x86/apic/msi: Fix misconfigured non-maskable MSI quirk

commit b56ebe7c896dc78b5865ec2c4b1dae3c93537517 upstream.

commit ef8dd01538ea ("genirq/msi: Make interrupt allocation less
convoluted"), reworked the code so that the x86 specific quirk for affinity
setting of non-maskable PCI/MSI interrupts is not longer activated if
necessary.

This could be solved by restoring the original logic in the core MSI code,
but after a deeper analysis it turned out that the quirk flag is not
required at all.

The quirk is only required when the PCI/MSI device cannot mask the MSI
interrupts, which in turn also prevents reservation mode from being enabled
for the affected interrupt.

This allows ot remove the NOMASK quirk bit completely as msi_set_affinity()
can instead check whether reservation mode is enabled for the interrupt,
which gives exactly the same answer.

Even in the momentary non-existing case that the reservation mode would be
not set for a maskable MSI interrupt this would not cause any harm as it
just would cause msi_set_affinity() to go needlessly through the
functionaly equivalent slow path, which works perfectly fine with maskable
interrupts as well.

Rework msi_set_affinity() to query the reservation mode and remove all
NOMASK quirk logic from the core code.

[ tglx: Massaged changelog ]

Fixes: ef8dd01538ea ("genirq/msi: Make interrupt allocation less convoluted")
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Koichiro Den <den@valinux.co.jp>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20231026032036.2462428-1-den@valinux.co.jp
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 7517eb05bdc1a22c999b4598bd0f228113259ad8..ab348aec86632adedf0149aa668f07e4547b3c55 100644 (file)
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -55,14 +55,14 @@ msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force)
         * caused by the non-atomic update of the address/data pair.
         *
         * Direct update is possible when:
-        * - The MSI is maskable (remapped MSI does not use this code path)).
-        *   The quirk bit is not set in this case.
+        * - The MSI is maskable (remapped MSI does not use this code path).
+        *   The reservation mode bit is set in this case.
         * - The new vector is the same as the old vector
         * - The old vector is MANAGED_IRQ_SHUTDOWN_VECTOR (interrupt starts up)
         * - The interrupt is not yet started up
         * - The new destination CPU is the same as the old destination CPU
         */
-       if (!irqd_msi_nomask_quirk(irqd) ||
+       if (!irqd_can_reserve(irqd) ||
            cfg->vector == old_cfg.vector ||
            old_cfg.vector == MANAGED_IRQ_SHUTDOWN_VECTOR ||
            !irqd_is_started(irqd) ||
@@ -202,8 +202,6 @@ struct irq_domain * __init native_create_pci_msi_domain(void)
        if (!d) {
                irq_domain_free_fwnode(fn);
                pr_warn("Failed to initialize PCI-MSI irqdomain.\n");
-       } else {
-               d->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK;
        }
        return d;
 }

diff --git a/include/linux/irq.h b/include/linux/irq.h
index c3eb89606c2b17c01a930211080038eb5db7f157..06c692cc0accb8e989d905418cb25c0591b7c1a3 100644 (file)
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -215,8 +215,6 @@ struct irq_data {
  * IRQD_SINGLE_TARGET          - IRQ allows only a single affinity target
  * IRQD_DEFAULT_TRIGGER_SET    - Expected trigger already been set
  * IRQD_CAN_RESERVE            - Can use reservation mode
- * IRQD_MSI_NOMASK_QUIRK       - Non-maskable MSI quirk for affinity change
- *                               required
  * IRQD_HANDLE_ENFORCE_IRQCTX  - Enforce that handle_irq_*() is only invoked
  *                               from actual interrupt context.
  * IRQD_AFFINITY_ON_ACTIVATE   - Affinity is set on activation. Don't call
@@ -245,10 +243,9 @@ enum {
        IRQD_SINGLE_TARGET              = (1 << 24),
        IRQD_DEFAULT_TRIGGER_SET        = (1 << 25),
        IRQD_CAN_RESERVE                = (1 << 26),
-       IRQD_MSI_NOMASK_QUIRK           = (1 << 27),
-       IRQD_HANDLE_ENFORCE_IRQCTX      = (1 << 28),
-       IRQD_AFFINITY_ON_ACTIVATE       = (1 << 29),
-       IRQD_IRQ_ENABLED_ON_SUSPEND     = (1 << 30),
+       IRQD_HANDLE_ENFORCE_IRQCTX      = (1 << 27),
+       IRQD_AFFINITY_ON_ACTIVATE       = (1 << 28),
+       IRQD_IRQ_ENABLED_ON_SUSPEND     = (1 << 29),
 };
 
