Merge tag 'irqchip-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into irq/core
Pull irqchip and irqdomain updates from Marc Zyngier:
New HW support:
- New driver for the Nuvoton WPCM450 interrupt controller
- New driver for the IDT 79rc3243x interrupt controller
- Add support for interrupt trigger configuration to the MStar irqchip
- Add more external interrupt support to the STM32 irqchip
- Add new compatible strings for QCOM SC7280 to the qcom-pdc binding
Fixes and cleanups:
- Drop irq_create_strict_mappings() and irq_create_identity_mapping()
from the irqdomain API, with cleanups in a couple of drivers
- Fix nested NMI issue with spurious interrupts on GICv3
- Don't allow GICv4.1 vSGIs when the CPU doesn't support them
- Various cleanups and minor fixes
Link: https://lore.kernel.org/r/20210424094640.1731920-1-maz@kernel.org
diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c
index 316a994..e96a4e8 100644
--- a/drivers/atm/eni.c
+++ b/drivers/atm/eni.c
@@ -2054,7 +2054,7 @@
}
submitted++;
ATM_SKB(skb)->vcc = vcc;
- tasklet_disable(&ENI_DEV(vcc->dev)->task);
+ tasklet_disable_in_atomic(&ENI_DEV(vcc->dev)->task);
res = do_tx(skb);
tasklet_enable(&ENI_DEV(vcc->dev)->task);
if (res == enq_ok) return 0;
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 9811c40..17c9d82 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -2545,7 +2545,7 @@
struct driver_data *driver_data = packet->driver_data;
int ret = -ENOENT;
- tasklet_disable(&ctx->tasklet);
+ tasklet_disable_in_atomic(&ctx->tasklet);
if (packet->ack != 0)
goto out;
@@ -3465,7 +3465,7 @@
struct iso_context *ctx = container_of(base, struct iso_context, base);
int ret = 0;
- tasklet_disable(&ctx->context.tasklet);
+ tasklet_disable_in_atomic(&ctx->context.tasklet);
if (!test_and_set_bit_lock(0, &ctx->flushing_completions)) {
context_tasklet((unsigned long)&ctx->context);
diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index e622aee..440c35f 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -105,7 +105,7 @@
static inline void __tasklet_disable_sync_once(struct tasklet_struct *t)
{
if (!atomic_fetch_inc(&t->count))
- tasklet_unlock_wait(t);
+ tasklet_unlock_spin_wait(t);
}
static inline bool __tasklet_is_enabled(const struct tasklet_struct *t)
diff --git a/drivers/irqchip/irq-aspeed-vic.c b/drivers/irqchip/irq-aspeed-vic.c
index 6567ed7..58717cd 100644
--- a/drivers/irqchip/irq-aspeed-vic.c
+++ b/drivers/irqchip/irq-aspeed-vic.c
@@ -71,7 +71,7 @@
writel(0, vic->base + AVIC_INT_SELECT);
writel(0, vic->base + AVIC_INT_SELECT + 4);
- /* Some interrupts have a programable high/low level trigger
+ /* Some interrupts have a programmable high/low level trigger
* (4 GPIO direct inputs), for now we assume this was configured
* by firmware. We read which ones are edge now.
*/
@@ -203,7 +203,7 @@
}
vic->base = regs;
- /* Initialize soures, all masked */
+ /* Initialize sources, all masked */
vic_init_hw(vic);
/* Ready to receive interrupts */
diff --git a/drivers/irqchip/irq-bcm7120-l2.c b/drivers/irqchip/irq-bcm7120-l2.c
index c7c9e97..ad59656 100644
--- a/drivers/irqchip/irq-bcm7120-l2.c
+++ b/drivers/irqchip/irq-bcm7120-l2.c
@@ -309,7 +309,7 @@
if (data->can_wake) {
/* This IRQ chip can wake the system, set all
- * relevant child interupts in wake_enabled mask
+ * relevant child interrupts in wake_enabled mask
*/
gc->wake_enabled = 0xffffffff;
gc->wake_enabled &= ~gc->unused;
diff --git a/drivers/irqchip/irq-csky-apb-intc.c b/drivers/irqchip/irq-csky-apb-intc.c
index 5a2ec43..ab91afa 100644
--- a/drivers/irqchip/irq-csky-apb-intc.c
+++ b/drivers/irqchip/irq-csky-apb-intc.c
@@ -176,7 +176,7 @@
writel(0x0, reg_base + GX_INTC_NEN63_32);
/*
- * Initial mask reg with all unmasked, because we only use enalbe reg
+ * Initial mask reg with all unmasked, because we only use enable reg
*/
writel(0x0, reg_base + GX_INTC_NMASK31_00);
writel(0x0, reg_base + GX_INTC_NMASK63_32);
diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c
index fbec07d..4116b48 100644
--- a/drivers/irqchip/irq-gic-v2m.c
+++ b/drivers/irqchip/irq-gic-v2m.c
@@ -371,7 +371,7 @@
* the MSI data is the absolute value within the range from
* spi_start to (spi_start + num_spis).
*
- * Broadom NS2 GICv2m implementation has an erratum where the MSI data
+ * Broadcom NS2 GICv2m implementation has an erratum where the MSI data
* is 'spi_number - 32'
*
* Reading that register fails on the Graviton implementation
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index ed46e60..c3485b2 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -1492,7 +1492,7 @@
*
* Ideally, we'd issue a VMAPTI to set the doorbell to its LPI
* value or to 1023, depending on the enable bit. But that
- * would be issueing a mapping for an /existing/ DevID+EventID
+ * would be issuing a mapping for an /existing/ DevID+EventID
* pair, which is UNPREDICTABLE. Instead, let's issue a VMOVI
* to the /same/ vPE, using this opportunity to adjust the
* doorbell. Mouahahahaha. We loves it, Precious.
@@ -3122,7 +3122,7 @@
/*
* It's possible for CPU to receive VLPIs before it is
- * sheduled as a vPE, especially for the first CPU, and the
+ * scheduled as a vPE, especially for the first CPU, and the
* VLPI with INTID larger than 2^(IDbits+1) will be considered
* as out of range and dropped by GIC.
* So we initialize IDbits to known value to avoid VLPI drop.
@@ -3616,7 +3616,7 @@
/*
* If all interrupts have been freed, start mopping the
- * floor. This is conditionned on the device not being shared.
+ * floor. This is conditioned on the device not being shared.
*/
if (!its_dev->shared &&
bitmap_empty(its_dev->event_map.lpi_map,
@@ -4194,7 +4194,7 @@
{
/*
* There is no notion of affinity for virtual SGIs, at least
- * not on the host (since they can only be targetting a vPE).
+ * not on the host (since they can only be targeting a vPE).
* Tell the kernel we've done whatever it asked for.
