[ANNOUNCE] 4.1.7-rt8
From: Thomas Gleixner
Date: Mon Sep 21 2015 - 12:48:53 EST
Dear RT folks!
I'm pleased to announce the v4.1.7-rt8 patch set. v4.1.6-rt6 and
v4.1.7-rt7 are non-announced updates to incorporate the linux-4.1.y
stable tree changes.
Changes since v4.1.5-rt5:
- Update to 4.1.7
- Cherry-pick a XFS lockdep annotation fix from mainline
- Use preempt_xxx_nort in the generic implementation of
k[un]map_atomic.
- Revert d04ea10ba1ea mmc: sdhci: don't provide hard irq handler
- Force thread primary handlers of interrupts which provide both a
primary and a threaded handler
- Move clear_tasks_mm_cpumask() call to __cpu_die() on ARM
(Grygoriii)
- Fix a RCU splat in the trace histogram (Philipp)
Solved issues:
- The high CPU usage problem reported by Nicholas turned out to be a
scalability issue of the gcov instrumentation
Known issues:
- bcache stays disabled
- CPU hotplug is not better than before
- The netlink_release() OOPS, reported by Clark, is still on the
list, but unsolved due to lack of information
The delta patch against 4.1.7-rt7 is appended below and can be found here:
https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/incr/patch-4.1.7-rt7-rt8.patch.xz
You can get this release via the git tree at:
git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git v4.1.7-rt8
The RT patch against 4.1.5 can be found here:
https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patch-4.1.7-rt8.patch.xz
The split quilt queue is available at:
https://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patches-4.1.7-rt8.tar.xz
Enjoy!
tglx
---
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index f11d82527076..e561aef093c7 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -213,8 +213,6 @@ int __cpu_disable(void)
flush_cache_louis();
local_flush_tlb_all();
- clear_tasks_mm_cpumask(cpu);
-
return 0;
}
@@ -230,6 +228,9 @@ void __cpu_die(unsigned int cpu)
pr_err("CPU%u: cpu didn't die\n", cpu);
return;
}
+
+ clear_tasks_mm_cpumask(cpu);
+
pr_notice("CPU%u: shutdown\n", cpu);
/*
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index acd8c620ec43..bec8a307f8cd 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -2691,31 +2691,6 @@ static irqreturn_t sdhci_thread_irq(int irq, void *dev_id)
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 *
@@ -2783,7 +2758,9 @@ int sdhci_resume_host(struct sdhci_host *host)
}
if (!device_may_wakeup(mmc_dev(host->mmc))) {
- ret = sdhci_req_irq(host);
+ ret = request_threaded_irq(host->irq, sdhci_irq,
+ sdhci_thread_irq, IRQF_SHARED,
+ mmc_hostname(host->mmc), host);
if (ret)
return ret;
} else {
@@ -3444,7 +3421,8 @@ int sdhci_add_host(struct sdhci_host *host)
sdhci_init(host, 0);
- ret = sdhci_req_irq(host);
+ ret = request_threaded_irq(host->irq, sdhci_irq, sdhci_thread_irq,
+ IRQF_SHARED, mmc_hostname(mmc), host);
if (ret) {
pr_err("%s: Failed to request IRQ %d: %d\n",
mmc_hostname(mmc), host->irq, ret);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 539a85fddbc2..fec4bfba0839 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -164,7 +164,7 @@ xfs_ilock(
(XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL));
ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
(XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
- ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_DEP_MASK)) == 0);
+ ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);
if (lock_flags & XFS_IOLOCK_EXCL)
mrupdate_nested(&ip->i_iolock, XFS_IOLOCK_DEP(lock_flags));
@@ -212,7 +212,7 @@ xfs_ilock_nowait(
(XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL));
ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
(XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
- ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_DEP_MASK)) == 0);
+ ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);
if (lock_flags & XFS_IOLOCK_EXCL) {
if (!mrtryupdate(&ip->i_iolock))
@@ -281,7 +281,7 @@ xfs_iunlock(
(XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL));
ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
(XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
- ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_DEP_MASK)) == 0);
+ ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0);
ASSERT(lock_flags != 0);
if (lock_flags & XFS_IOLOCK_EXCL)
@@ -364,30 +364,38 @@ int xfs_lock_delays;
/*
* Bump the subclass so xfs_lock_inodes() acquires each lock with a different
- * value. This shouldn't be called for page fault locking, but we also need to
- * ensure we don't overrun the number of lockdep subclasses for the iolock or
- * mmaplock as that is limited to 12 by the mmap lock lockdep annotations.
