpin_current_cpu+0x1a/0x6c +[ 82.172713] [] ? migrate_enable+0x12f/0x141 +[ 82.172716] [] wait_for_common+0xbb/0x11f +[ 82.172719] [] ? try_to_wake_up+0x182/0x182 +[ 82.172722] [] wait_for_completion_interruptible+0x1d/0x2e +[ 82.172726] [] crypto_wait_for_test+0x49/0x6b +[ 82.172728] [] crypto_register_alg+0x53/0x5a +[ 82.172730] [] crypto_register_algs+0x33/0x72 +[ 82.172734] [] ? aes_init+0x12/0x12 +[ 82.172737] [] aesni_init+0x64/0x66 +[ 82.172741] [] do_one_initcall+0x7f/0x13b +[ 82.172744] [] kernel_init+0x199/0x22c +[ 82.172747] [] ? loglevel+0x31/0x31 +[ 82.172752] [] kernel_thread_helper+0x4/0x10 +[ 82.172755] [] ? retint_restore_args+0x13/0x13 +[ 82.172759] [] ? start_kernel+0x3ca/0x3ca +[ 82.172761] [] ? gs_change+0x13/0x13 + +[ 82.174186] cryptomgr_test S 0000000000000001 0 41 2 0x00000000 +[ 82.174189] ffff88042c971980 0000000000000046 ffffffff81d74830 0000000000000292 +[ 82.174192] 0000000000011cc0 0000000000011cc0 ffff88042c96eb80 ffff88042c971fd8 +[ 82.174195] 0000000000011cc0 0000000000011cc0 ffff88042c971fd8 0000000000011cc0 +[ 82.174195] Call Trace: +[ 82.174198] [] schedule+0x64/0x66 +[ 82.174201] [] schedule_timeout+0x27/0xd0 +[ 82.174204] [] ? unpin_current_cpu+0x1a/0x6c +[ 82.174206] [] ? migrate_enable+0x12f/0x141 +[ 82.174209] [] wait_for_common+0xbb/0x11f +[ 82.174212] [] ? try_to_wake_up+0x182/0x182 +[ 82.174215] [] wait_for_completion_interruptible+0x1d/0x2e +[ 82.174218] [] cryptomgr_notify+0x280/0x385 +[ 82.174221] [] notifier_call_chain+0x6b/0x98 +[ 82.174224] [] ? rt_down_read+0x10/0x12 +[ 82.174227] [] __blocking_notifier_call_chain+0x70/0x8d +[ 82.174230] [] blocking_notifier_call_chain+0x14/0x16 +[ 82.174234] [] crypto_probing_notify+0x24/0x50 +[ 82.174236] [] crypto_alg_mod_lookup+0x3e/0x74 +[ 82.174238] [] crypto_alloc_base+0x36/0x8f +[ 82.174241] [] cryptd_alloc_ablkcipher+0x6e/0xb5 +[ 82.174243] [] ? kzalloc.clone.5+0xe/0x10 +[ 82.174246] [] ablk_init_common+0x1d/0x38 +[ 82.174249] [] ablk_ecb_init+0x15/0x17 +[ 82.174251] [] __crypto_alloc_tfm+0xc7/0x114 +[ 82.174254] [] ? crypto_lookup_skcipher+0x1f/0xe4 +[ 82.174256] [] crypto_alloc_ablkcipher+0x60/0xa5 +[ 82.174258] [] alg_test_skcipher+0x24/0x9b +[ 82.174261] [] ? finish_task_switch+0x3f/0xfa +[ 82.174263] [] alg_test+0x16f/0x1d7 +[ 82.174267] [] ? cryptomgr_probe+0xac/0xac +[ 82.174269] [] cryptomgr_test+0x2c/0x47 +[ 82.174272] [] kthread+0x7e/0x86 +[ 82.174275] [] ? finish_task_switch+0xaf/0xfa +[ 82.174278] [] kernel_thread_helper+0x4/0x10 +[ 82.174281] [] ? retint_restore_args+0x13/0x13 +[ 82.174284] [] ? __init_kthread_worker+0x8c/0x8c +[ 82.174287] [] ? gs_change+0x13/0x13 + +[ 82.174329] cryptomgr_probe D 0000000000000002 0 47 2 0x00000000 +[ 82.174332] ffff88042c991b70 0000000000000046 ffff88042c991bb0 0000000000000006 +[ 82.174335] 0000000000011cc0 0000000000011cc0 ffff88042c98ed00 ffff88042c991fd8 +[ 82.174338] 0000000000011cc0 0000000000011cc0 ffff88042c991fd8 0000000000011cc0 +[ 82.174338] Call Trace: +[ 82.174342] [] schedule+0x64/0x66 +[ 82.174344] [] __rt_mutex_slowlock+0x85/0xbe +[ 82.174347] [] rt_mutex_slowlock+0xec/0x159 +[ 82.174351] [] rt_mutex_fastlock.clone.8+0x29/0x2f +[ 82.174353] [] rt_mutex_lock+0x33/0x37 +[ 82.174356] [] __rt_down_read+0x50/0x5a +[ 82.174358] [] ? rt_down_read+0x10/0x12 +[ 82.174360] [] rt_down_read+0x10/0x12 +[ 82.174363] [] __blocking_notifier_call_chain+0x58/0x8d +[ 82.174366] [] blocking_notifier_call_chain+0x14/0x16 +[ 82.174369] [] crypto_probing_notify+0x24/0x50 +[ 82.174372] [] crypto_wait_for_test+0x22/0x6b +[ 82.174374] [] crypto_register_instance+0xb4/0xc0 +[ 82.174377] [] cryptd_create+0x378/0x3b6 +[ 82.174379] [] ? __crypto_lookup_template+0x5b/0x63 +[ 82.174382] [] cryptomgr_probe+0x45/0xac +[ 82.174385] [] ? crypto_alloc_pcomp+0x1b/0x1b +[ 82.174388] [] kthread+0x7e/0x86 +[ 82.174391] [] ? finish_task_switch+0xaf/0xfa +[ 82.174394] [] kernel_thread_helper+0x4/0x10 +[ 82.174398] [] ? retint_restore_args+0x13/0x13 +[ 82.174401] [] ? __init_kthread_worker+0x8c/0x8c +[ 82.174403] [] ? gs_change+0x13/0x13 + +cryptomgr_test spawns the cryptomgr_probe thread from the notifier +call. The probe thread fires the same notifier as the test thread and +deadlocks on the rwsem on RT. + +Now this is a potential deadlock in mainline as well, because we have +fifo fair rwsems. If another thread blocks with a down_write() on the +notifier chain before the probe thread issues the down_read() it will +block the probe thread and the whole party is dead locked. + +Signed-off-by: Peter Zijlstra +Signed-off-by: Thomas Gleixner +--- + crypto/algapi.c | 4 ++-- + crypto/api.c | 6 +++--- + crypto/internal.h | 4 ++-- + 3 files changed, 7 insertions(+), 7 deletions(-) + +--- a/crypto/algapi.c ++++ b/crypto/algapi.c +@@ -695,13 +695,13 @@ EXPORT_SYMBOL_GPL(crypto_spawn_tfm2); + + int crypto_register_notifier(struct notifier_block *nb) + { +- return blocking_notifier_chain_register(&crypto_chain, nb); ++ return srcu_notifier_chain_register(&crypto_chain, nb); + } + EXPORT_SYMBOL_GPL(crypto_register_notifier); + + int crypto_unregister_notifier(struct notifier_block *nb) + { +- return blocking_notifier_chain_unregister(&crypto_chain, nb); ++ return srcu_notifier_chain_unregister(&crypto_chain, nb); + } + EXPORT_SYMBOL_GPL(crypto_unregister_notifier); + +--- a/crypto/api.c ++++ b/crypto/api.c +@@ -31,7 +31,7 @@ EXPORT_SYMBOL_GPL(crypto_alg_list); + DECLARE_RWSEM(crypto_alg_sem); + EXPORT_SYMBOL_GPL(crypto_alg_sem); + +-BLOCKING_NOTIFIER_HEAD(crypto_chain); ++SRCU_NOTIFIER_HEAD(crypto_chain); + EXPORT_SYMBOL_GPL(crypto_chain); + + static struct crypto_alg *crypto_larval_wait(struct crypto_alg *alg); +@@ -236,10 +236,10 @@ int crypto_probing_notify(unsigned long + { + int ok; + +- ok = blocking_notifier_call_chain(&crypto_chain, val, v); ++ ok = srcu_notifier_call_chain(&crypto_chain, val, v); + if (ok == NOTIFY_DONE) { + request_module("cryptomgr"); +- ok = blocking_notifier_call_chain(&crypto_chain, val, v); ++ ok = srcu_notifier_call_chain(&crypto_chain, val, v); + } + + return ok; +--- a/crypto/internal.h ++++ b/crypto/internal.h +@@ -48,7 +48,7 @@ struct crypto_larval { + + extern struct list_head crypto_alg_list; + extern struct rw_semaphore crypto_alg_sem; +-extern struct blocking_notifier_head crypto_chain; ++extern struct srcu_notifier_head crypto_chain; + + #ifdef CONFIG_PROC_FS + void __init crypto_init_proc(void); +@@ -142,7 +142,7 @@ static inline int crypto_is_moribund(str + + static inline void crypto_notify(unsigned long val, void *v) + { +- blocking_notifier_call_chain(&crypto_chain, val, v); ++ srcu_notifier_call_chain(&crypto_chain, val, v); + } + + #endif /* _CRYPTO_INTERNAL_H */ diff --git a/debian/patches/features/all/rt/pid.h-include-atomic.h.patch b/debian/patches/features/all/rt/pid.h-include-atomic.h.patch new file mode 100644 index 000000000..033ab5bb4 --- /dev/null +++ b/debian/patches/features/all/rt/pid.h-include-atomic.h.patch @@ -0,0 +1,37 @@ +From: Grygorii Strashko +Date: Tue, 21 Jul 2015 19:43:56 +0300 +Subject: wait.h: include atomic.h +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +This patch fixes build error: + CC kernel/pid_namespace.o +In file included from kernel/pid_namespace.c:11:0: +include/linux/pid.h: In function 'get_pid': +include/linux/pid.h:78:3: error: implicit declaration of function 'atomic_inc' [-Werror=implicit-function-declaration] + atomic_inc(&pid->count); + ^ +which happens when + CONFIG_PROVE_LOCKING=n + CONFIG_DEBUG_SPINLOCK=n + CONFIG_DEBUG_MUTEXES=n + CONFIG_DEBUG_LOCK_ALLOC=n + CONFIG_PID_NS=y + +Vanilla gets this via spinlock.h. + +Signed-off-by: Grygorii Strashko +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/pid.h | 1 + + 1 file changed, 1 insertion(+) + +--- a/include/linux/pid.h ++++ b/include/linux/pid.h +@@ -2,6 +2,7 @@ + #define _LINUX_PID_H + + #include ++#include + + enum pid_type + { diff --git a/debian/patches/features/all/rt/ping-sysrq.patch b/debian/patches/features/all/rt/ping-sysrq.patch new file mode 100644 index 000000000..f4e1b4a57 --- /dev/null +++ b/debian/patches/features/all/rt/ping-sysrq.patch @@ -0,0 +1,122 @@ +Subject: net: sysrq via icmp +From: Carsten Emde +Date: Tue, 19 Jul 2011 13:51:17 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +There are (probably rare) situations when a system crashed and the system +console becomes unresponsive but the network icmp layer still is alive. +Wouldn't it be wonderful, if we then could submit a sysreq command via ping? + +This patch provides this facility. Please consult the updated documentation +Documentation/sysrq.txt for details. + +Signed-off-by: Carsten Emde + +--- + Documentation/sysrq.txt | 11 +++++++++-- + include/net/netns/ipv4.h | 1 + + net/ipv4/icmp.c | 30 ++++++++++++++++++++++++++++++ + net/ipv4/sysctl_net_ipv4.c | 7 +++++++ + 4 files changed, 47 insertions(+), 2 deletions(-) + +--- a/Documentation/sysrq.txt ++++ b/Documentation/sysrq.txt +@@ -59,10 +59,17 @@ On PowerPC - Press 'ALT - Print Screen ( + On other - If you know of the key combos for other architectures, please + let me know so I can add them to this section. + +-On all - write a character to /proc/sysrq-trigger. e.g.: +- ++On all - write a character to /proc/sysrq-trigger, e.g.: + echo t > /proc/sysrq-trigger + ++On all - Enable network SysRq by writing a cookie to icmp_echo_sysrq, e.g. ++ echo 0x01020304 >/proc/sys/net/ipv4/icmp_echo_sysrq ++ Send an ICMP echo request with this pattern plus the particular ++ SysRq command key. Example: ++ # ping -c1 -s57 -p0102030468 ++ will trigger the SysRq-H (help) command. ++ ++ + * What are the 'command' keys? + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + 'b' - Will immediately reboot the system without syncing or unmounting +--- a/include/net/netns/ipv4.h ++++ b/include/net/netns/ipv4.h +@@ -69,6 +69,7 @@ struct netns_ipv4 { + + int sysctl_icmp_echo_ignore_all; + int sysctl_icmp_echo_ignore_broadcasts; ++ int sysctl_icmp_echo_sysrq; + int sysctl_icmp_ignore_bogus_error_responses; + int sysctl_icmp_ratelimit; + int sysctl_icmp_ratemask; +--- a/net/ipv4/icmp.c ++++ b/net/ipv4/icmp.c +@@ -69,6 +69,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -867,6 +868,30 @@ static bool icmp_redirect(struct sk_buff + } + + /* ++ * 32bit and 64bit have different timestamp length, so we check for ++ * the cookie at offset 20 and verify it is repeated at offset 50 ++ */ ++#define CO_POS0 20 ++#define CO_POS1 50 ++#define CO_SIZE sizeof(int) ++#define ICMP_SYSRQ_SIZE 57 ++ ++/* ++ * We got a ICMP_SYSRQ_SIZE sized ping request. Check for the cookie ++ * pattern and if it matches send the next byte as a trigger to sysrq. ++ */ ++static void icmp_check_sysrq(struct net *net, struct sk_buff *skb) ++{ ++ int cookie = htonl(net->ipv4.sysctl_icmp_echo_sysrq); ++ char *p = skb->data; ++ ++ if (!memcmp(&cookie, p + CO_POS0, CO_SIZE) && ++ !memcmp(&cookie, p + CO_POS1, CO_SIZE) && ++ p[CO_POS0 + CO_SIZE] == p[CO_POS1 + CO_SIZE]) ++ handle_sysrq(p[CO_POS0 + CO_SIZE]); ++} ++ ++/* + * Handle ICMP_ECHO ("ping") requests. + * + * RFC 1122: 3.2.2.6 MUST have an echo server that answers ICMP echo +@@ -893,6 +918,11 @@ static bool icmp_echo(struct sk_buff *sk + icmp_param.data_len = skb->len; + icmp_param.head_len = sizeof(struct icmphdr); + icmp_reply(&icmp_param, skb); ++ ++ if (skb->len == ICMP_SYSRQ_SIZE && ++ net->ipv4.sysctl_icmp_echo_sysrq) { ++ icmp_check_sysrq(net, skb); ++ } + } + /* should there be an ICMP stat for ignored echos? */ + return true; +--- a/net/ipv4/sysctl_net_ipv4.c ++++ b/net/ipv4/sysctl_net_ipv4.c +@@ -779,6 +779,13 @@ static struct ctl_table ipv4_net_table[] + .proc_handler = proc_dointvec + }, + { ++ .procname = "icmp_echo_sysrq", ++ .data = &init_net.ipv4.sysctl_icmp_echo_sysrq, ++ .maxlen = sizeof(int), ++ .mode = 0644, ++ .proc_handler = proc_dointvec ++ }, ++ { + .procname = "icmp_ignore_bogus_error_responses", + .data = &init_net.ipv4.sysctl_icmp_ignore_bogus_error_responses, + .maxlen = sizeof(int), diff --git a/debian/patches/features/all/rt/posix-timers-no-broadcast.patch b/debian/patches/features/all/rt/posix-timers-no-broadcast.patch new file mode 100644 index 000000000..065f848ab --- /dev/null +++ b/debian/patches/features/all/rt/posix-timers-no-broadcast.patch @@ -0,0 +1,34 @@ +From: Thomas Gleixner +Date: Fri, 3 Jul 2009 08:29:20 -0500 +Subject: posix-timers: Prevent broadcast signals +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Posix timers should not send broadcast signals and kernel only +signals. Prevent it. + +Signed-off-by: Thomas Gleixner + +--- + kernel/time/posix-timers.c | 4 +++- + 1 file changed, 3 insertions(+), 1 deletion(-) + +--- a/kernel/time/posix-timers.c ++++ b/kernel/time/posix-timers.c +@@ -499,6 +499,7 @@ static enum hrtimer_restart posix_timer_ + static struct pid *good_sigevent(sigevent_t * event) + { + struct task_struct *rtn = current->group_leader; ++ int sig = event->sigev_signo; + + if ((event->sigev_notify & SIGEV_THREAD_ID ) && + (!(rtn = find_task_by_vpid(event->sigev_notify_thread_id)) || +@@ -507,7 +508,8 @@ static struct pid *good_sigevent(sigeven + return NULL; + + if (((event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) && +- ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX))) ++ (sig <= 0 || sig > SIGRTMAX || sig_kernel_only(sig) || ++ sig_kernel_coredump(sig))) + return NULL; + + return task_pid(rtn); diff --git a/debian/patches/features/all/rt/posix-timers-thread-posix-cpu-timers-on-rt.patch b/debian/patches/features/all/rt/posix-timers-thread-posix-cpu-timers-on-rt.patch new file mode 100644 index 000000000..35b54ffb9 --- /dev/null +++ b/debian/patches/features/all/rt/posix-timers-thread-posix-cpu-timers-on-rt.patch @@ -0,0 +1,316 @@ +From: John Stultz +Date: Fri, 3 Jul 2009 08:29:58 -0500 +Subject: posix-timers: Thread posix-cpu-timers on -rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +posix-cpu-timer code takes non -rt safe locks in hard irq +context. Move it to a thread. + +[ 3.0 fixes from Peter Zijlstra ] + +Signed-off-by: John Stultz +Signed-off-by: Thomas Gleixner + +--- + include/linux/init_task.h | 7 + + include/linux/sched.h | 3 + kernel/fork.c | 3 + kernel/time/posix-cpu-timers.c | 198 +++++++++++++++++++++++++++++++++++++++-- + 4 files changed, 205 insertions(+), 6 deletions(-) + +--- a/include/linux/init_task.h ++++ b/include/linux/init_task.h +@@ -147,6 +147,12 @@ extern struct task_group root_task_group + # define INIT_PERF_EVENTS(tsk) + #endif + ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define INIT_TIMER_LIST .posix_timer_list = NULL, ++#else ++# define INIT_TIMER_LIST ++#endif ++ + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN + # define INIT_VTIME(tsk) \ + .vtime_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.vtime_lock), \ +@@ -239,6 +245,7 @@ extern struct task_group root_task_group + .cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \ + .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock), \ + .timer_slack_ns = 50000, /* 50 usec default slack */ \ ++ INIT_TIMER_LIST \ + .pids = { \ + [PIDTYPE_PID] = INIT_PID_LINK(PIDTYPE_PID), \ + [PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), \ +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -1501,6 +1501,9 @@ struct task_struct { + + struct task_cputime cputime_expires; + struct list_head cpu_timers[3]; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct task_struct *posix_timer_list; ++#endif + + /* process credentials */ + const struct cred __rcu *real_cred; /* objective and real subjective task +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -1214,6 +1214,9 @@ static void rt_mutex_init_task(struct ta + */ + static void posix_cpu_timers_init(struct task_struct *tsk) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ tsk->posix_timer_list = NULL; ++#endif + tsk->cputime_expires.prof_exp = 0; + tsk->cputime_expires.virt_exp = 0; + tsk->cputime_expires.sched_exp = 0; +--- a/kernel/time/posix-cpu-timers.c ++++ b/kernel/time/posix-cpu-timers.c +@@ -3,6 +3,7 @@ + */ + + #include ++#include + #include + #include + #include +@@ -626,7 +627,7 @@ static int posix_cpu_timer_set(struct k_ + /* + * Disarm any old timer after extracting its expiry time. + */ +- WARN_ON_ONCE(!irqs_disabled()); ++ WARN_ON_ONCE_NONRT(!irqs_disabled()); + + ret = 0; + old_incr = timer->it.cpu.incr; +@@ -1047,7 +1048,7 @@ void posix_cpu_timer_schedule(struct k_i + /* + * Now re-arm for the new expiry time. + */ +- WARN_ON_ONCE(!irqs_disabled()); ++ WARN_ON_ONCE_NONRT(!irqs_disabled()); + arm_timer(timer); + unlock_task_sighand(p, &flags); + +@@ -1113,10 +1114,11 @@ static inline int fastpath_timer_check(s + sig = tsk->signal; + if (sig->cputimer.running) { + struct task_cputime group_sample; ++ unsigned long flags; + +- raw_spin_lock(&sig->cputimer.lock); ++ raw_spin_lock_irqsave(&sig->cputimer.lock, flags); + group_sample = sig->cputimer.cputime; +- raw_spin_unlock(&sig->cputimer.lock); ++ raw_spin_unlock_irqrestore(&sig->cputimer.lock, flags); + + if (task_cputime_expired(&group_sample, &sig->cputime_expires)) + return 1; +@@ -1130,13 +1132,13 @@ static inline int fastpath_timer_check(s + * already updated our counts. We need to check if any timers fire now. + * Interrupts are disabled. + */ +-void run_posix_cpu_timers(struct task_struct *tsk) ++static void __run_posix_cpu_timers(struct task_struct *tsk) + { + LIST_HEAD(firing); + struct k_itimer *timer, *next; + unsigned long flags; + +- WARN_ON_ONCE(!irqs_disabled()); ++ WARN_ON_ONCE_NONRT(!irqs_disabled()); + + /* + * The fast path checks that there are no expired thread or thread +@@ -1194,6 +1196,190 @@ void run_posix_cpu_timers(struct task_st + } + } + ++#ifdef CONFIG_PREEMPT_RT_BASE ++#include ++#include ++DEFINE_PER_CPU(struct task_struct *, posix_timer_task); ++DEFINE_PER_CPU(struct task_struct *, posix_timer_tasklist); ++ ++static int posix_cpu_timers_thread(void *data) ++{ ++ int cpu = (long)data; ++ ++ BUG_ON(per_cpu(posix_timer_task,cpu) != current); ++ ++ while (!kthread_should_stop()) { ++ struct task_struct *tsk = NULL; ++ struct task_struct *next = NULL; ++ ++ if (cpu_is_offline(cpu)) ++ goto wait_to_die; ++ ++ /* grab task list */ ++ raw_local_irq_disable(); ++ tsk = per_cpu(posix_timer_tasklist, cpu); ++ per_cpu(posix_timer_tasklist, cpu) = NULL; ++ raw_local_irq_enable(); ++ ++ /* its possible the list is empty, just return */ ++ if (!tsk) { ++ set_current_state(TASK_INTERRUPTIBLE); ++ schedule(); ++ __set_current_state(TASK_RUNNING); ++ continue; ++ } ++ ++ /* Process task list */ ++ while (1) { ++ /* save next */ ++ next = tsk->posix_timer_list; ++ ++ /* run the task timers, clear its ptr and ++ * unreference it ++ */ ++ __run_posix_cpu_timers(tsk); ++ tsk->posix_timer_list = NULL; ++ put_task_struct(tsk); ++ ++ /* check if this is the last on the list */ ++ if (next == tsk) ++ break; ++ tsk = next; ++ } ++ } ++ return 0; ++ ++wait_to_die: ++ /* Wait for kthread_stop */ ++ set_current_state(TASK_INTERRUPTIBLE); ++ while (!kthread_should_stop()) { ++ schedule(); ++ set_current_state(TASK_INTERRUPTIBLE); ++ } ++ __set_current_state(TASK_RUNNING); ++ return 0; ++} ++ ++static inline int __fastpath_timer_check(struct task_struct *tsk) ++{ ++ /* tsk == current, ensure it is safe to use ->signal/sighand */ ++ if (unlikely(tsk->exit_state)) ++ return 0; ++ ++ if (!task_cputime_zero(&tsk->cputime_expires)) ++ return 1; ++ ++ if (!task_cputime_zero(&tsk->signal->cputime_expires)) ++ return 1; ++ ++ return 0; ++} ++ ++void run_posix_cpu_timers(struct task_struct *tsk) ++{ ++ unsigned long cpu = smp_processor_id(); ++ struct task_struct *tasklist; ++ ++ BUG_ON(!irqs_disabled()); ++ if(!per_cpu(posix_timer_task, cpu)) ++ return; ++ /* get per-cpu references */ ++ tasklist = per_cpu(posix_timer_tasklist, cpu); ++ ++ /* check to see if we're already queued */ ++ if (!tsk->posix_timer_list && __fastpath_timer_check(tsk)) { ++ get_task_struct(tsk); ++ if (tasklist) { ++ tsk->posix_timer_list = tasklist; ++ } else { ++ /* ++ * The list is terminated by a self-pointing ++ * task_struct ++ */ ++ tsk->posix_timer_list = tsk; ++ } ++ per_cpu(posix_timer_tasklist, cpu) = tsk; ++ ++ wake_up_process(per_cpu(posix_timer_task, cpu)); ++ } ++} ++ ++/* ++ * posix_cpu_thread_call - callback that gets triggered when a CPU is added. ++ * Here we can start up the necessary migration thread for the new CPU. ++ */ ++static int posix_cpu_thread_call(struct notifier_block *nfb, ++ unsigned long action, void *hcpu) ++{ ++ int cpu = (long)hcpu; ++ struct task_struct *p; ++ struct sched_param param; ++ ++ switch (action) { ++ case CPU_UP_PREPARE: ++ p = kthread_create(posix_cpu_timers_thread, hcpu, ++ "posixcputmr/%d",cpu); ++ if (IS_ERR(p)) ++ return NOTIFY_BAD; ++ p->flags |= PF_NOFREEZE; ++ kthread_bind(p, cpu); ++ /* Must be high prio to avoid getting starved */ ++ param.sched_priority = MAX_RT_PRIO-1; ++ sched_setscheduler(p, SCHED_FIFO, ¶m); ++ per_cpu(posix_timer_task,cpu) = p; ++ break; ++ case CPU_ONLINE: ++ /* Strictly unneccessary, as first user will wake it. */ ++ wake_up_process(per_cpu(posix_timer_task,cpu)); ++ break; ++#ifdef CONFIG_HOTPLUG_CPU ++ case CPU_UP_CANCELED: ++ /* Unbind it from offline cpu so it can run. Fall thru. */ ++ kthread_bind(per_cpu(posix_timer_task, cpu), ++ cpumask_any(cpu_online_mask)); ++ kthread_stop(per_cpu(posix_timer_task,cpu)); ++ per_cpu(posix_timer_task,cpu) = NULL; ++ break; ++ case CPU_DEAD: ++ kthread_stop(per_cpu(posix_timer_task,cpu)); ++ per_cpu(posix_timer_task,cpu) = NULL; ++ break; ++#endif ++ } ++ return NOTIFY_OK; ++} ++ ++/* Register at highest priority so that task migration (migrate_all_tasks) ++ * happens before everything else. ++ */ ++static struct notifier_block posix_cpu_thread_notifier = { ++ .notifier_call = posix_cpu_thread_call, ++ .priority = 10 ++}; ++ ++static int __init posix_cpu_thread_init(void) ++{ ++ void *hcpu = (void *)(long)smp_processor_id(); ++ /* Start one for boot CPU. */ ++ unsigned long cpu; ++ ++ /* init the per-cpu posix_timer_tasklets */ ++ for_each_possible_cpu(cpu) ++ per_cpu(posix_timer_tasklist, cpu) = NULL; ++ ++ posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_UP_PREPARE, hcpu); ++ posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_ONLINE, hcpu); ++ register_cpu_notifier(&posix_cpu_thread_notifier); ++ return 0; ++} ++early_initcall(posix_cpu_thread_init); ++#else /* CONFIG_PREEMPT_RT_BASE */ ++void run_posix_cpu_timers(struct task_struct *tsk) ++{ ++ __run_posix_cpu_timers(tsk); ++} ++#endif /* CONFIG_PREEMPT_RT_BASE */ ++ + /* + * Set one of the process-wide special case CPU timers or RLIMIT_CPU. + * The tsk->sighand->siglock must be held by the caller. diff --git a/debian/patches/features/all/rt/power-disable-highmem-on-rt.patch b/debian/patches/features/all/rt/power-disable-highmem-on-rt.patch new file mode 100644 index 000000000..9b7289756 --- /dev/null +++ b/debian/patches/features/all/rt/power-disable-highmem-on-rt.patch @@ -0,0 +1,23 @@ +Subject: powerpc: Disable highmem on RT +From: Thomas Gleixner +Date: Mon, 18 Jul 2011 17:08:34 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The current highmem handling on -RT is not compatible and needs fixups. + +Signed-off-by: Thomas Gleixner +--- + arch/powerpc/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/arch/powerpc/Kconfig ++++ b/arch/powerpc/Kconfig +@@ -313,7 +313,7 @@ menu "Kernel options" + + config HIGHMEM + bool "High memory support" +- depends on PPC32 ++ depends on PPC32 && !PREEMPT_RT_FULL + + source kernel/Kconfig.hz + source kernel/Kconfig.preempt diff --git a/debian/patches/features/all/rt/power-use-generic-rwsem-on-rt.patch b/debian/patches/features/all/rt/power-use-generic-rwsem-on-rt.patch new file mode 100644 index 000000000..f56d9ee99 --- /dev/null +++ b/debian/patches/features/all/rt/power-use-generic-rwsem-on-rt.patch @@ -0,0 +1,27 @@ +From: Thomas Gleixner +Date: Tue, 14 Jul 2015 14:26:34 +0200 +Subject: powerpc: Use generic rwsem on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Use generic code which uses rtmutex + +Signed-off-by: Thomas Gleixner +--- + arch/powerpc/Kconfig | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +--- a/arch/powerpc/Kconfig ++++ b/arch/powerpc/Kconfig +@@ -60,10 +60,11 @@ config LOCKDEP_SUPPORT + + config RWSEM_GENERIC_SPINLOCK + bool ++ default y if PREEMPT_RT_FULL + + config RWSEM_XCHGADD_ALGORITHM + bool +- default y ++ default y if !PREEMPT_RT_FULL + + config GENERIC_LOCKBREAK + bool diff --git a/debian/patches/features/all/rt/powerpc-kvm-Disable-in-kernel-MPIC-emulation-for-PRE.patch b/debian/patches/features/all/rt/powerpc-kvm-Disable-in-kernel-MPIC-emulation-for-PRE.patch new file mode 100644 index 000000000..f3b8196bd --- /dev/null +++ b/debian/patches/features/all/rt/powerpc-kvm-Disable-in-kernel-MPIC-emulation-for-PRE.patch @@ -0,0 +1,38 @@ +From: Bogdan Purcareata +Date: Fri, 24 Apr 2015 15:53:13 +0000 +Subject: powerpc/kvm: Disable in-kernel MPIC emulation for PREEMPT_RT_FULL +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +While converting the openpic emulation code to use a raw_spinlock_t enables +guests to run on RT, there's still a performance issue. For interrupts sent in +directed delivery mode with a multiple CPU mask, the emulated openpic will loop +through all of the VCPUs, and for each VCPUs, it call IRQ_check, which will loop +through all the pending interrupts for that VCPU. This is done while holding the +raw_lock, meaning that in all this time the interrupts and preemption are +disabled on the host Linux. A malicious user app can max both these number and +cause a DoS. + +This temporary fix is sent for two reasons. First is so that users who want to +use the in-kernel MPIC emulation are aware of the potential latencies, thus +making sure that the hardware MPIC and their usage scenario does not involve +interrupts sent in directed delivery mode, and the number of possible pending +interrupts is kept small. Secondly, this should incentivize the development of a +proper openpic emulation that would be better suited for RT. + +Acked-by: Scott Wood +Signed-off-by: Bogdan Purcareata +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/powerpc/kvm/Kconfig | 1 + + 1 file changed, 1 insertion(+) + +--- a/arch/powerpc/kvm/Kconfig ++++ b/arch/powerpc/kvm/Kconfig +@@ -172,6 +172,7 @@ config KVM_E500MC + config KVM_MPIC + bool "KVM in-kernel MPIC emulation" + depends on KVM && E500 ++ depends on !PREEMPT_RT_FULL + select HAVE_KVM_IRQCHIP + select HAVE_KVM_IRQFD + select HAVE_KVM_IRQ_ROUTING diff --git a/debian/patches/features/all/rt/powerpc-preempt-lazy-support.patch b/debian/patches/features/all/rt/powerpc-preempt-lazy-support.patch new file mode 100644 index 000000000..55beb77ec --- /dev/null +++ b/debian/patches/features/all/rt/powerpc-preempt-lazy-support.patch @@ -0,0 +1,174 @@ +From: Thomas Gleixner +Date: Thu, 1 Nov 2012 10:14:11 +0100 +Subject: powerpc: Add support for lazy preemption +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Implement the powerpc pieces for lazy preempt. + +Signed-off-by: Thomas Gleixner +--- + arch/powerpc/Kconfig | 1 + + arch/powerpc/include/asm/thread_info.h | 11 ++++++++--- + arch/powerpc/kernel/asm-offsets.c | 1 + + arch/powerpc/kernel/entry_32.S | 17 ++++++++++++----- + arch/powerpc/kernel/entry_64.S | 14 +++++++++++--- + 5 files changed, 33 insertions(+), 11 deletions(-) + +--- a/arch/powerpc/Kconfig ++++ b/arch/powerpc/Kconfig +@@ -139,6 +139,7 @@ config PPC + select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST + select GENERIC_STRNCPY_FROM_USER + select GENERIC_STRNLEN_USER ++ select HAVE_PREEMPT_LAZY + select HAVE_MOD_ARCH_SPECIFIC + select MODULES_USE_ELF_RELA + select CLONE_BACKWARDS +--- a/arch/powerpc/include/asm/thread_info.h ++++ b/arch/powerpc/include/asm/thread_info.h +@@ -42,6 +42,8 @@ struct thread_info { + int cpu; /* cpu we're on */ + int preempt_count; /* 0 => preemptable, + <0 => BUG */ ++ int preempt_lazy_count; /* 0 => preemptable, ++ <0 => BUG */ + unsigned long local_flags; /* private flags for thread */ + + /* low level flags - has atomic operations done on it */ +@@ -82,8 +84,7 @@ static inline struct thread_info *curren + #define TIF_SYSCALL_TRACE 0 /* syscall trace active */ + #define TIF_SIGPENDING 1 /* signal pending */ + #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ +-#define TIF_POLLING_NRFLAG 3 /* true if poll_idle() is polling +- TIF_NEED_RESCHED */ ++#define TIF_NEED_RESCHED_LAZY 3 /* lazy rescheduling necessary */ + #define TIF_32BIT 4 /* 32 bit binary */ + #define TIF_RESTORE_TM 5 /* need to restore TM FP/VEC/VSX */ + #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ +@@ -101,6 +102,8 @@ static inline struct thread_info *curren + #if defined(CONFIG_PPC64) + #define TIF_ELF2ABI 18 /* function descriptors must die! */ + #endif ++#define TIF_POLLING_NRFLAG 19 /* true if poll_idle() is polling ++ TIF_NEED_RESCHED */ + + /* as above, but as bit values */ + #define _TIF_SYSCALL_TRACE (1< +Date: Sun, 31 May 2015 14:44:42 -0400 +Subject: powerpc: ps3/device-init.c - adapt to completions using swait vs wait +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +To fix: + + cc1: warnings being treated as errors + arch/powerpc/platforms/ps3/device-init.c: In function 'ps3_notification_read_write': + arch/powerpc/platforms/ps3/device-init.c:755:2: error: passing argument 1 of 'prepare_to_wait_event' from incompatible pointer type + arch/powerpc/platforms/ps3/device-init.c:755:2: error: passing argument 1 of 'abort_exclusive_wait' from incompatible pointer type + arch/powerpc/platforms/ps3/device-init.c:755:2: error: passing argument 1 of 'finish_wait' from incompatible pointer type + arch/powerpc/platforms/ps3/device-init.o] Error 1 + make[3]: *** Waiting for unfinished jobs.... + +Signed-off-by: Paul Gortmaker +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/powerpc/platforms/ps3/device-init.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/arch/powerpc/platforms/ps3/device-init.c ++++ b/arch/powerpc/platforms/ps3/device-init.c +@@ -752,7 +752,7 @@ static int ps3_notification_read_write(s + } + pr_debug("%s:%u: notification %s issued\n", __func__, __LINE__, op); + +- res = wait_event_interruptible(dev->done.wait, ++ res = swait_event_interruptible(dev->done.wait, + dev->done.done || kthread_should_stop()); + if (kthread_should_stop()) + res = -EINTR; diff --git a/debian/patches/features/all/rt/preempt-lazy-support.patch b/debian/patches/features/all/rt/preempt-lazy-support.patch new file mode 100644 index 000000000..425f8f333 --- /dev/null +++ b/debian/patches/features/all/rt/preempt-lazy-support.patch @@ -0,0 +1,590 @@ +Subject: sched: Add support for lazy preemption +From: Thomas Gleixner +Date: Fri, 26 Oct 2012 18:50:54 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +It has become an obsession to mitigate the determinism vs. throughput +loss of RT. Looking at the mainline semantics of preemption points +gives a hint why RT sucks throughput wise for ordinary SCHED_OTHER +tasks. One major issue is the wakeup of tasks which are right away +preempting the waking task while the waking task holds a lock on which +the woken task will block right after having preempted the wakee. In +mainline this is prevented due to the implicit preemption disable of +spin/rw_lock held regions. On RT this is not possible due to the fully +preemptible nature of sleeping spinlocks. + +Though for a SCHED_OTHER task preempting another SCHED_OTHER task this +is really not a correctness issue. RT folks are concerned about +SCHED_FIFO/RR tasks preemption and not about the purely fairness +driven SCHED_OTHER preemption latencies. + +So I introduced a lazy preemption mechanism which only applies to +SCHED_OTHER tasks preempting another SCHED_OTHER task. Aside of the +existing preempt_count each tasks sports now a preempt_lazy_count +which is manipulated on lock acquiry and release. This is slightly +incorrect as for lazyness reasons I coupled this on +migrate_disable/enable so some other mechanisms get the same treatment +(e.g. get_cpu_light). + +Now on the scheduler side instead of setting NEED_RESCHED this sets +NEED_RESCHED_LAZY in case of a SCHED_OTHER/SCHED_OTHER preemption and +therefor allows to exit the waking task the lock held region before +the woken task preempts. That also works better for cross CPU wakeups +as the other side can stay in the adaptive spinning loop. + +For RT class preemption there is no change. This simply sets +NEED_RESCHED and forgoes the lazy preemption counter. + + Initial test do not expose any observable latency increasement, but +history shows that I've been proven wrong before :) + +The lazy preemption mode is per default on, but with +CONFIG_SCHED_DEBUG enabled it can be disabled via: + + # echo NO_PREEMPT_LAZY >/sys/kernel/debug/sched_features + +and reenabled via + + # echo PREEMPT_LAZY >/sys/kernel/debug/sched_features + +The test results so far are very machine and workload dependent, but +there is a clear trend that it enhances the non RT workload +performance. + +Signed-off-by: Thomas Gleixner +--- + arch/x86/include/asm/preempt.h | 18 +++++++++++++- + include/linux/ftrace_event.h | 1 + include/linux/preempt.h | 29 ++++++++++++++++++++++- + include/linux/sched.h | 37 ++++++++++++++++++++++++++++++ + include/linux/thread_info.h | 12 +++++++++ + kernel/Kconfig.preempt | 6 ++++ + kernel/sched/core.c | 50 ++++++++++++++++++++++++++++++++++++++++- + kernel/sched/fair.c | 16 ++++++------- + kernel/sched/features.h | 3 ++ + kernel/sched/sched.h | 9 +++++++ + kernel/trace/trace.c | 37 ++++++++++++++++++------------ + kernel/trace/trace.h | 2 + + kernel/trace/trace_output.c | 13 +++++++++- + 13 files changed, 204 insertions(+), 29 deletions(-) + +--- a/arch/x86/include/asm/preempt.h ++++ b/arch/x86/include/asm/preempt.h +@@ -82,17 +82,33 @@ static __always_inline void __preempt_co + * a decrement which hits zero means we have no preempt_count and should + * reschedule. + */ +-static __always_inline bool __preempt_count_dec_and_test(void) ++static __always_inline bool ____preempt_count_dec_and_test(void) + { + GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e"); + } + ++static __always_inline bool __preempt_count_dec_and_test(void) ++{ ++ if (____preempt_count_dec_and_test()) ++ return true; ++#ifdef CONFIG_PREEMPT_LAZY ++ return test_thread_flag(TIF_NEED_RESCHED_LAZY); ++#else ++ return false; ++#endif ++} ++ + /* + * Returns true when we need to resched and can (barring IRQ state). + */ + static __always_inline bool should_resched(void) + { ++#ifdef CONFIG_PREEMPT_LAZY ++ return unlikely(!raw_cpu_read_4(__preempt_count) || \ ++ test_thread_flag(TIF_NEED_RESCHED_LAZY)); ++#else + return unlikely(!raw_cpu_read_4(__preempt_count)); ++#endif + } + + #ifdef CONFIG_PREEMPT +--- a/include/linux/ftrace_event.h ++++ b/include/linux/ftrace_event.h +@@ -68,6 +68,7 @@ struct trace_entry { + int pid; + unsigned short migrate_disable; + unsigned short padding; ++ unsigned char preempt_lazy_count; + }; + + #define FTRACE_MAX_EVENT \ +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -33,6 +33,20 @@ extern void preempt_count_sub(int val); + #define preempt_count_inc() preempt_count_add(1) + #define preempt_count_dec() preempt_count_sub(1) + ++#ifdef CONFIG_PREEMPT_LAZY ++#define add_preempt_lazy_count(val) do { preempt_lazy_count() += (val); } while (0) ++#define sub_preempt_lazy_count(val) do { preempt_lazy_count() -= (val); } while (0) ++#define inc_preempt_lazy_count() add_preempt_lazy_count(1) ++#define dec_preempt_lazy_count() sub_preempt_lazy_count(1) ++#define preempt_lazy_count() (current_thread_info()->preempt_lazy_count) ++#else ++#define add_preempt_lazy_count(val) do { } while (0) ++#define sub_preempt_lazy_count(val) do { } while (0) ++#define inc_preempt_lazy_count() do { } while (0) ++#define dec_preempt_lazy_count() do { } while (0) ++#define preempt_lazy_count() (0) ++#endif ++ + #ifdef CONFIG_PREEMPT_COUNT + + #define preempt_disable() \ +@@ -41,6 +55,12 @@ do { \ + barrier(); \ + } while (0) + ++#define preempt_lazy_disable() \ ++do { \ ++ inc_preempt_lazy_count(); \ ++ barrier(); \ ++} while (0) ++ + #define sched_preempt_enable_no_resched() \ + do { \ + barrier(); \ +@@ -69,6 +89,13 @@ do { \ + __preempt_schedule(); \ + } while (0) + ++#define preempt_lazy_enable() \ ++do { \ ++ dec_preempt_lazy_count(); \ ++ barrier(); \ ++ preempt_check_resched(); \ ++} while (0) ++ + #else + #define preempt_enable() \ + do { \ +@@ -147,7 +174,7 @@ do { \ + } while (0) + #define preempt_fold_need_resched() \ + do { \ +- if (tif_need_resched()) \ ++ if (tif_need_resched_now()) \ + set_preempt_need_resched(); \ + } while (0) + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -2898,6 +2898,43 @@ static inline int test_tsk_need_resched( + return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); + } + ++#ifdef CONFIG_PREEMPT_LAZY ++static inline void set_tsk_need_resched_lazy(struct task_struct *tsk) ++{ ++ set_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); ++} ++ ++static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) ++{ ++ clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); ++} ++ ++static inline int test_tsk_need_resched_lazy(struct task_struct *tsk) ++{ ++ return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY)); ++} ++ ++static inline int need_resched_lazy(void) ++{ ++ return test_thread_flag(TIF_NEED_RESCHED_LAZY); ++} ++ ++static inline int need_resched_now(void) ++{ ++ return test_thread_flag(TIF_NEED_RESCHED); ++} ++ ++#else ++static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) { } ++static inline int need_resched_lazy(void) { return 0; } ++ ++static inline int need_resched_now(void) ++{ ++ return test_thread_flag(TIF_NEED_RESCHED); ++} ++ ++#endif ++ + static inline int restart_syscall(void) + { + set_tsk_thread_flag(current, TIF_SIGPENDING); +--- a/include/linux/thread_info.h ++++ b/include/linux/thread_info.h +@@ -102,7 +102,17 @@ static inline int test_ti_thread_flag(st + #define test_thread_flag(flag) \ + test_ti_thread_flag(current_thread_info(), flag) + +-#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) ++#ifdef CONFIG_PREEMPT_LAZY ++#define tif_need_resched() (test_thread_flag(TIF_NEED_RESCHED) || \ ++ test_thread_flag(TIF_NEED_RESCHED_LAZY)) ++#define tif_need_resched_now() (test_thread_flag(TIF_NEED_RESCHED)) ++#define tif_need_resched_lazy() test_thread_flag(TIF_NEED_RESCHED_LAZY)) ++ ++#else ++#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) ++#define tif_need_resched_now() test_thread_flag(TIF_NEED_RESCHED) ++#define tif_need_resched_lazy() 0 ++#endif + + #if defined TIF_RESTORE_SIGMASK && !defined HAVE_SET_RESTORE_SIGMASK + /* +--- a/kernel/Kconfig.preempt ++++ b/kernel/Kconfig.preempt +@@ -6,6 +6,12 @@ config PREEMPT_RT_BASE + bool + select PREEMPT + ++config HAVE_PREEMPT_LAZY ++ bool ++ ++config PREEMPT_LAZY ++ def_bool y if HAVE_PREEMPT_LAZY && PREEMPT_RT_FULL ++ + choice + prompt "Preemption Model" + default PREEMPT_NONE +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -623,6 +623,38 @@ void resched_curr(struct rq *rq) + trace_sched_wake_idle_without_ipi(cpu); + } + ++#ifdef CONFIG_PREEMPT_LAZY ++void resched_curr_lazy(struct rq *rq) ++{ ++ struct task_struct *curr = rq->curr; ++ int cpu; ++ ++ if (!sched_feat(PREEMPT_LAZY)) { ++ resched_curr(rq); ++ return; ++ } ++ ++ lockdep_assert_held(&rq->lock); ++ ++ if (test_tsk_need_resched(curr)) ++ return; ++ ++ if (test_tsk_need_resched_lazy(curr)) ++ return; ++ ++ set_tsk_need_resched_lazy(curr); ++ ++ cpu = cpu_of(rq); ++ if (cpu == smp_processor_id()) ++ return; ++ ++ /* NEED_RESCHED_LAZY must be visible before we test polling */ ++ smp_mb(); ++ if (!tsk_is_polling(curr)) ++ smp_send_reschedule(cpu); ++} ++#endif ++ + void resched_cpu(int cpu) + { + struct rq *rq = cpu_rq(cpu); +@@ -2018,6 +2050,9 @@ int sched_fork(unsigned long clone_flags + p->on_cpu = 0; + #endif + init_task_preempt_count(p); ++#ifdef CONFIG_HAVE_PREEMPT_LAZY ++ task_thread_info(p)->preempt_lazy_count = 0; ++#endif + #ifdef CONFIG_SMP + plist_node_init(&p->pushable_tasks, MAX_PRIO); + RB_CLEAR_NODE(&p->pushable_dl_tasks); +@@ -2774,6 +2809,7 @@ void migrate_disable(void) + } + + preempt_disable(); ++ preempt_lazy_disable(); + pin_current_cpu(); + p->migrate_disable = 1; + preempt_enable(); +@@ -2831,6 +2867,7 @@ void migrate_enable(void) + + unpin_current_cpu(); + preempt_enable(); ++ preempt_lazy_enable(); + } + EXPORT_SYMBOL(migrate_enable); + #else +@@ -2964,6 +3001,7 @@ static void __sched __schedule(void) + + next = pick_next_task(rq, prev); + clear_tsk_need_resched(prev); ++ clear_tsk_need_resched_lazy(prev); + clear_preempt_need_resched(); + rq->clock_skip_update = 0; + +@@ -3108,6 +3146,14 @@ asmlinkage __visible void __sched notrac + if (likely(!preemptible())) + return; + ++#ifdef CONFIG_PREEMPT_LAZY ++ /* ++ * Check for lazy preemption ++ */ ++ if (current_thread_info()->preempt_lazy_count && ++ !test_thread_flag(TIF_NEED_RESCHED)) ++ return; ++#endif + do { + __preempt_count_add(PREEMPT_ACTIVE); + /* +@@ -4831,7 +4877,9 @@ void init_idle(struct task_struct *idle, + + /* Set the preempt count _outside_ the spinlocks! */ + init_idle_preempt_count(idle, cpu); +- ++#ifdef CONFIG_HAVE_PREEMPT_LAZY ++ task_thread_info(idle)->preempt_lazy_count = 0; ++#endif + /* + * The idle tasks have their own, simple scheduling class: + */ +--- a/kernel/sched/fair.c ++++ b/kernel/sched/fair.c +@@ -3201,7 +3201,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq + ideal_runtime = sched_slice(cfs_rq, curr); + delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; + if (delta_exec > ideal_runtime) { +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + /* + * The current task ran long enough, ensure it doesn't get + * re-elected due to buddy favours. +@@ -3225,7 +3225,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq + return; + + if (delta > ideal_runtime) +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + } + + static void +@@ -3366,7 +3366,7 @@ entity_tick(struct cfs_rq *cfs_rq, struc + * validating it and just reschedule. + */ + if (queued) { +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + return; + } + /* +@@ -3557,7 +3557,7 @@ static void __account_cfs_rq_runtime(str + * hierarchy can be throttled + */ + if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr)) +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + } + + static __always_inline +@@ -4180,7 +4180,7 @@ static void hrtick_start_fair(struct rq + + if (delta < 0) { + if (rq->curr == p) +- resched_curr(rq); ++ resched_curr_lazy(rq); + return; + } + hrtick_start(rq, delta); +@@ -5076,7 +5076,7 @@ static void check_preempt_wakeup(struct + return; + + preempt: +- resched_curr(rq); ++ resched_curr_lazy(rq); + /* + * Only set the backward buddy when the current task is still + * on the rq. This can happen when a wakeup gets interleaved +@@ -7866,7 +7866,7 @@ static void task_fork_fair(struct task_s + * 'current' within the tree based on its new key value. + */ + swap(curr->vruntime, se->vruntime); +- resched_curr(rq); ++ resched_curr_lazy(rq); + } + + se->vruntime -= cfs_rq->min_vruntime; +@@ -7891,7 +7891,7 @@ prio_changed_fair(struct rq *rq, struct + */ + if (rq->curr == p) { + if (p->prio > oldprio) +- resched_curr(rq); ++ resched_curr_lazy(rq); + } else + check_preempt_curr(rq, p, 0); + } +--- a/kernel/sched/features.h ++++ b/kernel/sched/features.h +@@ -52,6 +52,9 @@ SCHED_FEAT(NONTASK_CAPACITY, true) + + #ifdef CONFIG_PREEMPT_RT_FULL + SCHED_FEAT(TTWU_QUEUE, false) ++# ifdef CONFIG_PREEMPT_LAZY ++SCHED_FEAT(PREEMPT_LAZY, true) ++# endif + #else + + /* +--- a/kernel/sched/sched.h ++++ b/kernel/sched/sched.h +@@ -1290,6 +1290,15 @@ extern void init_sched_dl_class(void); + extern void resched_curr(struct rq *rq); + extern void resched_cpu(int cpu); + ++#ifdef CONFIG_PREEMPT_LAZY ++extern void resched_curr_lazy(struct rq *rq); ++#else ++static inline void resched_curr_lazy(struct rq *rq) ++{ ++ resched_curr(rq); ++} ++#endif ++ + extern struct rt_bandwidth def_rt_bandwidth; + extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); + +--- a/kernel/trace/trace.c ++++ b/kernel/trace/trace.c +@@ -1630,6 +1630,7 @@ tracing_generic_entry_update(struct trac + struct task_struct *tsk = current; + + entry->preempt_count = pc & 0xff; ++ entry->preempt_lazy_count = preempt_lazy_count(); + entry->pid = (tsk) ? tsk->pid : 0; + entry->flags = + #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT +@@ -1639,7 +1640,8 @@ tracing_generic_entry_update(struct trac + #endif + ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | + ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | +- (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) | ++ (tif_need_resched_now() ? TRACE_FLAG_NEED_RESCHED : 0) | ++ (need_resched_lazy() ? TRACE_FLAG_NEED_RESCHED_LAZY : 0) | + (test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0); + + entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 0; +@@ -2560,15 +2562,17 @@ get_total_entries(struct trace_buffer *b + + static void print_lat_help_header(struct seq_file *m) + { +- seq_puts(m, "# _------=> CPU# \n" +- "# / _-----=> irqs-off \n" +- "# | / _----=> need-resched \n" +- "# || / _---=> hardirq/softirq \n" +- "# ||| / _--=> preempt-depth \n" +- "# |||| / _--=> migrate-disable\n" +- "# ||||| / delay \n" +- "# cmd pid |||||| time | caller \n" +- "# \\ / ||||| \\ | / \n"); ++ seq_puts(m, "# _--------=> CPU# \n" ++ "# / _-------=> irqs-off \n" ++ "# | / _------=> need-resched \n" ++ "# || / _-----=> need-resched_lazy \n" ++ "# ||| / _----=> hardirq/softirq \n" ++ "# |||| / _---=> preempt-depth \n" ++ "# ||||| / _--=> preempt-lazy-depth\n" ++ "# |||||| / _-=> migrate-disable \n" ++ "# ||||||| / delay \n" ++ "# cmd pid |||||||| time | caller \n" ++ "# \\ / |||||||| \\ | / \n"); + } + + static void print_event_info(struct trace_buffer *buf, struct seq_file *m) +@@ -2594,11 +2598,14 @@ static void print_func_help_header_irq(s + print_event_info(buf, m); + seq_puts(m, "# _-----=> irqs-off\n" + "# / _----=> need-resched\n" +- "# | / _---=> hardirq/softirq\n" +- "# || / _--=> preempt-depth\n" +- "# ||| / delay\n" +- "# TASK-PID CPU# |||| TIMESTAMP FUNCTION\n" +- "# | | | |||| | |\n"); ++ "# |/ _-----=> need-resched_lazy\n" ++ "# || / _---=> hardirq/softirq\n" ++ "# ||| / _--=> preempt-depth\n" ++ "# |||| /_--=> preempt-lazy-depth\n" ++ "# ||||| _-=> migrate-disable \n" ++ "# ||||| / delay\n" ++ "# TASK-PID CPU# |||||| TIMESTAMP FUNCTION\n" ++ "# | | | |||||| | |\n"); + } + + void +--- a/kernel/trace/trace.h ++++ b/kernel/trace/trace.h +@@ -120,6 +120,7 @@ struct kretprobe_trace_entry_head { + * NEED_RESCHED - reschedule is requested + * HARDIRQ - inside an interrupt handler + * SOFTIRQ - inside a softirq handler ++ * NEED_RESCHED_LAZY - lazy reschedule is requested + */ + enum trace_flag_type { + TRACE_FLAG_IRQS_OFF = 0x01, +@@ -128,6 +129,7 @@ enum trace_flag_type { + TRACE_FLAG_HARDIRQ = 0x08, + TRACE_FLAG_SOFTIRQ = 0x10, + TRACE_FLAG_PREEMPT_RESCHED = 0x20, ++ TRACE_FLAG_NEED_RESCHED_LAZY = 0x40, + }; + + #define TRACE_BUF_SIZE 1024 +--- a/kernel/trace/trace_output.c ++++ b/kernel/trace/trace_output.c +@@ -430,6 +430,7 @@ int trace_print_lat_fmt(struct trace_seq + { + char hardsoft_irq; + char need_resched; ++ char need_resched_lazy; + char irqs_off; + int hardirq; + int softirq; +@@ -457,6 +458,8 @@ int trace_print_lat_fmt(struct trace_seq + need_resched = '.'; + break; + } ++ need_resched_lazy = ++ (entry->flags & TRACE_FLAG_NEED_RESCHED_LAZY) ? 'L' : '.'; + + hardsoft_irq = + (hardirq && softirq) ? 'H' : +@@ -464,14 +467,20 @@ int trace_print_lat_fmt(struct trace_seq + softirq ? 's' : + '.'; + +- trace_seq_printf(s, "%c%c%c", +- irqs_off, need_resched, hardsoft_irq); ++ trace_seq_printf(s, "%c%c%c%c", ++ irqs_off, need_resched, need_resched_lazy, ++ hardsoft_irq); + + if (entry->preempt_count) + trace_seq_printf(s, "%x", entry->preempt_count); + else + trace_seq_putc(s, '.'); + ++ if (entry->preempt_lazy_count) ++ trace_seq_printf(s, "%x", entry->preempt_lazy_count); ++ else ++ trace_seq_putc(s, '.'); ++ + if (entry->migrate_disable) + trace_seq_printf(s, "%x", entry->migrate_disable); + else diff --git a/debian/patches/features/all/rt/preempt-nort-rt-variants.patch b/debian/patches/features/all/rt/preempt-nort-rt-variants.patch new file mode 100644 index 000000000..f6a21d56c --- /dev/null +++ b/debian/patches/features/all/rt/preempt-nort-rt-variants.patch @@ -0,0 +1,48 @@ +From: Thomas Gleixner +Date: Fri, 24 Jul 2009 12:38:56 +0200 +Subject: preempt: Provide preempt_*_(no)rt variants +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +RT needs a few preempt_disable/enable points which are not necessary +otherwise. Implement variants to avoid #ifdeffery. + +Signed-off-by: Thomas Gleixner + +--- + include/linux/preempt.h | 18 +++++++++++++++++- + 1 file changed, 17 insertions(+), 1 deletion(-) + +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -47,7 +47,11 @@ do { \ + preempt_count_dec(); \ + } while (0) + +-#define preempt_enable_no_resched() sched_preempt_enable_no_resched() ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define preempt_enable_no_resched() sched_preempt_enable_no_resched() ++#else ++# define preempt_enable_no_resched() preempt_enable() ++#endif + + #ifdef CONFIG_PREEMPT + #define preempt_enable() \ +@@ -144,6 +148,18 @@ do { \ + set_preempt_need_resched(); \ + } while (0) + ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define preempt_disable_rt() preempt_disable() ++# define preempt_enable_rt() preempt_enable() ++# define preempt_disable_nort() barrier() ++# define preempt_enable_nort() barrier() ++#else ++# define preempt_disable_rt() barrier() ++# define preempt_enable_rt() barrier() ++# define preempt_disable_nort() preempt_disable() ++# define preempt_enable_nort() preempt_enable() ++#endif ++ + #ifdef CONFIG_PREEMPT_NOTIFIERS + + struct preempt_notifier; diff --git a/debian/patches/features/all/rt/printk-27force_early_printk-27-boot-param-to-help-with-debugging.patch b/debian/patches/features/all/rt/printk-27force_early_printk-27-boot-param-to-help-with-debugging.patch new file mode 100644 index 000000000..aa50f0d4f --- /dev/null +++ b/debian/patches/features/all/rt/printk-27force_early_printk-27-boot-param-to-help-with-debugging.patch @@ -0,0 +1,32 @@ +Subject: printk: Add "force_early_printk" boot param to help with debugging +From: Peter Zijlstra +Date: Fri, 02 Sep 2011 14:41:29 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Gives me an option to screw printk and actually see what the machine +says. + +Signed-off-by: Peter Zijlstra +Link: http://lkml.kernel.org/r/1314967289.1301.11.camel@twins +Signed-off-by: Thomas Gleixner +Link: http://lkml.kernel.org/n/tip-ykb97nsfmobq44xketrxs977@git.kernel.org +--- + kernel/printk/printk.c | 7 +++++++ + 1 file changed, 7 insertions(+) + +--- a/kernel/printk/printk.c ++++ b/kernel/printk/printk.c +@@ -1640,6 +1640,13 @@ asmlinkage void early_printk(const char + */ + static bool __read_mostly printk_killswitch; + ++static int __init force_early_printk_setup(char *str) ++{ ++ printk_killswitch = true; ++ return 0; ++} ++early_param("force_early_printk", force_early_printk_setup); ++ + void printk_kill(void) + { + printk_killswitch = true; diff --git a/debian/patches/features/all/rt/printk-kill.patch b/debian/patches/features/all/rt/printk-kill.patch new file mode 100644 index 000000000..b934d178a --- /dev/null +++ b/debian/patches/features/all/rt/printk-kill.patch @@ -0,0 +1,163 @@ +Subject: printk: Add a printk kill switch +From: Ingo Molnar +Date: Fri, 22 Jul 2011 17:58:40 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Add a prinkt-kill-switch. This is used from (NMI) watchdog to ensure that +it does not dead-lock with the early printk code. + +Signed-off-by: Thomas Gleixner +--- + include/linux/printk.h | 2 + + kernel/printk/printk.c | 76 ++++++++++++++++++++++++++++++++++++------------- + kernel/watchdog.c | 14 +++++++-- + 3 files changed, 70 insertions(+), 22 deletions(-) + +--- a/include/linux/printk.h ++++ b/include/linux/printk.h +@@ -115,9 +115,11 @@ int no_printk(const char *fmt, ...) + #ifdef CONFIG_EARLY_PRINTK + extern asmlinkage __printf(1, 2) + void early_printk(const char *fmt, ...); ++extern void printk_kill(void); + #else + static inline __printf(1, 2) __cold + void early_printk(const char *s, ...) { } ++static inline void printk_kill(void) { } + #endif + + typedef int(*printk_func_t)(const char *fmt, va_list args); +--- a/kernel/printk/printk.c ++++ b/kernel/printk/printk.c +@@ -1610,6 +1610,55 @@ static size_t cont_print_text(char *text + return textlen; + } + ++#ifdef CONFIG_EARLY_PRINTK ++struct console *early_console; ++ ++static void early_vprintk(const char *fmt, va_list ap) ++{ ++ if (early_console) { ++ char buf[512]; ++ int n = vscnprintf(buf, sizeof(buf), fmt, ap); ++ ++ early_console->write(early_console, buf, n); ++ } ++} ++ ++asmlinkage void early_printk(const char *fmt, ...) ++{ ++ va_list ap; ++ ++ va_start(ap, fmt); ++ early_vprintk(fmt, ap); ++ va_end(ap); ++} ++ ++/* ++ * This is independent of any log levels - a global ++ * kill switch that turns off all of printk. ++ * ++ * Used by the NMI watchdog if early-printk is enabled. ++ */ ++static bool __read_mostly printk_killswitch; ++ ++void printk_kill(void) ++{ ++ printk_killswitch = true; ++} ++ ++static int forced_early_printk(const char *fmt, va_list ap) ++{ ++ if (!printk_killswitch) ++ return 0; ++ early_vprintk(fmt, ap); ++ return 1; ++} ++#else ++static inline int forced_early_printk(const char *fmt, va_list ap) ++{ ++ return 0; ++} ++#endif ++ + asmlinkage int vprintk_emit(int facility, int level, + const char *dict, size_t dictlen, + const char *fmt, va_list args) +@@ -1626,6 +1675,13 @@ asmlinkage int vprintk_emit(int facility + /* cpu currently holding logbuf_lock in this function */ + static unsigned int logbuf_cpu = UINT_MAX; + ++ /* ++ * Fall back to early_printk if a debugging subsystem has ++ * killed printk output ++ */ ++ if (unlikely(forced_early_printk(fmt, args))) ++ return 1; ++ + if (level == LOGLEVEL_SCHED) { + level = LOGLEVEL_DEFAULT; + in_sched = true; +@@ -1905,26 +1961,6 @@ DEFINE_PER_CPU(printk_func_t, printk_fun + + #endif /* CONFIG_PRINTK */ + +-#ifdef CONFIG_EARLY_PRINTK +-struct console *early_console; +- +-asmlinkage __visible void early_printk(const char *fmt, ...) +-{ +- va_list ap; +- char buf[512]; +- int n; +- +- if (!early_console) +- return; +- +- va_start(ap, fmt); +- n = vscnprintf(buf, sizeof(buf), fmt, ap); +- va_end(ap); +- +- early_console->write(early_console, buf, n); +-} +-#endif +- + static int __add_preferred_console(char *name, int idx, char *options, + char *brl_options) + { +--- a/kernel/watchdog.c ++++ b/kernel/watchdog.c +@@ -262,6 +262,8 @@ static int is_softlockup(unsigned long t + + #ifdef CONFIG_HARDLOCKUP_DETECTOR + ++static DEFINE_RAW_SPINLOCK(watchdog_output_lock); ++ + static struct perf_event_attr wd_hw_attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, +@@ -295,13 +297,21 @@ static void watchdog_overflow_callback(s + /* only print hardlockups once */ + if (__this_cpu_read(hard_watchdog_warn) == true) + return; ++ /* ++ * If early-printk is enabled then make sure we do not ++ * lock up in printk() and kill console logging: ++ */ ++ printk_kill(); + +- if (hardlockup_panic) ++ if (hardlockup_panic) { + panic("Watchdog detected hard LOCKUP on cpu %d", + this_cpu); +- else ++ } else { ++ raw_spin_lock(&watchdog_output_lock); + WARN(1, "Watchdog detected hard LOCKUP on cpu %d", + this_cpu); ++ raw_spin_unlock(&watchdog_output_lock); ++ } + + __this_cpu_write(hard_watchdog_warn, true); + return; diff --git a/debian/patches/features/all/rt/printk-rt-aware.patch b/debian/patches/features/all/rt/printk-rt-aware.patch new file mode 100644 index 000000000..5c3748233 --- /dev/null +++ b/debian/patches/features/all/rt/printk-rt-aware.patch @@ -0,0 +1,101 @@ +Subject: printk: Make rt aware +From: Thomas Gleixner +Date: Wed, 19 Sep 2012 14:50:37 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Drop the lock before calling the console driver and do not disable +interrupts while printing to a serial console. + +Signed-off-by: Thomas Gleixner +--- + kernel/printk/printk.c | 26 +++++++++++++++++++++++--- + 1 file changed, 23 insertions(+), 3 deletions(-) + +--- a/kernel/printk/printk.c ++++ b/kernel/printk/printk.c +@@ -1404,6 +1404,7 @@ static void call_console_drivers(int lev + if (!console_drivers) + return; + ++ migrate_disable(); + for_each_console(con) { + if (exclusive_console && con != exclusive_console) + continue; +@@ -1416,6 +1417,7 @@ static void call_console_drivers(int lev + continue; + con->write(con, text, len); + } ++ migrate_enable(); + } + + /* +@@ -1476,6 +1478,15 @@ static inline int can_use_console(unsign + static int console_trylock_for_printk(void) + { + unsigned int cpu = smp_processor_id(); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ int lock = !early_boot_irqs_disabled && (preempt_count() == 0) && ++ !irqs_disabled(); ++#else ++ int lock = 1; ++#endif ++ ++ if (!lock) ++ return 0; + + if (!console_trylock()) + return 0; +@@ -1830,8 +1841,7 @@ asmlinkage int vprintk_emit(int facility + * console_sem which would prevent anyone from printing to + * console + */ +- preempt_disable(); +- ++ migrate_disable(); + /* + * Try to acquire and then immediately release the console + * semaphore. The release will print out buffers and wake up +@@ -1839,7 +1849,7 @@ asmlinkage int vprintk_emit(int facility + */ + if (console_trylock_for_printk()) + console_unlock(); +- preempt_enable(); ++ migrate_enable(); + lockdep_on(); + } + +@@ -2189,11 +2199,16 @@ static void console_cont_flush(char *tex + goto out; + + len = cont_print_text(text, size); ++#ifndef CONFIG_PREEMPT_RT_FULL + raw_spin_unlock(&logbuf_lock); + stop_critical_timings(); + call_console_drivers(cont.level, text, len); + start_critical_timings(); + local_irq_restore(flags); ++#else ++ raw_spin_unlock_irqrestore(&logbuf_lock, flags); ++ call_console_drivers(cont.level, text, len); ++#endif + return; + out: + raw_spin_unlock_irqrestore(&logbuf_lock, flags); +@@ -2281,12 +2296,17 @@ void console_unlock(void) + console_idx = log_next(console_idx); + console_seq++; + console_prev = msg->flags; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ raw_spin_unlock_irqrestore(&logbuf_lock, flags); ++ call_console_drivers(level, text, len); ++#else + raw_spin_unlock(&logbuf_lock); + + stop_critical_timings(); /* don't trace print latency */ + call_console_drivers(level, text, len); + start_critical_timings(); + local_irq_restore(flags); ++#endif + } + console_locked = 0; + diff --git a/debian/patches/features/all/rt/ptrace-fix-ptrace-vs-tasklist_lock-race.patch b/debian/patches/features/all/rt/ptrace-fix-ptrace-vs-tasklist_lock-race.patch new file mode 100644 index 000000000..6677ac927 --- /dev/null +++ b/debian/patches/features/all/rt/ptrace-fix-ptrace-vs-tasklist_lock-race.patch @@ -0,0 +1,161 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 29 Aug 2013 18:21:04 +0200 +Subject: ptrace: fix ptrace vs tasklist_lock race +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +As explained by Alexander Fyodorov : + +|read_lock(&tasklist_lock) in ptrace_stop() is converted to mutex on RT kernel, +|and it can remove __TASK_TRACED from task->state (by moving it to +|task->saved_state). If parent does wait() on child followed by a sys_ptrace +|call, the following race can happen: +| +|- child sets __TASK_TRACED in ptrace_stop() +|- parent does wait() which eventually calls wait_task_stopped() and returns +| child's pid +|- child blocks on read_lock(&tasklist_lock) in ptrace_stop() and moves +| __TASK_TRACED flag to saved_state +|- parent calls sys_ptrace, which calls ptrace_check_attach() and wait_task_inactive() + +The patch is based on his initial patch where an additional check is +added in case the __TASK_TRACED moved to ->saved_state. The pi_lock is +taken in case the caller is interrupted between looking into ->state and +->saved_state. + +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/sched.h | 48 +++++++++++++++++++++++++++++++++++++++++++++--- + kernel/ptrace.c | 7 ++++++- + kernel/sched/core.c | 19 ++++++++++++++++--- + 3 files changed, 67 insertions(+), 7 deletions(-) + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -234,10 +234,7 @@ extern char ___assert_task_state[1 - 2*! + TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \ + __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD) + +-#define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) + #define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0) +-#define task_is_stopped_or_traced(task) \ +- ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0) + #define task_contributes_to_load(task) \ + ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \ + (task->flags & PF_FROZEN) == 0) +@@ -2918,6 +2915,51 @@ static inline int signal_pending_state(l + return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); + } + ++static inline bool __task_is_stopped_or_traced(struct task_struct *task) ++{ ++ if (task->state & (__TASK_STOPPED | __TASK_TRACED)) ++ return true; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (task->saved_state & (__TASK_STOPPED | __TASK_TRACED)) ++ return true; ++#endif ++ return false; ++} ++ ++static inline bool task_is_stopped_or_traced(struct task_struct *task) ++{ ++ bool traced_stopped; ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&task->pi_lock, flags); ++ traced_stopped = __task_is_stopped_or_traced(task); ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); ++#else ++ traced_stopped = __task_is_stopped_or_traced(task); ++#endif ++ return traced_stopped; ++} ++ ++static inline bool task_is_traced(struct task_struct *task) ++{ ++ bool traced = false; ++ ++ if (task->state & __TASK_TRACED) ++ return true; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* in case the task is sleeping on tasklist_lock */ ++ raw_spin_lock_irq(&task->pi_lock); ++ if (task->state & __TASK_TRACED) ++ traced = true; ++ else if (task->saved_state & __TASK_TRACED) ++ traced = true; ++ raw_spin_unlock_irq(&task->pi_lock); ++#endif ++ return traced; ++} ++ + /* + * cond_resched() and cond_resched_lock(): latency reduction via + * explicit rescheduling in places that are safe. The return +--- a/kernel/ptrace.c ++++ b/kernel/ptrace.c +@@ -129,7 +129,12 @@ static bool ptrace_freeze_traced(struct + + spin_lock_irq(&task->sighand->siglock); + if (task_is_traced(task) && !