[PATCH 4/5] x86/apic: Support 15 bits of APIC ID in IOAPIC/MSI where available

[David Woodhouse]

From: David Woodhouse <dwmw@xxxxxxxxxxxx>

Some hypervisors can allow the guest to use the Extended Destination ID
field in the IOAPIC RTE and MSI address to address up to 32768 CPUs.

Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx>
---
 arch/x86/include/asm/mpspec.h   |  1 +
 arch/x86/include/asm/x86_init.h |  2 ++
 arch/x86/kernel/apic/apic.c     | 15 ++++++++++++++-
 arch/x86/kernel/apic/msi.c      | 10 +++++++++-
 arch/x86/kernel/x86_init.c      |  1 +
 5 files changed, 27 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index e90ac7e9ae2c..25ee8ca0a1f2 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -42,6 +42,7 @@ extern DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
 extern unsigned int boot_cpu_physical_apicid;
 extern u8 boot_cpu_apic_version;
 extern unsigned long mp_lapic_addr;
+extern int msi_ext_dest_id;
 
 #ifdef CONFIG_X86_LOCAL_APIC
 extern int smp_found_config;
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 397196fae24d..5af3fe9e38f3 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -114,6 +114,7 @@ struct x86_init_pci {
  * @init_platform:		platform setup
  * @guest_late_init:		guest late init
  * @x2apic_available:		X2APIC detection
+ * @msi_ext_dest_id:		MSI and IOAPIC support 15-bit APIC IDs
  * @init_mem_mapping:		setup early mappings during init_mem_mapping()
  * @init_after_bootmem:		guest init after boot allocator is finished
  */
@@ -121,6 +122,7 @@ struct x86_hyper_init {
 	void (*init_platform)(void);
 	void (*guest_late_init)(void);
 	bool (*x2apic_available)(void);
+	bool (*msi_ext_dest_id)(void);
 	void (*init_mem_mapping)(void);
 	void (*init_after_bootmem)(void);
 };
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 113f6ca7b828..ba24a343c1f2 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1837,9 +1837,21 @@ static __init void x2apic_enable(void)
 
 static __init void try_to_enable_x2apic(int remap_mode)
 {
+	u32 apic_limit = 255;
+
 	if (x2apic_state == X2APIC_DISABLED)
 		return;
 
+	/*
+	 * If the hypervisor supports extended destination ID in IOAPIC
+	 * and MSI, that increases the maximum APIC ID that can be used
+	 * for non-remapped IRQ domains.
+	 */
+	if (x86_init.hyper.msi_ext_dest_id()) {
+		msi_ext_dest_id = 1;
+		apic_limit = 32767;
+	}
+
 	if (remap_mode != IRQ_REMAP_X2APIC_MODE) {
 		/*
 		 * Using X2APIC without IR is not architecturally supported
@@ -1856,9 +1868,10 @@ static __init void try_to_enable_x2apic(int remap_mode)
 		 * in physical mode, and CPUs with an APIC ID that cannnot
 		 * be addressed must not be brought online.
 		 */
-		x2apic_set_max_apicid(255);
+		x2apic_set_max_apicid(apic_limit);
 		x2apic_phys = 1;
 	}
+
 	x2apic_enable();
 }
 
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 2825e003259c..85206f971284 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -23,8 +23,11 @@
 
 struct irq_domain *x86_pci_msi_default_domain __ro_after_init;
 
+int msi_ext_dest_id __ro_after_init;
+
 static void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg,
 				  bool dmar)
+
 {
 	msg->address_hi = MSI_ADDR_BASE_HI;
 
@@ -46,10 +49,15 @@ static void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg,
 	 * Only the IOMMU itself can use the trick of putting destination
 	 * APIC ID into the high bits of the address. Anything else would
 	 * just be writing to memory if it tried that, and needs IR to
-	 * address higher APIC IDs.
+	 * address APICs which can't be addressed in the normal 32-bit
+	 * address range at 0xFFExxxxx. That is typically just 8 bits, but
+	 * some hypervisors allow the extended destination ID field in bits
+	 * 11-5 to be used, giving support for 15 bits of APIC IDs in total.
 	 */
 	if (dmar)
 		msg->address_hi |= MSI_ADDR_EXT_DEST_ID(cfg->dest_apicid);
+	else if (msi_ext_dest_id && cfg->dest_apicid < 0x8000)
+		msg->address_lo |= MSI_ADDR_EXT_DEST_ID(cfg->dest_apicid) >> 3;
 	else
 		WARN_ON_ONCE(MSI_ADDR_EXT_DEST_ID(cfg->dest_apicid));
 }
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index a3038d8deb6a..8b395821cb8d 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -110,6 +110,7 @@ struct x86_init_ops x86_init __initdata = {
 		.init_platform		= x86_init_noop,
 		.guest_late_init	= x86_init_noop,
 		.x2apic_available	= bool_x86_init_noop,
+		.msi_ext_dest_id	= bool_x86_init_noop,
 		.init_mem_mapping	= x86_init_noop,
 		.init_after_bootmem	= x86_init_noop,
 	},
-- 
2.26.2