*/
irq_data_update_effective_affinity(d, mask_val);
@@ -4239,7 +4239,7 @@
/*
* Locking galore! We can race against two different events:
*
- * - Concurent vPE affinity change: we must make sure it cannot
+ * - Concurrent vPE affinity change: we must make sure it cannot
* happen, or we'll talk to the wrong redistributor. This is
* identical to what happens with vLPIs.
*
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 0040402..37a23aa 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -1379,7 +1379,7 @@
/*
* Make it clear that broken DTs are... broken.
- * Partitionned PPIs are an unfortunate exception.
+ * Partitioned PPIs are an unfortunate exception.
*/
WARN_ON(*type == IRQ_TYPE_NONE &&
fwspec->param[0] != GIC_IRQ_TYPE_PARTITION);
diff --git a/drivers/irqchip/irq-loongson-pch-pic.c b/drivers/irqchip/irq-loongson-pch-pic.c
index 9bf6b9a..f790ca6 100644
--- a/drivers/irqchip/irq-loongson-pch-pic.c
+++ b/drivers/irqchip/irq-loongson-pch-pic.c
@@ -163,7 +163,7 @@
int i;
for (i = 0; i < PIC_COUNT; i++) {
- /* Write vectore ID */
+ /* Write vectored ID */
writeb(priv->ht_vec_base + i, priv->base + PCH_INT_HTVEC(i));
/* Hardcode route to HT0 Lo */
writeb(1, priv->base + PCH_INT_ROUTE(i));
diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c
index bc7aebc..e50676c 100644
--- a/drivers/irqchip/irq-meson-gpio.c
+++ b/drivers/irqchip/irq-meson-gpio.c
@@ -227,7 +227,7 @@
/*
* Get the hwirq number assigned to this channel through
- * a pointer the channel_irq table. The added benifit of this
+ * a pointer the channel_irq table. The added benefit of this
* method is that we can also retrieve the channel index with
* it, using the table base.
*/
diff --git a/drivers/irqchip/irq-mtk-cirq.c b/drivers/irqchip/irq-mtk-cirq.c
index 69ba8ce..9bca091 100644
--- a/drivers/irqchip/irq-mtk-cirq.c
+++ b/drivers/irqchip/irq-mtk-cirq.c
@@ -217,7 +217,7 @@
{
u32 value;
- /* flush recored interrupts, will send signals to parent controller */
+ /* flush recorded interrupts, will send signals to parent controller */
value = readl_relaxed(cirq_data->base + CIRQ_CONTROL);
writel_relaxed(value | CIRQ_FLUSH, cirq_data->base + CIRQ_CONTROL);
diff --git a/drivers/irqchip/irq-mxs.c b/drivers/irqchip/irq-mxs.c
index a671938..d1f5740 100644
--- a/drivers/irqchip/irq-mxs.c
+++ b/drivers/irqchip/irq-mxs.c
@@ -58,7 +58,7 @@
static struct icoll_priv icoll_priv;
static struct irq_domain *icoll_domain;
-/* calculate bit offset depending on number of intterupt per register */
+/* calculate bit offset depending on number of interrupt per register */
static u32 icoll_intr_bitshift(struct irq_data *d, u32 bit)
{
/*
@@ -68,7 +68,7 @@
return bit << ((d->hwirq & 3) << 3);
}
-/* calculate mem offset depending on number of intterupt per register */
+/* calculate mem offset depending on number of interrupt per register */
static void __iomem *icoll_intr_reg(struct irq_data *d)
{
/* offset = hwirq / intr_per_reg * 0x10 */
diff --git a/drivers/irqchip/irq-sun4i.c b/drivers/irqchip/irq-sun4i.c
index fb78d66..9ea9445 100644
--- a/drivers/irqchip/irq-sun4i.c
+++ b/drivers/irqchip/irq-sun4i.c
@@ -189,7 +189,7 @@
* 3) spurious irq
* So if we immediately get a reading of 0, check the irq-pending reg
* to differentiate between 2 and 3. We only do this once to avoid
- * the extra check in the common case of 1 hapening after having
+ * the extra check in the common case of 1 happening after having
* read the vector-reg once.
*/
hwirq = readl(irq_ic_data->irq_base + SUN4I_IRQ_VECTOR_REG) >> 2;
diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c
index 532d0ae..ca1f593 100644
--- a/drivers/irqchip/irq-ti-sci-inta.c
+++ b/drivers/irqchip/irq-ti-sci-inta.c
@@ -78,7 +78,7 @@
* struct ti_sci_inta_irq_domain - Structure representing a TISCI based
* Interrupt Aggregator IRQ domain.
* @sci: Pointer to TISCI handle
- * @vint: TISCI resource pointer representing IA inerrupts.
+ * @vint: TISCI resource pointer representing IA interrupts.
* @global_event: TISCI resource pointer representing global events.
* @vint_list: List of the vints active in the system
* @vint_mutex: Mutex to protect vint_list
diff --git a/drivers/irqchip/irq-vic.c b/drivers/irqchip/irq-vic.c
index e460363..62f3d29 100644
--- a/drivers/irqchip/irq-vic.c
+++ b/drivers/irqchip/irq-vic.c
@@ -163,7 +163,7 @@
};
/**
- * vic_pm_init - initicall to register VIC pm
+ * vic_pm_init - initcall to register VIC pm
*
* This is called via late_initcall() to register
* the resources for the VICs due to the early
@@ -397,7 +397,7 @@
/*
* The PL190 cell from ARM has been modified by ST to handle 64 interrupts.
* The original cell has 32 interrupts, while the modified one has 64,
- * replocating two blocks 0x00..0x1f in 0x20..0x3f. In that case
+ * replicating two blocks 0x00..0x1f in 0x20..0x3f. In that case
* the probe function is called twice, with base set to offset 000
* and 020 within the page. We call this "second block".
*/
diff --git a/drivers/irqchip/irq-xilinx-intc.c b/drivers/irqchip/irq-xilinx-intc.c
index 1d3d273..8cd1bfc 100644
--- a/drivers/irqchip/irq-xilinx-intc.c
+++ b/drivers/irqchip/irq-xilinx-intc.c
@@ -210,7 +210,7 @@
/*
* Disable all external interrupts until they are
- * explicity requested.
+ * explicitly requested.
