Merge tag 'kvm-x86-irqs-6.17' of https://github.com/kvm-x86/linux into HEAD

KVM IRQ changes for 6.17

 - Rework irqbypass to track/match producers and consumers via an xarray
   instead of a linked list.  Using a linked list leads to O(n^2) insertion
   times, which is hugely problematic for use cases that create large numbers
   of VMs.  Such use cases typically don't actually use irqbypass, but
   eliminating the pointless registration is a future problem to solve as it
   likely requires new uAPI.

 - Track irqbypass's "token" as "struct eventfd_ctx *" instead of a "void *",
   to avoid making a simple concept unnecessarily difficult to understand.

 - Add CONFIG_KVM_IOAPIC for x86 to allow disabling support for I/O APIC, PIC,
   and PIT emulation at compile time.

 - Drop x86's irq_comm.c, and move a pile of IRQ related code into irq.c.

 - Fix a variety of flaws and bugs in the AVIC device posted IRQ code.

 - Inhibited AVIC if a vCPU's ID is too big (relative to what hardware
   supports) instead of rejecting vCPU creation.

 - Extend enable_ipiv module param support to SVM, by simply leaving IsRunning
   clear in the vCPU's physical ID table entry.

 - Disable IPI virtualization, via enable_ipiv, if the CPU is affected by
   erratum #1235, to allow (safely) enabling AVIC on such CPUs.

 - Dedup x86's device posted IRQ code, as the vast majority of functionality
   can be shared verbatime between SVM and VMX.

 - Harden the device posted IRQ code against bugs and runtime errors.

 - Use vcpu_idx, not vcpu_id, for GA log tag/metadata, to make lookups O(1)
   instead of O(n).

 - Generate GA Log interrupts if and only if the target vCPU is blocking, i.e.
   only if KVM needs a notification in order to wake the vCPU.

 - Decouple device posted IRQs from VFIO device assignment, as binding a VM to
   a VFIO group is not a requirement for enabling device posted IRQs.

 - Clean up and document/comment the irqfd assignment code.

 - Disallow binding multiple irqfds to an eventfd with a priority waiter, i.e.
   ensure an eventfd is bound to at most one irqfd through the entire host,
   and add a selftest to verify eventfd:irqfd bindings are globally unique.

1 files changed, 2 insertions, 82 deletions

diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index fc7d0f8ff078..0b6b79b1a1bc 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -82,95 +82,15 @@ TRACE_EVENT(kvm_set_irq,
 	TP_printk("gsi %u level %d source %d",
 		  __entry->gsi, __entry->level, __entry->irq_source_id)
 );
-#endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */
-
-#if defined(__KVM_HAVE_IOAPIC)
-#define kvm_deliver_mode		\
-	{0x0, "Fixed"},			\
-	{0x1, "LowPrio"},		\
-	{0x2, "SMI"},			\
-	{0x3, "Res3"},			\
-	{0x4, "NMI"},			\
-	{0x5, "INIT"},			\
-	{0x6, "SIPI"},			\
-	{0x7, "ExtINT"}
-
-TRACE_EVENT(kvm_ioapic_set_irq,
-	    TP_PROTO(__u64 e, int pin, bool coalesced),
-	    TP_ARGS(e, pin, coalesced),
-
-	TP_STRUCT__entry(
-		__field(	__u64,		e		)
-		__field(	int,		pin		)
-		__field(	bool,		coalesced	)
-	),
-
-	TP_fast_assign(
-		__entry->e		= e;
-		__entry->pin		= pin;
-		__entry->coalesced	= coalesced;
-	),
-
-	TP_printk("pin %u dst %x vec %u (%s|%s|%s%s)%s",
-		  __entry->pin, (u8)(__entry->e >> 56), (u8)__entry->e,
-		  __print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode),
-		  (__entry->e & (1<<11)) ? "logical" : "physical",
-		  (__entry->e & (1<<15)) ? "level" : "edge",
-		  (__entry->e & (1<<16)) ? "|masked" : "",
-		  __entry->coalesced ? " (coalesced)" : "")
-);
-
-TRACE_EVENT(kvm_ioapic_delayed_eoi_inj,
-	    TP_PROTO(__u64 e),
-	    TP_ARGS(e),
-
-	TP_STRUCT__entry(
-		__field(	__u64,		e		)
-	),
 
-	TP_fast_assign(
-		__entry->e		= e;
-	),
-
-	TP_printk("dst %x vec %u (%s|%s|%s%s)",
-		  (u8)(__entry->e >> 56), (u8)__entry->e,
-		  __print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode),
-		  (__entry->e & (1<<11)) ? "logical" : "physical",
-		  (__entry->e & (1<<15)) ? "level" : "edge",
-		  (__entry->e & (1<<16)) ? "|masked" : "")
-);
-
-TRACE_EVENT(kvm_msi_set_irq,
-	    TP_PROTO(__u64 address, __u64 data),
-	    TP_ARGS(address, data),
-
-	TP_STRUCT__entry(
-		__field(	__u64,		address		)
-		__field(	__u64,		data		)
-	),
-
-	TP_fast_assign(
-		__entry->address	= address;
-		__entry->data		= data;
-	),
-
-	TP_printk("dst %llx vec %u (%s|%s|%s%s)",
-		  (u8)(__entry->address >> 12) | ((__entry->address >> 32) & 0xffffff00),
-		  (u8)__entry->data,
-		  __print_symbolic((__entry->data >> 8 & 0x7), kvm_deliver_mode),
-		  (__entry->address & (1<<2)) ? "logical" : "physical",
-		  (__entry->data & (1<<15)) ? "level" : "edge",
-		  (__entry->address & (1<<3)) ? "|rh" : "")
-);
+#ifdef CONFIG_KVM_IOAPIC
 
 #define kvm_irqchips						\
 	{KVM_IRQCHIP_PIC_MASTER,	"PIC master"},		\
 	{KVM_IRQCHIP_PIC_SLAVE,		"PIC slave"},		\
 	{KVM_IRQCHIP_IOAPIC,		"IOAPIC"}
 
-#endif /* defined(__KVM_HAVE_IOAPIC) */
-
-#if defined(CONFIG_HAVE_KVM_IRQCHIP)
+#endif /* CONFIG_KVM_IOAPIC */
 
 #ifdef kvm_irqchips
 #define kvm_ack_irq_string "irqchip %s pin %u"