__fatal_signal_pending(task)) { +- task->state = __TASK_TRACED; ++ raw_spin_lock_irq(&task->pi_lock); ++ if (task->state & __TASK_TRACED) ++ task->state = __TASK_TRACED; ++ else ++ task->saved_state = __TASK_TRACED; ++ raw_spin_unlock_irq(&task->pi_lock); + ret = true; + } + spin_unlock_irq(&task->sighand->siglock); +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -1219,6 +1219,18 @@ struct migration_arg { + + static int migration_cpu_stop(void *data); + ++static bool check_task_state(struct task_struct *p, long match_state) ++{ ++ bool match = false; ++ ++ raw_spin_lock_irq(&p->pi_lock); ++ if (p->state == match_state || p->saved_state == match_state) ++ match = true; ++ raw_spin_unlock_irq(&p->pi_lock); ++ ++ return match; ++} ++ + /* + * wait_task_inactive - wait for a thread to unschedule. + * +@@ -1263,7 +1275,7 @@ unsigned long wait_task_inactive(struct + * is actually now running somewhere else! + */ + while (task_running(rq, p)) { +- if (match_state && unlikely(p->state != match_state)) ++ if (match_state && !check_task_state(p, match_state)) + return 0; + cpu_relax(); + } +@@ -1278,7 +1290,8 @@ unsigned long wait_task_inactive(struct + running = task_running(rq, p); + queued = task_on_rq_queued(p); + ncsw = 0; +- if (!match_state || p->state == match_state) ++ if (!match_state || p->state == match_state || ++ p->saved_state == match_state) + ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ + task_rq_unlock(rq, p, &flags); + +@@ -1833,7 +1846,7 @@ static void try_to_wake_up_local(struct + */ + int wake_up_process(struct task_struct *p) + { +- WARN_ON(task_is_stopped_or_traced(p)); ++ WARN_ON(__task_is_stopped_or_traced(p)); + return try_to_wake_up(p, TASK_NORMAL, 0); + } + EXPORT_SYMBOL(wake_up_process); diff --git a/debian/patches/features/all/rt/radix-tree-rt-aware.patch b/debian/patches/features/all/rt/radix-tree-rt-aware.patch new file mode 100644 index 000000000..142bb3f98 --- /dev/null +++ b/debian/patches/features/all/rt/radix-tree-rt-aware.patch @@ -0,0 +1,73 @@ +From: Thomas Gleixner +Date: Sun, 17 Jul 2011 21:33:18 +0200 +Subject: radix-tree: Make RT aware +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Disable radix_tree_preload() on -RT. This functions returns with +preemption disabled which may cause high latencies and breaks if the +user tries to grab any locks after invoking it. + +Signed-off-by: Thomas Gleixner +--- + include/linux/radix-tree.h | 7 ++++++- + lib/radix-tree.c | 5 ++++- + 2 files changed, 10 insertions(+), 2 deletions(-) + +--- a/include/linux/radix-tree.h ++++ b/include/linux/radix-tree.h +@@ -277,8 +277,13 @@ radix_tree_gang_lookup(struct radix_tree + unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root, + void ***results, unsigned long *indices, + unsigned long first_index, unsigned int max_items); ++#ifndef CONFIG_PREEMPT_RT_FULL + int radix_tree_preload(gfp_t gfp_mask); + int radix_tree_maybe_preload(gfp_t gfp_mask); ++#else ++static inline int radix_tree_preload(gfp_t gm) { return 0; } ++static inline int radix_tree_maybe_preload(gfp_t gfp_mask) { return 0; } ++#endif + void radix_tree_init(void); + void *radix_tree_tag_set(struct radix_tree_root *root, + unsigned long index, unsigned int tag); +@@ -303,7 +308,7 @@ unsigned long radix_tree_locate_item(str + + static inline void radix_tree_preload_end(void) + { +- preempt_enable(); ++ preempt_enable_nort(); + } + + /** +--- a/lib/radix-tree.c ++++ b/lib/radix-tree.c +@@ -195,12 +195,13 @@ radix_tree_node_alloc(struct radix_tree_ + * succeed in getting a node here (and never reach + * kmem_cache_alloc) + */ +- rtp = this_cpu_ptr(&radix_tree_preloads); ++ rtp = &get_cpu_var(radix_tree_preloads); + if (rtp->nr) { + ret = rtp->nodes[rtp->nr - 1]; + rtp->nodes[rtp->nr - 1] = NULL; + rtp->nr--; + } ++ put_cpu_var(radix_tree_preloads); + /* + * Update the allocation stack trace as this is more useful + * for debugging. +@@ -240,6 +241,7 @@ radix_tree_node_free(struct radix_tree_n + call_rcu(&node->rcu_head, radix_tree_node_rcu_free); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Load up this CPU's radix_tree_node buffer with sufficient objects to + * ensure that the addition of a single element in the tree cannot fail. On +@@ -305,6 +307,7 @@ int radix_tree_maybe_preload(gfp_t gfp_m + return 0; + } + EXPORT_SYMBOL(radix_tree_maybe_preload); ++#endif + + /* + * Return the maximum key which can be store into a diff --git a/debian/patches/features/all/rt/random-make-it-work-on-rt.patch b/debian/patches/features/all/rt/random-make-it-work-on-rt.patch new file mode 100644 index 000000000..5a3b37427 --- /dev/null +++ b/debian/patches/features/all/rt/random-make-it-work-on-rt.patch @@ -0,0 +1,116 @@ +Subject: random: Make it work on rt +From: Thomas Gleixner +Date: Tue, 21 Aug 2012 20:38:50 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Delegate the random insertion to the forced threaded interrupt +handler. Store the return IP of the hard interrupt handler in the irq +descriptor and feed it into the random generator as a source of +entropy. + +Signed-off-by: Thomas Gleixner + +--- + drivers/char/random.c | 11 +++++------ + include/linux/irqdesc.h | 1 + + include/linux/random.h | 2 +- + kernel/irq/handle.c | 8 +++++++- + kernel/irq/manage.c | 6 ++++++ + 5 files changed, 20 insertions(+), 8 deletions(-) + +--- a/drivers/char/random.c ++++ b/drivers/char/random.c +@@ -868,28 +868,27 @@ static __u32 get_reg(struct fast_pool *f + return *(ptr + f->reg_idx++); + } + +-void add_interrupt_randomness(int irq, int irq_flags) ++void add_interrupt_randomness(int irq, int irq_flags, __u64 ip) + { + struct entropy_store *r; + struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness); +- struct pt_regs *regs = get_irq_regs(); + unsigned long now = jiffies; + cycles_t cycles = random_get_entropy(); + __u32 c_high, j_high; +- __u64 ip; + unsigned long seed; + int credit = 0; + + if (cycles == 0) +- cycles = get_reg(fast_pool, regs); ++ cycles = get_reg(fast_pool, NULL); + c_high = (sizeof(cycles) > 4) ? cycles >> 32 : 0; + j_high = (sizeof(now) > 4) ? now >> 32 : 0; + fast_pool->pool[0] ^= cycles ^ j_high ^ irq; + fast_pool->pool[1] ^= now ^ c_high; +- ip = regs ? instruction_pointer(regs) : _RET_IP_; ++ if (!ip) ++ ip = _RET_IP_; + fast_pool->pool[2] ^= ip; + fast_pool->pool[3] ^= (sizeof(ip) > 4) ? ip >> 32 : +- get_reg(fast_pool, regs); ++ get_reg(fast_pool, NULL); + + fast_mix(fast_pool); + add_interrupt_bench(cycles); +--- a/include/linux/irqdesc.h ++++ b/include/linux/irqdesc.h +@@ -63,6 +63,7 @@ struct irq_desc { + unsigned int irqs_unhandled; + atomic_t threads_handled; + int threads_handled_last; ++ u64 random_ip; + raw_spinlock_t lock; + struct cpumask *percpu_enabled; + #ifdef CONFIG_SMP +--- a/include/linux/random.h ++++ b/include/linux/random.h +@@ -11,7 +11,7 @@ + extern void add_device_randomness(const void *, unsigned int); + extern void add_input_randomness(unsigned int type, unsigned int code, + unsigned int value); +-extern void add_interrupt_randomness(int irq, int irq_flags); ++extern void add_interrupt_randomness(int irq, int irq_flags, __u64 ip); + + extern void get_random_bytes(void *buf, int nbytes); + extern void get_random_bytes_arch(void *buf, int nbytes); +--- a/kernel/irq/handle.c ++++ b/kernel/irq/handle.c +@@ -133,6 +133,8 @@ void __irq_wake_thread(struct irq_desc * + irqreturn_t + handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) + { ++ struct pt_regs *regs = get_irq_regs(); ++ u64 ip = regs ? instruction_pointer(regs) : 0; + irqreturn_t retval = IRQ_NONE; + unsigned int flags = 0, irq = desc->irq_data.irq; + +@@ -173,7 +175,11 @@ handle_irq_event_percpu(struct irq_desc + action = action->next; + } while (action); + +- add_interrupt_randomness(irq, flags); ++#ifndef CONFIG_PREEMPT_RT_FULL ++ add_interrupt_randomness(irq, flags, ip); ++#else ++ desc->random_ip = ip; ++#endif + + if (!noirqdebug) + note_interrupt(irq, desc, retval); +--- a/kernel/irq/manage.c ++++ b/kernel/irq/manage.c +@@ -991,6 +991,12 @@ static int irq_thread(void *data) + if (action_ret == IRQ_HANDLED) + atomic_inc(&desc->threads_handled); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ migrate_disable(); ++ add_interrupt_randomness(action->irq, 0, ++ desc->random_ip ^ (unsigned long) action); ++ migrate_enable(); ++#endif + wake_threads_waitq(desc); + } + diff --git a/debian/patches/features/all/rt/rcu-Eliminate-softirq-processing-from-rcutree.patch b/debian/patches/features/all/rt/rcu-Eliminate-softirq-processing-from-rcutree.patch new file mode 100644 index 000000000..700ba5553 --- /dev/null +++ b/debian/patches/features/all/rt/rcu-Eliminate-softirq-processing-from-rcutree.patch @@ -0,0 +1,423 @@ +From: "Paul E. McKenney" +Date: Mon, 4 Nov 2013 13:21:10 -0800 +Subject: rcu: Eliminate softirq processing from rcutree +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Running RCU out of softirq is a problem for some workloads that would +like to manage RCU core processing independently of other softirq work, +for example, setting kthread priority. This commit therefore moves the +RCU core work from softirq to a per-CPU/per-flavor SCHED_OTHER kthread +named rcuc. The SCHED_OTHER approach avoids the scalability problems +that appeared with the earlier attempt to move RCU core processing to +from softirq to kthreads. That said, kernels built with RCU_BOOST=y +will run the rcuc kthreads at the RCU-boosting priority. + +Reported-by: Thomas Gleixner +Tested-by: Mike Galbraith +Signed-off-by: Paul E. McKenney +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/rcu/tree.c | 110 +++++++++++++++++++++++++++++++++--- + kernel/rcu/tree.h | 5 - + kernel/rcu/tree_plugin.h | 141 +++++------------------------------------------ + 3 files changed, 116 insertions(+), 140 deletions(-) + +--- a/kernel/rcu/tree.c ++++ b/kernel/rcu/tree.c +@@ -56,6 +56,11 @@ + #include + #include + #include ++#include ++#include ++#include ++#include ++#include "../time/tick-internal.h" + + #include "tree.h" + #include "rcu.h" +@@ -2882,18 +2887,17 @@ static void + /* + * Do RCU core processing for the current CPU. + */ +-static void rcu_process_callbacks(struct softirq_action *unused) ++static void rcu_process_callbacks(void) + { + struct rcu_state *rsp; + + if (cpu_is_offline(smp_processor_id())) + return; +- trace_rcu_utilization(TPS("Start RCU core")); + for_each_rcu_flavor(rsp) + __rcu_process_callbacks(rsp); +- trace_rcu_utilization(TPS("End RCU core")); + } + ++static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); + /* + * Schedule RCU callback invocation. If the specified type of RCU + * does not support RCU priority boosting, just do a direct call, +@@ -2905,18 +2909,105 @@ static void invoke_rcu_callbacks(struct + { + if (unlikely(!ACCESS_ONCE(rcu_scheduler_fully_active))) + return; +- if (likely(!rsp->boost)) { +- rcu_do_batch(rsp, rdp); ++ rcu_do_batch(rsp, rdp); ++} ++ ++static void rcu_wake_cond(struct task_struct *t, int status) ++{ ++ /* ++ * If the thread is yielding, only wake it when this ++ * is invoked from idle ++ */ ++ if (t && (status != RCU_KTHREAD_YIELDING || is_idle_task(current))) ++ wake_up_process(t); ++} ++ ++/* ++ * Wake up this CPU's rcuc kthread to do RCU core processing. ++ */ ++static void invoke_rcu_core(void) ++{ ++ unsigned long flags; ++ struct task_struct *t; ++ ++ if (!cpu_online(smp_processor_id())) + return; ++ local_irq_save(flags); ++ __this_cpu_write(rcu_cpu_has_work, 1); ++ t = __this_cpu_read(rcu_cpu_kthread_task); ++ if (t != NULL && current != t) ++ rcu_wake_cond(t, __this_cpu_read(rcu_cpu_kthread_status)); ++ local_irq_restore(flags); ++} ++ ++static void rcu_cpu_kthread_park(unsigned int cpu) ++{ ++ per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; ++} ++ ++static int rcu_cpu_kthread_should_run(unsigned int cpu) ++{ ++ return __this_cpu_read(rcu_cpu_has_work); ++} ++ ++/* ++ * Per-CPU kernel thread that invokes RCU callbacks. This replaces the ++ * RCU softirq used in flavors and configurations of RCU that do not ++ * support RCU priority boosting. ++ */ ++static void rcu_cpu_kthread(unsigned int cpu) ++{ ++ unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status); ++ char work, *workp = this_cpu_ptr(&rcu_cpu_has_work); ++ int spincnt; ++ ++ for (spincnt = 0; spincnt < 10; spincnt++) { ++ trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait")); ++ local_bh_disable(); ++ *statusp = RCU_KTHREAD_RUNNING; ++ this_cpu_inc(rcu_cpu_kthread_loops); ++ local_irq_disable(); ++ work = *workp; ++ *workp = 0; ++ local_irq_enable(); ++ if (work) ++ rcu_process_callbacks(); ++ local_bh_enable(); ++ if (*workp == 0) { ++ trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); ++ *statusp = RCU_KTHREAD_WAITING; ++ return; ++ } + } +- invoke_rcu_callbacks_kthread(); ++ *statusp = RCU_KTHREAD_YIELDING; ++ trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); ++ schedule_timeout_interruptible(2); ++ trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); ++ *statusp = RCU_KTHREAD_WAITING; + } + +-static void invoke_rcu_core(void) ++static struct smp_hotplug_thread rcu_cpu_thread_spec = { ++ .store = &rcu_cpu_kthread_task, ++ .thread_should_run = rcu_cpu_kthread_should_run, ++ .thread_fn = rcu_cpu_kthread, ++ .thread_comm = "rcuc/%u", ++ .setup = rcu_cpu_kthread_setup, ++ .park = rcu_cpu_kthread_park, ++}; ++ ++/* ++ * Spawn per-CPU RCU core processing kthreads. ++ */ ++static int __init rcu_spawn_core_kthreads(void) + { +- if (cpu_online(smp_processor_id())) +- raise_softirq(RCU_SOFTIRQ); ++ int cpu; ++ ++ for_each_possible_cpu(cpu) ++ per_cpu(rcu_cpu_has_work, cpu) = 0; ++ BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); ++ return 0; + } ++early_initcall(rcu_spawn_core_kthreads); + + /* + * Handle any core-RCU processing required by a call_rcu() invocation. +@@ -4148,7 +4239,6 @@ void __init rcu_init(void) + rcu_init_one(&rcu_bh_state, &rcu_bh_data); + rcu_init_one(&rcu_sched_state, &rcu_sched_data); + __rcu_init_preempt(); +- open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); + + /* + * We don't need protection against CPU-hotplug here because +--- a/kernel/rcu/tree.h ++++ b/kernel/rcu/tree.h +@@ -530,12 +530,10 @@ extern struct rcu_state rcu_preempt_stat + DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data); + #endif /* #ifdef CONFIG_PREEMPT_RCU */ + +-#ifdef CONFIG_RCU_BOOST + DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status); + DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu); + DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); + DECLARE_PER_CPU(char, rcu_cpu_has_work); +-#endif /* #ifdef CONFIG_RCU_BOOST */ + + #ifndef RCU_TREE_NONCORE + +@@ -554,10 +552,9 @@ void call_rcu(struct rcu_head *head, voi + static void __init __rcu_init_preempt(void); + static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); + static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); +-static void invoke_rcu_callbacks_kthread(void); + static bool rcu_is_callbacks_kthread(void); ++static void rcu_cpu_kthread_setup(unsigned int cpu); + #ifdef CONFIG_RCU_BOOST +-static void rcu_preempt_do_callbacks(void); + static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, + struct rcu_node *rnp); + #endif /* #ifdef CONFIG_RCU_BOOST */ +--- a/kernel/rcu/tree_plugin.h ++++ b/kernel/rcu/tree_plugin.h +@@ -24,28 +24,20 @@ + * Paul E. McKenney + */ + +-#include +-#include +-#include +-#include +-#include +-#include "../time/tick-internal.h" +- + #ifdef CONFIG_RCU_BOOST + + #include "../locking/rtmutex_common.h" + ++#endif /* #ifdef CONFIG_RCU_BOOST */ ++ + /* + * Control variables for per-CPU and per-rcu_node kthreads. These + * handle all flavors of RCU. + */ +-static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); + DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status); + DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); + DEFINE_PER_CPU(char, rcu_cpu_has_work); + +-#endif /* #ifdef CONFIG_RCU_BOOST */ +- + #ifdef CONFIG_RCU_NOCB_CPU + static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */ + static bool have_rcu_nocb_mask; /* Was rcu_nocb_mask allocated? */ +@@ -497,15 +489,6 @@ static void rcu_preempt_check_callbacks( + t->rcu_read_unlock_special.b.need_qs = true; + } + +-#ifdef CONFIG_RCU_BOOST +- +-static void rcu_preempt_do_callbacks(void) +-{ +- rcu_do_batch(&rcu_preempt_state, this_cpu_ptr(&rcu_preempt_data)); +-} +- +-#endif /* #ifdef CONFIG_RCU_BOOST */ +- + /* + * Queue a preemptible-RCU callback for invocation after a grace period. + */ +@@ -940,6 +923,19 @@ void exit_rcu(void) + + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + ++/* ++ * If boosting, set rcuc kthreads to realtime priority. ++ */ ++static void rcu_cpu_kthread_setup(unsigned int cpu) ++{ ++#ifdef CONFIG_RCU_BOOST ++ struct sched_param sp; ++ ++ sp.sched_priority = kthread_prio; ++ sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); ++#endif /* #ifdef CONFIG_RCU_BOOST */ ++} ++ + #ifdef CONFIG_RCU_BOOST + + #include "../locking/rtmutex_common.h" +@@ -971,16 +967,6 @@ static void rcu_initiate_boost_trace(str + + #endif /* #else #ifdef CONFIG_RCU_TRACE */ + +-static void rcu_wake_cond(struct task_struct *t, int status) +-{ +- /* +- * If the thread is yielding, only wake it when this +- * is invoked from idle +- */ +- if (status != RCU_KTHREAD_YIELDING || is_idle_task(current)) +- wake_up_process(t); +-} +- + /* + * Carry out RCU priority boosting on the task indicated by ->exp_tasks + * or ->boost_tasks, advancing the pointer to the next task in the +@@ -1126,23 +1112,6 @@ static void rcu_initiate_boost(struct rc + } + + /* +- * Wake up the per-CPU kthread to invoke RCU callbacks. +- */ +-static void invoke_rcu_callbacks_kthread(void) +-{ +- unsigned long flags; +- +- local_irq_save(flags); +- __this_cpu_write(rcu_cpu_has_work, 1); +- if (__this_cpu_read(rcu_cpu_kthread_task) != NULL && +- current != __this_cpu_read(rcu_cpu_kthread_task)) { +- rcu_wake_cond(__this_cpu_read(rcu_cpu_kthread_task), +- __this_cpu_read(rcu_cpu_kthread_status)); +- } +- local_irq_restore(flags); +-} +- +-/* + * Is the current CPU running the RCU-callbacks kthread? + * Caller must have preemption disabled. + */ +@@ -1197,67 +1166,6 @@ static int rcu_spawn_one_boost_kthread(s + return 0; + } + +-static void rcu_kthread_do_work(void) +-{ +- rcu_do_batch(&rcu_sched_state, this_cpu_ptr(&rcu_sched_data)); +- rcu_do_batch(&rcu_bh_state, this_cpu_ptr(&rcu_bh_data)); +- rcu_preempt_do_callbacks(); +-} +- +-static void rcu_cpu_kthread_setup(unsigned int cpu) +-{ +- struct sched_param sp; +- +- sp.sched_priority = kthread_prio; +- sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); +-} +- +-static void rcu_cpu_kthread_park(unsigned int cpu) +-{ +- per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; +-} +- +-static int rcu_cpu_kthread_should_run(unsigned int cpu) +-{ +- return __this_cpu_read(rcu_cpu_has_work); +-} +- +-/* +- * Per-CPU kernel thread that invokes RCU callbacks. This replaces the +- * RCU softirq used in flavors and configurations of RCU that do not +- * support RCU priority boosting. +- */ +-static void rcu_cpu_kthread(unsigned int cpu) +-{ +- unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status); +- char work, *workp = this_cpu_ptr(&rcu_cpu_has_work); +- int spincnt; +- +- for (spincnt = 0; spincnt < 10; spincnt++) { +- trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait")); +- local_bh_disable(); +- *statusp = RCU_KTHREAD_RUNNING; +- this_cpu_inc(rcu_cpu_kthread_loops); +- local_irq_disable(); +- work = *workp; +- *workp = 0; +- local_irq_enable(); +- if (work) +- rcu_kthread_do_work(); +- local_bh_enable(); +- if (*workp == 0) { +- trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); +- *statusp = RCU_KTHREAD_WAITING; +- return; +- } +- } +- *statusp = RCU_KTHREAD_YIELDING; +- trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); +- schedule_timeout_interruptible(2); +- trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); +- *statusp = RCU_KTHREAD_WAITING; +-} +- + /* + * Set the per-rcu_node kthread's affinity to cover all CPUs that are + * served by the rcu_node in question. The CPU hotplug lock is still +@@ -1287,26 +1195,12 @@ static void rcu_boost_kthread_setaffinit + free_cpumask_var(cm); + } + +-static struct smp_hotplug_thread rcu_cpu_thread_spec = { +- .store = &rcu_cpu_kthread_task, +- .thread_should_run = rcu_cpu_kthread_should_run, +- .thread_fn = rcu_cpu_kthread, +- .thread_comm = "rcuc/%u", +- .setup = rcu_cpu_kthread_setup, +- .park = rcu_cpu_kthread_park, +-}; +- + /* + * Spawn boost kthreads -- called as soon as the scheduler is running. + */ + static void __init rcu_spawn_boost_kthreads(void) + { + struct rcu_node *rnp; +- int cpu; +- +- for_each_possible_cpu(cpu) +- per_cpu(rcu_cpu_has_work, cpu) = 0; +- BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); + rcu_for_each_leaf_node(rcu_state_p, rnp) + (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); + } +@@ -1329,11 +1223,6 @@ static void rcu_initiate_boost(struct rc + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } + +-static void invoke_rcu_callbacks_kthread(void) +-{ +- WARN_ON_ONCE(1); +-} +- + static bool rcu_is_callbacks_kthread(void) + { + return false; diff --git a/debian/patches/features/all/rt/rcu-disable-rcu-fast-no-hz-on-rt.patch b/debian/patches/features/all/rt/rcu-disable-rcu-fast-no-hz-on-rt.patch new file mode 100644 index 000000000..f3cd25a85 --- /dev/null +++ b/debian/patches/features/all/rt/rcu-disable-rcu-fast-no-hz-on-rt.patch @@ -0,0 +1,25 @@ +Subject: rcu: Disable RCU_FAST_NO_HZ on RT +From: Thomas Gleixner +Date: Sun, 28 Oct 2012 13:26:09 +0000 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +This uses a timer_list timer from the irq disabled guts of the idle +code. Disable it for now to prevent wreckage. + +Signed-off-by: Thomas Gleixner + +--- + init/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/init/Kconfig ++++ b/init/Kconfig +@@ -637,7 +637,7 @@ config RCU_FANOUT_EXACT + + config RCU_FAST_NO_HZ + bool "Accelerate last non-dyntick-idle CPU's grace periods" +- depends on NO_HZ_COMMON && SMP ++ depends on NO_HZ_COMMON && SMP && !PREEMPT_RT_FULL + default n + help + This option permits CPUs to enter dynticks-idle state even if diff --git a/debian/patches/features/all/rt/rcu-make-RCU_BOOST-default-on-RT.patch b/debian/patches/features/all/rt/rcu-make-RCU_BOOST-default-on-RT.patch new file mode 100644 index 000000000..4f4ffee9d --- /dev/null +++ b/debian/patches/features/all/rt/rcu-make-RCU_BOOST-default-on-RT.patch @@ -0,0 +1,27 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 21 Mar 2014 20:19:05 +0100 +Subject: rcu: make RCU_BOOST default on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Since it is no longer invoked from the softirq people run into OOM more +often if the priority of the RCU thread is too low. Making boosting +default on RT should help in those case and it can be switched off if +someone knows better. + + +Signed-off-by: Sebastian Andrzej Siewior +--- + init/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/init/Kconfig ++++ b/init/Kconfig +@@ -664,7 +664,7 @@ config TREE_RCU_TRACE + config RCU_BOOST + bool "Enable RCU priority boosting" + depends on RT_MUTEXES && PREEMPT_RCU +- default n ++ default y if PREEMPT_RT_FULL + help + This option boosts the priority of preempted RCU readers that + block the current preemptible RCU grace period for too long. diff --git a/debian/patches/features/all/rt/rcu-merge-rcu-bh-into-rcu-preempt-for-rt.patch b/debian/patches/features/all/rt/rcu-merge-rcu-bh-into-rcu-preempt-for-rt.patch new file mode 100644 index 000000000..af4bd2bd5 --- /dev/null +++ b/debian/patches/features/all/rt/rcu-merge-rcu-bh-into-rcu-preempt-for-rt.patch @@ -0,0 +1,272 @@ +Subject: rcu: Merge RCU-bh into RCU-preempt +Date: Wed, 5 Oct 2011 11:59:38 -0700 +From: Thomas Gleixner +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The Linux kernel has long RCU-bh read-side critical sections that +intolerably increase scheduling latency under mainline's RCU-bh rules, +which include RCU-bh read-side critical sections being non-preemptible. +This patch therefore arranges for RCU-bh to be implemented in terms of +RCU-preempt for CONFIG_PREEMPT_RT_FULL=y. + +This has the downside of defeating the purpose of RCU-bh, namely, +handling the case where the system is subjected to a network-based +denial-of-service attack that keeps at least one CPU doing full-time +softirq processing. This issue will be fixed by a later commit. + +The current commit will need some work to make it appropriate for +mainline use, for example, it needs to be extended to cover Tiny RCU. + +[ paulmck: Added a useful changelog ] + +Signed-off-by: Thomas Gleixner +Signed-off-by: Paul E. McKenney +Link: http://lkml.kernel.org/r/20111005185938.GA20403@linux.vnet.ibm.com +Signed-off-by: Thomas Gleixner + +--- + include/linux/rcupdate.h | 25 +++++++++++++++++++++++++ + include/linux/rcutree.h | 18 ++++++++++++++++-- + kernel/rcu/tree.c | 16 ++++++++++++++++ + kernel/rcu/update.c | 2 ++ + 4 files changed, 59 insertions(+), 2 deletions(-) + +--- a/include/linux/rcupdate.h ++++ b/include/linux/rcupdate.h +@@ -167,6 +167,9 @@ void call_rcu(struct rcu_head *head, + + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + ++#ifdef CONFIG_PREEMPT_RT_FULL ++#define call_rcu_bh call_rcu ++#else + /** + * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. + * @head: structure to be used for queueing the RCU updates. +@@ -190,6 +193,7 @@ void call_rcu(struct rcu_head *head, + */ + void call_rcu_bh(struct rcu_head *head, + void (*func)(struct rcu_head *head)); ++#endif + + /** + * call_rcu_sched() - Queue an RCU for invocation after sched grace period. +@@ -296,7 +300,13 @@ static inline int rcu_preempt_depth(void + void rcu_init(void); + void rcu_end_inkernel_boot(void); + void rcu_sched_qs(void); ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++static inline void rcu_bh_qs(void) { } ++#else + void rcu_bh_qs(void); ++#endif ++ + void rcu_check_callbacks(int user); + struct notifier_block; + void rcu_idle_enter(void); +@@ -470,7 +480,14 @@ extern struct lockdep_map rcu_callback_m + int debug_lockdep_rcu_enabled(void); + + int rcu_read_lock_held(void); ++#ifdef CONFIG_PREEMPT_RT_FULL ++static inline int rcu_read_lock_bh_held(void) ++{ ++ return rcu_read_lock_held(); ++} ++#else + int rcu_read_lock_bh_held(void); ++#endif + + /** + * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section? +@@ -997,10 +1014,14 @@ static inline void rcu_read_unlock(void) + static inline void rcu_read_lock_bh(void) + { + local_bh_disable(); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ rcu_read_lock(); ++#else + __acquire(RCU_BH); + rcu_lock_acquire(&rcu_bh_lock_map); + rcu_lockdep_assert(rcu_is_watching(), + "rcu_read_lock_bh() used illegally while idle"); ++#endif + } + + /* +@@ -1010,10 +1031,14 @@ static inline void rcu_read_lock_bh(void + */ + static inline void rcu_read_unlock_bh(void) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ rcu_read_unlock(); ++#else + rcu_lockdep_assert(rcu_is_watching(), + "rcu_read_unlock_bh() used illegally while idle"); + rcu_lock_release(&rcu_bh_lock_map); + __release(RCU_BH); ++#endif + local_bh_enable(); + } + +--- a/include/linux/rcutree.h ++++ b/include/linux/rcutree.h +@@ -46,7 +46,11 @@ static inline void rcu_virt_note_context + rcu_note_context_switch(); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define synchronize_rcu_bh synchronize_rcu ++#else + void synchronize_rcu_bh(void); ++#endif + void synchronize_sched_expedited(void); + void synchronize_rcu_expedited(void); + +@@ -74,7 +78,11 @@ static inline void synchronize_rcu_bh_ex + } + + void rcu_barrier(void); ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define rcu_barrier_bh rcu_barrier ++#else + void rcu_barrier_bh(void); ++#endif + void rcu_barrier_sched(void); + unsigned long get_state_synchronize_rcu(void); + void cond_synchronize_rcu(unsigned long oldstate); +@@ -85,12 +93,10 @@ unsigned long rcu_batches_started(void); + unsigned long rcu_batches_started_bh(void); + unsigned long rcu_batches_started_sched(void); + unsigned long rcu_batches_completed(void); +-unsigned long rcu_batches_completed_bh(void); + unsigned long rcu_batches_completed_sched(void); + void show_rcu_gp_kthreads(void); + + void rcu_force_quiescent_state(void); +-void rcu_bh_force_quiescent_state(void); + void rcu_sched_force_quiescent_state(void); + + void exit_rcu(void); +@@ -100,6 +106,14 @@ extern int rcu_scheduler_active __read_m + + bool rcu_is_watching(void); + ++#ifndef CONFIG_PREEMPT_RT_FULL ++void rcu_bh_force_quiescent_state(void); ++unsigned long rcu_batches_completed_bh(void); ++#else ++# define rcu_bh_force_quiescent_state rcu_force_quiescent_state ++# define rcu_batches_completed_bh rcu_batches_completed ++#endif ++ + void rcu_all_qs(void); + + #endif /* __LINUX_RCUTREE_H */ +--- a/kernel/rcu/tree.c ++++ b/kernel/rcu/tree.c +@@ -220,6 +220,7 @@ void rcu_sched_qs(void) + } + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void rcu_bh_qs(void) + { + if (!__this_cpu_read(rcu_bh_data.passed_quiesce)) { +@@ -229,6 +230,7 @@ void rcu_bh_qs(void) + __this_cpu_write(rcu_bh_data.passed_quiesce, 1); + } + } ++#endif + + static DEFINE_PER_CPU(int, rcu_sched_qs_mask); + +@@ -404,6 +406,7 @@ unsigned long rcu_batches_completed_sche + } + EXPORT_SYMBOL_GPL(rcu_batches_completed_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Return the number of RCU BH batches completed thus far for debug & stats. + */ +@@ -431,6 +434,13 @@ void rcu_bh_force_quiescent_state(void) + } + EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); + ++#else ++void rcu_force_quiescent_state(void) ++{ ++} ++EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); ++#endif ++ + /* + * Force a quiescent state for RCU-sched. + */ +@@ -3040,6 +3050,7 @@ void call_rcu_sched(struct rcu_head *hea + } + EXPORT_SYMBOL_GPL(call_rcu_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Queue an RCU callback for invocation after a quicker grace period. + */ +@@ -3048,6 +3059,7 @@ void call_rcu_bh(struct rcu_head *head, + __call_rcu(head, func, &rcu_bh_state, -1, 0); + } + EXPORT_SYMBOL_GPL(call_rcu_bh); ++#endif + + /* + * Queue an RCU callback for lazy invocation after a grace period. +@@ -3139,6 +3151,7 @@ void synchronize_sched(void) + } + EXPORT_SYMBOL_GPL(synchronize_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed. + * +@@ -3165,6 +3178,7 @@ void synchronize_rcu_bh(void) + wait_rcu_gp(call_rcu_bh); + } + EXPORT_SYMBOL_GPL(synchronize_rcu_bh); ++#endif + + /** + * get_state_synchronize_rcu - Snapshot current RCU state +@@ -3677,6 +3691,7 @@ static void _rcu_barrier(struct rcu_stat + mutex_unlock(&rsp->barrier_mutex); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete. + */ +@@ -3685,6 +3700,7 @@ void rcu_barrier_bh(void) + _rcu_barrier(&rcu_bh_state); + } + EXPORT_SYMBOL_GPL(rcu_barrier_bh); ++#endif + + /** + * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks. +--- a/kernel/rcu/update.c ++++ b/kernel/rcu/update.c +@@ -227,6 +227,7 @@ int rcu_read_lock_held(void) + } + EXPORT_SYMBOL_GPL(rcu_read_lock_held); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section? + * +@@ -253,6 +254,7 @@ int rcu_read_lock_bh_held(void) + return in_softirq() || irqs_disabled(); + } + EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); ++#endif + + #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + diff --git a/debian/patches/features/all/rt/rcu-more-swait-conversions.patch b/debian/patches/features/all/rt/rcu-more-swait-conversions.patch new file mode 100644 index 000000000..d6d9993e0 --- /dev/null +++ b/debian/patches/features/all/rt/rcu-more-swait-conversions.patch @@ -0,0 +1,175 @@ +From: Thomas Gleixner +Date: Wed, 31 Jul 2013 19:00:35 +0200 +Subject: rcu: use simple waitqueues +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Convert RCU's wait-queues into simple waitqueues. + +Signed-off-by: Thomas Gleixner + +Merged Steven's + + static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) { +- swait_wake(&rnp->nocb_gp_wq[rnp->completed & 0x1]); ++ wake_up_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]); + } + +Signed-off-by: Steven Rostedt +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/rcu/tree.c | 8 ++++---- + kernel/rcu/tree.h | 7 ++++--- + kernel/rcu/tree_plugin.h | 18 +++++++++--------- + 3 files changed, 17 insertions(+), 16 deletions(-) + +--- a/kernel/rcu/tree.c ++++ b/kernel/rcu/tree.c +@@ -1567,7 +1567,7 @@ static void rcu_gp_kthread_wake(struct r + !ACCESS_ONCE(rsp->gp_flags) || + !rsp->gp_kthread) + return; +- wake_up(&rsp->gp_wq); ++ swait_wake(&rsp->gp_wq); + } + + /* +@@ -2008,7 +2008,7 @@ static int __noreturn rcu_gp_kthread(voi + ACCESS_ONCE(rsp->gpnum), + TPS("reqwait")); + rsp->gp_state = RCU_GP_WAIT_GPS; +- wait_event_interruptible(rsp->gp_wq, ++ swait_event_interruptible(rsp->gp_wq, + ACCESS_ONCE(rsp->gp_flags) & + RCU_GP_FLAG_INIT); + /* Locking provides needed memory barrier. */ +@@ -2037,7 +2037,7 @@ static int __noreturn rcu_gp_kthread(voi + ACCESS_ONCE(rsp->gpnum), + TPS("fqswait")); + rsp->gp_state = RCU_GP_WAIT_FQS; +- ret = wait_event_interruptible_timeout(rsp->gp_wq, ++ ret = swait_event_interruptible_timeout(rsp->gp_wq, + ((gf = ACCESS_ONCE(rsp->gp_flags)) & + RCU_GP_FLAG_FQS) || + (!ACCESS_ONCE(rnp->qsmask) && +@@ -4049,7 +4049,7 @@ static void __init rcu_init_one(struct r + } + } + +- init_waitqueue_head(&rsp->gp_wq); ++ init_swait_head(&rsp->gp_wq); + rnp = rsp->level[rcu_num_lvls - 1]; + for_each_possible_cpu(i) { + while (i > rnp->grphi) +--- a/kernel/rcu/tree.h ++++ b/kernel/rcu/tree.h +@@ -27,6 +27,7 @@ + #include + #include + #include ++#include + + /* + * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and +@@ -210,7 +211,7 @@ struct rcu_node { + /* This can happen due to race conditions. */ + #endif /* #ifdef CONFIG_RCU_BOOST */ + #ifdef CONFIG_RCU_NOCB_CPU +- wait_queue_head_t nocb_gp_wq[2]; ++ struct swait_head nocb_gp_wq[2]; + /* Place for rcu_nocb_kthread() to wait GP. */ + #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ + int need_future_gp[2]; +@@ -349,7 +350,7 @@ struct rcu_data { + atomic_long_t nocb_q_count_lazy; /* invocation (all stages). */ + struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */ + struct rcu_head **nocb_follower_tail; +- wait_queue_head_t nocb_wq; /* For nocb kthreads to sleep on. */ ++ struct swait_head nocb_wq; /* For nocb kthreads to sleep on. */ + struct task_struct *nocb_kthread; + int nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */ + +@@ -438,7 +439,7 @@ struct rcu_state { + unsigned long gpnum; /* Current gp number. */ + unsigned long completed; /* # of last completed gp. */ + struct task_struct *gp_kthread; /* Task for grace periods. */ +- wait_queue_head_t gp_wq; /* Where GP task waits. */ ++ struct swait_head gp_wq; /* Where GP task waits. */ + short gp_flags; /* Commands for GP task. */ + short gp_state; /* GP kthread sleep state. */ + +--- a/kernel/rcu/tree_plugin.h ++++ b/kernel/rcu/tree_plugin.h +@@ -1864,7 +1864,7 @@ early_param("rcu_nocb_poll", parse_rcu_n + */ + static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) + { +- wake_up_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]); ++ swait_wake_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]); + } + + /* +@@ -1882,8 +1882,8 @@ static void rcu_nocb_gp_set(struct rcu_n + + static void rcu_init_one_nocb(struct rcu_node *rnp) + { +- init_waitqueue_head(&rnp->nocb_gp_wq[0]); +- init_waitqueue_head(&rnp->nocb_gp_wq[1]); ++ init_swait_head(&rnp->nocb_gp_wq[0]); ++ init_swait_head(&rnp->nocb_gp_wq[1]); + } + + #ifndef CONFIG_RCU_NOCB_CPU_ALL +@@ -1908,7 +1908,7 @@ static void wake_nocb_leader(struct rcu_ + if (ACCESS_ONCE(rdp_leader->nocb_leader_sleep) || force) { + /* Prior smp_mb__after_atomic() orders against prior enqueue. */ + ACCESS_ONCE(rdp_leader->nocb_leader_sleep) = false; +- wake_up(&rdp_leader->nocb_wq); ++ swait_wake(&rdp_leader->nocb_wq); + } + } + +@@ -2121,7 +2121,7 @@ static void rcu_nocb_wait_gp(struct rcu_ + */ + trace_rcu_future_gp(rnp, rdp, c, TPS("StartWait")); + for (;;) { +- wait_event_interruptible( ++ swait_event_interruptible( + rnp->nocb_gp_wq[c & 0x1], + (d = ULONG_CMP_GE(ACCESS_ONCE(rnp->completed), c))); + if (likely(d)) +@@ -2149,7 +2149,7 @@ static void nocb_leader_wait(struct rcu_ + /* Wait for callbacks to appear. */ + if (!rcu_nocb_poll) { + trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep"); +- wait_event_interruptible(my_rdp->nocb_wq, ++ swait_event_interruptible(my_rdp->nocb_wq, + !ACCESS_ONCE(my_rdp->nocb_leader_sleep)); + /* Memory barrier handled by smp_mb() calls below and repoll. */ + } else if (firsttime) { +@@ -2224,7 +2224,7 @@ static void nocb_leader_wait(struct rcu_ + * List was empty, wake up the follower. + * Memory barriers supplied by atomic_long_add(). + */ +- wake_up(&rdp->nocb_wq); ++ swait_wake(&rdp->nocb_wq); + } + } + +@@ -2245,7 +2245,7 @@ static void nocb_follower_wait(struct rc + if (!rcu_nocb_poll) { + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + "FollowerSleep"); +- wait_event_interruptible(rdp->nocb_wq, ++ swait_event_interruptible(rdp->nocb_wq, + ACCESS_ONCE(rdp->nocb_follower_head)); + } else if (firsttime) { + /* Don't drown trace log with "Poll"! */ +@@ -2404,7 +2404,7 @@ void __init rcu_init_nohz(void) + static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) + { + rdp->nocb_tail = &rdp->nocb_head; +- init_waitqueue_head(&rdp->nocb_wq); ++ init_swait_head(&rdp->nocb_wq); + rdp->nocb_follower_tail = &rdp->nocb_follower_head; + } + diff --git a/debian/patches/features/all/rt/rcutree-rcu_bh_qs-disable-irq-while-calling-rcu_pree.patch b/debian/patches/features/all/rt/rcutree-rcu_bh_qs-disable-irq-while-calling-rcu_pree.patch new file mode 100644 index 000000000..019a71f96 --- /dev/null +++ b/debian/patches/features/all/rt/rcutree-rcu_bh_qs-disable-irq-while-calling-rcu_pree.patch @@ -0,0 +1,49 @@ +From: Tiejun Chen +Date: Wed, 18 Dec 2013 17:51:49 +0800 +Subject: rcutree/rcu_bh_qs: Disable irq while calling rcu_preempt_qs() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Any callers to the function rcu_preempt_qs() must disable irqs in +order to protect the assignment to ->rcu_read_unlock_special. In +RT case, rcu_bh_qs() as the wrapper of rcu_preempt_qs() is called +in some scenarios where irq is enabled, like this path, + +do_single_softirq() + | + + local_irq_enable(); + + handle_softirq() + | | + | + rcu_bh_qs() + | | + | + rcu_preempt_qs() + | + + local_irq_disable() + +So here we'd better disable irq directly inside of rcu_bh_qs() to +fix this, otherwise the kernel may be freezable sometimes as +observed. And especially this way is also kind and safe for the +potential rcu_bh_qs() usage elsewhere in the future. + + +Signed-off-by: Tiejun Chen +Signed-off-by: Bin Jiang +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/rcu/tree.c | 5 +++++ + 1 file changed, 5 insertions(+) + +--- a/kernel/rcu/tree.c ++++ b/kernel/rcu/tree.c +@@ -225,7 +225,12 @@ static void rcu_preempt_qs(void); + + void rcu_bh_qs(void) + { ++ unsigned long flags; ++ ++ /* Callers to this function, rcu_preempt_qs(), must disable irqs. */ ++ local_irq_save(flags); + rcu_preempt_qs(); ++ local_irq_restore(flags); + } + #else + void rcu_bh_qs(void) diff --git a/debian/patches/features/all/rt/re-migrate_disable-race-with-cpu-hotplug-3f.patch b/debian/patches/features/all/rt/re-migrate_disable-race-with-cpu-hotplug-3f.patch new file mode 100644 index 000000000..11a323329 --- /dev/null +++ b/debian/patches/features/all/rt/re-migrate_disable-race-with-cpu-hotplug-3f.patch @@ -0,0 +1,35 @@ +From: Yong Zhang +Date: Thu, 28 Jul 2011 11:16:00 +0800 +Subject: hotplug: Reread hotplug_pcp on pin_current_cpu() retry +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +When retry happens, it's likely that the task has been migrated to +another cpu (except unplug failed), but it still derefernces the +original hotplug_pcp per cpu data. + +Update the pointer to hotplug_pcp in the retry path, so it points to +the current cpu. + +Signed-off-by: Yong Zhang +Cc: Peter Zijlstra +Link: http://lkml.kernel.org/r/20110728031600.GA338@windriver.com +Signed-off-by: Thomas Gleixner +--- + kernel/cpu.c | 4 +++- + 1 file changed, 3 insertions(+), 1 deletion(-) + +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -106,9 +106,11 @@ static DEFINE_PER_CPU(struct hotplug_pcp + */ + void pin_current_cpu(void) + { +- struct hotplug_pcp *hp = this_cpu_ptr(&hotplug_pcp); ++ struct hotplug_pcp *hp; + + retry: ++ hp = this_cpu_ptr(&hotplug_pcp); ++ + if (!hp->unplug || hp->refcount || preempt_count() > 1 || + hp->unplug == current) { + hp->refcount++; diff --git a/debian/patches/features/all/rt/re-preempt_rt_full-arm-coredump-fails-for-cpu-3e-3d-4.patch b/debian/patches/features/all/rt/re-preempt_rt_full-arm-coredump-fails-for-cpu-3e-3d-4.patch new file mode 100644 index 000000000..51d2d75c6 --- /dev/null +++ b/debian/patches/features/all/rt/re-preempt_rt_full-arm-coredump-fails-for-cpu-3e-3d-4.patch @@ -0,0 +1,69 @@ +Subject: ARM: Initialize split page table locks for vector page +From: Frank Rowand +Date: Sat, 1 Oct 2011 18:58:13 -0700 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Without this patch, ARM can not use SPLIT_PTLOCK_CPUS if +PREEMPT_RT_FULL=y because vectors_user_mapping() creates a +VM_ALWAYSDUMP mapping of the vector page (address 0xffff0000), but no +ptl->lock has been allocated for the page. An attempt to coredump +that page will result in a kernel NULL pointer dereference when +follow_page() attempts to lock the page. + +The call tree to the NULL pointer dereference is: + + do_notify_resume() + get_signal_to_deliver() + do_coredump() + elf_core_dump() + get_dump_page() + __get_user_pages() + follow_page() + pte_offset_map_lock() <----- a #define + ... + rt_spin_lock() + +The underlying problem is exposed by mm-shrink-the-page-frame-to-rt-size.patch. + +Signed-off-by: Frank Rowand +Cc: Frank +Cc: Peter Zijlstra +Link: http://lkml.kernel.org/r/4E87C535.2030907@am.sony.com +Signed-off-by: Thomas Gleixner +--- + arch/arm/kernel/process.c | 24 ++++++++++++++++++++++++ + 1 file changed, 24 insertions(+) + +--- a/arch/arm/kernel/process.c ++++ b/arch/arm/kernel/process.c +@@ -290,6 +290,30 @@ unsigned long arch_randomize_brk(struct + } + + #ifdef CONFIG_MMU ++/* ++ * CONFIG_SPLIT_PTLOCK_CPUS results in a page->ptl lock. If the lock is not ++ * initialized by pgtable_page_ctor() then a coredump of the vector page will ++ * fail. ++ */ ++static int __init vectors_user_mapping_init_page(void) ++{ ++ struct page *page; ++ unsigned long addr = 0xffff0000; ++ pgd_t *pgd; ++ pud_t *pud; ++ pmd_t *pmd; ++ ++ pgd = pgd_offset_k(addr); ++ pud = pud_offset(pgd, addr); ++ pmd = pmd_offset(pud, addr); ++ page = pmd_page(*(pmd)); ++ ++ pgtable_page_ctor(page); ++ ++ return 0; ++} ++late_initcall(vectors_user_mapping_init_page); ++ + #ifdef CONFIG_KUSER_HELPERS + /* + * The vectors page is always readable from user space for the diff --git a/debian/patches/features/all/rt/relay-fix-timer-madness.patch b/debian/patches/features/all/rt/relay-fix-timer-madness.patch new file mode 100644 index 000000000..bbc8a0b61 --- /dev/null +++ b/debian/patches/features/all/rt/relay-fix-timer-madness.patch @@ -0,0 +1,53 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:44:07 -0500 +Subject: relay: Fix timer madness +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +remove timer calls (!!!) from deep within the tracing infrastructure. +This was totally bogus code that can cause lockups and worse. Poll +the buffer every 2 jiffies for now. + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + kernel/relay.c | 14 +++++--------- + 1 file changed, 5 insertions(+), 9 deletions(-) + +--- a/kernel/relay.c ++++ b/kernel/relay.c +@@ -339,6 +339,10 @@ static void wakeup_readers(unsigned long + { + struct rchan_buf *buf = (struct rchan_buf *)data; + wake_up_interruptible(&buf->read_wait); ++ /* ++ * Stupid polling for now: ++ */ ++ mod_timer(&buf->timer, jiffies + 1); + } + + /** +@@ -356,6 +360,7 @@ static void __relay_reset(struct rchan_b + init_waitqueue_head(&buf->read_wait); + kref_init(&buf->kref); + setup_timer(&buf->timer, wakeup_readers, (unsigned long)buf); ++ mod_timer(&buf->timer, jiffies + 1); + } else + del_timer_sync(&buf->timer); + +@@ -739,15 +744,6 @@ size_t relay_switch_subbuf(struct rchan_ + else + buf->early_bytes += buf->chan->subbuf_size - + buf->padding[old_subbuf]; +- smp_mb(); +- if (waitqueue_active(&buf->read_wait)) +- /* +- * Calling wake_up_interruptible() from here +- * will deadlock if we happen to be logging +- * from the scheduler (trying to re-grab +- * rq->lock), so defer it. +- */ +- mod_timer(&buf->timer, jiffies + 1); + } + + old = buf->data; diff --git a/debian/patches/features/all/rt/rt-add-rt-locks.patch b/debian/patches/features/all/rt/rt-add-rt-locks.patch new file mode 100644 index 000000000..eaea5753b --- /dev/null +++ b/debian/patches/features/all/rt/rt-add-rt-locks.patch @@ -0,0 +1,1983 @@ +From: Thomas Gleixner +Date: Sun, 26 Jul 2009 19:39:56 +0200 +Subject: rt: Add the preempt-rt lock replacement APIs +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Map spinlocks, rwlocks, rw_semaphores and semaphores to the rt_mutex +based locking functions for preempt-rt. +This also introduces RT's sleeping locks. + +Signed-off-by: Thomas Gleixner + +--- + include/linux/kernel.h | 4 + include/linux/locallock.h | 6 + include/linux/mutex.h | 20 + + include/linux/mutex_rt.h | 84 ++++++ + include/linux/rtmutex.h | 27 +- + include/linux/rwlock_rt.h | 99 ++++++++ + include/linux/rwlock_types_rt.h | 33 ++ + include/linux/rwsem.h | 6 + include/linux/rwsem_rt.h | 140 +++++++++++ + include/linux/sched.h | 5 + include/linux/spinlock.h | 12 + include/linux/spinlock_api_smp.h | 4 + include/linux/spinlock_rt.h | 173 ++++++++++++++ + include/linux/spinlock_types.h | 11 + include/linux/spinlock_types_rt.h | 51 ++++ + kernel/futex.c | 5 + kernel/locking/Makefile | 9 + kernel/locking/rt.c | 461 ++++++++++++++++++++++++++++++++++++++ + kernel/locking/rtmutex.c | 395 ++++++++++++++++++++++++++++++-- + kernel/locking/rtmutex_common.h | 11 + kernel/locking/spinlock.c | 7 + kernel/locking/spinlock_debug.c | 5 + 22 files changed, 1525 insertions(+), 43 deletions(-) + +--- a/include/linux/kernel.h ++++ b/include/linux/kernel.h +@@ -188,6 +188,9 @@ extern int _cond_resched(void); + */ + # define might_sleep() \ + do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) ++ ++# define might_sleep_no_state_check() \ ++ do { ___might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) + # define sched_annotate_sleep() (current->task_state_change = 0) + #else + static inline void ___might_sleep(const char *file, int line, +@@ -195,6 +198,7 @@ extern int _cond_resched(void); + static inline void __might_sleep(const char *file, int line, + int preempt_offset) { } + # define might_sleep() do { might_resched(); } while (0) ++# define might_sleep_no_state_check() do { might_resched(); } while (0) + # define sched_annotate_sleep() do { } while (0) + #endif + +--- a/include/linux/locallock.h ++++ b/include/linux/locallock.h +@@ -42,9 +42,15 @@ struct local_irq_lock { + * already takes care of the migrate_disable/enable + * for CONFIG_PREEMPT_BASE map to the normal spin_* calls. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define spin_lock_local(lock) rt_spin_lock(lock) ++# define spin_trylock_local(lock) rt_spin_trylock(lock) ++# define spin_unlock_local(lock) rt_spin_unlock(lock) ++#else + # define spin_lock_local(lock) spin_lock(lock) + # define spin_trylock_local(lock) spin_trylock(lock) + # define spin_unlock_local(lock) spin_unlock(lock) ++#endif + + static inline void __local_lock(struct local_irq_lock *lv) + { +--- a/include/linux/mutex.h ++++ b/include/linux/mutex.h +@@ -19,6 +19,17 @@ + #include + #include + ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ ++ , .dep_map = { .name = #lockname } ++#else ++# define __DEP_MAP_MUTEX_INITIALIZER(lockname) ++#endif ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++# include ++#else ++ + /* + * Simple, straightforward mutexes with strict semantics: + * +@@ -99,13 +110,6 @@ do { \ + static inline void mutex_destroy(struct mutex *lock) {} + #endif + +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +-# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ +- , .dep_map = { .name = #lockname } +-#else +-# define __DEP_MAP_MUTEX_INITIALIZER(lockname) +-#endif +- + #define __MUTEX_INITIALIZER(lockname) \ + { .count = ATOMIC_INIT(1) \ + , .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ +@@ -173,6 +177,8 @@ extern int __must_check mutex_lock_killa + extern int mutex_trylock(struct mutex *lock); + extern void mutex_unlock(struct mutex *lock); + ++#endif /* !PREEMPT_RT_FULL */ ++ + extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); + + #endif /* __LINUX_MUTEX_H */ +--- /dev/null ++++ b/include/linux/mutex_rt.h +@@ -0,0 +1,84 @@ ++#ifndef __LINUX_MUTEX_RT_H ++#define __LINUX_MUTEX_RT_H ++ ++#ifndef __LINUX_MUTEX_H ++#error "Please include mutex.h" ++#endif ++ ++#include ++ ++/* FIXME: Just for __lockfunc */ ++#include ++ ++struct mutex { ++ struct rt_mutex lock; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++}; ++ ++#define __MUTEX_INITIALIZER(mutexname) \ ++ { \ ++ .lock = __RT_MUTEX_INITIALIZER(mutexname.lock) \ ++ __DEP_MAP_MUTEX_INITIALIZER(mutexname) \ ++ } ++ ++#define DEFINE_MUTEX(mutexname) \ ++ struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) ++ ++extern void __mutex_do_init(struct mutex *lock, const char *name, struct lock_class_key *key); ++extern void __lockfunc _mutex_lock(struct mutex *lock); ++extern int __lockfunc _mutex_lock_interruptible(struct mutex *lock); ++extern int __lockfunc _mutex_lock_killable(struct mutex *lock); ++extern void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass); ++extern void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock); ++extern int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass); ++extern int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass); ++extern int __lockfunc _mutex_trylock(struct mutex *lock); ++extern void __lockfunc _mutex_unlock(struct mutex *lock); ++ ++#define mutex_is_locked(l) rt_mutex_is_locked(&(l)->lock) ++#define mutex_lock(l) _mutex_lock(l) ++#define mutex_lock_interruptible(l) _mutex_lock_interruptible(l) ++#define mutex_lock_killable(l) _mutex_lock_killable(l) ++#define mutex_trylock(l) _mutex_trylock(l) ++#define mutex_unlock(l) _mutex_unlock(l) ++#define mutex_destroy(l) rt_mutex_destroy(&(l)->lock) ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define mutex_lock_nested(l, s) _mutex_lock_nested(l, s) ++# define mutex_lock_interruptible_nested(l, s) \ ++ _mutex_lock_interruptible_nested(l, s) ++# define mutex_lock_killable_nested(l, s) \ ++ _mutex_lock_killable_nested(l, s) ++ ++# define mutex_lock_nest_lock(lock, nest_lock) \ ++do { \ ++ typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ ++ _mutex_lock_nest_lock(lock, &(nest_lock)->dep_map); \ ++} while (0) ++ ++#else ++# define mutex_lock_nested(l, s) _mutex_lock(l) ++# define mutex_lock_interruptible_nested(l, s) \ ++ _mutex_lock_interruptible(l) ++# define mutex_lock_killable_nested(l, s) \ ++ _mutex_lock_killable(l) ++# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock) ++#endif ++ ++# define mutex_init(mutex) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ rt_mutex_init(&(mutex)->lock); \ ++ __mutex_do_init((mutex), #mutex, &__key); \ ++} while (0) ++ ++# define __mutex_init(mutex, name, key) \ ++do { \ ++ rt_mutex_init(&(mutex)->lock); \ ++ __mutex_do_init((mutex), name, key); \ ++} while (0) ++ ++#endif +--- a/include/linux/rtmutex.h ++++ b/include/linux/rtmutex.h +@@ -18,6 +18,10 @@ + + extern int max_lock_depth; /* for sysctl */ + ++#ifdef CONFIG_DEBUG_MUTEXES ++#include ++#endif ++ + /** + * The rt_mutex structure + * +@@ -31,8 +35,8 @@ struct rt_mutex { + struct rb_root waiters; + struct rb_node *waiters_leftmost; + struct task_struct *owner; +-#ifdef CONFIG_DEBUG_RT_MUTEXES + int save_state; ++#ifdef CONFIG_DEBUG_RT_MUTEXES + const char *name, *file; + int line; + void *magic; +@@ -55,22 +59,33 @@ struct hrtimer_sleeper; + # define rt_mutex_debug_check_no_locks_held(task) do { } while (0) + #endif + ++# define rt_mutex_init(mutex) \ ++ do { \ ++ raw_spin_lock_init(&(mutex)->wait_lock); \ ++ __rt_mutex_init(mutex, #mutex); \ ++ } while (0) ++ + #ifdef CONFIG_DEBUG_RT_MUTEXES + # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \ + , .name = #mutexname, .file = __FILE__, .line = __LINE__ +-# define rt_mutex_init(mutex) __rt_mutex_init(mutex, __func__) + extern void rt_mutex_debug_task_free(struct task_struct *tsk); + #else + # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) +-# define rt_mutex_init(mutex) __rt_mutex_init(mutex, NULL) + # define rt_mutex_debug_task_free(t) do { } while (0) + #endif + +-#define __RT_MUTEX_INITIALIZER(mutexname) \ +- { .