x86/xen: Provide a "Xen PV" APIC driver to support >255 VCPUs

Instead of mangling the default APIC driver, provide a Xen PV guest
specific one that explicitly provides appropriate methods.

This allows use to report that all APIC IDs are valid, allowing dom0
to boot with more than 255 VCPUs.

Since the probe order of APIC drivers is link dependent, we add in an
late probe function to change to the Xen PV if it hadn't been done
during bootup.

Suggested-by: David Vrabel <david.vrabel@citrix.com>
Reported-by: Cathy Avery <cathy.avery@oracle.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>

arch/x86/xen/apic.c

@@ -7,6 +7,7 @@
 #include <xen/xen.h>
 #include <xen/interface/physdev.h>
 #include "xen-ops.h"
+#include "smp.h"
 
 static unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
 {
@@ -28,7 +29,186 @@ static unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
 	return 0xfd;
 }
 
+static unsigned long xen_set_apic_id(unsigned int x)
+{
+	WARN_ON(1);
+	return x;
+}
+
+static unsigned int xen_get_apic_id(unsigned long x)
+{
+	return ((x)>>24) & 0xFFu;
+}
+
+static u32 xen_apic_read(u32 reg)
+{
+	struct xen_platform_op op = {
+		.cmd = XENPF_get_cpuinfo,
+		.interface_version = XENPF_INTERFACE_VERSION,
+		.u.pcpu_info.xen_cpuid = 0,
+	};
+	int ret = 0;
+
+	/* Shouldn't need this as APIC is turned off for PV, and we only
+	 * get called on the bootup processor. But just in case. */
+	if (!xen_initial_domain() || smp_processor_id())
+		return 0;
+
+	if (reg == APIC_LVR)
+		return 0x10;
+#ifdef CONFIG_X86_32
+	if (reg == APIC_LDR)
+		return SET_APIC_LOGICAL_ID(1UL << smp_processor_id());
+#endif
+	if (reg != APIC_ID)
+		return 0;
+
+	ret = HYPERVISOR_dom0_op(&op);
+	if (ret)
+		return 0;
+
+	return op.u.pcpu_info.apic_id << 24;
+}
+
+static void xen_apic_write(u32 reg, u32 val)
+{
+	/* Warn to see if there's any stray references */
+	WARN_ON(1);
+}
+
+static u64 xen_apic_icr_read(void)
+{
+	return 0;
+}
+
+static void xen_apic_icr_write(u32 low, u32 id)
+{
+	/* Warn to see if there's any stray references */
+	WARN_ON(1);
+}
+
+static u32 xen_safe_apic_wait_icr_idle(void)
+{
+        return 0;
+}
+
+static int xen_apic_probe_pv(void)
+{
+	if (xen_pv_domain())
+		return 1;
+
+	return 0;
+}
+
+static int xen_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	return xen_pv_domain();
+}
+
+static int xen_id_always_valid(int apicid)
+{
+	return 1;
+}
+
+static int xen_id_always_registered(void)
+{
+	return 1;
+}
+
+static int xen_phys_pkg_id(int initial_apic_id, int index_msb)
+{
+	return initial_apic_id >> index_msb;
+}
+
+#ifdef CONFIG_X86_32
+static int xen_x86_32_early_logical_apicid(int cpu)
+{
+	/* Match with APIC_LDR read. Otherwise setup_local_APIC complains. */
+	return 1 << cpu;
+}
+#endif
+
+static void xen_noop(void)
+{
+}
+
+static void xen_silent_inquire(int apicid)
+{
+}
+
+static struct apic xen_pv_apic = {
+	.name 				= "Xen PV",
+	.probe 				= xen_apic_probe_pv,
+	.acpi_madt_oem_check		= xen_madt_oem_check,
+	.apic_id_valid 			= xen_id_always_valid,
+	.apic_id_registered 		= xen_id_always_registered,
+
+	/* .irq_delivery_mode - used in native_compose_msi_msg only */
+	/* .irq_dest_mode     - used in native_compose_msi_msg only */
+
+	.target_cpus			= default_target_cpus,
+	.disable_esr			= 0,
+	/* .dest_logical      -  default_send_IPI_ use it but we use our own. */
+	.check_apicid_used		= default_check_apicid_used, /* Used on 32-bit */
+
+	.vector_allocation_domain	= flat_vector_allocation_domain,
+	.init_apic_ldr			= xen_noop, /* setup_local_APIC calls it */
+
+	.ioapic_phys_id_map		= default_ioapic_phys_id_map, /* Used on 32-bit */
+	.setup_apic_routing		= NULL,
+	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
+	.apicid_to_cpu_present		= physid_set_mask_of_physid, /* Used on 32-bit */
+	.check_phys_apicid_present	= default_check_phys_apicid_present, /* smp_sanity_check needs it */
+	.phys_pkg_id			= xen_phys_pkg_id, /* detect_ht */
+
+	.get_apic_id 			= xen_get_apic_id,
+	.set_apic_id 			= xen_set_apic_id, /* Can be NULL on 32-bit. */
+	.apic_id_mask			= 0xFF << 24, /* Used by verify_local_APIC. Match with what xen_get_apic_id does. */
+
+	.cpu_mask_to_apicid_and		= flat_cpu_mask_to_apicid_and,
+
+#ifdef CONFIG_SMP
+	.send_IPI_mask 			= xen_send_IPI_mask,
+	.send_IPI_mask_allbutself 	= xen_send_IPI_mask_allbutself,
+	.send_IPI_allbutself 		= xen_send_IPI_allbutself,
+	.send_IPI_all 			= xen_send_IPI_all,
+	.send_IPI_self 			= xen_send_IPI_self,
+#endif
+	/* .wait_for_init_deassert- used  by AP bootup - smp_callin which we don't use */
+	.inquire_remote_apic		= xen_silent_inquire,
+
+	.read				= xen_apic_read,
+	.write				= xen_apic_write,
+	.eoi_write			= xen_apic_write,
+
+	.icr_read 			= xen_apic_icr_read,
+	.icr_write 			= xen_apic_icr_write,
+	.wait_icr_idle 			= xen_noop,
+	.safe_wait_icr_idle 		= xen_safe_apic_wait_icr_idle,
+
+#ifdef CONFIG_X86_32
+	/* generic_processor_info and setup_local_APIC. */
+	.x86_32_early_logical_apicid	= xen_x86_32_early_logical_apicid,
+#endif
+};
+
+static void __init xen_apic_check(void)
+{
+	if (apic == &xen_pv_apic)
+		return;
+
+	pr_info("Switched APIC routing from %s to %s.\n", apic->name,
+		xen_pv_apic.name);
+	apic = &xen_pv_apic;
+}
 void __init xen_init_apic(void)
 {
 	x86_io_apic_ops.read = xen_io_apic_read;
+	/* On PV guests the APIC CPUID bit is disabled so none of the
+	 * routines end up executing. */
+	if (!xen_initial_domain())
+		apic = &xen_pv_apic;
+
+	x86_platform.apic_post_init = xen_apic_check;
 }
+apic_driver(xen_pv_apic);