*/
xintc_write(irqc, IER, 0);
diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c
index e3a8858..df0eab4 100644
--- a/drivers/net/ethernet/dlink/sundance.c
+++ b/drivers/net/ethernet/dlink/sundance.c
@@ -963,7 +963,7 @@
unsigned long flag;
netif_stop_queue(dev);
- tasklet_disable(&np->tx_tasklet);
+ tasklet_disable_in_atomic(&np->tx_tasklet);
iowrite16(0, ioaddr + IntrEnable);
printk(KERN_WARNING "%s: Transmit timed out, TxStatus %2.2x "
"TxFrameId %2.2x,"
diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index e9efe07..f1b9284 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -1265,9 +1265,9 @@
jwrite32f(jme, JME_APMC, apmc);
}
-static void jme_link_change_tasklet(struct tasklet_struct *t)
+static void jme_link_change_work(struct work_struct *work)
{
- struct jme_adapter *jme = from_tasklet(jme, t, linkch_task);
+ struct jme_adapter *jme = container_of(work, struct jme_adapter, linkch_task);
struct net_device *netdev = jme->dev;
int rc;
@@ -1510,7 +1510,7 @@
* all other events are ignored
*/
jwrite32(jme, JME_IEVE, intrstat);
- tasklet_schedule(&jme->linkch_task);
+ schedule_work(&jme->linkch_task);
goto out_reenable;
}
@@ -1832,7 +1832,6 @@
jme_clear_pm_disable_wol(jme);
JME_NAPI_ENABLE(jme);
- tasklet_setup(&jme->linkch_task, jme_link_change_tasklet);
tasklet_setup(&jme->txclean_task, jme_tx_clean_tasklet);
tasklet_setup(&jme->rxclean_task, jme_rx_clean_tasklet);
tasklet_setup(&jme->rxempty_task, jme_rx_empty_tasklet);
@@ -1920,7 +1919,7 @@
JME_NAPI_DISABLE(jme);
- tasklet_kill(&jme->linkch_task);
+ cancel_work_sync(&jme->linkch_task);
tasklet_kill(&jme->txclean_task);
tasklet_kill(&jme->rxclean_task);
tasklet_kill(&jme->rxempty_task);
@@ -3035,6 +3034,7 @@
atomic_set(&jme->rx_empty, 1);
tasklet_setup(&jme->pcc_task, jme_pcc_tasklet);
+ INIT_WORK(&jme->linkch_task, jme_link_change_work);
jme->dpi.cur = PCC_P1;
jme->reg_ghc = 0;
diff --git a/drivers/net/ethernet/jme.h b/drivers/net/ethernet/jme.h
index a2c3b00..2af7632 100644
--- a/drivers/net/ethernet/jme.h
+++ b/drivers/net/ethernet/jme.h
@@ -411,7 +411,7 @@
struct tasklet_struct rxempty_task;
struct tasklet_struct rxclean_task;
struct tasklet_struct txclean_task;
- struct tasklet_struct linkch_task;
+ struct work_struct linkch_task;
struct tasklet_struct pcc_task;
unsigned long flags;
u32 reg_txcs;
diff --git a/drivers/net/wireless/ath/ath9k/beacon.c b/drivers/net/wireless/ath/ath9k/beacon.c
index 71e2ada..72e2e71 100644
--- a/drivers/net/wireless/ath/ath9k/beacon.c
+++ b/drivers/net/wireless/ath/ath9k/beacon.c
@@ -251,7 +251,7 @@
int first_slot = ATH_BCBUF;
int slot;
- tasklet_disable(&sc->bcon_tasklet);
+ tasklet_disable_in_atomic(&sc->bcon_tasklet);
/* Find first taken slot. */
for (slot = 0; slot < ATH_BCBUF; slot++) {
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 27a17a1..a313708 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -1458,7 +1458,7 @@
* Prevents hv_pci_onchannelcallback() from running concurrently
* in the tasklet.
*/
- tasklet_disable(&channel->callback_event);
+ tasklet_disable_in_atomic(&channel->callback_event);
/*
* Since this function is called with IRQ locks held, can't
diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h
index a19519f..eed86eb 100644
--- a/include/linux/bottom_half.h
+++ b/include/linux/bottom_half.h
@@ -4,7 +4,7 @@
#include <linux/preempt.h>
-#ifdef CONFIG_TRACE_IRQFLAGS
+#if defined(CONFIG_PREEMPT_RT) || defined(CONFIG_TRACE_IRQFLAGS)
extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt);
#else
static __always_inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
@@ -32,4 +32,10 @@
__local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET);
}
+#ifdef CONFIG_PREEMPT_RT
+extern bool local_bh_blocked(void);
+#else
+static inline bool local_bh_blocked(void) { return false; }
+#endif
+
#endif /* _LINUX_BH_H */
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 7c9d6a2..69bc86e 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -6,6 +6,7 @@
#include <linux/preempt.h>
#include <linux/lockdep.h>
#include <linux/ftrace_irq.h>
+#include <linux/sched.h>
#include <linux/vtime.h>
#include <asm/hardirq.h>
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 967e257..4777850 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -61,6 +61,9 @@
* interrupt handler after suspending interrupts. For system
* wakeup devices users need to implement wakeup detection in
* their interrupt handlers.
+ * IRQF_NO_AUTOEN - Don't enable IRQ or NMI automatically when users request it.
+ * Users will enable it explicitly by enable_irq() or enable_nmi()
+ * later.
*/
#define IRQF_SHARED 0x00000080
#define IRQF_PROBE_SHARED 0x00000100
@@ -74,6 +77,7 @@
#define IRQF_NO_THREAD 0x00010000
#define IRQF_EARLY_RESUME 0x00020000
#define IRQF_COND_SUSPEND 0x00040000
+#define IRQF_NO_AUTOEN 0x00080000
#define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD)
@@ -654,26 +658,21 @@
TASKLET_STATE_RUN /* Tasklet is running (SMP only) */
};
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
static inline int tasklet_trylock(struct tasklet_struct *t)
{
return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state);
}
-static inline void tasklet_unlock(struct tasklet_struct *t)
-{
- smp_mb__before_atomic();
- clear_bit(TASKLET_STATE_RUN, &(t)->state);
-}
+void tasklet_unlock(struct tasklet_struct *t);
+void tasklet_unlock_wait(struct tasklet_struct *t);
+void tasklet_unlock_spin_wait(struct tasklet_struct *t);
-static inline void tasklet_unlock_wait(struct tasklet_struct *t)
-{
- while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { barrier(); }
-}
#else
-#define tasklet_trylock(t) 1
-#define tasklet_unlock_wait(t) do { } while (0)
-#define tasklet_unlock(t) do { } while (0)
+static inline int tasklet_trylock(struct tasklet_struct *t) { return 1; }
+static inline void tasklet_unlock(struct tasklet_struct *t) { }
+static inline void tasklet_unlock_wait(struct tasklet_struct *t) { }
+static inline void tasklet_unlock_spin_wait(struct tasklet_struct *t) { }
#endif
extern void __tasklet_schedule(struct tasklet_struct *t);
@@ -698,6 +697,17 @@
smp_mb__after_atomic();
}
+/*
+ * Do not use in new code. Disabling tasklets from atomic contexts is
+ * error prone and should be avoided.
