From: Thomas Gleixner <tglx@linutronix.de>

To support posted MSIs, create a posted interrupt descriptor (PID) for each
host CPU. Later on, when setting up IRQ CPU affinity, IOMMU's interrupt
remapping table entry (IRTE) will point to the physical address of the
matching CPU's PID.

Each PID is initialized with the owner CPU's physical APICID as the
destination.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
---
 arch/x86/include/asm/hardirq.h     |  3 +++
 arch/x86/include/asm/posted_intr.h |  7 +++++++
 arch/x86/kernel/cpu/common.c       |  3 +++
 arch/x86/kernel/irq.c              | 16 ++++++++++++++++
 4 files changed, 29 insertions(+)

diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 66837b8c67f1..72c6a084dba3 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -48,6 +48,9 @@ typedef struct {
 
 DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 
+#ifdef CONFIG_X86_POSTED_MSI
+DECLARE_PER_CPU_ALIGNED(struct pi_desc, posted_interrupt_desc);
+#endif
 #define __ARCH_IRQ_STAT
 
 #define inc_irq_stat(member)	this_cpu_inc(irq_stat.member)
diff --git a/arch/x86/include/asm/posted_intr.h b/arch/x86/include/asm/posted_intr.h
index 896b3462f3dd..a36cc971ea13 100644
--- a/arch/x86/include/asm/posted_intr.h
+++ b/arch/x86/include/asm/posted_intr.h
@@ -88,4 +88,11 @@ static inline bool pi_test_sn(struct pi_desc *pi_desc)
 	return test_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control);
 }
 
+#ifdef CONFIG_X86_POSTED_MSI
+extern void intel_posted_msi_init(void);
+
+#else
+static inline void intel_posted_msi_init(void) {};
+
+#endif /* X86_POSTED_MSI */
 #endif /* _X86_POSTED_INTR_H */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 0b97bcde70c6..9b6248e7c073 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -67,6 +67,7 @@
 #include <asm/traps.h>
 #include <asm/sev.h>
 #include <asm/tdx.h>
+#include <asm/posted_intr.h>
 
 #include "cpu.h"
 
@@ -2253,6 +2254,8 @@ void cpu_init(void)
 		barrier();
 
 		x2apic_setup();
+
+		intel_posted_msi_init();
 	}
 
 	mmgrab(&init_mm);
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 11761c124545..f6546f83d616 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -22,6 +22,8 @@
 #include <asm/desc.h>
 #include <asm/traps.h>
 #include <asm/thermal.h>
+#include <asm/posted_intr.h>
+#include <asm/irq_remapping.h>
 
 #define CREATE_TRACE_POINTS
 #include <asm/trace/irq_vectors.h>
@@ -334,6 +336,20 @@ DEFINE_IDTENTRY_SYSVEC_SIMPLE(sysvec_kvm_posted_intr_nested_ipi)
 }
 #endif
 
+#ifdef CONFIG_X86_POSTED_MSI
+
+/* Posted Interrupt Descriptors for coalesced MSIs to be posted */
+DEFINE_PER_CPU_ALIGNED(struct pi_desc, posted_interrupt_desc);
+
+void intel_posted_msi_init(void)
+{
+	struct pi_desc *pid = this_cpu_ptr(&posted_interrupt_desc);
+
+	pid->nv = POSTED_MSI_NOTIFICATION_VECTOR;
+	pid->ndst = this_cpu_read(x86_cpu_to_apicid);
+}
+}
+#endif /* X86_POSTED_MSI */
 
 #ifdef CONFIG_HOTPLUG_CPU
 /* A cpu has been removed from cpu_online_mask.  Reset irq affinities. */
-- 
2.25.1

On Fri, 26 Jan 2024 15:42:28 -0800, Jacob Pan
<jacob.jun.pan@linux.intel.com> wrote:
I have made a couple of mistakes here, caught by LKP testing.
Reported by Oliver Sang.

>  
> +#ifdef CONFIG_X86_POSTED_MSI
> +
> +/* Posted Interrupt Descriptors for coalesced MSIs to be posted */
> +DEFINE_PER_CPU_ALIGNED(struct pi_desc, posted_interrupt_desc);
> +
> +void intel_posted_msi_init(void)
> +{
> +	struct pi_desc *pid = this_cpu_ptr(&posted_interrupt_desc);
> +
> +	pid->nv = POSTED_MSI_NOTIFICATION_VECTOR;
> +	pid->ndst = this_cpu_read(x86_cpu_to_apicid);
Based on VT-d specification 9.11, middle portion of the 32 bit field
are used in xAPIC mode instead of the lowest 8 bit. Not sure why it was
designed this way, making sure people ready the spec carefully :)

xAPIC Mode (Physical): 
 319:304 - Reserved (0)
 303:296 - APIC DestinationID[7:0]
 295:288 - Reserved (0)
x2APIC Mode (Physical):
 319:288 - APIC DestinationID[31:0]

So it should be something like:
	pid->ndst = x2apic_enabled() ? apic_id : apic_id << 8;

> +}
> +}
partitioning mistake, will fix.

> +#endif /* X86_POSTED_MSI */

Thanks,

Jacob