[GIT pull] genirq updates for 5.0

[GIT pull] genirq updates for 5.0

[Thomas Gleixner]

Linus,

please pull the latest irq-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq-urgent-for-linus

A small set of fixes for the interrupt subsystem:

  - Fix a double increment in the irq descriptor allocator which causes
    that a sanity check is only done for every second affinity mask

  - Add a missing device tree translation in the stm32-exti driver. Without
    that the interrupt association is completely wrong.

  - Initialize the mutex in the GIC-V3 MBI driver

  - Fix the alignment for aliasing devices in the GIC-V3-ITS driver so
    multi MSI allocations work correctly

  - Ensure that the initial affinity of a interrupt is not empty at startup
    time.

  - Drop bogus include in the madera irq chip driver

  - Fix KernelDoc regression

Thanks,

	tglx

------------------>
Huacai Chen (1):
      genirq/irqdesc: Fix double increment in alloc_descs()

Jonathan Corbet (1):
      genirq: Fix the kerneldoc comment for struct irq_affinity_desc

Linus Walleij (1):
      irqchip/madera: Drop GPIO includes

Loic Pallardy (1):
      irqchip/stm32-exti: Add domain translate function

Marc Zyngier (1):
      irqchip/gic-v3-its: Align PCI Multi-MSI allocation on their size

Srinivas Ramana (1):
      genirq: Make sure the initial affinity is not empty

Yang Yingliang (1):
      irqchip/gic-v3-mbi: Fix uninitialized mbi_lock


 drivers/irqchip/irq-gic-v3-its.c | 25 +++++++++++++------------
 drivers/irqchip/irq-gic-v3-mbi.c |  2 +-
 drivers/irqchip/irq-madera.c     |  2 --
 drivers/irqchip/irq-stm32-exti.c |  1 +
 include/linux/interrupt.h        |  1 +
 kernel/irq/irqdesc.c             |  2 +-
 kernel/irq/manage.c              |  3 +++
 7 files changed, 20 insertions(+), 16 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index db20e992a40f..7f2a45445b00 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -2399,13 +2399,14 @@ static void its_free_device(struct its_device *its_dev)
 	kfree(its_dev);
 }
 
-static int its_alloc_device_irq(struct its_device *dev, irq_hw_number_t *hwirq)
+static int its_alloc_device_irq(struct its_device *dev, int nvecs, irq_hw_number_t *hwirq)
 {
 	int idx;
 
-	idx = find_first_zero_bit(dev->event_map.lpi_map,
-				  dev->event_map.nr_lpis);
-	if (idx == dev->event_map.nr_lpis)
+	idx = bitmap_find_free_region(dev->event_map.lpi_map,
+				      dev->event_map.nr_lpis,
+				      get_count_order(nvecs));
+	if (idx < 0)
 		return -ENOSPC;
 
 	*hwirq = dev->event_map.lpi_base + idx;
@@ -2501,21 +2502,21 @@ static int its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 	int err;
 	int i;
 
-	for (i = 0; i < nr_irqs; i++) {
-		err = its_alloc_device_irq(its_dev, &hwirq);
-		if (err)
-			return err;
+	err = its_alloc_device_irq(its_dev, nr_irqs, &hwirq);
+	if (err)
+		return err;
 
-		err = its_irq_gic_domain_alloc(domain, virq + i, hwirq);
+	for (i = 0; i < nr_irqs; i++) {
+		err = its_irq_gic_domain_alloc(domain, virq + i, hwirq + i);
 		if (err)
 			return err;
 
 		irq_domain_set_hwirq_and_chip(domain, virq + i,
-					      hwirq, &its_irq_chip, its_dev);
+					      hwirq + i, &its_irq_chip, its_dev);
 		irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(virq + i)));
 		pr_debug("ID:%d pID:%d vID:%d\n",
-			 (int)(hwirq - its_dev->event_map.lpi_base),
-			 (int) hwirq, virq + i);
+			 (int)(hwirq + i - its_dev->event_map.lpi_base),
+			 (int)(hwirq + i), virq + i);
 	}
 
 	return 0;
diff --git a/drivers/irqchip/irq-gic-v3-mbi.c b/drivers/irqchip/irq-gic-v3-mbi.c
index ad70e7c416e3..fbfa7ff6deb1 100644
--- a/drivers/irqchip/irq-gic-v3-mbi.c
+++ b/drivers/irqchip/irq-gic-v3-mbi.c
@@ -24,7 +24,7 @@ struct mbi_range {
 	unsigned long		*bm;
 };
 