+ */
+static inline void tasklet_disable_in_atomic(struct tasklet_struct *t)
+{
+ tasklet_disable_nosync(t);
+ tasklet_unlock_spin_wait(t);
+ smp_mb();
+}
+
static inline void tasklet_disable(struct tasklet_struct *t)
{
tasklet_disable_nosync(t);
@@ -712,7 +722,6 @@
}
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,
void (*func)(unsigned long), unsigned long data);
extern void tasklet_setup(struct tasklet_struct *t,
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 2efde6a..bee8280 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -116,7 +116,7 @@
* IRQ_SET_MASK_NOCPY - OK, chip did update irq_common_data.affinity
* IRQ_SET_MASK_OK_DONE - Same as IRQ_SET_MASK_OK for core. Special code to
* support stacked irqchips, which indicates skipping
- * all descendent irqchips.
+ * all descendant irqchips.
*/
enum {
IRQ_SET_MASK_OK = 0,
@@ -302,7 +302,7 @@
/*
* Must only be called of irqchip.irq_set_affinity() or low level
- * hieararchy domain allocation functions.
+ * hierarchy domain allocation functions.
*/
static inline void irqd_set_single_target(struct irq_data *d)
{
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 891b323..df46512 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -32,7 +32,7 @@
* @last_unhandled: aging timer for unhandled count
* @irqs_unhandled: stats field for spurious unhandled interrupts
* @threads_handled: stats field for deferred spurious detection of threaded handlers
- * @threads_handled_last: comparator field for deferred spurious detection of theraded handlers
+ * @threads_handled_last: comparator field for deferred spurious detection of threaded handlers
* @lock: locking for SMP
* @affinity_hint: hint to user space for preferred irq affinity
* @affinity_notify: context for notification of affinity changes
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 69cc8b6..9881eac 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -79,7 +79,11 @@
#define nmi_count() (preempt_count() & NMI_MASK)
#define hardirq_count() (preempt_count() & HARDIRQ_MASK)
-#define softirq_count() (preempt_count() & SOFTIRQ_MASK)
+#ifdef CONFIG_PREEMPT_RT
+# define softirq_count() (current->softirq_disable_cnt & SOFTIRQ_MASK)
+#else
+# define softirq_count() (preempt_count() & SOFTIRQ_MASK)
+#endif
#define irq_count() (nmi_count() | hardirq_count() | softirq_count())
/*
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index bd04f72..6d855ef 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -334,7 +334,8 @@
#define rcu_sleep_check() \
do { \
rcu_preempt_sleep_check(); \
- RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \
+ RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \
"Illegal context switch in RCU-bh read-side critical section"); \
RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map), \
"Illegal context switch in RCU-sched read-side critical section"); \
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ef00bb2..743a613 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1044,6 +1044,9 @@
int softirq_context;
int irq_config;
#endif
+#ifdef CONFIG_PREEMPT_RT
+ int softirq_disable_cnt;
+#endif
#ifdef CONFIG_LOCKDEP
# define MAX_LOCK_DEPTH 48UL
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 6d89e33..8cc8e571 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -761,7 +761,7 @@
* handle_edge_irq - edge type IRQ handler
* @desc: the interrupt description structure for this irq
*
- * Interrupt occures on the falling and/or rising edge of a hardware
+ * Interrupt occurs on the falling and/or rising edge of a hardware
* signal. The occurrence is latched into the irq controller hardware
* and must be acked in order to be reenabled. After the ack another
* interrupt can happen on the same source even before the first one
@@ -808,7 +808,7 @@
/*
* When another irq arrived while we were handling
* one, we could have masked the irq.
- * Renable it, if it was not disabled in meantime.
+ * Reenable it, if it was not disabled in meantime.
*/
if (unlikely(desc->istate & IRQS_PENDING)) {
if (!irqd_irq_disabled(&desc->irq_data) &&
@@ -1419,7 +1419,7 @@
* @dest: The affinity mask to set
* @force: Flag to enforce setting (disable online checks)
*
- * Conditinal, as the underlying parent chip might not implement it.
+ * Conditional, as the underlying parent chip might not implement it.
*/
int irq_chip_set_affinity_parent(struct irq_data *data,
const struct cpumask *dest, bool force)
@@ -1531,7 +1531,7 @@
#endif
/**
- * irq_chip_compose_msi_msg - Componse msi message for a irq chip
+ * irq_chip_compose_msi_msg - Compose msi message for a irq chip
* @data: Pointer to interrupt specific data
* @msg: Pointer to the MSI message
*
diff --git a/kernel/irq/dummychip.c b/kernel/irq/dummychip.c
index 0b0cdf2..7fe6cff 100644
--- a/kernel/irq/dummychip.c
+++ b/kernel/irq/dummychip.c
@@ -13,7 +13,7 @@
/*
* What should we do if we get a hw irq event on an illegal vector?
- * Each architecture has to answer this themself.
+ * Each architecture has to answer this themselves.
*/
static void ack_bad(struct irq_data *data)
{
diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c
index 43e3d1b..52f11c7 100644
--- a/kernel/irq/ipi.c
+++ b/kernel/irq/ipi.c
@@ -107,7 +107,7 @@
* @irq: linux irq number to be destroyed
* @dest: cpumask of cpus which should have the IPI removed
*
- * The IPIs allocated with irq_reserve_ipi() are retuerned to the system
+ * The IPIs allocated with irq_reserve_ipi() are returned to the system
* destroying all virqs associated with them.
*
* Return 0 on success or error code on failure.