+ * value. This can be called for any type of inode lock combination, including
+ * parent locking. Care must be taken to ensure we don't overrun the subclass
+ * storage fields in the class mask we build.
*/
static inline int
xfs_lock_inumorder(int lock_mode, int subclass)
{
+ int class = 0;
+
+ ASSERT(!(lock_mode & (XFS_ILOCK_PARENT | XFS_ILOCK_RTBITMAP |
+ XFS_ILOCK_RTSUM)));
+
if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)) {
- ASSERT(subclass + XFS_LOCK_INUMORDER <
- (1 << (XFS_MMAPLOCK_SHIFT - XFS_IOLOCK_SHIFT)));
- lock_mode |= (subclass + XFS_LOCK_INUMORDER) << XFS_IOLOCK_SHIFT;
+ ASSERT(subclass <= XFS_IOLOCK_MAX_SUBCLASS);
+ ASSERT(subclass + XFS_IOLOCK_PARENT_VAL <
+ MAX_LOCKDEP_SUBCLASSES);
+ class += subclass << XFS_IOLOCK_SHIFT;
+ if (lock_mode & XFS_IOLOCK_PARENT)
+ class += XFS_IOLOCK_PARENT_VAL << XFS_IOLOCK_SHIFT;
}
if (lock_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) {
- ASSERT(subclass + XFS_LOCK_INUMORDER <
- (1 << (XFS_ILOCK_SHIFT - XFS_MMAPLOCK_SHIFT)));
- lock_mode |= (subclass + XFS_LOCK_INUMORDER) <<
- XFS_MMAPLOCK_SHIFT;
+ ASSERT(subclass <= XFS_MMAPLOCK_MAX_SUBCLASS);
+ class += subclass << XFS_MMAPLOCK_SHIFT;
}
- if (lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL))
- lock_mode |= (subclass + XFS_LOCK_INUMORDER) << XFS_ILOCK_SHIFT;
+ if (lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)) {
+ ASSERT(subclass <= XFS_ILOCK_MAX_SUBCLASS);
+ class += subclass << XFS_ILOCK_SHIFT;
+ }
- return lock_mode;
+ return (lock_mode & ~XFS_LOCK_SUBCLASS_MASK) | class;
}
/*
@@ -399,6 +407,11 @@ xfs_lock_inumorder(int lock_mode, int subclass)
* transaction (such as truncate). This can result in deadlock since the long
* running trans might need to wait for the inode we just locked in order to
* push the tail and free space in the log.
+ *
+ * xfs_lock_inodes() can only be used to lock one type of lock at a time -
+ * the iolock, the mmaplock or the ilock, but not more than one at a time. If we
+ * lock more than one at a time, lockdep will report false positives saying we
+ * have violated locking orders.
*/
void
xfs_lock_inodes(
@@ -409,8 +422,29 @@ xfs_lock_inodes(
int attempts = 0, i, j, try_lock;
xfs_log_item_t *lp;
- /* currently supports between 2 and 5 inodes */
+ /*
+ * Currently supports between 2 and 5 inodes with exclusive locking. We
+ * support an arbitrary depth of locking here, but absolute limits on
+ * inodes depend on the the type of locking and the limits placed by
+ * lockdep annotations in xfs_lock_inumorder. These are all checked by
+ * the asserts.