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ ++#define __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \ ++ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ + , .waiters = RB_ROOT \ + , .owner = NULL \ +- __DEBUG_RT_MUTEX_INITIALIZER(mutexname)} ++ __DEBUG_RT_MUTEX_INITIALIZER(mutexname) ++ ++#define __RT_MUTEX_INITIALIZER(mutexname) \ ++ { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) } ++ ++#define __RT_MUTEX_INITIALIZER_SAVE_STATE(mutexname) \ ++ { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \ ++ , .save_state = 1 } + + #define DEFINE_RT_MUTEX(mutexname) \ + struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname) +--- /dev/null ++++ b/include/linux/rwlock_rt.h +@@ -0,0 +1,99 @@ ++#ifndef __LINUX_RWLOCK_RT_H ++#define __LINUX_RWLOCK_RT_H ++ ++#ifndef __LINUX_SPINLOCK_H ++#error Do not include directly. Use spinlock.h ++#endif ++ ++#define rwlock_init(rwl) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ rt_mutex_init(&(rwl)->lock); \ ++ __rt_rwlock_init(rwl, #rwl, &__key); \ ++} while (0) ++ ++extern void __lockfunc rt_write_lock(rwlock_t *rwlock); ++extern void __lockfunc rt_read_lock(rwlock_t *rwlock); ++extern int __lockfunc rt_write_trylock(rwlock_t *rwlock); ++extern int __lockfunc rt_write_trylock_irqsave(rwlock_t *trylock, unsigned long *flags); ++extern int __lockfunc rt_read_trylock(rwlock_t *rwlock); ++extern void __lockfunc rt_write_unlock(rwlock_t *rwlock); ++extern void __lockfunc rt_read_unlock(rwlock_t *rwlock); ++extern unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock); ++extern unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock); ++extern void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key); ++ ++#define read_trylock(lock) __cond_lock(lock, rt_read_trylock(lock)) ++#define write_trylock(lock) __cond_lock(lock, rt_write_trylock(lock)) ++ ++#define write_trylock_irqsave(lock, flags) \ ++ __cond_lock(lock, rt_write_trylock_irqsave(lock, &flags)) ++ ++#define read_lock_irqsave(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = rt_read_lock_irqsave(lock); \ ++ } while (0) ++ ++#define write_lock_irqsave(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = rt_write_lock_irqsave(lock); \ ++ } while (0) ++ ++#define read_lock(lock) rt_read_lock(lock) ++ ++#define read_lock_bh(lock) \ ++ do { \ ++ local_bh_disable(); \ ++ rt_read_lock(lock); \ ++ } while (0) ++ ++#define read_lock_irq(lock) read_lock(lock) ++ ++#define write_lock(lock) rt_write_lock(lock) ++ ++#define write_lock_bh(lock) \ ++ do { \ ++ local_bh_disable(); \ ++ rt_write_lock(lock); \ ++ } while (0) ++ ++#define write_lock_irq(lock) write_lock(lock) ++ ++#define read_unlock(lock) rt_read_unlock(lock) ++ ++#define read_unlock_bh(lock) \ ++ do { \ ++ rt_read_unlock(lock); \ ++ local_bh_enable(); \ ++ } while (0) ++ ++#define read_unlock_irq(lock) read_unlock(lock) ++ ++#define write_unlock(lock) rt_write_unlock(lock) ++ ++#define write_unlock_bh(lock) \ ++ do { \ ++ rt_write_unlock(lock); \ ++ local_bh_enable(); \ ++ } while (0) ++ ++#define write_unlock_irq(lock) write_unlock(lock) ++ ++#define read_unlock_irqrestore(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ (void) flags; \ ++ rt_read_unlock(lock); \ ++ } while (0) ++ ++#define write_unlock_irqrestore(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ (void) flags; \ ++ rt_write_unlock(lock); \ ++ } while (0) ++ ++#endif +--- /dev/null ++++ b/include/linux/rwlock_types_rt.h +@@ -0,0 +1,33 @@ ++#ifndef __LINUX_RWLOCK_TYPES_RT_H ++#define __LINUX_RWLOCK_TYPES_RT_H ++ ++#ifndef __LINUX_SPINLOCK_TYPES_H ++#error "Do not include directly. Include spinlock_types.h instead" ++#endif ++ ++/* ++ * rwlocks - rtmutex which allows single reader recursion ++ */ ++typedef struct { ++ struct rt_mutex lock; ++ int read_depth; ++ unsigned int break_lock; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++} rwlock_t; ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define RW_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } ++#else ++# define RW_DEP_MAP_INIT(lockname) ++#endif ++ ++#define __RW_LOCK_UNLOCKED(name) \ ++ { .lock = __RT_MUTEX_INITIALIZER_SAVE_STATE(name.lock), \ ++ RW_DEP_MAP_INIT(name) } ++ ++#define DEFINE_RWLOCK(name) \ ++ rwlock_t name __cacheline_aligned_in_smp = __RW_LOCK_UNLOCKED(name) ++ ++#endif +--- a/include/linux/rwsem.h ++++ b/include/linux/rwsem.h +@@ -18,6 +18,10 @@ + #include + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++#include ++#else /* PREEMPT_RT_FULL */ ++ + struct rw_semaphore; + + #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK +@@ -177,4 +181,6 @@ extern void up_read_non_owner(struct rw_ + # define up_read_non_owner(sem) up_read(sem) + #endif + ++#endif /* !PREEMPT_RT_FULL */ ++ + #endif /* _LINUX_RWSEM_H */ +--- /dev/null ++++ b/include/linux/rwsem_rt.h +@@ -0,0 +1,140 @@ ++#ifndef _LINUX_RWSEM_RT_H ++#define _LINUX_RWSEM_RT_H ++ ++#ifndef _LINUX_RWSEM_H ++#error "Include rwsem.h" ++#endif ++ ++/* ++ * RW-semaphores are a spinlock plus a reader-depth count. ++ * ++ * Note that the semantics are different from the usual ++ * Linux rw-sems, in PREEMPT_RT mode we do not allow ++ * multiple readers to hold the lock at once, we only allow ++ * a read-lock owner to read-lock recursively. This is ++ * better for latency, makes the implementation inherently ++ * fair and makes it simpler as well. ++ */ ++ ++#include ++ ++struct rw_semaphore { ++ struct rt_mutex lock; ++ int read_depth; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++}; ++ ++#define __RWSEM_INITIALIZER(name) \ ++ { .lock = __RT_MUTEX_INITIALIZER(name.lock), \ ++ RW_DEP_MAP_INIT(name) } ++ ++#define DECLARE_RWSEM(lockname) \ ++ struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname) ++ ++extern void __rt_rwsem_init(struct rw_semaphore *rwsem, const char *name, ++ struct lock_class_key *key); ++ ++#define __rt_init_rwsem(sem, name, key) \ ++ do { \ ++ rt_mutex_init(&(sem)->lock); \ ++ __rt_rwsem_init((sem), (name), (key));\ ++ } while (0) ++ ++#define __init_rwsem(sem, name, key) __rt_init_rwsem(sem, name, key) ++ ++# define rt_init_rwsem(sem) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ __rt_init_rwsem((sem), #sem, &__key); \ ++} while (0) ++ ++extern void rt_down_write(struct rw_semaphore *rwsem); ++extern void rt_down_read_nested(struct rw_semaphore *rwsem, int subclass); ++extern void rt_down_write_nested(struct rw_semaphore *rwsem, int subclass); ++extern void rt_down_write_nested_lock(struct rw_semaphore *rwsem, ++ struct lockdep_map *nest); ++extern void rt_down_read(struct rw_semaphore *rwsem); ++extern int rt_down_write_trylock(struct rw_semaphore *rwsem); ++extern int rt_down_read_trylock(struct rw_semaphore *rwsem); ++extern void __rt_up_read(struct rw_semaphore *rwsem); ++extern void rt_up_read(struct rw_semaphore *rwsem); ++extern void rt_up_write(struct rw_semaphore *rwsem); ++extern void rt_downgrade_write(struct rw_semaphore *rwsem); ++ ++#define init_rwsem(sem) rt_init_rwsem(sem) ++#define rwsem_is_locked(s) rt_mutex_is_locked(&(s)->lock) ++ ++static inline int rwsem_is_contended(struct rw_semaphore *sem) ++{ ++ /* rt_mutex_has_waiters() */ ++ return !RB_EMPTY_ROOT(&sem->lock.waiters); ++} ++ ++static inline void down_read(struct rw_semaphore *sem) ++{ ++ rt_down_read(sem); ++} ++ ++static inline int down_read_trylock(struct rw_semaphore *sem) ++{ ++ return rt_down_read_trylock(sem); ++} ++ ++static inline void down_write(struct rw_semaphore *sem) ++{ ++ rt_down_write(sem); ++} ++ ++static inline int down_write_trylock(struct rw_semaphore *sem) ++{ ++ return rt_down_write_trylock(sem); ++} ++ ++static inline void __up_read(struct rw_semaphore *sem) ++{ ++ __rt_up_read(sem); ++} ++ ++static inline void up_read(struct rw_semaphore *sem) ++{ ++ rt_up_read(sem); ++} ++ ++static inline void up_write(struct rw_semaphore *sem) ++{ ++ rt_up_write(sem); ++} ++ ++static inline void downgrade_write(struct rw_semaphore *sem) ++{ ++ rt_downgrade_write(sem); ++} ++ ++static inline void down_read_nested(struct rw_semaphore *sem, int subclass) ++{ ++ return rt_down_read_nested(sem, subclass); ++} ++ ++static inline void down_write_nested(struct rw_semaphore *sem, int subclass) ++{ ++ rt_down_write_nested(sem, subclass); ++} ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++static inline void down_write_nest_lock(struct rw_semaphore *sem, ++ struct rw_semaphore *nest_lock) ++{ ++ rt_down_write_nested_lock(sem, &nest_lock->dep_map); ++} ++ ++#else ++ ++static inline void down_write_nest_lock(struct rw_semaphore *sem, ++ struct rw_semaphore *nest_lock) ++{ ++ rt_down_write_nested_lock(sem, NULL); ++} ++#endif ++#endif +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -302,6 +302,11 @@ extern char ___assert_task_state[1 - 2*! + + #endif + ++#define __set_current_state_no_track(state_value) \ ++ do { current->state = (state_value); } while (0) ++#define set_current_state_no_track(state_value) \ ++ set_mb(current->state, (state_value)) ++ + /* Task command name length */ + #define TASK_COMM_LEN 16 + +--- a/include/linux/spinlock.h ++++ b/include/linux/spinlock.h +@@ -281,7 +281,11 @@ static inline void do_raw_spin_unlock(ra + #define raw_spin_can_lock(lock) (!raw_spin_is_locked(lock)) + + /* Include rwlock functions */ +-#include ++#ifdef CONFIG_PREEMPT_RT_FULL ++# include ++#else ++# include ++#endif + + /* + * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: +@@ -292,6 +296,10 @@ static inline void do_raw_spin_unlock(ra + # include + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++# include ++#else /* PREEMPT_RT_FULL */ ++ + /* + * Map the spin_lock functions to the raw variants for PREEMPT_RT=n + */ +@@ -426,4 +434,6 @@ extern int _atomic_dec_and_lock(atomic_t + #define atomic_dec_and_lock(atomic, lock) \ + __cond_lock(lock, _atomic_dec_and_lock(atomic, lock)) + ++#endif /* !PREEMPT_RT_FULL */ ++ + #endif /* __LINUX_SPINLOCK_H */ +--- a/include/linux/spinlock_api_smp.h ++++ b/include/linux/spinlock_api_smp.h +@@ -189,6 +189,8 @@ static inline int __raw_spin_trylock_bh( + return 0; + } + +-#include ++#ifndef CONFIG_PREEMPT_RT_FULL ++# include ++#endif + + #endif /* __LINUX_SPINLOCK_API_SMP_H */ +--- /dev/null ++++ b/include/linux/spinlock_rt.h +@@ -0,0 +1,173 @@ ++#ifndef __LINUX_SPINLOCK_RT_H ++#define __LINUX_SPINLOCK_RT_H ++ ++#ifndef __LINUX_SPINLOCK_H ++#error Do not include directly. Use spinlock.h ++#endif ++ ++#include ++ ++extern void ++__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key); ++ ++#define spin_lock_init(slock) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ rt_mutex_init(&(slock)->lock); \ ++ __rt_spin_lock_init(slock, #slock, &__key); \ ++} while (0) ++ ++extern void __lockfunc rt_spin_lock(spinlock_t *lock); ++extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock); ++extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass); ++extern void __lockfunc rt_spin_unlock(spinlock_t *lock); ++extern void __lockfunc rt_spin_unlock_wait(spinlock_t *lock); ++extern int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags); ++extern int __lockfunc rt_spin_trylock_bh(spinlock_t *lock); ++extern int __lockfunc rt_spin_trylock(spinlock_t *lock); ++extern int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock); ++ ++/* ++ * lockdep-less calls, for derived types like rwlock: ++ * (for trylock they can use rt_mutex_trylock() directly. ++ */ ++extern void __lockfunc __rt_spin_lock(struct rt_mutex *lock); ++extern void __lockfunc __rt_spin_unlock(struct rt_mutex *lock); ++ ++#define spin_lock(lock) \ ++ do { \ ++ migrate_disable(); \ ++ rt_spin_lock(lock); \ ++ } while (0) ++ ++#define spin_lock_bh(lock) \ ++ do { \ ++ local_bh_disable(); \ ++ migrate_disable(); \ ++ rt_spin_lock(lock); \ ++ } while (0) ++ ++#define spin_lock_irq(lock) spin_lock(lock) ++ ++#define spin_do_trylock(lock) __cond_lock(lock, rt_spin_trylock(lock)) ++ ++#define spin_trylock(lock) \ ++({ \ ++ int __locked; \ ++ migrate_disable(); \ ++ __locked = spin_do_trylock(lock); \ ++ if (!__locked) \ ++ migrate_enable(); \ ++ __locked; \ ++}) ++ ++#ifdef CONFIG_LOCKDEP ++# define spin_lock_nested(lock, subclass) \ ++ do { \ ++ migrate_disable(); \ ++ rt_spin_lock_nested(lock, subclass); \ ++ } while (0) ++ ++#define spin_lock_bh_nested(lock, subclass) \ ++ do { \ ++ local_bh_disable(); \ ++ migrate_disable(); \ ++ rt_spin_lock_nested(lock, subclass); \ ++ } while (0) ++ ++# define spin_lock_irqsave_nested(lock, flags, subclass) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = 0; \ ++ migrate_disable(); \ ++ rt_spin_lock_nested(lock, subclass); \ ++ } while (0) ++#else ++# define spin_lock_nested(lock, subclass) spin_lock(lock) ++# define spin_lock_bh_nested(lock, subclass) spin_lock_bh(lock) ++ ++# define spin_lock_irqsave_nested(lock, flags, subclass) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = 0; \ ++ spin_lock(lock); \ ++ } while (0) ++#endif ++ ++#define spin_lock_irqsave(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = 0; \ ++ spin_lock(lock); \ ++ } while (0) ++ ++static inline unsigned long spin_lock_trace_flags(spinlock_t *lock) ++{ ++ unsigned long flags = 0; ++#ifdef CONFIG_TRACE_IRQFLAGS ++ flags = rt_spin_lock_trace_flags(lock); ++#else ++ spin_lock(lock); /* lock_local */ ++#endif ++ return flags; ++} ++ ++/* FIXME: we need rt_spin_lock_nest_lock */ ++#define spin_lock_nest_lock(lock, nest_lock) spin_lock_nested(lock, 0) ++ ++#define spin_unlock(lock) \ ++ do { \ ++ rt_spin_unlock(lock); \ ++ migrate_enable(); \ ++ } while (0) ++ ++#define spin_unlock_bh(lock) \ ++ do { \ ++ rt_spin_unlock(lock); \ ++ migrate_enable(); \ ++ local_bh_enable(); \ ++ } while (0) ++ ++#define spin_unlock_irq(lock) spin_unlock(lock) ++ ++#define spin_unlock_irqrestore(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ (void) flags; \ ++ spin_unlock(lock); \ ++ } while (0) ++ ++#define spin_trylock_bh(lock) __cond_lock(lock, rt_spin_trylock_bh(lock)) ++#define spin_trylock_irq(lock) spin_trylock(lock) ++ ++#define spin_trylock_irqsave(lock, flags) \ ++ rt_spin_trylock_irqsave(lock, &(flags)) ++ ++#define spin_unlock_wait(lock) rt_spin_unlock_wait(lock) ++ ++#ifdef CONFIG_GENERIC_LOCKBREAK ++# define spin_is_contended(lock) ((lock)->break_lock) ++#else ++# define spin_is_contended(lock) (((void)(lock), 0)) ++#endif ++ ++static inline int spin_can_lock(spinlock_t *lock) ++{ ++ return !rt_mutex_is_locked(&lock->lock); ++} ++ ++static inline int spin_is_locked(spinlock_t *lock) ++{ ++ return rt_mutex_is_locked(&lock->lock); ++} ++ ++static inline void assert_spin_locked(spinlock_t *lock) ++{ ++ BUG_ON(!spin_is_locked(lock)); ++} ++ ++#define atomic_dec_and_lock(atomic, lock) \ ++ atomic_dec_and_spin_lock(atomic, lock) ++ ++#endif +--- a/include/linux/spinlock_types.h ++++ b/include/linux/spinlock_types.h +@@ -11,8 +11,13 @@ + + #include + +-#include +- +-#include ++#ifndef CONFIG_PREEMPT_RT_FULL ++# include ++# include ++#else ++# include ++# include ++# include ++#endif + + #endif /* __LINUX_SPINLOCK_TYPES_H */ +--- /dev/null ++++ b/include/linux/spinlock_types_rt.h +@@ -0,0 +1,51 @@ ++#ifndef __LINUX_SPINLOCK_TYPES_RT_H ++#define __LINUX_SPINLOCK_TYPES_RT_H ++ ++#ifndef __LINUX_SPINLOCK_TYPES_H ++#error "Do not include directly. Include spinlock_types.h instead" ++#endif ++ ++#include ++ ++/* ++ * PREEMPT_RT: spinlocks - an RT mutex plus lock-break field: ++ */ ++typedef struct spinlock { ++ struct rt_mutex lock; ++ unsigned int break_lock; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++} spinlock_t; ++ ++#ifdef CONFIG_DEBUG_RT_MUTEXES ++# define __RT_SPIN_INITIALIZER(name) \ ++ { \ ++ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ ++ .save_state = 1, \ ++ .file = __FILE__, \ ++ .line = __LINE__ , \ ++ } ++#else ++# define __RT_SPIN_INITIALIZER(name) \ ++ { \ ++ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ ++ .save_state = 1, \ ++ } ++#endif ++ ++/* ++.wait_list = PLIST_HEAD_INIT_RAW((name).lock.wait_list, (name).lock.wait_lock) ++*/ ++ ++#define __SPIN_LOCK_UNLOCKED(name) \ ++ { .lock = __RT_SPIN_INITIALIZER(name.lock), \ ++ SPIN_DEP_MAP_INIT(name) } ++ ++#define __DEFINE_SPINLOCK(name) \ ++ spinlock_t name = __SPIN_LOCK_UNLOCKED(name) ++ ++#define DEFINE_SPINLOCK(name) \ ++ spinlock_t name __cacheline_aligned_in_smp = __SPIN_LOCK_UNLOCKED(name) ++ ++#endif +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -2613,10 +2613,7 @@ static int futex_wait_requeue_pi(u32 __u + * The waiter is allocated on our stack, manipulated by the requeue + * code while we sleep on uaddr. + */ +- debug_rt_mutex_init_waiter(&rt_waiter); +- RB_CLEAR_NODE(&rt_waiter.pi_tree_entry); +- RB_CLEAR_NODE(&rt_waiter.tree_entry); +- rt_waiter.task = NULL; ++ rt_mutex_init_waiter(&rt_waiter, false); + + ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE); + if (unlikely(ret != 0)) +--- a/kernel/locking/Makefile ++++ b/kernel/locking/Makefile +@@ -1,5 +1,5 @@ + +-obj-y += mutex.o semaphore.o rwsem.o ++obj-y += semaphore.o + + ifdef CONFIG_FUNCTION_TRACER + CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE) +@@ -8,7 +8,11 @@ CFLAGS_REMOVE_mutex-debug.o = $(CC_FLAGS + CFLAGS_REMOVE_rtmutex-debug.o = $(CC_FLAGS_FTRACE) + endif + ++ifneq ($(CONFIG_PREEMPT_RT_FULL),y) ++obj-y += mutex.o + obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o ++obj-y += rwsem.o ++endif + obj-$(CONFIG_LOCKDEP) += lockdep.o + ifeq ($(CONFIG_PROC_FS),y) + obj-$(CONFIG_LOCKDEP) += lockdep_proc.o +@@ -22,8 +26,11 @@ obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmute + obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o + obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o + obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o ++ifneq ($(CONFIG_PREEMPT_RT_FULL),y) + obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o + obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o ++endif + obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o ++obj-$(CONFIG_PREEMPT_RT_FULL) += rt.o + obj-$(CONFIG_QUEUE_RWLOCK) += qrwlock.o + obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o +--- /dev/null ++++ b/kernel/locking/rt.c +@@ -0,0 +1,461 @@ ++/* ++ * kernel/rt.c ++ * ++ * Real-Time Preemption Support ++ * ++ * started by Ingo Molnar: ++ * ++ * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar ++ * Copyright (C) 2006, Timesys Corp., Thomas Gleixner ++ * ++ * historic credit for proving that Linux spinlocks can be implemented via ++ * RT-aware mutexes goes to many people: The Pmutex project (Dirk Grambow ++ * and others) who prototyped it on 2.4 and did lots of comparative ++ * research and analysis; TimeSys, for proving that you can implement a ++ * fully preemptible kernel via the use of IRQ threading and mutexes; ++ * Bill Huey for persuasively arguing on lkml that the mutex model is the ++ * right one; and to MontaVista, who ported pmutexes to 2.6. ++ * ++ * This code is a from-scratch implementation and is not based on pmutexes, ++ * but the idea of converting spinlocks to mutexes is used here too. ++ * ++ * lock debugging, locking tree, deadlock detection: ++ * ++ * Copyright (C) 2004, LynuxWorks, Inc., Igor Manyilov, Bill Huey ++ * Released under the General Public License (GPL). ++ * ++ * Includes portions of the generic R/W semaphore implementation from: ++ * ++ * Copyright (c) 2001 David Howells (dhowells@redhat.com). ++ * - Derived partially from idea by Andrea Arcangeli ++ * - Derived also from comments by Linus ++ * ++ * Pending ownership of locks and ownership stealing: ++ * ++ * Copyright (C) 2005, Kihon Technologies Inc., Steven Rostedt ++ * ++ * (also by Steven Rostedt) ++ * - Converted single pi_lock to individual task locks. ++ * ++ * By Esben Nielsen: ++ * Doing priority inheritance with help of the scheduler. ++ * ++ * Copyright (C) 2006, Timesys Corp., Thomas Gleixner ++ * - major rework based on Esben Nielsens initial patch ++ * - replaced thread_info references by task_struct refs ++ * - removed task->pending_owner dependency ++ * - BKL drop/reacquire for semaphore style locks to avoid deadlocks ++ * in the scheduler return path as discussed with Steven Rostedt ++ * ++ * Copyright (C) 2006, Kihon Technologies Inc. ++ * Steven Rostedt ++ * - debugged and patched Thomas Gleixner's rework. ++ * - added back the cmpxchg to the rework. ++ * - turned atomic require back on for SMP. ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++#include "rtmutex_common.h" ++ ++/* ++ * struct mutex functions ++ */ ++void __mutex_do_init(struct mutex *mutex, const char *name, ++ struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held lock: ++ */ ++ debug_check_no_locks_freed((void *)mutex, sizeof(*mutex)); ++ lockdep_init_map(&mutex->dep_map, name, key, 0); ++#endif ++ mutex->lock.save_state = 0; ++} ++EXPORT_SYMBOL(__mutex_do_init); ++ ++void __lockfunc _mutex_lock(struct mutex *lock) ++{ ++ mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++ rt_mutex_lock(&lock->lock); ++} ++EXPORT_SYMBOL(_mutex_lock); ++ ++int __lockfunc _mutex_lock_interruptible(struct mutex *lock) ++{ ++ int ret; ++ ++ mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++ ret = rt_mutex_lock_interruptible(&lock->lock); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_interruptible); ++ ++int __lockfunc _mutex_lock_killable(struct mutex *lock) ++{ ++ int ret; ++ ++ mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++ ret = rt_mutex_lock_killable(&lock->lock); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_killable); ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass) ++{ ++ mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); ++ rt_mutex_lock(&lock->lock); ++} ++EXPORT_SYMBOL(_mutex_lock_nested); ++ ++void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) ++{ ++ mutex_acquire_nest(&lock->dep_map, 0, 0, nest, _RET_IP_); ++ rt_mutex_lock(&lock->lock); ++} ++EXPORT_SYMBOL(_mutex_lock_nest_lock); ++ ++int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass) ++{ ++ int ret; ++ ++ mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); ++ ret = rt_mutex_lock_interruptible(&lock->lock); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_interruptible_nested); ++ ++int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass) ++{ ++ int ret; ++ ++ mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); ++ ret = rt_mutex_lock_killable(&lock->lock); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_killable_nested); ++#endif ++ ++int __lockfunc _mutex_trylock(struct mutex *lock) ++{ ++ int ret = rt_mutex_trylock(&lock->lock); ++ ++ if (ret) ++ mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_trylock); ++ ++void __lockfunc _mutex_unlock(struct mutex *lock) ++{ ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ rt_mutex_unlock(&lock->lock); ++} ++EXPORT_SYMBOL(_mutex_unlock); ++ ++/* ++ * rwlock_t functions ++ */ ++int __lockfunc rt_write_trylock(rwlock_t *rwlock) ++{ ++ int ret; ++ ++ migrate_disable(); ++ ret = rt_mutex_trylock(&rwlock->lock); ++ if (ret) ++ rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); ++ else ++ migrate_enable(); ++ ++ return ret; ++} ++EXPORT_SYMBOL(rt_write_trylock); ++ ++int __lockfunc rt_write_trylock_irqsave(rwlock_t *rwlock, unsigned long *flags) ++{ ++ int ret; ++ ++ *flags = 0; ++ ret = rt_write_trylock(rwlock); ++ return ret; ++} ++EXPORT_SYMBOL(rt_write_trylock_irqsave); ++ ++int __lockfunc rt_read_trylock(rwlock_t *rwlock) ++{ ++ struct rt_mutex *lock = &rwlock->lock; ++ int ret = 1; ++ ++ /* ++ * recursive read locks succeed when current owns the lock, ++ * but not when read_depth == 0 which means that the lock is ++ * write locked. ++ */ ++ if (rt_mutex_owner(lock) != current) { ++ migrate_disable(); ++ ret = rt_mutex_trylock(lock); ++ if (ret) ++ rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); ++ else ++ migrate_enable(); ++ ++ } else if (!rwlock->read_depth) { ++ ret = 0; ++ } ++ ++ if (ret) ++ rwlock->read_depth++; ++ ++ return ret; ++} ++EXPORT_SYMBOL(rt_read_trylock); ++ ++void __lockfunc rt_write_lock(rwlock_t *rwlock) ++{ ++ rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); ++ migrate_disable(); ++ __rt_spin_lock(&rwlock->lock); ++} ++EXPORT_SYMBOL(rt_write_lock); ++ ++void __lockfunc rt_read_lock(rwlock_t *rwlock) ++{ ++ struct rt_mutex *lock = &rwlock->lock; ++ ++ ++ /* ++ * recursive read locks succeed when current owns the lock ++ */ ++ if (rt_mutex_owner(lock) != current) { ++ migrate_disable(); ++ rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); ++ __rt_spin_lock(lock); ++ } ++ rwlock->read_depth++; ++} ++ ++EXPORT_SYMBOL(rt_read_lock); ++ ++void __lockfunc rt_write_unlock(rwlock_t *rwlock) ++{ ++ /* NOTE: we always pass in '1' for nested, for simplicity */ ++ rwlock_release(&rwlock->dep_map, 1, _RET_IP_); ++ __rt_spin_unlock(&rwlock->lock); ++ migrate_enable(); ++} ++EXPORT_SYMBOL(rt_write_unlock); ++ ++void __lockfunc rt_read_unlock(rwlock_t *rwlock) ++{ ++ /* Release the lock only when read_depth is down to 0 */ ++ if (--rwlock->read_depth == 0) { ++ rwlock_release(&rwlock->dep_map, 1, _RET_IP_); ++ __rt_spin_unlock(&rwlock->lock); ++ migrate_enable(); ++ } ++} ++EXPORT_SYMBOL(rt_read_unlock); ++ ++unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock) ++{ ++ rt_write_lock(rwlock); ++ ++ return 0; ++} ++EXPORT_SYMBOL(rt_write_lock_irqsave); ++ ++unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock) ++{ ++ rt_read_lock(rwlock); ++ ++ return 0; ++} ++EXPORT_SYMBOL(rt_read_lock_irqsave); ++ ++void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held lock: ++ */ ++ debug_check_no_locks_freed((void *)rwlock, sizeof(*rwlock)); ++ lockdep_init_map(&rwlock->dep_map, name, key, 0); ++#endif ++ rwlock->lock.save_state = 1; ++ rwlock->read_depth = 0; ++} ++EXPORT_SYMBOL(__rt_rwlock_init); ++ ++/* ++ * rw_semaphores ++ */ ++ ++void rt_up_write(struct rw_semaphore *rwsem) ++{ ++ rwsem_release(&rwsem->dep_map, 1, _RET_IP_); ++ rt_mutex_unlock(&rwsem->lock); ++} ++EXPORT_SYMBOL(rt_up_write); ++ ++void __rt_up_read(struct rw_semaphore *rwsem) ++{ ++ if (--rwsem->read_depth == 0) ++ rt_mutex_unlock(&rwsem->lock); ++} ++ ++void rt_up_read(struct rw_semaphore *rwsem) ++{ ++ rwsem_release(&rwsem->dep_map, 1, _RET_IP_); ++ __rt_up_read(rwsem); ++} ++EXPORT_SYMBOL(rt_up_read); ++ ++/* ++ * downgrade a write lock into a read lock ++ * - just wake up any readers at the front of the queue ++ */ ++void rt_downgrade_write(struct rw_semaphore *rwsem) ++{ ++ BUG_ON(rt_mutex_owner(&rwsem->lock) != current); ++ rwsem->read_depth = 1; ++} ++EXPORT_SYMBOL(rt_downgrade_write); ++ ++int rt_down_write_trylock(struct rw_semaphore *rwsem) ++{ ++ int ret = rt_mutex_trylock(&rwsem->lock); ++ ++ if (ret) ++ rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(rt_down_write_trylock); ++ ++void rt_down_write(struct rw_semaphore *rwsem) ++{ ++ rwsem_acquire(&rwsem->dep_map, 0, 0, _RET_IP_); ++ rt_mutex_lock(&rwsem->lock); ++} ++EXPORT_SYMBOL(rt_down_write); ++ ++void rt_down_write_nested(struct rw_semaphore *rwsem, int subclass) ++{ ++ rwsem_acquire(&rwsem->dep_map, subclass, 0, _RET_IP_); ++ rt_mutex_lock(&rwsem->lock); ++} ++EXPORT_SYMBOL(rt_down_write_nested); ++ ++void rt_down_write_nested_lock(struct rw_semaphore *rwsem, ++ struct lockdep_map *nest) ++{ ++ rwsem_acquire_nest(&rwsem->dep_map, 0, 0, nest, _RET_IP_); ++ rt_mutex_lock(&rwsem->lock); ++} ++EXPORT_SYMBOL(rt_down_write_nested_lock); ++ ++int rt_down_read_trylock(struct rw_semaphore *rwsem) ++{ ++ struct rt_mutex *lock = &rwsem->lock; ++ int ret = 1; ++ ++ /* ++ * recursive read locks succeed when current owns the rwsem, ++ * but not when read_depth == 0 which means that the rwsem is ++ * write locked. ++ */ ++ if (rt_mutex_owner(lock) != current) ++ ret = rt_mutex_trylock(&rwsem->lock); ++ else if (!rwsem->read_depth) ++ ret = 0; ++ ++ if (ret) { ++ rwsem->read_depth++; ++ rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_); ++ } ++ return ret; ++} ++EXPORT_SYMBOL(rt_down_read_trylock); ++ ++static void __rt_down_read(struct rw_semaphore *rwsem, int subclass) ++{ ++ struct rt_mutex *lock = &rwsem->lock; ++ ++ rwsem_acquire_read(&rwsem->dep_map, subclass, 0, _RET_IP_); ++ ++ if (rt_mutex_owner(lock) != current) ++ rt_mutex_lock(&rwsem->lock); ++ rwsem->read_depth++; ++} ++ ++void rt_down_read(struct rw_semaphore *rwsem) ++{ ++ __rt_down_read(rwsem, 0); ++} ++EXPORT_SYMBOL(rt_down_read); ++ ++void rt_down_read_nested(struct rw_semaphore *rwsem, int subclass) ++{ ++ __rt_down_read(rwsem, subclass); ++} ++EXPORT_SYMBOL(rt_down_read_nested); ++ ++void __rt_rwsem_init(struct rw_semaphore *rwsem, const char *name, ++ struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held lock: ++ */ ++ debug_check_no_locks_freed((void *)rwsem, sizeof(*rwsem)); ++ lockdep_init_map(&rwsem->dep_map, name, key, 0); ++#endif ++ rwsem->read_depth = 0; ++ rwsem->lock.save_state = 0; ++} ++EXPORT_SYMBOL(__rt_rwsem_init); ++ ++/** ++ * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0 ++ * @cnt: the atomic which we are to dec ++ * @lock: the mutex to return holding if we dec to 0 ++ * ++ * return true and hold lock if we dec to 0, return false otherwise ++ */ ++int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock) ++{ ++ /* dec if we can't possibly hit 0 */ ++ if (atomic_add_unless(cnt, -1, 1)) ++ return 0; ++ /* we might hit 0, so take the lock */ ++ mutex_lock(lock); ++ if (!atomic_dec_and_test(cnt)) { ++ /* when we actually did the dec, we didn't hit 0 */ ++ mutex_unlock(lock); ++ return 0; ++ } ++ /* we hit 0, and we hold the lock */ ++ return 1; ++} ++EXPORT_SYMBOL(atomic_dec_and_mutex_lock); +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -7,6 +7,11 @@ + * Copyright (C) 2005-2006 Timesys Corp., Thomas Gleixner + * Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt + * Copyright (C) 2006 Esben Nielsen ++ * Adaptive Spinlocks: ++ * Copyright (C) 2008 Novell, Inc., Gregory Haskins, Sven Dietrich, ++ * and Peter Morreale, ++ * Adaptive Spinlocks simplification: ++ * Copyright (C) 2008 Red Hat, Inc., Steven Rostedt + * + * See Documentation/locking/rt-mutex-design.txt for details. + */ +@@ -341,6 +346,14 @@ static bool rt_mutex_cond_detect_deadloc + return debug_rt_mutex_detect_deadlock(waiter, chwalk); + } + ++static void rt_mutex_wake_waiter(struct rt_mutex_waiter *waiter) ++{ ++ if (waiter->savestate) ++ wake_up_lock_sleeper(waiter->task); ++ else ++ wake_up_process(waiter->task); ++} ++ + /* + * Max number of times we'll walk the boosting chain: + */ +@@ -648,13 +661,16 @@ static int rt_mutex_adjust_prio_chain(st + * follow here. This is the end of the chain we are walking. + */ + if (!rt_mutex_owner(lock)) { ++ struct rt_mutex_waiter *lock_top_waiter; ++ + /* + * If the requeue [7] above changed the top waiter, + * then we need to wake the new top waiter up to try + * to get the lock. + */ +- if (prerequeue_top_waiter != rt_mutex_top_waiter(lock)) +- wake_up_process(rt_mutex_top_waiter(lock)->task); ++ lock_top_waiter = rt_mutex_top_waiter(lock); ++ if (prerequeue_top_waiter != lock_top_waiter) ++ rt_mutex_wake_waiter(lock_top_waiter); + raw_spin_unlock(&lock->wait_lock); + return 0; + } +@@ -747,6 +763,25 @@ static int rt_mutex_adjust_prio_chain(st + return ret; + } + ++ ++#define STEAL_NORMAL 0 ++#define STEAL_LATERAL 1 ++ ++/* ++ * Note that RT tasks are excluded from lateral-steals to prevent the ++ * introduction of an unbounded latency ++ */ ++static inline int lock_is_stealable(struct task_struct *task, ++ struct task_struct *pendowner, int mode) ++{ ++ if (mode == STEAL_NORMAL || rt_task(task)) { ++ if (task->prio >= pendowner->prio) ++ return 0; ++ } else if (task->prio > pendowner->prio) ++ return 0; ++ return 1; ++} ++ + /* + * Try to take an rt-mutex + * +@@ -757,8 +792,9 @@ static int rt_mutex_adjust_prio_chain(st + * @waiter: The waiter that is queued to the lock's wait list if the + * callsite called task_blocked_on_lock(), otherwise NULL + */ +-static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, +- struct rt_mutex_waiter *waiter) ++static int __try_to_take_rt_mutex(struct rt_mutex *lock, ++ struct task_struct *task, ++ struct rt_mutex_waiter *waiter, int mode) + { + unsigned long flags; + +@@ -797,8 +833,10 @@ static int try_to_take_rt_mutex(struct r + * If waiter is not the highest priority waiter of + * @lock, give up. + */ +- if (waiter != rt_mutex_top_waiter(lock)) ++ if (waiter != rt_mutex_top_waiter(lock)) { ++ /* XXX lock_is_stealable() ? */ + return 0; ++ } + + /* + * We can acquire the lock. Remove the waiter from the +@@ -816,14 +854,10 @@ static int try_to_take_rt_mutex(struct r + * not need to be dequeued. + */ + if (rt_mutex_has_waiters(lock)) { +- /* +- * If @task->prio is greater than or equal to +- * the top waiter priority (kernel view), +- * @task lost. +- */ +- if (task->prio >= rt_mutex_top_waiter(lock)->prio) +- return 0; ++ struct task_struct *pown = rt_mutex_top_waiter(lock)->task; + ++ if (task != pown && !lock_is_stealable(task, pown, mode)) ++ return 0; + /* + * The current top waiter stays enqueued. We + * don't have to change anything in the lock +@@ -872,6 +906,308 @@ static int try_to_take_rt_mutex(struct r + return 1; + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * preemptible spin_lock functions: ++ */ ++static inline void rt_spin_lock_fastlock(struct rt_mutex *lock, ++ void (*slowfn)(struct rt_mutex *lock)) ++{ ++ might_sleep_no_state_check(); ++ ++ if (likely(rt_mutex_cmpxchg(lock, NULL, current))) ++ rt_mutex_deadlock_account_lock(lock, current); ++ else ++ slowfn(lock); ++} ++ ++static inline void rt_spin_lock_fastunlock(struct rt_mutex *lock, ++ void (*slowfn)(struct rt_mutex *lock)) ++{ ++ if (likely(rt_mutex_cmpxchg(lock, current, NULL))) ++ rt_mutex_deadlock_account_unlock(current); ++ else ++ slowfn(lock); ++} ++#ifdef CONFIG_SMP ++/* ++ * Note that owner is a speculative pointer and dereferencing relies ++ * on rcu_read_lock() and the check against the lock owner. ++ */ ++static int adaptive_wait(struct rt_mutex *lock, ++ struct task_struct *owner) ++{ ++ int res = 0; ++ ++ rcu_read_lock(); ++ for (;;) { ++ if (owner != rt_mutex_owner(lock)) ++ break; ++ /* ++ * Ensure that owner->on_cpu is dereferenced _after_ ++ * checking the above to be valid. ++ */ ++ barrier(); ++ if (!owner->on_cpu) { ++ res = 1; ++ break; ++ } ++ cpu_relax(); ++ } ++ rcu_read_unlock(); ++ return res; ++} ++#else ++static int adaptive_wait(struct rt_mutex *lock, ++ struct task_struct *orig_owner) ++{ ++ return 1; ++} ++#endif ++ ++# define pi_lock(lock) raw_spin_lock_irq(lock) ++# define pi_unlock(lock) raw_spin_unlock_irq(lock) ++ ++static int task_blocks_on_rt_mutex(struct rt_mutex *lock, ++ struct rt_mutex_waiter *waiter, ++ struct task_struct *task, ++ enum rtmutex_chainwalk chwalk); ++/* ++ * Slow path lock function spin_lock style: this variant is very ++ * careful not to miss any non-lock wakeups. ++ * ++ * We store the current state under p->pi_lock in p->saved_state and ++ * the try_to_wake_up() code handles this accordingly. ++ */ ++static void noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock) ++{ ++ struct task_struct *lock_owner, *self = current; ++ struct rt_mutex_waiter waiter, *top_waiter; ++ int ret; ++ ++ rt_mutex_init_waiter(&waiter, true); ++ ++ raw_spin_lock(&lock->wait_lock); ++ ++ if (__try_to_take_rt_mutex(lock, self, NULL, STEAL_LATERAL)) { ++ raw_spin_unlock(&lock->wait_lock); ++ return; ++ } ++ ++ BUG_ON(rt_mutex_owner(lock) == self); ++ ++ /* ++ * We save whatever state the task is in and we'll restore it ++ * after acquiring the lock taking real wakeups into account ++ * as well. We are serialized via pi_lock against wakeups. See ++ * try_to_wake_up(). ++ */ ++ pi_lock(&self->pi_lock); ++ self->saved_state = self->state; ++ __set_current_state_no_track(TASK_UNINTERRUPTIBLE); ++ pi_unlock(&self->pi_lock); ++ ++ ret = task_blocks_on_rt_mutex(lock, &waiter, self, 0); ++ BUG_ON(ret); ++ ++ for (;;) { ++ /* Try to acquire the lock again. */ ++ if (__try_to_take_rt_mutex(lock, self, &waiter, STEAL_LATERAL)) ++ break; ++ ++ top_waiter = rt_mutex_top_waiter(lock); ++ lock_owner = rt_mutex_owner(lock); ++ ++ raw_spin_unlock(&lock->wait_lock); ++ ++ debug_rt_mutex_print_deadlock(&waiter); ++ ++ if (top_waiter != &waiter || adaptive_wait(lock, lock_owner)) ++ schedule_rt_mutex(lock); ++ ++ raw_spin_lock(&lock->wait_lock); ++ ++ pi_lock(&self->pi_lock); ++ __set_current_state_no_track(TASK_UNINTERRUPTIBLE); ++ pi_unlock(&self->pi_lock); ++ } ++ ++ /* ++ * Restore the task state to current->saved_state. We set it ++ * to the original state above and the try_to_wake_up() code ++ * has possibly updated it when a real (non-rtmutex) wakeup ++ * happened while we were blocked. Clear saved_state so ++ * try_to_wakeup() does not get confused. ++ */ ++ pi_lock(&self->pi_lock); ++ __set_current_state_no_track(self->saved_state); ++ self->saved_state = TASK_RUNNING; ++ pi_unlock(&self->pi_lock); ++ ++ /* ++ * try_to_take_rt_mutex() sets the waiter bit ++ * unconditionally. We might have to fix that up: ++ */ ++ fixup_rt_mutex_waiters(lock); ++ ++ BUG_ON(rt_mutex_has_waiters(lock) && &waiter == rt_mutex_top_waiter(lock)); ++ BUG_ON(!RB_EMPTY_NODE(&waiter.tree_entry)); ++ ++ raw_spin_unlock(&lock->wait_lock); ++ ++ debug_rt_mutex_free_waiter(&waiter); ++} ++ ++static void wakeup_next_waiter(struct rt_mutex *lock); ++/* ++ * Slow path to release a rt_mutex spin_lock style ++ */ ++static void noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) ++{ ++ raw_spin_lock(&lock->wait_lock); ++ ++ debug_rt_mutex_unlock(lock); ++ ++ rt_mutex_deadlock_account_unlock(current); ++ ++ if (!rt_mutex_has_waiters(lock)) { ++ lock->owner = NULL; ++ raw_spin_unlock(&lock->wait_lock); ++ return; ++ } ++ ++ wakeup_next_waiter(lock); ++ ++ raw_spin_unlock(&lock->wait_lock); ++ ++ /* Undo pi boosting.when necessary */ ++ rt_mutex_adjust_prio(current); ++} ++ ++void __lockfunc rt_spin_lock(spinlock_t *lock) ++{ ++ rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); ++ spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++} ++EXPORT_SYMBOL(rt_spin_lock); ++ ++void __lockfunc __rt_spin_lock(struct rt_mutex *lock) ++{ ++ rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock); ++} ++EXPORT_SYMBOL(__rt_spin_lock); ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass) ++{ ++ rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); ++ spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); ++} ++EXPORT_SYMBOL(rt_spin_lock_nested); ++#endif ++ ++void __lockfunc rt_spin_unlock(spinlock_t *lock) ++{ ++ /* NOTE: we always pass in '1' for nested, for simplicity */ ++ spin_release(&lock->dep_map, 1, _RET_IP_); ++ rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock); ++} ++EXPORT_SYMBOL(rt_spin_unlock); ++ ++void __lockfunc __rt_spin_unlock(struct rt_mutex *lock) ++{ ++ rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock); ++} ++EXPORT_SYMBOL(__rt_spin_unlock); ++ ++/* ++ * Wait for the lock to get unlocked: instead of polling for an unlock ++ * (like raw spinlocks do), we lock and unlock, to force the kernel to ++ * schedule if there's contention: ++ */ ++void __lockfunc rt_spin_unlock_wait(spinlock_t *lock) ++{ ++ spin_lock(lock); ++ spin_unlock(lock); ++} ++EXPORT_SYMBOL(rt_spin_unlock_wait); ++ ++int __lockfunc rt_spin_trylock(spinlock_t *lock) ++{ ++ int ret = rt_mutex_trylock(&lock->lock); ++ ++ if (ret) ++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(rt_spin_trylock); ++ ++int __lockfunc rt_spin_trylock_bh(spinlock_t *lock) ++{ ++ int ret; ++ ++ local_bh_disable(); ++ ret = rt_mutex_trylock(&lock->lock); ++ if (ret) { ++ migrate_disable(); ++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ } else ++ local_bh_enable(); ++ return ret; ++} ++EXPORT_SYMBOL(rt_spin_trylock_bh); ++ ++int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags) ++{ ++ int ret; ++ ++ *flags = 0; ++ ret = rt_mutex_trylock(&lock->lock); ++ if (ret) { ++ migrate_disable(); ++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ } ++ return ret; ++} ++EXPORT_SYMBOL(rt_spin_trylock_irqsave); ++ ++int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock) ++{ ++ /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ ++ if (atomic_add_unless(atomic, -1, 1)) ++ return 0; ++ migrate_disable(); ++ rt_spin_lock(lock); ++ if (atomic_dec_and_test(atomic)) ++ return 1; ++ rt_spin_unlock(lock); ++ migrate_enable(); ++ return 0; ++} ++EXPORT_SYMBOL(atomic_dec_and_spin_lock); ++ ++ void ++__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held lock: ++ */ ++ debug_check_no_locks_freed((void *)lock, sizeof(*lock)); ++ lockdep_init_map(&lock->dep_map, name, key, 0); ++#endif ++} ++EXPORT_SYMBOL(__rt_spin_lock_init); ++ ++#endif /* PREEMPT_RT_FULL */ ++ ++static inline int ++try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, ++ struct rt_mutex_waiter *waiter) ++{ ++ return __try_to_take_rt_mutex(lock, task, waiter, STEAL_NORMAL); ++} ++ + /* + * Task blocks on lock. + * +@@ -1021,7 +1357,7 @@ static void wakeup_next_waiter(struct rt + * long as we hold lock->wait_lock. The waiter task needs to + * acquire it in order to dequeue the waiter. + */ +- wake_up_process(waiter->task); ++ rt_mutex_wake_waiter(waiter); + } + + /* +@@ -1103,11 +1439,11 @@ void rt_mutex_adjust_pi(struct task_stru + return; + } + next_lock = waiter->lock; +- raw_spin_unlock_irqrestore(&task->pi_lock, flags); + + /* gets dropped in rt_mutex_adjust_prio_chain()! */ + get_task_struct(task); + ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); + rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL, + next_lock, NULL, task); + } +@@ -1193,9 +1529,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, + struct rt_mutex_waiter waiter; + int ret = 0; + +- debug_rt_mutex_init_waiter(&waiter); +- RB_CLEAR_NODE(&waiter.pi_tree_entry); +- RB_CLEAR_NODE(&waiter.tree_entry); ++ rt_mutex_init_waiter(&waiter, false); + + raw_spin_lock(&lock->wait_lock); + +@@ -1554,13 +1888,12 @@ EXPORT_SYMBOL_GPL(rt_mutex_destroy); + void __rt_mutex_init(struct rt_mutex *lock, const char *name) + { + lock->owner = NULL; +- raw_spin_lock_init(&lock->wait_lock); + lock->waiters = RB_ROOT; + lock->waiters_leftmost = NULL; + + debug_rt_mutex_init(lock, name); + } +-EXPORT_SYMBOL_GPL(__rt_mutex_init); ++EXPORT_SYMBOL(__rt_mutex_init); + + /** + * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a +@@ -1575,7 +1908,7 @@ EXPORT_SYMBOL_GPL(__rt_mutex_init); + void rt_mutex_init_proxy_locked(struct rt_mutex *lock, + struct task_struct *proxy_owner) + { +- __rt_mutex_init(lock, NULL); ++ rt_mutex_init(lock); + debug_rt_mutex_proxy_lock(lock, proxy_owner); + rt_mutex_set_owner(lock, proxy_owner); + rt_mutex_deadlock_account_lock(lock, proxy_owner); +@@ -1737,3 +2070,25 @@ int rt_mutex_finish_proxy_lock(struct rt + + return ret; + } ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++struct ww_mutex { ++}; ++struct ww_acquire_ctx { ++}; ++int __ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) ++{ ++ BUG(); ++} ++EXPORT_SYMBOL_GPL(__ww_mutex_lock); ++int __ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) ++{ ++ BUG(); ++} ++EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible); ++void __sched ww_mutex_unlock(struct ww_mutex *lock) ++{ ++ BUG(); ++} ++EXPORT_SYMBOL_GPL(ww_mutex_unlock); ++#endif +--- a/kernel/locking/rtmutex_common.h ++++ b/kernel/locking/rtmutex_common.h +@@ -49,6 +49,7 @@ struct rt_mutex_waiter { + struct rb_node pi_tree_entry; + struct task_struct *task; + struct rt_mutex *lock; ++ bool savestate; + #ifdef CONFIG_DEBUG_RT_MUTEXES + unsigned long ip; + struct pid *deadlock_task_pid; +@@ -145,4 +146,14 @@ extern void rt_mutex_adjust_prio(struct + # include "rtmutex.h" + #endif + ++static inline void ++rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savestate) ++{ ++ debug_rt_mutex_init_waiter(waiter); ++ waiter->task = NULL; ++ waiter->savestate = savestate; ++ RB_CLEAR_NODE(&waiter->pi_tree_entry); ++ RB_CLEAR_NODE(&waiter->tree_entry); ++} ++ + #endif +--- a/kernel/locking/spinlock.c ++++ b/kernel/locking/spinlock.c +@@ -124,8 +124,11 @@ void __lockfunc __raw_##op##_lock_bh(loc + * __[spin|read|write]_lock_bh() + */ + BUILD_LOCK_OPS(spin, raw_spinlock); ++ ++#ifndef CONFIG_PREEMPT_RT_FULL + BUILD_LOCK_OPS(read, rwlock); + BUILD_LOCK_OPS(write, rwlock); ++#endif + + #endif + +@@ -209,6 +212,8 @@ void __lockfunc _raw_spin_unlock_bh(raw_ + EXPORT_SYMBOL(_raw_spin_unlock_bh); + #endif + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #ifndef CONFIG_INLINE_READ_TRYLOCK + int __lockfunc _raw_read_trylock(rwlock_t *lock) + { +@@ -353,6 +358,8 @@ void __lockfunc _raw_write_unlock_bh(rwl + EXPORT_SYMBOL(_raw_write_unlock_bh); + #endif + ++#endif /* !PREEMPT_RT_FULL */ ++ + #ifdef CONFIG_DEBUG_LOCK_ALLOC + + void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass) +--- a/kernel/locking/spinlock_debug.c ++++ b/kernel/locking/spinlock_debug.c +@@ -31,6 +31,7 @@ void __raw_spin_lock_init(raw_spinlock_t + + EXPORT_SYMBOL(__raw_spin_lock_init); + ++#ifndef CONFIG_PREEMPT_RT_FULL + void __rwlock_init(rwlock_t *lock, const char *name, + struct lock_class_key *key) + { +@@ -48,6 +49,7 @@ void __rwlock_init(rwlock_t *lock, const + } + + EXPORT_SYMBOL(__rwlock_init); ++#endif + + static void spin_dump(raw_spinlock_t *lock, const char *msg) + { +@@ -159,6 +161,7 @@ void do_raw_spin_unlock(raw_spinlock_t * + arch_spin_unlock(&lock->raw_lock); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + static void rwlock_bug(rwlock_t *lock, const char *msg) + { + if (!debug_locks_off()) +@@ -300,3 +303,5 @@ void do_raw_write_unlock(rwlock_t *lock) + debug_write_unlock(lock); + arch_write_unlock(&lock->raw_lock); + } ++ ++#endif diff --git a/debian/patches/features/all/rt/rt-introduce-cpu-chill.patch b/debian/patches/features/all/rt/rt-introduce-cpu-chill.patch new file mode 100644 index 000000000..4c6415f3c --- /dev/null +++ b/debian/patches/features/all/rt/rt-introduce-cpu-chill.patch @@ -0,0 +1,129 @@ +Subject: rt: Introduce cpu_chill() +From: Thomas Gleixner +Date: Wed, 07 Mar 2012 20:51:03 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Retry loops on RT might loop forever when the modifying side was +preempted. Add cpu_chill() to replace cpu_relax(). cpu_chill() +defaults to cpu_relax() for non RT. On RT it puts the looping task to +sleep for a tick so the preempted task can make progress. + +Steven Rostedt changed it to use a hrtimer instead of msleep(): +| +|Ulrich Obergfell pointed out that cpu_chill() calls msleep() which is woken +|up by the ksoftirqd running the TIMER softirq. But as the cpu_chill() is +|called from softirq context, it may block the ksoftirqd() from running, in +|which case, it may never wake up the msleep() causing the deadlock. +| +|I checked the vmcore, and irq/74-qla2xxx is stuck in the msleep() call, +|running on CPU 8. The one ksoftirqd that is stuck, happens to be the one that +|runs on CPU 8, and it is blocked on a lock held by irq/74-qla2xxx. As that +|ksoftirqd is the one that will wake up irq/74-qla2xxx, and it happens to be +|blocked on a lock that irq/74-qla2xxx holds, we have our deadlock. +| +|The solution is not to convert the cpu_chill() back to a cpu_relax() as that +|will re-create a possible live lock that the cpu_chill() fixed earlier, and may +|also leave this bug open on other softirqs. The fix is to remove the +|dependency on ksoftirqd from cpu_chill(). That is, instead of calling +|msleep() that requires ksoftirqd to wake it up, use the +|hrtimer_nanosleep() code that does the wakeup from hard irq context. +| +||Looks to be the lock of the block softirq. I don't have the core dump +||anymore, but from what I could tell the ksoftirqd was blocked on the +||block softirq lock, where the block softirq handler did a msleep +||(called by the qla2xxx interrupt handler). +|| +||Looking at trigger_softirq() in block/blk-softirq.c, it can do a +||smp_callfunction() to another cpu to run the block softirq. If that +||happens to be the cpu where the qla2xx irq handler is doing the block +||softirq and is in a middle of a msleep(), I believe the ksoftirqd will +||try to run the softirq. If it does that, then BOOM, it's deadlocked +||because the ksoftirqd will never run the timer softirq either. +| +||I should have also stated that it was only one lock that was involved. +||But the lock owner was doing a msleep() that requires a wakeup by +||ksoftirqd to continue. If ksoftirqd happens to be blocked on a lock +||held by the msleep() caller, then you have your deadlock. +|| +||It's best not to have any softirqs going to sleep requiring another +||softirq to wake it up. Note, if we ever require a timer softirq to do a +||cpu_chill() it will most definitely hit this deadlock. + ++ bigeasy: add PF_NOFREEZE: +| [....] Waiting for /dev to be fully populated... +| ===================================== +| [ BUG: udevd/229 still has locks held! ] +| 3.12.11-rt17 #23 Not tainted +| ------------------------------------- +| 1 lock held by udevd/229: +| #0: (&type->i_mutex_dir_key#2){+.+.+.}, at: lookup_slow+0x28/0x98 +| +| stack backtrace: +| CPU: 0 PID: 229 Comm: udevd Not tainted 3.12.11-rt17 #23 +| (unwind_backtrace+0x0/0xf8) from (show_stack+0x10/0x14) +| (show_stack+0x10/0x14) from (dump_stack+0x74/0xbc) +| (dump_stack+0x74/0xbc) from (do_nanosleep+0x120/0x160) +| (do_nanosleep+0x120/0x160) from (hrtimer_nanosleep+0x90/0x110) +| (hrtimer_nanosleep+0x90/0x110) from (cpu_chill+0x30/0x38) +| (cpu_chill+0x30/0x38) from (dentry_kill+0x158/0x1ec) +| (dentry_kill+0x158/0x1ec) from (dput+0x74/0x15c) +| (dput+0x74/0x15c) from (lookup_real+0x4c/0x50) +| (lookup_real+0x4c/0x50) from (__lookup_hash+0x34/0x44) +| (__lookup_hash+0x34/0x44) from (lookup_slow+0x38/0x98) +| (lookup_slow+0x38/0x98) from (path_lookupat+0x208/0x7fc) +| (path_lookupat+0x208/0x7fc) from (filename_lookup+0x20/0x60) +| (filename_lookup+0x20/0x60) from (user_path_at_empty+0x50/0x7c) +| (user_path_at_empty+0x50/0x7c) from (user_path_at+0x14/0x1c) +| (user_path_at+0x14/0x1c) from (vfs_fstatat+0x48/0x94) +| (vfs_fstatat+0x48/0x94) from (SyS_stat64+0x14/0x30) +| (SyS_stat64+0x14/0x30) from (ret_fast_syscall+0x0/0x48) + +Signed-off-by: Thomas Gleixner +Signed-off-by: Steven Rostedt +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/delay.h | 6 ++++++ + kernel/time/hrtimer.c | 19 +++++++++++++++++++ + 2 files changed, 25 insertions(+) + +--- a/include/linux/delay.h ++++ b/include/linux/delay.h +@@ -52,4 +52,10 @@ static inline void ssleep(unsigned int s + msleep(seconds * 1000); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++extern void cpu_chill(void); ++#else ++# define cpu_chill() cpu_relax() ++#endif ++ + #endif /* defined(_LINUX_DELAY_H) */ +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -1867,6 +1867,25 @@ SYSCALL_DEFINE2(nanosleep, struct timesp + return hrtimer_nanosleep(&tu, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * Sleep for 1 ms in hope whoever holds what we want will let it go. ++ */ ++void cpu_chill(void) ++{ ++ struct timespec tu = { ++ .tv_nsec = NSEC_PER_MSEC, ++ }; ++ unsigned int freeze_flag = current->flags & PF_NOFREEZE; ++ ++ current->flags |= PF_NOFREEZE; ++ hrtimer_nanosleep(&tu, NULL, HRTIMER_MODE_REL, CLOCK_MONOTONIC); ++ if (!freeze_flag) ++ current->flags &= ~PF_NOFREEZE; ++} ++EXPORT_SYMBOL(cpu_chill); ++#endif ++ + /* + * Functions related to boot-time initialization: + */ diff --git a/debian/patches/features/all/rt/rt-local-irq-lock.patch b/debian/patches/features/all/rt/rt-local-irq-lock.patch new file mode 100644 index 000000000..d4d68b9ba --- /dev/null +++ b/debian/patches/features/all/rt/rt-local-irq-lock.patch @@ -0,0 +1,324 @@ +Subject: rt: Add local irq locks +From: Thomas Gleixner +Date: Mon, 20 Jun 2011 09:03:47 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Introduce locallock. For !RT this maps to preempt_disable()/ +local_irq_disable() so there is not much that changes. For RT this will +map to a spinlock. This makes preemption possible and locked "ressource" +gets the lockdep anotation it wouldn't have otherwise. The locks are +recursive for owner == current. Also, all locks user migrate_disable() +which ensures that the task is not migrated to another CPU while the lock +is held and the owner is preempted. + +Signed-off-by: Thomas Gleixner +--- + include/linux/locallock.h | 264 ++++++++++++++++++++++++++++++++++++++++++++++ + include/linux/percpu.h | 29 +++++ + 2 files changed, 293 insertions(+) + +--- /dev/null ++++ b/include/linux/locallock.h +@@ -0,0 +1,264 @@ ++#ifndef _LINUX_LOCALLOCK_H ++#define _LINUX_LOCALLOCK_H ++ ++#include ++#include ++ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ ++#ifdef CONFIG_DEBUG_SPINLOCK ++# define LL_WARN(cond) WARN_ON(cond) ++#else ++# define LL_WARN(cond) do { } while (0) ++#endif ++ ++/* ++ * per cpu lock based substitute for local_irq_*() ++ */ ++struct local_irq_lock { ++ spinlock_t lock; ++ struct task_struct *owner; ++ int nestcnt; ++ unsigned long flags; ++}; ++ ++#define DEFINE_LOCAL_IRQ_LOCK(lvar) \ ++ DEFINE_PER_CPU(struct local_irq_lock, lvar) = { \ ++ .lock = __SPIN_LOCK_UNLOCKED((lvar).lock) } ++ ++#define DECLARE_LOCAL_IRQ_LOCK(lvar) \ ++ DECLARE_PER_CPU(struct local_irq_lock, lvar) ++ ++#define local_irq_lock_init(lvar) \ ++ do { \ ++ int __cpu; \ ++ for_each_possible_cpu(__cpu) \ ++ spin_lock_init(&per_cpu(lvar, __cpu).lock); \ ++ } while (0) ++ ++/* ++ * spin_lock|trylock|unlock_local flavour that does not migrate disable ++ * used for __local_lock|trylock|unlock where get_local_var/put_local_var ++ * already takes care of the migrate_disable/enable ++ * for CONFIG_PREEMPT_BASE map to the normal spin_* calls. ++ */ ++# define spin_lock_local(lock) spin_lock(lock) ++# define spin_trylock_local(lock) spin_trylock(lock) ++# define spin_unlock_local(lock) spin_unlock(lock) ++ ++static inline void __local_lock(struct local_irq_lock *lv) ++{ ++ if (lv->owner != current) { ++ spin_lock_local(&lv->lock); ++ LL_WARN(lv->owner); ++ LL_WARN(lv->nestcnt); ++ lv->owner = current; ++ } ++ lv->nestcnt++; ++} ++ ++#define local_lock(lvar) \ ++ do { __local_lock(&get_local_var(lvar)); } while (0) ++ ++static inline int __local_trylock(struct local_irq_lock *lv) ++{ ++ if (lv->owner != current && spin_trylock_local(&lv->lock)) { ++ LL_WARN(lv->owner); ++ LL_WARN(lv->nestcnt); ++ lv->owner = current; ++ lv->nestcnt = 1; ++ return 1; ++ } ++ return 0; ++} ++ ++#define local_trylock(lvar) \ ++ ({ \ ++ int __locked; \ ++ __locked = __local_trylock(&get_local_var(lvar)); \ ++ if (!__locked) \ ++ put_local_var(lvar); \ ++ __locked; \ ++ }) ++ ++static inline void __local_unlock(struct local_irq_lock *lv) ++{ ++ LL_WARN(lv->nestcnt == 0); ++ LL_WARN(lv->owner != current); ++ if (--lv->nestcnt) ++ return; ++ ++ lv->owner = NULL; ++ spin_unlock_local(&lv->lock); ++} ++ ++#define local_unlock(lvar) \ ++ do { \ ++ __local_unlock(this_cpu_ptr(&lvar)); \ ++ put_local_var(lvar); \ ++ } while (0) ++ ++static inline void __local_lock_irq(struct local_irq_lock *lv) ++{ ++ spin_lock_irqsave(&lv->lock, lv->flags); ++ LL_WARN(lv->owner); ++ LL_WARN(lv->nestcnt); ++ lv->owner = current; ++ lv->nestcnt = 1; ++} ++ ++#define local_lock_irq(lvar) \ ++ do { __local_lock_irq(&get_local_var(lvar)); } while (0) ++ ++#define local_lock_irq_on(lvar, cpu) \ ++ do { __local_lock_irq(&per_cpu(lvar, cpu)); } while (0) ++ ++static inline void __local_unlock_irq(struct local_irq_lock *lv) ++{ ++ LL_WARN(!lv->nestcnt); ++ LL_WARN(lv->owner != current); ++ lv->owner = NULL; ++ lv->nestcnt = 0; ++ spin_unlock_irq(&lv->lock); ++} ++ ++#define local_unlock_irq(lvar) \ ++ do { \ ++ __local_unlock_irq(this_cpu_ptr(&lvar)); \ ++ put_local_var(lvar); \ ++ } while (0) ++ ++#define local_unlock_irq_on(lvar, cpu) \ ++ do { \ ++ __local_unlock_irq(&per_cpu(lvar, cpu)); \ ++ } while (0) ++ ++static inline int __local_lock_irqsave(struct local_irq_lock *lv) ++{ ++ if (lv->owner != current) { ++ __local_lock_irq(lv); ++ return 0; ++ } else { ++ lv->nestcnt++; ++ return 1; ++ } ++} ++ ++#define local_lock_irqsave(lvar, _flags) \ ++ do { \ ++ if (__local_lock_irqsave(&get_local_var(lvar))) \ ++ put_local_var(lvar); \ ++ _flags = __this_cpu_read(lvar.flags); \ ++ } while (0) ++ ++#define local_lock_irqsave_on(lvar, _flags, cpu) \ ++ do { \ ++ __local_lock_irqsave(&per_cpu(lvar, cpu)); \ ++ _flags = per_cpu(lvar, cpu).flags; \ ++ } while (0) ++ ++static inline int __local_unlock_irqrestore(struct local_irq_lock *lv, ++ unsigned long flags) ++{ ++ LL_WARN(!lv->nestcnt); ++ LL_WARN(lv->owner != current); ++ if (--lv->nestcnt) ++ return 0; ++ ++ lv->owner = NULL; ++ spin_unlock_irqrestore(&lv->lock, lv->flags); ++ return 1; ++} ++ ++#define local_unlock_irqrestore(lvar, flags) \ ++ do { \ ++ if (__local_unlock_irqrestore(this_cpu_ptr(&lvar), flags)) \ ++ put_local_var(lvar); \ ++ } while (0) ++ ++#define local_unlock_irqrestore_on(lvar, flags, cpu) \ ++ do { \ ++ __local_unlock_irqrestore(&per_cpu(lvar, cpu), flags); \ ++ } while (0) ++ ++#define local_spin_trylock_irq(lvar, lock) \ ++ ({ \ ++ int __locked; \ ++ local_lock_irq(lvar); \ ++ __locked = spin_trylock(lock); \ ++ if (!