diff --git a/kernel/irq/irq_sim.c b/kernel/irq/irq_sim.c
index 4800660..6e935d4 100644
--- a/kernel/irq/irq_sim.c
+++ b/kernel/irq/irq_sim.c
@@ -24,10 +24,6 @@
struct irq_sim_work_ctx *work_ctx;
};
-struct irq_sim_devres {
- struct irq_domain *domain;
-};
-
static void irq_sim_irqmask(struct irq_data *data)
{
struct irq_sim_irq_ctx *irq_ctx = irq_data_get_irq_chip_data(data);
@@ -216,11 +212,11 @@
}
EXPORT_SYMBOL_GPL(irq_domain_remove_sim);
-static void devm_irq_domain_release_sim(struct device *dev, void *res)
+static void devm_irq_domain_remove_sim(void *data)
{
- struct irq_sim_devres *this = res;
+ struct irq_domain *domain = data;
- irq_domain_remove_sim(this->domain);
+ irq_domain_remove_sim(domain);
}
/**
@@ -238,20 +234,17 @@
struct fwnode_handle *fwnode,
unsigned int num_irqs)
{
- struct irq_sim_devres *dr;
+ struct irq_domain *domain;
+ int ret;
- dr = devres_alloc(devm_irq_domain_release_sim,
- sizeof(*dr), GFP_KERNEL);
- if (!dr)
- return ERR_PTR(-ENOMEM);
+ domain = irq_domain_create_sim(fwnode, num_irqs);
+ if (IS_ERR(domain))
+ return domain;
- dr->domain = irq_domain_create_sim(fwnode, num_irqs);
- if (IS_ERR(dr->domain)) {
- devres_free(dr);
- return dr->domain;
- }
+ ret = devm_add_action_or_reset(dev, devm_irq_domain_remove_sim, domain);
+ if (ret)
+ return ERR_PTR(ret);
- devres_add(dev, dr);
- return dr->domain;
+ return domain;
}
EXPORT_SYMBOL_GPL(devm_irq_domain_create_sim);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index cc1a094..4a617d73 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -31,7 +31,7 @@
cpulist_parse(str, irq_default_affinity);
/*
* Set at least the boot cpu. We don't want to end up with
- * bugreports caused by random comandline masks
+ * bugreports caused by random commandline masks
*/
cpumask_set_cpu(smp_processor_id(), irq_default_affinity);
return 1;
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 6ab428f..f42ef868 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -62,7 +62,7 @@
* @name: Optional user provided domain name
* @pa: Optional user-provided physical address
*
- * Allocate a struct irqchip_fwid, and return a poiner to the embedded
+ * Allocate a struct irqchip_fwid, and return a pointer to the embedded
* fwnode_handle (or NULL on failure).
*
* Note: The types IRQCHIP_FWNODE_NAMED and IRQCHIP_FWNODE_NAMED_ID are
@@ -665,7 +665,7 @@
pr_debug("irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq);
- /* Look for default domain if nececssary */
+ /* Look for default domain if necessary */
if (domain == NULL)
domain = irq_default_domain;
if (domain == NULL) {
@@ -871,7 +871,7 @@
{
struct irq_data *data;
- /* Look for default domain if nececssary */
+ /* Look for default domain if necessary */
if (domain == NULL)
domain = irq_default_domain;
if (domain == NULL)
@@ -1401,7 +1401,7 @@
* The whole process to setup an IRQ has been split into two steps.
* The first step, __irq_domain_alloc_irqs(), is to allocate IRQ
* descriptor and required hardware resources. The second step,
- * irq_domain_activate_irq(), is to program hardwares with preallocated
+ * irq_domain_activate_irq(), is to program the hardware with preallocated
* resources. In this way, it's easier to rollback when failing to
* allocate resources.
*/
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index dec3f73..e976c49 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -179,7 +179,7 @@
/**
* irq_set_thread_affinity - Notify irq threads to adjust affinity
- * @desc: irq descriptor which has affitnity changed
+ * @desc: irq descriptor which has affinity changed
*
* We just set IRQTF_AFFINITY and delegate the affinity setting
* to the interrupt thread itself. We can not call
@@ -326,7 +326,7 @@
* If the interrupt is not yet activated, just store the affinity
* mask and do not call the chip driver at all. On activation the
* driver has to make sure anyway that the interrupt is in a
- * useable state so startup works.
+ * usable state so startup works.
*/
if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) ||
irqd_is_activated(data) || !irqd_affinity_on_activate(data))
@@ -1054,7 +1054,7 @@
* to IRQS_INPROGRESS and the irq line is masked forever.
*
* This also serializes the state of shared oneshot handlers
- * versus "desc->threads_onehsot |= action->thread_mask;" in
+ * versus "desc->threads_oneshot |= action->thread_mask;" in
* irq_wake_thread(). See the comment there which explains the
* serialization.
*/
@@ -1153,7 +1153,7 @@
/*
* Interrupts explicitly requested as threaded interrupts want to be
- * preemtible - many of them need to sleep and wait for slow busses to
+ * preemptible - many of them need to sleep and wait for slow busses to
* complete.
*/
static irqreturn_t irq_thread_fn(struct irq_desc *desc,
@@ -1693,7 +1693,8 @@
irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
}
- if (irq_settings_can_autoenable(desc)) {
+ if (!(new->flags & IRQF_NO_AUTOEN) &&
+ irq_settings_can_autoenable(desc)) {
irq_startup(desc, IRQ_RESEND, IRQ_START_COND);
} else {
/*
@@ -1908,7 +1909,7 @@
/* Last action releases resources */
if (!desc->action) {
/*
- * Reaquire bus lock as irq_release_resources() might
+ * Reacquire bus lock as irq_release_resources() might
* require it to deallocate resources over the slow bus.
*/
chip_bus_lock(desc);
@@ -2086,10 +2087,15 @@
* which interrupt is which (messes up the interrupt freeing
* logic etc).
*
+ * Also shared interrupts do not go well with disabling auto enable.
+ * The sharing interrupt might request it while it's still disabled
+ * and then wait for interrupts forever.
+ *
* Also IRQF_COND_SUSPEND only makes sense for shared interrupts and
* it cannot be set along with IRQF_NO_SUSPEND.
*/
if (((irqflags & IRQF_SHARED) && !dev_id) ||
+ ((irqflags & IRQF_SHARED) && (irqflags & IRQF_NO_AUTOEN)) ||
(!(irqflags & IRQF_SHARED) && (irqflags & IRQF_COND_SUSPEND)) ||
((irqflags & IRQF_NO_SUSPEND) && (irqflags & IRQF_COND_SUSPEND)))
return -EINVAL;
@@ -2245,7 +2251,8 @@
desc = irq_to_desc(irq);
- if (!desc || irq_settings_can_autoenable(desc) ||
+ if (!desc || (irq_settings_can_autoenable(desc) &&
+ !(irqflags & IRQF_NO_AUTOEN)) ||
!irq_settings_can_request(desc) ||
WARN_ON(irq_settings_is_per_cpu_devid(desc)) ||
!irq_supports_nmi(desc))
@@ -2742,7 +2749,7 @@
* irq_get_irqchip_state - returns the irqchip state of a interrupt.
* @irq: Interrupt line that is forwarded to a VM
* @which: One of IRQCHIP_STATE_* the caller wants to know about
- * @state: a pointer to a boolean where the state is to be storeed
+ * @state: a pointer to a boolean where the state is to be stored
*
* This call snapshots the internal irqchip state of an
* interrupt, returning into @state the bit corresponding to
diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c
index 651a4ad..578596e 100644
--- a/kernel/irq/matrix.c
+++ b/kernel/irq/matrix.c
@@ -337,15 +337,14 @@
* irq_matrix_reserve - Reserve interrupts
* @m: Matrix pointer
*
- * This is merily a book keeping call. It increments the number of globally
+ * This is merely a book keeping call. It increments the number of globally
* reserved interrupt bits w/o actually allocating them. This allows to
* setup interrupt descriptors w/o assigning low level resources to it.
* The actual allocation happens when the interrupt gets activated.