-static struct mutex		mbi_lock;
+static DEFINE_MUTEX(mbi_lock);
 static phys_addr_t		mbi_phys_base;
 static struct mbi_range		*mbi_ranges;
 static unsigned int		mbi_range_nr;
diff --git a/drivers/irqchip/irq-madera.c b/drivers/irqchip/irq-madera.c
index e9256dee1a45..8b81271c823c 100644
--- a/drivers/irqchip/irq-madera.c
+++ b/drivers/irqchip/irq-madera.c
@@ -7,7 +7,6 @@
  */
 
 #include <linux/module.h>
-#include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
@@ -16,7 +15,6 @@
 #include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-#include <linux/of_gpio.h>
 #include <linux/of_irq.h>
 #include <linux/irqchip/irq-madera.h>
 #include <linux/mfd/madera/core.h>
diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c
index 6edfd4bfa169..a93296b9b45d 100644
--- a/drivers/irqchip/irq-stm32-exti.c
+++ b/drivers/irqchip/irq-stm32-exti.c
@@ -822,6 +822,7 @@ static int __init stm32_exti_init(const struct stm32_exti_drv_data *drv_data,
 static const struct irq_domain_ops stm32_exti_h_domain_ops = {
 	.alloc	= stm32_exti_h_domain_alloc,
 	.free	= irq_domain_free_irqs_common,
+	.xlate = irq_domain_xlate_twocell,
 };
 
 static int
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index c672f34235e7..4a728dba02e2 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -260,6 +260,7 @@ struct irq_affinity {
 /**
  * struct irq_affinity_desc - Interrupt affinity descriptor
  * @mask:	cpumask to hold the affinity assignment
+ * @is_managed: 1 if the interrupt is managed internally
  */
 struct irq_affinity_desc {
 	struct cpumask	mask;
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index ee062b7939d3..ef8ad36cadcf 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -457,7 +457,7 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node,
 
 	/* Validate affinity mask(s) */
 	if (affinity) {
-		for (i = 0; i < cnt; i++, i++) {
+		for (i = 0; i < cnt; i++) {
 			if (cpumask_empty(&affinity[i].mask))
 				return -EINVAL;
 		}
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index a4888ce4667a..84b54a17b95d 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -393,6 +393,9 @@ int irq_setup_affinity(struct irq_desc *desc)
 	}
 
 	cpumask_and(&mask, cpu_online_mask, set);
+	if (cpumask_empty(&mask))
+		cpumask_copy(&mask, cpu_online_mask);
+
 	if (node != NUMA_NO_NODE) {
 		const struct cpumask *nodemask = cpumask_of_node(node);
 

[GIT pull] locking updates for 5.0

[Thomas Gleixner]

Linus,

please pull the latest locking-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking-urgent-for-linus

A small series of fixes which all address possible missed wakeups:

 - Document and fix the wakeup ordering of wake_q

 - Add the missing barrier in rcuwait_wake_up(), which was documented in
   the comment but missing in the code

 - Fix the possible missed wakeups in the rwsem and futex code

Thanks,

	tglx

------------------>
Peter Zijlstra (3):
      sched/wake_q: Document wake_q_add()
      sched/wake_q: Fix wakeup ordering for wake_q
      futex: Fix (possible) missed wakeup

Prateek Sood (1):
      sched/wait: Fix rcuwait_wake_up() ordering

Xie Yongji (1):
      locking/rwsem: Fix (possible) missed wakeup


 include/linux/sched/wake_q.h |  6 +++++-
 kernel/exit.c                |  2 +-
 kernel/futex.c               | 13 ++++++++-----
 kernel/locking/rwsem-xadd.c  | 11 +++++++++--
 kernel/sched/core.c          | 19 ++++++++++++++++---
 5 files changed, 39 insertions(+), 12 deletions(-)

diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h
index 10b19a192b2d..545f37138057 100644
--- a/include/linux/sched/wake_q.h
+++ b/include/linux/sched/wake_q.h
@@ -24,9 +24,13 @@
  * called near the end of a function. Otherwise, the list can be
  * re-initialized for later re-use by wake_q_init().
  *
- * Note that this can cause spurious wakeups. schedule() callers
+ * 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.
+ *
+ * NOTE that there is no guarantee the wakeup will happen any later than the
+ * wake_q_add() location. Therefore task must be ready to be woken at the
+ * location of the wake_q_add().
  */
 