+ */
ASSERT(ips && inodes >= 2 && inodes <= 5);
+ ASSERT(lock_mode & (XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL |
+ XFS_ILOCK_EXCL));
+ ASSERT(!(lock_mode & (XFS_IOLOCK_SHARED | XFS_MMAPLOCK_SHARED |
+ XFS_ILOCK_SHARED)));
+ ASSERT(!(lock_mode & XFS_IOLOCK_EXCL) ||
+ inodes <= XFS_IOLOCK_MAX_SUBCLASS + 1);
+ ASSERT(!(lock_mode & XFS_MMAPLOCK_EXCL) ||
+ inodes <= XFS_MMAPLOCK_MAX_SUBCLASS + 1);
+ ASSERT(!(lock_mode & XFS_ILOCK_EXCL) ||
+ inodes <= XFS_ILOCK_MAX_SUBCLASS + 1);
+
+ if (lock_mode & XFS_IOLOCK_EXCL) {
+ ASSERT(!(lock_mode & (XFS_MMAPLOCK_EXCL | XFS_ILOCK_EXCL)));
+ } else if (lock_mode & XFS_MMAPLOCK_EXCL)
+ ASSERT(!(lock_mode & XFS_ILOCK_EXCL));
try_lock = 0;
i = 0;
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 8f22d20368d8..ee26a603c131 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -284,9 +284,9 @@ static inline int xfs_isiflocked(struct xfs_inode *ip)
* Flags for lockdep annotations.
*
* XFS_LOCK_PARENT - for directory operations that require locking a
- * parent directory inode and a child entry inode. The parent gets locked
- * with this flag so it gets a lockdep subclass of 1 and the child entry
- * lock will have a lockdep subclass of 0.
+ * parent directory inode and a child entry inode. IOLOCK requires nesting,
+ * MMAPLOCK does not support this class, ILOCK requires a single subclass
+ * to differentiate parent from child.
*
* XFS_LOCK_RTBITMAP/XFS_LOCK_RTSUM - the realtime device bitmap and summary
* inodes do not participate in the normal lock order, and thus have their
@@ -295,30 +295,63 @@ static inline int xfs_isiflocked(struct xfs_inode *ip)
* XFS_LOCK_INUMORDER - for locking several inodes at the some time
* with xfs_lock_inodes(). This flag is used as the starting subclass
* and each subsequent lock acquired will increment the subclass by one.
- * So the first lock acquired will have a lockdep subclass of 4, the
- * second lock will have a lockdep subclass of 5, and so on. It is
- * the responsibility of the class builder to shift this to the correct
- * portion of the lock_mode lockdep mask.
+ * However, MAX_LOCKDEP_SUBCLASSES == 8, which means we are greatly
+ * limited to the subclasses we can represent via nesting. We need at least
+ * 5 inodes nest depth for the ILOCK through rename, and we also have to support
+ * XFS_ILOCK_PARENT, which gives 6 subclasses. Then we have XFS_ILOCK_RTBITMAP
+ * and XFS_ILOCK_RTSUM, which are another 2 unique subclasses, so that's all
+ * 8 subclasses supported by lockdep.
+ *
+ * This also means we have to number the sub-classes in the lowest bits of
+ * the mask we keep, and we have to ensure we never exceed 3 bits of lockdep
+ * mask and we can't use bit-masking to build the subclasses. What a mess.
+ *
+ * Bit layout:
+ *
+ * Bit Lock Region
+ * 16-19 XFS_IOLOCK_SHIFT dependencies
+ * 20-23 XFS_MMAPLOCK_SHIFT dependencies
+ * 24-31 XFS_ILOCK_SHIFT dependencies
+ *
+ * IOLOCK values
+ *
+ * 0-3 subclass value
+ * 4-7 PARENT subclass values
+ *
+ * MMAPLOCK values
+ *
+ * 0-3 subclass value
+ * 4-7 unused
+ *
+ * ILOCK values
+ * 0-4 subclass values
+ * 5 PARENT subclass (not nestable)
+ * 6 RTBITMAP subclass (not nestable)
+ * 7 RTSUM subclass (not nestable)
+ *
*/
-#define XFS_LOCK_PARENT 1
-#define XFS_LOCK_RTBITMAP 2
-#define XFS_LOCK_RTSUM 3
-#define XFS_LOCK_INUMORDER 4
-
-#define XFS_IOLOCK_SHIFT 16
-#define XFS_IOLOCK_PARENT (XFS_LOCK_PARENT << XFS_IOLOCK_SHIFT)
-
-#define XFS_MMAPLOCK_SHIFT 20
-
-#define XFS_ILOCK_SHIFT 24
-#define XFS_ILOCK_PARENT (XFS_LOCK_PARENT << XFS_ILOCK_SHIFT)