*/
void irq_matrix_reserve(struct irq_matrix *m)
{
- if (m->global_reserved <= m->global_available &&
- m->global_reserved + 1 > m->global_available)
+ if (m->global_reserved == m->global_available)
pr_warn("Interrupt reservation exceeds available resources\n");
m->global_reserved++;
@@ -356,7 +355,7 @@
* irq_matrix_remove_reserved - Remove interrupt reservation
* @m: Matrix pointer
*
- * This is merily a book keeping call. It decrements the number of globally
+ * This is merely a book keeping call. It decrements the number of globally
* reserved interrupt bits. This is used to undo irq_matrix_reserve() when the
* interrupt was never in use and a real vector allocated, which undid the
* reservation.
@@ -423,7 +422,9 @@
if (WARN_ON_ONCE(bit < m->alloc_start || bit >= m->alloc_end))
return;
- clear_bit(bit, cm->alloc_map);
+ if (WARN_ON_ONCE(!test_and_clear_bit(bit, cm->alloc_map)))
+ return;
+
cm->allocated--;
if(managed)
cm->managed_allocated--;
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index def48589..61ca924 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -7,7 +7,7 @@
/**
* irq_fixup_move_pending - Cleanup irq move pending from a dying CPU
- * @desc: Interrupt descpriptor to clean up
+ * @desc: Interrupt descriptor to clean up
* @force_clear: If set clear the move pending bit unconditionally.
* If not set, clear it only when the dying CPU is the
* last one in the pending mask.
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index b338d62..c41965e 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -5,7 +5,7 @@
*
* This file is licensed under GPLv2.
*
- * This file contains common code to support Message Signalled Interrupt for
+ * This file contains common code to support Message Signaled Interrupts for
* PCI compatible and non PCI compatible devices.
*/
#include <linux/types.h>
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 9813878..7c5cd42 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -144,7 +144,7 @@
if (!irq_can_set_affinity_usr(irq) || no_irq_affinity)
return -EIO;
- if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&new_value, GFP_KERNEL))
return -ENOMEM;
if (type)
@@ -238,7 +238,7 @@
cpumask_var_t new_value;
int err;
- if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&new_value, GFP_KERNEL))
return -ENOMEM;
err = cpumask_parse_user(buffer, count, new_value);
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index bd1d85c..0c46e9f 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -128,7 +128,7 @@
if (!try_retrigger(desc))
err = irq_sw_resend(desc);
- /* If the retrigger was successfull, mark it with the REPLAY bit */
+ /* If the retrigger was successful, mark it with the REPLAY bit */
if (!err)
desc->istate |= IRQS_REPLAY;
return err;
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index f865e5f..c481d84 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -403,6 +403,10 @@
desc->irqs_unhandled -= ok;
}
+ if (likely(!desc->irqs_unhandled))
+ return;
+
+ /* Now getting into unhandled irq detection */
desc->irq_count++;
if (likely(desc->irq_count < 100000))
return;
diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c
index 773b610..d309d6f 100644
--- a/kernel/irq/timings.c
+++ b/kernel/irq/timings.c
@@ -84,7 +84,7 @@
* 2. Log interval
*
* We saw the irq timings allow to compute the interval of the
- * occurrences for a specific interrupt. We can reasonibly assume the
+ * occurrences for a specific interrupt. We can reasonably assume the
* longer is the interval, the higher is the error for the next event
* and we can consider storing those interval values into an array
* where each slot in the array correspond to an interval at the power
@@ -416,7 +416,7 @@
* Copy the content of the circular buffer into another buffer
* in order to linearize the buffer instead of dealing with
* wrapping indexes and shifted array which will be prone to
- * error and extremelly difficult to debug.
+ * error and extremely difficult to debug.
*/
for (i = 0; i < count; i++) {
int index = (start + i) & IRQ_TIMINGS_MASK;
@@ -485,7 +485,7 @@
/*
* The interrupt triggered more than one second apart, that
- * ends the sequence as predictible for our purpose. In this
+ * ends the sequence as predictable for our purpose. In this
* case, assume we have the beginning of a sequence and the
* timestamp is the first value. As it is impossible to
* predict anything at this point, return.
@@ -514,7 +514,7 @@
* If more than the array size interrupts happened during the
* last busy/idle cycle, the index wrapped up and we have to
* begin with the next element in the array which is the last one
- * in the sequence, otherwise it is a the index 0.
+ * in the sequence, otherwise it is at the index 0.
*
* - have an indication of the interrupts activity on this CPU
* (eg. irq/sec)
diff --git a/kernel/profile.c b/kernel/profile.c
index 6f69a41..c2ebddb 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -430,7 +430,7 @@
cpumask_var_t new_value;
int err;
- if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&new_value, GFP_KERNEL))
return -ENOMEM;
err = cpumask_parse_user(buffer, count, new_value);
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 5f61165..2c36a5f 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -60,7 +60,7 @@
cpu = smp_processor_id();
delta = sched_clock_cpu(cpu) - irqtime->irq_start_time;
irqtime->irq_start_time += delta;
- pc = preempt_count() - offset;
+ pc = irq_count() - offset;
/*
* We do not account for softirq time from ksoftirqd here.
@@ -421,7 +421,7 @@
void vtime_account_irq(struct task_struct *tsk, unsigned int offset)
{
- unsigned int pc = preempt_count() - offset;
+ unsigned int pc = irq_count() - offset;
if (pc & HARDIRQ_OFFSET) {
vtime_account_hardirq(tsk);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 9908ec4a..5a99696 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -13,6 +13,7 @@
#include <linux/kernel_stat.h>
#include <linux/interrupt.h>
#include <linux/init.h>
+#include <linux/local_lock.h>
#include <linux/mm.h>
#include <linux/notifier.h>
#include <linux/percpu.h>
@@ -25,6 +26,7 @@
#include <linux/smpboot.h>
#include <linux/tick.h>
#include <linux/irq.h>
+#include <linux/wait_bit.h>
#include <asm/softirq_stack.h>
@@ -102,20 +104,204 @@
#endif
/*
- * preempt_count and SOFTIRQ_OFFSET usage:
- * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving
- * softirq processing.
- * - preempt_count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET)
+ * SOFTIRQ_OFFSET usage:
+ *
+ * On !RT kernels 'count' is the preempt counter, on RT kernels this applies
+ * to a per CPU counter and to task::softirqs_disabled_cnt.
+ *
+ * - count is changed by SOFTIRQ_OFFSET on entering or leaving softirq
+ * processing.
+ *
+ * - count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET)
* on local_bh_disable or local_bh_enable.
+ *
* This lets us distinguish between whether we are currently processing
* softirq and whether we just have bh disabled.