 #include <linux/sched.h>
diff --git a/kernel/exit.c b/kernel/exit.c
index 284f2fe9a293..3fb7be001964 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -307,7 +307,7 @@ void rcuwait_wake_up(struct rcuwait *w)
 	 *        MB (A)	      MB (B)
 	 *    [L] cond		  [L] tsk
 	 */
-	smp_rmb(); /* (B) */
+	smp_mb(); /* (B) */
 
 	/*
 	 * Avoid using task_rcu_dereference() magic as long as we are careful,
diff --git a/kernel/futex.c b/kernel/futex.c
index be3bff2315ff..fdd312da0992 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1452,11 +1452,7 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
 	if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n"))
 		return;
 
-	/*
-	 * Queue the task for later wakeup for after we've released
-	 * the hb->lock. wake_q_add() grabs reference to p.
-	 */
-	wake_q_add(wake_q, p);
+	get_task_struct(p);
 	__unqueue_futex(q);
 	/*
 	 * The waiting task can free the futex_q as soon as q->lock_ptr = NULL
@@ -1466,6 +1462,13 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
 	 * plist_del in __unqueue_futex().
 	 */
 	smp_store_release(&q->lock_ptr, NULL);
+
+	/*
+	 * Queue the task for later wakeup for after we've released
+	 * the hb->lock. wake_q_add() grabs reference to p.
+	 */
+	wake_q_add(wake_q, p);
+	put_task_struct(p);
 }
 
 /*
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 09b180063ee1..50d9af615dc4 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -198,15 +198,22 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
 		woken++;
 		tsk = waiter->task;
 
-		wake_q_add(wake_q, tsk);
+		get_task_struct(tsk);
 		list_del(&waiter->list);
 		/*
-		 * Ensure that the last operation is setting the reader
+		 * Ensure calling get_task_struct() before setting the reader
 		 * waiter to nil such that rwsem_down_read_failed() cannot
 		 * race with do_exit() by always holding a reference count
 		 * to the task to wakeup.
 		 */
 		smp_store_release(&waiter->task, NULL);
+		/*
+		 * Ensure issuing the wakeup (either by us or someone else)
+		 * after setting the reader waiter to nil.
+		 */
+		wake_q_add(wake_q, tsk);
+		/* wake_q_add() already take the task ref */
+		put_task_struct(tsk);
 	}
 
 	adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a674c7db2f29..d8d76a65cfdd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -396,6 +396,18 @@ static bool set_nr_if_polling(struct task_struct *p)
 #endif
 #endif
 
+/**
+ * wake_q_add() - queue a wakeup for 'later' waking.
+ * @head: the wake_q_head to add @task to
+ * @task: the task to queue for 'later' wakeup
+ *
+ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
+ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
+ * instantly.
+ *
+ * This function must be used as-if it were wake_up_process(); IOW the task
+ * must be ready to be woken at this location.
+ */
 void wake_q_add(struct wake_q_head *head, struct task_struct *task)
 {
 	struct wake_q_node *node = &task->wake_q;
@@ -405,10 +417,11 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
 	 * its already queued (either by us or someone else) and will get the
 	 * wakeup due to that.
 	 *
-	 * This cmpxchg() executes a full barrier, which pairs with the full
-	 * barrier executed by the wakeup in wake_up_q().
+	 * In order to ensure that a pending wakeup will observe our pending
+	 * state, even in the failed case, an explicit smp_mb() must be used.
 	 */
-	if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
+	smp_mb__before_atomic();
+	if (cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL))
 		return;
 
 	get_task_struct(task);

[GIT pull] timer updates for 5.0

[Thomas Gleixner]

Linus,

please pull the latest timers-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers-urgent-for-linus

A single regression fix to address the unintended breakage of posix cpu
timers. This is caused by a new sanity check in the common code, which
fails for posix cpu timers under certain conditions because the posix cpu
timer code never updates the variable which is checked.

Thanks,

	tglx

------------------>
Thomas Gleixner (1):
      posix-cpu-timers: Unbreak timer rearming


 kernel/time/posix-cpu-timers.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 8f0644af40be..80f955210861 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -685,6 +685,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 	 * set up the signal and overrun bookkeeping.
 	 */
 	timer->it.cpu.incr = timespec64_to_ns(&new->it_interval);
+	timer->it_interval = ns_to_ktime(timer->it.cpu.incr);
 
 	/*
 	 * This acts as a modification timestamp for the timer,

[GIT pull] x86/timer updates for 5.0

[Thomas Gleixner]

Linus,

please pull the latest x86-timers-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-timers-for-linus

Two commits which were missed to be sent during the merge window.