__locked) \ ++ local_unlock_irq(lvar); \ ++ __locked; \ ++ }) ++ ++#define local_spin_lock_irq(lvar, lock) \ ++ do { \ ++ local_lock_irq(lvar); \ ++ spin_lock(lock); \ ++ } while (0) ++ ++#define local_spin_unlock_irq(lvar, lock) \ ++ do { \ ++ spin_unlock(lock); \ ++ local_unlock_irq(lvar); \ ++ } while (0) ++ ++#define local_spin_lock_irqsave(lvar, lock, flags) \ ++ do { \ ++ local_lock_irqsave(lvar, flags); \ ++ spin_lock(lock); \ ++ } while (0) ++ ++#define local_spin_unlock_irqrestore(lvar, lock, flags) \ ++ do { \ ++ spin_unlock(lock); \ ++ local_unlock_irqrestore(lvar, flags); \ ++ } while (0) ++ ++#define get_locked_var(lvar, var) \ ++ (*({ \ ++ local_lock(lvar); \ ++ this_cpu_ptr(&var); \ ++ })) ++ ++#define put_locked_var(lvar, var) local_unlock(lvar); ++ ++#define local_lock_cpu(lvar) \ ++ ({ \ ++ local_lock(lvar); \ ++ smp_processor_id(); \ ++ }) ++ ++#define local_unlock_cpu(lvar) local_unlock(lvar) ++ ++#else /* PREEMPT_RT_BASE */ ++ ++#define DEFINE_LOCAL_IRQ_LOCK(lvar) __typeof__(const int) lvar ++#define DECLARE_LOCAL_IRQ_LOCK(lvar) extern __typeof__(const int) lvar ++ ++static inline void local_irq_lock_init(int lvar) { } ++ ++#define local_lock(lvar) preempt_disable() ++#define local_unlock(lvar) preempt_enable() ++#define local_lock_irq(lvar) local_irq_disable() ++#define local_unlock_irq(lvar) local_irq_enable() ++#define local_lock_irqsave(lvar, flags) local_irq_save(flags) ++#define local_unlock_irqrestore(lvar, flags) local_irq_restore(flags) ++ ++#define local_spin_trylock_irq(lvar, lock) spin_trylock_irq(lock) ++#define local_spin_lock_irq(lvar, lock) spin_lock_irq(lock) ++#define local_spin_unlock_irq(lvar, lock) spin_unlock_irq(lock) ++#define local_spin_lock_irqsave(lvar, lock, flags) \ ++ spin_lock_irqsave(lock, flags) ++#define local_spin_unlock_irqrestore(lvar, lock, flags) \ ++ spin_unlock_irqrestore(lock, flags) ++ ++#define get_locked_var(lvar, var) get_cpu_var(var) ++#define put_locked_var(lvar, var) put_cpu_var(var) ++ ++#define local_lock_cpu(lvar) get_cpu() ++#define local_unlock_cpu(lvar) put_cpu() ++ ++#endif ++ ++#endif +--- a/include/linux/percpu.h ++++ b/include/linux/percpu.h +@@ -24,6 +24,35 @@ + PERCPU_MODULE_RESERVE) + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++#define get_local_var(var) (*({ \ ++ migrate_disable(); \ ++ this_cpu_ptr(&var); })) ++ ++#define put_local_var(var) do { \ ++ (void)&(var); \ ++ migrate_enable(); \ ++} while (0) ++ ++# define get_local_ptr(var) ({ \ ++ migrate_disable(); \ ++ this_cpu_ptr(var); }) ++ ++# define put_local_ptr(var) do { \ ++ (void)(var); \ ++ migrate_enable(); \ ++} while (0) ++ ++#else ++ ++#define get_local_var(var) get_cpu_var(var) ++#define put_local_var(var) put_cpu_var(var) ++#define get_local_ptr(var) get_cpu_ptr(var) ++#define put_local_ptr(var) put_cpu_ptr(var) ++ ++#endif ++ + /* minimum unit size, also is the maximum supported allocation size */ + #define PCPU_MIN_UNIT_SIZE PFN_ALIGN(32 << 10) + diff --git a/debian/patches/features/all/rt/rt-preempt-base-config.patch b/debian/patches/features/all/rt/rt-preempt-base-config.patch new file mode 100644 index 000000000..0a666be69 --- /dev/null +++ b/debian/patches/features/all/rt/rt-preempt-base-config.patch @@ -0,0 +1,54 @@ +Subject: rt: Provide PREEMPT_RT_BASE config switch +From: Thomas Gleixner +Date: Fri, 17 Jun 2011 12:39:57 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Introduce PREEMPT_RT_BASE which enables parts of +PREEMPT_RT_FULL. Forces interrupt threading and enables some of the RT +substitutions for testing. + +Signed-off-by: Thomas Gleixner +--- + kernel/Kconfig.preempt | 19 +++++++++++++++++-- + 1 file changed, 17 insertions(+), 2 deletions(-) + +--- a/kernel/Kconfig.preempt ++++ b/kernel/Kconfig.preempt +@@ -1,3 +1,10 @@ ++config PREEMPT ++ bool ++ select PREEMPT_COUNT ++ ++config PREEMPT_RT_BASE ++ bool ++ select PREEMPT + + choice + prompt "Preemption Model" +@@ -33,9 +40,9 @@ config PREEMPT_VOLUNTARY + + Select this if you are building a kernel for a desktop system. + +-config PREEMPT ++config PREEMPT__LL + bool "Preemptible Kernel (Low-Latency Desktop)" +- select PREEMPT_COUNT ++ select PREEMPT + select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK + help + This option reduces the latency of the kernel by making +@@ -52,6 +59,14 @@ config PREEMPT + embedded system with latency requirements in the milliseconds + range. + ++config PREEMPT_RTB ++ bool "Preemptible Kernel (Basic RT)" ++ select PREEMPT_RT_BASE ++ help ++ This option is basically the same as (Low-Latency Desktop) but ++ enables changes which are preliminary for the full preemptible ++ RT kernel. ++ + endchoice + + config PREEMPT_COUNT diff --git a/debian/patches/features/all/rt/rt-serial-warn-fix.patch b/debian/patches/features/all/rt/rt-serial-warn-fix.patch new file mode 100644 index 000000000..74f5c88b8 --- /dev/null +++ b/debian/patches/features/all/rt/rt-serial-warn-fix.patch @@ -0,0 +1,38 @@ +Subject: rt: Improve the serial console PASS_LIMIT +From: Ingo Molnar +Date: Wed Dec 14 13:05:54 CET 2011 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Beyond the warning: + + drivers/tty/serial/8250/8250.c:1613:6: warning: unused variable ‘pass_counter’ [-Wunused-variable] + +the solution of just looping infinitely was ugly - up it to 1 million to +give it a chance to continue in some really ugly situation. + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner +--- + drivers/tty/serial/8250/8250_core.c | 11 ++++++++++- + 1 file changed, 10 insertions(+), 1 deletion(-) + +--- a/drivers/tty/serial/8250/8250_core.c ++++ b/drivers/tty/serial/8250/8250_core.c +@@ -80,7 +80,16 @@ static unsigned int skip_txen_test; /* f + #define DEBUG_INTR(fmt...) do { } while (0) + #endif + +-#define PASS_LIMIT 512 ++/* ++ * On -rt we can have a more delays, and legitimately ++ * so - so don't drop work spuriously and spam the ++ * syslog: ++ */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define PASS_LIMIT 1000000 ++#else ++# define PASS_LIMIT 512 ++#endif + + #define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE) + diff --git a/debian/patches/features/all/rt/rtmutex-add-a-first-shot-of-ww_mutex.patch b/debian/patches/features/all/rt/rtmutex-add-a-first-shot-of-ww_mutex.patch new file mode 100644 index 000000000..f6fdfc0e8 --- /dev/null +++ b/debian/patches/features/all/rt/rtmutex-add-a-first-shot-of-ww_mutex.patch @@ -0,0 +1,424 @@ +From: Sebastian Andrzej Siewior +Date: Mon, 28 Oct 2013 09:36:37 +0100 +Subject: rtmutex: Add RT aware ww locks +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +lockdep says: +| -------------------------------------------------------------------------- +| | Wound/wait tests | +| --------------------- +| ww api failures: ok | ok | ok | +| ww contexts mixing: ok | ok | +| finishing ww context: ok | ok | ok | ok | +| locking mismatches: ok | ok | ok | +| EDEADLK handling: ok | ok | ok | ok | ok | ok | ok | ok | ok | ok | +| spinlock nest unlocked: ok | +| ----------------------------------------------------- +| |block | try |context| +| ----------------------------------------------------- +| context: ok | ok | ok | +| try: ok | ok | ok | +| block: ok | ok | ok | +| spinlock: ok | ok | ok | + +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/locking/rtmutex.c | 251 ++++++++++++++++++++++++++++++++++++++++++----- + 1 file changed, 226 insertions(+), 25 deletions(-) + +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -21,6 +21,7 @@ + #include + #include + #include ++#include + + #include "rtmutex_common.h" + +@@ -1201,6 +1202,40 @@ EXPORT_SYMBOL(__rt_spin_lock_init); + + #endif /* PREEMPT_RT_FULL */ + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ static inline int __sched ++__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) ++{ ++ struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); ++ struct ww_acquire_ctx *hold_ctx = ACCESS_ONCE(ww->ctx); ++ ++ if (!hold_ctx) ++ return 0; ++ ++ if (unlikely(ctx == hold_ctx)) ++ return -EALREADY; ++ ++ if (ctx->stamp - hold_ctx->stamp <= LONG_MAX && ++ (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) { ++#ifdef CONFIG_DEBUG_MUTEXES ++ DEBUG_LOCKS_WARN_ON(ctx->contending_lock); ++ ctx->contending_lock = ww; ++#endif ++ return -EDEADLK; ++ } ++ ++ return 0; ++} ++#else ++ static inline int __sched ++__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) ++{ ++ BUG(); ++ return 0; ++} ++ ++#endif ++ + static inline int + try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, + struct rt_mutex_waiter *waiter) +@@ -1461,7 +1496,8 @@ void rt_mutex_adjust_pi(struct task_stru + static int __sched + __rt_mutex_slowlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- struct rt_mutex_waiter *waiter) ++ struct rt_mutex_waiter *waiter, ++ struct ww_acquire_ctx *ww_ctx) + { + int ret = 0; + +@@ -1484,6 +1520,12 @@ static int __sched + break; + } + ++ if (ww_ctx && ww_ctx->acquired > 0) { ++ ret = __mutex_lock_check_stamp(lock, ww_ctx); ++ if (ret) ++ break; ++ } ++ + raw_spin_unlock(&lock->wait_lock); + + debug_rt_mutex_print_deadlock(waiter); +@@ -1518,13 +1560,90 @@ static void rt_mutex_handle_deadlock(int + } + } + ++static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, ++ struct ww_acquire_ctx *ww_ctx) ++{ ++#ifdef CONFIG_DEBUG_MUTEXES ++ /* ++ * If this WARN_ON triggers, you used ww_mutex_lock to acquire, ++ * but released with a normal mutex_unlock in this call. ++ * ++ * This should never happen, always use ww_mutex_unlock. ++ */ ++ DEBUG_LOCKS_WARN_ON(ww->ctx); ++ ++ /* ++ * Not quite done after calling ww_acquire_done() ? ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire); ++ ++ if (ww_ctx->contending_lock) { ++ /* ++ * After -EDEADLK you tried to ++ * acquire a different ww_mutex? Bad! ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww); ++ ++ /* ++ * You called ww_mutex_lock after receiving -EDEADLK, ++ * but 'forgot' to unlock everything else first? ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0); ++ ww_ctx->contending_lock = NULL; ++ } ++ ++ /* ++ * Naughty, using a different class will lead to undefined behavior! ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); ++#endif ++ ww_ctx->acquired++; ++} ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void ww_mutex_account_lock(struct rt_mutex *lock, ++ struct ww_acquire_ctx *ww_ctx) ++{ ++ struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); ++ struct rt_mutex_waiter *waiter, *n; ++ ++ /* ++ * This branch gets optimized out for the common case, ++ * and is only important for ww_mutex_lock. ++ */ ++ ww_mutex_lock_acquired(ww, ww_ctx); ++ ww->ctx = ww_ctx; ++ ++ /* ++ * Give any possible sleeping processes the chance to wake up, ++ * so they can recheck if they have to back off. ++ */ ++ rbtree_postorder_for_each_entry_safe(waiter, n, &lock->waiters, ++ tree_entry) { ++ /* XXX debug rt mutex waiter wakeup */ ++ ++ BUG_ON(waiter->lock != lock); ++ rt_mutex_wake_waiter(waiter); ++ } ++} ++ ++#else ++ ++static void ww_mutex_account_lock(struct rt_mutex *lock, ++ struct ww_acquire_ctx *ww_ctx) ++{ ++ BUG(); ++} ++#endif ++ + /* + * Slow path lock function: + */ + static int __sched + rt_mutex_slowlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- enum rtmutex_chainwalk chwalk) ++ enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx) + { + struct rt_mutex_waiter waiter; + int ret = 0; +@@ -1535,6 +1654,8 @@ rt_mutex_slowlock(struct rt_mutex *lock, + + /* Try to acquire the lock again: */ + if (try_to_take_rt_mutex(lock, current, NULL)) { ++ if (ww_ctx) ++ ww_mutex_account_lock(lock, ww_ctx); + raw_spin_unlock(&lock->wait_lock); + return 0; + } +@@ -1552,13 +1673,23 @@ rt_mutex_slowlock(struct rt_mutex *lock, + + if (likely(!ret)) + /* sleep on the mutex */ +- ret = __rt_mutex_slowlock(lock, state, timeout, &waiter); ++ ret = __rt_mutex_slowlock(lock, state, timeout, &waiter, ++ ww_ctx); ++ else if (ww_ctx) { ++ /* ww_mutex received EDEADLK, let it become EALREADY */ ++ ret = __mutex_lock_check_stamp(lock, ww_ctx); ++ BUG_ON(!ret); ++ } + + if (unlikely(ret)) { + __set_current_state(TASK_RUNNING); + if (rt_mutex_has_waiters(lock)) + remove_waiter(lock, &waiter); +- rt_mutex_handle_deadlock(ret, chwalk, &waiter); ++ /* ww_mutex want to report EDEADLK/EALREADY, let them */ ++ if (!ww_ctx) ++ rt_mutex_handle_deadlock(ret, chwalk, &waiter); ++ } else if (ww_ctx) { ++ ww_mutex_account_lock(lock, ww_ctx); + } + + /* +@@ -1682,31 +1813,36 @@ rt_mutex_slowunlock(struct rt_mutex *loc + */ + static inline int + rt_mutex_fastlock(struct rt_mutex *lock, int state, ++ struct ww_acquire_ctx *ww_ctx, + int (*slowfn)(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- enum rtmutex_chainwalk chwalk)) ++ enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx)) + { + if (likely(rt_mutex_cmpxchg(lock, NULL, current))) { + rt_mutex_deadlock_account_lock(lock, current); + return 0; + } else +- return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK); ++ return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK, ++ ww_ctx); + } + + static inline int + rt_mutex_timed_fastlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx, + int (*slowfn)(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- enum rtmutex_chainwalk chwalk)) ++ enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx)) + { + if (chwalk == RT_MUTEX_MIN_CHAINWALK && + likely(rt_mutex_cmpxchg(lock, NULL, current))) { + rt_mutex_deadlock_account_lock(lock, current); + return 0; + } else +- return slowfn(lock, state, timeout, chwalk); ++ return slowfn(lock, state, timeout, chwalk, ww_ctx); + } + + static inline int +@@ -1741,7 +1877,7 @@ void __sched rt_mutex_lock(struct rt_mut + { + might_sleep(); + +- rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); ++ rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, NULL, rt_mutex_slowlock); + } + EXPORT_SYMBOL_GPL(rt_mutex_lock); + +@@ -1758,7 +1894,7 @@ int __sched rt_mutex_lock_interruptible( + { + might_sleep(); + +- return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock); ++ return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, NULL, rt_mutex_slowlock); + } + EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible); + +@@ -1771,7 +1907,7 @@ int rt_mutex_timed_futex_lock(struct rt_ + might_sleep(); + + return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, +- RT_MUTEX_FULL_CHAINWALK, ++ RT_MUTEX_FULL_CHAINWALK, NULL, + rt_mutex_slowlock); + } + +@@ -1790,7 +1926,7 @@ int __sched rt_mutex_lock_killable(struc + { + might_sleep(); + +- return rt_mutex_fastlock(lock, TASK_KILLABLE, rt_mutex_slowlock); ++ return rt_mutex_fastlock(lock, TASK_KILLABLE, NULL, rt_mutex_slowlock); + } + EXPORT_SYMBOL_GPL(rt_mutex_lock_killable); + +@@ -1814,6 +1950,7 @@ rt_mutex_timed_lock(struct rt_mutex *loc + + return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, + RT_MUTEX_MIN_CHAINWALK, ++ NULL, + rt_mutex_slowlock); + } + EXPORT_SYMBOL_GPL(rt_mutex_timed_lock); +@@ -2055,7 +2192,7 @@ int rt_mutex_finish_proxy_lock(struct rt + set_current_state(TASK_INTERRUPTIBLE); + + /* sleep on the mutex */ +- ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter); ++ ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter, NULL); + + if (unlikely(ret)) + remove_waiter(lock, waiter); +@@ -2071,24 +2208,88 @@ int rt_mutex_finish_proxy_lock(struct rt + return ret; + } + +-#ifdef CONFIG_PREEMPT_RT_FULL +-struct ww_mutex { +-}; +-struct ww_acquire_ctx { +-}; +-int __ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) ++static inline int ++ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) + { +- BUG(); ++#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH ++ unsigned tmp; ++ ++ if (ctx->deadlock_inject_countdown-- == 0) { ++ tmp = ctx->deadlock_inject_interval; ++ if (tmp > UINT_MAX/4) ++ tmp = UINT_MAX; ++ else ++ tmp = tmp*2 + tmp + tmp/2; ++ ++ ctx->deadlock_inject_interval = tmp; ++ ctx->deadlock_inject_countdown = tmp; ++ ctx->contending_lock = lock; ++ ++ ww_mutex_unlock(lock); ++ ++ return -EDEADLK; ++ } ++#endif ++ ++ return 0; + } +-EXPORT_SYMBOL_GPL(__ww_mutex_lock); +-int __ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++int __sched ++__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) + { +- BUG(); ++ int ret; ++ ++ might_sleep(); ++ ++ mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_); ++ ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL, 0, ww_ctx); ++ if (ret) ++ mutex_release(&lock->base.dep_map, 1, _RET_IP_); ++ else if (!ret && ww_ctx->acquired > 1) ++ return ww_mutex_deadlock_injection(lock, ww_ctx); ++ ++ return ret; + } + EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible); ++ ++int __sched ++__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) ++{ ++ int ret; ++ ++ might_sleep(); ++ ++ mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_); ++ ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL, 0, ww_ctx); ++ if (ret) ++ mutex_release(&lock->base.dep_map, 1, _RET_IP_); ++ else if (!ret && ww_ctx->acquired > 1) ++ return ww_mutex_deadlock_injection(lock, ww_ctx); ++ ++ return ret; ++} ++EXPORT_SYMBOL_GPL(__ww_mutex_lock); ++ + void __sched ww_mutex_unlock(struct ww_mutex *lock) + { +- BUG(); ++ int nest = !!lock->ctx; ++ ++ /* ++ * The unlocking fastpath is the 0->1 transition from 'locked' ++ * into 'unlocked' state: ++ */ ++ if (nest) { ++#ifdef CONFIG_DEBUG_MUTEXES ++ DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired); ++#endif ++ if (lock->ctx->acquired > 0) ++ lock->ctx->acquired--; ++ lock->ctx = NULL; ++ } ++ ++ mutex_release(&lock->base.dep_map, nest, _RET_IP_); ++ rt_mutex_unlock(&lock->base.lock); + } +-EXPORT_SYMBOL_GPL(ww_mutex_unlock); ++EXPORT_SYMBOL(ww_mutex_unlock); + #endif diff --git a/debian/patches/features/all/rt/rtmutex-avoid-include-hell.patch b/debian/patches/features/all/rt/rtmutex-avoid-include-hell.patch new file mode 100644 index 000000000..f42c6fda3 --- /dev/null +++ b/debian/patches/features/all/rt/rtmutex-avoid-include-hell.patch @@ -0,0 +1,24 @@ +Subject: rtmutex: Avoid include hell +From: Thomas Gleixner +Date: Wed, 29 Jun 2011 20:06:39 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Include only the required raw types. This avoids pulling in the +complete spinlock header which in turn requires rtmutex.h at some point. + +Signed-off-by: Thomas Gleixner +--- + include/linux/rtmutex.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/include/linux/rtmutex.h ++++ b/include/linux/rtmutex.h +@@ -14,7 +14,7 @@ + + #include + #include +-#include ++#include + + extern int max_lock_depth; /* for sysctl */ + diff --git a/debian/patches/features/all/rt/rtmutex-futex-prepare-rt.patch b/debian/patches/features/all/rt/rtmutex-futex-prepare-rt.patch new file mode 100644 index 000000000..0afbc5071 --- /dev/null +++ b/debian/patches/features/all/rt/rtmutex-futex-prepare-rt.patch @@ -0,0 +1,239 @@ +Subject: rtmutex: Handle the various new futex race conditions +From: Thomas Gleixner +Date: Fri, 10 Jun 2011 11:04:15 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +RT opens a few new interesting race conditions in the rtmutex/futex +combo due to futex hash bucket lock being a 'sleeping' spinlock and +therefor not disabling preemption. + +Signed-off-by: Thomas Gleixner +--- + kernel/futex.c | 77 ++++++++++++++++++++++++++++++++-------- + kernel/locking/rtmutex.c | 36 +++++++++++++++--- + kernel/locking/rtmutex_common.h | 2 + + 3 files changed, 94 insertions(+), 21 deletions(-) + +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -1717,6 +1717,16 @@ static int futex_requeue(u32 __user *uad + requeue_pi_wake_futex(this, &key2, hb2); + drop_count++; + continue; ++ } else if (ret == -EAGAIN) { ++ /* ++ * Waiter was woken by timeout or ++ * signal and has set pi_blocked_on to ++ * PI_WAKEUP_INPROGRESS before we ++ * tried to enqueue it on the rtmutex. ++ */ ++ this->pi_state = NULL; ++ free_pi_state(pi_state); ++ continue; + } else if (ret) { + /* -EDEADLK */ + this->pi_state = NULL; +@@ -2576,7 +2586,7 @@ static int futex_wait_requeue_pi(u32 __u + struct hrtimer_sleeper timeout, *to = NULL; + struct rt_mutex_waiter rt_waiter; + struct rt_mutex *pi_mutex = NULL; +- struct futex_hash_bucket *hb; ++ struct futex_hash_bucket *hb, *hb2; + union futex_key key2 = FUTEX_KEY_INIT; + struct futex_q q = futex_q_init; + int res, ret; +@@ -2635,20 +2645,55 @@ static int futex_wait_requeue_pi(u32 __u + /* Queue the futex_q, drop the hb lock, wait for wakeup. */ + futex_wait_queue_me(hb, &q, to); + +- spin_lock(&hb->lock); +- ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); +- spin_unlock(&hb->lock); +- if (ret) +- goto out_put_keys; ++ /* ++ * On RT we must avoid races with requeue and trying to block ++ * on two mutexes (hb->lock and uaddr2's rtmutex) by ++ * serializing access to pi_blocked_on with pi_lock. ++ */ ++ raw_spin_lock_irq(¤t->pi_lock); ++ if (current->pi_blocked_on) { ++ /* ++ * We have been requeued or are in the process of ++ * being requeued. ++ */ ++ raw_spin_unlock_irq(¤t->pi_lock); ++ } else { ++ /* ++ * Setting pi_blocked_on to PI_WAKEUP_INPROGRESS ++ * prevents a concurrent requeue from moving us to the ++ * uaddr2 rtmutex. After that we can safely acquire ++ * (and possibly block on) hb->lock. ++ */ ++ current->pi_blocked_on = PI_WAKEUP_INPROGRESS; ++ raw_spin_unlock_irq(¤t->pi_lock); ++ ++ spin_lock(&hb->lock); ++ ++ /* ++ * Clean up pi_blocked_on. We might leak it otherwise ++ * when we succeeded with the hb->lock in the fast ++ * path. ++ */ ++ raw_spin_lock_irq(¤t->pi_lock); ++ current->pi_blocked_on = NULL; ++ raw_spin_unlock_irq(¤t->pi_lock); ++ ++ ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); ++ spin_unlock(&hb->lock); ++ if (ret) ++ goto out_put_keys; ++ } + + /* +- * In order for us to be here, we know our q.key == key2, and since +- * we took the hb->lock above, we also know that futex_requeue() has +- * completed and we no longer have to concern ourselves with a wakeup +- * race with the atomic proxy lock acquisition by the requeue code. The +- * futex_requeue dropped our key1 reference and incremented our key2 +- * reference count. ++ * In order to be here, we have either been requeued, are in ++ * the process of being requeued, or requeue successfully ++ * acquired uaddr2 on our behalf. If pi_blocked_on was ++ * non-null above, we may be racing with a requeue. Do not ++ * rely on q->lock_ptr to be hb2->lock until after blocking on ++ * hb->lock or hb2->lock. The futex_requeue dropped our key1 ++ * reference and incremented our key2 reference count. + */ ++ hb2 = hash_futex(&key2); + + /* Check if the requeue code acquired the second futex for us. */ + if (!q.rt_waiter) { +@@ -2657,9 +2702,10 @@ static int futex_wait_requeue_pi(u32 __u + * did a lock-steal - fix up the PI-state in that case. + */ + if (q.pi_state && (q.pi_state->owner != current)) { +- spin_lock(q.lock_ptr); ++ spin_lock(&hb2->lock); ++ BUG_ON(&hb2->lock != q.lock_ptr); + ret = fixup_pi_state_owner(uaddr2, &q, current); +- spin_unlock(q.lock_ptr); ++ spin_unlock(&hb2->lock); + } + } else { + /* +@@ -2672,7 +2718,8 @@ static int futex_wait_requeue_pi(u32 __u + ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter); + debug_rt_mutex_free_waiter(&rt_waiter); + +- spin_lock(q.lock_ptr); ++ spin_lock(&hb2->lock); ++ BUG_ON(&hb2->lock != q.lock_ptr); + /* + * Fixup the pi_state owner and possibly acquire the lock if we + * haven't already. +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -69,6 +69,11 @@ static void fixup_rt_mutex_waiters(struc + clear_rt_mutex_waiters(lock); + } + ++static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter) ++{ ++ return waiter && waiter != PI_WAKEUP_INPROGRESS; ++} ++ + /* + * We can speed up the acquire/release, if the architecture + * supports cmpxchg and if there's no debugging state to be set up +@@ -342,7 +347,8 @@ int max_lock_depth = 1024; + + static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p) + { +- return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL; ++ return rt_mutex_real_waiter(p->pi_blocked_on) ? ++ p->pi_blocked_on->lock : NULL; + } + + /* +@@ -479,7 +485,7 @@ static int rt_mutex_adjust_prio_chain(st + * reached or the state of the chain has changed while we + * dropped the locks. + */ +- if (!waiter) ++ if (!rt_mutex_real_waiter(waiter)) + goto out_unlock_pi; + + /* +@@ -896,6 +902,23 @@ static int task_blocks_on_rt_mutex(struc + return -EDEADLK; + + raw_spin_lock_irqsave(&task->pi_lock, flags); ++ ++ /* ++ * In the case of futex requeue PI, this will be a proxy ++ * lock. The task will wake unaware that it is enqueueed on ++ * this lock. Avoid blocking on two locks and corrupting ++ * pi_blocked_on via the PI_WAKEUP_INPROGRESS ++ * flag. futex_wait_requeue_pi() sets this when it wakes up ++ * before requeue (due to a signal or timeout). Do not enqueue ++ * the task if PI_WAKEUP_INPROGRESS is set. ++ */ ++ if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) { ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); ++ return -EAGAIN; ++ } ++ ++ BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)); ++ + __rt_mutex_adjust_prio(task); + waiter->task = task; + waiter->lock = lock; +@@ -919,7 +942,7 @@ static int task_blocks_on_rt_mutex(struc + rt_mutex_enqueue_pi(owner, waiter); + + __rt_mutex_adjust_prio(owner); +- if (owner->pi_blocked_on) ++ if (rt_mutex_real_waiter(owner->pi_blocked_on)) + chain_walk = 1; + } else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) { + chain_walk = 1; +@@ -1011,7 +1034,7 @@ static void remove_waiter(struct rt_mute + { + bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock)); + struct task_struct *owner = rt_mutex_owner(lock); +- struct rt_mutex *next_lock; ++ struct rt_mutex *next_lock = NULL; + unsigned long flags; + + raw_spin_lock_irqsave(¤t->pi_lock, flags); +@@ -1036,7 +1059,8 @@ static void remove_waiter(struct rt_mute + __rt_mutex_adjust_prio(owner); + + /* Store the lock on which owner is blocked or NULL */ +- next_lock = task_blocked_on_lock(owner); ++ if (rt_mutex_real_waiter(owner->pi_blocked_on)) ++ next_lock = task_blocked_on_lock(owner); + + raw_spin_unlock_irqrestore(&owner->pi_lock, flags); + +@@ -1072,7 +1096,7 @@ void rt_mutex_adjust_pi(struct task_stru + raw_spin_lock_irqsave(&task->pi_lock, flags); + + waiter = task->pi_blocked_on; +- if (!waiter || (waiter->prio == task->prio && ++ if (!rt_mutex_real_waiter(waiter) || (waiter->prio == task->prio && + !dl_prio(task->prio))) { + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + return; +--- a/kernel/locking/rtmutex_common.h ++++ b/kernel/locking/rtmutex_common.h +@@ -119,6 +119,8 @@ enum rtmutex_chainwalk { + /* + * PI-futex support (proxy locking functions, etc.): + */ ++#define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1) ++ + extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); + extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, + struct task_struct *proxy_owner); diff --git a/debian/patches/features/all/rt/rtmutex-lock-killable.patch b/debian/patches/features/all/rt/rtmutex-lock-killable.patch new file mode 100644 index 000000000..9c3b0c124 --- /dev/null +++ b/debian/patches/features/all/rt/rtmutex-lock-killable.patch @@ -0,0 +1,52 @@ +Subject: rtmutex: Add rtmutex_lock_killable() +From: Thomas Gleixner +Date: Thu, 09 Jun 2011 11:43:52 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Add "killable" type to rtmutex. We need this since rtmutex are used as +"normal" mutexes which do use this type. + +Signed-off-by: Thomas Gleixner +--- + include/linux/rtmutex.h | 1 + + kernel/locking/rtmutex.c | 19 +++++++++++++++++++ + 2 files changed, 20 insertions(+) + +--- a/include/linux/rtmutex.h ++++ b/include/linux/rtmutex.h +@@ -91,6 +91,7 @@ extern void rt_mutex_destroy(struct rt_m + + extern void rt_mutex_lock(struct rt_mutex *lock); + extern int rt_mutex_lock_interruptible(struct rt_mutex *lock); ++extern int rt_mutex_lock_killable(struct rt_mutex *lock); + extern int rt_mutex_timed_lock(struct rt_mutex *lock, + struct hrtimer_sleeper *timeout); + +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -1442,6 +1442,25 @@ int rt_mutex_timed_futex_lock(struct rt_ + } + + /** ++ * rt_mutex_lock_killable - lock a rt_mutex killable ++ * ++ * @lock: the rt_mutex to be locked ++ * @detect_deadlock: deadlock detection on/off ++ * ++ * Returns: ++ * 0 on success ++ * -EINTR when interrupted by a signal ++ * -EDEADLK when the lock would deadlock (when deadlock detection is on) ++ */ ++int __sched rt_mutex_lock_killable(struct rt_mutex *lock) ++{ ++ might_sleep(); ++ ++ return rt_mutex_fastlock(lock, TASK_KILLABLE, rt_mutex_slowlock); ++} ++EXPORT_SYMBOL_GPL(rt_mutex_lock_killable); ++ ++/** + * rt_mutex_timed_lock - lock a rt_mutex interruptible + * the timeout structure is provided + * by the caller diff --git a/debian/patches/features/all/rt/sas-ata-isci-dont-t-disable-interrupts-in-qc_issue-h.patch b/debian/patches/features/all/rt/sas-ata-isci-dont-t-disable-interrupts-in-qc_issue-h.patch new file mode 100644 index 000000000..a839fcaf9 --- /dev/null +++ b/debian/patches/features/all/rt/sas-ata-isci-dont-t-disable-interrupts-in-qc_issue-h.patch @@ -0,0 +1,79 @@ +From: Paul Gortmaker +Date: Sat, 14 Feb 2015 11:01:16 -0500 +Subject: sas-ata/isci: dont't disable interrupts in qc_issue handler +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +On 3.14-rt we see the following trace on Canoe Pass for +SCSI_ISCI "Intel(R) C600 Series Chipset SAS Controller" +when the sas qc_issue handler is run: + + BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:905 + in_atomic(): 0, irqs_disabled(): 1, pid: 432, name: udevd + CPU: 11 PID: 432 Comm: udevd Not tainted 3.14.28-rt22 #2 + Hardware name: Intel Corporation S2600CP/S2600CP, BIOS SE5C600.86B.02.01.0002.082220131453 08/22/2013 + ffff880fab500000 ffff880fa9f239c0 ffffffff81a2d273 0000000000000000 + ffff880fa9f239d8 ffffffff8107f023 ffff880faac23dc0 ffff880fa9f239f0 + ffffffff81a33cc0 ffff880faaeb1400 ffff880fa9f23a40 ffffffff815de891 + Call Trace: + [] dump_stack+0x4e/0x7a + [] __might_sleep+0xe3/0x160 + [] rt_spin_lock+0x20/0x50 + [] isci_task_execute_task+0x171/0x2f0 <----- + [] sas_ata_qc_issue+0x25b/0x2a0 + [] ata_qc_issue+0x1f3/0x370 + [] ? ata_scsi_invalid_field+0x40/0x40 + [] ata_scsi_translate+0xa5/0x1b0 + [] ata_sas_queuecmd+0x86/0x280 + [] sas_queuecommand+0x196/0x230 + [] ? get_parent_ip+0xd/0x50 + [] scsi_dispatch_cmd+0xb4/0x210 + [] scsi_request_fn+0x314/0x530 + +and gdb shows: + +(gdb) list * isci_task_execute_task+0x171 +0xffffffff815ddfb1 is in isci_task_execute_task (drivers/scsi/isci/task.c:138). +133 dev_dbg(&ihost->pdev->dev, "%s: num=%d\n", __func__, num); +134 +135 for_each_sas_task(num, task) { +136 enum sci_status status = SCI_FAILURE; +137 +138 spin_lock_irqsave(&ihost->scic_lock, flags); <----- +139 idev = isci_lookup_device(task->dev); +140 io_ready = isci_device_io_ready(idev, task); +141 tag = isci_alloc_tag(ihost); +142 spin_unlock_irqrestore(&ihost->scic_lock, flags); +(gdb) + +In addition to the scic_lock, the function also contains locking of +the task_state_lock -- which is clearly not a candidate for raw lock +conversion. As can be seen by the comment nearby, we really should +be running the qc_issue code with interrupts enabled anyway. + + +Signed-off-by: Paul Gortmaker +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/scsi/libsas/sas_ata.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/drivers/scsi/libsas/sas_ata.c ++++ b/drivers/scsi/libsas/sas_ata.c +@@ -190,7 +190,7 @@ static unsigned int sas_ata_qc_issue(str + /* TODO: audit callers to ensure they are ready for qc_issue to + * unconditionally re-enable interrupts + */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + spin_unlock(ap->lock); + + /* If the device fell off, no sense in issuing commands */ +@@ -255,7 +255,7 @@ static unsigned int sas_ata_qc_issue(str + + out: + spin_lock(ap->lock); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + return ret; + } + diff --git a/debian/patches/features/all/rt/sched-deadline-dl_task_timer-has-to-be-irqsafe.patch b/debian/patches/features/all/rt/sched-deadline-dl_task_timer-has-to-be-irqsafe.patch new file mode 100644 index 000000000..5de73e12c --- /dev/null +++ b/debian/patches/features/all/rt/sched-deadline-dl_task_timer-has-to-be-irqsafe.patch @@ -0,0 +1,23 @@ +From: Juri Lelli +Date: Tue, 13 May 2014 15:30:20 +0200 +Subject: sched/deadline: dl_task_timer has to be irqsafe +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +As for rt_period_timer, dl_task_timer has to be irqsafe. + +Signed-off-by: Juri Lelli +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/sched/deadline.c | 1 + + 1 file changed, 1 insertion(+) + +--- a/kernel/sched/deadline.c ++++ b/kernel/sched/deadline.c +@@ -637,6 +637,7 @@ void init_dl_task_timer(struct sched_dl_ + + hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + timer->function = dl_task_timer; ++ timer->irqsafe = 1; + } + + static diff --git a/debian/patches/features/all/rt/sched-delay-put-task.patch b/debian/patches/features/all/rt/sched-delay-put-task.patch new file mode 100644 index 000000000..0637ee3ab --- /dev/null +++ b/debian/patches/features/all/rt/sched-delay-put-task.patch @@ -0,0 +1,82 @@ +Subject: sched: Move task_struct cleanup to RCU +From: Thomas Gleixner +Date: Tue, 31 May 2011 16:59:16 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +__put_task_struct() does quite some expensive work. We don't want to +burden random tasks with that. + +Signed-off-by: Thomas Gleixner +--- + include/linux/sched.h | 13 +++++++++++++ + kernel/fork.c | 15 ++++++++++++++- + 2 files changed, 27 insertions(+), 1 deletion(-) + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -1788,6 +1788,9 @@ struct task_struct { + unsigned int sequential_io; + unsigned int sequential_io_avg; + #endif ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct rcu_head put_rcu; ++#endif + #ifdef CONFIG_DEBUG_ATOMIC_SLEEP + unsigned long task_state_change; + #endif +@@ -1982,6 +1985,15 @@ extern struct pid *cad_pid; + extern void free_task(struct task_struct *tsk); + #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0) + ++#ifdef CONFIG_PREEMPT_RT_BASE ++extern void __put_task_struct_cb(struct rcu_head *rhp); ++ ++static inline void put_task_struct(struct task_struct *t) ++{ ++ if (atomic_dec_and_test(&t->usage)) ++ call_rcu(&t->put_rcu, __put_task_struct_cb); ++} ++#else + extern void __put_task_struct(struct task_struct *t); + + static inline void put_task_struct(struct task_struct *t) +@@ -1989,6 +2001,7 @@ static inline void put_task_struct(struc + if (atomic_dec_and_test(&t->usage)) + __put_task_struct(t); + } ++#endif + + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN + extern void task_cputime(struct task_struct *t, +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -244,7 +244,9 @@ static inline void put_signal_struct(str + if (atomic_dec_and_test(&sig->sigcnt)) + free_signal_struct(sig); + } +- ++#ifdef CONFIG_PREEMPT_RT_BASE ++static ++#endif + void __put_task_struct(struct task_struct *tsk) + { + WARN_ON(!tsk->exit_state); +@@ -260,7 +262,18 @@ void __put_task_struct(struct task_struc + if (!profile_handoff_task(tsk)) + free_task(tsk); + } ++#ifndef CONFIG_PREEMPT_RT_BASE + EXPORT_SYMBOL_GPL(__put_task_struct); ++#else ++void __put_task_struct_cb(struct rcu_head *rhp) ++{ ++ struct task_struct *tsk = container_of(rhp, struct task_struct, put_rcu); ++ ++ __put_task_struct(tsk); ++ ++} ++EXPORT_SYMBOL_GPL(__put_task_struct_cb); ++#endif + + void __init __weak arch_task_cache_init(void) { } + diff --git a/debian/patches/features/all/rt/sched-disable-rt-group-sched-on-rt.patch b/debian/patches/features/all/rt/sched-disable-rt-group-sched-on-rt.patch new file mode 100644 index 000000000..5f5d9fe9f --- /dev/null +++ b/debian/patches/features/all/rt/sched-disable-rt-group-sched-on-rt.patch @@ -0,0 +1,29 @@ +Subject: sched: Disable CONFIG_RT_GROUP_SCHED on RT +From: Thomas Gleixner +Date: Mon, 18 Jul 2011 17:03:52 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Carsten reported problems when running: + + taskset 01 chrt -f 1 sleep 1 + +from within rc.local on a F15 machine. The task stays running and +never gets on the run queue because some of the run queues have +rt_throttled=1 which does not go away. Works nice from a ssh login +shell. Disabling CONFIG_RT_GROUP_SCHED solves that as well. + +Signed-off-by: Thomas Gleixner +--- + init/Kconfig | 1 + + 1 file changed, 1 insertion(+) + +--- a/init/Kconfig ++++ b/init/Kconfig +@@ -1101,6 +1101,7 @@ config CFS_BANDWIDTH + config RT_GROUP_SCHED + bool "Group scheduling for SCHED_RR/FIFO" + depends on CGROUP_SCHED ++ depends on !PREEMPT_RT_FULL + default n + help + This feature lets you explicitly allocate real CPU bandwidth diff --git a/debian/patches/features/all/rt/sched-disable-ttwu-queue.patch b/debian/patches/features/all/rt/sched-disable-ttwu-queue.patch new file mode 100644 index 000000000..ea88b96e9 --- /dev/null +++ b/debian/patches/features/all/rt/sched-disable-ttwu-queue.patch @@ -0,0 +1,32 @@ +Subject: sched: Disable TTWU_QUEUE on RT +From: Thomas Gleixner +Date: Tue, 13 Sep 2011 16:42:35 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The queued remote wakeup mechanism can introduce rather large +latencies if the number of migrated tasks is high. Disable it for RT. + +Signed-off-by: Thomas Gleixner +--- + kernel/sched/features.h | 5 +++++ + 1 file changed, 5 insertions(+) + +--- a/kernel/sched/features.h ++++ b/kernel/sched/features.h +@@ -50,11 +50,16 @@ SCHED_FEAT(LB_BIAS, true) + */ + SCHED_FEAT(NONTASK_CAPACITY, true) + ++#ifdef CONFIG_PREEMPT_RT_FULL ++SCHED_FEAT(TTWU_QUEUE, false) ++#else ++ + /* + * Queue remote wakeups on the target CPU and process them + * using the scheduler IPI. Reduces rq->lock contention/bounces. + */ + SCHED_FEAT(TTWU_QUEUE, true) ++#endif + + #ifdef HAVE_RT_PUSH_IPI + /* diff --git a/debian/patches/features/all/rt/sched-limit-nr-migrate.patch b/debian/patches/features/all/rt/sched-limit-nr-migrate.patch new file mode 100644 index 000000000..81eb3c793 --- /dev/null +++ b/debian/patches/features/all/rt/sched-limit-nr-migrate.patch @@ -0,0 +1,27 @@ +Subject: sched: Limit the number of task migrations per batch +From: Thomas Gleixner +Date: Mon, 06 Jun 2011 12:12:51 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Put an upper limit on the number of tasks which are migrated per batch +to avoid large latencies. + +Signed-off-by: Thomas Gleixner +--- + kernel/sched/core.c | 4 ++++ + 1 file changed, 4 insertions(+) + +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -282,7 +282,11 @@ late_initcall(sched_init_debug); + * Number of tasks to iterate in a single balance run. + * Limited because this is done with IRQs disabled. + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + const_debug unsigned int sysctl_sched_nr_migrate = 32; ++#else ++const_debug unsigned int sysctl_sched_nr_migrate = 8; ++#endif + + /* + * period over which we average the RT time consumption, measured diff --git a/debian/patches/features/all/rt/sched-might-sleep-do-not-account-rcu-depth.patch b/debian/patches/features/all/rt/sched-might-sleep-do-not-account-rcu-depth.patch new file mode 100644 index 000000000..1783a2061 --- /dev/null +++ b/debian/patches/features/all/rt/sched-might-sleep-do-not-account-rcu-depth.patch @@ -0,0 +1,49 @@ +Subject: sched: Do not account rcu_preempt_depth on RT in might_sleep() +From: Thomas Gleixner +Date: Tue, 07 Jun 2011 09:19:06 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +RT changes the rcu_preempt_depth semantics, so we cannot check for it +in might_sleep(). + +Signed-off-by: Thomas Gleixner +--- + include/linux/rcupdate.h | 7 +++++++ + kernel/sched/core.c | 3 ++- + 2 files changed, 9 insertions(+), 1 deletion(-) + +--- a/include/linux/rcupdate.h ++++ b/include/linux/rcupdate.h +@@ -260,6 +260,11 @@ void synchronize_rcu(void); + * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. + */ + #define rcu_preempt_depth() (current->rcu_read_lock_nesting) ++#ifndef CONFIG_PREEMPT_RT_FULL ++#define sched_rcu_preempt_depth() rcu_preempt_depth() ++#else ++static inline int sched_rcu_preempt_depth(void) { return 0; } ++#endif + + #else /* #ifdef CONFIG_PREEMPT_RCU */ + +@@ -283,6 +288,8 @@ static inline int rcu_preempt_depth(void + return 0; + } + ++#define sched_rcu_preempt_depth() rcu_preempt_depth() ++ + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + + /* Internal to kernel */ +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -7496,7 +7496,8 @@ void __init sched_init(void) + #ifdef CONFIG_DEBUG_ATOMIC_SLEEP + static inline int preempt_count_equals(int preempt_offset) + { +- int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth(); ++ int nested = (preempt_count() & ~PREEMPT_ACTIVE) + ++ sched_rcu_preempt_depth(); + + return (nested == preempt_offset); + } diff --git a/debian/patches/features/all/rt/sched-mmdrop-delayed.patch b/debian/patches/features/all/rt/sched-mmdrop-delayed.patch new file mode 100644 index 000000000..08c7bd944 --- /dev/null +++ b/debian/patches/features/all/rt/sched-mmdrop-delayed.patch @@ -0,0 +1,134 @@ +Subject: sched: Move mmdrop to RCU on RT +From: Thomas Gleixner +Date: Mon, 06 Jun 2011 12:20:33 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Takes sleeping locks and calls into the memory allocator, so nothing +we want to do in task switch and oder atomic contexts. + +Signed-off-by: Thomas Gleixner +--- + include/linux/mm_types.h | 4 ++++ + include/linux/sched.h | 12 ++++++++++++ + kernel/fork.c | 13 +++++++++++++ + kernel/sched/core.c | 18 ++++++++++++++++-- + 4 files changed, 45 insertions(+), 2 deletions(-) + +--- a/include/linux/mm_types.h ++++ b/include/linux/mm_types.h +@@ -11,6 +11,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -462,6 +463,9 @@ struct mm_struct { + bool tlb_flush_pending; + #endif + struct uprobes_state uprobes_state; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct rcu_head delayed_drop; ++#endif + #ifdef CONFIG_X86_INTEL_MPX + /* address of the bounds directory */ + void __user *bd_addr; +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -2548,12 +2548,24 @@ extern struct mm_struct * mm_alloc(void) + + /* mmdrop drops the mm and the page tables */ + extern void __mmdrop(struct mm_struct *); ++ + static inline void mmdrop(struct mm_struct * mm) + { + if (unlikely(atomic_dec_and_test(&mm->mm_count))) + __mmdrop(mm); + } + ++#ifdef CONFIG_PREEMPT_RT_BASE ++extern void __mmdrop_delayed(struct rcu_head *rhp); ++static inline void mmdrop_delayed(struct mm_struct *mm) ++{ ++ if (atomic_dec_and_test(&mm->mm_count)) ++ call_rcu(&mm->delayed_drop, __mmdrop_delayed); ++} ++#else ++# define mmdrop_delayed(mm) mmdrop(mm) ++#endif ++ + /* mmput gets rid of the mappings and all user-space */ + extern void mmput(struct mm_struct *); + /* Grab a reference to a task's mm, if it is not already going away */ +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -693,6 +693,19 @@ void __mmdrop(struct mm_struct *mm) + } + EXPORT_SYMBOL_GPL(__mmdrop); + ++#ifdef CONFIG_PREEMPT_RT_BASE ++/* ++ * RCU callback for delayed mm drop. Not strictly rcu, but we don't ++ * want another facility to make this work. ++ */ ++void __mmdrop_delayed(struct rcu_head *rhp) ++{ ++ struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop); ++ ++ __mmdrop(mm); ++} ++#endif ++ + /* + * Decrement the use count and release all resources for an mm. + */ +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -2286,8 +2286,12 @@ static struct rq *finish_task_switch(str + finish_arch_post_lock_switch(); + + fire_sched_in_preempt_notifiers(current); ++ /* ++ * We use mmdrop_delayed() here so we don't have to do the ++ * full __mmdrop() when we are the last user. ++ */ + if (mm) +- mmdrop(mm); ++ mmdrop_delayed(mm); + if (unlikely(prev_state == TASK_DEAD)) { + if (prev->sched_class->task_dead) + prev->sched_class->task_dead(prev); +@@ -5125,6 +5129,8 @@ static int migration_cpu_stop(void *data + + #ifdef CONFIG_HOTPLUG_CPU + ++static DEFINE_PER_CPU(struct mm_struct *, idle_last_mm); ++ + /* + * Ensures that the idle task is using init_mm right before its cpu goes + * offline. +@@ -5139,7 +5145,11 @@ void idle_task_exit(void) + switch_mm(mm, &init_mm, current); + finish_arch_post_lock_switch(); + } +- mmdrop(mm); ++ /* ++ * Defer the cleanup to an alive cpu. On RT we can neither ++ * call mmdrop() nor mmdrop_delayed() from here. ++ */ ++ per_cpu(idle_last_mm, smp_processor_id()) = mm; + } + + /* +@@ -5482,6 +5492,10 @@ migration_call(struct notifier_block *nf + + case CPU_DEAD: + calc_load_migrate(rq); ++ if (per_cpu(idle_last_mm, cpu)) { ++ mmdrop(per_cpu(idle_last_mm, cpu)); ++ per_cpu(idle_last_mm, cpu) = NULL; ++ } + break; + #endif + } diff --git a/debian/patches/features/all/rt/sched-rt-mutex-wakeup.patch b/debian/patches/features/all/rt/sched-rt-mutex-wakeup.patch new file mode 100644 index 000000000..cc0bdb385 --- /dev/null +++ b/debian/patches/features/all/rt/sched-rt-mutex-wakeup.patch @@ -0,0 +1,94 @@ +Subject: sched: Add saved_state for tasks blocked on sleeping locks +From: Thomas Gleixner +Date: Sat, 25 Jun 2011 09:21:04 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Spinlocks are state preserving in !RT. RT changes the state when a +task gets blocked on a lock. So we need to remember the state before +the lock contention. If a regular wakeup (not a RTmutex related +wakeup) happens, the saved_state is updated to running. When the lock +sleep is done, the saved state is restored. + +Signed-off-by: Thomas Gleixner +--- + include/linux/sched.h | 2 ++ + kernel/sched/core.c | 31 ++++++++++++++++++++++++++++++- + kernel/sched/sched.h | 1 + + 3 files changed, 33 insertions(+), 1 deletion(-) + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -1335,6 +1335,7 @@ enum perf_event_task_context { + + struct task_struct { + volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */ ++ volatile long saved_state; /* saved state for "spinlock sleepers" */ + void *stack; + atomic_t usage; + unsigned int flags; /* per process flags, defined below */ +@@ -2432,6 +2433,7 @@ extern void xtime_update(unsigned long t + + extern int wake_up_state(struct task_struct *tsk, unsigned int state); + extern int wake_up_process(struct task_struct *tsk); ++extern int wake_up_lock_sleeper(struct task_struct * tsk); + extern void wake_up_new_task(struct task_struct *tsk); + #ifdef CONFIG_SMP + extern void kick_process(struct task_struct *tsk); +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -1721,8 +1721,25 @@ try_to_wake_up(struct task_struct *p, un + */ + smp_mb__before_spinlock(); + raw_spin_lock_irqsave(&p->pi_lock, flags); +- if (!(p->state & state)) ++ if (!(p->state & state)) { ++ /* ++ * The task might be running due to a spinlock sleeper ++ * wakeup. Check the saved state and set it to running ++ * if the wakeup condition is true. ++ */ ++ if (!(wake_flags & WF_LOCK_SLEEPER)) { ++ if (p->saved_state & state) ++ p->saved_state = TASK_RUNNING; ++ } + goto out; ++ } ++ ++ /* ++ * If this is a regular wakeup, then we can unconditionally ++ * clear the saved state of a "lock sleeper". ++ */ ++ if (!(wake_flags & WF_LOCK_SLEEPER)) ++ p->saved_state = TASK_RUNNING; + + success = 1; /* we're going to change ->state */ + cpu = task_cpu(p); +@@ -1819,6 +1836,18 @@ int wake_up_process(struct task_struct * + } + EXPORT_SYMBOL(wake_up_process); + ++/** ++ * wake_up_lock_sleeper - Wake up a specific process blocked on a "sleeping lock" ++ * @p: The process to be woken up. ++ * ++ * Same as wake_up_process() above, but wake_flags=WF_LOCK_SLEEPER to indicate ++ * the nature of the wakeup. ++ */ ++int wake_up_lock_sleeper(struct task_struct *p) ++{ ++ return try_to_wake_up(p, TASK_ALL, WF_LOCK_SLEEPER); ++} ++ + int wake_up_state(struct task_struct *p, unsigned int state) + { + return try_to_wake_up(p, state, 0); +--- a/kernel/sched/sched.h ++++ b/kernel/sched/sched.h +@@ -1092,6 +1092,7 @@ static inline void finish_lock_switch(st + #define WF_SYNC 0x01 /* waker goes to sleep after wakeup */ + #define WF_FORK 0x02 /* child wakeup after fork */ + #define WF_MIGRATED 0x4 /* internal use, task got migrated */ ++#define WF_LOCK_SLEEPER 0x08 /* wakeup spinlock "sleeper" */ + + /* + * To aid in avoiding the subversion of "niceness" due to uneven distribution diff --git a/debian/patches/features/all/rt/sched-ttwu-ensure-success-return-is-correct.patch b/debian/patches/features/all/rt/sched-ttwu-ensure-success-return-is-correct.patch new file mode 100644 index 000000000..b72cd8084 --- /dev/null +++ b/debian/patches/features/all/rt/sched-ttwu-ensure-success-return-is-correct.patch @@ -0,0 +1,35 @@ +Subject: sched: ttwu: Return success when only changing the saved_state value +From: Thomas Gleixner +Date: Tue, 13 Dec 2011 21:42:19 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +When a task blocks on a rt lock, it saves the current state in +p->saved_state, so a lock related wake up will not destroy the +original state. + +When a real wakeup happens, while the task is running due to a lock +wakeup already, we update p->saved_state to TASK_RUNNING, but we do +not return success, which might cause another wakeup in the waitqueue +code and the task remains in the waitqueue list. Return success in +that case as well. + +Signed-off-by: Thomas Gleixner + +--- + kernel/sched/core.c | 4 +++- + 1 file changed, 3 insertions(+), 1 deletion(-) + +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -1728,8 +1728,10 @@ try_to_wake_up(struct task_struct *p, un + * if the wakeup condition is true. + */ + if (!(wake_flags & WF_LOCK_SLEEPER)) { +- if (p->saved_state & state) ++ if (p->saved_state & state) { + p->saved_state = TASK_RUNNING; ++ success = 1; ++ } + } + goto out; + } diff --git a/debian/patches/features/all/rt/sched-workqueue-Only-wake-up-idle-workers-if-not-blo.patch b/debian/patches/features/all/rt/sched-workqueue-Only-wake-up-idle-workers-if-not-blo.patch new file mode 100644 index 000000000..d17a715e1 --- /dev/null +++ b/debian/patches/features/all/rt/sched-workqueue-Only-wake-up-idle-workers-if-not-blo.patch @@ -0,0 +1,38 @@ +From: Steven Rostedt +Date: Mon, 18 Mar 2013 15:12:49 -0400 +Subject: sched/workqueue: Only wake up idle workers if not blocked on sleeping spin lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +In -rt, most spin_locks() turn into mutexes. One of these spin_lock +conversions is performed on the workqueue gcwq->lock. When the idle +worker is worken, the first thing it will do is grab that same lock and +it too will block, possibly jumping into the same code, but because +nr_running would already be decremented it prevents an infinite loop. + +But this is still a waste of CPU cycles, and it doesn't follow the method +of mainline, as new workers should only be woken when a worker thread is +truly going to sleep, and not just blocked on a spin_lock(). + +Check the saved_state too before waking up new workers. + + +Signed-off-by: Steven Rostedt +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/sched/core.c | 4 +++- + 1 file changed, 3 insertions(+), 1 deletion(-) + +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -2981,8 +2981,10 @@ static void __sched __schedule(void) + * If a worker went to sleep, notify and ask workqueue + * whether it wants to wake up a task to maintain + * concurrency. ++ * Only call wake up if prev isn't blocked on a sleeping ++ * spin lock. + */ +- if (prev->flags & PF_WQ_WORKER) { ++ if (prev->flags & PF_WQ_WORKER && !prev->saved_state) { + struct task_struct *to_wakeup; + + to_wakeup = wq_worker_sleeping(prev, cpu); diff --git a/debian/patches/features/all/rt/scsi-fcoe-rt-aware.patch b/debian/patches/features/all/rt/scsi-fcoe-rt-aware.patch new file mode 100644 index 000000000..6dd3b500b --- /dev/null +++ b/debian/patches/features/all/rt/scsi-fcoe-rt-aware.patch @@ -0,0 +1,115 @@ +Subject: scsi/fcoe: Make RT aware. +From: Thomas Gleixner +Date: Sat, 12 Nov 2011 14:00:48 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Do not disable preemption while taking sleeping locks. All user look safe +for migrate_diable() only. + +Signed-off-by: Thomas Gleixner +--- + drivers/scsi/fcoe/fcoe.c | 18 +++++++++--------- + drivers/scsi/fcoe/fcoe_ctlr.c | 4 ++-- + drivers/scsi/libfc/fc_exch.c | 4 ++-- + 3 files changed, 13 insertions(+), 13 deletions(-) + +--- a/drivers/scsi/fcoe/fcoe.c ++++ b/drivers/scsi/fcoe/fcoe.c +@@ -1287,7 +1287,7 @@ static void fcoe_percpu_thread_destroy(u + struct sk_buff *skb; + #ifdef CONFIG_SMP + struct fcoe_percpu_s *p0; +- unsigned targ_cpu = get_cpu(); ++ unsigned targ_cpu = get_cpu_light(); + #endif /* CONFIG_SMP */ + + FCOE_DBG("Destroying receive thread for CPU %d\n", cpu); +@@ -1343,7 +1343,7 @@ static void fcoe_percpu_thread_destroy(u + kfree_skb(skb); + spin_unlock_bh(&p->fcoe_rx_list.lock); + } +- put_cpu(); ++ put_cpu_light(); + #else + /* + * This a non-SMP scenario where the singular Rx thread is +@@ -1567,11 +1567,11 @@ static int fcoe_rcv(struct sk_buff *skb, + static int fcoe_alloc_paged_crc_eof(struct sk_buff *skb, int tlen) + { + struct fcoe_percpu_s *fps; +- int rc; ++ int rc, cpu = get_cpu_light(); + +- fps = &get_cpu_var(fcoe_percpu); ++ fps = &per_cpu(fcoe_percpu, cpu); + rc = fcoe_get_paged_crc_eof(skb, tlen, fps); +- put_cpu_var(fcoe_percpu); ++ put_cpu_light(); + + return rc; + } +@@ -1767,11 +1767,11 @@ static inline int fcoe_filter_frames(str + return 0; + } + +- stats = per_cpu_ptr(lport->stats, get_cpu()); ++ stats = per_cpu_ptr(lport->stats, get_cpu_light()); + stats->InvalidCRCCount++; + if (stats->InvalidCRCCount < 5) + printk(KERN_WARNING "fcoe: dropping frame with CRC error\n"); +- put_cpu(); ++ put_cpu_light(); + return -EINVAL; + } + +@@ -1847,13 +1847,13 @@ static void fcoe_recv_frame(struct sk_bu + goto drop; + + if (!fcoe_filter_frames(lport, fp)) { +- put_cpu(); ++ put_cpu_light(); + fc_exch_recv(lport, fp); + return; + } + drop: + stats->ErrorFrames++; +- put_cpu(); ++ put_cpu_light(); + kfree_skb(skb); + } + +--- a/drivers/scsi/fcoe/fcoe_ctlr.c ++++ b/drivers/scsi/fcoe/fcoe_ctlr.c +@@ -831,7 +831,7 @@ static unsigned long fcoe_ctlr_age_fcfs( + + INIT_LIST_HEAD(&del_list); + +- stats = per_cpu_ptr(fip->lp->stats, get_cpu()); ++ stats = per_cpu_ptr(fip->lp->stats, get_cpu_light()); + + list_for_each_entry_safe(fcf, next, &fip->fcfs, list) { + deadline = fcf->time + fcf->fka_period + fcf->fka_period / 2; +@@ -867,7 +867,7 @@ static unsigned long fcoe_ctlr_age_fcfs( + sel_time = fcf->time; + } + } +- put_cpu(); ++ put_cpu_light(); + + list_for_each_entry_safe(fcf, next, &del_list, list) { + /* Removes fcf from current list */ +--- a/drivers/scsi/libfc/fc_exch.c ++++ b/drivers/scsi/libfc/fc_exch.c +@@ -816,10 +816,10 @@ static struct fc_exch *fc_exch_em_alloc( + } + memset(ep, 0, sizeof(*ep)); + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + pool = per_cpu_ptr(mp->pool, cpu); + spin_lock_bh(&pool->lock); +- put_cpu(); ++ put_cpu_light(); + + /* peek cache of free slot */ + if (pool->left != FC_XID_UNKNOWN) { diff --git a/debian/patches/features/all/rt/scsi-qla2xxx-fix-bug-sleeping-function-called-from-invalid-context.patch b/debian/patches/features/all/rt/scsi-qla2xxx-fix-bug-sleeping-function-called-from-invalid-context.patch new file mode 100644 index 000000000..70e889628 --- /dev/null +++ b/debian/patches/features/all/rt/scsi-qla2xxx-fix-bug-sleeping-function-called-from-invalid-context.patch @@ -0,0 +1,48 @@ +Subject: scsi: qla2xxx: Use local_irq_save_nort() in qla2x00_poll +From: John Kacur +Date: Fri, 27 Apr 2012 12:48:46 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +RT triggers the following: + +[ 11.307652] [] __might_sleep+0xe7/0x110 +[ 11.307663] [] rt_spin_lock+0x24/0x60 +[ 11.307670] [] ? rt_spin_lock_slowunlock+0x78/0x90 +[ 11.307703] [] qla24xx_intr_handler+0x63/0x2d0 [qla2xxx] +[ 11.307736] [] qla2x00_poll+0x67/0x90 [qla2xxx] + +Function qla2x00_poll does local_irq_save() before calling qla24xx_intr_handler +which has a spinlock. Since spinlocks are sleepable on rt, it is not allowed +to call them with interrupts disabled. Therefore we use local_irq_save_nort() +instead which saves flags without disabling interrupts. + +This fix needs to be applied to v3.0-rt, v3.2-rt and v3.4-rt + +Suggested-by: Thomas Gleixner +Signed-off-by: John Kacur +Cc: Steven Rostedt +Cc: David Sommerseth +Link: http://lkml.kernel.org/r/1335523726-10024-1-git-send-email-jkacur@redhat.com + +Signed-off-by: Thomas Gleixner +--- + drivers/scsi/qla2xxx/qla_inline.h | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/drivers/scsi/qla2xxx/qla_inline.h ++++ b/drivers/scsi/qla2xxx/qla_inline.h +@@ -59,12 +59,12 @@ qla2x00_poll(struct rsp_que *rsp) + { + unsigned long flags; + struct qla_hw_data *ha = rsp->hw; +- local_irq_save(flags); ++ local_irq_save_nort(flags); + if (IS_P3P_TYPE(ha)) + qla82xx_poll(0, rsp); + else + ha->isp_ops->intr_handler(0, rsp); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + + static inline uint8_t * diff --git a/debian/patches/features/all/rt/seqlock-prevent-rt-starvation.patch b/debian/patches/features/all/rt/seqlock-prevent-rt-starvation.patch new file mode 100644 index 000000000..d21b601ac --- /dev/null +++ b/debian/patches/features/all/rt/seqlock-prevent-rt-starvation.patch @@ -0,0 +1,191 @@ +Subject: seqlock: Prevent rt starvation +From: Thomas Gleixner +Date: Wed, 22 Feb 2012 12:03:30 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +If a low prio writer gets preempted while holding the seqlock write +locked, a high prio reader spins forever on RT. + +To prevent this let the reader grab the spinlock, so it blocks and +eventually boosts the writer. This way the writer can proceed and +endless spinning is prevented. + +For seqcount writers we disable preemption over the update code +path. Thanks to Al Viro for distangling some VFS code to make that +possible. + +Nicholas Mc Guire: +- spin_lock+unlock => spin_unlock_wait +- __write_seqcount_begin => __raw_write_seqcount_begin + +Signed-off-by: Thomas Gleixner + + +--- + include/linux/seqlock.h | 56 +++++++++++++++++++++++++++++++++++++----------- + include/net/dst.h | 2 - + include/net/neighbour.h | 4 +-- + 3 files changed, 47 insertions(+), 15 deletions(-) + +--- a/include/linux/seqlock.h ++++ b/include/linux/seqlock.h +@@ -219,20 +219,30 @@ static inline int read_seqcount_retry(co + return __read_seqcount_retry(s, start); + } + +- +- +-static inline void raw_write_seqcount_begin(seqcount_t *s) ++static inline void __raw_write_seqcount_begin(seqcount_t *s) + { + s->sequence++; + smp_wmb(); + } + +-static inline void raw_write_seqcount_end(seqcount_t *s) ++static inline void raw_write_seqcount_begin(seqcount_t *s) ++{ ++ preempt_disable_rt(); ++ __raw_write_seqcount_begin(s); ++} ++ ++static inline void __raw_write_seqcount_end(seqcount_t *s) + { + smp_wmb(); + s->sequence++; + } + ++static inline void raw_write_seqcount_end(seqcount_t *s) ++{ ++ __raw_write_seqcount_end(s); ++ preempt_enable_rt(); ++} ++ + /* + * raw_write_seqcount_latch - redirect readers to even/odd copy + * @s: pointer to seqcount_t +@@ -305,10 +315,32 @@ typedef struct { + /* + * Read side functions for starting and finalizing a read side section. + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + static inline unsigned read_seqbegin(const seqlock_t *sl) + { + return read_seqcount_begin(&sl->seqcount); + } ++#else ++/* ++ * Starvation safe read side for RT ++ */ ++static inline unsigned read_seqbegin(seqlock_t *sl) ++{ ++ unsigned ret; ++ ++repeat: ++ ret = ACCESS_ONCE(sl->seqcount.sequence); ++ if (unlikely(ret & 1)) { ++ /* ++ * Take the lock and let the writer proceed (i.e. evtl ++ * boost it), otherwise we could loop here forever. ++ */ ++ spin_unlock_wait(&sl->lock); ++ goto repeat; ++ } ++ return ret; ++} ++#endif + + static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) + { +@@ -323,36 +355,36 @@ static inline unsigned read_seqretry(con + static inline void write_seqlock(seqlock_t *sl) + { + spin_lock(&sl->lock); +- write_seqcount_begin(&sl->seqcount); ++ __raw_write_seqcount_begin(&sl->seqcount); + } + + static inline void write_sequnlock(seqlock_t *sl) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_write_seqcount_end(&sl->seqcount); + spin_unlock(&sl->lock); + } + + static inline void write_seqlock_bh(seqlock_t *sl) + { + spin_lock_bh(&sl->lock); +- write_seqcount_begin(&sl->seqcount); ++ __raw_write_seqcount_begin(&sl->seqcount); + } + + static inline void write_sequnlock_bh(seqlock_t *sl) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_write_seqcount_end(&sl->seqcount); + spin_unlock_bh(&sl->lock); + } + + static inline void write_seqlock_irq(seqlock_t *sl) + { + spin_lock_irq(&sl->lock); +- write_seqcount_begin(&sl->seqcount); ++ __raw_write_seqcount_begin(&sl->seqcount); + } + + static inline void write_sequnlock_irq(seqlock_t *sl) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_write_seqcount_end(&sl->seqcount); + spin_unlock_irq(&sl->lock); + } + +@@ -361,7 +393,7 @@ static inline unsigned long __write_seql + unsigned long flags; + + spin_lock_irqsave(&sl->lock, flags); +- write_seqcount_begin(&sl->seqcount); ++ __raw_write_seqcount_begin(&sl->seqcount); + return flags; + } + +@@ -371,7 +403,7 @@ static inline unsigned long __write_seql + static inline void + write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_write_seqcount_end(&sl->seqcount); + spin_unlock_irqrestore(&sl->lock, flags); + } + +--- a/include/net/dst.h ++++ b/include/net/dst.h +@@ -403,7 +403,7 @@ static inline void dst_confirm(struct ds + static inline int dst_neigh_output(struct dst_entry *dst, struct neighbour *n, + struct sk_buff *skb) + { +- const struct hh_cache *hh; ++ struct hh_cache *hh; + + if (dst->pending_confirm) { + unsigned long now = jiffies; +--- a/include/net/neighbour.h ++++ b/include/net/neighbour.h +@@ -445,7 +445,7 @@ static inline int neigh_hh_bridge(struct + } + #endif + +-static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb) ++static inline int neigh_hh_output(struct hh_cache *hh, struct sk_buff *skb) + { + unsigned int seq; + int hh_len; +@@ -500,7 +500,7 @@ struct neighbour_cb { + + #define NEIGH_CB(skb) ((struct neighbour_cb *)(skb)->cb) + +-static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n, ++static inline void neigh_ha_snapshot(char *dst, struct neighbour *n, + const struct net_device *dev) + { + unsigned int seq; diff --git a/debian/patches/features/all/rt/signal-fix-up-rcu-wreckage.patch b/debian/patches/features/all/rt/signal-fix-up-rcu-wreckage.patch