*/
+#ifdef CONFIG_PREEMPT_RT
-#ifdef CONFIG_TRACE_IRQFLAGS
/*
- * This is for softirq.c-internal use, where hardirqs are disabled
+ * RT accounts for BH disabled sections in task::softirqs_disabled_cnt and
+ * also in per CPU softirq_ctrl::cnt. This is necessary to allow tasks in a
+ * softirq disabled section to be preempted.
+ *
+ * The per task counter is used for softirq_count(), in_softirq() and
+ * in_serving_softirqs() because these counts are only valid when the task
+ * holding softirq_ctrl::lock is running.
+ *
+ * The per CPU counter prevents pointless wakeups of ksoftirqd in case that
+ * the task which is in a softirq disabled section is preempted or blocks.
+ */
+struct softirq_ctrl {
+ local_lock_t lock;
+ int cnt;
+};
+
+static DEFINE_PER_CPU(struct softirq_ctrl, softirq_ctrl) = {
+ .lock = INIT_LOCAL_LOCK(softirq_ctrl.lock),
+};
+
+/**
+ * local_bh_blocked() - Check for idle whether BH processing is blocked
+ *
+ * Returns false if the per CPU softirq::cnt is 0 otherwise true.
+ *
+ * This is invoked from the idle task to guard against false positive
+ * softirq pending warnings, which would happen when the task which holds
+ * softirq_ctrl::lock was the only running task on the CPU and blocks on
+ * some other lock.
+ */
+bool local_bh_blocked(void)
+{
+ return __this_cpu_read(softirq_ctrl.cnt) != 0;
+}
+
+void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
+{
+ unsigned long flags;
+ int newcnt;
+
+ WARN_ON_ONCE(in_hardirq());
+
+ /* First entry of a task into a BH disabled section? */
+ if (!current->softirq_disable_cnt) {
+ if (preemptible()) {
+ local_lock(&softirq_ctrl.lock);
+ /* Required to meet the RCU bottomhalf requirements. */
+ rcu_read_lock();
+ } else {
+ DEBUG_LOCKS_WARN_ON(this_cpu_read(softirq_ctrl.cnt));
+ }
+ }
+
+ /*
+ * Track the per CPU softirq disabled state. On RT this is per CPU
+ * state to allow preemption of bottom half disabled sections.
+ */
+ newcnt = __this_cpu_add_return(softirq_ctrl.cnt, cnt);
+ /*
+ * Reflect the result in the task state to prevent recursion on the
+ * local lock and to make softirq_count() & al work.
+ */
+ current->softirq_disable_cnt = newcnt;
+
+ if (IS_ENABLED(CONFIG_TRACE_IRQFLAGS) && newcnt == cnt) {
+ raw_local_irq_save(flags);
+ lockdep_softirqs_off(ip);
+ raw_local_irq_restore(flags);
+ }
+}
+EXPORT_SYMBOL(__local_bh_disable_ip);
+
+static void __local_bh_enable(unsigned int cnt, bool unlock)
+{
+ unsigned long flags;
+ int newcnt;
+
+ DEBUG_LOCKS_WARN_ON(current->softirq_disable_cnt !=
+ this_cpu_read(softirq_ctrl.cnt));
+
+ if (IS_ENABLED(CONFIG_TRACE_IRQFLAGS) && softirq_count() == cnt) {
+ raw_local_irq_save(flags);
+ lockdep_softirqs_on(_RET_IP_);
+ raw_local_irq_restore(flags);
+ }
+
+ newcnt = __this_cpu_sub_return(softirq_ctrl.cnt, cnt);
+ current->softirq_disable_cnt = newcnt;
+
+ if (!newcnt && unlock) {
+ rcu_read_unlock();
+ local_unlock(&softirq_ctrl.lock);
+ }
+}
+
+void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
+{
+ bool preempt_on = preemptible();
+ unsigned long flags;
+ u32 pending;
+ int curcnt;
+
+ WARN_ON_ONCE(in_irq());
+ lockdep_assert_irqs_enabled();
+
+ local_irq_save(flags);
+ curcnt = __this_cpu_read(softirq_ctrl.cnt);
+
+ /*
+ * If this is not reenabling soft interrupts, no point in trying to
+ * run pending ones.
+ */
+ if (curcnt != cnt)
+ goto out;
+
+ pending = local_softirq_pending();
+ if (!pending || ksoftirqd_running(pending))
+ goto out;
+
+ /*
+ * If this was called from non preemptible context, wake up the
+ * softirq daemon.
+ */
+ if (!preempt_on) {
+ wakeup_softirqd();
+ goto out;
+ }
+
+ /*
+ * Adjust softirq count to SOFTIRQ_OFFSET which makes
+ * in_serving_softirq() become true.
+ */
+ cnt = SOFTIRQ_OFFSET;
+ __local_bh_enable(cnt, false);
+ __do_softirq();
+
+out:
+ __local_bh_enable(cnt, preempt_on);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(__local_bh_enable_ip);
+
+/*
+ * Invoked from ksoftirqd_run() outside of the interrupt disabled section
+ * to acquire the per CPU local lock for reentrancy protection.
+ */
+static inline void ksoftirqd_run_begin(void)
+{
+ __local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
+ local_irq_disable();
+}
+
+/* Counterpart to ksoftirqd_run_begin() */
+static inline void ksoftirqd_run_end(void)
+{
+ __local_bh_enable(SOFTIRQ_OFFSET, true);
+ WARN_ON_ONCE(in_interrupt());
+ local_irq_enable();
+}
+
+static inline void softirq_handle_begin(void) { }
+static inline void softirq_handle_end(void) { }
+
+static inline bool should_wake_ksoftirqd(void)
+{
+ return !this_cpu_read(softirq_ctrl.cnt);
+}
+
+static inline void invoke_softirq(void)
+{
+ if (should_wake_ksoftirqd())
+ wakeup_softirqd();
+}
+
+#else /* CONFIG_PREEMPT_RT */
+
+/*
+ * This one is for softirq.c-internal use, where hardirqs are disabled
* legitimately:
*/
+#ifdef CONFIG_TRACE_IRQFLAGS
void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
{
unsigned long flags;
@@ -206,6 +392,32 @@
}
EXPORT_SYMBOL(__local_bh_enable_ip);
+static inline void softirq_handle_begin(void)
+{
+ __local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
+}
+
+static inline void softirq_handle_end(void)
+{
+ __local_bh_enable(SOFTIRQ_OFFSET);
+ WARN_ON_ONCE(in_interrupt());
+}
+
+static inline void ksoftirqd_run_begin(void)
+{
+ local_irq_disable();
+}
+
+static inline void ksoftirqd_run_end(void)
+{
+ local_irq_enable();
+}
+
+static inline bool should_wake_ksoftirqd(void)
+{
+ return true;
+}
+
static inline void invoke_softirq(void)
{
if (ksoftirqd_running(local_softirq_pending()))
@@ -250,6 +462,8 @@
local_irq_restore(flags);
}
+#endif /* !CONFIG_PREEMPT_RT */
+
/*
* We restart softirq processing for at most MAX_SOFTIRQ_RESTART times,
* but break the loop if need_resched() is set or after 2 ms.
