Linux-HyperV Archive on lore.kernel.org
 help / color / Atom feed
From: David Woodhouse <dwmw2@infradead.org>
To: x86@kernel.org
Cc: iommu <iommu@lists.linux-foundation.org>,
	kvm <kvm@vger.kernel.org>,
	linux-hyperv@vger.kernel.org, Paolo Bonzini <pbonzini@redhat.com>
Subject: [PATCH 04/13] x86/apic: Support 15 bits of APIC ID in IOAPIC/MSI where available
Date: Mon,  5 Oct 2020 16:28:47 +0100
Message-ID: <20201005152856.974112-4-dwmw2@infradead.org> (raw)
In-Reply-To: <20201005152856.974112-1-dwmw2@infradead.org>

From: David Woodhouse <dwmw@amazon.co.uk>

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@amazon.co.uk>
---
 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      |  9 ++++++++-
 arch/x86/kernel/x86_init.c      |  1 +
 5 files changed, 26 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 a75767052a92..459c78558f36 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1837,6 +1837,8 @@ static __init void x2apic_enable(void)
 
 static __init void try_to_enable_x2apic(int remap_mode)
 {
+	u32 apic_limit = 0;
+
 	if (x2apic_state == X2APIC_DISABLED)
 		return;
 
@@ -1858,7 +1860,15 @@ static __init void try_to_enable_x2apic(int remap_mode)
 				return;
 			}
 
-			x2apic_set_max_apicid(255);
+			/*
+			 * If the hypervisor supports extended destination ID
+			 * in IOAPIC and MSI, we can support that many CPUs.
+			 */
+			if (x86_init.hyper.msi_ext_dest_id()) {
+				msi_ext_dest_id = 1;
+				apic_limit = 32767;
+			} else
+				apic_limit = 255;
 		}
 
 		/*
@@ -1867,6 +1877,9 @@ static __init void try_to_enable_x2apic(int remap_mode)
 		 */
 		x2apic_phys = 1;
 	}
+	if (apic_limit)
+		x2apic_set_max_apicid(apic_limit);
+
 	x2apic_enable();
 }
 
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 356f8acf4927..4d891967bea4 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -23,6 +23,8 @@
 
 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, int dmar)
 {
 	msg->address_hi = MSI_ADDR_BASE_HI;
@@ -45,10 +47,15 @@ static void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg, int
 	 * 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 APICs above 255.
+	 * 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


  parent reply index

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-05 15:28 [PATCH 0/13] Fix per-domain IRQ affinity, allow >255 CPUs on x86 without IRQ remapping David Woodhouse
2020-10-05 15:28 ` [PATCH 01/13] x86/apic: Use x2apic in guest kernels even with unusable CPUs David Woodhouse
2020-10-05 15:28   ` [PATCH 02/13] x86/msi: Only use high bits of MSI address for DMAR unit David Woodhouse
2020-10-06 20:45     ` Thomas Gleixner
2020-10-05 15:28   ` [PATCH 03/13] x86/ioapic: Handle Extended Destination ID field in RTE David Woodhouse
2020-10-05 15:28   ` David Woodhouse [this message]
2020-10-05 15:28   ` [PATCH 05/13] genirq: Prepare for default affinity to be passed to __irq_alloc_descs() David Woodhouse
2020-10-06 21:01     ` Thomas Gleixner
2020-10-06 21:07       ` David Woodhouse
2020-10-05 15:28   ` [PATCH 06/13] genirq: Add default_affinity argument " David Woodhouse
2020-10-06 21:06     ` Thomas Gleixner
2020-10-05 15:28   ` [PATCH 07/13] irqdomain: Add max_affinity argument to irq_domain_alloc_descs() David Woodhouse
2020-10-06 21:26     ` Thomas Gleixner
2020-10-07  7:19       ` David Woodhouse
2020-10-07 13:37         ` Thomas Gleixner
2020-10-07 14:10           ` David Woodhouse
2020-10-07 15:57             ` Thomas Gleixner
2020-10-07 16:11               ` David Woodhouse
2020-10-07 20:53                 ` Thomas Gleixner
2020-10-08  7:21               ` David Woodhouse
2020-10-08  9:34                 ` Thomas Gleixner
2020-10-08 11:10                   ` David Woodhouse
2020-10-08 12:40                     ` Thomas Gleixner
2020-10-09  7:54                       ` David Woodhouse
2020-10-05 15:28   ` [PATCH 08/13] genirq: Add irq_domain_set_affinity() David Woodhouse
2020-10-06 21:32     ` Thomas Gleixner
2020-10-07  7:22       ` David Woodhouse
2020-10-05 15:28   ` [PATCH 09/13] x86/irq: Add x86_non_ir_cpumask David Woodhouse
2020-10-06 21:42     ` Thomas Gleixner
2020-10-07  7:25       ` David Woodhouse
2020-10-05 15:28   ` [PATCH 10/13] x86/irq: Limit IOAPIC and MSI domains' affinity without IR David Woodhouse
2020-10-06 21:54     ` Thomas Gleixner
2020-10-07  7:48       ` David Woodhouse
2020-10-07 12:59         ` Thomas Gleixner
2020-10-07 13:08           ` David Woodhouse
2020-10-07 14:05             ` Thomas Gleixner
2020-10-07 14:23               ` David Woodhouse
2020-10-07 16:02                 ` Thomas Gleixner
2020-10-07 16:15                   ` David Woodhouse
2020-10-07 15:05               ` David Woodhouse
2020-10-07 15:25                 ` Thomas Gleixner
2020-10-07 15:46                   ` David Woodhouse
2020-10-07 17:23                     ` Thomas Gleixner
2020-10-07 17:34                       ` David Woodhouse
2020-10-05 15:28   ` [PATCH 11/13] x86/smp: Allow more than 255 CPUs even without interrupt remapping David Woodhouse
2020-10-05 15:28   ` [PATCH 12/13] iommu/irq_remapping: Kill most of hyperv-iommu.c now it's redundant David Woodhouse
2020-10-05 15:28   ` [PATCH 13/13] x86/kvm: Add KVM_FEATURE_MSI_EXT_DEST_ID David Woodhouse
2020-10-07  8:14     ` Paolo Bonzini
2020-10-07  8:59       ` David Woodhouse
2020-10-07 11:15         ` Paolo Bonzini
2020-10-07 12:04           ` David Woodhouse

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20201005152856.974112-4-dwmw2@infradead.org \
    --to=dwmw2@infradead.org \
    --cc=iommu@lists.linux-foundation.org \
    --cc=kvm@vger.kernel.org \
    --cc=linux-hyperv@vger.kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-HyperV Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-hyperv/0 linux-hyperv/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-hyperv linux-hyperv/ https://lore.kernel.org/linux-hyperv \
		linux-hyperv@vger.kernel.org
	public-inbox-index linux-hyperv

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-hyperv


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git