new file mode 100644 index 000000000..014d34d0c --- /dev/null +++ b/debian/patches/features/all/rt/signal-fix-up-rcu-wreckage.patch @@ -0,0 +1,39 @@ +Subject: signal: Make __lock_task_sighand() RT aware +From: Thomas Gleixner +Date: Fri, 22 Jul 2011 08:07:08 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +local_irq_save() + spin_lock(&sighand->siglock) does not work on +-RT. Use the nort variants. + +Signed-off-by: Thomas Gleixner +--- + kernel/signal.c | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +--- a/kernel/signal.c ++++ b/kernel/signal.c +@@ -1342,12 +1342,12 @@ struct sighand_struct *__lock_task_sigha + * Disable interrupts early to avoid deadlocks. + * See rcu_read_unlock() comment header for details. + */ +- local_irq_save(*flags); ++ local_irq_save_nort(*flags); + rcu_read_lock(); + sighand = rcu_dereference(tsk->sighand); + if (unlikely(sighand == NULL)) { + rcu_read_unlock(); +- local_irq_restore(*flags); ++ local_irq_restore_nort(*flags); + break; + } + /* +@@ -1368,7 +1368,7 @@ struct sighand_struct *__lock_task_sigha + } + spin_unlock(&sighand->siglock); + rcu_read_unlock(); +- local_irq_restore(*flags); ++ local_irq_restore_nort(*flags); + } + + return sighand; diff --git a/debian/patches/features/all/rt/signal-revert-ptrace-preempt-magic.patch b/debian/patches/features/all/rt/signal-revert-ptrace-preempt-magic.patch new file mode 100644 index 000000000..f63cdc2b9 --- /dev/null +++ b/debian/patches/features/all/rt/signal-revert-ptrace-preempt-magic.patch @@ -0,0 +1,32 @@ +Subject: signal: Revert ptrace preempt magic +From: Thomas Gleixner +Date: Wed, 21 Sep 2011 19:57:12 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Upstream commit '53da1d9456fe7f8 fix ptrace slowness' is nothing more +than a bandaid around the ptrace design trainwreck. It's not a +correctness issue, it's merily a cosmetic bandaid. + +Signed-off-by: Thomas Gleixner +--- + kernel/signal.c | 8 -------- + 1 file changed, 8 deletions(-) + +--- a/kernel/signal.c ++++ b/kernel/signal.c +@@ -1897,15 +1897,7 @@ static void ptrace_stop(int exit_code, i + if (gstop_done && ptrace_reparented(current)) + do_notify_parent_cldstop(current, false, why); + +- /* +- * Don't want to allow preemption here, because +- * sys_ptrace() needs this task to be inactive. +- * +- * XXX: implement read_unlock_no_resched(). +- */ +- preempt_disable(); + read_unlock(&tasklist_lock); +- preempt_enable_no_resched(); + freezable_schedule(); + } else { + /* diff --git a/debian/patches/features/all/rt/signals-allow-rt-tasks-to-cache-one-sigqueue-struct.patch b/debian/patches/features/all/rt/signals-allow-rt-tasks-to-cache-one-sigqueue-struct.patch new file mode 100644 index 000000000..6b5ced429 --- /dev/null +++ b/debian/patches/features/all/rt/signals-allow-rt-tasks-to-cache-one-sigqueue-struct.patch @@ -0,0 +1,214 @@ +From: Thomas Gleixner +Date: Fri, 3 Jul 2009 08:44:56 -0500 +Subject: signals: Allow rt tasks to cache one sigqueue struct +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +To avoid allocation allow rt tasks to cache one sigqueue struct in +task struct. + +Signed-off-by: Thomas Gleixner + +--- + include/linux/sched.h | 1 + include/linux/signal.h | 1 + kernel/exit.c | 2 - + kernel/fork.c | 1 + kernel/signal.c | 84 ++++++++++++++++++++++++++++++++++++++++++++++--- + 5 files changed, 84 insertions(+), 5 deletions(-) + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -1527,6 +1527,7 @@ struct task_struct { + /* signal handlers */ + struct signal_struct *signal; + struct sighand_struct *sighand; ++ struct sigqueue *sigqueue_cache; + + sigset_t blocked, real_blocked; + sigset_t saved_sigmask; /* restored if set_restore_sigmask() was used */ +--- a/include/linux/signal.h ++++ b/include/linux/signal.h +@@ -218,6 +218,7 @@ static inline void init_sigpending(struc + } + + extern void flush_sigqueue(struct sigpending *queue); ++extern void flush_task_sigqueue(struct task_struct *tsk); + + /* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */ + static inline int valid_signal(unsigned long sig) +--- a/kernel/exit.c ++++ b/kernel/exit.c +@@ -144,7 +144,7 @@ static void __exit_signal(struct task_st + * Do this under ->siglock, we can race with another thread + * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. + */ +- flush_sigqueue(&tsk->pending); ++ flush_task_sigqueue(tsk); + tsk->sighand = NULL; + spin_unlock(&sighand->siglock); + +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -1338,6 +1338,7 @@ static struct task_struct *copy_process( + spin_lock_init(&p->alloc_lock); + + init_sigpending(&p->pending); ++ p->sigqueue_cache = NULL; + + p->utime = p->stime = p->gtime = 0; + p->utimescaled = p->stimescaled = 0; +--- a/kernel/signal.c ++++ b/kernel/signal.c +@@ -14,6 +14,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -352,13 +353,45 @@ static bool task_participate_group_stop( + return false; + } + ++#ifdef __HAVE_ARCH_CMPXCHG ++static inline struct sigqueue *get_task_cache(struct task_struct *t) ++{ ++ struct sigqueue *q = t->sigqueue_cache; ++ ++ if (cmpxchg(&t->sigqueue_cache, q, NULL) != q) ++ return NULL; ++ return q; ++} ++ ++static inline int put_task_cache(struct task_struct *t, struct sigqueue *q) ++{ ++ if (cmpxchg(&t->sigqueue_cache, NULL, q) == NULL) ++ return 0; ++ return 1; ++} ++ ++#else ++ ++static inline struct sigqueue *get_task_cache(struct task_struct *t) ++{ ++ return NULL; ++} ++ ++static inline int put_task_cache(struct task_struct *t, struct sigqueue *q) ++{ ++ return 1; ++} ++ ++#endif ++ + /* + * allocate a new signal queue record + * - this may be called without locks if and only if t == current, otherwise an + * appropriate lock must be held to stop the target task from exiting + */ + static struct sigqueue * +-__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit) ++__sigqueue_do_alloc(int sig, struct task_struct *t, gfp_t flags, ++ int override_rlimit, int fromslab) + { + struct sigqueue *q = NULL; + struct user_struct *user; +@@ -375,7 +408,10 @@ static struct sigqueue * + if (override_rlimit || + atomic_read(&user->sigpending) <= + task_rlimit(t, RLIMIT_SIGPENDING)) { +- q = kmem_cache_alloc(sigqueue_cachep, flags); ++ if (!fromslab) ++ q = get_task_cache(t); ++ if (!q) ++ q = kmem_cache_alloc(sigqueue_cachep, flags); + } else { + print_dropped_signal(sig); + } +@@ -392,6 +428,13 @@ static struct sigqueue * + return q; + } + ++static struct sigqueue * ++__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, ++ int override_rlimit) ++{ ++ return __sigqueue_do_alloc(sig, t, flags, override_rlimit, 0); ++} ++ + static void __sigqueue_free(struct sigqueue *q) + { + if (q->flags & SIGQUEUE_PREALLOC) +@@ -401,6 +444,21 @@ static void __sigqueue_free(struct sigqu + kmem_cache_free(sigqueue_cachep, q); + } + ++static void sigqueue_free_current(struct sigqueue *q) ++{ ++ struct user_struct *up; ++ ++ if (q->flags & SIGQUEUE_PREALLOC) ++ return; ++ ++ up = q->user; ++ if (rt_prio(current->normal_prio) && !put_task_cache(current, q)) { ++ atomic_dec(&up->sigpending); ++ free_uid(up); ++ } else ++ __sigqueue_free(q); ++} ++ + void flush_sigqueue(struct sigpending *queue) + { + struct sigqueue *q; +@@ -414,6 +472,21 @@ void flush_sigqueue(struct sigpending *q + } + + /* ++ * Called from __exit_signal. Flush tsk->pending and ++ * tsk->sigqueue_cache ++ */ ++void flush_task_sigqueue(struct task_struct *tsk) ++{ ++ struct sigqueue *q; ++ ++ flush_sigqueue(&tsk->pending); ++ ++ q = get_task_cache(tsk); ++ if (q) ++ kmem_cache_free(sigqueue_cachep, q); ++} ++ ++/* + * Flush all pending signals for a task. + */ + void __flush_signals(struct task_struct *t) +@@ -565,7 +638,7 @@ static void collect_signal(int sig, stru + still_pending: + list_del_init(&first->list); + copy_siginfo(info, &first->info); +- __sigqueue_free(first); ++ sigqueue_free_current(first); + } else { + /* + * Ok, it wasn't in the queue. This must be +@@ -611,6 +684,8 @@ int dequeue_signal(struct task_struct *t + { + int signr; + ++ WARN_ON_ONCE(tsk != current); ++ + /* We only dequeue private signals from ourselves, we don't let + * signalfd steal them + */ +@@ -1536,7 +1611,8 @@ EXPORT_SYMBOL(kill_pid); + */ + struct sigqueue *sigqueue_alloc(void) + { +- struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0); ++ /* Preallocated sigqueue objects always from the slabcache ! */ ++ struct sigqueue *q = __sigqueue_do_alloc(-1, current, GFP_KERNEL, 0, 1); + + if (q) + q->flags |= SIGQUEUE_PREALLOC; diff --git a/debian/patches/features/all/rt/skbufhead-raw-lock.patch b/debian/patches/features/all/rt/skbufhead-raw-lock.patch new file mode 100644 index 000000000..9d410c378 --- /dev/null +++ b/debian/patches/features/all/rt/skbufhead-raw-lock.patch @@ -0,0 +1,114 @@ +From: Thomas Gleixner +Date: Tue, 12 Jul 2011 15:38:34 +0200 +Subject: net: Use skbufhead with raw lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Use the rps lock as rawlock so we can keep irq-off regions. It looks low +latency. However we can't kfree() from this context therefore we defer this +to the softirq and use the tofree_queue list for it (similar to process_queue). + +Signed-off-by: Thomas Gleixner +--- + include/linux/netdevice.h | 1 + + include/linux/skbuff.h | 7 +++++++ + net/core/dev.c | 19 +++++++++++++------ + 3 files changed, 21 insertions(+), 6 deletions(-) + +--- a/include/linux/netdevice.h ++++ b/include/linux/netdevice.h +@@ -2469,6 +2469,7 @@ struct softnet_data { + unsigned int dropped; + struct sk_buff_head input_pkt_queue; + struct napi_struct backlog; ++ struct sk_buff_head tofree_queue; + + }; + +--- a/include/linux/skbuff.h ++++ b/include/linux/skbuff.h +@@ -187,6 +187,7 @@ struct sk_buff_head { + + __u32 qlen; + spinlock_t lock; ++ raw_spinlock_t raw_lock; + }; + + struct sk_buff; +@@ -1336,6 +1337,12 @@ static inline void skb_queue_head_init(s + __skb_queue_head_init(list); + } + ++static inline void skb_queue_head_init_raw(struct sk_buff_head *list) ++{ ++ raw_spin_lock_init(&list->raw_lock); ++ __skb_queue_head_init(list); ++} ++ + static inline void skb_queue_head_init_class(struct sk_buff_head *list, + struct lock_class_key *class) + { +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -205,14 +205,14 @@ static inline struct hlist_head *dev_ind + static inline void rps_lock(struct softnet_data *sd) + { + #ifdef CONFIG_RPS +- spin_lock(&sd->input_pkt_queue.lock); ++ raw_spin_lock(&sd->input_pkt_queue.raw_lock); + #endif + } + + static inline void rps_unlock(struct softnet_data *sd) + { + #ifdef CONFIG_RPS +- spin_unlock(&sd->input_pkt_queue.lock); ++ raw_spin_unlock(&sd->input_pkt_queue.raw_lock); + #endif + } + +@@ -3885,7 +3885,7 @@ static void flush_backlog(void *arg) + skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { + if (skb->dev == dev) { + __skb_unlink(skb, &sd->input_pkt_queue); +- kfree_skb(skb); ++ __skb_queue_tail(&sd->tofree_queue, skb); + input_queue_head_incr(sd); + } + } +@@ -3894,10 +3894,13 @@ static void flush_backlog(void *arg) + skb_queue_walk_safe(&sd->process_queue, skb, tmp) { + if (skb->dev == dev) { + __skb_unlink(skb, &sd->process_queue); +- kfree_skb(skb); ++ __skb_queue_tail(&sd->tofree_queue, skb); + input_queue_head_incr(sd); + } + } ++ ++ if (!skb_queue_empty(&sd->tofree_queue)) ++ raise_softirq_irqoff(NET_RX_SOFTIRQ); + } + + static int napi_gro_complete(struct sk_buff *skb) +@@ -7183,6 +7186,9 @@ static int dev_cpu_callback(struct notif + netif_rx_ni(skb); + input_queue_head_incr(oldsd); + } ++ while ((skb = __skb_dequeue(&oldsd->tofree_queue))) { ++ kfree_skb(skb); ++ } + + return NOTIFY_OK; + } +@@ -7484,8 +7490,9 @@ static int __init net_dev_init(void) + for_each_possible_cpu(i) { + struct softnet_data *sd = &per_cpu(softnet_data, i); + +- skb_queue_head_init(&sd->input_pkt_queue); +- skb_queue_head_init(&sd->process_queue); ++ skb_queue_head_init_raw(&sd->input_pkt_queue); ++ skb_queue_head_init_raw(&sd->process_queue); ++ skb_queue_head_init_raw(&sd->tofree_queue); + INIT_LIST_HEAD(&sd->poll_list); + sd->output_queue_tailp = &sd->output_queue; + #ifdef CONFIG_RPS diff --git a/debian/patches/features/all/rt/slub-disable-SLUB_CPU_PARTIAL.patch b/debian/patches/features/all/rt/slub-disable-SLUB_CPU_PARTIAL.patch new file mode 100644 index 000000000..bcb80721e --- /dev/null +++ b/debian/patches/features/all/rt/slub-disable-SLUB_CPU_PARTIAL.patch @@ -0,0 +1,48 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 15 Apr 2015 19:00:47 +0200 +Subject: slub: Disable SLUB_CPU_PARTIAL +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +|BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:915 +|in_atomic(): 1, irqs_disabled(): 0, pid: 87, name: rcuop/7 +|1 lock held by rcuop/7/87: +| #0: (rcu_callback){......}, at: [] rcu_nocb_kthread+0x1ca/0x5d0 +|Preemption disabled at:[] put_cpu_partial+0x29/0x220 +| +|CPU: 0 PID: 87 Comm: rcuop/7 Tainted: G W 4.0.0-rt0+ #477 +|Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014 +| 000000000007a9fc ffff88013987baf8 ffffffff817441c7 0000000000000007 +| 0000000000000000 ffff88013987bb18 ffffffff810eee51 0000000000000000 +| ffff88013fc10200 ffff88013987bb48 ffffffff8174a1c4 000000000007a9fc +|Call Trace: +| [] dump_stack+0x4f/0x90 +| [] ___might_sleep+0x121/0x1b0 +| [] rt_spin_lock+0x24/0x60 +| [] __free_pages_ok+0xaa/0x540 +| [] __free_pages+0x1d/0x30 +| [] __free_slab+0xc5/0x1e0 +| [] free_delayed+0x56/0x70 +| [] put_cpu_partial+0x14d/0x220 +| [] __slab_free+0x158/0x2c0 +| [] kmem_cache_free+0x221/0x2d0 +| [] file_free_rcu+0x2c/0x40 +| [] rcu_nocb_kthread+0x243/0x5d0 +| [] kthread+0xfc/0x120 +| [] ret_from_fork+0x58/0x90 + +Signed-off-by: Sebastian Andrzej Siewior +--- + init/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/init/Kconfig ++++ b/init/Kconfig +@@ -1717,7 +1717,7 @@ endchoice + + config SLUB_CPU_PARTIAL + default y +- depends on SLUB && SMP ++ depends on SLUB && SMP && !PREEMPT_RT_FULL + bool "SLUB per cpu partial cache" + help + Per cpu partial caches accellerate objects allocation and freeing diff --git a/debian/patches/features/all/rt/slub-enable-irqs-for-no-wait.patch b/debian/patches/features/all/rt/slub-enable-irqs-for-no-wait.patch new file mode 100644 index 000000000..fd759924c --- /dev/null +++ b/debian/patches/features/all/rt/slub-enable-irqs-for-no-wait.patch @@ -0,0 +1,47 @@ +Subject: slub: Enable irqs for __GFP_WAIT +From: Thomas Gleixner +Date: Wed, 09 Jan 2013 12:08:15 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +SYSTEM_RUNNING might be too late for enabling interrupts. Allocations +with GFP_WAIT can happen before that. So use this as an indicator. + +Signed-off-by: Thomas Gleixner +--- + mm/slub.c | 13 +++++-------- + 1 file changed, 5 insertions(+), 8 deletions(-) + +--- a/mm/slub.c ++++ b/mm/slub.c +@@ -1355,14 +1355,15 @@ static struct page *allocate_slab(struct + gfp_t alloc_gfp; + void *start, *p; + int idx, order; ++ bool enableirqs; + + flags &= gfp_allowed_mask; + ++ enableirqs = (flags & __GFP_WAIT) != 0; + #ifdef CONFIG_PREEMPT_RT_FULL +- if (system_state == SYSTEM_RUNNING) +-#else +- if (flags & __GFP_WAIT) ++ enableirqs |= system_state == SYSTEM_RUNNING; + #endif ++ if (enableirqs) + local_irq_enable(); + + flags |= s->allocflags; +@@ -1431,11 +1432,7 @@ static struct page *allocate_slab(struct + page->frozen = 1; + + out: +-#ifdef CONFIG_PREEMPT_RT_FULL +- if (system_state == SYSTEM_RUNNING) +-#else +- if (flags & __GFP_WAIT) +-#endif ++ if (enableirqs) + local_irq_disable(); + if (!page) + return NULL; diff --git a/debian/patches/features/all/rt/snd-pcm-fix-snd_pcm_stream_lock-irqs_disabled-splats.patch b/debian/patches/features/all/rt/snd-pcm-fix-snd_pcm_stream_lock-irqs_disabled-splats.patch new file mode 100644 index 000000000..d7370816a --- /dev/null +++ b/debian/patches/features/all/rt/snd-pcm-fix-snd_pcm_stream_lock-irqs_disabled-splats.patch @@ -0,0 +1,70 @@ +From: Mike Galbraith +Date: Wed, 18 Feb 2015 15:09:23 +0100 +Subject: snd/pcm: fix snd_pcm_stream_lock*() irqs_disabled() splats +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Locking functions previously using read_lock_irq()/read_lock_irqsave() were +changed to local_irq_disable/save(), leading to gripes. Use nort variants. + +|BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:915 +|in_atomic(): 0, irqs_disabled(): 1, pid: 5947, name: alsa-sink-ALC88 +|CPU: 5 PID: 5947 Comm: alsa-sink-ALC88 Not tainted 3.18.7-rt1 #9 +|Hardware name: MEDION MS-7848/MS-7848, BIOS M7848W08.404 11/06/2014 +| ffff880409316240 ffff88040866fa38 ffffffff815bdeb5 0000000000000002 +| 0000000000000000 ffff88040866fa58 ffffffff81073c86 ffffffffa03b2640 +| ffff88040239ec00 ffff88040866fa78 ffffffff815c3d34 ffffffffa03b2640 +|Call Trace: +| [] dump_stack+0x4f/0x9e +| [] __might_sleep+0xe6/0x150 +| [] __rt_spin_lock+0x24/0x50 +| [] rt_read_lock+0x34/0x40 +| [] snd_pcm_stream_lock+0x29/0x70 [snd_pcm] +| [] snd_pcm_playback_poll+0x5d/0x120 [snd_pcm] +| [] do_sys_poll+0x322/0x5b0 +| [] SyS_ppoll+0x1a8/0x1c0 +| [] system_call_fastpath+0x16/0x1b + +Signed-off-by: Mike Galbraith +Signed-off-by: Sebastian Andrzej Siewior +--- + sound/core/pcm_native.c | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +--- a/sound/core/pcm_native.c ++++ b/sound/core/pcm_native.c +@@ -123,7 +123,7 @@ EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock) + void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream) + { + if (!substream->pcm->nonatomic) +- local_irq_disable(); ++ local_irq_disable_nort(); + snd_pcm_stream_lock(substream); + } + EXPORT_SYMBOL_GPL(snd_pcm_stream_lock_irq); +@@ -138,7 +138,7 @@ void snd_pcm_stream_unlock_irq(struct sn + { + snd_pcm_stream_unlock(substream); + if (!substream->pcm->nonatomic) +- local_irq_enable(); ++ local_irq_enable_nort(); + } + EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irq); + +@@ -146,7 +146,7 @@ unsigned long _snd_pcm_stream_lock_irqsa + { + unsigned long flags = 0; + if (!substream->pcm->nonatomic) +- local_irq_save(flags); ++ local_irq_save_nort(flags); + snd_pcm_stream_lock(substream); + return flags; + } +@@ -164,7 +164,7 @@ void snd_pcm_stream_unlock_irqrestore(st + { + snd_pcm_stream_unlock(substream); + if (!substream->pcm->nonatomic) +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irqrestore); + diff --git a/debian/patches/features/all/rt/softirq-disable-softirq-stacks-for-rt.patch b/debian/patches/features/all/rt/softirq-disable-softirq-stacks-for-rt.patch new file mode 100644 index 000000000..81b9c1bf5 --- /dev/null +++ b/debian/patches/features/all/rt/softirq-disable-softirq-stacks-for-rt.patch @@ -0,0 +1,157 @@ +Subject: softirq: Disable softirq stacks for RT +From: Thomas Gleixner +Date: Mon, 18 Jul 2011 13:59:17 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Disable extra stacks for softirqs. We want to preempt softirqs and +having them on special IRQ-stack does not make this easier. + +Signed-off-by: Thomas Gleixner +--- + arch/powerpc/kernel/irq.c | 2 ++ + arch/powerpc/kernel/misc_32.S | 2 ++ + arch/powerpc/kernel/misc_64.S | 2 ++ + arch/sh/kernel/irq.c | 2 ++ + arch/sparc/kernel/irq_64.c | 2 ++ + arch/x86/kernel/entry_64.S | 2 ++ + arch/x86/kernel/irq_32.c | 2 ++ + include/linux/interrupt.h | 2 +- + 8 files changed, 15 insertions(+), 1 deletion(-) + +--- a/arch/powerpc/kernel/irq.c ++++ b/arch/powerpc/kernel/irq.c +@@ -614,6 +614,7 @@ void irq_ctx_init(void) + } + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void do_softirq_own_stack(void) + { + struct thread_info *curtp, *irqtp; +@@ -631,6 +632,7 @@ void do_softirq_own_stack(void) + if (irqtp->flags) + set_bits(irqtp->flags, &curtp->flags); + } ++#endif + + irq_hw_number_t virq_to_hw(unsigned int virq) + { +--- a/arch/powerpc/kernel/misc_32.S ++++ b/arch/powerpc/kernel/misc_32.S +@@ -40,6 +40,7 @@ + * We store the saved ksp_limit in the unused part + * of the STACK_FRAME_OVERHEAD + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + _GLOBAL(call_do_softirq) + mflr r0 + stw r0,4(r1) +@@ -56,6 +57,7 @@ + stw r10,THREAD+KSP_LIMIT(r2) + mtlr r0 + blr ++#endif + + /* + * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp); +--- a/arch/powerpc/kernel/misc_64.S ++++ b/arch/powerpc/kernel/misc_64.S +@@ -29,6 +29,7 @@ + + .text + ++#ifndef CONFIG_PREEMPT_RT_FULL + _GLOBAL(call_do_softirq) + mflr r0 + std r0,16(r1) +@@ -39,6 +40,7 @@ + ld r0,16(r1) + mtlr r0 + blr ++#endif + + _GLOBAL(call_do_irq) + mflr r0 +--- a/arch/sh/kernel/irq.c ++++ b/arch/sh/kernel/irq.c +@@ -147,6 +147,7 @@ void irq_ctx_exit(int cpu) + hardirq_ctx[cpu] = NULL; + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void do_softirq_own_stack(void) + { + struct thread_info *curctx; +@@ -174,6 +175,7 @@ void do_softirq_own_stack(void) + "r5", "r6", "r7", "r8", "r9", "r15", "t", "pr" + ); + } ++#endif + #else + static inline void handle_one_irq(unsigned int irq) + { +--- a/arch/sparc/kernel/irq_64.c ++++ b/arch/sparc/kernel/irq_64.c +@@ -849,6 +849,7 @@ void __irq_entry handler_irq(int pil, st + set_irq_regs(old_regs); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void do_softirq_own_stack(void) + { + void *orig_sp, *sp = softirq_stack[smp_processor_id()]; +@@ -863,6 +864,7 @@ void do_softirq_own_stack(void) + __asm__ __volatile__("mov %0, %%sp" + : : "r" (orig_sp)); + } ++#endif + + #ifdef CONFIG_HOTPLUG_CPU + void fixup_irqs(void) +--- a/arch/x86/kernel/entry_64.S ++++ b/arch/x86/kernel/entry_64.S +@@ -1120,6 +1120,7 @@ END(native_load_gs_index) + jmp 2b + .previous + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* Call softirq on interrupt stack. Interrupts are off. */ + ENTRY(do_softirq_own_stack) + CFI_STARTPROC +@@ -1139,6 +1140,7 @@ ENTRY(do_softirq_own_stack) + ret + CFI_ENDPROC + END(do_softirq_own_stack) ++#endif + + #ifdef CONFIG_XEN + idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0 +--- a/arch/x86/kernel/irq_32.c ++++ b/arch/x86/kernel/irq_32.c +@@ -135,6 +135,7 @@ void irq_ctx_init(int cpu) + cpu, per_cpu(hardirq_stack, cpu), per_cpu(softirq_stack, cpu)); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void do_softirq_own_stack(void) + { + struct thread_info *curstk; +@@ -153,6 +154,7 @@ void do_softirq_own_stack(void) + + call_on_stack(__do_softirq, isp); + } ++#endif + + bool handle_irq(unsigned irq, struct pt_regs *regs) + { +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -443,7 +443,7 @@ struct softirq_action + asmlinkage void do_softirq(void); + asmlinkage void __do_softirq(void); + +-#ifdef __ARCH_HAS_DO_SOFTIRQ ++#if defined(__ARCH_HAS_DO_SOFTIRQ) && !defined(CONFIG_PREEMPT_RT_FULL) + void do_softirq_own_stack(void); + #else + static inline void do_softirq_own_stack(void) diff --git a/debian/patches/features/all/rt/softirq-preempt-fix-3-re.patch b/debian/patches/features/all/rt/softirq-preempt-fix-3-re.patch new file mode 100644 index 000000000..5c7ffc5dc --- /dev/null +++ b/debian/patches/features/all/rt/softirq-preempt-fix-3-re.patch @@ -0,0 +1,154 @@ +Subject: softirq: Check preemption after reenabling interrupts +From: Thomas Gleixner +Date: Sun, 13 Nov 2011 17:17:09 +0100 (CET) +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +raise_softirq_irqoff() disables interrupts and wakes the softirq +daemon, but after reenabling interrupts there is no preemption check, +so the execution of the softirq thread might be delayed arbitrarily. + +In principle we could add that check to local_irq_enable/restore, but +that's overkill as the rasie_softirq_irqoff() sections are the only +ones which show this behaviour. + +Reported-by: Carsten Emde +Signed-off-by: Thomas Gleixner + +--- + block/blk-iopoll.c | 3 +++ + block/blk-softirq.c | 3 +++ + include/linux/preempt.h | 3 +++ + net/core/dev.c | 7 +++++++ + 4 files changed, 16 insertions(+) + +--- a/block/blk-iopoll.c ++++ b/block/blk-iopoll.c +@@ -35,6 +35,7 @@ void blk_iopoll_sched(struct blk_iopoll + list_add_tail(&iop->list, this_cpu_ptr(&blk_cpu_iopoll)); + __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(blk_iopoll_sched); + +@@ -132,6 +133,7 @@ static void blk_iopoll_softirq(struct so + __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ); + + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + /** +@@ -201,6 +203,7 @@ static int blk_iopoll_cpu_notify(struct + this_cpu_ptr(&blk_cpu_iopoll)); + __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ); + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + return NOTIFY_OK; +--- a/block/blk-softirq.c ++++ b/block/blk-softirq.c +@@ -51,6 +51,7 @@ static void trigger_softirq(void *data) + raise_softirq_irqoff(BLOCK_SOFTIRQ); + + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + + /* +@@ -93,6 +94,7 @@ static int blk_cpu_notify(struct notifie + this_cpu_ptr(&blk_cpu_done)); + raise_softirq_irqoff(BLOCK_SOFTIRQ); + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + return NOTIFY_OK; +@@ -150,6 +152,7 @@ void __blk_complete_request(struct reque + goto do_local; + + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + + /** +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -49,8 +49,10 @@ do { \ + + #ifdef CONFIG_PREEMPT_RT_BASE + # define preempt_enable_no_resched() sched_preempt_enable_no_resched() ++# define preempt_check_resched_rt() preempt_check_resched() + #else + # define preempt_enable_no_resched() preempt_enable() ++# define preempt_check_resched_rt() barrier(); + #endif + + #ifdef CONFIG_PREEMPT +@@ -125,6 +127,7 @@ do { \ + #define preempt_disable_notrace() barrier() + #define preempt_enable_no_resched_notrace() barrier() + #define preempt_enable_notrace() barrier() ++#define preempt_check_resched_rt() barrier() + + #endif /* CONFIG_PREEMPT_COUNT */ + +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -2218,6 +2218,7 @@ static inline void __netif_reschedule(st + sd->output_queue_tailp = &q->next_sched; + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + + void __netif_schedule(struct Qdisc *q) +@@ -2299,6 +2300,7 @@ void __dev_kfree_skb_irq(struct sk_buff + __this_cpu_write(softnet_data.completion_queue, skb); + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(__dev_kfree_skb_irq); + +@@ -3366,6 +3368,7 @@ static int enqueue_to_backlog(struct sk_ + rps_unlock(sd); + + local_irq_restore(flags); ++ preempt_check_resched_rt(); + + atomic_long_inc(&skb->dev->rx_dropped); + kfree_skb(skb); +@@ -4347,6 +4350,7 @@ static void net_rps_action_and_irq_enabl + sd->rps_ipi_list = NULL; + + local_irq_enable(); ++ preempt_check_resched_rt(); + + /* Send pending IPI's to kick RPS processing on remote cpus. */ + while (remsd) { +@@ -4360,6 +4364,7 @@ static void net_rps_action_and_irq_enabl + } else + #endif + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + static bool sd_has_rps_ipi_waiting(struct softnet_data *sd) +@@ -4439,6 +4444,7 @@ void __napi_schedule(struct napi_struct + local_irq_save(flags); + ____napi_schedule(this_cpu_ptr(&softnet_data), n); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(__napi_schedule); + +@@ -7168,6 +7174,7 @@ static int dev_cpu_callback(struct notif + + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_enable(); ++ preempt_check_resched_rt(); + + /* Process offline CPU's input_pkt_queue */ + while ((skb = __skb_dequeue(&oldsd->process_queue))) { diff --git a/debian/patches/features/all/rt/softirq-split-locks.patch b/debian/patches/features/all/rt/softirq-split-locks.patch new file mode 100644 index 000000000..c48bc6fca --- /dev/null +++ b/debian/patches/features/all/rt/softirq-split-locks.patch @@ -0,0 +1,827 @@ +From: Thomas Gleixner +Date: Thu, 04 Oct 2012 14:20:47 +0100 +Subject: softirq: Split softirq locks +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The 3.x RT series removed the split softirq implementation in favour +of pushing softirq processing into the context of the thread which +raised it. Though this prevents us from handling the various softirqs +at different priorities. Now instead of reintroducing the split +softirq threads we split the locks which serialize the softirq +processing. + +If a softirq is raised in context of a thread, then the softirq is +noted on a per thread field, if the thread is in a bh disabled +region. If the softirq is raised from hard interrupt context, then the +bit is set in the flag field of ksoftirqd and ksoftirqd is invoked. +When a thread leaves a bh disabled region, then it tries to execute +the softirqs which have been raised in its own context. It acquires +the per softirq / per cpu lock for the softirq and then checks, +whether the softirq is still pending in the per cpu +local_softirq_pending() field. If yes, it runs the softirq. If no, +then some other task executed it already. This allows for zero config +softirq elevation in the context of user space tasks or interrupt +threads. + +Signed-off-by: Thomas Gleixner +--- + include/linux/bottom_half.h | 12 + include/linux/interrupt.h | 15 + + include/linux/preempt_mask.h | 15 - + include/linux/sched.h | 3 + init/main.c | 1 + kernel/softirq.c | 518 ++++++++++++++++++++++++++++++++++++------- + kernel/time/tick-sched.c | 9 + net/core/dev.c | 6 + 8 files changed, 485 insertions(+), 94 deletions(-) + +--- a/include/linux/bottom_half.h ++++ b/include/linux/bottom_half.h +@@ -4,6 +4,17 @@ + #include + #include + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++extern void local_bh_disable(void); ++extern void _local_bh_enable(void); ++extern void local_bh_enable(void); ++extern void local_bh_enable_ip(unsigned long ip); ++extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt); ++extern void __local_bh_enable_ip(unsigned long ip, unsigned int cnt); ++ ++#else ++ + #ifdef CONFIG_TRACE_IRQFLAGS + extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt); + #else +@@ -31,5 +42,6 @@ static inline void local_bh_enable(void) + { + __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET); + } ++#endif + + #endif /* _LINUX_BH_H */ +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -440,10 +440,11 @@ struct softirq_action + void (*action)(struct softirq_action *); + }; + ++#ifndef CONFIG_PREEMPT_RT_FULL + asmlinkage void do_softirq(void); + asmlinkage void __do_softirq(void); +- +-#if defined(__ARCH_HAS_DO_SOFTIRQ) && !defined(CONFIG_PREEMPT_RT_FULL) ++static inline void thread_do_softirq(void) { do_softirq(); } ++#ifdef __ARCH_HAS_DO_SOFTIRQ + void do_softirq_own_stack(void); + #else + static inline void do_softirq_own_stack(void) +@@ -451,6 +452,9 @@ static inline void do_softirq_own_stack( + __do_softirq(); + } + #endif ++#else ++extern void thread_do_softirq(void); ++#endif + + extern void open_softirq(int nr, void (*action)(struct softirq_action *)); + extern void softirq_init(void); +@@ -458,6 +462,7 @@ extern void __raise_softirq_irqoff(unsig + + extern void raise_softirq_irqoff(unsigned int nr); + extern void raise_softirq(unsigned int nr); ++extern void softirq_check_pending_idle(void); + + DECLARE_PER_CPU(struct task_struct *, ksoftirqd); + +@@ -615,6 +620,12 @@ void tasklet_hrtimer_cancel(struct taskl + tasklet_kill(&ttimer->tasklet); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++extern void softirq_early_init(void); ++#else ++static inline void softirq_early_init(void) { } ++#endif ++ + /* + * Autoprobing for irqs: + * +--- a/include/linux/preempt_mask.h ++++ b/include/linux/preempt_mask.h +@@ -44,16 +44,26 @@ + #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) + #define NMI_OFFSET (1UL << NMI_SHIFT) + +-#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) ++#ifndef CONFIG_PREEMPT_RT_FULL ++# define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) ++#else ++# define SOFTIRQ_DISABLE_OFFSET (0) ++#endif + + #define PREEMPT_ACTIVE_BITS 1 + #define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS) + #define PREEMPT_ACTIVE (__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT) + + #define hardirq_count() (preempt_count() & HARDIRQ_MASK) +-#define softirq_count() (preempt_count() & SOFTIRQ_MASK) + #define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \ + | NMI_MASK)) ++#ifndef CONFIG_PREEMPT_RT_FULL ++# define softirq_count() (preempt_count() & SOFTIRQ_MASK) ++# define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) ++#else ++# define softirq_count() (0UL) ++extern int in_serving_softirq(void); ++#endif + + /* + * Are we doing bottom half or hardware interrupt processing? +@@ -64,7 +74,6 @@ + #define in_irq() (hardirq_count()) + #define in_softirq() (softirq_count()) + #define in_interrupt() (irq_count()) +-#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) + + /* + * Are we in NMI context? +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -1791,6 +1791,8 @@ struct task_struct { + #endif + #ifdef CONFIG_PREEMPT_RT_BASE + struct rcu_head put_rcu; ++ int softirq_nestcnt; ++ unsigned int softirqs_raised; + #endif + #ifdef CONFIG_DEBUG_ATOMIC_SLEEP + unsigned long task_state_change; +@@ -2041,6 +2043,7 @@ extern void thread_group_cputime_adjuste + /* + * Per process flags + */ ++#define PF_IN_SOFTIRQ 0x00000001 /* Task is serving softirq */ + #define PF_EXITING 0x00000004 /* getting shut down */ + #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ + #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ +--- a/init/main.c ++++ b/init/main.c +@@ -525,6 +525,7 @@ asmlinkage __visible void __init start_k + setup_command_line(command_line); + setup_nr_cpu_ids(); + setup_per_cpu_areas(); ++ softirq_early_init(); + smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ + + build_all_zonelists(NULL, NULL); +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -26,6 +26,7 @@ + #include + #include + #include ++#include + #include + + #define CREATE_TRACE_POINTS +@@ -63,6 +64,98 @@ const char * const softirq_to_name[NR_SO + "TASKLET", "SCHED", "HRTIMER", "RCU" + }; + ++#ifdef CONFIG_NO_HZ_COMMON ++# ifdef CONFIG_PREEMPT_RT_FULL ++ ++struct softirq_runner { ++ struct task_struct *runner[NR_SOFTIRQS]; ++}; ++ ++static DEFINE_PER_CPU(struct softirq_runner, softirq_runners); ++ ++static inline void softirq_set_runner(unsigned int sirq) ++{ ++ struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); ++ ++ sr->runner[sirq] = current; ++} ++ ++static inline void softirq_clr_runner(unsigned int sirq) ++{ ++ struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); ++ ++ sr->runner[sirq] = NULL; ++} ++ ++/* ++ * On preempt-rt a softirq running context might be blocked on a ++ * lock. There might be no other runnable task on this CPU because the ++ * lock owner runs on some other CPU. So we have to go into idle with ++ * the pending bit set. Therefor we need to check this otherwise we ++ * warn about false positives which confuses users and defeats the ++ * whole purpose of this test. ++ * ++ * This code is called with interrupts disabled. ++ */ ++void softirq_check_pending_idle(void) ++{ ++ static int rate_limit; ++ struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); ++ u32 warnpending; ++ int i; ++ ++ if (rate_limit >= 10) ++ return; ++ ++ warnpending = local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK; ++ for (i = 0; i < NR_SOFTIRQS; i++) { ++ struct task_struct *tsk = sr->runner[i]; ++ ++ /* ++ * The wakeup code in rtmutex.c wakes up the task ++ * _before_ it sets pi_blocked_on to NULL under ++ * tsk->pi_lock. So we need to check for both: state ++ * and pi_blocked_on. ++ */ ++ if (tsk) { ++ raw_spin_lock(&tsk->pi_lock); ++ if (tsk->pi_blocked_on || tsk->state == TASK_RUNNING) { ++ /* Clear all bits pending in that task */ ++ warnpending &= ~(tsk->softirqs_raised); ++ warnpending &= ~(1 << i); ++ } ++ raw_spin_unlock(&tsk->pi_lock); ++ } ++ } ++ ++ if (warnpending) { ++ printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", ++ warnpending); ++ rate_limit++; ++ } ++} ++# else ++/* ++ * On !PREEMPT_RT we just printk rate limited: ++ */ ++void softirq_check_pending_idle(void) ++{ ++ static int rate_limit; ++ ++ if (rate_limit < 10 && ++ (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { ++ printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", ++ local_softirq_pending()); ++ rate_limit++; ++ } ++} ++# endif ++ ++#else /* !CONFIG_NO_HZ_COMMON */ ++static inline void softirq_set_runner(unsigned int sirq) { } ++static inline void softirq_clr_runner(unsigned int sirq) { } ++#endif ++ + /* + * we cannot loop indefinitely here to avoid userspace starvation, + * but we also don't want to introduce a worst case 1/HZ latency +@@ -78,6 +171,68 @@ static void wakeup_softirqd(void) + wake_up_process(tsk); + } + ++static void handle_softirq(unsigned int vec_nr) ++{ ++ struct softirq_action *h = softirq_vec + vec_nr; ++ int prev_count; ++ ++ prev_count = preempt_count(); ++ ++ kstat_incr_softirqs_this_cpu(vec_nr); ++ ++ trace_softirq_entry(vec_nr); ++ h->action(h); ++ trace_softirq_exit(vec_nr); ++ if (unlikely(prev_count != preempt_count())) { ++ pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n", ++ vec_nr, softirq_to_name[vec_nr], h->action, ++ prev_count, preempt_count()); ++ preempt_count_set(prev_count); ++ } ++} ++ ++#ifndef CONFIG_PREEMPT_RT_FULL ++static inline int ksoftirqd_softirq_pending(void) ++{ ++ return local_softirq_pending(); ++} ++ ++static void handle_pending_softirqs(u32 pending) ++{ ++ struct softirq_action *h = softirq_vec; ++ int softirq_bit; ++ ++ local_irq_enable(); ++ ++ h = softirq_vec; ++ ++ while ((softirq_bit = ffs(pending))) { ++ unsigned int vec_nr; ++ ++ h += softirq_bit - 1; ++ vec_nr = h - softirq_vec; ++ handle_softirq(vec_nr); ++ ++ h++; ++ pending >>= softirq_bit; ++ } ++ ++ rcu_bh_qs(); ++ local_irq_disable(); ++} ++ ++static void run_ksoftirqd(unsigned int cpu) ++{ ++ local_irq_disable(); ++ if (ksoftirqd_softirq_pending()) { ++ __do_softirq(); ++ local_irq_enable(); ++ cond_resched_rcu_qs(); ++ return; ++ } ++ local_irq_enable(); ++} ++ + /* + * preempt_count and SOFTIRQ_OFFSET usage: + * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving +@@ -233,10 +388,8 @@ asmlinkage __visible void __do_softirq(v + unsigned long end = jiffies + MAX_SOFTIRQ_TIME; + unsigned long old_flags = current->flags; + int max_restart = MAX_SOFTIRQ_RESTART; +- struct softirq_action *h; + bool in_hardirq; + __u32 pending; +- int softirq_bit; + + /* + * Mask out PF_MEMALLOC s current task context is borrowed for the +@@ -255,36 +408,7 @@ asmlinkage __visible void __do_softirq(v + /* Reset the pending bitmask before enabling irqs */ + set_softirq_pending(0); + +- local_irq_enable(); +- +- h = softirq_vec; +- +- while ((softirq_bit = ffs(pending))) { +- unsigned int vec_nr; +- int prev_count; +- +- h += softirq_bit - 1; +- +- vec_nr = h - softirq_vec; +- prev_count = preempt_count(); +- +- kstat_incr_softirqs_this_cpu(vec_nr); +- +- trace_softirq_entry(vec_nr); +- h->action(h); +- trace_softirq_exit(vec_nr); +- if (unlikely(prev_count != preempt_count())) { +- pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n", +- vec_nr, softirq_to_name[vec_nr], h->action, +- prev_count, preempt_count()); +- preempt_count_set(prev_count); +- } +- h++; +- pending >>= softirq_bit; +- } +- +- rcu_bh_qs(); +- local_irq_disable(); ++ handle_pending_softirqs(pending); + + pending = local_softirq_pending(); + if (pending) { +@@ -321,6 +445,276 @@ asmlinkage __visible void do_softirq(voi + } + + /* ++ * This function must run with irqs disabled! ++ */ ++void raise_softirq_irqoff(unsigned int nr) ++{ ++ __raise_softirq_irqoff(nr); ++ ++ /* ++ * If we're in an interrupt or softirq, we're done ++ * (this also catches softirq-disabled code). We will ++ * actually run the softirq once we return from ++ * the irq or softirq. ++ * ++ * Otherwise we wake up ksoftirqd to make sure we ++ * schedule the softirq soon. ++ */ ++ if (!in_interrupt()) ++ wakeup_softirqd(); ++} ++ ++void __raise_softirq_irqoff(unsigned int nr) ++{ ++ trace_softirq_raise(nr); ++ or_softirq_pending(1UL << nr); ++} ++ ++static inline void local_bh_disable_nort(void) { local_bh_disable(); } ++static inline void _local_bh_enable_nort(void) { _local_bh_enable(); } ++static void ksoftirqd_set_sched_params(unsigned int cpu) { } ++static void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) { } ++ ++#else /* !PREEMPT_RT_FULL */ ++ ++/* ++ * On RT we serialize softirq execution with a cpu local lock per softirq ++ */ ++static DEFINE_PER_CPU(struct local_irq_lock [NR_SOFTIRQS], local_softirq_locks); ++ ++void __init softirq_early_init(void) ++{ ++ int i; ++ ++ for (i = 0; i < NR_SOFTIRQS; i++) ++ local_irq_lock_init(local_softirq_locks[i]); ++} ++ ++static void lock_softirq(int which) ++{ ++ local_lock(local_softirq_locks[which]); ++} ++ ++static void unlock_softirq(int which) ++{ ++ local_unlock(local_softirq_locks[which]); ++} ++ ++static void do_single_softirq(int which) ++{ ++ unsigned long old_flags = current->flags; ++ ++ current->flags &= ~PF_MEMALLOC; ++ vtime_account_irq_enter(current); ++ current->flags |= PF_IN_SOFTIRQ; ++ lockdep_softirq_enter(); ++ local_irq_enable(); ++ handle_softirq(which); ++ local_irq_disable(); ++ lockdep_softirq_exit(); ++ current->flags &= ~PF_IN_SOFTIRQ; ++ vtime_account_irq_enter(current); ++ tsk_restore_flags(current, old_flags, PF_MEMALLOC); ++} ++ ++/* ++ * Called with interrupts disabled. Process softirqs which were raised ++ * in current context (or on behalf of ksoftirqd). ++ */ ++static void do_current_softirqs(void) ++{ ++ while (current->softirqs_raised) { ++ int i = __ffs(current->softirqs_raised); ++ unsigned int pending, mask = (1U << i); ++ ++ current->softirqs_raised &= ~mask; ++ local_irq_enable(); ++ ++ /* ++ * If the lock is contended, we boost the owner to ++ * process the softirq or leave the critical section ++ * now. ++ */ ++ lock_softirq(i); ++ local_irq_disable(); ++ softirq_set_runner(i); ++ /* ++ * Check with the local_softirq_pending() bits, ++ * whether we need to process this still or if someone ++ * else took care of it. ++ */ ++ pending = local_softirq_pending(); ++ if (pending & mask) { ++ set_softirq_pending(pending & ~mask); ++ do_single_softirq(i); ++ } ++ softirq_clr_runner(i); ++ unlock_softirq(i); ++ WARN_ON(current->softirq_nestcnt != 1); ++ } ++} ++ ++static void __local_bh_disable(void) ++{ ++ if (++current->softirq_nestcnt == 1) ++ migrate_disable(); ++} ++ ++void local_bh_disable(void) ++{ ++ __local_bh_disable(); ++} ++EXPORT_SYMBOL(local_bh_disable); ++ ++void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) ++{ ++ __local_bh_disable(); ++ if (cnt & PREEMPT_CHECK_OFFSET) ++ preempt_disable(); ++} ++ ++static void __local_bh_enable(void) ++{ ++ if (WARN_ON(current->softirq_nestcnt == 0)) ++ return; ++ ++ local_irq_disable(); ++ if (current->softirq_nestcnt == 1 && current->softirqs_raised) ++ do_current_softirqs(); ++ local_irq_enable(); ++ ++ if (--current->softirq_nestcnt == 0) ++ migrate_enable(); ++} ++ ++void local_bh_enable(void) ++{ ++ __local_bh_enable(); ++} ++EXPORT_SYMBOL(local_bh_enable); ++ ++extern void __local_bh_enable_ip(unsigned long ip, unsigned int cnt) ++{ ++ __local_bh_enable(); ++ if (cnt & PREEMPT_CHECK_OFFSET) ++ preempt_enable(); ++} ++ ++void local_bh_enable_ip(unsigned long ip) ++{ ++ local_bh_enable(); ++} ++EXPORT_SYMBOL(local_bh_enable_ip); ++ ++int in_serving_softirq(void) ++{ ++ return current->flags & PF_IN_SOFTIRQ; ++} ++EXPORT_SYMBOL(in_serving_softirq); ++ ++/* Called with preemption disabled */ ++static void run_ksoftirqd(unsigned int cpu) ++{ ++ local_irq_disable(); ++ current->softirq_nestcnt++; ++ ++ do_current_softirqs(); ++ current->softirq_nestcnt--; ++ rcu_note_context_switch(); ++ local_irq_enable(); ++} ++ ++/* ++ * Called from netif_rx_ni(). Preemption enabled, but migration ++ * disabled. So the cpu can't go away under us. ++ */ ++void thread_do_softirq(void) ++{ ++ if (!in_serving_softirq() && current->softirqs_raised) { ++ current->softirq_nestcnt++; ++ do_current_softirqs(); ++ current->softirq_nestcnt--; ++ } ++} ++ ++static void do_raise_softirq_irqoff(unsigned int nr) ++{ ++ trace_softirq_raise(nr); ++ or_softirq_pending(1UL << nr); ++ ++ /* ++ * If we are not in a hard interrupt and inside a bh disabled ++ * region, we simply raise the flag on current. local_bh_enable() ++ * will make sure that the softirq is executed. Otherwise we ++ * delegate it to ksoftirqd. ++ */ ++ if (!in_irq() && current->softirq_nestcnt) ++ current->softirqs_raised |= (1U << nr); ++ else if (__this_cpu_read(ksoftirqd)) ++ __this_cpu_read(ksoftirqd)->softirqs_raised |= (1U << nr); ++} ++ ++void __raise_softirq_irqoff(unsigned int nr) ++{ ++ do_raise_softirq_irqoff(nr); ++ if (!in_irq() && !current->softirq_nestcnt) ++ wakeup_softirqd(); ++} ++ ++/* ++ * This function must run with irqs disabled! ++ */ ++void raise_softirq_irqoff(unsigned int nr) ++{ ++ do_raise_softirq_irqoff(nr); ++ ++ /* ++ * If we're in an hard interrupt we let irq return code deal ++ * with the wakeup of ksoftirqd. ++ */ ++ if (in_irq()) ++ return; ++ /* ++ * If we are in thread context but outside of a bh disabled ++ * region, we need to wake ksoftirqd as well. ++ * ++ * CHECKME: Some of the places which do that could be wrapped ++ * into local_bh_disable/enable pairs. Though it's unclear ++ * whether this is worth the effort. To find those places just ++ * raise a WARN() if the condition is met. ++ */ ++ if (!current->softirq_nestcnt) ++ wakeup_softirqd(); ++} ++ ++static inline int ksoftirqd_softirq_pending(void) ++{ ++ return current->softirqs_raised; ++} ++ ++static inline void local_bh_disable_nort(void) { } ++static inline void _local_bh_enable_nort(void) { } ++ ++static inline void ksoftirqd_set_sched_params(unsigned int cpu) ++{ ++ struct sched_param param = { .sched_priority = 1 }; ++ ++ sched_setscheduler(current, SCHED_FIFO, ¶m); ++ /* Take over all pending softirqs when starting */ ++ local_irq_disable(); ++ current->softirqs_raised = local_softirq_pending(); ++ local_irq_enable(); ++} ++ ++static inline void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) ++{ ++ struct sched_param param = { .sched_priority = 0 }; ++ ++ sched_setscheduler(current, SCHED_NORMAL, ¶m); ++} ++ ++#endif /* PREEMPT_RT_FULL */ ++/* + * Enter an interrupt context. + */ + void irq_enter(void) +@@ -331,9 +725,9 @@ void irq_enter(void) + * Prevent raise_softirq from needlessly waking up ksoftirqd + * here, as softirq will be serviced on return from interrupt. + */ +- local_bh_disable(); ++ local_bh_disable_nort(); + tick_irq_enter(); +- _local_bh_enable(); ++ _local_bh_enable_nort(); + } + + __irq_enter(); +@@ -341,6 +735,7 @@ void irq_enter(void) + + static inline void invoke_softirq(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + if (!force_irqthreads) { + #ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK + /* +@@ -360,6 +755,15 @@ static inline void invoke_softirq(void) + } else { + wakeup_softirqd(); + } ++#else /* PREEMPT_RT_FULL */ ++ unsigned long flags; ++ ++ local_irq_save(flags); ++ if (__this_cpu_read(ksoftirqd) && ++ __this_cpu_read(ksoftirqd)->softirqs_raised) ++ wakeup_softirqd(); ++ local_irq_restore(flags); ++#endif + } + + static inline void tick_irq_exit(void) +@@ -396,26 +800,6 @@ void irq_exit(void) + trace_hardirq_exit(); /* must be last! */ + } + +-/* +- * This function must run with irqs disabled! +- */ +-inline void raise_softirq_irqoff(unsigned int nr) +-{ +- __raise_softirq_irqoff(nr); +- +- /* +- * If we're in an interrupt or softirq, we're done +- * (this also catches softirq-disabled code). We will +- * actually run the softirq once we return from +- * the irq or softirq. +- * +- * Otherwise we wake up ksoftirqd to make sure we +- * schedule the softirq soon. +- */ +- if (!in_interrupt()) +- wakeup_softirqd(); +-} +- + void raise_softirq(unsigned int nr) + { + unsigned long flags; +@@ -425,12 +809,6 @@ void raise_softirq(unsigned int nr) + local_irq_restore(flags); + } + +-void __raise_softirq_irqoff(unsigned int nr) +-{ +- trace_softirq_raise(nr); +- or_softirq_pending(1UL << nr); +-} +- + void open_softirq(int nr, void (*action)(struct softirq_action *)) + { + softirq_vec[nr].action = action; +@@ -733,23 +1111,7 @@ EXPORT_SYMBOL(tasklet_unlock_wait); + + static int ksoftirqd_should_run(unsigned int cpu) + { +- return local_softirq_pending(); +-} +- +-static void run_ksoftirqd(unsigned int cpu) +-{ +- local_irq_disable(); +- if (local_softirq_pending()) { +- /* +- * We can safely run softirq on inline stack, as we are not deep +- * in the task stack here. +- */ +- __do_softirq(); +- local_irq_enable(); +- cond_resched_rcu_qs(); +- return; +- } +- local_irq_enable(); ++ return ksoftirqd_softirq_pending(); + } + + #ifdef CONFIG_HOTPLUG_CPU +@@ -831,6 +1193,8 @@ static struct notifier_block cpu_nfb = { + + static struct smp_hotplug_thread softirq_threads = { + .store = &ksoftirqd, ++ .setup = ksoftirqd_set_sched_params, ++ .cleanup = ksoftirqd_clr_sched_params, + .thread_should_run = ksoftirqd_should_run, + .thread_fn = run_ksoftirqd, + .thread_comm = "ksoftirqd/%u", +--- a/kernel/time/tick-sched.c ++++ b/kernel/time/tick-sched.c +@@ -764,14 +764,7 @@ static bool can_stop_idle_tick(int cpu, + return false; + + if (unlikely(local_softirq_pending() && cpu_online(cpu))) { +- static int ratelimit; +- +- if (ratelimit < 10 && +- (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { +- pr_warn("NOHZ: local_softirq_pending %02x\n", +- (unsigned int) local_softirq_pending()); +- ratelimit++; +- } ++ softirq_check_pending_idle(); + return false; + } + +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -3437,11 +3437,9 @@ int netif_rx_ni(struct sk_buff *skb) + + trace_netif_rx_ni_entry(skb); + +- preempt_disable(); ++ local_bh_disable(); + err = netif_rx_internal(skb); +- if (local_softirq_pending()) +- do_softirq(); +- preempt_enable(); ++ local_bh_enable(); + + return err; + } diff --git a/debian/patches/features/all/rt/sparc64-use-generic-rwsem-spinlocks-rt.patch b/debian/patches/features/all/rt/sparc64-use-generic-rwsem-spinlocks-rt.patch new file mode 100644 index 000000000..e37b136b3 --- /dev/null +++ b/debian/patches/features/all/rt/sparc64-use-generic-rwsem-spinlocks-rt.patch @@ -0,0 +1,29 @@ +From d6a6675d436897cd1b09e299436df3499abd753e Mon Sep 17 00:00:00 2001 +From: Allen Pais +Date: Fri, 13 Dec 2013 09:44:41 +0530 +Subject: [PATCH 1/3] sparc64: use generic rwsem spinlocks rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Signed-off-by: Allen Pais +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/sparc/Kconfig | 6 ++---- + 1 file changed, 2 insertions(+), 4 deletions(-) + +--- a/arch/sparc/Kconfig ++++ b/arch/sparc/Kconfig +@@ -189,12 +189,10 @@ config NR_CPUS + source kernel/Kconfig.hz + + config RWSEM_GENERIC_SPINLOCK +- bool +- default y if SPARC32 ++ def_bool PREEMPT_RT_FULL + + config RWSEM_XCHGADD_ALGORITHM +- bool +- default y if SPARC64 ++ def_bool !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL + + config GENERIC_HWEIGHT + bool diff --git a/debian/patches/features/all/rt/spinlock-types-separate-raw.patch b/debian/patches/features/all/rt/spinlock-types-separate-raw.patch new file mode 100644 index 000000000..19a61eb85 --- /dev/null +++ b/debian/patches/features/all/rt/spinlock-types-separate-raw.patch @@ -0,0 +1,209 @@ +Subject: spinlock: Split the lock types header +From: Thomas Gleixner +Date: Wed, 29 Jun 2011 19:34:01 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Split raw_spinlock into its own file and the remaining spinlock_t into +its own non-RT header. The non-RT header will be replaced later by sleeping +spinlocks. + +Signed-off-by: Thomas Gleixner +--- + include/linux/rwlock_types.h | 4 + + include/linux/spinlock_types.h | 74 ------------------------------------ + include/linux/spinlock_types_nort.h | 33 ++++++++++++++++ + include/linux/spinlock_types_raw.h | 56 +++++++++++++++++++++++++++ + 4 files changed, 95 insertions(+), 72 deletions(-) + +--- a/include/linux/rwlock_types.h ++++ b/include/linux/rwlock_types.h +@@ -1,6 +1,10 @@ + #ifndef __LINUX_RWLOCK_TYPES_H + #define __LINUX_RWLOCK_TYPES_H + ++#if !defined(__LINUX_SPINLOCK_TYPES_H) ++# error "Do not include directly, include spinlock_types.h" ++#endif ++ + /* + * include/linux/rwlock_types.h - generic rwlock type definitions + * and initializers +--- a/include/linux/spinlock_types.h ++++ b/include/linux/spinlock_types.h +@@ -9,79 +9,9 @@ + * Released under the General Public License (GPL). + */ + +-#if defined(CONFIG_SMP) +-# include +-#else +-# include +-#endif ++#include + +-#include +- +-typedef struct raw_spinlock { +- arch_spinlock_t raw_lock; +-#ifdef CONFIG_GENERIC_LOCKBREAK +- unsigned int break_lock; +-#endif +-#ifdef CONFIG_DEBUG_SPINLOCK +- unsigned int magic, owner_cpu; +- void *owner; +-#endif +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +- struct lockdep_map dep_map; +-#endif +-} raw_spinlock_t; +- +-#define SPINLOCK_MAGIC 0xdead4ead +- +-#define SPINLOCK_OWNER_INIT ((void *)-1L) +- +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +-# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } +-#else +-# define SPIN_DEP_MAP_INIT(lockname) +-#endif +- +-#ifdef CONFIG_DEBUG_SPINLOCK +-# define SPIN_DEBUG_INIT(lockname) \ +- .magic = SPINLOCK_MAGIC, \ +- .owner_cpu = -1, \ +- .owner = SPINLOCK_OWNER_INIT, +-#else +-# define SPIN_DEBUG_INIT(lockname) +-#endif +- +-#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ +- { \ +- .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ +- SPIN_DEBUG_INIT(lockname) \ +- SPIN_DEP_MAP_INIT(lockname) } +- +-#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ +- (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) +- +-#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) +- +-typedef struct spinlock { +- union { +- struct raw_spinlock rlock; +- +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +-# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map)) +- struct { +- u8 __padding[LOCK_PADSIZE]; +- struct lockdep_map dep_map; +- }; +-#endif +- }; +-} spinlock_t; +- +-#define __SPIN_LOCK_INITIALIZER(lockname) \ +- { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } } +- +-#define __SPIN_LOCK_UNLOCKED(lockname) \ +- (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname) +- +-#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) ++#include + + #include + +--- /dev/null ++++ b/include/linux/spinlock_types_nort.h +@@ -0,0 +1,33 @@ ++#ifndef __LINUX_SPINLOCK_TYPES_NORT_H ++#define __LINUX_SPINLOCK_TYPES_NORT_H ++ ++#ifndef __LINUX_SPINLOCK_TYPES_H ++#error "Do not include directly. Include spinlock_types.h instead" ++#endif ++ ++/* ++ * The non RT version maps spinlocks to raw_spinlocks ++ */ ++typedef struct spinlock { ++ union { ++ struct raw_spinlock rlock; ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map)) ++ struct { ++ u8 __padding[LOCK_PADSIZE]; ++ struct lockdep_map dep_map; ++ }; ++#endif ++ }; ++} spinlock_t; ++ ++#define __SPIN_LOCK_INITIALIZER(lockname) \ ++ { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } } ++ ++#define __SPIN_LOCK_UNLOCKED(lockname) \ ++ (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname) ++ ++#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) ++ ++#endif +--- /dev/null ++++ b/include/linux/spinlock_types_raw.h +@@ -0,0 +1,56 @@ ++#ifndef __LINUX_SPINLOCK_TYPES_RAW_H ++#define __LINUX_SPINLOCK_TYPES_RAW_H ++ ++#if defined(CONFIG_SMP) ++# include ++#else ++# include ++#endif ++ ++#include ++ ++typedef struct raw_spinlock { ++ arch_spinlock_t raw_lock; ++#ifdef CONFIG_GENERIC_LOCKBREAK ++ unsigned int break_lock; ++#endif ++#ifdef CONFIG_DEBUG_SPINLOCK ++ unsigned int magic, owner_cpu; ++ void *owner; ++#endif ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++} raw_spinlock_t; ++ ++#define SPINLOCK_MAGIC 0xdead4ead ++ ++#define SPINLOCK_OWNER_INIT ((void *)-1L) ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } ++#else ++# define SPIN_DEP_MAP_INIT(lockname) ++#endif ++ ++#ifdef CONFIG_DEBUG_SPINLOCK ++# define SPIN_DEBUG_INIT(lockname) \ ++ .magic = SPINLOCK_MAGIC, \ ++ .owner_cpu = -1, \ ++ .owner = SPINLOCK_OWNER_INIT, ++#else ++# define SPIN_DEBUG_INIT(lockname) ++#endif ++ ++#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ ++ { \ ++ .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ ++ SPIN_DEBUG_INIT(lockname) \ ++ SPIN_DEP_MAP_INIT(lockname) } ++ ++#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ ++ (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) ++ ++#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) ++ ++#endif diff --git a/debian/patches/features/all/rt/stomp-machine-create-lg_global_trylock_relax-primiti.patch b/debian/patches/features/all/rt/stomp-machine-create-lg_global_trylock_relax-primiti.patch new file mode 100644 index 000000000..a92401dd9 --- /dev/null +++ b/debian/patches/features/all/rt/stomp-machine-create-lg_global_trylock_relax-primiti.patch @@ -0,0 +1,87 @@ +From: Mike Galbraith +Date: Fri, 2 May 2014 13:13:22 +0200 +Subject: stomp-machine: create lg_global_trylock_relax() primitive +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Create lg_global_trylock_relax() for use by stopper thread when it cannot +schedule, to deal with stop_cpus_lock, which is now an lglock. + +Signed-off-by: Mike Galbraith +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/lglock.h | 6 ++++++ + include/linux/spinlock_rt.h | 1 + + kernel/locking/lglock.c | 25 +++++++++++++++++++++++++ + kernel/locking/rtmutex.c | 5 +++++ + 4 files changed, 37 insertions(+) + +--- a/include/linux/lglock.h ++++ b/include/linux/lglock.h +@@ -76,6 +76,12 @@ void lg_local_unlock_cpu(struct lglock * + void lg_global_lock(struct lglock *lg); + void lg_global_unlock(struct lglock *lg); + ++#ifndef CONFIG_PREEMPT_RT_FULL ++#define lg_global_trylock_relax(name) lg_global_lock(name) ++#else ++void lg_global_trylock_relax(struct lglock *lg); ++#endif ++ + #else + /* When !CONFIG_SMP, map lglock to spinlock */ + #define lglock spinlock +--- a/include/linux/spinlock_rt.h ++++ b/include/linux/spinlock_rt.h +@@ -34,6 +34,7 @@ extern int atomic_dec_and_spin_lock(atom + */ + extern void __lockfunc __rt_spin_lock(struct rt_mutex *lock); + extern void __lockfunc __rt_spin_unlock(struct rt_mutex *lock); ++extern int __lockfunc __rt_spin_trylock(struct rt_mutex *lock); + + #define spin_lock(lock) \ + do { \ +--- a/kernel/locking/lglock.c ++++ b/kernel/locking/lglock.c +@@ -105,3 +105,28 @@ void lg_global_unlock(struct lglock *lg) + preempt_enable_nort(); + } + EXPORT_SYMBOL(lg_global_unlock); ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * HACK: If you use this, you get to keep the pieces. ++ * Used in queue_stop_cpus_work() when stop machinery ++ * is called from inactive CPU, so we can't schedule. ++ */ ++# define lg_do_trylock_relax(l) \ ++ do { \ ++ while (!