@@ -318,7 +532,7 @@
pending = local_softirq_pending();
- __local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
+ softirq_handle_begin();
in_hardirq = lockdep_softirq_start();
account_softirq_enter(current);
@@ -354,8 +568,10 @@
pending >>= softirq_bit;
}
- if (__this_cpu_read(ksoftirqd) == current)
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT) &&
+ __this_cpu_read(ksoftirqd) == current)
rcu_softirq_qs();
+
local_irq_disable();
pending = local_softirq_pending();
@@ -369,8 +585,7 @@
account_softirq_exit(current);
lockdep_softirq_end(in_hardirq);
- __local_bh_enable(SOFTIRQ_OFFSET);
- WARN_ON_ONCE(in_interrupt());
+ softirq_handle_end();
current_restore_flags(old_flags, PF_MEMALLOC);
}
@@ -465,7 +680,7 @@
* Otherwise we wake up ksoftirqd to make sure we
* schedule the softirq soon.
*/
- if (!in_interrupt())
+ if (!in_interrupt() && should_wake_ksoftirqd())
wakeup_softirqd();
}
@@ -531,6 +746,20 @@
}
EXPORT_SYMBOL(__tasklet_hi_schedule);
+static bool tasklet_clear_sched(struct tasklet_struct *t)
+{
+ if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) {
+ wake_up_var(&t->state);
+ return true;
+ }
+
+ WARN_ONCE(1, "tasklet SCHED state not set: %s %pS\n",
+ t->use_callback ? "callback" : "func",
+ t->use_callback ? (void *)t->callback : (void *)t->func);
+
+ return false;
+}
+
static void tasklet_action_common(struct softirq_action *a,
struct tasklet_head *tl_head,
unsigned int softirq_nr)
@@ -550,13 +779,12 @@
if (tasklet_trylock(t)) {
if (!atomic_read(&t->count)) {
- if (!test_and_clear_bit(TASKLET_STATE_SCHED,
- &t->state))
- BUG();
- if (t->use_callback)
- t->callback(t);
- else
- t->func(t->data);
+ if (tasklet_clear_sched(t)) {
+ if (t->use_callback)
+ t->callback(t);
+ else
+ t->func(t->data);
+ }
tasklet_unlock(t);
continue;
}
@@ -606,21 +834,62 @@
}
EXPORT_SYMBOL(tasklet_init);
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
+/*
+ * Do not use in new code. Waiting for tasklets from atomic contexts is
+ * error prone and should be avoided.
+ */
+void tasklet_unlock_spin_wait(struct tasklet_struct *t)
+{
+ while (test_bit(TASKLET_STATE_RUN, &(t)->state)) {
+ if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+ /*
+ * Prevent a live lock when current preempted soft
+ * interrupt processing or prevents ksoftirqd from
+ * running. If the tasklet runs on a different CPU
+ * then this has no effect other than doing the BH
+ * disable/enable dance for nothing.
+ */
+ local_bh_disable();
+ local_bh_enable();
+ } else {
+ cpu_relax();
+ }
+ }
+}
+EXPORT_SYMBOL(tasklet_unlock_spin_wait);
+#endif
+
void tasklet_kill(struct tasklet_struct *t)
{
if (in_interrupt())
pr_notice("Attempt to kill tasklet from interrupt\n");
- while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
- do {
- yield();
- } while (test_bit(TASKLET_STATE_SCHED, &t->state));
- }
+ while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state))
+ wait_var_event(&t->state, !test_bit(TASKLET_STATE_SCHED, &t->state));
+
tasklet_unlock_wait(t);
- clear_bit(TASKLET_STATE_SCHED, &t->state);
+ tasklet_clear_sched(t);
}
EXPORT_SYMBOL(tasklet_kill);
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
+void tasklet_unlock(struct tasklet_struct *t)
+{
+ smp_mb__before_atomic();
+ clear_bit(TASKLET_STATE_RUN, &t->state);
+ smp_mb__after_atomic();
+ wake_up_var(&t->state);
+}
+EXPORT_SYMBOL_GPL(tasklet_unlock);
+
+void tasklet_unlock_wait(struct tasklet_struct *t)
+{
+ wait_var_event(&t->state, !test_bit(TASKLET_STATE_RUN, &t->state));
+}
+EXPORT_SYMBOL_GPL(tasklet_unlock_wait);
+#endif
+
void __init softirq_init(void)
{
int cpu;
@@ -643,53 +912,21 @@
static void run_ksoftirqd(unsigned int cpu)
{
- local_irq_disable();
+ ksoftirqd_run_begin();
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();
+ ksoftirqd_run_end();
cond_resched();
return;
}
- local_irq_enable();
+ ksoftirqd_run_end();
}
#ifdef CONFIG_HOTPLUG_CPU
-/*
- * tasklet_kill_immediate is called to remove a tasklet which can already be
- * scheduled for execution on @cpu.
- *
- * Unlike tasklet_kill, this function removes the tasklet
- * _immediately_, even if the tasklet is in TASKLET_STATE_SCHED state.
- *
- * When this function is called, @cpu must be in the CPU_DEAD state.
- */
-void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu)
-{
- struct tasklet_struct **i;
-
- BUG_ON(cpu_online(cpu));
- BUG_ON(test_bit(TASKLET_STATE_RUN, &t->state));
-
- if (!test_bit(TASKLET_STATE_SCHED, &t->state))
- return;
-
- /* CPU is dead, so no lock needed. */
- for (i = &per_cpu(tasklet_vec, cpu).head; *i; i = &(*i)->next) {
- if (*i == t) {
- *i = t->next;
- /* If this was the tail element, move the tail ptr */
- if (*i == NULL)
- per_cpu(tasklet_vec, cpu).tail = i;
- return;
- }
- }
- BUG();
-}
-
static int takeover_tasklets(unsigned int cpu)
{
/* CPU is dead, so no lock needed. */
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index e10a4af..0cc5579 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -973,7 +973,7 @@
if (unlikely(local_softirq_pending())) {
static int ratelimit;
- if (ratelimit < 10 &&
+ if (ratelimit < 10 && !local_bh_blocked() &&
(local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) {
pr_warn("NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #%02x!!!\n",
(unsigned int) local_softirq_pending());
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index eccb4e1..7607dc8 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4827,7 +4827,7 @@
cpumask_var_t tracing_cpumask_new;
int err;
- if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
return -ENOMEM;
err = cpumask_parse_user(ubuf, count, tracing_cpumask_new);