-#define XFS_ILOCK_RTBITMAP (XFS_LOCK_RTBITMAP << XFS_ILOCK_SHIFT)
-#define XFS_ILOCK_RTSUM (XFS_LOCK_RTSUM << XFS_ILOCK_SHIFT)
-
-#define XFS_IOLOCK_DEP_MASK 0x000f0000
-#define XFS_MMAPLOCK_DEP_MASK 0x00f00000
-#define XFS_ILOCK_DEP_MASK 0xff000000
-#define XFS_LOCK_DEP_MASK (XFS_IOLOCK_DEP_MASK | \
+#define XFS_IOLOCK_SHIFT 16
+#define XFS_IOLOCK_PARENT_VAL 4
+#define XFS_IOLOCK_MAX_SUBCLASS (XFS_IOLOCK_PARENT_VAL - 1)
+#define XFS_IOLOCK_DEP_MASK 0x000f0000
+#define XFS_IOLOCK_PARENT (XFS_IOLOCK_PARENT_VAL << XFS_IOLOCK_SHIFT)
+
+#define XFS_MMAPLOCK_SHIFT 20
+#define XFS_MMAPLOCK_NUMORDER 0
+#define XFS_MMAPLOCK_MAX_SUBCLASS 3
+#define XFS_MMAPLOCK_DEP_MASK 0x00f00000
+
+#define XFS_ILOCK_SHIFT 24
+#define XFS_ILOCK_PARENT_VAL 5
+#define XFS_ILOCK_MAX_SUBCLASS (XFS_ILOCK_PARENT_VAL - 1)
+#define XFS_ILOCK_RTBITMAP_VAL 6
+#define XFS_ILOCK_RTSUM_VAL 7
+#define XFS_ILOCK_DEP_MASK 0xff000000
+#define XFS_ILOCK_PARENT (XFS_ILOCK_PARENT_VAL << XFS_ILOCK_SHIFT)
+#define XFS_ILOCK_RTBITMAP (XFS_ILOCK_RTBITMAP_VAL << XFS_ILOCK_SHIFT)
+#define XFS_ILOCK_RTSUM (XFS_ILOCK_RTSUM_VAL << XFS_ILOCK_SHIFT)
+
+#define XFS_LOCK_SUBCLASS_MASK (XFS_IOLOCK_DEP_MASK | \
XFS_MMAPLOCK_DEP_MASK | \
XFS_ILOCK_DEP_MASK)
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index d89b5e083c35..06bae5a6761d 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -66,7 +66,7 @@ static inline void kunmap(struct page *page)
static inline void *kmap_atomic(struct page *page)
{
- preempt_disable();
+ preempt_disable_nort();
pagefault_disable();
return page_address(page);
}
@@ -75,7 +75,7 @@ static inline void *kmap_atomic(struct page *page)
static inline void __kunmap_atomic(void *addr)
{
pagefault_enable();
- preempt_enable();
+ preempt_enable_nort();
}
#define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn))
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 67f2af8c0cd5..fe254555cf95 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -104,6 +104,7 @@ typedef irqreturn_t (*irq_handler_t)(int, void *);
* @flags: flags (see IRQF_* above)
* @thread_fn: interrupt handler function for threaded interrupts
* @thread: thread pointer for threaded interrupts
+ * @secondary: pointer to secondary irqaction (force threading)
* @thread_flags: flags related to @thread
* @thread_mask: bitmask for keeping track of @thread activity
* @dir: pointer to the proc/irq/NN/name entry
@@ -115,6 +116,7 @@ struct irqaction {
struct irqaction *next;
irq_handler_t thread_fn;
struct task_struct *thread;
+ struct irqaction *secondary;
unsigned int irq;
unsigned int flags;
unsigned long thread_flags;
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 1b5c50a68e23..79c55c26eaee 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -772,6 +772,12 @@ static irqreturn_t irq_nested_primary_handler(int irq, void *dev_id)
return IRQ_NONE;
}
+static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id)
+{
+ WARN(1, "Secondary action handler called for irq %d\n", irq);
+ return IRQ_NONE;
+}
+
static int irq_wait_for_interrupt(struct irqaction *action)
{
set_current_state(TASK_INTERRUPTIBLE);
@@ -798,7 +804,8 @@ static int irq_wait_for_interrupt(struct irqaction *action)
static void irq_finalize_oneshot(struct irq_desc *desc,
struct irqaction *action)
{
- if (!(desc->istate & IRQS_ONESHOT))
+ if (!(desc->istate & IRQS_ONESHOT) ||
+ action->handler == irq_forced_secondary_handler)
return;
again:
chip_bus_lock(desc);
@@ -960,6 +967,18 @@ static void irq_thread_dtor(struct callback_head *unused)
irq_finalize_oneshot(desc, action);
}