__rt_spin_trylock(l)) \ ++ cpu_relax(); \ ++ } while (0) ++ ++void lg_global_trylock_relax(struct lglock *lg) ++{ ++ int i; ++ ++ lock_acquire_exclusive(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); ++ for_each_possible_cpu(i) { ++ lg_lock_ptr *lock; ++ lock = per_cpu_ptr(lg->lock, i); ++ lg_do_trylock_relax(lock); ++ } ++} ++#endif +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -1133,6 +1133,11 @@ void __lockfunc rt_spin_unlock_wait(spin + } + EXPORT_SYMBOL(rt_spin_unlock_wait); + ++int __lockfunc __rt_spin_trylock(struct rt_mutex *lock) ++{ ++ return rt_mutex_trylock(lock); ++} ++ + int __lockfunc rt_spin_trylock(spinlock_t *lock) + { + int ret = rt_mutex_trylock(&lock->lock); diff --git a/debian/patches/features/all/rt/stomp-machine-use-lg_global_trylock_relax-to-dead-wi.patch b/debian/patches/features/all/rt/stomp-machine-use-lg_global_trylock_relax-to-dead-wi.patch new file mode 100644 index 000000000..21cf2a737 --- /dev/null +++ b/debian/patches/features/all/rt/stomp-machine-use-lg_global_trylock_relax-to-dead-wi.patch @@ -0,0 +1,101 @@ +From: Mike Galbraith +Date: Fri, 2 May 2014 13:13:34 +0200 +Subject: stomp-machine: use lg_global_trylock_relax() to dead with stop_cpus_lock lglock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +If the stop machinery is called from inactive CPU we cannot use +lg_global_lock(), because some other stomp machine invocation might be +in progress and the lock can be contended. We cannot schedule from this +context, so use the lovely new lg_global_trylock_relax() primitive to +do what we used to do via one mutex_trylock()/cpu_relax() loop. We +now do that trylock()/relax() across an entire herd of locks. Joy. + +Signed-off-by: Mike Galbraith +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/stop_machine.c | 24 ++++++++++++++---------- + 1 file changed, 14 insertions(+), 10 deletions(-) + +--- a/kernel/stop_machine.c ++++ b/kernel/stop_machine.c +@@ -266,7 +266,7 @@ int stop_two_cpus(unsigned int cpu1, uns + struct irq_cpu_stop_queue_work_info call_args; + struct multi_stop_data msdata; + +- preempt_disable(); ++ preempt_disable_nort(); + msdata = (struct multi_stop_data){ + .fn = fn, + .data = arg, +@@ -299,7 +299,7 @@ int stop_two_cpus(unsigned int cpu1, uns + * This relies on the stopper workqueues to be FIFO. + */ + if (!cpu_active(cpu1) || !cpu_active(cpu2)) { +- preempt_enable(); ++ preempt_enable_nort(); + return -ENOENT; + } + +@@ -313,7 +313,7 @@ int stop_two_cpus(unsigned int cpu1, uns + &irq_cpu_stop_queue_work, + &call_args, 1); + lg_local_unlock(&stop_cpus_lock); +- preempt_enable(); ++ preempt_enable_nort(); + + wait_for_stop_done(&done); + +@@ -347,7 +347,7 @@ static DEFINE_PER_CPU(struct cpu_stop_wo + + static void queue_stop_cpus_work(const struct cpumask *cpumask, + cpu_stop_fn_t fn, void *arg, +- struct cpu_stop_done *done) ++ struct cpu_stop_done *done, bool inactive) + { + struct cpu_stop_work *work; + unsigned int cpu; +@@ -361,11 +361,13 @@ static void queue_stop_cpus_work(const s + } + + /* +- * Disable preemption while queueing to avoid getting +- * preempted by a stopper which might wait for other stoppers +- * to enter @fn which can lead to deadlock. ++ * Make sure that all work is queued on all cpus before ++ * any of the cpus can execute it. + */ +- lg_global_lock(&stop_cpus_lock); ++ if (!inactive) ++ lg_global_lock(&stop_cpus_lock); ++ else ++ lg_global_trylock_relax(&stop_cpus_lock); + for_each_cpu(cpu, cpumask) + cpu_stop_queue_work(cpu, &per_cpu(stop_cpus_work, cpu)); + lg_global_unlock(&stop_cpus_lock); +@@ -377,7 +379,7 @@ static int __stop_cpus(const struct cpum + struct cpu_stop_done done; + + cpu_stop_init_done(&done, cpumask_weight(cpumask)); +- queue_stop_cpus_work(cpumask, fn, arg, &done); ++ queue_stop_cpus_work(cpumask, fn, arg, &done, false); + wait_for_stop_done(&done); + return done.executed ? done.ret : -ENOENT; + } +@@ -573,6 +575,8 @@ static int __init cpu_stop_init(void) + INIT_LIST_HEAD(&stopper->works); + } + ++ lg_lock_init(&stop_cpus_lock, "stop_cpus_lock"); ++ + BUG_ON(smpboot_register_percpu_thread(&cpu_stop_threads)); + stop_machine_initialized = true; + return 0; +@@ -668,7 +672,7 @@ int stop_machine_from_inactive_cpu(int ( + set_state(&msdata, MULTI_STOP_PREPARE); + cpu_stop_init_done(&done, num_active_cpus()); + queue_stop_cpus_work(cpu_active_mask, multi_cpu_stop, &msdata, +- &done); ++ &done, true); + ret = multi_cpu_stop(&msdata); + + /* Busy wait for completion. */ diff --git a/debian/patches/features/all/rt/stop-machine-raw-lock.patch b/debian/patches/features/all/rt/stop-machine-raw-lock.patch new file mode 100644 index 000000000..0a6538285 --- /dev/null +++ b/debian/patches/features/all/rt/stop-machine-raw-lock.patch @@ -0,0 +1,197 @@ +Subject: stop_machine: Use raw spinlocks +From: Thomas Gleixner +Date: Wed, 29 Jun 2011 11:01:51 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Use raw-locks in stomp_machine() to allow locking in irq-off regions. + +Signed-off-by: Thomas Gleixner +--- + kernel/stop_machine.c | 64 ++++++++++++++++++++++++++++++++++---------------- + 1 file changed, 44 insertions(+), 20 deletions(-) + +--- a/kernel/stop_machine.c ++++ b/kernel/stop_machine.c +@@ -30,12 +30,12 @@ struct cpu_stop_done { + atomic_t nr_todo; /* nr left to execute */ + bool executed; /* actually executed? */ + int ret; /* collected return value */ +- struct completion completion; /* fired if nr_todo reaches 0 */ ++ struct task_struct *waiter; /* woken when nr_todo reaches 0 */ + }; + + /* the actual stopper, one per every possible cpu, enabled on online cpus */ + struct cpu_stopper { +- spinlock_t lock; ++ raw_spinlock_t lock; + bool enabled; /* is this stopper enabled? */ + struct list_head works; /* list of pending works */ + }; +@@ -56,7 +56,7 @@ static void cpu_stop_init_done(struct cp + { + memset(done, 0, sizeof(*done)); + atomic_set(&done->nr_todo, nr_todo); +- init_completion(&done->completion); ++ done->waiter = current; + } + + /* signal completion unless @done is NULL */ +@@ -65,8 +65,10 @@ static void cpu_stop_signal_done(struct + if (done) { + if (executed) + done->executed = true; +- if (atomic_dec_and_test(&done->nr_todo)) +- complete(&done->completion); ++ if (atomic_dec_and_test(&done->nr_todo)) { ++ wake_up_process(done->waiter); ++ done->waiter = NULL; ++ } + } + } + +@@ -78,7 +80,7 @@ static void cpu_stop_queue_work(unsigned + + unsigned long flags; + +- spin_lock_irqsave(&stopper->lock, flags); ++ raw_spin_lock_irqsave(&stopper->lock, flags); + + if (stopper->enabled) { + list_add_tail(&work->list, &stopper->works); +@@ -86,7 +88,23 @@ static void cpu_stop_queue_work(unsigned + } else + cpu_stop_signal_done(work->done, false); + +- spin_unlock_irqrestore(&stopper->lock, flags); ++ raw_spin_unlock_irqrestore(&stopper->lock, flags); ++} ++ ++static void wait_for_stop_done(struct cpu_stop_done *done) ++{ ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ while (atomic_read(&done->nr_todo)) { ++ schedule(); ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ } ++ /* ++ * We need to wait until cpu_stop_signal_done() has cleared ++ * done->waiter. ++ */ ++ while (done->waiter) ++ cpu_relax(); ++ set_current_state(TASK_RUNNING); + } + + /** +@@ -120,7 +138,7 @@ int stop_one_cpu(unsigned int cpu, cpu_s + + cpu_stop_init_done(&done, 1); + cpu_stop_queue_work(cpu, &work); +- wait_for_completion(&done.completion); ++ wait_for_stop_done(&done); + return done.executed ? done.ret : -ENOENT; + } + +@@ -297,7 +315,7 @@ int stop_two_cpus(unsigned int cpu1, uns + lg_local_unlock(&stop_cpus_lock); + preempt_enable(); + +- wait_for_completion(&done.completion); ++ wait_for_stop_done(&done); + + return done.executed ? done.ret : -ENOENT; + } +@@ -360,7 +378,7 @@ static int __stop_cpus(const struct cpum + + cpu_stop_init_done(&done, cpumask_weight(cpumask)); + queue_stop_cpus_work(cpumask, fn, arg, &done); +- wait_for_completion(&done.completion); ++ wait_for_stop_done(&done); + return done.executed ? done.ret : -ENOENT; + } + +@@ -439,9 +457,9 @@ static int cpu_stop_should_run(unsigned + unsigned long flags; + int run; + +- spin_lock_irqsave(&stopper->lock, flags); ++ raw_spin_lock_irqsave(&stopper->lock, flags); + run = !list_empty(&stopper->works); +- spin_unlock_irqrestore(&stopper->lock, flags); ++ raw_spin_unlock_irqrestore(&stopper->lock, flags); + return run; + } + +@@ -453,13 +471,13 @@ static void cpu_stopper_thread(unsigned + + repeat: + work = NULL; +- spin_lock_irq(&stopper->lock); ++ raw_spin_lock_irq(&stopper->lock); + if (!list_empty(&stopper->works)) { + work = list_first_entry(&stopper->works, + struct cpu_stop_work, list); + list_del_init(&work->list); + } +- spin_unlock_irq(&stopper->lock); ++ raw_spin_unlock_irq(&stopper->lock); + + if (work) { + cpu_stop_fn_t fn = work->fn; +@@ -491,7 +509,13 @@ static void cpu_stopper_thread(unsigned + kallsyms_lookup((unsigned long)fn, NULL, NULL, NULL, + ksym_buf), arg); + ++ /* ++ * Make sure that the wakeup and setting done->waiter ++ * to NULL is atomic. ++ */ ++ local_irq_disable(); + cpu_stop_signal_done(done, true); ++ local_irq_enable(); + goto repeat; + } + } +@@ -510,20 +534,20 @@ static void cpu_stop_park(unsigned int c + unsigned long flags; + + /* drain remaining works */ +- spin_lock_irqsave(&stopper->lock, flags); ++ raw_spin_lock_irqsave(&stopper->lock, flags); + list_for_each_entry(work, &stopper->works, list) + cpu_stop_signal_done(work->done, false); + stopper->enabled = false; +- spin_unlock_irqrestore(&stopper->lock, flags); ++ raw_spin_unlock_irqrestore(&stopper->lock, flags); + } + + static void cpu_stop_unpark(unsigned int cpu) + { + struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); + +- spin_lock_irq(&stopper->lock); ++ raw_spin_lock_irq(&stopper->lock); + stopper->enabled = true; +- spin_unlock_irq(&stopper->lock); ++ raw_spin_unlock_irq(&stopper->lock); + } + + static struct smp_hotplug_thread cpu_stop_threads = { +@@ -545,7 +569,7 @@ static int __init cpu_stop_init(void) + for_each_possible_cpu(cpu) { + struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); + +- spin_lock_init(&stopper->lock); ++ raw_spin_lock_init(&stopper->lock); + INIT_LIST_HEAD(&stopper->works); + } + +@@ -648,7 +672,7 @@ int stop_machine_from_inactive_cpu(int ( + ret = multi_cpu_stop(&msdata); + + /* Busy wait for completion. */ +- while (!completion_done(&done.completion)) ++ while (atomic_read(&done.nr_todo)) + cpu_relax(); + + mutex_unlock(&stop_cpus_mutex); diff --git a/debian/patches/features/all/rt/stop_machine-convert-stop_machine_run-to-PREEMPT_RT.patch b/debian/patches/features/all/rt/stop_machine-convert-stop_machine_run-to-PREEMPT_RT.patch new file mode 100644 index 000000000..59d07778d --- /dev/null +++ b/debian/patches/features/all/rt/stop_machine-convert-stop_machine_run-to-PREEMPT_RT.patch @@ -0,0 +1,35 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:30:27 -0500 +Subject: stop_machine: convert stop_machine_run() to PREEMPT_RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Instead of playing with non-preemption, introduce explicit +startup serialization. This is more robust and cleaner as +well. + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner +[bigeasy: XXX: stopper_lock -> stop_cpus_lock] +--- + kernel/stop_machine.c | 10 ++++++++++ + 1 file changed, 10 insertions(+) + +--- a/kernel/stop_machine.c ++++ b/kernel/stop_machine.c +@@ -467,6 +467,16 @@ static void cpu_stopper_thread(unsigned + struct cpu_stop_done *done = work->done; + char ksym_buf[KSYM_NAME_LEN] __maybe_unused; + ++ /* ++ * Wait until the stopper finished scheduling on all ++ * cpus ++ */ ++ lg_global_lock(&stop_cpus_lock); ++ /* ++ * Let other cpu threads continue as well ++ */ ++ lg_global_unlock(&stop_cpus_lock); ++ + /* cpu stop callbacks are not allowed to sleep */ + preempt_disable(); + diff --git a/debian/patches/features/all/rt/sunrpc-make-svc_xprt_do_enqueue-use-get_cpu_light.patch b/debian/patches/features/all/rt/sunrpc-make-svc_xprt_do_enqueue-use-get_cpu_light.patch new file mode 100644 index 000000000..f933b957b --- /dev/null +++ b/debian/patches/features/all/rt/sunrpc-make-svc_xprt_do_enqueue-use-get_cpu_light.patch @@ -0,0 +1,63 @@ +From: Mike Galbraith +Date: Wed, 18 Feb 2015 16:05:28 +0100 +Subject: sunrpc: Make svc_xprt_do_enqueue() use get_cpu_light() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +|BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:915 +|in_atomic(): 1, irqs_disabled(): 0, pid: 3194, name: rpc.nfsd +|Preemption disabled at:[] svc_xprt_received+0x4b/0xc0 [sunrpc] +|CPU: 6 PID: 3194 Comm: rpc.nfsd Not tainted 3.18.7-rt1 #9 +|Hardware name: MEDION MS-7848/MS-7848, BIOS M7848W08.404 11/06/2014 +| ffff880409630000 ffff8800d9a33c78 ffffffff815bdeb5 0000000000000002 +| 0000000000000000 ffff8800d9a33c98 ffffffff81073c86 ffff880408dd6008 +| ffff880408dd6000 ffff8800d9a33cb8 ffffffff815c3d84 ffff88040b3ac000 +|Call Trace: +| [] dump_stack+0x4f/0x9e +| [] __might_sleep+0xe6/0x150 +| [] rt_spin_lock+0x24/0x50 +| [] svc_xprt_do_enqueue+0x80/0x230 [sunrpc] +| [] svc_xprt_received+0x4b/0xc0 [sunrpc] +| [] svc_add_new_perm_xprt+0x6d/0x80 [sunrpc] +| [] svc_addsock+0x143/0x200 [sunrpc] +| [] write_ports+0x28c/0x340 [nfsd] +| [] nfsctl_transaction_write+0x4c/0x80 [nfsd] +| [] vfs_write+0xb3/0x1d0 +| [] SyS_write+0x49/0xb0 +| [] system_call_fastpath+0x16/0x1b + + +Signed-off-by: Mike Galbraith +Signed-off-by: Sebastian Andrzej Siewior +--- + net/sunrpc/svc_xprt.c | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +--- a/net/sunrpc/svc_xprt.c ++++ b/net/sunrpc/svc_xprt.c +@@ -341,7 +341,7 @@ static void svc_xprt_do_enqueue(struct s + goto out; + } + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + pool = svc_pool_for_cpu(xprt->xpt_server, cpu); + + atomic_long_inc(&pool->sp_stats.packets); +@@ -377,7 +377,7 @@ static void svc_xprt_do_enqueue(struct s + + atomic_long_inc(&pool->sp_stats.threads_woken); + wake_up_process(rqstp->rq_task); +- put_cpu(); ++ put_cpu_light(); + goto out; + } + rcu_read_unlock(); +@@ -398,7 +398,7 @@ static void svc_xprt_do_enqueue(struct s + goto redo_search; + } + rqstp = NULL; +- put_cpu(); ++ put_cpu_light(); + out: + trace_svc_xprt_do_enqueue(xprt, rqstp); + } diff --git a/debian/patches/features/all/rt/suspend-prevernt-might-sleep-splats.patch b/debian/patches/features/all/rt/suspend-prevernt-might-sleep-splats.patch new file mode 100644 index 000000000..b70ec0a33 --- /dev/null +++ b/debian/patches/features/all/rt/suspend-prevernt-might-sleep-splats.patch @@ -0,0 +1,107 @@ +From: Thomas Gleixner +Date: Thu, 15 Jul 2010 10:29:00 +0200 +Subject: suspend: Prevent might sleep splats +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +timekeeping suspend/resume calls read_persistant_clock() which takes +rtc_lock. That results in might sleep warnings because at that point +we run with interrupts disabled. + +We cannot convert rtc_lock to a raw spinlock as that would trigger +other might sleep warnings. + +As a temporary workaround we disable the might sleep warnings by +setting system_state to SYSTEM_SUSPEND before calling sysdev_suspend() +and restoring it to SYSTEM_RUNNING afer sysdev_resume(). + +Needs to be revisited. + +Signed-off-by: Thomas Gleixner + +--- + include/linux/kernel.h | 1 + + kernel/power/hibernate.c | 7 +++++++ + kernel/power/suspend.c | 4 ++++ + 3 files changed, 12 insertions(+) + +--- a/include/linux/kernel.h ++++ b/include/linux/kernel.h +@@ -467,6 +467,7 @@ extern enum system_states { + SYSTEM_HALT, + SYSTEM_POWER_OFF, + SYSTEM_RESTART, ++ SYSTEM_SUSPEND, + } system_state; + + #define TAINT_PROPRIETARY_MODULE 0 +--- a/kernel/power/hibernate.c ++++ b/kernel/power/hibernate.c +@@ -285,6 +285,8 @@ static int create_image(int platform_mod + + local_irq_disable(); + ++ system_state = SYSTEM_SUSPEND; ++ + error = syscore_suspend(); + if (error) { + printk(KERN_ERR "PM: Some system devices failed to power down, " +@@ -314,6 +316,7 @@ static int create_image(int platform_mod + syscore_resume(); + + Enable_irqs: ++ system_state = SYSTEM_RUNNING; + local_irq_enable(); + + Enable_cpus: +@@ -437,6 +440,7 @@ static int resume_target_kernel(bool pla + goto Enable_cpus; + + local_irq_disable(); ++ system_state = SYSTEM_SUSPEND; + + error = syscore_suspend(); + if (error) +@@ -470,6 +474,7 @@ static int resume_target_kernel(bool pla + syscore_resume(); + + Enable_irqs: ++ system_state = SYSTEM_RUNNING; + local_irq_enable(); + + Enable_cpus: +@@ -555,6 +560,7 @@ int hibernation_platform_enter(void) + goto Platform_finish; + + local_irq_disable(); ++ system_state = SYSTEM_SUSPEND; + syscore_suspend(); + if (pm_wakeup_pending()) { + error = -EAGAIN; +@@ -567,6 +573,7 @@ int hibernation_platform_enter(void) + + Power_up: + syscore_resume(); ++ system_state = SYSTEM_RUNNING; + local_irq_enable(); + enable_nonboot_cpus(); + +--- a/kernel/power/suspend.c ++++ b/kernel/power/suspend.c +@@ -356,6 +356,8 @@ static int suspend_enter(suspend_state_t + arch_suspend_disable_irqs(); + BUG_ON(!irqs_disabled()); + ++ system_state = SYSTEM_SUSPEND; ++ + error = syscore_suspend(); + if (!error) { + *wakeup = pm_wakeup_pending(); +@@ -370,6 +372,8 @@ static int suspend_enter(suspend_state_t + syscore_resume(); + } + ++ system_state = SYSTEM_RUNNING; ++ + arch_suspend_enable_irqs(); + BUG_ON(irqs_disabled()); + diff --git a/debian/patches/features/all/rt/sysfs-realtime-entry.patch b/debian/patches/features/all/rt/sysfs-realtime-entry.patch new file mode 100644 index 000000000..900ecf068 --- /dev/null +++ b/debian/patches/features/all/rt/sysfs-realtime-entry.patch @@ -0,0 +1,48 @@ +Subject: sysfs: Add /sys/kernel/realtime entry +From: Clark Williams +Date: Sat Jul 30 21:55:53 2011 -0500 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Add a /sys/kernel entry to indicate that the kernel is a +realtime kernel. + +Clark says that he needs this for udev rules, udev needs to evaluate +if its a PREEMPT_RT kernel a few thousand times and parsing uname +output is too slow or so. + +Are there better solutions? Should it exist and return 0 on !-rt? + +Signed-off-by: Clark Williams +Signed-off-by: Peter Zijlstra +--- + kernel/ksysfs.c | 12 ++++++++++++ + 1 file changed, 12 insertions(+) + +--- a/kernel/ksysfs.c ++++ b/kernel/ksysfs.c +@@ -136,6 +136,15 @@ KERNEL_ATTR_RO(vmcoreinfo); + + #endif /* CONFIG_KEXEC */ + ++#if defined(CONFIG_PREEMPT_RT_FULL) ++static ssize_t realtime_show(struct kobject *kobj, ++ struct kobj_attribute *attr, char *buf) ++{ ++ return sprintf(buf, "%d\n", 1); ++} ++KERNEL_ATTR_RO(realtime); ++#endif ++ + /* whether file capabilities are enabled */ + static ssize_t fscaps_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +@@ -203,6 +212,9 @@ static struct attribute * kernel_attrs[] + &vmcoreinfo_attr.attr, + #endif + &rcu_expedited_attr.attr, ++#ifdef CONFIG_PREEMPT_RT_FULL ++ &realtime_attr.attr, ++#endif + NULL + }; + diff --git a/debian/patches/features/all/rt/tasklet-rt-prevent-tasklets-from-going-into-infinite-spin-in-rt.patch b/debian/patches/features/all/rt/tasklet-rt-prevent-tasklets-from-going-into-infinite-spin-in-rt.patch new file mode 100644 index 000000000..1471b9e30 --- /dev/null +++ b/debian/patches/features/all/rt/tasklet-rt-prevent-tasklets-from-going-into-infinite-spin-in-rt.patch @@ -0,0 +1,392 @@ +Subject: tasklet: Prevent tasklets from going into infinite spin in RT +From: Ingo Molnar +Date: Tue Nov 29 20:18:22 2011 -0500 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +When CONFIG_PREEMPT_RT_FULL is enabled, tasklets run as threads, +and spinlocks turn are mutexes. But this can cause issues with +tasks disabling tasklets. A tasklet runs under ksoftirqd, and +if a tasklets are disabled with tasklet_disable(), the tasklet +count is increased. When a tasklet runs, it checks this counter +and if it is set, it adds itself back on the softirq queue and +returns. + +The problem arises in RT because ksoftirq will see that a softirq +is ready to run (the tasklet softirq just re-armed itself), and will +not sleep, but instead run the softirqs again. The tasklet softirq +will still see that the count is non-zero and will not execute +the tasklet and requeue itself on the softirq again, which will +cause ksoftirqd to run it again and again and again. + +It gets worse because ksoftirqd runs as a real-time thread. +If it preempted the task that disabled tasklets, and that task +has migration disabled, or can't run for other reasons, the tasklet +softirq will never run because the count will never be zero, and +ksoftirqd will go into an infinite loop. As an RT task, it this +becomes a big problem. + +This is a hack solution to have tasklet_disable stop tasklets, and +when a tasklet runs, instead of requeueing the tasklet softirqd +it delays it. When tasklet_enable() is called, and tasklets are +waiting, then the tasklet_enable() will kick the tasklets to continue. +This prevents the lock up from ksoftirq going into an infinite loop. + +[ rostedt@goodmis.org: ported to 3.0-rt ] + +Signed-off-by: Ingo Molnar +Signed-off-by: Steven Rostedt +Signed-off-by: Thomas Gleixner + +--- + include/linux/interrupt.h | 33 ++++--- + kernel/softirq.c | 201 ++++++++++++++++++++++++++++++++-------------- + 2 files changed, 162 insertions(+), 72 deletions(-) + +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -479,8 +479,9 @@ static inline struct task_struct *this_c + to be executed on some cpu at least once after this. + * If the tasklet is already scheduled, but its execution is still not + started, it will be executed only once. +- * If this tasklet is already running on another CPU (or schedule is called +- from tasklet itself), it is rescheduled for later. ++ * If this tasklet is already running on another CPU, it is rescheduled ++ for later. ++ * Schedule must not be called from the tasklet itself (a lockup occurs) + * Tasklet is strictly serialized wrt itself, but not + wrt another tasklets. If client needs some intertask synchronization, + he makes it with spinlocks. +@@ -505,27 +506,36 @@ struct tasklet_struct name = { NULL, 0, + enum + { + TASKLET_STATE_SCHED, /* Tasklet is scheduled for execution */ +- TASKLET_STATE_RUN /* Tasklet is running (SMP only) */ ++ TASKLET_STATE_RUN, /* Tasklet is running (SMP only) */ ++ TASKLET_STATE_PENDING /* Tasklet is pending */ + }; + +-#ifdef CONFIG_SMP ++#define TASKLET_STATEF_SCHED (1 << TASKLET_STATE_SCHED) ++#define TASKLET_STATEF_RUN (1 << TASKLET_STATE_RUN) ++#define TASKLET_STATEF_PENDING (1 << TASKLET_STATE_PENDING) ++ ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) + static inline int tasklet_trylock(struct tasklet_struct *t) + { + return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state); + } + ++static inline int tasklet_tryunlock(struct tasklet_struct *t) ++{ ++ return cmpxchg(&t->state, TASKLET_STATEF_RUN, 0) == TASKLET_STATEF_RUN; ++} ++ + static inline void tasklet_unlock(struct tasklet_struct *t) + { + smp_mb__before_atomic(); + clear_bit(TASKLET_STATE_RUN, &(t)->state); + } + +-static inline void tasklet_unlock_wait(struct tasklet_struct *t) +-{ +- while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { barrier(); } +-} ++extern void tasklet_unlock_wait(struct tasklet_struct *t); ++ + #else + #define tasklet_trylock(t) 1 ++#define tasklet_tryunlock(t) 1 + #define tasklet_unlock_wait(t) do { } while (0) + #define tasklet_unlock(t) do { } while (0) + #endif +@@ -574,12 +584,7 @@ static inline void tasklet_disable(struc + smp_mb(); + } + +-static inline void tasklet_enable(struct tasklet_struct *t) +-{ +- smp_mb__before_atomic(); +- atomic_dec(&t->count); +-} +- ++extern void tasklet_enable(struct tasklet_struct *t); + extern void tasklet_kill(struct tasklet_struct *t); + extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu); + extern void tasklet_init(struct tasklet_struct *t, +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -21,6 +21,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -446,15 +447,45 @@ struct tasklet_head { + static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec); + static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec); + ++static void inline ++__tasklet_common_schedule(struct tasklet_struct *t, struct tasklet_head *head, unsigned int nr) ++{ ++ if (tasklet_trylock(t)) { ++again: ++ /* We may have been preempted before tasklet_trylock ++ * and __tasklet_action may have already run. ++ * So double check the sched bit while the takslet ++ * is locked before adding it to the list. ++ */ ++ if (test_bit(TASKLET_STATE_SCHED, &t->state)) { ++ t->next = NULL; ++ *head->tail = t; ++ head->tail = &(t->next); ++ raise_softirq_irqoff(nr); ++ tasklet_unlock(t); ++ } else { ++ /* This is subtle. If we hit the corner case above ++ * It is possible that we get preempted right here, ++ * and another task has successfully called ++ * tasklet_schedule(), then this function, and ++ * failed on the trylock. Thus we must be sure ++ * before releasing the tasklet lock, that the ++ * SCHED_BIT is clear. Otherwise the tasklet ++ * may get its SCHED_BIT set, but not added to the ++ * list ++ */ ++ if (!tasklet_tryunlock(t)) ++ goto again; ++ } ++ } ++} ++ + void __tasklet_schedule(struct tasklet_struct *t) + { + unsigned long flags; + + local_irq_save(flags); +- t->next = NULL; +- *__this_cpu_read(tasklet_vec.tail) = t; +- __this_cpu_write(tasklet_vec.tail, &(t->next)); +- raise_softirq_irqoff(TASKLET_SOFTIRQ); ++ __tasklet_common_schedule(t, this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ); + local_irq_restore(flags); + } + EXPORT_SYMBOL(__tasklet_schedule); +@@ -464,10 +495,7 @@ void __tasklet_hi_schedule(struct taskle + unsigned long flags; + + local_irq_save(flags); +- t->next = NULL; +- *__this_cpu_read(tasklet_hi_vec.tail) = t; +- __this_cpu_write(tasklet_hi_vec.tail, &(t->next)); +- raise_softirq_irqoff(HI_SOFTIRQ); ++ __tasklet_common_schedule(t, this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ); + local_irq_restore(flags); + } + EXPORT_SYMBOL(__tasklet_hi_schedule); +@@ -476,82 +504,122 @@ void __tasklet_hi_schedule_first(struct + { + BUG_ON(!irqs_disabled()); + +- t->next = __this_cpu_read(tasklet_hi_vec.head); +- __this_cpu_write(tasklet_hi_vec.head, t); +- __raise_softirq_irqoff(HI_SOFTIRQ); ++ __tasklet_hi_schedule(t); + } + EXPORT_SYMBOL(__tasklet_hi_schedule_first); + +-static void tasklet_action(struct softirq_action *a) ++void tasklet_enable(struct tasklet_struct *t) + { +- struct tasklet_struct *list; ++ if (!atomic_dec_and_test(&t->count)) ++ return; ++ if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state)) ++ tasklet_schedule(t); ++} ++EXPORT_SYMBOL(tasklet_enable); + +- local_irq_disable(); +- list = __this_cpu_read(tasklet_vec.head); +- __this_cpu_write(tasklet_vec.head, NULL); +- __this_cpu_write(tasklet_vec.tail, this_cpu_ptr(&tasklet_vec.head)); +- local_irq_enable(); ++static void __tasklet_action(struct softirq_action *a, ++ struct tasklet_struct *list) ++{ ++ int loops = 1000000; + + while (list) { + struct tasklet_struct *t = list; + + list = list->next; + +- if (tasklet_trylock(t)) { +- if (!atomic_read(&t->count)) { +- if (!test_and_clear_bit(TASKLET_STATE_SCHED, +- &t->state)) +- BUG(); +- t->func(t->data); +- tasklet_unlock(t); +- continue; +- } +- tasklet_unlock(t); ++ /* ++ * Should always succeed - after a tasklist got on the ++ * list (after getting the SCHED bit set from 0 to 1), ++ * nothing but the tasklet softirq it got queued to can ++ * lock it: ++ */ ++ if (!tasklet_trylock(t)) { ++ WARN_ON(1); ++ continue; + } + +- local_irq_disable(); + t->next = NULL; +- *__this_cpu_read(tasklet_vec.tail) = t; +- __this_cpu_write(tasklet_vec.tail, &(t->next)); +- __raise_softirq_irqoff(TASKLET_SOFTIRQ); +- local_irq_enable(); ++ ++ /* ++ * If we cannot handle the tasklet because it's disabled, ++ * mark it as pending. tasklet_enable() will later ++ * re-schedule the tasklet. ++ */ ++ if (unlikely(atomic_read(&t->count))) { ++out_disabled: ++ /* implicit unlock: */ ++ wmb(); ++ t->state = TASKLET_STATEF_PENDING; ++ continue; ++ } ++ ++ /* ++ * After this point on the tasklet might be rescheduled ++ * on another CPU, but it can only be added to another ++ * CPU's tasklet list if we unlock the tasklet (which we ++ * dont do yet). ++ */ ++ if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) ++ WARN_ON(1); ++ ++again: ++ t->func(t->data); ++ ++ /* ++ * Try to unlock the tasklet. We must use cmpxchg, because ++ * another CPU might have scheduled or disabled the tasklet. ++ * We only allow the STATE_RUN -> 0 transition here. ++ */ ++ while (!tasklet_tryunlock(t)) { ++ /* ++ * If it got disabled meanwhile, bail out: ++ */ ++ if (atomic_read(&t->count)) ++ goto out_disabled; ++ /* ++ * If it got scheduled meanwhile, re-execute ++ * the tasklet function: ++ */ ++ if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) ++ goto again; ++ if (!--loops) { ++ printk("hm, tasklet state: %08lx\n", t->state); ++ WARN_ON(1); ++ tasklet_unlock(t); ++ break; ++ } ++ } + } + } + ++static void tasklet_action(struct softirq_action *a) ++{ ++ struct tasklet_struct *list; ++ ++ local_irq_disable(); ++ ++ list = __this_cpu_read(tasklet_vec.head); ++ __this_cpu_write(tasklet_vec.head, NULL); ++ __this_cpu_write(tasklet_vec.tail, this_cpu_ptr(&tasklet_vec.head)); ++ ++ local_irq_enable(); ++ ++ __tasklet_action(a, list); ++} ++ + static void tasklet_hi_action(struct softirq_action *a) + { + struct tasklet_struct *list; + + local_irq_disable(); ++ + list = __this_cpu_read(tasklet_hi_vec.head); + __this_cpu_write(tasklet_hi_vec.head, NULL); + __this_cpu_write(tasklet_hi_vec.tail, this_cpu_ptr(&tasklet_hi_vec.head)); +- local_irq_enable(); +- +- while (list) { +- struct tasklet_struct *t = list; + +- list = list->next; +- +- if (tasklet_trylock(t)) { +- if (!atomic_read(&t->count)) { +- if (!test_and_clear_bit(TASKLET_STATE_SCHED, +- &t->state)) +- BUG(); +- t->func(t->data); +- tasklet_unlock(t); +- continue; +- } +- tasklet_unlock(t); +- } ++ local_irq_enable(); + +- local_irq_disable(); +- t->next = NULL; +- *__this_cpu_read(tasklet_hi_vec.tail) = t; +- __this_cpu_write(tasklet_hi_vec.tail, &(t->next)); +- __raise_softirq_irqoff(HI_SOFTIRQ); +- local_irq_enable(); +- } ++ __tasklet_action(a, list); + } + + void tasklet_init(struct tasklet_struct *t, +@@ -572,7 +640,7 @@ void tasklet_kill(struct tasklet_struct + + while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) { + do { +- yield(); ++ msleep(1); + } while (test_bit(TASKLET_STATE_SCHED, &t->state)); + } + tasklet_unlock_wait(t); +@@ -646,6 +714,23 @@ void __init softirq_init(void) + open_softirq(HI_SOFTIRQ, tasklet_hi_action); + } + ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) ++void tasklet_unlock_wait(struct tasklet_struct *t) ++{ ++ while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { ++ /* ++ * Hack for now to avoid this busy-loop: ++ */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ msleep(1); ++#else ++ barrier(); ++#endif ++ } ++} ++EXPORT_SYMBOL(tasklet_unlock_wait); ++#endif ++ + static int ksoftirqd_should_run(unsigned int cpu) + { + return local_softirq_pending(); diff --git a/debian/patches/features/all/rt/tasklist-lock-fix-section-conflict.patch b/debian/patches/features/all/rt/tasklist-lock-fix-section-conflict.patch new file mode 100644 index 000000000..ef79934a0 --- /dev/null +++ b/debian/patches/features/all/rt/tasklist-lock-fix-section-conflict.patch @@ -0,0 +1,56 @@ +Subject: rwlocks: Fix section mismatch +From: John Kacur +Date: Mon, 19 Sep 2011 11:09:27 +0200 (CEST) +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +This fixes the following build error for the preempt-rt kernel. + +make kernel/fork.o + CC kernel/fork.o +kernel/fork.c:90: error: section of tasklist_lock conflicts with previous declaration +make[2]: *** [kernel/fork.o] Error 1 +make[1]: *** [kernel/fork.o] Error 2 + +The rt kernel cache aligns the RWLOCK in DEFINE_RWLOCK by default. +The non-rt kernels explicitly cache align only the tasklist_lock in +kernel/fork.c +That can create a build conflict. This fixes the build problem by making the +non-rt kernels cache align RWLOCKs by default. The side effect is that +the other RWLOCKs are also cache aligned for non-rt. + +This is a short term solution for rt only. +The longer term solution would be to push the cache aligned DEFINE_RWLOCK +to mainline. If there are objections, then we could create a +DEFINE_RWLOCK_CACHE_ALIGNED or something of that nature. + +Signed-off-by: John Kacur +Cc: Peter Zijlstra +Link: http://lkml.kernel.org/r/alpine.LFD.2.00.1109191104010.23118@localhost6.localdomain6 +Signed-off-by: Thomas Gleixner +--- + include/linux/rwlock_types.h | 3 ++- + kernel/fork.c | 2 +- + 2 files changed, 3 insertions(+), 2 deletions(-) + +--- a/include/linux/rwlock_types.h ++++ b/include/linux/rwlock_types.h +@@ -47,6 +47,7 @@ typedef struct { + RW_DEP_MAP_INIT(lockname) } + #endif + +-#define DEFINE_RWLOCK(x) rwlock_t x = __RW_LOCK_UNLOCKED(x) ++#define DEFINE_RWLOCK(name) \ ++ rwlock_t name __cacheline_aligned_in_smp = __RW_LOCK_UNLOCKED(name) + + #endif /* __LINUX_RWLOCK_TYPES_H */ +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -108,7 +108,7 @@ int max_threads; /* tunable limit on nr + + DEFINE_PER_CPU(unsigned long, process_counts) = 0; + +-__cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ ++DEFINE_RWLOCK(tasklist_lock); /* outer */ + + #ifdef CONFIG_PROVE_RCU + int lockdep_tasklist_lock_is_held(void) diff --git a/debian/patches/features/all/rt/thermal-Defer-thermal-wakups-to-threads.patch b/debian/patches/features/all/rt/thermal-Defer-thermal-wakups-to-threads.patch new file mode 100644 index 000000000..9799dd105 --- /dev/null +++ b/debian/patches/features/all/rt/thermal-Defer-thermal-wakups-to-threads.patch @@ -0,0 +1,133 @@ +From: Daniel Wagner +Date: Tue, 17 Feb 2015 09:37:44 +0100 +Subject: thermal: Defer thermal wakups to threads +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +On RT the spin lock in pkg_temp_thermal_platfrom_thermal_notify will +call schedule while we run in irq context. + +[] dump_stack+0x4e/0x8f +[] __schedule_bug+0xa6/0xb4 +[] __schedule+0x5b4/0x700 +[] schedule+0x2a/0x90 +[] rt_spin_lock_slowlock+0xe5/0x2d0 +[] rt_spin_lock+0x25/0x30 +[] pkg_temp_thermal_platform_thermal_notify+0x45/0x134 [x86_pkg_temp_thermal] +[] ? therm_throt_process+0x1b/0x160 +[] intel_thermal_interrupt+0x211/0x250 +[] smp_thermal_interrupt+0x21/0x40 +[] thermal_interrupt+0x6d/0x80 + +Let's defer the work to a kthread. + +Signed-off-by: Daniel Wagner +[bigeasy: reoder init/denit position. TODO: flush swork on exit] +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/thermal/x86_pkg_temp_thermal.c | 50 +++++++++++++++++++++++++++++++-- + 1 file changed, 47 insertions(+), 3 deletions(-) + +--- a/drivers/thermal/x86_pkg_temp_thermal.c ++++ b/drivers/thermal/x86_pkg_temp_thermal.c +@@ -29,6 +29,7 @@ + #include + #include + #include ++#include + #include + #include + +@@ -352,7 +353,7 @@ static void pkg_temp_thermal_threshold_w + } + } + +-static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val) ++static void platform_thermal_notify_work(struct swork_event *event) + { + unsigned long flags; + int cpu = smp_processor_id(); +@@ -369,7 +370,7 @@ static int pkg_temp_thermal_platform_the + pkg_work_scheduled[phy_id]) { + disable_pkg_thres_interrupt(); + spin_unlock_irqrestore(&pkg_work_lock, flags); +- return -EINVAL; ++ return; + } + pkg_work_scheduled[phy_id] = 1; + spin_unlock_irqrestore(&pkg_work_lock, flags); +@@ -378,9 +379,48 @@ static int pkg_temp_thermal_platform_the + schedule_delayed_work_on(cpu, + &per_cpu(pkg_temp_thermal_threshold_work, cpu), + msecs_to_jiffies(notify_delay_ms)); ++} ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++static struct swork_event notify_work; ++ ++static int thermal_notify_work_init(void) ++{ ++ int err; ++ ++ err = swork_get(); ++ if (err) ++ return err; ++ ++ INIT_SWORK(¬ify_work, platform_thermal_notify_work); + return 0; + } + ++static void thermal_notify_work_cleanup(void) ++{ ++ swork_put(); ++} ++ ++static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val) ++{ ++ swork_queue(¬ify_work); ++ return 0; ++} ++ ++#else /* !CONFIG_PREEMPT_RT_FULL */ ++ ++static int thermal_notify_work_init(void) { return 0; } ++ ++static void thermal_notify_work_cleanup(void) { } ++ ++static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val) ++{ ++ platform_thermal_notify_work(NULL); ++ ++ return 0; ++} ++#endif /* CONFIG_PREEMPT_RT_FULL */ ++ + static int find_siblings_cpu(int cpu) + { + int i; +@@ -584,6 +624,9 @@ static int __init pkg_temp_thermal_init( + if (!x86_match_cpu(pkg_temp_thermal_ids)) + return -ENODEV; + ++ if (!thermal_notify_work_init()) ++ return -ENODEV; ++ + spin_lock_init(&pkg_work_lock); + platform_thermal_package_notify = + pkg_temp_thermal_platform_thermal_notify; +@@ -608,7 +651,7 @@ static int __init pkg_temp_thermal_init( + kfree(pkg_work_scheduled); + platform_thermal_package_notify = NULL; + platform_thermal_package_rate_control = NULL; +- ++ thermal_notify_work_cleanup(); + return -ENODEV; + } + +@@ -633,6 +676,7 @@ static void __exit pkg_temp_thermal_exit + mutex_unlock(&phy_dev_list_mutex); + platform_thermal_package_notify = NULL; + platform_thermal_package_rate_control = NULL; ++ thermal_notify_work_cleanup(); + for_each_online_cpu(i) + cancel_delayed_work_sync( + &per_cpu(pkg_temp_thermal_threshold_work, i)); diff --git a/debian/patches/features/all/rt/timekeeping-split-jiffies-lock.patch b/debian/patches/features/all/rt/timekeeping-split-jiffies-lock.patch new file mode 100644 index 000000000..4780f1d88 --- /dev/null +++ b/debian/patches/features/all/rt/timekeeping-split-jiffies-lock.patch @@ -0,0 +1,157 @@ +Subject: timekeeping: Split jiffies seqlock +From: Thomas Gleixner +Date: Thu, 14 Feb 2013 22:36:59 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Replace jiffies_lock seqlock with a simple seqcounter and a rawlock so +it can be taken in atomic context on RT. + +Signed-off-by: Thomas Gleixner +--- + kernel/time/jiffies.c | 7 ++++--- + kernel/time/tick-common.c | 10 ++++++---- + kernel/time/tick-sched.c | 19 ++++++++++++------- + kernel/time/timekeeping.c | 6 ++++-- + kernel/time/timekeeping.h | 3 ++- + 5 files changed, 28 insertions(+), 17 deletions(-) + +--- a/kernel/time/jiffies.c ++++ b/kernel/time/jiffies.c +@@ -74,7 +74,8 @@ static struct clocksource clocksource_ji + .max_cycles = 10, + }; + +-__cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock); ++__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(jiffies_lock); ++__cacheline_aligned_in_smp seqcount_t jiffies_seq; + + #if (BITS_PER_LONG < 64) + u64 get_jiffies_64(void) +@@ -83,9 +84,9 @@ u64 get_jiffies_64(void) + u64 ret; + + do { +- seq = read_seqbegin(&jiffies_lock); ++ seq = read_seqcount_begin(&jiffies_seq); + ret = jiffies_64; +- } while (read_seqretry(&jiffies_lock, seq)); ++ } while (read_seqcount_retry(&jiffies_seq, seq)); + return ret; + } + EXPORT_SYMBOL(get_jiffies_64); +--- a/kernel/time/tick-common.c ++++ b/kernel/time/tick-common.c +@@ -78,13 +78,15 @@ int tick_is_oneshot_available(void) + static void tick_periodic(int cpu) + { + if (tick_do_timer_cpu == cpu) { +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_seq); + + /* Keep track of the next tick event */ + tick_next_period = ktime_add(tick_next_period, tick_period); + + do_timer(1); +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + update_wall_time(); + } + +@@ -146,9 +148,9 @@ void tick_setup_periodic(struct clock_ev + ktime_t next; + + do { +- seq = read_seqbegin(&jiffies_lock); ++ seq = read_seqcount_begin(&jiffies_seq); + next = tick_next_period; +- } while (read_seqretry(&jiffies_lock, seq)); ++ } while (read_seqcount_retry(&jiffies_seq, seq)); + + clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); + +--- a/kernel/time/tick-sched.c ++++ b/kernel/time/tick-sched.c +@@ -62,7 +62,8 @@ static void tick_do_update_jiffies64(kti + return; + + /* Reevalute with jiffies_lock held */ +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_seq); + + delta = ktime_sub(now, last_jiffies_update); + if (delta.tv64 >= tick_period.tv64) { +@@ -85,10 +86,12 @@ static void tick_do_update_jiffies64(kti + /* Keep the tick_next_period variable up to date */ + tick_next_period = ktime_add(last_jiffies_update, tick_period); + } else { +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + return; + } +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + update_wall_time(); + } + +@@ -99,12 +102,14 @@ static ktime_t tick_init_jiffy_update(vo + { + ktime_t period; + +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_seq); + /* Did we start the jiffies update yet ? */ + if (last_jiffies_update.tv64 == 0) + last_jiffies_update = tick_next_period; + period = last_jiffies_update; +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + return period; + } + +@@ -578,10 +583,10 @@ static ktime_t tick_nohz_stop_sched_tick + + /* Read jiffies and the time when jiffies were updated last */ + do { +- seq = read_seqbegin(&jiffies_lock); ++ seq = read_seqcount_begin(&jiffies_seq); + last_update = last_jiffies_update; + last_jiffies = jiffies; +- } while (read_seqretry(&jiffies_lock, seq)); ++ } while (read_seqcount_retry(&jiffies_seq, seq)); + + if (rcu_needs_cpu(&rcu_delta_jiffies) || + arch_needs_cpu() || irq_work_needs_cpu()) { +--- a/kernel/time/timekeeping.c ++++ b/kernel/time/timekeeping.c +@@ -2065,8 +2065,10 @@ EXPORT_SYMBOL(hardpps); + */ + void xtime_update(unsigned long ticks) + { +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_seq); + do_timer(ticks); +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + update_wall_time(); + } +--- a/kernel/time/timekeeping.h ++++ b/kernel/time/timekeeping.h +@@ -22,7 +22,8 @@ extern void timekeeping_resume(void); + extern void do_timer(unsigned long ticks); + extern void update_wall_time(void); + +-extern seqlock_t jiffies_lock; ++extern raw_spinlock_t jiffies_lock; ++extern seqcount_t jiffies_seq; + + #define CS_NAME_LEN 32 + diff --git a/debian/patches/features/all/rt/timer-delay-waking-softirqs-from-the-jiffy-tick.patch b/debian/patches/features/all/rt/timer-delay-waking-softirqs-from-the-jiffy-tick.patch new file mode 100644 index 000000000..cf261fd8d --- /dev/null +++ b/debian/patches/features/all/rt/timer-delay-waking-softirqs-from-the-jiffy-tick.patch @@ -0,0 +1,76 @@ +From: Peter Zijlstra +Date: Fri, 21 Aug 2009 11:56:45 +0200 +Subject: timer: delay waking softirqs from the jiffy tick +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +People were complaining about broken balancing with the recent -rt +series. + +A look at /proc/sched_debug yielded: + +cpu#0, 2393.874 MHz + .nr_running : 0 + .load : 0 + .cpu_load[0] : 177522 + .cpu_load[1] : 177522 + .cpu_load[2] : 177522 + .cpu_load[3] : 177522 + .cpu_load[4] : 177522 +cpu#1, 2393.874 MHz + .nr_running : 4 + .load : 4096 + .cpu_load[0] : 181618 + .cpu_load[1] : 180850 + .cpu_load[2] : 180274 + .cpu_load[3] : 179938 + .cpu_load[4] : 179758 + +Which indicated the cpu_load computation was hosed, the 177522 value +indicates that there is one RT task runnable. Initially I thought the +old problem of calculating the cpu_load from a softirq had re-surfaced, +however looking at the code shows its being done from scheduler_tick(). + +[ we really should fix this RT/cfs interaction some day... ] + +A few trace_printk()s later: + + sirq-timer/1-19 [001] 174.289744: 19: 50:S ==> [001] 0:140:R + -0 [001] 174.290724: enqueue_task_rt: adding task: 19/sirq-timer/1 with load: 177522 + -0 [001] 174.290725: 0:140:R + [001] 19: 50:S sirq-timer/1 + -0 [001] 174.290730: scheduler_tick: current load: 177522 + -0 [001] 174.290732: scheduler_tick: current: 0/swapper + -0 [001] 174.290736: 0:140:R ==> [001] 19: 50:R sirq-timer/1 + sirq-timer/1-19 [001] 174.290741: dequeue_task_rt: removing task: 19/sirq-timer/1 with load: 177522 + sirq-timer/1-19 [001] 174.290743: 19: 50:S ==> [001] 0:140:R + +We see that we always raise the timer softirq before doing the load +calculation. Avoid this by re-ordering the scheduler_tick() call in +update_process_times() to occur before we deal with timers. + +This lowers the load back to sanity and restores regular load-balancing +behaviour. + +Signed-off-by: Peter Zijlstra +Signed-off-by: Thomas Gleixner + +--- + kernel/time/timer.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/kernel/time/timer.c ++++ b/kernel/time/timer.c +@@ -1428,13 +1428,13 @@ void update_process_times(int user_tick) + + /* Note: this timer irq context must be accounted for as well. */ + account_process_tick(p, user_tick); ++ scheduler_tick(); + run_local_timers(); + rcu_check_callbacks(user_tick); + #ifdef CONFIG_IRQ_WORK + if (in_irq()) + irq_work_tick(); + #endif +- scheduler_tick(); + run_posix_cpu_timers(p); + } + diff --git a/debian/patches/features/all/rt/timer-fd-avoid-live-lock.patch b/debian/patches/features/all/rt/timer-fd-avoid-live-lock.patch new file mode 100644 index 000000000..fdfc6b022 --- /dev/null +++ b/debian/patches/features/all/rt/timer-fd-avoid-live-lock.patch @@ -0,0 +1,31 @@ +Subject: timer-fd: Prevent live lock +From: Thomas Gleixner +Date: Wed, 25 Jan 2012 11:08:40 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +If hrtimer_try_to_cancel() requires a retry, then depending on the +priority setting te retry loop might prevent timer callback completion +on RT. Prevent that by waiting for completion on RT, no change for a +non RT kernel. + +Reported-by: Sankara Muthukrishnan +Signed-off-by: Thomas Gleixner + +--- + fs/timerfd.c | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +--- a/fs/timerfd.c ++++ b/fs/timerfd.c +@@ -450,7 +450,10 @@ static int do_timerfd_settime(int ufd, i + break; + } + spin_unlock_irq(&ctx->wqh.lock); +- cpu_relax(); ++ if (isalarm(ctx)) ++ hrtimer_wait_for_timer(&ctx->t.alarm.timer); ++ else ++ hrtimer_wait_for_timer(&ctx->t.tmr); + } + + /* diff --git a/debian/patches/features/all/rt/timers-avoid-the-base-null-otptimization-on-rt.patch b/debian/patches/features/all/rt/timers-avoid-the-base-null-otptimization-on-rt.patch new file mode 100644 index 000000000..5c4c640a7 --- /dev/null +++ b/debian/patches/features/all/rt/timers-avoid-the-base-null-otptimization-on-rt.patch @@ -0,0 +1,69 @@ +Subject: timers: Avoid the switch timers base set to NULL trick on RT +From: Thomas Gleixner +Date: Thu, 21 Jul 2011 15:23:39 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +On RT that code is preemptible, so we cannot assign NULL to timers +base as a preempter would spin forever in lock_timer_base(). + +Signed-off-by: Thomas Gleixner +--- + kernel/time/timer.c | 40 ++++++++++++++++++++++++++++++++-------- + 1 file changed, 32 insertions(+), 8 deletions(-) + +--- a/kernel/time/timer.c ++++ b/kernel/time/timer.c +@@ -771,6 +771,36 @@ static struct tvec_base *lock_timer_base + } + } + ++#ifndef CONFIG_PREEMPT_RT_FULL ++static inline struct tvec_base *switch_timer_base(struct timer_list *timer, ++ struct tvec_base *old, ++ struct tvec_base *new) ++{ ++ /* See the comment in lock_timer_base() */ ++ timer_set_base(timer, NULL); ++ spin_unlock(&old->lock); ++ spin_lock(&new->lock); ++ timer_set_base(timer, new); ++ return new; ++} ++#else ++static inline struct tvec_base *switch_timer_base(struct timer_list *timer, ++ struct tvec_base *old, ++ struct tvec_base *new) ++{ ++ /* ++ * We cannot do the above because we might be preempted and ++ * then the preempter would see NULL and loop forever. ++ */ ++ if (spin_trylock(&new->lock)) { ++ timer_set_base(timer, new); ++ spin_unlock(&old->lock); ++ return new; ++ } ++ return old; ++} ++#endif ++ + static inline int + __mod_timer(struct timer_list *timer, unsigned long expires, + bool pending_only, int pinned) +@@ -801,14 +831,8 @@ static inline int + * handler yet has not finished. This also guarantees that + * the timer is serialized wrt itself. + */ +- if (likely(base->running_timer != timer)) { +- /* See the comment in lock_timer_base() */ +- timer_set_base(timer, NULL); +- spin_unlock(&base->lock); +- base = new_base; +- spin_lock(&base->lock); +- timer_set_base(timer, base); +- } ++ if (likely(base->running_timer != timer)) ++ base = switch_timer_base(timer, base, new_base); + } + + timer->expires = expires; diff --git a/debian/patches/features/all/rt/timers-preempt-rt-support.patch b/debian/patches/features/all/rt/timers-preempt-rt-support.patch new file mode 100644 index 000000000..e36c54fda --- /dev/null +++ b/debian/patches/features/all/rt/timers-preempt-rt-support.patch @@ -0,0 +1,55 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:30:20 -0500 +Subject: timers: Preempt-rt support +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The base->lock is a sleeping lock. Try not to workaround with a +spin_trylock(). The rt-mutex lock is not irq save even the try-lock +due to way how the inner lock accessed. Even with this fixed have the +problem that the owner is not the current process on the CPU but his +pid is used while taking the lock. Therefore we go with ext jiffy for +the wakeup. Also drop preempt_disable() usage since we need just to +ensure not to switch CPUs (the data structures have own locks). + +[bigeasy: dropped that spin try lock] +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner +--- + kernel/time/timer.c | 12 ++++++++++-- + 1 file changed, 10 insertions(+), 2 deletions(-) + +--- a/kernel/time/timer.c ++++ b/kernel/time/timer.c +@@ -1395,6 +1395,14 @@ unsigned long get_next_timer_interrupt(u + if (cpu_is_offline(smp_processor_id())) + return expires; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* ++ * On PREEMPT_RT we cannot sleep here. As a result we can't take ++ * the base lock to check when the next timer is pending and so ++ * we assume the next jiffy. ++ */ ++ return now + 1; ++#endif + spin_lock(&base->lock); + if (base->active_timers) { + if (time_before_eq(base->next_timer, base->timer_jiffies)) +@@ -1594,7 +1602,7 @@ static void migrate_timers(int cpu) + + BUG_ON(cpu_online(cpu)); + old_base = per_cpu(tvec_bases, cpu); +- new_base = get_cpu_var(tvec_bases); ++ new_base = get_local_var(tvec_bases); + /* + * The caller is globally serialized and nobody else + * takes two locks at once, deadlock is not possible. +@@ -1618,7 +1626,7 @@ static void migrate_timers(int cpu) + + spin_unlock(&old_base->lock); + spin_unlock_irq(&new_base->lock); +- put_cpu_var(tvec_bases); ++ put_local_var(tvec_bases); + } + + static int timer_cpu_notify(struct notifier_block *self, diff --git a/debian/patches/features/all/rt/timers-prepare-for-full-preemption.patch b/debian/patches/features/all/rt/timers-prepare-for-full-preemption.patch new file mode 100644 index 000000000..0a790ce90 --- /dev/null +++ b/debian/patches/features/all/rt/timers-prepare-for-full-preemption.patch @@ -0,0 +1,146 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:29:34 -0500 +Subject: timers: Prepare for full preemption +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +When softirqs can be preempted we need to make sure that cancelling +the timer from the active thread can not deadlock vs. a running timer +callback. Add a waitqueue to resolve that. + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + include/linux/timer.h | 2 +- + kernel/sched/core.c | 8 ++++++-- + kernel/time/timer.c | 37 ++++++++++++++++++++++++++++++++++--- + 3 files changed, 41 insertions(+), 6 deletions(-) + +--- a/include/linux/timer.h ++++ b/include/linux/timer.h +@@ -241,7 +241,7 @@ extern void add_timer(struct timer_list + + extern int try_to_del_timer_sync(struct timer_list *timer); + +-#ifdef CONFIG_SMP ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) + extern int del_timer_sync(struct timer_list *timer); + #else + # define del_timer_sync(t) del_timer(t) +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -641,12 +641,14 @@ void resched_cpu(int cpu) + */ + int get_nohz_timer_target(int pinned) + { +- int cpu = smp_processor_id(); ++ int cpu; + int i; + struct sched_domain *sd; + ++ preempt_disable_rt(); ++ cpu = smp_processor_id(); + if (pinned || !get_sysctl_timer_migration() || !idle_cpu(cpu)) +- return cpu; ++ goto preempt_en_rt; + + rcu_read_lock(); + for_each_domain(cpu, sd) { +@@ -659,6 +661,8 @@ int get_nohz_timer_target(int pinned) + } + unlock: + rcu_read_unlock(); ++preempt_en_rt: ++ preempt_enable_rt(); + return cpu; + } + /* +--- a/kernel/time/timer.c ++++ b/kernel/time/timer.c +@@ -78,6 +78,9 @@ struct tvec_root { + struct tvec_base { + spinlock_t lock; + struct timer_list *running_timer; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ wait_queue_head_t wait_for_running_timer; ++#endif + unsigned long timer_jiffies; + unsigned long next_timer; + unsigned long active_timers; +@@ -979,6 +982,29 @@ void add_timer_on(struct timer_list *tim + } + EXPORT_SYMBOL_GPL(add_timer_on); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * Wait for a running timer ++ */ ++static void wait_for_running_timer(struct timer_list *timer) ++{ ++ struct tvec_base *base = timer->base; ++ ++ if (base->running_timer == timer) ++ wait_event(base->wait_for_running_timer, ++ base->running_timer != timer); ++} ++ ++# define wakeup_timer_waiters(b) wake_up(&(b)->wait_for_running_timer) ++#else ++static inline void wait_for_running_timer(struct timer_list *timer) ++{ ++ cpu_relax(); ++} ++ ++# define wakeup_timer_waiters(b) do { } while (0) ++#endif ++ + /** + * del_timer - deactive a timer. + * @timer: the timer to be deactivated +@@ -1036,7 +1062,7 @@ int try_to_del_timer_sync(struct timer_l + } + EXPORT_SYMBOL(try_to_del_timer_sync); + +-#ifdef CONFIG_SMP ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) + static DEFINE_PER_CPU(struct tvec_base, __tvec_bases); + + /** +@@ -1098,7 +1124,7 @@ int del_timer_sync(struct timer_list *ti + int ret = try_to_del_timer_sync(timer); + if (ret >= 0) + return ret; +- cpu_relax(); ++ wait_for_running_timer(timer); + } + } + EXPORT_SYMBOL(del_timer_sync); +@@ -1219,15 +1245,17 @@ static inline void __run_timers(struct t + if (irqsafe) { + spin_unlock(&base->lock); + call_timer_fn(timer, fn, data); ++ base->running_timer = NULL; + spin_lock(&base->lock); + } else { + spin_unlock_irq(&base->lock); + call_timer_fn(timer, fn, data); ++ base->running_timer = NULL; + spin_lock_irq(&base->lock); + } + } + } +- base->running_timer = NULL; ++ wakeup_timer_waiters(base); + spin_unlock_irq(&base->lock); + } + +@@ -1625,6 +1653,9 @@ static void __init init_timer_cpu(struct + base->cpu = cpu; + per_cpu(tvec_bases, cpu) = base; + spin_lock_init(&base->lock); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ init_waitqueue_head(&base->wait_for_running_timer); ++#endif + + for (j = 0; j < TVN_SIZE; j++) { + INIT_LIST_HEAD(base->tv5.vec + j); diff --git a/debian/patches/features/all/rt/tracing-account-for-preempt-off-in-preempt_schedule.patch b/debian/patches/features/all/rt/tracing-account-for-preempt-off-in-preempt_schedule.patch new file mode 100644 index 000000000..31da0c54a --- /dev/null +++ b/debian/patches/features/all/rt/tracing-account-for-preempt-off-in-preempt_schedule.patch @@ -0,0 +1,47 @@ +From: Steven Rostedt +Date: Thu, 29 Sep 2011 12:24:30 -0500 +Subject: tracing: Account for preempt off in preempt_schedule() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +The preempt_schedule() uses the preempt_disable_notrace() version +because it can cause infinite recursion by the function tracer as +the function tracer uses preempt_enable_notrace() which may call +back into the preempt_schedule() code as the NEED_RESCHED is still +set and the PREEMPT_ACTIVE has not been set yet. + +See commit: d1f74e20b5b064a130cd0743a256c2d3cfe84010 that made this +change. + +The preemptoff and preemptirqsoff latency tracers require the first +and last preempt count modifiers to enable tracing. But this skips +the checks. Since we can not convert them back to the non notrace +version, we can use the idle() hooks for the latency tracers here. +That is, the start/stop_critical_timings() works well to manually +start and stop the latency tracer for preempt off timings. + +Signed-off-by: Steven Rostedt +Signed-off-by: Clark Williams +Signed-off-by: Thomas Gleixner +--- + kernel/sched/core.c | 9 +++++++++ + 1 file changed, 9 insertions(+) + +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -2970,7 +2970,16 @@ asmlinkage __visible void __sched notrac + * an infinite recursion. + */ + prev_ctx = exception_enter(); ++ /* ++ * The add/subtract must not be traced by the function ++ * tracer. But we still want to account for the ++ * preempt off latency tracer. Since the _notrace versions ++ * of add/subtract skip the accounting for latency tracer ++ * we must force it manually. ++ */ ++ start_critical_timings(); + __schedule(); ++ stop_critical_timings(); + exception_exit(prev_ctx); + + __preempt_count_sub(PREEMPT_ACTIVE); diff --git a/debian/patches/features/all/rt/upstream-net-rt-remove-preemption-disabling-in-netif_rx.patch b/debian/patches/features/all/rt/upstream-net-rt-remove-preemption-disabling-in-netif_rx.patch new file mode 100644 index 000000000..9938d3845 --- /dev/null +++ b/debian/patches/features/all/rt/upstream-net-rt-remove-preemption-disabling-in-netif_rx.patch @@ -0,0 +1,66 @@ +Subject: net: Remove preemption disabling in netif_rx() +From: Priyanka Jain +Date: Thu, 17 May 2012 09:35:11 +0530 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +1)enqueue_to_backlog() (called from netif_rx) should be + bind to a particluar CPU. This can be achieved by + disabling migration. No need to disable preemption + +2)Fixes crash "BUG: scheduling while atomic: ksoftirqd" + in case of RT. + If preemption is disabled, enqueue_to_backog() is called + in atomic context. And if backlog exceeds its count, + kfree_skb() is called. But in RT, kfree_skb() might + gets scheduled out, so it expects non atomic context. + +3)When CONFIG_PREEMPT_RT_FULL is not defined, + migrate_enable(), migrate_disable() maps to + preempt_enable() and preempt_disable(), so no + change in functionality in case of non-RT. + +-Replace preempt_enable(), preempt_disable() with + migrate_enable(), migrate_disable() respectively +-Replace get_cpu(), put_cpu() with get_cpu_light(), + put_cpu_light() respectively + +Signed-off-by: Priyanka Jain +Acked-by: Rajan Srivastava +Cc: +Link: http://lkml.kernel.org/r/1337227511-2271-1-git-send-email-Priyanka.Jain@freescale.com + +Signed-off-by: Thomas Gleixner +--- + Testing: Tested successfully on p4080ds(8-core SMP system) + + net/core/dev.c | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -3387,7 +3387,7 @@ static int netif_rx_internal(struct sk_b + struct rps_dev_flow voidflow, *rflow = &voidflow; + int cpu; + +- preempt_disable(); ++ migrate_disable(); + rcu_read_lock(); + + cpu = get_rps_cpu(skb->dev, skb, &rflow); +@@ -3397,13 +3397,13 @@ static int netif_rx_internal(struct sk_b + ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); + + rcu_read_unlock(); +- preempt_enable(); ++ migrate_enable(); + } else + #endif + { + unsigned int qtail; +- ret = enqueue_to_backlog(skb, get_cpu(), &qtail); +- put_cpu(); ++ ret = enqueue_to_backlog(skb, get_cpu_light(), &qtail); ++ put_cpu_light(); + } + return ret; + } diff --git a/debian/patches/features/all/rt/usb-use-_nort-in-giveback.patch b/debian/patches/features/all/rt/usb-use-_nort-in-giveback.patch new file mode 100644 index 000000000..2c9c93cc4 --- /dev/null +++ b/debian/patches/features/all/rt/usb-use-_nort-in-giveback.patch @@ -0,0 +1,58 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 8 Nov 2013 17:34:54 +0100 +Subject: usb: Use _nort in giveback function +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Since commit 94dfd7ed ("USB: HCD: support giveback of URB in tasklet +context") I see + +|BUG: sleeping function called from invalid context at kernel/rtmutex.c:673 +|in_atomic(): 0, irqs_disabled(): 1, pid: 109, name: irq/11-uhci_hcd +|no locks held by irq/11-uhci_hcd/109. +|irq event stamp: 440 +|hardirqs last enabled at (439): [] _raw_spin_unlock_irqrestore+0x75/0x90 +|hardirqs last disabled at (440): [] __usb_hcd_giveback_urb+0x46/0xc0 +|softirqs last enabled at (0): [] copy_process.part.52+0x511/0x1510 +|softirqs last disabled at (0): [< (null)>] (null) +|CPU: 3 PID: 109 Comm: irq/11-uhci_hcd Not tainted 3.12.0-rt0-rc1+ #13 +|Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 +| 0000000000000000 ffff8800db9ffbe0 ffffffff8169f064 0000000000000000 +| ffff8800db9ffbf8 ffffffff810b2122 ffff88020f03e888 ffff8800db9ffc18 +| ffffffff816a6944 ffffffff810b5748 ffff88020f03c000 ffff8800db9ffc50 +|Call Trace: +| [] dump_stack+0x4e/0x8f +| [] __might_sleep+0x112/0x190 +| [] rt_spin_lock+0x24/0x60 +| [] hid_ctrl+0x3b/0x190 +| [] __usb_hcd_giveback_urb+0x4f/0xc0 +| [] usb_hcd_giveback_urb+0x3f/0x140 +| [] uhci_giveback_urb+0xaf/0x280 +| [] uhci_scan_schedule+0x47a/0xb10 +| [] uhci_irq+0xa6/0x1a0 +| [] usb_hcd_irq+0x28/0x40 +| [] irq_forced_thread_fn+0x23/0x70 +| [] irq_thread+0x10f/0x150 +| [] kthread+0xcd/0xe0 +| [] ret_from_fork+0x7c/0xb0 + +on -RT we run threaded so no need to disable interrupts. + +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/usb/core/hcd.