 - The TSC calibration fix turns out to be more urgent as recent Skylake-X
   systems seem to have massive trouble with calibration disturbance. This
   should go back into stable for that reason and it the risk of breakage
   is rather low.

 - Drop an unused define

Thanks,

	tglx

------------------>
Daniel Vacek (1):
      x86/tsc: Make calibration refinement more robust

Roland Dreier (1):
      x86/hpet: Remove unused FSEC_PER_NSEC define


 arch/x86/kernel/hpet.c |  4 ----
 arch/x86/kernel/tsc.c  | 30 ++++++++++++++++--------------
 2 files changed, 16 insertions(+), 18 deletions(-)

diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index b0acb22e5a46..dfd3aca82c61 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -21,10 +21,6 @@
 
 #define HPET_MASK			CLOCKSOURCE_MASK(32)
 
-/* FSEC = 10^-15
-   NSEC = 10^-9 */
-#define FSEC_PER_NSEC			1000000L
-
 #define HPET_DEV_USED_BIT		2
 #define HPET_DEV_USED			(1 << HPET_DEV_USED_BIT)
 #define HPET_DEV_VALID			0x8
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index e9f777bfed40..3fae23834069 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -297,15 +297,16 @@ static int __init tsc_setup(char *str)
 
 __setup("tsc=", tsc_setup);
 
-#define MAX_RETRIES     5
-#define SMI_TRESHOLD    50000
+#define MAX_RETRIES		5
+#define TSC_DEFAULT_THRESHOLD	0x20000
 
 /*
- * Read TSC and the reference counters. Take care of SMI disturbance
+ * Read TSC and the reference counters. Take care of any disturbances
  */
 static u64 tsc_read_refs(u64 *p, int hpet)
 {
 	u64 t1, t2;
+	u64 thresh = tsc_khz ? tsc_khz >> 5 : TSC_DEFAULT_THRESHOLD;
 	int i;
 
 	for (i = 0; i < MAX_RETRIES; i++) {
@@ -315,7 +316,7 @@ static u64 tsc_read_refs(u64 *p, int hpet)
 		else
 			*p = acpi_pm_read_early();
 		t2 = get_cycles();
-		if ((t2 - t1) < SMI_TRESHOLD)
+		if ((t2 - t1) < thresh)
 			return t2;
 	}
 	return ULLONG_MAX;
@@ -703,15 +704,15 @@ static unsigned long pit_hpet_ptimer_calibrate_cpu(void)
 	 * zero. In each wait loop iteration we read the TSC and check
 	 * the delta to the previous read. We keep track of the min
 	 * and max values of that delta. The delta is mostly defined
-	 * by the IO time of the PIT access, so we can detect when a
-	 * SMI/SMM disturbance happened between the two reads. If the
+	 * by the IO time of the PIT access, so we can detect when
+	 * any disturbance happened between the two reads. If the
 	 * maximum time is significantly larger than the minimum time,
 	 * then we discard the result and have another try.
 	 *
 	 * 2) Reference counter. If available we use the HPET or the
 	 * PMTIMER as a reference to check the sanity of that value.
 	 * We use separate TSC readouts and check inside of the
-	 * reference read for a SMI/SMM disturbance. We dicard
+	 * reference read for any possible disturbance. We dicard
 	 * disturbed values here as well. We do that around the PIT
 	 * calibration delay loop as we have to wait for a certain
 	 * amount of time anyway.
@@ -744,7 +745,7 @@ static unsigned long pit_hpet_ptimer_calibrate_cpu(void)
 		if (ref1 == ref2)
 			continue;
 
-		/* Check, whether the sampling was disturbed by an SMI */
+		/* Check, whether the sampling was disturbed */
 		if (tsc1 == ULLONG_MAX || tsc2 == ULLONG_MAX)
 			continue;
 
@@ -1268,7 +1269,7 @@ static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work);
  */
 static void tsc_refine_calibration_work(struct work_struct *work)
 {
-	static u64 tsc_start = -1, ref_start;
+	static u64 tsc_start = ULLONG_MAX, ref_start;
 	static int hpet;
 	u64 tsc_stop, ref_stop, delta;
 	unsigned long freq;
@@ -1283,14 +1284,15 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 	 * delayed the first time we expire. So set the workqueue
 	 * again once we know timers are working.
 	 */
-	if (tsc_start == -1) {
+	if (tsc_start == ULLONG_MAX) {
+restart:
 		/*
 		 * Only set hpet once, to avoid mixing hardware
 		 * if the hpet becomes enabled later.
 		 */
 		hpet = is_hpet_enabled();
-		schedule_delayed_work(&tsc_irqwork, HZ);
 		tsc_start = tsc_read_refs(&ref_start, hpet);
+		schedule_delayed_work(&tsc_irqwork, HZ);
 		return;
 	}
 