+static void irq_wake_secondary(struct irq_desc *desc, struct irqaction *action)
+{
+ struct irqaction *secondary = action->secondary;
+
+ if (WARN_ON_ONCE(!secondary))
+ return;
+
+ raw_spin_lock_irq(&desc->lock);
+ __irq_wake_thread(desc, secondary);
+ raw_spin_unlock_irq(&desc->lock);
+}
+
/*
* Interrupt handler thread
*/
@@ -990,6 +1009,8 @@ static int irq_thread(void *data)
action_ret = handler_fn(desc, action);
if (action_ret == IRQ_HANDLED)
atomic_inc(&desc->threads_handled);
+ if (action_ret == IRQ_WAKE_THREAD)
+ irq_wake_secondary(desc, action);
#ifdef CONFIG_PREEMPT_RT_FULL
migrate_disable();
@@ -1040,20 +1061,36 @@ void irq_wake_thread(unsigned int irq, void *dev_id)
}
EXPORT_SYMBOL_GPL(irq_wake_thread);
-static void irq_setup_forced_threading(struct irqaction *new)
+static int irq_setup_forced_threading(struct irqaction *new)
{
if (!force_irqthreads)
- return;
+ return 0;
if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT))
- return;
+ return 0;
new->flags |= IRQF_ONESHOT;
- if (!new->thread_fn) {
- set_bit(IRQTF_FORCED_THREAD, &new->thread_flags);
- new->thread_fn = new->handler;
- new->handler = irq_default_primary_handler;
+ /*
+ * Handle the case where we have a real primary handler and a
+ * thread handler. We force thread them as well by creating a
+ * secondary action.
+ */
+ if (new->handler != irq_default_primary_handler && new->thread_fn) {
+ /* Allocate the secondary action */
+ new->secondary = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
+ if (!new->secondary)
+ return -ENOMEM;
+ new->secondary->handler = irq_forced_secondary_handler;
+ new->secondary->thread_fn = new->thread_fn;
+ new->secondary->dev_id = new->dev_id;
+ new->secondary->irq = new->irq;
+ new->secondary->name = new->name;
}
+ /* Deal with the primary handler */
+ set_bit(IRQTF_FORCED_THREAD, &new->thread_flags);
+ new->thread_fn = new->handler;
+ new->handler = irq_default_primary_handler;
+ return 0;
}
static int irq_request_resources(struct irq_desc *desc)
@@ -1073,6 +1110,48 @@ static void irq_release_resources(struct irq_desc *desc)
c->irq_release_resources(d);
}
+static int
+setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary)
+{
+ struct task_struct *t;
+ struct sched_param param = {
+ .sched_priority = MAX_USER_RT_PRIO/2,
+ };
+
+ if (!secondary) {
+ t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
+ new->name);
+ } else {
+ t = kthread_create(irq_thread, new, "irq/%d-s-%s", irq,
+ new->name);
+ param.sched_priority += 1;
+ }
+
+ if (IS_ERR(t))
+ return PTR_ERR(t);
+
+ sched_setscheduler_nocheck(t, SCHED_FIFO, ¶m);
+
+ /*
+ * We keep the reference to the task struct even if
+ * the thread dies to avoid that the interrupt code
+ * references an already freed task_struct.
+ */
+ get_task_struct(t);
+ new->thread = t;
+ /*
+ * Tell the thread to set its affinity. This is
+ * important for shared interrupt handlers as we do
+ * not invoke setup_affinity() for the secondary
+ * handlers as everything is already set up. Even for
+ * interrupts marked with IRQF_NO_BALANCE this is
+ * correct as we want the thread to move to the cpu(s)
+ * on which the requesting code placed the interrupt.
+ */
+ set_bit(IRQTF_AFFINITY, &new->thread_flags);
+ return 0;
+}
+
/*
* Internal function to register an irqaction - typically used to
* allocate special interrupts that are part of the architecture.
@@ -1093,6 +1172,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
if (!try_module_get(desc->owner))
return -ENODEV;
+ new->irq = irq;
+
/*
* Check whether the interrupt nests into another interrupt
* thread.
