Date:   Fri, 18 Mar 2022 18:30:39 +0300
From:   "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
To:     tglx@...utronix.de, mingo@...hat.com, bp@...en8.de,
        dave.hansen@...el.com, luto@...nel.org, peterz@...radead.org
Cc:     sathyanarayanan.kuppuswamy@...ux.intel.com, aarcange@...hat.com,
        ak@...ux.intel.com, dan.j.williams@...el.com, david@...hat.com,
        hpa@...or.com, jgross@...e.com, jmattson@...gle.com,
        joro@...tes.org, jpoimboe@...hat.com, knsathya@...nel.org,
        pbonzini@...hat.com, sdeep@...are.com, seanjc@...gle.com,
        tony.luck@...el.com, vkuznets@...hat.com, wanpengli@...cent.com,
        thomas.lendacky@....com, brijesh.singh@....com, x86@...nel.org,
        linux-kernel@...r.kernel.org,
        Sean Christopherson <sean.j.christopherson@...el.com>,
        "Rafael J . Wysocki" <rafael.j.wysocki@...el.com>,
        "Kirill A . Shutemov" <kirill.shutemov@...ux.intel.com>
Subject: [PATCHv7 21/30] x86/acpi, x86/boot: Add multiprocessor wake-up support

From: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@...ux.intel.com>

TDX cannot use INIT/SIPI protocol to bring up secondary CPUs because it
requires assistance from untrusted VMM.

For platforms that do not support SIPI/INIT, ACPI defines a wakeup
model (using mailbox) via MADT multiprocessor wakeup structure. More
details about it can be found in ACPI specification v6.4, the section
titled "Multiprocessor Wakeup Structure". If a platform firmware
produces the multiprocessor wakeup structure, then OS may use this
new mailbox-based mechanism to wake up the APs.

Add ACPI MADT wake structure parsing support for x86 platform and if
MADT wake table is present, update apic->wakeup_secondary_cpu_64 with
new API which uses MADT wake mailbox to wake-up CPU.

Co-developed-by: Sean Christopherson <sean.j.christopherson@...el.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@...el.com>
Reviewed-by: Andi Kleen <ak@...ux.intel.com>
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@...el.com>
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@...ux.intel.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
---
 arch/x86/include/asm/apic.h |   5 ++
 arch/x86/kernel/acpi/boot.c | 115 ++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/apic/apic.c |  10 ++++
 3 files changed, 130 insertions(+)

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 35006e151774..bd8ae0a7010a 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -490,6 +490,11 @@ static inline unsigned int read_apic_id(void)
 	return apic->get_apic_id(reg);
 }
 
+#ifdef CONFIG_X86_64
+typedef int (*wakeup_cpu_handler)(int apicid, unsigned long start_eip);
+extern void acpi_wake_cpu_handler_update(wakeup_cpu_handler handler);
+#endif
+
 extern int default_apic_id_valid(u32 apicid);
 extern int default_acpi_madt_oem_check(char *, char *);
 extern void default_setup_apic_routing(void);
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 5b6d1a95776f..0ebfab0f4f7a 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -65,6 +65,13 @@ static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
 static bool acpi_support_online_capable;
 #endif
 
+#ifdef CONFIG_X86_64
+/* Physical address of the Multiprocessor Wakeup Structure mailbox */
+static u64 acpi_mp_wake_mailbox_paddr;
+/* Virtual address of the Multiprocessor Wakeup Structure mailbox */
+static struct acpi_madt_multiproc_wakeup_mailbox *acpi_mp_wake_mailbox;
+#endif
+
 #ifdef CONFIG_X86_IO_APIC
 /*
  * Locks related to IOAPIC hotplug
@@ -336,6 +343,83 @@ acpi_parse_lapic_nmi(union acpi_subtable_headers * header, const unsigned long e
 	return 0;
 }
 