@@ -1300,9 +1302,9 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 	if (ref_start == ref_stop)
 		goto out;
 
-	/* Check, whether the sampling was disturbed by an SMI */
-	if (tsc_start == ULLONG_MAX || tsc_stop == ULLONG_MAX)
-		goto out;
+	/* Check, whether the sampling was disturbed */
+	if (tsc_stop == ULLONG_MAX)
+		goto restart;
 
 	delta = tsc_stop - tsc_start;
 	delta *= 1000000LL;

[GIT pull] x86 updates for 5.0

[Thomas Gleixner]

Linus,

please pull the latest x86-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-urgent-for-linus

A set of fixes for x86:

 - Fix the swapped outb() parameters in the KASLR code

 - Fix the PKEY handling at fork which missed to preserve the pkey state
   for the child. Comes with a test case to validate that.

 - Fix the entry stack handling for XEN PV to respect that XEN PV systems
   enter the function already on the current thread stack and not on the
   trampoline.

 - Fix kexec load failure caused by using a stale value when the kexec_buf
   structure is reused for subsequent allocations.

 - Fix a bogus sizeof() in the memory encryption code

 - Enforce PCI dependency for the Intel Low Power Subsystem

 - Enforce PCI_LOCKLESS_CONFIG when PCI is enabled

Thanks,

	tglx

------------------>
Daniel Drake (1):
      x86/kaslr: Fix incorrect i8254 outb() parameters

Dave Hansen (2):
      x86/pkeys: Properly copy pkey state at fork()
      x86/selftests/pkeys: Fork() to check for state being preserved

Dave Young (1):
      x86/kexec: Fix a kexec_file_load() failure

Jan Beulich (1):
      x86/entry/64/compat: Fix stack switching for XEN PV

Peng Hao (1):
      x86/mm/mem_encrypt: Fix erroneous sizeof()

Sinan Kaya (2):
      x86/intel/lpss: Make PCI dependency explicit
      x86/Kconfig: Select PCI_LOCKLESS_CONFIG if PCI is enabled


 arch/x86/Kconfig                              |  4 +--
 arch/x86/entry/entry_64_compat.S              |  6 ++--
 arch/x86/include/asm/mmu_context.h            | 18 ++++++++++++
 arch/x86/kernel/crash.c                       |  1 +
 arch/x86/kernel/kexec-bzimage64.c             |  2 ++
 arch/x86/lib/kaslr.c                          |  4 +--
 arch/x86/mm/mem_encrypt_identity.c            |  4 +--
 tools/testing/selftests/x86/protection_keys.c | 41 ++++++++++++++++++++-------
 8 files changed, 62 insertions(+), 18 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 15af091611e2..26387c7bf305 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -198,7 +198,7 @@ config X86
 	select IRQ_FORCED_THREADING
 	select NEED_SG_DMA_LENGTH
 	select PCI_DOMAINS			if PCI
-	select PCI_LOCKLESS_CONFIG
+	select PCI_LOCKLESS_CONFIG		if PCI
 	select PERF_EVENTS
 	select RTC_LIB
 	select RTC_MC146818_LIB
@@ -617,7 +617,7 @@ config X86_INTEL_QUARK
 
 config X86_INTEL_LPSS
 	bool "Intel Low Power Subsystem Support"
-	depends on X86 && ACPI
+	depends on X86 && ACPI && PCI
 	select COMMON_CLK
 	select PINCTRL
 	select IOSF_MBI
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 8eaf8952c408..39913770a44d 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -361,7 +361,8 @@ ENTRY(entry_INT80_compat)
 
 	/* Need to switch before accessing the thread stack. */
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
-	movq	%rsp, %rdi
+	/* In the Xen PV case we already run on the thread stack. */
+	ALTERNATIVE "movq %rsp, %rdi", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	pushq	6*8(%rdi)		/* regs->ss */
@@ -370,8 +371,9 @@ ENTRY(entry_INT80_compat)
 	pushq	3*8(%rdi)		/* regs->cs */
 	pushq	2*8(%rdi)		/* regs->ip */
 	pushq	1*8(%rdi)		/* regs->orig_ax */
-
 	pushq	(%rdi)			/* pt_regs->di */
+.Lint80_keep_stack:
+
 	pushq	%rsi			/* pt_regs->si */
 	xorl	%esi, %esi		/* nospec   si */
 	pushq	%rdx			/* pt_regs->dx */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 0ca50611e8ce..19d18fae6ec6 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -178,6 +178,10 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next)
 
 void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
 
+/*
+ * Init a new mm.  Used on mm copies, like at fork()
+ * and on mm's that are brand-new, like at execve().
+ */
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
@@ -228,8 +232,22 @@ do {						\
 } while (0)
 #endif
 