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/drivers/usb/core/hcd.c ++++ b/drivers/usb/core/hcd.c +@@ -1681,9 +1681,9 @@ static void __usb_hcd_giveback_urb(struc + * and no one may trigger the above deadlock situation when + * running complete() in tasklet. + */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + urb->complete(urb); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + usb_anchor_resume_wakeups(anchor); + atomic_dec(&urb->use_count); diff --git a/debian/patches/features/all/rt/user-use-local-irq-nort.patch b/debian/patches/features/all/rt/user-use-local-irq-nort.patch new file mode 100644 index 000000000..ff39c1ef0 --- /dev/null +++ b/debian/patches/features/all/rt/user-use-local-irq-nort.patch @@ -0,0 +1,30 @@ +From: Thomas Gleixner +Date: Tue, 21 Jul 2009 23:06:05 +0200 +Subject: core: Do not disable interrupts on RT in kernel/users.c +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Use the local_irq_*_nort variants to reduce latencies in RT. The code +is serialized by the locks. No need to disable interrupts. + +Signed-off-by: Thomas Gleixner + +--- + kernel/user.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/kernel/user.c ++++ b/kernel/user.c +@@ -161,11 +161,11 @@ void free_uid(struct user_struct *up) + if (!up) + return; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + if (atomic_dec_and_lock(&up->__count, &uidhash_lock)) + free_user(up, flags); + else +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + + struct user_struct *alloc_uid(kuid_t uid) diff --git a/debian/patches/features/all/rt/vtime-split-lock-and-seqcount.patch b/debian/patches/features/all/rt/vtime-split-lock-and-seqcount.patch new file mode 100644 index 000000000..7737226a7 --- /dev/null +++ b/debian/patches/features/all/rt/vtime-split-lock-and-seqcount.patch @@ -0,0 +1,206 @@ +Subject: vtime: Split lock and seqcount +From: Thomas Gleixner +Date: Tue, 23 Jul 2013 15:45:51 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Replace vtime_seqlock seqlock with a simple seqcounter and a rawlock +so it can taken in atomic context on RT. + +Signed-off-by: Thomas Gleixner +--- + include/linux/init_task.h | 3 +- + include/linux/sched.h | 3 +- + kernel/fork.c | 3 +- + kernel/sched/cputime.c | 62 +++++++++++++++++++++++++++++----------------- + 4 files changed, 46 insertions(+), 25 deletions(-) +--- a/include/linux/init_task.h ++++ b/include/linux/init_task.h +@@ -149,7 +149,8 @@ extern struct task_group root_task_group + + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN + # define INIT_VTIME(tsk) \ +- .vtime_seqlock = __SEQLOCK_UNLOCKED(tsk.vtime_seqlock), \ ++ .vtime_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.vtime_lock), \ ++ .vtime_seq = SEQCNT_ZERO(tsk.vtime_seq), \ + .vtime_snap = 0, \ + .vtime_snap_whence = VTIME_SYS, + #else +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -1478,7 +1478,8 @@ struct task_struct { + struct cputime prev_cputime; + #endif + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +- seqlock_t vtime_seqlock; ++ raw_spinlock_t vtime_lock; ++ seqcount_t vtime_seq; + unsigned long long vtime_snap; + enum { + VTIME_SLEEPING = 0, +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -1345,7 +1345,8 @@ static struct task_struct *copy_process( + p->prev_cputime.utime = p->prev_cputime.stime = 0; + #endif + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +- seqlock_init(&p->vtime_seqlock); ++ raw_spin_lock_init(&p->vtime_lock); ++ seqcount_init(&p->vtime_seq); + p->vtime_snap = 0; + p->vtime_snap_whence = VTIME_SLEEPING; + #endif +--- a/kernel/sched/cputime.c ++++ b/kernel/sched/cputime.c +@@ -675,37 +675,45 @@ static void __vtime_account_system(struc + + void vtime_account_system(struct task_struct *tsk) + { +- write_seqlock(&tsk->vtime_seqlock); ++ raw_spin_lock(&tsk->vtime_lock); ++ write_seqcount_begin(&tsk->vtime_seq); + __vtime_account_system(tsk); +- write_sequnlock(&tsk->vtime_seqlock); ++ write_seqcount_end(&tsk->vtime_seq); ++ raw_spin_unlock(&tsk->vtime_lock); + } + + void vtime_gen_account_irq_exit(struct task_struct *tsk) + { +- write_seqlock(&tsk->vtime_seqlock); ++ raw_spin_lock(&tsk->vtime_lock); ++ write_seqcount_begin(&tsk->vtime_seq); + __vtime_account_system(tsk); + if (context_tracking_in_user()) + tsk->vtime_snap_whence = VTIME_USER; +- write_sequnlock(&tsk->vtime_seqlock); ++ write_seqcount_end(&tsk->vtime_seq); ++ raw_spin_unlock(&tsk->vtime_lock); + } + + void vtime_account_user(struct task_struct *tsk) + { + cputime_t delta_cpu; + +- write_seqlock(&tsk->vtime_seqlock); ++ raw_spin_lock(&tsk->vtime_lock); ++ write_seqcount_begin(&tsk->vtime_seq); + delta_cpu = get_vtime_delta(tsk); + tsk->vtime_snap_whence = VTIME_SYS; + account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); +- write_sequnlock(&tsk->vtime_seqlock); ++ write_seqcount_end(&tsk->vtime_seq); ++ raw_spin_unlock(&tsk->vtime_lock); + } + + void vtime_user_enter(struct task_struct *tsk) + { +- write_seqlock(&tsk->vtime_seqlock); ++ raw_spin_lock(&tsk->vtime_lock); ++ write_seqcount_begin(&tsk->vtime_seq); + __vtime_account_system(tsk); + tsk->vtime_snap_whence = VTIME_USER; +- write_sequnlock(&tsk->vtime_seqlock); ++ write_seqcount_end(&tsk->vtime_seq); ++ raw_spin_unlock(&tsk->vtime_lock); + } + + void vtime_guest_enter(struct task_struct *tsk) +@@ -717,19 +725,23 @@ void vtime_guest_enter(struct task_struc + * synchronization against the reader (task_gtime()) + * that can thus safely catch up with a tickless delta. + */ +- write_seqlock(&tsk->vtime_seqlock); ++ raw_spin_lock(&tsk->vtime_lock); ++ write_seqcount_begin(&tsk->vtime_seq); + __vtime_account_system(tsk); + current->flags |= PF_VCPU; +- write_sequnlock(&tsk->vtime_seqlock); ++ write_seqcount_end(&tsk->vtime_seq); ++ raw_spin_unlock(&tsk->vtime_lock); + } + EXPORT_SYMBOL_GPL(vtime_guest_enter); + + void vtime_guest_exit(struct task_struct *tsk) + { +- write_seqlock(&tsk->vtime_seqlock); ++ raw_spin_lock(&tsk->vtime_lock); ++ write_seqcount_begin(&tsk->vtime_seq); + __vtime_account_system(tsk); + current->flags &= ~PF_VCPU; +- write_sequnlock(&tsk->vtime_seqlock); ++ write_seqcount_end(&tsk->vtime_seq); ++ raw_spin_unlock(&tsk->vtime_lock); + } + EXPORT_SYMBOL_GPL(vtime_guest_exit); + +@@ -742,24 +754,30 @@ void vtime_account_idle(struct task_stru + + void arch_vtime_task_switch(struct task_struct *prev) + { +- write_seqlock(&prev->vtime_seqlock); ++ raw_spin_lock(&prev->vtime_lock); ++ write_seqcount_begin(&prev->vtime_seq); + prev->vtime_snap_whence = VTIME_SLEEPING; +- write_sequnlock(&prev->vtime_seqlock); ++ write_seqcount_end(&prev->vtime_seq); ++ raw_spin_unlock(&prev->vtime_lock); + +- write_seqlock(¤t->vtime_seqlock); ++ raw_spin_lock(¤t->vtime_lock); ++ write_seqcount_begin(¤t->vtime_seq); + current->vtime_snap_whence = VTIME_SYS; + current->vtime_snap = sched_clock_cpu(smp_processor_id()); +- write_sequnlock(¤t->vtime_seqlock); ++ write_seqcount_end(¤t->vtime_seq); ++ raw_spin_unlock(¤t->vtime_lock); + } + + void vtime_init_idle(struct task_struct *t, int cpu) + { + unsigned long flags; + +- write_seqlock_irqsave(&t->vtime_seqlock, flags); ++ raw_spin_lock_irqsave(&t->vtime_lock, flags); ++ write_seqcount_begin(&t->vtime_seq); + t->vtime_snap_whence = VTIME_SYS; + t->vtime_snap = sched_clock_cpu(cpu); +- write_sequnlock_irqrestore(&t->vtime_seqlock, flags); ++ write_seqcount_end(&t->vtime_seq); ++ raw_spin_unlock_irqrestore(&t->vtime_lock, flags); + } + + cputime_t task_gtime(struct task_struct *t) +@@ -768,13 +786,13 @@ cputime_t task_gtime(struct task_struct + cputime_t gtime; + + do { +- seq = read_seqbegin(&t->vtime_seqlock); ++ seq = read_seqcount_begin(&t->vtime_seq); + + gtime = t->gtime; + if (t->flags & PF_VCPU) + gtime += vtime_delta(t); + +- } while (read_seqretry(&t->vtime_seqlock, seq)); ++ } while (read_seqcount_retry(&t->vtime_seq, seq)); + + return gtime; + } +@@ -797,7 +815,7 @@ fetch_task_cputime(struct task_struct *t + *udelta = 0; + *sdelta = 0; + +- seq = read_seqbegin(&t->vtime_seqlock); ++ seq = read_seqcount_begin(&t->vtime_seq); + + if (u_dst) + *u_dst = *u_src; +@@ -821,7 +839,7 @@ fetch_task_cputime(struct task_struct *t + if (t->vtime_snap_whence == VTIME_SYS) + *sdelta = delta; + } +- } while (read_seqretry(&t->vtime_seqlock, seq)); ++ } while (read_seqcount_retry(&t->vtime_seq, seq)); + } + + diff --git a/debian/patches/features/all/rt/wait-simple-implementation.patch b/debian/patches/features/all/rt/wait-simple-implementation.patch new file mode 100644 index 000000000..f7d598a30 --- /dev/null +++ b/debian/patches/features/all/rt/wait-simple-implementation.patch @@ -0,0 +1,363 @@ +From: Thomas Gleixner +Date: Mon Dec 12 12:29:04 2011 +0100 +Subject: wait-simple: Simple waitqueue implementation + +wait_queue is a swiss army knife and in most of the cases the +complexity is not needed. For RT waitqueues are a constant source of +trouble as we can't convert the head lock to a raw spinlock due to +fancy and long lasting callbacks. + +Provide a slim version, which allows RT to replace wait queues. This +should go mainline as well, as it lowers memory consumption and +runtime overhead. + +Signed-off-by: Thomas Gleixner +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +smp_mb() added by Steven Rostedt to fix a race condition with swait +wakeups vs adding items to the list. +--- + include/linux/wait-simple.h | 207 ++++++++++++++++++++++++++++++++++++++++++++ + kernel/sched/Makefile | 2 + kernel/sched/wait-simple.c | 115 ++++++++++++++++++++++++ + 3 files changed, 323 insertions(+), 1 deletion(-) + +--- /dev/null ++++ b/include/linux/wait-simple.h +@@ -0,0 +1,207 @@ ++#ifndef _LINUX_WAIT_SIMPLE_H ++#define _LINUX_WAIT_SIMPLE_H ++ ++#include ++#include ++ ++#include ++ ++struct swaiter { ++ struct task_struct *task; ++ struct list_head node; ++}; ++ ++#define DEFINE_SWAITER(name) \ ++ struct swaiter name = { \ ++ .task = current, \ ++ .node = LIST_HEAD_INIT((name).node), \ ++ } ++ ++struct swait_head { ++ raw_spinlock_t lock; ++ struct list_head list; ++}; ++ ++#define SWAIT_HEAD_INITIALIZER(name) { \ ++ .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ ++ .list = LIST_HEAD_INIT((name).list), \ ++ } ++ ++#define DEFINE_SWAIT_HEAD(name) \ ++ struct swait_head name = SWAIT_HEAD_INITIALIZER(name) ++ ++extern void __init_swait_head(struct swait_head *h, struct lock_class_key *key); ++ ++#define init_swait_head(swh) \ ++ do { \ ++ static struct lock_class_key __key; \ ++ \ ++ __init_swait_head((swh), &__key); \ ++ } while (0) ++ ++/* ++ * Waiter functions ++ */ ++extern void swait_prepare_locked(struct swait_head *head, struct swaiter *w); ++extern void swait_prepare(struct swait_head *head, struct swaiter *w, int state); ++extern void swait_finish_locked(struct swait_head *head, struct swaiter *w); ++extern void swait_finish(struct swait_head *head, struct swaiter *w); ++ ++/* Check whether a head has waiters enqueued */ ++static inline bool swaitqueue_active(struct swait_head *h) ++{ ++ /* Make sure the condition is visible before checking list_empty() */ ++ smp_mb(); ++ return !list_empty(&h->list); ++} ++ ++/* ++ * Wakeup functions ++ */ ++extern unsigned int __swait_wake(struct swait_head *head, unsigned int state, unsigned int num); ++extern unsigned int __swait_wake_locked(struct swait_head *head, unsigned int state, unsigned int num); ++ ++#define swait_wake(head) __swait_wake(head, TASK_NORMAL, 1) ++#define swait_wake_interruptible(head) __swait_wake(head, TASK_INTERRUPTIBLE, 1) ++#define swait_wake_all(head) __swait_wake(head, TASK_NORMAL, 0) ++#define swait_wake_all_interruptible(head) __swait_wake(head, TASK_INTERRUPTIBLE, 0) ++ ++/* ++ * Event API ++ */ ++#define __swait_event(wq, condition) \ ++do { \ ++ DEFINE_SWAITER(__wait); \ ++ \ ++ for (;;) { \ ++ swait_prepare(&wq, &__wait, TASK_UNINTERRUPTIBLE); \ ++ if (condition) \ ++ break; \ ++ schedule(); \ ++ } \ ++ swait_finish(&wq, &__wait); \ ++} while (0) ++ ++/** ++ * swait_event - sleep until a condition gets true ++ * @wq: the waitqueue to wait on ++ * @condition: a C expression for the event to wait for ++ * ++ * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the ++ * @condition evaluates to true. The @condition is checked each time ++ * the waitqueue @wq is woken up. ++ * ++ * wake_up() has to be called after changing any variable that could ++ * change the result of the wait condition. ++ */ ++#define swait_event(wq, condition) \ ++do { \ ++ if (condition) \ ++ break; \ ++ __swait_event(wq, condition); \ ++} while (0) ++ ++#define __swait_event_interruptible(wq, condition, ret) \ ++do { \ ++ DEFINE_SWAITER(__wait); \ ++ \ ++ for (;;) { \ ++ swait_prepare(&wq, &__wait, TASK_INTERRUPTIBLE); \ ++ if (condition) \ ++ break; \ ++ if (signal_pending(current)) { \ ++ ret = -ERESTARTSYS; \ ++ break; \ ++ } \ ++ schedule(); \ ++ } \ ++ swait_finish(&wq, &__wait); \ ++} while (0) ++ ++#define __swait_event_interruptible_timeout(wq, condition, ret) \ ++do { \ ++ DEFINE_SWAITER(__wait); \ ++ \ ++ for (;;) { \ ++ swait_prepare(&wq, &__wait, TASK_INTERRUPTIBLE); \ ++ if (condition) \ ++ break; \ ++ if (signal_pending(current)) { \ ++ ret = -ERESTARTSYS; \ ++ break; \ ++ } \ ++ ret = schedule_timeout(ret); \ ++ if (!ret) \ ++ break; \ ++ } \ ++ swait_finish(&wq, &__wait); \ ++} while (0) ++ ++/** ++ * swait_event_interruptible - sleep until a condition gets true ++ * @wq: the waitqueue to wait on ++ * @condition: a C expression for the event to wait for ++ * ++ * The process is put to sleep (TASK_INTERRUPTIBLE) until the ++ * @condition evaluates to true. The @condition is checked each time ++ * the waitqueue @wq is woken up. ++ * ++ * wake_up() has to be called after changing any variable that could ++ * change the result of the wait condition. ++ */ ++#define swait_event_interruptible(wq, condition) \ ++({ \ ++ int __ret = 0; \ ++ if (!(condition)) \ ++ __swait_event_interruptible(wq, condition, __ret); \ ++ __ret; \ ++}) ++ ++#define swait_event_interruptible_timeout(wq, condition, timeout) \ ++({ \ ++ int __ret = timeout; \ ++ if (!(condition)) \ ++ __swait_event_interruptible_timeout(wq, condition, __ret); \ ++ __ret; \ ++}) ++ ++#define __swait_event_timeout(wq, condition, ret) \ ++do { \ ++ DEFINE_SWAITER(__wait); \ ++ \ ++ for (;;) { \ ++ swait_prepare(&wq, &__wait, TASK_UNINTERRUPTIBLE); \ ++ if (condition) \ ++ break; \ ++ ret = schedule_timeout(ret); \ ++ if (!ret) \ ++ break; \ ++ } \ ++ swait_finish(&wq, &__wait); \ ++} while (0) ++ ++/** ++ * swait_event_timeout - sleep until a condition gets true or a timeout elapses ++ * @wq: the waitqueue to wait on ++ * @condition: a C expression for the event to wait for ++ * @timeout: timeout, in jiffies ++ * ++ * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the ++ * @condition evaluates to true. The @condition is checked each time ++ * the waitqueue @wq is woken up. ++ * ++ * wake_up() has to be called after changing any variable that could ++ * change the result of the wait condition. ++ * ++ * The function returns 0 if the @timeout elapsed, and the remaining ++ * jiffies if the condition evaluated to true before the timeout elapsed. ++ */ ++#define swait_event_timeout(wq, condition, timeout) \ ++({ \ ++ long __ret = timeout; \ ++ if (!(condition)) \ ++ __swait_event_timeout(wq, condition, __ret); \ ++ __ret; \ ++}) ++ ++#endif +--- a/kernel/sched/Makefile ++++ b/kernel/sched/Makefile +@@ -13,7 +13,7 @@ endif + + obj-y += core.o proc.o clock.o cputime.o + obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o +-obj-y += wait.o completion.o idle.o ++obj-y += wait.o wait-simple.o completion.o idle.o + obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o + obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o + obj-$(CONFIG_SCHEDSTATS) += stats.o +--- /dev/null ++++ b/kernel/sched/wait-simple.c +@@ -0,0 +1,115 @@ ++/* ++ * Simple waitqueues without fancy flags and callbacks ++ * ++ * (C) 2011 Thomas Gleixner ++ * ++ * Based on kernel/wait.c ++ * ++ * For licencing details see kernel-base/COPYING ++ */ ++#include ++#include ++#include ++#include ++ ++/* Adds w to head->list. Must be called with head->lock locked. */ ++static inline void __swait_enqueue(struct swait_head *head, struct swaiter *w) ++{ ++ list_add(&w->node, &head->list); ++ /* We can't let the condition leak before the setting of head */ ++ smp_mb(); ++} ++ ++/* Removes w from head->list. Must be called with head->lock locked. */ ++static inline void __swait_dequeue(struct swaiter *w) ++{ ++ list_del_init(&w->node); ++} ++ ++void __init_swait_head(struct swait_head *head, struct lock_class_key *key) ++{ ++ raw_spin_lock_init(&head->lock); ++ lockdep_set_class(&head->lock, key); ++ INIT_LIST_HEAD(&head->list); ++} ++EXPORT_SYMBOL(__init_swait_head); ++ ++void swait_prepare_locked(struct swait_head *head, struct swaiter *w) ++{ ++ w->task = current; ++ if (list_empty(&w->node)) ++ __swait_enqueue(head, w); ++} ++ ++void swait_prepare(struct swait_head *head, struct swaiter *w, int state) ++{ ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&head->lock, flags); ++ swait_prepare_locked(head, w); ++ __set_current_state(state); ++ raw_spin_unlock_irqrestore(&head->lock, flags); ++} ++EXPORT_SYMBOL(swait_prepare); ++ ++void swait_finish_locked(struct swait_head *head, struct swaiter *w) ++{ ++ __set_current_state(TASK_RUNNING); ++ if (w->task) ++ __swait_dequeue(w); ++} ++ ++void swait_finish(struct swait_head *head, struct swaiter *w) ++{ ++ unsigned long flags; ++ ++ __set_current_state(TASK_RUNNING); ++ if (w->task) { ++ raw_spin_lock_irqsave(&head->lock, flags); ++ __swait_dequeue(w); ++ raw_spin_unlock_irqrestore(&head->lock, flags); ++ } ++} ++EXPORT_SYMBOL(swait_finish); ++ ++unsigned int ++__swait_wake_locked(struct swait_head *head, unsigned int state, unsigned int num) ++{ ++ struct swaiter *curr, *next; ++ int woken = 0; ++ ++ list_for_each_entry_safe(curr, next, &head->list, node) { ++ if (wake_up_state(curr->task, state)) { ++ __swait_dequeue(curr); ++ /* ++ * The waiting task can free the waiter as ++ * soon as curr->task = NULL is written, ++ * without taking any locks. A memory barrier ++ * is required here to prevent the following ++ * store to curr->task from getting ahead of ++ * the dequeue operation. ++ */ ++ smp_wmb(); ++ curr->task = NULL; ++ if (++woken == num) ++ break; ++ } ++ } ++ return woken; ++} ++ ++unsigned int ++__swait_wake(struct swait_head *head, unsigned int state, unsigned int num) ++{ ++ unsigned long flags; ++ int woken; ++ ++ if (!swaitqueue_active(head)) ++ return 0; ++ ++ raw_spin_lock_irqsave(&head->lock, flags); ++ woken = __swait_wake_locked(head, state, num); ++ raw_spin_unlock_irqrestore(&head->lock, flags); ++ return woken; ++} ++EXPORT_SYMBOL(__swait_wake); diff --git a/debian/patches/features/all/rt/wait.h-include-atomic.h.patch b/debian/patches/features/all/rt/wait.h-include-atomic.h.patch new file mode 100644 index 000000000..6a2835976 --- /dev/null +++ b/debian/patches/features/all/rt/wait.h-include-atomic.h.patch @@ -0,0 +1,33 @@ +From: Sebastian Andrzej Siewior +Date: Mon, 28 Oct 2013 12:19:57 +0100 +Subject: wait.h: include atomic.h +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +| CC init/main.o +|In file included from include/linux/mmzone.h:9:0, +| from include/linux/gfp.h:4, +| from include/linux/kmod.h:22, +| from include/linux/module.h:13, +| from init/main.c:15: +|include/linux/wait.h: In function ‘wait_on_atomic_t’: +|include/linux/wait.h:982:2: error: implicit declaration of function ‘atomic_read’ [-Werror=implicit-function-declaration] +| if (atomic_read(val) == 0) +| ^ + +This pops up on ARM. Non-RT gets its atomic.h include from spinlock.h + +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/wait.h | 1 + + 1 file changed, 1 insertion(+) + +--- a/include/linux/wait.h ++++ b/include/linux/wait.h +@@ -8,6 +8,7 @@ + #include + #include + #include ++#include + + typedef struct __wait_queue wait_queue_t; + typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int flags, void *key); diff --git a/debian/patches/features/all/rt/work-queue-work-around-irqsafe-timer-optimization.patch b/debian/patches/features/all/rt/work-queue-work-around-irqsafe-timer-optimization.patch new file mode 100644 index 000000000..6b04c3fb3 --- /dev/null +++ b/debian/patches/features/all/rt/work-queue-work-around-irqsafe-timer-optimization.patch @@ -0,0 +1,133 @@ +From: Thomas Gleixner +Date: Mon, 01 Jul 2013 11:02:42 +0200 +Subject: workqueue: Prevent workqueue versus ata-piix livelock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +An Intel i7 system regularly detected rcu_preempt stalls after the kernel +was upgraded from 3.6-rt to 3.8-rt. When the stall happened, disk I/O was no +longer possible, unless the system was restarted. + +The kernel message was: +INFO: rcu_preempt self-detected stall on CPU { 6} +[..] +NMI backtrace for cpu 6 +CPU 6 +Pid: 119, comm: irq/19-ata_piix Not tainted 3.8.13-rt13 #11 Shuttle Inc. SX58/SX58 +RIP: 0010:[] [] ip_compute_csum+0x30/0x30 +RSP: 0018:ffff880333303cb0 EFLAGS: 00000002 +RAX: 0000000000000006 RBX: 00000000000003e9 RCX: 0000000000000034 +RDX: 0000000000000000 RSI: ffffffff81aa16d0 RDI: 0000000000000001 +RBP: ffff880333303ce8 R08: ffffffff81aa16d0 R09: ffffffff81c1b8cc +R10: 0000000000000000 R11: 0000000000000000 R12: 000000000005161f +R13: 0000000000000006 R14: ffffffff81aa16d0 R15: 0000000000000002 +FS: 0000000000000000(0000) GS:ffff880333300000(0000) knlGS:0000000000000000 +CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b +CR2: 0000003c1b2bb420 CR3: 0000000001a0f000 CR4: 00000000000007e0 +DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 +DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 +Process irq/19-ata_piix (pid: 119, threadinfo ffff88032d88a000, task ffff88032df80000) +Stack: +ffffffff8124cb32 000000000005161e 00000000000003e9 0000000000001000 +0000000000009022 ffffffff81aa16d0 0000000000000002 ffff880333303cf8 +ffffffff8124caa9 ffff880333303d08 ffffffff8124cad2 ffff880333303d28 +Call Trace: + +[] ? delay_tsc+0x33/0xe3 +[] __delay+0xf/0x11 +[] __const_udelay+0x27/0x29 +[] native_safe_apic_wait_icr_idle+0x39/0x45 +[] __default_send_IPI_dest_field.constprop.0+0x1e/0x58 +[] default_send_IPI_mask_sequence_phys+0x49/0x7d +[] physflat_send_IPI_all+0x17/0x19 +[] arch_trigger_all_cpu_backtrace+0x50/0x79 +[] rcu_check_callbacks+0x1cb/0x568 +[] ? raise_softirq+0x2e/0x35 +[] ? tick_sched_do_timer+0x38/0x38 +[] update_process_times+0x44/0x55 +[] tick_sched_handle+0x4a/0x59 +[] tick_sched_timer+0x3c/0x5b +[] __run_hrtimer+0x9b/0x158 +[] hrtimer_interrupt+0x172/0x2aa +[] smp_apic_timer_interrupt+0x76/0x89 +[] apic_timer_interrupt+0x6d/0x80 + +[] ? __local_lock_irqsave+0x17/0x4a +[] try_to_grab_pending+0x42/0x17e +[] mod_delayed_work_on+0x32/0x88 +[] mod_delayed_work+0x1c/0x1e +[] blk_run_queue_async+0x37/0x39 +[] flush_end_io+0xf1/0x107 +[] blk_finish_request+0x21e/0x264 +[] blk_end_bidi_request+0x42/0x60 +[] blk_end_request+0x10/0x12 +[] scsi_io_completion+0x1bf/0x492 +[] ? sd_done+0x298/0x2ef +[] scsi_finish_command+0xe9/0xf2 +[] scsi_softirq_done+0x106/0x10f +[] blk_done_softirq+0x77/0x87 +[] do_current_softirqs+0x172/0x2e1 +[] ? irq_thread_fn+0x3a/0x3a +[] local_bh_enable+0x43/0x72 +[] irq_forced_thread_fn+0x46/0x52 +[] irq_thread+0x8c/0x17c +[] ? irq_thread+0x17c/0x17c +[] ? wake_threads_waitq+0x44/0x44 +[] kthread+0x8d/0x95 +[] ? __kthread_parkme+0x65/0x65 +[] ret_from_fork+0x7c/0xb0 +[] ? __kthread_parkme+0x65/0x65 + +The state of softirqd of this CPU at the time of the crash was: +ksoftirqd/6 R running task 0 53 2 0x00000000 +ffff88032fc39d18 0000000000000046 ffff88033330c4c0 ffff8803303f4710 +ffff88032fc39fd8 ffff88032fc39fd8 0000000000000000 0000000000062500 +ffff88032df88000 ffff8803303f4710 0000000000000000 ffff88032fc38000 +Call Trace: +[] ? __queue_work+0x27c/0x27c +[] preempt_schedule+0x61/0x76 +[] migrate_enable+0xe5/0x1df +[] ? __queue_work+0x27c/0x27c +[] run_timer_softirq+0x161/0x1d6 +[] do_current_softirqs+0x172/0x2e1 +[] run_ksoftirqd+0x2d/0x45 +[] smpboot_thread_fn+0x2ea/0x308 +[] ? test_ti_thread_flag+0xc/0xc +[] ? test_ti_thread_flag+0xc/0xc +[] kthread+0x8d/0x95 +[] ? __kthread_parkme+0x65/0x65 +[] ret_from_fork+0x7c/0xb0 +[] ? __kthread_parkme+0x65/0x65 + +Apparently, the softirq demon and the ata_piix IRQ handler were waiting +for each other to finish ending up in a livelock. After the below patch +was applied, the system no longer crashes. + +Reported-by: Carsten Emde +Proposed-by: Thomas Gleixner +Tested by: Carsten Emde +Signed-off-by: Carsten Emde +Signed-off-by: Thomas Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/workqueue.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +--- a/kernel/workqueue.c ++++ b/kernel/workqueue.c +@@ -49,6 +49,7 @@ + #include + #include + #include ++#include + + #include "workqueue_internal.h" + +@@ -1239,7 +1240,7 @@ static int try_to_grab_pending(struct wo + local_unlock_irqrestore(pendingb_lock, *flags); + if (work_is_canceling(work)) + return -ENOENT; +- cpu_relax(); ++ cpu_chill(); + return -EAGAIN; + } + diff --git a/debian/patches/features/all/rt/work-simple-Simple-work-queue-implemenation.patch b/debian/patches/features/all/rt/work-simple-Simple-work-queue-implemenation.patch new file mode 100644 index 000000000..d04691a34 --- /dev/null +++ b/debian/patches/features/all/rt/work-simple-Simple-work-queue-implemenation.patch @@ -0,0 +1,233 @@ +From: Daniel Wagner +Date: Fri, 11 Jul 2014 15:26:11 +0200 +Subject: work-simple: Simple work queue implemenation +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Provides a framework for enqueuing callbacks from irq context +PREEMPT_RT_FULL safe. The callbacks are executed in kthread context. + +Bases on wait-simple. + +Signed-off-by: Daniel Wagner +Cc: Sebastian Andrzej Siewior +--- + include/linux/work-simple.h | 24 ++++++ + kernel/sched/Makefile | 2 + kernel/sched/work-simple.c | 172 ++++++++++++++++++++++++++++++++++++++++++++ + 3 files changed, 197 insertions(+), 1 deletion(-) + create mode 100644 include/linux/work-simple.h + create mode 100644 kernel/sched/work-simple.c + +--- /dev/null ++++ b/include/linux/work-simple.h +@@ -0,0 +1,24 @@ ++#ifndef _LINUX_SWORK_H ++#define _LINUX_SWORK_H ++ ++#include ++ ++struct swork_event { ++ struct list_head item; ++ unsigned long flags; ++ void (*func)(struct swork_event *); ++}; ++ ++static inline void INIT_SWORK(struct swork_event *event, ++ void (*func)(struct swork_event *)) ++{ ++ event->flags = 0; ++ event->func = func; ++} ++ ++bool swork_queue(struct swork_event *sev); ++ ++int swork_get(void); ++void swork_put(void); ++ ++#endif /* _LINUX_SWORK_H */ +--- a/kernel/sched/Makefile ++++ b/kernel/sched/Makefile +@@ -13,7 +13,7 @@ endif + + obj-y += core.o proc.o clock.o cputime.o + obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o +-obj-y += wait.o wait-simple.o completion.o idle.o ++obj-y += wait.o wait-simple.o work-simple.o completion.o idle.o + obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o + obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o + obj-$(CONFIG_SCHEDSTATS) += stats.o +--- /dev/null ++++ b/kernel/sched/work-simple.c +@@ -0,0 +1,172 @@ ++/* ++ * Copyright (C) 2014 BMW Car IT GmbH, Daniel Wagner daniel.wagner@bmw-carit.de ++ * ++ * Provides a framework for enqueuing callbacks from irq context ++ * PREEMPT_RT_FULL safe. The callbacks are executed in kthread context. ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++ ++#define SWORK_EVENT_PENDING (1 << 0) ++ ++static DEFINE_MUTEX(worker_mutex); ++static struct sworker *glob_worker; ++ ++struct sworker { ++ struct list_head events; ++ struct swait_head wq; ++ ++ raw_spinlock_t lock; ++ ++ struct task_struct *task; ++ int refs; ++}; ++ ++static bool swork_readable(struct sworker *worker) ++{ ++ bool r; ++ ++ if (kthread_should_stop()) ++ return true; ++ ++ raw_spin_lock_irq(&worker->lock); ++ r = !list_empty(&worker->events); ++ raw_spin_unlock_irq(&worker->lock); ++ ++ return r; ++} ++ ++static int swork_kthread(void *arg) ++{ ++ struct sworker *worker = arg; ++ ++ for (;;) { ++ swait_event_interruptible(worker->wq, ++ swork_readable(worker)); ++ if (kthread_should_stop()) ++ break; ++ ++ raw_spin_lock_irq(&worker->lock); ++ while (!list_empty(&worker->events)) { ++ struct swork_event *sev; ++ ++ sev = list_first_entry(&worker->events, ++ struct swork_event, item); ++ list_del(&sev->item); ++ raw_spin_unlock_irq(&worker->lock); ++ ++ WARN_ON_ONCE(!test_and_clear_bit(SWORK_EVENT_PENDING, ++ &sev->flags)); ++ sev->func(sev); ++ raw_spin_lock_irq(&worker->lock); ++ } ++ raw_spin_unlock_irq(&worker->lock); ++ } ++ return 0; ++} ++ ++static struct sworker *swork_create(void) ++{ ++ struct sworker *worker; ++ ++ worker = kzalloc(sizeof(*worker), GFP_KERNEL); ++ if (!worker) ++ return ERR_PTR(-ENOMEM); ++ ++ INIT_LIST_HEAD(&worker->events); ++ raw_spin_lock_init(&worker->lock); ++ init_swait_head(&worker->wq); ++ ++ worker->task = kthread_run(swork_kthread, worker, "kswork"); ++ if (IS_ERR(worker->task)) { ++ kfree(worker); ++ return ERR_PTR(-ENOMEM); ++ } ++ ++ return worker; ++} ++ ++static void swork_destroy(struct sworker *worker) ++{ ++ kthread_stop(worker->task); ++ ++ WARN_ON(!list_empty(&worker->events)); ++ kfree(worker); ++} ++ ++/** ++ * swork_queue - queue swork ++ * ++ * Returns %false if @work was already on a queue, %true otherwise. ++ * ++ * The work is queued and processed on a random CPU ++ */ ++bool swork_queue(struct swork_event *sev) ++{ ++ unsigned long flags; ++ ++ if (test_and_set_bit(SWORK_EVENT_PENDING, &sev->flags)) ++ return false; ++ ++ raw_spin_lock_irqsave(&glob_worker->lock, flags); ++ list_add_tail(&sev->item, &glob_worker->events); ++ raw_spin_unlock_irqrestore(&glob_worker->lock, flags); ++ ++ swait_wake(&glob_worker->wq); ++ return true; ++} ++EXPORT_SYMBOL_GPL(swork_queue); ++ ++/** ++ * swork_get - get an instance of the sworker ++ * ++ * Returns an negative error code if the initialization if the worker did not ++ * work, %0 otherwise. ++ * ++ */ ++int swork_get(void) ++{ ++ struct sworker *worker; ++ ++ mutex_lock(&worker_mutex); ++ if (!glob_worker) { ++ worker = swork_create(); ++ if (IS_ERR(worker)) { ++ mutex_unlock(&worker_mutex); ++ return -ENOMEM; ++ } ++ ++ glob_worker = worker; ++ } ++ ++ glob_worker->refs++; ++ mutex_unlock(&worker_mutex); ++ ++ return 0; ++} ++EXPORT_SYMBOL_GPL(swork_get); ++ ++/** ++ * swork_put - puts an instance of the sworker ++ * ++ * Will destroy the sworker thread. This function must not be called until all ++ * queued events have been completed. ++ */ ++void swork_put(void) ++{ ++ mutex_lock(&worker_mutex); ++ ++ glob_worker->refs--; ++ if (glob_worker->refs > 0) ++ goto out; ++ ++ swork_destroy(glob_worker); ++ glob_worker = NULL; ++out: ++ mutex_unlock(&worker_mutex); ++} ++EXPORT_SYMBOL_GPL(swork_put); diff --git a/debian/patches/features/all/rt/workqueue-distangle-from-rq-lock.patch b/debian/patches/features/all/rt/workqueue-distangle-from-rq-lock.patch new file mode 100644 index 000000000..b7dc32da2 --- /dev/null +++ b/debian/patches/features/all/rt/workqueue-distangle-from-rq-lock.patch @@ -0,0 +1,261 @@ +From: Thomas Gleixner +Date: Wed Jun 22 19:47:03 2011 +0200 +Subject: sched: Distangle worker accounting from rqlock + +The worker accounting for cpu bound workers is plugged into the core +scheduler code and the wakeup code. This is not a hard requirement and +can be avoided by keeping track of the state in the workqueue code +itself. + +Keep track of the sleeping state in the worker itself and call the +notifier before entering the core scheduler. There might be false +positives when the task is woken between that call and actually +scheduling, but that's not really different from scheduling and being +woken immediately after switching away. There is also no harm from +updating nr_running when the task returns from scheduling instead of +accounting it in the wakeup code. + +Signed-off-by: Thomas Gleixner +Cc: Peter Zijlstra +Cc: Tejun Heo +Cc: Jens Axboe +Cc: Linus Torvalds +Link: http://lkml.kernel.org/r/20110622174919.135236139@linutronix.de +Signed-off-by: Thomas Gleixner +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +--- + kernel/sched/core.c | 70 +++++++++----------------------------------- + kernel/workqueue.c | 55 ++++++++++++++-------------------- + kernel/workqueue_internal.h | 5 +-- + 3 files changed, 41 insertions(+), 89 deletions(-) + +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -1517,10 +1517,6 @@ static void ttwu_activate(struct rq *rq, + { + activate_task(rq, p, en_flags); + p->on_rq = TASK_ON_RQ_QUEUED; +- +- /* if a worker is waking up, notify workqueue */ +- if (p->flags & PF_WQ_WORKER) +- wq_worker_waking_up(p, cpu_of(rq)); + } + + /* +@@ -1797,42 +1793,6 @@ try_to_wake_up(struct task_struct *p, un + } + + /** +- * try_to_wake_up_local - try to wake up a local task with rq lock held +- * @p: the thread to be awakened +- * +- * Put @p on the run-queue if it's not already there. The caller must +- * ensure that this_rq() is locked, @p is bound to this_rq() and not +- * the current task. +- */ +-static void try_to_wake_up_local(struct task_struct *p) +-{ +- struct rq *rq = task_rq(p); +- +- if (WARN_ON_ONCE(rq != this_rq()) || +- WARN_ON_ONCE(p == current)) +- return; +- +- lockdep_assert_held(&rq->lock); +- +- if (!raw_spin_trylock(&p->pi_lock)) { +- raw_spin_unlock(&rq->lock); +- raw_spin_lock(&p->pi_lock); +- raw_spin_lock(&rq->lock); +- } +- +- if (!(p->state & TASK_NORMAL)) +- goto out; +- +- if (!task_on_rq_queued(p)) +- ttwu_activate(rq, p, ENQUEUE_WAKEUP); +- +- ttwu_do_wakeup(rq, p, 0); +- ttwu_stat(p, smp_processor_id(), 0); +-out: +- raw_spin_unlock(&p->pi_lock); +-} +- +-/** + * wake_up_process - Wake up a specific process + * @p: The process to be woken up. + * +@@ -2995,21 +2955,6 @@ static void __sched __schedule(void) + } else { + deactivate_task(rq, prev, DEQUEUE_SLEEP); + prev->on_rq = 0; +- +- /* +- * If a worker went to sleep, notify and ask workqueue +- * whether it wants to wake up a task to maintain +- * concurrency. +- * Only call wake up if prev isn't blocked on a sleeping +- * spin lock. +- */ +- if (prev->flags & PF_WQ_WORKER && !prev->saved_state) { +- struct task_struct *to_wakeup; +- +- to_wakeup = wq_worker_sleeping(prev, cpu); +- if (to_wakeup) +- try_to_wake_up_local(to_wakeup); +- } + } + switch_count = &prev->nvcsw; + } +@@ -3041,6 +2986,14 @@ static inline void sched_submit_work(str + { + if (!tsk->state || tsk_is_pi_blocked(tsk)) + return; ++ ++ /* ++ * If a worker went to sleep, notify and ask workqueue whether ++ * it wants to wake up a task to maintain concurrency. ++ */ ++ if (tsk->flags & PF_WQ_WORKER) ++ wq_worker_sleeping(tsk); ++ + /* + * If we are going to sleep and we have plugged IO queued, + * make sure to submit it to avoid deadlocks. +@@ -3049,6 +3002,12 @@ static inline void sched_submit_work(str + blk_schedule_flush_plug(tsk); + } + ++static void sched_update_worker(struct task_struct *tsk) ++{ ++ if (tsk->flags & PF_WQ_WORKER) ++ wq_worker_running(tsk); ++} ++ + asmlinkage __visible void __sched schedule(void) + { + struct task_struct *tsk = current; +@@ -3057,6 +3016,7 @@ asmlinkage __visible void __sched schedu + do { + __schedule(); + } while (need_resched()); ++ sched_update_worker(tsk); + } + EXPORT_SYMBOL(schedule); + +--- a/kernel/workqueue.c ++++ b/kernel/workqueue.c +@@ -804,44 +804,31 @@ static void wake_up_worker(struct worker + } + + /** +- * wq_worker_waking_up - a worker is waking up +- * @task: task waking up +- * @cpu: CPU @task is waking up to ++ * wq_worker_running - a worker is running again ++ * @task: task returning from sleep + * +- * This function is called during try_to_wake_up() when a worker is +- * being awoken. +- * +- * CONTEXT: +- * spin_lock_irq(rq->lock) ++ * This function is called when a worker returns from schedule() + */ +-void wq_worker_waking_up(struct task_struct *task, int cpu) ++void wq_worker_running(struct task_struct *task) + { + struct worker *worker = kthread_data(task); + +- if (!(worker->flags & WORKER_NOT_RUNNING)) { +- WARN_ON_ONCE(worker->pool->cpu != cpu); ++ if (!worker->sleeping) ++ return; ++ if (!(worker->flags & WORKER_NOT_RUNNING)) + atomic_inc(&worker->pool->nr_running); +- } ++ worker->sleeping = 0; + } + + /** + * wq_worker_sleeping - a worker is going to sleep + * @task: task going to sleep +- * @cpu: CPU in question, must be the current CPU number +- * +- * This function is called during schedule() when a busy worker is +- * going to sleep. Worker on the same cpu can be woken up by +- * returning pointer to its task. +- * +- * CONTEXT: +- * spin_lock_irq(rq->lock) +- * +- * Return: +- * Worker task on @cpu to wake up, %NULL if none. ++ * This function is called from schedule() when a busy worker is ++ * going to sleep. + */ +-struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu) ++void wq_worker_sleeping(struct task_struct *task) + { +- struct worker *worker = kthread_data(task), *to_wakeup = NULL; ++ struct worker *next, *worker = kthread_data(task); + struct worker_pool *pool; + + /* +@@ -850,14 +837,15 @@ struct task_struct *wq_worker_sleeping(s + * checking NOT_RUNNING. + */ + if (worker->flags & WORKER_NOT_RUNNING) +- return NULL; ++ return; + + pool = worker->pool; + +- /* this can only happen on the local cpu */ +- if (WARN_ON_ONCE(cpu != raw_smp_processor_id() || pool->cpu != cpu)) +- return NULL; ++ if (WARN_ON_ONCE(worker->sleeping)) ++ return; + ++ worker->sleeping = 1; ++ spin_lock_irq(&pool->lock); + /* + * The counterpart of the following dec_and_test, implied mb, + * worklist not empty test sequence is in insert_work(). +@@ -870,9 +858,12 @@ struct task_struct *wq_worker_sleeping(s + * lock is safe. + */ + if (atomic_dec_and_test(&pool->nr_running) && +- !list_empty(&pool->worklist)) +- to_wakeup = first_idle_worker(pool); +- return to_wakeup ? to_wakeup->task : NULL; ++ !list_empty(&pool->worklist)) { ++ next = first_idle_worker(pool); ++ if (next) ++ wake_up_process(next->task); ++ } ++ spin_unlock_irq(&pool->lock); + } + + /** +--- a/kernel/workqueue_internal.h ++++ b/kernel/workqueue_internal.h +@@ -43,6 +43,7 @@ struct worker { + unsigned long last_active; /* L: last active timestamp */ + unsigned int flags; /* X: flags */ + int id; /* I: worker id */ ++ int sleeping; /* None */ + + /* + * Opaque string set with work_set_desc(). Printed out with task +@@ -68,7 +69,7 @@ static inline struct worker *current_wq_ + * Scheduler hooks for concurrency managed workqueue. Only to be used from + * sched/core.c and workqueue.c. + */ +-void wq_worker_waking_up(struct task_struct *task, int cpu); +-struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu); ++void wq_worker_running(struct task_struct *task); ++void wq_worker_sleeping(struct task_struct *task); + + #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ diff --git a/debian/patches/features/all/rt/workqueue-prevent-deadlock-stall.patch b/debian/patches/features/all/rt/workqueue-prevent-deadlock-stall.patch new file mode 100644 index 000000000..d85815fe1 --- /dev/null +++ b/debian/patches/features/all/rt/workqueue-prevent-deadlock-stall.patch @@ -0,0 +1,201 @@ +Subject: workqueue: Prevent deadlock/stall on RT +From: Thomas Gleixner +Date: Fri, 27 Jun 2014 16:24:52 +0200 (CEST) +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Austin reported a XFS deadlock/stall on RT where scheduled work gets +never exececuted and tasks are waiting for each other for ever. + +The underlying problem is the modification of the RT code to the +handling of workers which are about to go to sleep. In mainline a +worker thread which goes to sleep wakes an idle worker if there is +more work to do. This happens from the guts of the schedule() +function. On RT this must be outside and the accessed data structures +are not protected against scheduling due to the spinlock to rtmutex +conversion. So the naive solution to this was to move the code outside +of the scheduler and protect the data structures by the pool +lock. That approach turned out to be a little naive as we cannot call +into that code when the thread blocks on a lock, as it is not allowed +to block on two locks in parallel. So we dont call into the worker +wakeup magic when the worker is blocked on a lock, which causes the +deadlock/stall observed by Austin and Mike. + +Looking deeper into that worker code it turns out that the only +relevant data structure which needs to be protected is the list of +idle workers which can be woken up. + +So the solution is to protect the list manipulation operations with +preempt_enable/disable pairs on RT and call unconditionally into the +worker code even when the worker is blocked on a lock. The preemption +protection is safe as there is nothing which can fiddle with the list +outside of thread context. + +Reported-and_tested-by: Austin Schuh +Reported-and_tested-by: Mike Galbraith +Signed-off-by: Thomas Gleixner +Link: http://vger.kernel.org/r/alpine.DEB.2.10.1406271249510.5170@nanos +Cc: Richard Weinberger +Cc: Steven Rostedt + +--- + kernel/sched/core.c | 7 ++++- + kernel/workqueue.c | 61 ++++++++++++++++++++++++++++++++++++++++------------ + 2 files changed, 53 insertions(+), 15 deletions(-) + +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -3022,9 +3022,8 @@ static void __sched __schedule(void) + + static inline void sched_submit_work(struct task_struct *tsk) + { +- if (!tsk->state || tsk_is_pi_blocked(tsk)) ++ if (!tsk->state) + return; +- + /* + * If a worker went to sleep, notify and ask workqueue whether + * it wants to wake up a task to maintain concurrency. +@@ -3032,6 +3031,10 @@ static inline void sched_submit_work(str + if (tsk->flags & PF_WQ_WORKER) + wq_worker_sleeping(tsk); + ++ ++ if (tsk_is_pi_blocked(tsk)) ++ return; ++ + /* + * If we are going to sleep and we have plugged IO queued, + * make sure to submit it to avoid deadlocks. +--- a/kernel/workqueue.c ++++ b/kernel/workqueue.c +@@ -123,6 +123,11 @@ enum { + * cpu or grabbing pool->lock is enough for read access. If + * POOL_DISASSOCIATED is set, it's identical to L. + * ++ * On RT we need the extra protection via rt_lock_idle_list() for ++ * the list manipulations against read access from ++ * wq_worker_sleeping(). All other places are nicely serialized via ++ * pool->lock. ++ * + * A: pool->attach_mutex protected. + * + * PL: wq_pool_mutex protected. +@@ -405,6 +410,31 @@ static void workqueue_sysfs_unregister(s + if (({ assert_rcu_or_wq_mutex(wq); false; })) { } \ + else + ++#ifdef CONFIG_PREEMPT_RT_BASE ++static inline void rt_lock_idle_list(struct worker_pool *pool) ++{ ++ preempt_disable(); ++} ++static inline void rt_unlock_idle_list(struct worker_pool *pool) ++{ ++ preempt_enable(); ++} ++static inline void sched_lock_idle_list(struct worker_pool *pool) { } ++static inline void sched_unlock_idle_list(struct worker_pool *pool) { } ++#else ++static inline void rt_lock_idle_list(struct worker_pool *pool) { } ++static inline void rt_unlock_idle_list(struct worker_pool *pool) { } ++static inline void sched_lock_idle_list(struct worker_pool *pool) ++{ ++ spin_lock_irq(&pool->lock); ++} ++static inline void sched_unlock_idle_list(struct worker_pool *pool) ++{ ++ spin_unlock_irq(&pool->lock); ++} ++#endif ++ ++ + #ifdef CONFIG_DEBUG_OBJECTS_WORK + + static struct debug_obj_descr work_debug_descr; +@@ -797,10 +827,16 @@ static struct worker *first_idle_worker( + */ + static void wake_up_worker(struct worker_pool *pool) + { +- struct worker *worker = first_idle_worker(pool); ++ struct worker *worker; ++ ++ rt_lock_idle_list(pool); ++ ++ worker = first_idle_worker(pool); + + if (likely(worker)) + wake_up_process(worker->task); ++ ++ rt_unlock_idle_list(pool); + } + + /** +@@ -828,7 +864,7 @@ void wq_worker_running(struct task_struc + */ + void wq_worker_sleeping(struct task_struct *task) + { +- struct worker *next, *worker = kthread_data(task); ++ struct worker *worker = kthread_data(task); + struct worker_pool *pool; + + /* +@@ -845,25 +881,18 @@ void wq_worker_sleeping(struct task_stru + return; + + worker->sleeping = 1; +- spin_lock_irq(&pool->lock); ++ + /* + * The counterpart of the following dec_and_test, implied mb, + * worklist not empty test sequence is in insert_work(). + * Please read comment there. +- * +- * NOT_RUNNING is clear. This means that we're bound to and +- * running on the local cpu w/ rq lock held and preemption +- * disabled, which in turn means that none else could be +- * manipulating idle_list, so dereferencing idle_list without pool +- * lock is safe. + */ + if (atomic_dec_and_test(&pool->nr_running) && + !list_empty(&pool->worklist)) { +- next = first_idle_worker(pool); +- if (next) +- wake_up_process(next->task); ++ sched_lock_idle_list(pool); ++ wake_up_worker(pool); ++ sched_unlock_idle_list(pool); + } +- spin_unlock_irq(&pool->lock); + } + + /** +@@ -1554,7 +1583,9 @@ static void worker_enter_idle(struct wor + worker->last_active = jiffies; + + /* idle_list is LIFO */ ++ rt_lock_idle_list(pool); + list_add(&worker->entry, &pool->idle_list); ++ rt_unlock_idle_list(pool); + + if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) + mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); +@@ -1587,7 +1618,9 @@ static void worker_leave_idle(struct wor + return; + worker_clr_flags(worker, WORKER_IDLE); + pool->nr_idle--; ++ rt_lock_idle_list(pool); + list_del_init(&worker->entry); ++ rt_unlock_idle_list(pool); + } + + static struct worker *alloc_worker(int node) +@@ -1755,7 +1788,9 @@ static void destroy_worker(struct worker + pool->nr_workers--; + pool->nr_idle--; + ++ rt_lock_idle_list(pool); + list_del_init(&worker->entry); ++ rt_unlock_idle_list(pool); + worker->flags |= WORKER_DIE; + wake_up_process(worker->task); + } diff --git a/debian/patches/features/all/rt/workqueue-use-locallock.patch b/debian/patches/features/all/rt/workqueue-use-locallock.patch new file mode 100644 index 000000000..73efd0c45 --- /dev/null +++ b/debian/patches/features/all/rt/workqueue-use-locallock.patch @@ -0,0 +1,145 @@ +Subject: workqueue: Use local irq lock instead of irq disable regions +From: Thomas Gleixner +Date: Sun, 17 Jul 2011 21:42:26 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Use a local_irq_lock as a replacement for irq off regions. We keep the +semantic of irq-off in regard to the pool->lock and remain preemptible. + +Signed-off-by: Thomas Gleixner +--- + kernel/workqueue.c | 31 +++++++++++++++++-------------- + 1 file changed, 17 insertions(+), 14 deletions(-) + +--- a/kernel/workqueue.c ++++ b/kernel/workqueue.c +@@ -48,6 +48,7 @@ + #include + #include + #include ++#include + + #include "workqueue_internal.h" + +@@ -329,6 +330,8 @@ EXPORT_SYMBOL_GPL(system_power_efficient + struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly; + EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); + ++static DEFINE_LOCAL_IRQ_LOCK(pendingb_lock); ++ + static int worker_thread(void *__worker); + static void copy_workqueue_attrs(struct workqueue_attrs *to, + const struct workqueue_attrs *from); +@@ -1065,9 +1068,9 @@ static void put_pwq_unlocked(struct pool + * As both pwqs and pools are RCU protected, the + * following lock operations are safe. + */ +- spin_lock_irq(&pwq->pool->lock); ++ local_spin_lock_irq(pendingb_lock, &pwq->pool->lock); + put_pwq(pwq); +- spin_unlock_irq(&pwq->pool->lock); ++ local_spin_unlock_irq(pendingb_lock, &pwq->pool->lock); + } + } + +@@ -1169,7 +1172,7 @@ static int try_to_grab_pending(struct wo + struct worker_pool *pool; + struct pool_workqueue *pwq; + +- local_irq_save(*flags); ++ local_lock_irqsave(pendingb_lock, *flags); + + /* try to steal the timer if it exists */ + if (is_dwork) { +@@ -1233,7 +1236,7 @@ static int try_to_grab_pending(struct wo + spin_unlock(&pool->lock); + fail: + rcu_read_unlock(); +- local_irq_restore(*flags); ++ local_unlock_irqrestore(pendingb_lock, *flags); + if (work_is_canceling(work)) + return -ENOENT; + cpu_relax(); +@@ -1305,7 +1308,7 @@ static void __queue_work(int cpu, struct + * queued or lose PENDING. Grabbing PENDING and queueing should + * happen with IRQ disabled. + */ +- WARN_ON_ONCE(!irqs_disabled()); ++ WARN_ON_ONCE_NONRT(!irqs_disabled()); + + debug_work_activate(work); + +@@ -1410,14 +1413,14 @@ bool queue_work_on(int cpu, struct workq + bool ret = false; + unsigned long flags; + +- local_irq_save(flags); ++ local_lock_irqsave(pendingb_lock,flags); + + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + __queue_work(cpu, wq, work); + ret = true; + } + +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + return ret; + } + EXPORT_SYMBOL(queue_work_on); +@@ -1484,14 +1487,14 @@ bool queue_delayed_work_on(int cpu, stru + unsigned long flags; + + /* read the comment in __queue_work() */ +- local_irq_save(flags); ++ local_lock_irqsave(pendingb_lock, flags); + + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + __queue_delayed_work(cpu, wq, dwork, delay); + ret = true; + } + +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + return ret; + } + EXPORT_SYMBOL(queue_delayed_work_on); +@@ -1526,7 +1529,7 @@ bool mod_delayed_work_on(int cpu, struct + + if (likely(ret >= 0)) { + __queue_delayed_work(cpu, wq, dwork, delay); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + } + + /* -ENOENT from try_to_grab_pending() becomes %true */ +@@ -2802,7 +2805,7 @@ static bool __cancel_work_timer(struct w + + /* tell other tasks trying to grab @work to back off */ + mark_work_canceling(work); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + + flush_work(work); + clear_work_data(work); +@@ -2857,10 +2860,10 @@ EXPORT_SYMBOL_GPL(cancel_work_sync); + */ + bool flush_delayed_work(struct delayed_work *dwork) + { +- local_irq_disable(); ++ local_lock_irq(pendingb_lock); + if (del_timer_sync(&dwork->timer)) + __queue_work(dwork->cpu, dwork->wq, &dwork->work); +- local_irq_enable(); ++ local_unlock_irq(pendingb_lock); + return flush_work(&dwork->work); + } + EXPORT_SYMBOL(flush_delayed_work); +@@ -2895,7 +2898,7 @@ bool cancel_delayed_work(struct delayed_ + + set_work_pool_and_clear_pending(&dwork->work, + get_work_pool_id(&dwork->work)); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + return ret; + } + EXPORT_SYMBOL(cancel_delayed_work); diff --git a/debian/patches/features/all/rt/workqueue-use-rcu.patch b/debian/patches/features/all/rt/workqueue-use-rcu.patch new file mode 100644 index 000000000..3a6809830 --- /dev/null +++ b/debian/patches/features/all/rt/workqueue-use-rcu.patch @@ -0,0 +1,343 @@ +Subject: workqueue: Use normal rcu +From: Thomas Gleixner +Date: Wed, 24 Jul 2013 15:26:54 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +There is no need for sched_rcu. The undocumented reason why sched_rcu +is used is to avoid a few explicit rcu_read_lock()/unlock() pairs by +abusing the fact that sched_rcu reader side critical sections are also +protected by preempt or irq disabled regions. + +Signed-off-by: Thomas Gleixner +--- + kernel/workqueue.c | 92 +++++++++++++++++++++++++++++------------------------ + 1 file changed, 51 insertions(+), 41 deletions(-) + +--- a/kernel/workqueue.c ++++ b/kernel/workqueue.c +@@ -125,11 +125,11 @@ enum { + * + * PL: wq_pool_mutex protected. + * +- * PR: wq_pool_mutex protected for writes. Sched-RCU protected for reads. ++ * PR: wq_pool_mutex protected for writes. RCU protected for reads. + * + * WQ: wq->mutex protected. + * +- * WR: wq->mutex protected for writes. Sched-RCU protected for reads. ++ * WR: wq->mutex protected for writes. RCU protected for reads. + * + * MD: wq_mayday_lock protected. + */ +@@ -178,7 +178,7 @@ struct worker_pool { + atomic_t nr_running ____cacheline_aligned_in_smp; + + /* +- * Destruction of pool is sched-RCU protected to allow dereferences ++ * Destruction of pool is RCU protected to allow dereferences + * from get_work_pool(). + */ + struct rcu_head rcu; +@@ -207,7 +207,7 @@ struct pool_workqueue { + /* + * Release of unbound pwq is punted to system_wq. See put_pwq() + * and pwq_unbound_release_workfn() for details. pool_workqueue +- * itself is also sched-RCU protected so that the first pwq can be ++ * itself is also RCU protected so that the first pwq can be + * determined without grabbing wq->mutex. + */ + struct work_struct unbound_release_work; +@@ -338,14 +338,14 @@ static void workqueue_sysfs_unregister(s + #include + + #define assert_rcu_or_pool_mutex() \ +- rcu_lockdep_assert(rcu_read_lock_sched_held() || \ ++ rcu_lockdep_assert(rcu_read_lock_held() || \ + lockdep_is_held(&wq_pool_mutex), \ +- "sched RCU or wq_pool_mutex should be held") ++ "RCU or wq_pool_mutex should be held") + + #define assert_rcu_or_wq_mutex(wq) \ +- rcu_lockdep_assert(rcu_read_lock_sched_held() || \ ++ rcu_lockdep_assert(rcu_read_lock_held() || \ + lockdep_is_held(&wq->mutex), \ +- "sched RCU or wq->mutex should be held") ++ "RCU or wq->mutex should be held") + + #define for_each_cpu_worker_pool(pool, cpu) \ + for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ +@@ -357,7 +357,7 @@ static void workqueue_sysfs_unregister(s + * @pool: iteration cursor + * @pi: integer used for iteration + * +- * This must be called either with wq_pool_mutex held or sched RCU read ++ * This must be called either with wq_pool_mutex held or RCU read + * locked. If the pool needs to be used beyond the locking in effect, the + * caller is responsible for guaranteeing that the pool stays online. + * +@@ -389,7 +389,7 @@ static void workqueue_sysfs_unregister(s + * @pwq: iteration cursor + * @wq: the target workqueue + * +- * This must be called either with wq->mutex held or sched RCU read locked. ++ * This must be called either with wq->mutex held or RCU read locked. + * If the pwq needs to be used beyond the locking in effect, the caller is + * responsible for guaranteeing that the pwq stays online. + * +@@ -551,7 +551,7 @@ static int worker_pool_assign_id(struct + * @wq: the target workqueue + * @node: the node ID + * +- * This must be called either with pwq_lock held or sched RCU read locked. ++ * This must be called either with pwq_lock held or RCU read locked. + * If the pwq needs to be used beyond the locking in effect, the caller is + * responsible for guaranteeing that the pwq stays online. + * +@@ -655,8 +655,8 @@ static struct pool_workqueue *get_work_p + * @work: the work item of interest + * + * Pools are created and destroyed under wq_pool_mutex, and allows read +- * access under sched-RCU read lock. As such, this function should be +- * called under wq_pool_mutex or with preemption disabled. ++ * access under RCU read lock. As such, this function should be ++ * called under wq_pool_mutex or inside of a rcu_read_lock() region. + * + * All fields of the returned pool are accessible as long as the above + * mentioned locking is in effect. If the returned pool needs to be used +@@ -1062,7 +1062,7 @@ static void put_pwq_unlocked(struct pool + { + if (pwq) { + /* +- * As both pwqs and pools are sched-RCU protected, the ++ * As both pwqs and pools are RCU protected, the + * following lock operations are safe. + */ + spin_lock_irq(&pwq->pool->lock); +@@ -1188,6 +1188,7 @@ static int try_to_grab_pending(struct wo + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) + return 0; + ++ rcu_read_lock(); + /* + * The queueing is in progress, or it is already queued. Try to + * steal it from ->worklist without clearing WORK_STRUCT_PENDING. +@@ -1226,10 +1227,12 @@ static int try_to_grab_pending(struct wo + set_work_pool_and_keep_pending(work, pool->id); + + spin_unlock(&pool->lock); ++ rcu_read_unlock(); + return 1; + } + spin_unlock(&pool->lock); + fail: ++ rcu_read_unlock(); + local_irq_restore(*flags); + if (work_is_canceling(work)) + return -ENOENT; +@@ -1310,6 +1313,8 @@ static void __queue_work(int cpu, struct + if (unlikely(wq->flags & __WQ_DRAINING) && + WARN_ON_ONCE(!is_chained_work(wq))) + return; ++ ++ rcu_read_lock(); + retry: + if (req_cpu == WORK_CPU_UNBOUND) + cpu = raw_smp_processor_id(); +@@ -1366,10 +1371,8 @@ static void __queue_work(int cpu, struct + /* pwq determined, queue */ + trace_workqueue_queue_work(req_cpu, pwq, work); + +- if (WARN_ON(!list_empty(&work->entry))) { +- spin_unlock(&pwq->pool->lock); +- return; +- } ++ if (WARN_ON(!list_empty(&work->entry))) ++ goto out; + + pwq->nr_in_flight[pwq->work_color]++; + work_flags = work_color_to_flags(pwq->work_color); +@@ -1385,7 +1388,9 @@ static void __queue_work(int cpu, struct + + insert_work(pwq, work, worklist, work_flags); + ++out: + spin_unlock(&pwq->pool->lock); ++ rcu_read_unlock(); + } + + /** +@@ -2672,14 +2677,14 @@ static bool start_flush_work(struct work + + might_sleep(); + +- local_irq_disable(); ++ rcu_read_lock(); + pool = get_work_pool(work); + if (!pool) { +- local_irq_enable(); ++ rcu_read_unlock(); + return false; + } + +- spin_lock(&pool->lock); ++ spin_lock_irq(&pool->lock); + /* see the comment in try_to_grab_pending() with the same code */ + pwq = get_work_pwq(work); + if (pwq) { +@@ -2706,10 +2711,11 @@ static bool start_flush_work(struct work + else + lock_map_acquire_read(&pwq->wq->lockdep_map); + lock_map_release(&pwq->wq->lockdep_map); +- ++ rcu_read_unlock(); + return true; + already_gone: + spin_unlock_irq(&pool->lock); ++ rcu_read_unlock(); + return false; + } + +@@ -3147,7 +3153,7 @@ static void rcu_free_pool(struct rcu_hea + * put_unbound_pool - put a worker_pool + * @pool: worker_pool to put + * +- * Put @pool. If its refcnt reaches zero, it gets destroyed in sched-RCU ++ * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU + * safe manner. get_unbound_pool() calls this function on its failure path + * and this function should be able to release pools which went through, + * successfully or not, init_worker_pool(). +@@ -3201,8 +3207,8 @@ static void put_unbound_pool(struct work + del_timer_sync(&pool->idle_timer); + del_timer_sync(&pool->mayday_timer); + +- /* sched-RCU protected to allow dereferences from get_work_pool() */ +- call_rcu_sched(&pool->rcu, rcu_free_pool); ++ /* RCU protected to allow dereferences from get_work_pool() */ ++ call_rcu(&pool->rcu, rcu_free_pool); + } + + /** +@@ -3307,14 +3313,14 @@ static void pwq_unbound_release_workfn(s + put_unbound_pool(pool); + mutex_unlock(&wq_pool_mutex); + +- call_rcu_sched(&pwq->rcu, rcu_free_pwq); ++ call_rcu(&pwq->rcu, rcu_free_pwq); + + /* + * If we're the last pwq going away, @wq is already dead and no one + * is gonna access it anymore. Schedule RCU free. + */ + if (is_last) +- call_rcu_sched(&wq->rcu, rcu_free_wq); ++ call_rcu(&wq->rcu, rcu_free_wq); + } + + /** +@@ -3920,7 +3926,7 @@ void destroy_workqueue(struct workqueue_ + * The base ref is never dropped on per-cpu pwqs. Directly + * schedule RCU free. + */ +- call_rcu_sched(&wq->rcu, rcu_free_wq); ++ call_rcu(&wq->rcu, rcu_free_wq); + } else { + /* + * We're the sole accessor of @wq at this point. Directly +@@ -4013,7 +4019,8 @@ bool workqueue_congested(int cpu, struct + struct pool_workqueue *pwq; + bool ret; + +- rcu_read_lock_sched(); ++ rcu_read_lock(); ++ preempt_disable(); + + if (cpu == WORK_CPU_UNBOUND) + cpu = smp_processor_id(); +@@ -4024,7 +4031,8 @@ bool workqueue_congested(int cpu, struct + pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); + + ret = !list_empty(&pwq->delayed_works); +- rcu_read_unlock_sched(); ++ preempt_enable(); ++ rcu_read_unlock(); + + return ret; + } +@@ -4050,15 +4058,15 @@ unsigned int work_busy(struct work_struc + if (work_pending(work)) + ret |= WORK_BUSY_PENDING; + +- local_irq_save(flags); ++ rcu_read_lock(); + pool = get_work_pool(work); + if (pool) { +- spin_lock(&pool->lock); ++ spin_lock_irqsave(&pool->lock, flags); + if (find_worker_executing_work(pool, work)) + ret |= WORK_BUSY_RUNNING; +- spin_unlock(&pool->lock); ++ spin_unlock_irqrestore(&pool->lock, flags); + } +- local_irq_restore(flags); ++ rcu_read_unlock(); + + return ret; + } +@@ -4247,7 +4255,7 @@ void show_workqueue_state(void) + unsigned long flags; + int pi; + +- rcu_read_lock_sched(); ++ rcu_read_lock(); + + pr_info("Showing busy workqueues and worker pools:\n"); + +@@ -4298,7 +4306,7 @@ void show_workqueue_state(void) + spin_unlock_irqrestore(&pool->lock, flags); + } + +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); + } + + /* +@@ -4648,16 +4656,16 @@ bool freeze_workqueues_busy(void) + * nr_active is monotonically decreasing. It's safe + * to peek without lock. + */ +- rcu_read_lock_sched(); ++ rcu_read_lock(); + for_each_pwq(pwq, wq) { + WARN_ON_ONCE(pwq->nr_active < 0); + if (pwq->nr_active) { + busy = true; +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); + goto out_unlock; + } + } +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); + } + out_unlock: + mutex_unlock(&wq_pool_mutex); +@@ -4771,7 +4779,8 @@ static ssize_t wq_pool_ids_show(struct d + const char *delim = ""; + int node, written = 0; + +- rcu_read_lock_sched(); ++ get_online_cpus(); ++ rcu_read_lock(); + for_each_node(node) { + written += scnprintf(buf + written, PAGE_SIZE - written, + "%s%d:%d", delim, node, +@@ -4779,7 +4788,8 @@ static ssize_t wq_pool_ids_show(struct d + delim = " "; + } + written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); ++ put_online_cpus(); + + return written; + } diff --git a/debian/patches/features/all/rt/x86-UV-raw_spinlock-conversion.patch b/debian/patches/features/all/rt/x86-UV-raw_spinlock-conversion.patch new file mode 100644 index 000000000..927f93db8 --- /dev/null +++ b/debian/patches/features/all/rt/x86-UV-raw_spinlock-conversion.patch @@ -0,0 +1,245 @@ +From: Mike Galbraith +Date: Sun, 2 Nov 2014 08:31:37 +0100 +Subject: x86: UV: raw_spinlock conversion +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Shrug. Lots of hobbyists have a beast in their basement, right? + + +Signed-off-by: Mike Galbraith +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/x86/include/asm/uv/uv_bau.h | 14 +++++++------- + arch/x86/include/asm/uv/uv_hub.h | 2 +- + arch/x86/kernel/apic/x2apic_uv_x.c | 2 +- + arch/x86/platform/uv/tlb_uv.c | 26 +++++++++++++------------- + arch/x86/platform/uv/uv_time.c | 21 +++++++++++++-------- + 5 files changed, 35 insertions(+), 30 deletions(-) + +--- a/arch/x86/include/asm/uv/uv_bau.h ++++ b/arch/x86/include/asm/uv/uv_bau.h +@@ -615,9 +615,9 @@ struct bau_control { + cycles_t send_message; + cycles_t period_end; + cycles_t period_time; +- spinlock_t uvhub_lock; +- spinlock_t queue_lock; +- spinlock_t disable_lock; ++ raw_spinlock_t uvhub_lock; ++ raw_spinlock_t queue_lock; ++ raw_spinlock_t disable_lock; + /* tunables */ + int max_concurr; + int max_concurr_const; +@@ -776,15 +776,15 @@ static inline int atom_asr(short i, stru + * to be lowered below the current 'v'. atomic_add_unless can only stop + * on equal. + */ +-static inline int atomic_inc_unless_ge(spinlock_t *lock, atomic_t *v, int u) ++static inline int atomic_inc_unless_ge(raw_spinlock_t *lock, atomic_t *v, int u) + { +- spin_lock(lock); ++ raw_spin_lock(lock); + if (atomic_read(v) >= u) { +- spin_unlock(lock); ++ raw_spin_unlock(lock); + return 0; + } + atomic_inc(v); +- spin_unlock(lock); ++ raw_spin_unlock(lock); + return 1; + } + +--- a/arch/x86/include/asm/uv/uv_hub.h ++++ b/arch/x86/include/asm/uv/uv_hub.h +@@ -492,7 +492,7 @@ struct uv_blade_info { + unsigned short nr_online_cpus; + unsigned short pnode; + short memory_nid; +- spinlock_t nmi_lock; /* obsolete, see uv_hub_nmi */ ++ raw_spinlock_t nmi_lock; /* obsolete, see uv_hub_nmi */ + unsigned long nmi_count; /* obsolete, see uv_hub_nmi */ + }; + extern struct uv_blade_info *uv_blade_info; +--- a/arch/x86/kernel/apic/x2apic_uv_x.c ++++ b/arch/x86/kernel/apic/x2apic_uv_x.c +@@ -949,7 +949,7 @@ void __init uv_system_init(void) + uv_blade_info[blade].pnode = pnode; + uv_blade_info[blade].nr_possible_cpus = 0; + uv_blade_info[blade].nr_online_cpus = 0; +- spin_lock_init(&uv_blade_info[blade].nmi_lock); ++ raw_spin_lock_init(&uv_blade_info[blade].nmi_lock); + min_pnode = min(pnode, min_pnode); + max_pnode = max(pnode, max_pnode); + blade++; +--- a/arch/x86/platform/uv/tlb_uv.c ++++ b/arch/x86/platform/uv/tlb_uv.c +@@ -714,9 +714,9 @@ static void destination_plugged(struct b + + quiesce_local_uvhub(hmaster); + +- spin_lock(&hmaster->queue_lock); ++ raw_spin_lock(&hmaster->queue_lock); + reset_with_ipi(&bau_desc->distribution, bcp); +- spin_unlock(&hmaster->queue_lock); ++ raw_spin_unlock(&hmaster->queue_lock); + + end_uvhub_quiesce(hmaster); + +@@ -736,9 +736,9 @@ static void destination_timeout(struct b + + quiesce_local_uvhub(hmaster); + +- spin_lock(&hmaster->queue_lock); ++ raw_spin_lock(&hmaster->queue_lock); + reset_with_ipi(&bau_desc->distribution, bcp); +- spin_unlock(&hmaster->queue_lock); ++ raw_spin_unlock(&hmaster->queue_lock); + + end_uvhub_quiesce(hmaster); + +@@ -759,7 +759,7 @@ static void disable_for_period(struct ba + cycles_t tm1; + + hmaster = bcp->uvhub_master; +- spin_lock(&hmaster->disable_lock); ++ raw_spin_lock(&hmaster->disable_lock); + if (!bcp->baudisabled) { + stat->s_bau_disabled++; + tm1 = get_cycles(); +@@ -772,7 +772,7 @@ static void disable_for_period(struct ba + } + } + } +- spin_unlock(&hmaster->disable_lock); ++ raw_spin_unlock(&hmaster->disable_lock); + } + + static void count_max_concurr(int stat, struct bau_control *bcp, +@@ -835,7 +835,7 @@ static void record_send_stats(cycles_t t + */ + static void uv1_throttle(struct bau_control *hmaster, struct ptc_stats *stat) + { +- spinlock_t *lock = &hmaster->uvhub_lock; ++ raw_spinlock_t *lock = &hmaster->uvhub_lock; + atomic_t *v; + + v = &hmaster->active_descriptor_count; +@@ -968,7 +968,7 @@ static int check_enable(struct bau_contr + struct bau_control *hmaster; + + hmaster = bcp->uvhub_master; +- spin_lock(&hmaster->disable_lock); ++ raw_spin_lock(&hmaster->disable_lock); + if (bcp->baudisabled && (get_cycles() >= bcp->set_bau_on_time)) { + stat->s_bau_reenabled++; + for_each_present_cpu(tcpu) { +@@ -980,10 +980,10 @@ static int check_enable(struct bau_contr + tbcp->period_giveups = 0; + } + } +- spin_unlock(&hmaster->disable_lock); ++ raw_spin_unlock(&hmaster->disable_lock); + return 0; + } +- spin_unlock(&hmaster->disable_lock); ++ raw_spin_unlock(&hmaster->disable_lock); + return -1; + } + +@@ -1901,9 +1901,9 @@ static void __init init_per_cpu_tunables + bcp->cong_reps = congested_reps; + bcp->disabled_period = sec_2_cycles(disabled_period); + bcp->giveup_limit = giveup_limit; +- spin_lock_init(&bcp->queue_lock); +- spin_lock_init(&bcp->uvhub_lock); +- spin_lock_init(&bcp->disable_lock); ++ raw_spin_lock_init(&bcp->queue_lock); ++ raw_spin_lock_init(&bcp->uvhub_lock); ++ raw_spin_lock_init(&bcp->disable_lock); + } + } + +--- a/arch/x86/platform/uv/uv_time.c ++++ b/arch/x86/platform/uv/uv_time.c +@@ -58,7 +58,7 @@ static DEFINE_PER_CPU(struct clock_event + + /* There is one of these allocated per node */ + struct uv_rtc_timer_head { +- spinlock_t lock; ++ raw_spinlock_t lock; + /* next cpu waiting for timer, local node relative: */ + int next_cpu; + /* number of cpus on this node: */ +@@ -178,7 +178,7 @@ static __init int uv_rtc_allocate_timers + uv_rtc_deallocate_timers(); + return -ENOMEM; + } +- spin_lock_init(&head->lock); ++ raw_spin_lock_init(&head->lock); + head->ncpus = uv_blade_nr_possible_cpus(bid); + head->next_cpu = -1; + blade_info[bid] = head; +@@ -232,7 +232,7 @@ static int uv_rtc_set_timer(int cpu, u64 + unsigned long flags; + int next_cpu; + +- spin_lock_irqsave(&head->lock, flags); ++ raw_spin_lock_irqsave(&head->lock, flags); + + next_cpu = head->next_cpu; + *t = expires; +@@ -244,12 +244,12 @@ static int uv_rtc_set_timer(int cpu, u64 + if (uv_setup_intr(cpu, expires)) { + *t = ULLONG_MAX; + uv_rtc_find_next_timer(head, pnode); +- spin_unlock_irqrestore(&head->lock, flags); ++ raw_spin_unlock_irqrestore(&head->lock, flags); + return -ETIME; + } + } + +- spin_unlock_irqrestore(&head->lock, flags); ++ raw_spin_unlock_irqrestore(&head->lock, flags); + return 0; + } + +@@ -268,7 +268,7 @@ static int uv_rtc_unset_timer(int cpu, i + unsigned long flags; + int rc = 0; + +- spin_lock_irqsave(&head->lock, flags); ++ raw_spin_lock_irqsave(&head->lock, flags); + + if ((head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t) || force) + rc = 1; +@@ -280,7 +280,7 @@ static int uv_rtc_unset_timer(int cpu, i + uv_rtc_find_next_timer(head, pnode); + } + +- spin_unlock_irqrestore(&head->lock, flags); ++ raw_spin_unlock_irqrestore(&head->lock, flags); + + return rc; + } +@@ -300,13 +300,18 @@ static int uv_rtc_unset_timer(int cpu, i + static cycle_t uv_read_rtc(struct clocksource *cs) + { + unsigned long offset; ++ cycle_t cycles; + ++ preempt_disable(); + if (uv_get_min_hub_revision_id() == 1) + offset = 0; + else + offset = (uv_blade_processor_id() * L1_CACHE_BYTES) % PAGE_SIZE; + +- return (cycle_t)uv_read_local_mmr(UVH_RTC | offset); ++ cycles = (cycle_t)uv_read_local_mmr(UVH_RTC | offset); ++ preempt_enable(); ++ ++ return cycles; + } + + /* diff --git a/debian/patches/features/all/rt/x86-crypto-reduce-preempt-disabled-regions.patch b/debian/patches/features/all/rt/x86-crypto-reduce-preempt-disabled-regions.patch new file mode 100644 index 000000000..cdec1a13d --- /dev/null +++ b/debian/patches/features/all/rt/x86-crypto-reduce-preempt-disabled-regions.patch @@ -0,0 +1,113 @@ +Subject: x86: crypto: Reduce preempt disabled regions +From: Peter Zijlstra +Date: Mon, 14 Nov 2011 18:19:27 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Restrict the preempt disabled regions to the actual floating point +operations and enable preemption for the administrative actions. + +This is necessary on RT to avoid that kfree and other operations are +called with preemption disabled. + +Reported-and-tested-by: Carsten Emde +Signed-off-by: Peter Zijlstra + +Signed-off-by: Thomas Gleixner +--- + arch/x86/crypto/aesni-intel_glue.c | 24 +++++++++++++----------- + 1 file changed, 13 insertions(+), 11 deletions(-) + +--- a/arch/x86/crypto/aesni-intel_glue.c ++++ b/arch/x86/crypto/aesni-intel_glue.c +@@ -382,14 +382,14 @@ static int ecb_encrypt(struct blkcipher_ + err = blkcipher_walk_virt(desc, &walk); + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_ecb_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, +- nbytes & AES_BLOCK_MASK); ++ nbytes & AES_BLOCK_MASK); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -406,14 +406,14 @@ static int ecb_decrypt(struct blkcipher_ + err = blkcipher_walk_virt(desc, &walk); + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_ecb_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -430,14 +430,14 @@ static int cbc_encrypt(struct blkcipher_ + err = blkcipher_walk_virt(desc, &walk); + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -454,14 +454,14 @@ static int cbc_decrypt(struct blkcipher_ + err = blkcipher_walk_virt(desc, &walk); + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -513,18 +513,20 @@ static int ctr_crypt(struct blkcipher_de + err = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE); + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) { ++ kernel_fpu_begin(); + aesni_ctr_enc_tfm(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } + if (walk.nbytes) { ++ kernel_fpu_begin(); + ctr_crypt_final(ctx, &walk); ++ kernel_fpu_end(); + err = blkcipher_walk_done(desc, &walk, 0); + } +- kernel_fpu_end(); + + return err; + } diff --git a/debian/patches/features/all/rt/x86-highmem-add-a-already-used-pte-check.patch b/debian/patches/features/all/rt/x86-highmem-add-a-already-used-pte-check.patch new file mode 100644 index 000000000..c2fd37585 --- /dev/null +++ b/debian/patches/features/all/rt/x86-highmem-add-a-already-used-pte-check.patch @@ -0,0 +1,23 @@ +From: Sebastian Andrzej Siewior +Date: Mon, 11 Mar 2013 17:09:55 +0100 +Subject: x86/highmem: Add a "already used pte" check +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +This is a copy from kmap_atomic_prot(). + +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/x86/mm/iomap_32.c | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/arch/x86/mm/iomap_32.c ++++ b/arch/x86/mm/iomap_32.c +@@ -66,6 +66,8 @@ void *kmap_atomic_prot_pfn(unsigned long + type = kmap_atomic_idx_push(); + idx = type + KM_TYPE_NR * smp_processor_id(); + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); ++ WARN_ON(!pte_none(*(kmap_pte - idx))); ++ + #ifdef CONFIG_PREEMPT_RT_FULL + current->kmap_pte[type] = pte; + #endif diff --git a/debian/patches/features/all/rt/x86-io-apic-migra-no-unmask.patch b/debian/patches/features/all/rt/x86-io-apic-migra-no-unmask.patch new file mode 100644 index 000000000..c5ac8e5fa --- /dev/null +++ b/debian/patches/features/all/rt/x86-io-apic-migra-no-unmask.patch @@ -0,0 +1,27 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:29:27 -0500 +Subject: x86/ioapic: Do not unmask io_apic when interrupt is in progress +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +With threaded interrupts we might see an interrupt in progress on +migration. Do not unmask it when this is the case. + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + arch/x86/kernel/apic/io_apic.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +--- a/arch/x86/kernel/apic/io_apic.c ++++ b/arch/x86/kernel/apic/io_apic.c +@@ -1891,7 +1891,8 @@ static bool io_apic_level_ack_pending(st + static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg) + { + /* If we are moving the irq we need to mask it */ +- if (unlikely(irqd_is_setaffinity_pending(data))) { ++ if (unlikely(irqd_is_setaffinity_pending(data) && ++ !irqd_irq_inprogress(data))) { + mask_ioapic(cfg); + return true; + } diff --git a/debian/patches/features/all/rt/x86-kvm-require-const-tsc-for-rt.patch b/debian/patches/features/all/rt/x86-kvm-require-const-tsc-for-rt.patch new file mode 100644 index 000000000..d1272e698 --- /dev/null +++ b/debian/patches/features/all/rt/x86-kvm-require-const-tsc-for-rt.patch @@ -0,0 +1,31 @@ +Subject: x86: kvm Require const tsc for RT +From: Thomas Gleixner +Date: Sun, 06 Nov 2011 12:26:18 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Non constant TSC is a nightmare on bare metal already, but with +virtualization it becomes a complete disaster because the workarounds +are horrible latency wise. That's also a preliminary for running RT in +a guest on top of a RT host. + +Signed-off-by: Thomas Gleixner +--- + arch/x86/kvm/x86.c | 7 +++++++ + 1 file changed, 7 insertions(+) + +--- a/arch/x86/kvm/x86.c ++++ b/arch/x86/kvm/x86.c +@@ -5813,6 +5813,13 @@ int kvm_arch_init(void *opaque) + goto out; + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { ++ printk(KERN_ERR "RT requires X86_FEATURE_CONSTANT_TSC\n"); ++ return -EOPNOTSUPP; ++ } ++#endif ++ + r = kvm_mmu_module_init(); + if (r) + goto out_free_percpu; diff --git a/debian/patches/features/all/rt/x86-mce-timer-hrtimer.patch b/debian/patches/features/all/rt/x86-mce-timer-hrtimer.patch new file mode 100644 index 000000000..df77bed1e --- /dev/null +++ b/debian/patches/features/all/rt/x86-mce-timer-hrtimer.patch @@ -0,0 +1,180 @@ +From: Thomas Gleixner +Date: Mon, 13 Dec 2010 16:33:39 +0100 +Subject: x86: Convert mce timer to hrtimer +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +mce_timer is started in atomic contexts of cpu bringup. This results +in might_sleep() warnings on RT. Convert mce_timer to a hrtimer to +avoid this. + +Signed-off-by: Thomas Gleixner +fold in: +|From: Mike Galbraith +|Date: Wed, 29 May 2013 13:52:13 +0200 +|Subject: [PATCH] x86/mce: fix mce timer interval +| +|Seems mce timer fire at the wrong frequency in -rt kernels since roughly +|forever due to 32 bit overflow. 3.8-rt is also missing a multiplier. +| +|Add missing us -> ns conversion and 32 bit overflow prevention. +| +|Signed-off-by: Mike Galbraith +|[bigeasy: use ULL instead of u64 cast] +|Signed-off-by: Sebastian Andrzej Siewior +--- + arch/x86/kernel/cpu/mcheck/mce.c | 52 +++++++++++++++------------------------ + 1 file changed, 20 insertions(+), 32 deletions(-) + +--- a/arch/x86/kernel/cpu/mcheck/mce.c ++++ b/arch/x86/kernel/cpu/mcheck/mce.c +@@ -41,6 +41,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -1267,7 +1268,7 @@ void mce_log_therm_throt_event(__u64 sta + static unsigned long check_interval = INITIAL_CHECK_INTERVAL; + + static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */ +-static DEFINE_PER_CPU(struct timer_list, mce_timer); ++static DEFINE_PER_CPU(struct hrtimer, mce_timer); + + static unsigned long mce_adjust_timer_default(unsigned long interval) + { +@@ -1276,32 +1277,18 @@ static unsigned long mce_adjust_timer_de + + static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default; + +-static void __restart_timer(struct timer_list *t, unsigned long interval) ++static enum hrtimer_restart __restart_timer(struct hrtimer *timer, unsigned long interval) + { +- unsigned long when = jiffies + interval; +- unsigned long flags; +- +- local_irq_save(flags); +- +- if (timer_pending(t)) { +- if (time_before(when, t->expires)) +- mod_timer_pinned(t, when); +- } else { +- t->expires = round_jiffies(when); +- add_timer_on(t, smp_processor_id()); +- } +- +- local_irq_restore(flags); ++ if (!interval) ++ return HRTIMER_NORESTART; ++ hrtimer_forward_now(timer, ns_to_ktime(jiffies_to_nsecs(interval))); ++ return HRTIMER_RESTART; + } + +-static void mce_timer_fn(unsigned long data) ++static enum hrtimer_restart mce_timer_fn(struct hrtimer *timer) + { +- struct timer_list *t = this_cpu_ptr(&mce_timer); +- int cpu = smp_processor_id(); + unsigned long iv; + +- WARN_ON(cpu != data); +- + iv = __this_cpu_read(mce_next_interval); + + if (mce_available(this_cpu_ptr(&cpu_info))) { +@@ -1324,7 +1311,7 @@ static void mce_timer_fn(unsigned long d + + done: + __this_cpu_write(mce_next_interval, iv); +- __restart_timer(t, iv); ++ return __restart_timer(timer, iv); + } + + /* +@@ -1332,7 +1319,7 @@ static void mce_timer_fn(unsigned long d + */ + void mce_timer_kick(unsigned long interval) + { +- struct timer_list *t = this_cpu_ptr(&mce_timer); ++ struct hrtimer *t = this_cpu_ptr(&mce_timer); + unsigned long iv = __this_cpu_read(mce_next_interval); + + __restart_timer(t, interval); +@@ -1347,7 +1334,7 @@ static void mce_timer_delete_all(void) + int cpu; + + for_each_online_cpu(cpu) +- del_timer_sync(&per_cpu(mce_timer, cpu)); ++ hrtimer_cancel(&per_cpu(mce_timer, cpu)); + } + + static void mce_do_trigger(struct work_struct *work) +@@ -1649,7 +1636,7 @@ static void __mcheck_cpu_init_vendor(str + } + } + +-static void mce_start_timer(unsigned int cpu, struct timer_list *t) ++static void mce_start_timer(unsigned int cpu, struct hrtimer *t) + { + unsigned long iv = check_interval * HZ; + +@@ -1658,16 +1645,17 @@ static void mce_start_timer(unsigned int + + per_cpu(mce_next_interval, cpu) = iv; + +- t->expires = round_jiffies(jiffies + iv); +- add_timer_on(t, cpu); ++ hrtimer_start_range_ns(t, ns_to_ktime(jiffies_to_usecs(iv) * 1000ULL), ++ 0, HRTIMER_MODE_REL_PINNED); + } + + static void __mcheck_cpu_init_timer(void) + { +- struct timer_list *t = this_cpu_ptr(&mce_timer); ++ struct hrtimer *t = this_cpu_ptr(&mce_timer); + unsigned int cpu = smp_processor_id(); + +- setup_timer(t, mce_timer_fn, cpu); ++ hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ t->function = mce_timer_fn; + mce_start_timer(cpu, t); + } + +@@ -2345,6 +2333,8 @@ static void mce_disable_cpu(void *h) + if (!mce_available(raw_cpu_ptr(&cpu_info))) + return; + ++ hrtimer_cancel(this_cpu_ptr(&mce_timer)); ++ + if (!(action & CPU_TASKS_FROZEN)) + cmci_clear(); + for (i = 0; i < mca_cfg.banks; i++) { +@@ -2371,6 +2361,7 @@ static void mce_reenable_cpu(void *h) + if (b->init) + wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl); + } ++ __mcheck_cpu_init_timer(); + } + + /* Get notified when a cpu comes on/off. Be hotplug friendly. */ +@@ -2378,7 +2369,6 @@ static int + mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) + { + unsigned int cpu = (unsigned long)hcpu; +- struct timer_list *t = &per_cpu(mce_timer, cpu); + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_ONLINE: +@@ -2398,11 +2388,9 @@ mce_cpu_callback(struct notifier_block * + break; + case CPU_DOWN_PREPARE: + smp_call_function_single(cpu, mce_disable_cpu, &action, 1); +- del_timer_sync(t); + break; + case CPU_DOWN_FAILED: + smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); +- mce_start_timer(cpu, t); + break; + } + diff --git a/debian/patches/features/all/rt/x86-mce-use-swait-queue-for-mce-wakeups.patch b/debian/patches/features/all/rt/x86-mce-use-swait-queue-for-mce-wakeups.patch new file mode 100644 index 000000000..b7d6f2bfc --- /dev/null +++ b/debian/patches/features/all/rt/x86-mce-use-swait-queue-for-mce-wakeups.patch @@ -0,0 +1,160 @@ +Subject: x86/mce: use swait queue for mce wakeups +From: Steven Rostedt +Date: Fri, 27 Feb 2015 15:20:37 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +We had a customer report a lockup on a 3.0-rt kernel that had the +following backtrace: + +[ffff88107fca3e80] rt_spin_lock_slowlock at ffffffff81499113 +[ffff88107fca3f40] rt_spin_lock at ffffffff81499a56 +[ffff88107fca3f50] __wake_up at ffffffff81043379 +[ffff88107fca3f80] mce_notify_irq at ffffffff81017328 +[ffff88107fca3f90] intel_threshold_interrupt at ffffffff81019508 +[ffff88107fca3fa0] smp_threshold_interrupt at ffffffff81019fc1 +[ffff88107fca3fb0] threshold_interrupt at ffffffff814a1853 + +It actually bugged because the lock was taken by the same owner that +already had that lock. What happened was the thread that was setting +itself on a wait queue had the lock when an MCE triggered. The MCE +interrupt does a wake up on its wait list and grabs the same lock. + +NOTE: THIS IS NOT A BUG ON MAINLINE + +Sorry for yelling, but as I Cc'd mainline maintainers I want them to +know that this is an PREEMPT_RT bug only. I only Cc'd them for advice. + +On PREEMPT_RT the wait queue locks are converted from normal +"spin_locks" into an rt_mutex (see the rt_spin_lock_slowlock above). +These are not to be taken by hard interrupt context. This usually isn't +a problem as most all interrupts in PREEMPT_RT are converted into +schedulable threads. Unfortunately that's not the case with the MCE irq. + +As wait queue locks are notorious for long hold times, we can not +convert them to raw_spin_locks without causing issues with -rt. But +Thomas has created a "simple-wait" structure that uses raw spin locks +which may have been a good fit. + +Unfortunately, wait queues are not the only issue, as the mce_notify_irq +also does a schedule_work(), which grabs the workqueue spin locks that +have the exact same issue. + +Thus, this patch I'm proposing is to move the actual work of the MCE +interrupt into a helper thread that gets woken up on the MCE interrupt +and does the work in a schedulable context. + +NOTE: THIS PATCH ONLY CHANGES THE BEHAVIOR WHEN PREEMPT_RT IS SET + +Oops, sorry for yelling again, but I want to stress that I keep the same +behavior of mainline when PREEMPT_RT is not set. Thus, this only changes +the MCE behavior when PREEMPT_RT is configured. + +Signed-off-by: Steven Rostedt +[bigeasy@linutronix: make mce_notify_work() a proper prototype, use + kthread_run()] +Signed-off-by: Sebastian Andrzej Siewior +[wagi: use work-simple framework to defer work to a kthread] +Signed-off-by: Daniel Wagner +--- + arch/x86/kernel/cpu/mcheck/mce.c | 68 ++++++++++++++++++++++++++++++++------- + 1 file changed, 56 insertions(+), 12 deletions(-) + +--- a/arch/x86/kernel/cpu/mcheck/mce.c ++++ b/arch/x86/kernel/cpu/mcheck/mce.c +@@ -42,6 +42,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -1344,6 +1345,56 @@ static void mce_do_trigger(struct work_s + + static DECLARE_WORK(mce_trigger_work, mce_do_trigger); + ++static void __mce_notify_work(struct swork_event *event) ++{ ++ /* Not more than two messages every minute */ ++ static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); ++ ++ /* wake processes polling /dev/mcelog */ ++ wake_up_interruptible(&mce_chrdev_wait); ++ ++ /* ++ * There is no risk of missing notifications because ++ * work_pending is always cleared before the function is ++ * executed. ++ */ ++ if (mce_helper[0] && !work_pending(&mce_trigger_work)) ++ schedule_work(&mce_trigger_work); ++ ++ if (__ratelimit(&ratelimit)) ++ pr_info(HW_ERR "Machine check events logged\n"); ++} ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++static bool notify_work_ready __read_mostly; ++static struct swork_event notify_work; ++ ++static int mce_notify_work_init(void) ++{ ++ int err; ++ ++ err = swork_get(); ++ if (err) ++ return err; ++ ++ INIT_SWORK(¬ify_work, __mce_notify_work); ++ notify_work_ready = true; ++ return 0; ++} ++ ++static void mce_notify_work(void) ++{ ++ if (notify_work_ready) ++ swork_queue(¬ify_work); ++} ++#else ++static void mce_notify_work(void) ++{ ++ __mce_notify_work(NULL); ++} ++static inline int mce_notify_work_init(void) { return 0; } ++#endif ++ + /* + * Notify the user(s) about new machine check events. + * Can be called from interrupt context, but not from machine check/NMI +@@ -1351,19 +1402,8 @@ static DECLARE_WORK(mce_trigger_work, mc + */ + int mce_notify_irq(void) + { +- /* Not more than two messages every minute */ +- static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); +- + if (test_and_clear_bit(0, &mce_need_notify)) { +- /* wake processes polling /dev/mcelog */ +- wake_up_interruptible(&mce_chrdev_wait); +- +- if (mce_helper[0]) +- schedule_work(&mce_trigger_work); +- +- if (__ratelimit(&ratelimit)) +- pr_info(HW_ERR "Machine check events logged\n"); +- ++ mce_notify_work(); + return 1; + } + return 0; +@@ -2429,6 +2469,10 @@ static __init int mcheck_init_device(voi + goto err_out; + } + ++ err = mce_notify_work_init(); ++ if (err) ++ goto err_out; ++ + if (!zalloc_cpumask_var(&mce_device_initialized, GFP_KERNEL)) { + err = -ENOMEM; + goto err_out; diff --git a/debian/patches/features/all/rt/x86-preempt-lazy.patch b/debian/patches/features/all/rt/x86-preempt-lazy.patch new file mode 100644 index 000000000..b6debd816 --- /dev/null +++ b/debian/patches/features/all/rt/x86-preempt-lazy.patch @@ -0,0 +1,171 @@ +Subject: x86: Support for lazy preemption +From: Thomas Gleixner +Date: Thu, 01 Nov 2012 11:03:47 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Implement the x86 pieces for lazy preempt. + +Signed-off-by: Thomas Gleixner +--- + arch/x86/Kconfig | 1 + + arch/x86/include/asm/thread_info.h | 6 ++++++ + arch/x86/kernel/asm-offsets.c | 2 ++ + arch/x86/kernel/entry_32.S | 20 ++++++++++++++++++-- + arch/x86/kernel/entry_64.S | 24 ++++++++++++++++++++---- + 5 files changed, 47 insertions(+), 6 deletions(-) + +--- a/arch/x86/Kconfig ++++ b/arch/x86/Kconfig +@@ -22,6 +22,7 @@ config X86_64 + ### Arch settings + config X86 + def_bool y ++ select HAVE_PREEMPT_LAZY + select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI + select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI + select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS +--- a/arch/x86/include/asm/thread_info.h ++++ b/arch/x86/include/asm/thread_info.h +@@ -55,6 +55,8 @@ struct thread_info { + __u32 status; /* thread synchronous flags */ + __u32 cpu; /* current CPU */ + int saved_preempt_count; ++ int preempt_lazy_count; /* 0 => lazy preemptable ++ <0 => BUG */ + mm_segment_t addr_limit; + void __user *sysenter_return; + unsigned int sig_on_uaccess_error:1; +@@ -95,6 +97,7 @@ struct thread_info { + #define TIF_SYSCALL_EMU 6 /* syscall emulation active */ + #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ + #define TIF_SECCOMP 8 /* secure computing */ ++#define TIF_NEED_RESCHED_LAZY 9 /* lazy rescheduling necessary */ + #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ + #define TIF_UPROBE 12 /* breakpointed or singlestepping */ + #define TIF_NOTSC 16 /* TSC is not accessible in userland */ +@@ -119,6 +122,7 @@ struct thread_info { + #define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) + #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) + #define _TIF_SECCOMP (1 << TIF_SECCOMP) ++#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) + #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) + #define _TIF_UPROBE (1 << TIF_UPROBE) + #define _TIF_NOTSC (1 << TIF_NOTSC) +@@ -168,6 +172,8 @@ struct thread_info { + #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) + #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) + ++#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) ++ + #define STACK_WARN (THREAD_SIZE/8) + + /* +--- a/arch/x86/kernel/asm-offsets.c ++++ b/arch/x86/kernel/asm-offsets.c +@@ -32,6 +32,7 @@ void common(void) { + OFFSET(TI_flags, thread_info, flags); + OFFSET(TI_status, thread_info, status); + OFFSET(TI_addr_limit, thread_info, addr_limit); ++ OFFSET(TI_preempt_lazy_count, thread_info, preempt_lazy_count); + + BLANK(); + OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx); +@@ -71,4 +72,5 @@ void common(void) { + + BLANK(); + DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); ++ DEFINE(_PREEMPT_ENABLED, PREEMPT_ENABLED); + } +--- a/arch/x86/kernel/entry_32.S ++++ b/arch/x86/kernel/entry_32.S +@@ -359,8 +359,24 @@ END(ret_from_exception) + ENTRY(resume_kernel) + DISABLE_INTERRUPTS(CLBR_ANY) + need_resched: ++ # preempt count == 0 + NEED_RS set? + cmpl $0,PER_CPU_VAR(__preempt_count) ++#ifndef CONFIG_PREEMPT_LAZY + jnz restore_all ++#else ++ jz test_int_off ++ ++ # atleast preempt count == 0 ? ++ cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) ++ jne restore_all ++ ++ cmpl $0,TI_preempt_lazy_count(%ebp) # non-zero preempt_lazy_count ? ++ jnz restore_all ++ ++ testl $_TIF_NEED_RESCHED_LAZY, TI_flags(%ebp) ++ jz restore_all ++test_int_off: ++#endif + testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off (exception path) ? + jz restore_all + call preempt_schedule_irq +@@ -594,7 +610,7 @@ ENDPROC(system_call) + ALIGN + RING0_PTREGS_FRAME # can't unwind into user space anyway + work_pending: +- testb $_TIF_NEED_RESCHED, %cl ++ testl $_TIF_NEED_RESCHED_MASK, %ecx + jz work_notifysig + work_resched: + call schedule +@@ -607,7 +623,7 @@ ENDPROC(system_call) + andl $_TIF_WORK_MASK, %ecx # is there any work to be done other + # than syscall tracing? + jz restore_all +- testb $_TIF_NEED_RESCHED, %cl ++ testl $_TIF_NEED_RESCHED_MASK, %ecx + jnz work_resched + + work_notifysig: # deal with pending signals and +--- a/arch/x86/kernel/entry_64.S ++++ b/arch/x86/kernel/entry_64.S +@@ -370,8 +370,8 @@ GLOBAL(int_with_check) + /* First do a reschedule test. */ + /* edx: work, edi: workmask */ + int_careful: +- bt $TIF_NEED_RESCHED,%edx +- jnc int_very_careful ++ testl $_TIF_NEED_RESCHED_MASK,%edx ++ jz int_very_careful + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) + pushq_cfi %rdi +@@ -776,7 +776,23 @@ retint_swapgs: /* return to user-space + bt $9,EFLAGS(%rsp) /* interrupts were off? */ + jnc 1f + 0: cmpl $0,PER_CPU_VAR(__preempt_count) ++#ifndef CONFIG_PREEMPT_LAZY + jnz 1f ++#else ++ jz do_preempt_schedule_irq ++ ++ # atleast preempt count == 0 ? ++ cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) ++ jnz 1f ++ ++ GET_THREAD_INFO(%rcx) ++ cmpl $0, TI_preempt_lazy_count(%rcx) ++ jnz 1f ++ ++ bt $TIF_NEED_RESCHED_LAZY,TI_flags(%rcx) ++ jnc 1f ++do_preempt_schedule_irq: ++#endif + call preempt_schedule_irq + jmp 0b + 1: +@@ -846,8 +862,8 @@ ENTRY(native_iret) + /* edi: workmask, edx: work */ + retint_careful: + CFI_RESTORE_STATE +- bt $TIF_NEED_RESCHED,%edx +- jnc retint_signal ++ testl $_TIF_NEED_RESCHED_MASK,%edx ++ jz retint_signal + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) + pushq_cfi %rdi diff --git a/debian/patches/features/all/rt/x86-stackprot-no-random-on-rt.patch b/debian/patches/features/all/rt/x86-stackprot-no-random-on-rt.patch new file mode 100644 index 000000000..99892b175 --- /dev/null +++ b/debian/patches/features/all/rt/x86-stackprot-no-random-on-rt.patch @@ -0,0 +1,48 @@ +From: Thomas Gleixner +Date: Thu, 16 Dec 2010 14:25:18 +0100 +Subject: x86: stackprotector: Avoid random pool on rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +CPU bringup calls into the random pool to initialize the stack +canary. During boot that works nicely even on RT as the might sleep +checks are disabled. During CPU hotplug the might sleep checks +trigger. Making the locks in random raw is a major PITA, so avoid the +call on RT is the only sensible solution. This is basically the same +randomness which we get during boot where the random pool has no +entropy and we rely on the TSC randomnness. + +Reported-by: Carsten Emde +Signed-off-by: Thomas Gleixner + +--- + arch/x86/include/asm/stackprotector.h | 10 +++++++++- + 1 file changed, 9 insertions(+), 1 deletion(-) + +--- a/arch/x86/include/asm/stackprotector.h ++++ b/arch/x86/include/asm/stackprotector.h +@@ -57,7 +57,7 @@ + */ + static __always_inline void boot_init_stack_canary(void) + { +- u64 canary; ++ u64 uninitialized_var(canary); + u64 tsc; + + #ifdef CONFIG_X86_64 +@@ -68,8 +68,16 @@ static __always_inline void boot_init_st + * of randomness. The TSC only matters for very early init, + * there it already has some randomness on most systems. Later + * on during the bootup the random pool has true entropy too. ++ * ++ * For preempt-rt we need to weaken the randomness a bit, as ++ * we can't call into the random generator from atomic context ++ * due to locking constraints. We just leave canary ++ * uninitialized and use the TSC based randomness on top of ++ * it. + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + get_random_bytes(&canary, sizeof(canary)); ++#endif + tsc = __native_read_tsc(); + canary += tsc + (tsc << 32UL); + diff --git a/debian/patches/features/all/rt/x86-use-gen-rwsem-spinlocks-rt.patch b/debian/patches/features/all/rt/x86-use-gen-rwsem-spinlocks-rt.patch new file mode 100644 index 000000000..47657a35b --- /dev/null +++ b/debian/patches/features/all/rt/x86-use-gen-rwsem-spinlocks-rt.patch @@ -0,0 +1,29 @@ +From: Thomas Gleixner +Date: Sun, 26 Jul 2009 02:21:32 +0200 +Subject: x86: Use generic rwsem_spinlocks on -rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.3-rt3.tar.xz + +Simplifies the separation of anon_rw_semaphores and rw_semaphores for +-rt. + +Signed-off-by: Thomas Gleixner + +--- + arch/x86/Kconfig | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +--- a/arch/x86/Kconfig ++++ b/arch/x86/Kconfig +@@ -203,8 +203,11 @@ config ARCH_MAY_HAVE_PC_FDC + def_bool y + depends on ISA_DMA_API + ++config RWSEM_GENERIC_SPINLOCK ++ def_bool PREEMPT_RT_FULL ++ + config RWSEM_XCHGADD_ALGORITHM +- def_bool y ++ def_bool !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL + + config GENERIC_CALIBRATE_DELAY + def_bool y diff --git a/debian/patches/series-rt b/debian/patches/series-rt new file mode 100644 index 000000000..9d39893ba --- /dev/null +++ b/debian/patches/series-rt @@ -0,0 +1,574 @@ +########################################################### +# DELTA against a known Linus release +########################################################### + +############################################################ +# UPSTREAM changes queued +############################################################ + +############################################################ +# UPSTREAM FIXES, patches pending +############################################################ +features/all/rt/0001-arm64-Mark-PMU-interrupt-IRQF_NO_THREAD.patch +features/all/rt/0002-arm64-Allow-forced-irq-threading.patch +features/all/rt/0001-uaccess-count-pagefault_disable-levels-in-pagefault_.patch +features/all/rt/0002-mm-uaccess-trigger-might_sleep-in-might_fault-with-d.patch +features/all/rt/0003-uaccess-clarify-that-uaccess-may-only-sleep-if-pagef.patch +features/all/rt/0004-mm-explicitly-disable-enable-preemption-in-kmap_atom.patch +features/all/rt/0005-mips-kmap_coherent-relies-on-disabled-preemption.patch +features/all/rt/0006-mm-use-pagefault_disable-to-check-for-disabled-pagef.patch +features/all/rt/0007-drm-i915-use-pagefault_disabled-to-check-for-disable.patch +features/all/rt/0008-futex-UP-futex_atomic_op_inuser-relies-on-disabled-p.patch +features/all/rt/0009-futex-UP-futex_atomic_cmpxchg_inatomic-relies-on-dis.patch +features/all/rt/0010-arm-futex-UP-futex_atomic_cmpxchg_inatomic-relies-on.patch +features/all/rt/0011-arm-futex-UP-futex_atomic_op_inuser-relies-on-disabl.patch +features/all/rt/0012-futex-clarify-that-preemption-doesn-t-have-to-be-dis.patch +features/all/rt/0013-mips-properly-lock-access-to-the-fpu.patch +features/all/rt/0014-uaccess-decouple-preemption-from-the-pagefault-logic.patch +features/all/rt/0001-sched-Implement-lockless-wake-queues.patch +features/all/rt/0002-futex-Implement-lockless-wakeups.patch +features/all/rt/0004-ipc-mqueue-Implement-lockless-pipelined-wakeups.patch +features/all/rt/mm-slub-move-slab-initialization-into-irq-enabled-region.patch + +############################################################ +# Stuff broken upstream, patches submitted +############################################################ +features/all/rt/cpufreq-Remove-cpufreq_rwsem.patch + +############################################################ +# Stuff which needs addressing upstream, but requires more +# information +############################################################ + +############################################################ +# Stuff broken upstream, need to be sent +############################################################ + +############################################################ +# Submitted on LKML +############################################################ + +# SPARC part of erly printk consolidation +features/all/rt/sparc64-use-generic-rwsem-spinlocks-rt.patch + +# SRCU +features/all/rt/kernel-SRCU-provide-a-static-initializer.patch + +############################################################ +# Submitted to mips ML +############################################################ + +############################################################ +# Submitted to ARM ML +############################################################ + +############################################################ +# Submitted to PPC ML +############################################################ + +############################################################ +# Submitted on LKML +############################################################ + +############################################################ +# Submitted to net-dev +############################################################ + +############################################################ +# Pending in tip +############################################################ + +############################################################ +# Stuff which should go upstream ASAP +############################################################ +features/all/rt/gpio-omap-use-raw-locks-for-locking.patch + +# SCHED BLOCK/WQ +features/all/rt/block-shorten-interrupt-disabled-regions.patch + +# Timekeeping split jiffies lock. Needs a good argument :) +features/all/rt/timekeeping-split-jiffies-lock.patch + +# CHECKME: Should local_irq_enable() generally do a preemption check ? +features/all/rt/vtime-split-lock-and-seqcount.patch + +# Tracing +features/all/rt/tracing-account-for-preempt-off-in-preempt_schedule.patch + +# PTRACE/SIGNAL crap +features/all/rt/signal-revert-ptrace-preempt-magic.patch + +# ARM lock annotation +features/all/rt/arm-convert-boot-lock-to-raw.patch + +# PREEMPT_ENABLE_NO_RESCHED + +# SIGNALS / POSIXTIMERS +features/all/rt/posix-timers-no-broadcast.patch +features/all/rt/signals-allow-rt-tasks-to-cache-one-sigqueue-struct.patch + +# SCHED + +# GENERIC CMPXCHG + +# SHORTEN PREEMPT DISABLED +features/all/rt/drivers-random-reduce-preempt-disabled-region.patch + +# CLOCKSOURCE +features/all/rt/arm-at91-pit-remove-irq-handler-when-clock-is-unused.patch +features/all/rt/clocksource-tclib-allow-higher-clockrates.patch + +# DRIVERS NET +features/all/rt/drivers-net-8139-disable-irq-nosync.patch + +# PREEMPT + +# PM +features/all/rt/suspend-prevernt-might-sleep-splats.patch + +# NETWORKING +features/all/rt/net-prevent-abba-deadlock.patch +features/all/rt/net-sched-dev_deactivate_many-use-msleep-1-instead-o.patch + +# X86 +features/all/rt/x86-io-apic-migra-no-unmask.patch +features/all/rt/fix-rt-int3-x86_32-3.2-rt.patch + +# RCU + +# LOCKING INIT FIXES + +# PCI +features/all/rt/pci-access-use-__wake_up_all_locked.patch + +# WORKQUEUE + + +##################################################### +# Stuff which should go mainline, but wants some care +##################################################### +features/all/rt/futex-avoid-double-wake-up-in-PI-futex-wait-wake-on-.patch + +# SEQLOCK + +# ANON RW SEMAPHORES + +# TRACING +features/all/rt/latency-hist.patch + +# HW LATENCY DETECTOR - this really wants a rewrite +features/all/rt/hwlatdetect.patch +features/all/rt/hwlat-detector-Update-hwlat_detector-to-add-outer-lo.patch +features/all/rt/hwlat-detector-Use-trace_clock_local-if-available.patch +features/all/rt/hwlat-detector-Use-thread-instead-of-stop-machine.patch +features/all/rt/hwlat-detector-Don-t-ignore-threshold-module-paramet.patch + +################################################## +# REAL RT STUFF starts here +################################################## + +# PRINTK +features/all/rt/printk-kill.patch +features/all/rt/printk-27force_early_printk-27-boot-param-to-help-with-debugging.patch + +# Enable RT CONFIG +features/all/rt/rt-preempt-base-config.patch +features/all/rt/kconfig-disable-a-few-options-rt.patch +features/all/rt/kconfig-preempt-rt-full.patch + +# WARN/BUG_ON_RT +features/all/rt/bug-rt-dependend-variants.patch + +# LOCAL_IRQ_RT/NON_RT +features/all/rt/local-irq-rt-depending-variants.patch + +# PREEMPT NORT +features/all/rt/preempt-nort-rt-variants.patch + +# local locks & migrate disable +features/all/rt/introduce_migrate_disable_cpu_light.patch +features/all/rt/rt-local-irq-lock.patch + +# ANNOTATE local_irq_disable sites +features/all/rt/ata-disable-interrupts-if-non-rt.patch +features/all/rt/ide-use-nort-local-irq-variants.patch +features/all/rt/infiniband-mellanox-ib-use-nort-irq.patch +features/all/rt/inpt-gameport-use-local-irq-nort.patch +features/all/rt/user-use-local-irq-nort.patch +features/all/rt/usb-use-_nort-in-giveback.patch +features/all/rt/mm-scatterlist-dont-disable-irqs-on-RT.patch +features/all/rt/mm-workingset-do-not-protect-workingset_shadow_nodes.patch + +# Sigh +features/all/rt/signal-fix-up-rcu-wreckage.patch +features/all/rt/oleg-signal-rt-fix.patch + +# ANNOTATE BUG/WARNON +features/all/rt/net-wireless-warn-nort.patch + +# BIT SPINLOCKS - SIGH +features/all/rt/fs-replace-bh_uptodate_lock-for-rt.patch +features/all/rt/fs-jbd-replace-bh_state-lock.patch + +# GENIRQ +features/all/rt/list_bl.h-make-list-head-locking-RT-safe.patch +features/all/rt/genirq-disable-irqpoll-on-rt.patch +features/all/rt/genirq-force-threading.patch +features/all/rt/genirq-do-not-invoke-the-affinity-callback-via-a-wor.patch + +# DRIVERS NET +features/all/rt/drivers-net-fix-livelock-issues.patch +features/all/rt/drivers-net-vortex-fix-locking-issues.patch +features/all/rt/net-gianfar-do-not-disable-interrupts.patch + +# MM PAGE_ALLOC +features/all/rt/mm-page_alloc-rt-friendly-per-cpu-pages.patch +features/all/rt/mm-page_alloc-reduce-lock-sections-further.patch + +# MM SWAP +features/all/rt/mm-convert-swap-to-percpu-locked.patch + +# MM vmstat +features/all/rt/mm-make-vmstat-rt-aware.patch + +# MM memory +features/all/rt/re-preempt_rt_full-arm-coredump-fails-for-cpu-3e-3d-4.patch + +# MM bounce +features/all/rt/mm-bounce-local-irq-save-nort.patch + +# MM SLxB +features/all/rt/mm-disable-sloub-rt.patch +features/all/rt/mm-enable-slub.patch +features/all/rt/slub-enable-irqs-for-no-wait.patch +features/all/rt/slub-disable-SLUB_CPU_PARTIAL.patch + +# MM +features/all/rt/mm-page-alloc-use-local-lock-on-target-cpu.patch +features/all/rt/mm-memcontrol-Don-t-call-schedule_work_on-in-preempt.patch +features/all/rt/mm-memcontrol-do_not_disable_irq.patch + +# RADIX TREE +features/all/rt/radix-tree-rt-aware.patch + +# PANIC +features/all/rt/panic-disable-random-on-rt.patch + +# IPC +features/all/rt/ipc-make-rt-aware.patch + +# RELAY +features/all/rt/relay-fix-timer-madness.patch + +# NETWORKING + +# WORKQUEUE SIGH + +# TIMERS +features/all/rt/timers-prepare-for-full-preemption.patch +features/all/rt/timers-preempt-rt-support.patch +features/all/rt/timer-delay-waking-softirqs-from-the-jiffy-tick.patch +features/all/rt/timers-avoid-the-base-null-otptimization-on-rt.patch + +# HRTIMERS +features/all/rt/hrtimers-prepare-full-preemption.patch +features/all/rt/hrtimer-fixup-hrtimer-callback-changes-for-preempt-r.patch +features/all/rt/sched-deadline-dl_task_timer-has-to-be-irqsafe.patch +features/all/rt/timer-fd-avoid-live-lock.patch +features/all/rt/hrtimer-raise-softirq-if-hrtimer-irq-stalled.patch +features/all/rt/hrtimer-Move-schedule_work-call-to-helper-thread.patch + +# POSIX-CPU-TIMERS +features/all/rt/posix-timers-thread-posix-cpu-timers-on-rt.patch + +# SCHEDULER +features/all/rt/sched-delay-put-task.patch +features/all/rt/sched-limit-nr-migrate.patch +features/all/rt/sched-mmdrop-delayed.patch +features/all/rt/sched-rt-mutex-wakeup.patch +features/all/rt/sched-might-sleep-do-not-account-rcu-depth.patch +features/all/rt/cond-resched-softirq-rt.patch +features/all/rt/cond-resched-lock-rt-tweak.patch +features/all/rt/sched-disable-ttwu-queue.patch +features/all/rt/sched-disable-rt-group-sched-on-rt.patch +features/all/rt/sched-ttwu-ensure-success-return-is-correct.patch +features/all/rt/sched-workqueue-Only-wake-up-idle-workers-if-not-blo.patch + +# STOP MACHINE +features/all/rt/stop_machine-convert-stop_machine_run-to-PREEMPT_RT.patch +features/all/rt/stop-machine-raw-lock.patch + +# MIGRATE DISABLE AND PER CPU +features/all/rt/hotplug-light-get-online-cpus.patch +features/all/rt/hotplug-sync_unplug-no-27-5cn-27-in-task-name.patch +features/all/rt/re-migrate_disable-race-with-cpu-hotplug-3f.patch +features/all/rt/ftrace-migrate-disable-tracing.patch +features/all/rt/hotplug-use-migrate-disable.patch + +# NETWORKING +features/all/rt/sunrpc-make-svc_xprt_do_enqueue-use-get_cpu_light.patch + +# NOHZ + +# LOCKDEP +features/all/rt/lockdep-no-softirq-accounting-on-rt.patch + +# SOFTIRQ +features/all/rt/mutex-no-spin-on-rt.patch +features/all/rt/tasklet-rt-prevent-tasklets-from-going-into-infinite-spin-in-rt.patch +features/all/rt/softirq-preempt-fix-3-re.patch +features/all/rt/softirq-disable-softirq-stacks-for-rt.patch +features/all/rt/softirq-split-locks.patch +features/all/rt/irq-allow-disabling-of-softirq-processing-in-irq-thread-context.patch + +# RAID5 +features/all/rt/md-raid5-percpu-handling-rt-aware.patch + +# FUTEX/RTMUTEX +features/all/rt/rtmutex-futex-prepare-rt.patch +features/all/rt/futex-requeue-pi-fix.patch +features/all/rt/0005-futex-Ensure-lock-unlock-symetry-versus-pi_lock-and-.patch + +# RTMUTEX +features/all/rt/pid.h-include-atomic.h.patch +features/all/rt/locking-locktorture-Do-NOT-include-rwlock.h-directly.patch +features/all/rt/rtmutex-lock-killable.patch +features/all/rt/spinlock-types-separate-raw.patch +features/all/rt/rtmutex-avoid-include-hell.patch +features/all/rt/rt-add-rt-locks.patch +features/all/rt/rtmutex-add-a-first-shot-of-ww_mutex.patch + +features/all/rt/ptrace-fix-ptrace-vs-tasklist_lock-race.patch + +# RTMUTEX Fallout +features/all/rt/tasklist-lock-fix-section-conflict.patch + +# RCU +features/all/rt/peter_zijlstra-frob-rcu.patch +features/all/rt/rcu-merge-rcu-bh-into-rcu-preempt-for-rt.patch +features/all/rt/patch-to-introduce-rcu-bh-qs-where-safe-from-softirq.patch +features/all/rt/rcutree-rcu_bh_qs-disable-irq-while-calling-rcu_pree.patch + +# LGLOCKS - lovely +features/all/rt/lglocks-rt.patch + +# STOP machine (depend on lglock & rtmutex) +features/all/rt/stomp-machine-create-lg_global_trylock_relax-primiti.patch +features/all/rt/stomp-machine-use-lg_global_trylock_relax-to-dead-wi.patch + +# DRIVERS SERIAL +features/all/rt/drivers-tty-fix-omap-lock-crap.patch +features/all/rt/drivers-tty-pl011-irq-disable-madness.patch +features/all/rt/rt-serial-warn-fix.patch + +# SIMPLE WAITQUEUE +features/all/rt/wait.h-include-atomic.h.patch +features/all/rt/wait-simple-implementation.patch +features/all/rt/work-simple-Simple-work-queue-implemenation.patch +features/all/rt/rcu-more-swait-conversions.patch +features/all/rt/completion-use-simple-wait-queues.patch +features/all/rt/fs-aio-simple-simple-work.patch + +# FS +features/all/rt/fs-namespace-preemption-fix.patch +features/all/rt/mm-protect-activate-switch-mm.patch +features/all/rt/fs-block-rt-support.patch +features/all/rt/fs-ntfs-disable-interrupt-non-rt.patch +features/all/rt/fs-jbd-pull-plug-when-waiting-for-space.patch +features/all/rt/fs-jbd2-pull-your-plug-when-waiting-for-space.patch + +# X86 +features/all/rt/x86-mce-timer-hrtimer.patch +features/all/rt/x86-mce-use-swait-queue-for-mce-wakeups.patch +features/all/rt/x86-stackprot-no-random-on-rt.patch +features/all/rt/x86-use-gen-rwsem-spinlocks-rt.patch +features/all/rt/x86-UV-raw_spinlock-conversion.patch +features/all/rt/thermal-Defer-thermal-wakups-to-threads.patch + +# CPU get light +features/all/rt/epoll-use-get-cpu-light.patch +features/all/rt/mm-vmalloc-use-get-cpu-light.patch +features/all/rt/block-mq-use-cpu_light.patch +features/all/rt/block-mq-drop-preempt-disable.patch +features/all/rt/block-mq-don-t-complete-requests-via-IPI.patch + +# CPU CHILL +features/all/rt/rt-introduce-cpu-chill.patch +features/all/rt/cpu_chill-Add-a-UNINTERRUPTIBLE-hrtimer_nanosleep.patch + +# block +features/all/rt/blk-mq-revert-raw-locks-post-pone-notifier-to-POST_D.patchto-POST_D.patch +features/all/rt/block-blk-mq-use-swait.patch +features/all/rt/block-mq-drop-per-ctx-cpu_lock.patch + +# BLOCK LIVELOCK PREVENTION +features/all/rt/block-use-cpu-chill.patch + +# FS LIVELOCK PREVENTION +features/all/rt/fs-dcache-use-cpu-chill-in-trylock-loops.patch +features/all/rt/net-use-cpu-chill.patch + +# WORKQUEUE more fixes +features/all/rt/workqueue-use-rcu.patch +features/all/rt/workqueue-use-locallock.patch +features/all/rt/work-queue-work-around-irqsafe-timer-optimization.patch +features/all/rt/workqueue-distangle-from-rq-lock.patch + +# IDR +features/all/rt/idr-use-local-lock-for-protection.patch +features/all/rt/percpu_ida-use-locklocks.patch + +# DEBUGOBJECTS +features/all/rt/debugobjects-rt.patch + +# JUMPLABEL +features/all/rt/jump-label-rt.patch + +# NET +features/all/rt/skbufhead-raw-lock.patch + +# irqwork +features/all/rt/irqwork-push_most_work_into_softirq_context.patch + +# Sound +features/all/rt/snd-pcm-fix-snd_pcm_stream_lock-irqs_disabled-splats.patch +features/all/rt/ASoC-Intel-sst-use-instead-of-at-the-of-a-C-statemen.patch + +# CONSOLE. NEEDS more thought !!! +features/all/rt/printk-rt-aware.patch +features/all/rt/HACK-printk-drop-the-logbuf_lock-more-often.patch + +# POWERC +features/all/rt/power-use-generic-rwsem-on-rt.patch +features/all/rt/powerpc-kvm-Disable-in-kernel-MPIC-emulation-for-PRE.patch +features/all/rt/powerpc-ps3-device-init.c-adapt-to-completions-using.patch + +# ARM +features/all/rt/arm-at91-tclib-default-to-tclib-timer-for-rt.patch +features/all/rt/arm-unwind-use_raw_lock.patch +features/all/rt/ARM-enable-irq-in-translation-section-permission-fau.patch +features/all/rt/ARM-cmpxchg-define-__HAVE_ARCH_CMPXCHG-for-armv6-and.patch + +# NETWORK livelock fix +features/all/rt/net-tx-action-avoid-livelock-on-rt.patch + +# NETWORK DEBUGGING AID +features/all/rt/ping-sysrq.patch + +# KGDB +features/all/rt/kgb-serial-hackaround.patch + +# SYSFS - RT indicator +features/all/rt/sysfs-realtime-entry.patch + +# KMAP/HIGHMEM +features/all/rt/power-disable-highmem-on-rt.patch +features/all/rt/mips-disable-highmem-on-rt.patch +features/all/rt/mm-rt-kmap-atomic-scheduling.patch +features/all/rt/x86-highmem-add-a-already-used-pte-check.patch +features/all/rt/arm-highmem-flush-tlb-on-unmap.patch +features/all/rt/arm-enable-highmem-for-rt.patch + +# IPC +features/all/rt/ipc-sem-rework-semaphore-wakeups.patch + +# SYSRQ + +# KVM require constant freq TSC (smp function call -> cpufreq) +features/all/rt/x86-kvm-require-const-tsc-for-rt.patch +features/all/rt/KVM-lapic-mark-LAPIC-timer-handler-as-irqsafe.patch +features/all/rt/KVM-use-simple-waitqueue-for-vcpu-wq.patch + +# SCSI/FCOE +features/all/rt/scsi-fcoe-rt-aware.patch +features/all/rt/sas-ata-isci-dont-t-disable-interrupts-in-qc_issue-h.patch + +# X86 crypto +features/all/rt/x86-crypto-reduce-preempt-disabled-regions.patch +features/all/rt/crypto-Reduce-preempt-disabled-regions-more-algos.patch + +# Device mapper +features/all/rt/dm-make-rt-aware.patch + +# ACPI +features/all/rt/acpi-rt-Convert-acpi_gbl_hardware-lock-back-to-a-raw.patch + +# CPUMASK OFFSTACK +features/all/rt/cpumask-disable-offstack-on-rt.patch + +# RANDOM +features/all/rt/random-make-it-work-on-rt.patch + +# SEQLOCKS +features/all/rt/seqlock-prevent-rt-starvation.patch + +# HOTPLUG +features/all/rt/cpu-rt-make-hotplug-lock-a-sleeping-spinlock-on-rt.patch +features/all/rt/cpu-rt-rework-cpu-down.patch +features/all/rt/cpu-hotplug-Document-why-PREEMPT_RT-uses-a-spinlock.patch +features/all/rt/kernel-cpu-fix-cpu-down-problem-if-kthread-s-cpu-is-.patch +features/all/rt/kernel-hotplug-restore-original-cpu-mask-oncpu-down.patch +features/all/rt/cpu_down_move_migrate_enable_back.patch +features/all/rt/hotplug-Use-set_cpus_allowed_ptr-in-sync_unplug_thre.patch + +# SCSCI QLA2xxx +features/all/rt/scsi-qla2xxx-fix-bug-sleeping-function-called-from-invalid-context.patch + +# NET +features/all/rt/upstream-net-rt-remove-preemption-disabling-in-netif_rx.patch +features/all/rt/net-another-local-irq-disable-alloc-atomic-headache.patch +features/all/rt/net-fix-iptable-xt-write-recseq-begin-rt-fallout.patch +features/all/rt/net-make-devnet_rename_seq-a-mutex.patch + +# CRYPTO +features/all/rt/peterz-srcu-crypto-chain.patch + +# LOCKDEP +features/all/rt/lockdep-selftest-only-do-hardirq-context-test-for-raw-spinlock.patch +features/all/rt/lockdep-selftest-fix-warnings-due-to-missing-PREEMPT.patch + +# PERF +features/all/rt/perf-make-swevent-hrtimer-irqsafe.patch + +# RCU +features/all/rt/rcu-disable-rcu-fast-no-hz-on-rt.patch +features/all/rt/rcu-Eliminate-softirq-processing-from-rcutree.patch +features/all/rt/rcu-make-RCU_BOOST-default-on-RT.patch + +# PREEMPT LAZY +features/all/rt/preempt-lazy-support.patch +features/all/rt/x86-preempt-lazy.patch +features/all/rt/arm-preempt-lazy-support.patch +features/all/rt/powerpc-preempt-lazy-support.patch +features/all/rt/arch-arm64-Add-lazy-preempt-support.patch + +# LEDS +features/all/rt/leds-trigger-disable-CPU-trigger-on-RT.patch + +# DRIVERS +features/all/rt/i2c-omap-drop-the-lock-hard-irq-context.patch +features/all/rt/mmci-remove-bogus-irq-save.patch +features/all/rt/mmc-sdhci-don-t-provide-hard-irq-handler.patch +features/all/rt/cpufreq-drop-K8-s-driver-from-beeing-selected.patch + +# I915 +features/all/rt/i915_compile_fix.patch +features/all/rt/drm-i915-drop-trace_i915_gem_ring_dispatch-onrt.patch +features/all/rt/i915-bogus-warning-from-i915-when-running-on-PREEMPT.patch + + +features/all/rt/cgroups-use-simple-wait-in-css_release.patch +features/all/rt/cgroups-scheduling-while-atomic-in-cgroup-code.patch + +# New stuff +# Revisit: We need this in other places as well +features/all/rt/move_sched_delayed_work_to_helper.patch + +# bcache disabled +features/all/rt/md-disable-bcache.patch + +# Latest fixes +features/all/rt/workqueue-prevent-deadlock-stall.patch + +# Add RT to version +features/all/rt/localversion.patch