+#ifdef CONFIG_X86_64
+/* Virtual address of the Multiprocessor Wakeup Structure mailbox */
+static int acpi_wakeup_cpu(int apicid, unsigned long start_ip)
+{
+	static physid_mask_t apic_id_wakemap = PHYSID_MASK_NONE;
+	u8 timeout;
+
+	/*
+	 * Remap mailbox memory only for the first call to acpi_wakeup_cpu().
+	 *
+	 * Wakeup of secondary CPUs is fully serialized in the core code.
+	 * No need to protect acpi_mp_wake_mailbox from concurrent accesses.
+	 */
+	if (!acpi_mp_wake_mailbox) {
+		acpi_mp_wake_mailbox = memremap(acpi_mp_wake_mailbox_paddr,
+						sizeof(*acpi_mp_wake_mailbox),
+						MEMREMAP_WB);
+	}
+
+	/*
+	 * According to the ACPI specification r6.4, section titled
+	 * "Multiprocessor Wakeup Structure" the mailbox-based wakeup
+	 * mechanism cannot be used more than once for the same CPU.
+	 * Skip wakeups if they are attempted more than once.
+	 */
+	if (physid_isset(apicid, apic_id_wakemap)) {
+		pr_err("CPU already awake (APIC ID %x), skipping wakeup\n",
+		       apicid);
+		return -EINVAL;
+	}
+
+	/*
+	 * Mailbox memory is shared between firmware and OS. Firmware will
+	 * listen on mailbox command address, and once it receives the wakeup
+	 * command, CPU associated with the given apicid will be booted.
+	 *
+	 * The value of apic_id and wakeup_vector has to be set before updating
+	 * the wakeup command. Use memory barrier to preserve write order.
+	 */
+	acpi_mp_wake_mailbox->apic_id		= apicid;
+	acpi_mp_wake_mailbox->wakeup_vector	= start_ip;
+	smp_wmb();
+	WRITE_ONCE(acpi_mp_wake_mailbox->command, ACPI_MP_WAKE_COMMAND_WAKEUP);
+
+	/*
+	 * After writing the wakeup command, wait for maximum timeout of 0xFF
+	 * for firmware to reset the command address back zero to indicate
+	 * the successful reception of command.
+	 * NOTE: 0xFF as timeout value is decided based on our experiments.
+	 *
+	 * XXX: Change the timeout once ACPI specification comes up with
+	 *      standard maximum timeout value.
+	 */
+	timeout = 0xFF;
+	while (READ_ONCE(acpi_mp_wake_mailbox->command) && --timeout)
+		cpu_relax();
+
+	/* If timed out (timeout == 0), return error */
+	if (!timeout) {
+		/*
+		 * XXX: Is there a recovery path after timeout is hit?
+		 * Spec is unclear. Reset command to 0 if timeout is hit.
+		 */
+		acpi_mp_wake_mailbox->command = 0;
+		return -EIO;
+	}
+
+	/*
+	 * If the CPU wakeup process is successful, store the
+	 * status in apic_id_wakemap to prevent re-wakeup
+	 * requests.
+	 */
+	physid_set(apicid, apic_id_wakemap);
+
+	return 0;
+}
+#endif
 #endif				/*CONFIG_X86_LOCAL_APIC */
 
 #ifdef CONFIG_X86_IO_APIC
@@ -1083,6 +1167,29 @@ static int __init acpi_parse_madt_lapic_entries(void)
 	}
 	return 0;
 }
+
+#ifdef CONFIG_X86_64
+static int __init acpi_parse_mp_wake(union acpi_subtable_headers *header,
+				     const unsigned long end)
+{
+	struct acpi_madt_multiproc_wakeup *mp_wake;
+
+	if (!IS_ENABLED(CONFIG_SMP))
+		return -ENODEV;
+
+	mp_wake = (struct acpi_madt_multiproc_wakeup *)header;
+	if (BAD_MADT_ENTRY(mp_wake, end))
+		return -EINVAL;
+
+	acpi_table_print_madt_entry(&header->common);
+
+	acpi_mp_wake_mailbox_paddr = mp_wake->base_address;
+
+	acpi_wake_cpu_handler_update(acpi_wakeup_cpu);
+
+	return 0;
+}
+#endif				/* CONFIG_X86_64 */
 #endif				/* CONFIG_X86_LOCAL_APIC */
 
 #ifdef	CONFIG_X86_IO_APIC
@@ -1278,6 +1385,14 @@ static void __init acpi_process_madt(void)
 
 				smp_found_config = 1;
 			}
+
+#ifdef CONFIG_X86_64
+			/*
+			 * Parse MADT MP Wake entry.
+			 */
+			acpi_table_parse_madt(ACPI_MADT_TYPE_MULTIPROC_WAKEUP,
+					      acpi_parse_mp_wake, 1);
+#endif
 		}
 		if (error == -EINVAL) {
 			/*
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index b70344bf6600..3c8f2c797a98 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2551,6 +2551,16 @@ u32 x86_msi_msg_get_destid(struct msi_msg *msg, bool extid)
 }
 EXPORT_SYMBOL_GPL(x86_msi_msg_get_destid);
 
+#ifdef CONFIG_X86_64
+void __init acpi_wake_cpu_handler_update(wakeup_cpu_handler handler)
+{
+	struct apic **drv;
+
+	for (drv = __apicdrivers; drv < __apicdrivers_end; drv++)
+		(*drv)->wakeup_secondary_cpu_64 = handler;
+}
+#endif
+
 /*
  * Override the generic EOI implementation with an optimized version.
  * Only called during early boot when only one CPU is active and with
-- 
2.34.1

Powered by blists - more mailing lists