+static inline void arch_dup_pkeys(struct mm_struct *oldmm,
+				  struct mm_struct *mm)
+{
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+	if (!cpu_feature_enabled(X86_FEATURE_OSPKE))
+		return;
+
+	/* Duplicate the oldmm pkey state in mm: */
+	mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map;
+	mm->context.execute_only_pkey   = oldmm->context.execute_only_pkey;
+#endif
+}
+
 static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 {
+	arch_dup_pkeys(oldmm, mm);
 	paravirt_arch_dup_mmap(oldmm, mm);
 	return ldt_dup_context(oldmm, mm);
 }
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index c8b07d8ea5a2..17ffc869cab8 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -470,6 +470,7 @@ int crash_load_segments(struct kimage *image)
 
 	kbuf.memsz = kbuf.bufsz;
 	kbuf.buf_align = ELF_CORE_HEADER_ALIGN;
+	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	ret = kexec_add_buffer(&kbuf);
 	if (ret) {
 		vfree((void *)image->arch.elf_headers);
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 278cd07228dd..0d5efa34f359 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -434,6 +434,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 	kbuf.memsz = PAGE_ALIGN(header->init_size);
 	kbuf.buf_align = header->kernel_alignment;
 	kbuf.buf_min = MIN_KERNEL_LOAD_ADDR;
+	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	ret = kexec_add_buffer(&kbuf);
 	if (ret)
 		goto out_free_params;
@@ -448,6 +449,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 		kbuf.bufsz = kbuf.memsz = initrd_len;
 		kbuf.buf_align = PAGE_SIZE;
 		kbuf.buf_min = MIN_INITRD_LOAD_ADDR;
+		kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 		ret = kexec_add_buffer(&kbuf);
 		if (ret)
 			goto out_free_params;
diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c
index 79778ab200e4..a53665116458 100644
--- a/arch/x86/lib/kaslr.c
+++ b/arch/x86/lib/kaslr.c
@@ -36,8 +36,8 @@ static inline u16 i8254(void)
 	u16 status, timer;
 
 	do {
-		outb(I8254_PORT_CONTROL,
-		     I8254_CMD_READBACK | I8254_SELECT_COUNTER0);
+		outb(I8254_CMD_READBACK | I8254_SELECT_COUNTER0,
+		     I8254_PORT_CONTROL);
 		status = inb(I8254_PORT_COUNTER0);
 		timer  = inb(I8254_PORT_COUNTER0);
 		timer |= inb(I8254_PORT_COUNTER0) << 8;
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index a19ef1a416ff..4aa9b1480866 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -158,8 +158,8 @@ static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd)
 	pmd = pmd_offset(pud, ppd->vaddr);
 	if (pmd_none(*pmd)) {
 		pte = ppd->pgtable_area;
-		memset(pte, 0, sizeof(pte) * PTRS_PER_PTE);
-		ppd->pgtable_area += sizeof(pte) * PTRS_PER_PTE;
+		memset(pte, 0, sizeof(*pte) * PTRS_PER_PTE);
+		ppd->pgtable_area += sizeof(*pte) * PTRS_PER_PTE;
 		set_pmd(pmd, __pmd(PMD_FLAGS | __pa(pte)));
 	}
 
diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c
index 460b4bdf4c1e..5d546dcdbc80 100644
--- a/tools/testing/selftests/x86/protection_keys.c
+++ b/tools/testing/selftests/x86/protection_keys.c
@@ -1133,6 +1133,21 @@ void test_pkey_syscalls_bad_args(int *ptr, u16 pkey)
 	pkey_assert(err);
 }
 
+void become_child(void)
+{
+	pid_t forkret;
+
+	forkret = fork();
+	pkey_assert(forkret >= 0);
+	dprintf3("[%d] fork() ret: %d\n", getpid(), forkret);
+
+	if (!forkret) {
+		/* in the child */
+		return;
+	}
+	exit(0);
+}
+
 /* Assumes that all pkeys other than 'pkey' are unallocated */
 void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
 {
@@ -1141,7 +1156,7 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
 	int nr_allocated_pkeys = 0;
 	int i;
 