@@ -1110,8 +1191,11 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
*/
new->handler = irq_nested_primary_handler;
} else {
- if (irq_settings_can_thread(desc))
- irq_setup_forced_threading(new);
+ if (irq_settings_can_thread(desc)) {
+ ret = irq_setup_forced_threading(new);
+ if (ret)
+ goto out_mput;
+ }
}
/*
@@ -1120,37 +1204,14 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
* thread.
*/
if (new->thread_fn && !nested) {
- struct task_struct *t;
- static const struct sched_param param = {
- .sched_priority = MAX_USER_RT_PRIO/2,
- };
-
- t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
- new->name);
- if (IS_ERR(t)) {
- ret = PTR_ERR(t);
+ ret = setup_irq_thread(new, irq, false);
+ if (ret)
goto out_mput;
+ if (new->secondary) {
+ ret = setup_irq_thread(new->secondary, irq, true);
+ if (ret)
+ goto out_thread;
}
-
- sched_setscheduler_nocheck(t, SCHED_FIFO, ¶m);
-
- /*
- * We keep the reference to the task struct even if
- * the thread dies to avoid that the interrupt code
- * references an already freed task_struct.
- */
- get_task_struct(t);
- new->thread = t;
- /*
- * Tell the thread to set its affinity. This is
- * important for shared interrupt handlers as we do
- * not invoke setup_affinity() for the secondary
- * handlers as everything is already set up. Even for
- * interrupts marked with IRQF_NO_BALANCE this is
- * correct as we want the thread to move to the cpu(s)
- * on which the requesting code placed the interrupt.
- */
- set_bit(IRQTF_AFFINITY, &new->thread_flags);
}
if (!alloc_cpumask_var(&mask, GFP_KERNEL)) {
@@ -1326,7 +1387,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
irq, nmsk, omsk);
}
- new->irq = irq;
*old_ptr = new;
irq_pm_install_action(desc, new);
@@ -1352,6 +1412,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
*/
if (new->thread)
wake_up_process(new->thread);
+ if (new->secondary)
+ wake_up_process(new->secondary->thread);
register_irq_proc(irq, desc);
new->dir = NULL;
@@ -1382,6 +1444,13 @@ out_thread:
kthread_stop(t);
put_task_struct(t);
}
+ if (new->secondary && new->secondary->thread) {
+ struct task_struct *t = new->secondary->thread;
+
+ new->secondary->thread = NULL;
+ kthread_stop(t);
+ put_task_struct(t);
+ }
out_mput:
module_put(desc->owner);
return ret;
@@ -1489,9 +1558,14 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
if (action->thread) {
kthread_stop(action->thread);
put_task_struct(action->thread);
+ if (action->secondary && action->secondary->thread) {
+ kthread_stop(action->secondary->thread);
+ put_task_struct(action->secondary->thread);
+ }
}
module_put(desc->owner);
+ kfree(action->secondary);
return action;
}
@@ -1635,8 +1709,10 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
retval = __setup_irq(irq, desc, action);
chip_bus_sync_unlock(desc);
- if (retval)
+ if (retval) {
+ kfree(action->secondary);
kfree(action);
+ }
#ifdef CONFIG_DEBUG_SHIRQ_FIXME
if (!retval && (irqflags & IRQF_SHARED)) {
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index aaade2efc560..d0e1d0e48640 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -450,7 +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);
+ trace_preemptirqsoff_hist_rcuidle(IRQS_ON, 0);
if (!preempt_trace() && irq_trace())
stop_critical_timing(a0, a1);
}
@@ -459,7 +459,7 @@ void time_hardirqs_off(unsigned long a0, unsigned long a1)
{
if (!preempt_trace() && irq_trace())
start_critical_timing(a0, a1);
- trace_preemptirqsoff_hist(IRQS_OFF, 1);
+ trace_preemptirqsoff_hist_rcuidle(IRQS_OFF, 1);
}
#else /* !CONFIG_PROVE_LOCKING */
diff --git a/localversion-rt b/localversion-rt
index 045478966e9f..700c857efd9b 100644
--- a/localversion-rt
+++ b/localversion-rt
@@ -1 +1 @@
--rt7
+-rt8
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/