 #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors)
@@ -423,21 +420,6 @@ static inline bool irqd_can_reserve(struct irq_data *d)
        return __irqd_to_state(d) & IRQD_CAN_RESERVE;
 }
 
-static inline void irqd_set_msi_nomask_quirk(struct irq_data *d)
-{
-       __irqd_to_state(d) |= IRQD_MSI_NOMASK_QUIRK;
-}
-
-static inline void irqd_clr_msi_nomask_quirk(struct irq_data *d)
-{
-       __irqd_to_state(d) &= ~IRQD_MSI_NOMASK_QUIRK;
-}
-
-static inline bool irqd_msi_nomask_quirk(struct irq_data *d)
-{
-       return __irqd_to_state(d) & IRQD_MSI_NOMASK_QUIRK;
-}
-
 static inline void irqd_set_affinity_on_activate(struct irq_data *d)
 {
        __irqd_to_state(d) |= IRQD_AFFINITY_ON_ACTIVATE;

diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c
index bbcaac64038ef7e4e01cdaa298f15b081f3a67b1..0b78fac882b2b43170da67465561f18be45c1e5e 100644 (file)
--- a/kernel/irq/debugfs.c
+++ b/kernel/irq/debugfs.c
@@ -121,7 +121,6 @@ static const struct irq_bit_descr irqdata_states[] = {
        BIT_MASK_DESCR(IRQD_AFFINITY_ON_ACTIVATE),
        BIT_MASK_DESCR(IRQD_MANAGED_SHUTDOWN),
        BIT_MASK_DESCR(IRQD_CAN_RESERVE),
-       BIT_MASK_DESCR(IRQD_MSI_NOMASK_QUIRK),
 
        BIT_MASK_DESCR(IRQD_FORWARDED_TO_VCPU),
 

diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 77e513e2e5da7ea1ccb2fc7ecebc39d25c40dbde..4e462b5f7bbe891a796834aecc6dc4bdefa2a115 100644 (file)
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -807,7 +807,6 @@ static int msi_handle_pci_fail(struct irq_domain *domain, struct msi_desc *desc,
 
 #define VIRQ_CAN_RESERVE       0x01
 #define VIRQ_ACTIVATE          0x02
-#define VIRQ_NOMASK_QUIRK      0x04
 
 static int msi_init_virq(struct irq_domain *domain, int virq, unsigned int vflags)
 {
@@ -816,8 +815,6 @@ static int msi_init_virq(struct irq_domain *domain, int virq, unsigned int vflag
 
        if (!(vflags & VIRQ_CAN_RESERVE)) {
                irqd_clr_can_reserve(irqd);
-               if (vflags & VIRQ_NOMASK_QUIRK)
-                       irqd_set_msi_nomask_quirk(irqd);
 
                /*
                 * If the interrupt is managed but no CPU is available to
@@ -877,15 +874,8 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
         * Interrupt can use a reserved vector and will not occupy
         * a real device vector until the interrupt is requested.
         */
-       if (msi_check_reservation_mode(domain, info, dev)) {
+       if (msi_check_reservation_mode(domain, info, dev))
                vflags |= VIRQ_CAN_RESERVE;
-               /*
-                * MSI affinity setting requires a special quirk (X86) when
-                * reservation mode is active.
-                */
-               if (domain->flags & IRQ_DOMAIN_MSI_NOMASK_QUIRK)
-                       vflags |= VIRQ_NOMASK_QUIRK;
-       }
 
        msi_for_each_desc(desc, dev, MSI_DESC_NOTASSOCIATED) {
                ops->set_desc(&arg, desc);