-	for (i = 0; i < NR_PKEYS*2; i++) {
+	for (i = 0; i < NR_PKEYS*3; i++) {
 		int new_pkey;
 		dprintf1("%s() alloc loop: %d\n", __func__, i);
 		new_pkey = alloc_pkey();
@@ -1152,20 +1167,26 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
 		if ((new_pkey == -1) && (errno == ENOSPC)) {
 			dprintf2("%s() failed to allocate pkey after %d tries\n",
 				__func__, nr_allocated_pkeys);
-			break;
+		} else {
+			/*
+			 * Ensure the number of successes never
+			 * exceeds the number of keys supported
+			 * in the hardware.
+			 */
+			pkey_assert(nr_allocated_pkeys < NR_PKEYS);
+			allocated_pkeys[nr_allocated_pkeys++] = new_pkey;
 		}
-		pkey_assert(nr_allocated_pkeys < NR_PKEYS);
-		allocated_pkeys[nr_allocated_pkeys++] = new_pkey;
+
+		/*
+		 * Make sure that allocation state is properly
+		 * preserved across fork().
+		 */
+		if (i == NR_PKEYS*2)
+			become_child();
 	}
 
 	dprintf3("%s()::%d\n", __func__, __LINE__);
 
-	/*
-	 * ensure it did not reach the end of the loop without
-	 * failure:
-	 */
-	pkey_assert(i < NR_PKEYS*2);
-
 	/*
 	 * There are 16 pkeys supported in hardware.  Three are
 	 * allocated by the time we get here:

Re: [GIT pull] genirq updates for 5.0

[pr-tracker-bot]

The pull request you sent on Sun, 27 Jan 2019 12:05:05 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/0d484375d73ad2ec39a395365449a70c200645b1

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT pull] genirq updates for 5.0

[Thomas Gleixner, Thomas Gleixner]

Linus,

please pull the latest irq-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq-urgent-for-linus

A small set of fixes for the interrupt subsystem:

  - Fix a double increment in the irq descriptor allocator which causes
    that a sanity check is only done for every second affinity mask

  - Add a missing device tree translation in the stm32-exti driver. Without
    that the interrupt association is completely wrong.

  - Initialize the mutex in the GIC-V3 MBI driver

  - Fix the alignment for aliasing devices in the GIC-V3-ITS driver so
    multi MSI allocations work correctly

  - Ensure that the initial affinity of a interrupt is not empty at startup
    time.

  - Drop bogus include in the madera irq chip driver

  - Fix KernelDoc regression

Thanks,

	tglx

------------------>
Huacai Chen (1):
      genirq/irqdesc: Fix double increment in alloc_descs()

Jonathan Corbet (1):
      genirq: Fix the kerneldoc comment for struct irq_affinity_desc

Linus Walleij (1):
      irqchip/madera: Drop GPIO includes

Loic Pallardy (1):
      irqchip/stm32-exti: Add domain translate function

Marc Zyngier (1):
      irqchip/gic-v3-its: Align PCI Multi-MSI allocation on their size

Srinivas Ramana (1):
      genirq: Make sure the initial affinity is not empty

Yang Yingliang (1):
      irqchip/gic-v3-mbi: Fix uninitialized mbi_lock


 drivers/irqchip/irq-gic-v3-its.c | 25 +++++++++++++------------
 drivers/irqchip/irq-gic-v3-mbi.c |  2 +-
 drivers/irqchip/irq-madera.c     |  2 --
 drivers/irqchip/irq-stm32-exti.c |  1 +
 include/linux/interrupt.h        |  1 +
 kernel/irq/irqdesc.c             |  2 +-
 kernel/irq/manage.c              |  3 +++
 7 files changed, 20 insertions(+), 16 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index db20e992a40f..7f2a45445b00 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -2399,13 +2399,14 @@ static void its_free_device(struct its_device *its_dev)
 	kfree(its_dev);
 }
 
-static int its_alloc_device_irq(struct its_device *dev, irq_hw_number_t *hwirq)
+static int its_alloc_device_irq(struct its_device *dev, int nvecs, irq_hw_number_t *hwirq)
 {
 	int idx;
 
-	idx = find_first_zero_bit(dev->event_map.lpi_map,
-				  dev->event_map.nr_lpis);
-	if (idx == dev->event_map.nr_lpis)
+	idx = bitmap_find_free_region(dev->event_map.lpi_map,
+				      dev->event_map.nr_lpis,
+				      get_count_order(nvecs));
+	if (idx < 0)
 		return -ENOSPC;
 
 	*hwirq = dev->event_map.lpi_base + idx;
@@ -2501,21 +2502,21 @@ static int its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 	int err;
 	int i;
 
-	for (i = 0; i < nr_irqs; i++) {
-		err = its_alloc_device_irq(its_dev, &hwirq);
-		if (err)
-			return err;
+	err = its_alloc_device_irq(its_dev, nr_irqs, &hwirq);
+	if (err)
+		return err;
 
-		err = its_irq_gic_domain_alloc(domain, virq + i, hwirq);
+	for (i = 0; i < nr_irqs; i++) {
+		err = its_irq_gic_domain_alloc(domain, virq + i, hwirq + i);
 		if (err)
 			return err;
 
 		irq_domain_set_hwirq_and_chip(domain, virq + i,
-					      hwirq, &its_irq_chip, its_dev);
+					      hwirq + i, &its_irq_chip, its_dev);
 		irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(virq + i)));
 		pr_debug("ID:%d pID:%d vID:%d\n",
-			 (int)(hwirq - its_dev->event_map.lpi_base),
-			 (int) hwirq, virq + i);
+			 (int)(hwirq + i - its_dev->event_map.lpi_base),
+			 (int)(hwirq + i), virq + i);
 	}
 
 	return 0;
diff --git a/drivers/irqchip/irq-gic-v3-mbi.c b/drivers/irqchip/irq-gic-v3-mbi.c
index ad70e7c416e3..fbfa7ff6deb1 100644
--- a/drivers/irqchip/irq-gic-v3-mbi.c
+++ b/drivers/irqchip/irq-gic-v3-mbi.c
@@ -24,7 +24,7 @@ struct mbi_range {
 	unsigned long		*bm;
 };
 
-static struct mutex		mbi_lock;
+static DEFINE_MUTEX(mbi_lock);
 static phys_addr_t		mbi_phys_base;
 static struct mbi_range		*mbi_ranges;
 static unsigned int		mbi_range_nr;
diff --git a/drivers/irqchip/irq-madera.c b/drivers/irqchip/irq-madera.c
index e9256dee1a45..8b81271c823c 100644
--- a/drivers/irqchip/irq-madera.c
+++ b/drivers/irqchip/irq-madera.c
@@ -7,7 +7,6 @@
  */
 
 #include <linux/module.h>
-#include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
@@ -16,7 +15,6 @@
 #include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-#include <linux/of_gpio.h>
 #include <linux/of_irq.h>
 #include <linux/irqchip/irq-madera.h>
 #include <linux/mfd/madera/core.h>
diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c
index 6edfd4bfa169..a93296b9b45d 100644
--- a/drivers/irqchip/irq-stm32-exti.c
+++ b/drivers/irqchip/irq-stm32-exti.c
@@ -822,6 +822,7 @@ static int __init stm32_exti_init(const struct stm32_exti_drv_data *drv_data,
 static const struct irq_domain_ops stm32_exti_h_domain_ops = {
 	.alloc	= stm32_exti_h_domain_alloc,
 	.free	= irq_domain_free_irqs_common,
+	.xlate = irq_domain_xlate_twocell,
 };
 
 static int
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index c672f34235e7..4a728dba02e2 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -260,6 +260,7 @@ struct irq_affinity {
 /**
  * struct irq_affinity_desc - Interrupt affinity descriptor
  * @mask:	cpumask to hold the affinity assignment
+ * @is_managed: 1 if the interrupt is managed internally
  */
 struct irq_affinity_desc {
 	struct cpumask	mask;
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index ee062b7939d3..ef8ad36cadcf 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -457,7 +457,7 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node,
 
 	/* Validate affinity mask(s) */
 	if (affinity) {
-		for (i = 0; i < cnt; i++, i++) {
+		for (i = 0; i < cnt; i++) {
 			if (cpumask_empty(&affinity[i].mask))
 				return -EINVAL;
 		}
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index a4888ce4667a..84b54a17b95d 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -393,6 +393,9 @@ int irq_setup_affinity(struct irq_desc *desc)
 	}
 
 	cpumask_and(&mask, cpu_online_mask, set);
+	if (cpumask_empty(&mask))
+		cpumask_copy(&mask, cpu_online_mask);
+
 	if (node != NUMA_NO_NODE) {
 		const struct cpumask *nodemask = cpumask_of_node(node);