arch/x86/xen/enlighten.c

@@ -927,92 +927,6 @@ static void xen_io_delay(void)
 {
 }
 
-#ifdef CONFIG_X86_LOCAL_APIC
-static unsigned long xen_set_apic_id(unsigned int x)
-{
-	WARN_ON(1);
-	return x;
-}
-static unsigned int xen_get_apic_id(unsigned long x)
-{
-	return ((x)>>24) & 0xFFu;
-}
-static u32 xen_apic_read(u32 reg)
-{
-	struct xen_platform_op op = {
-		.cmd = XENPF_get_cpuinfo,
-		.interface_version = XENPF_INTERFACE_VERSION,
-		.u.pcpu_info.xen_cpuid = 0,
-	};
-	int ret = 0;
-
-	/* Shouldn't need this as APIC is turned off for PV, and we only
-	 * get called on the bootup processor. But just in case. */
-	if (!xen_initial_domain() || smp_processor_id())
-		return 0;
-
-	if (reg == APIC_LVR)
-		return 0x10;
-
-	if (reg != APIC_ID)
-		return 0;
-
-	ret = HYPERVISOR_dom0_op(&op);
-	if (ret)
-		return 0;
-
-	return op.u.pcpu_info.apic_id << 24;
-}
-
-static void xen_apic_write(u32 reg, u32 val)
-{
-	/* Warn to see if there's any stray references */
-	WARN_ON(1);
-}
-
-static u64 xen_apic_icr_read(void)
-{
-	return 0;
-}
-
-static void xen_apic_icr_write(u32 low, u32 id)
-{
-	/* Warn to see if there's any stray references */
-	WARN_ON(1);
-}
-
-static void xen_apic_wait_icr_idle(void)
-{
-        return;
-}
-
-static u32 xen_safe_apic_wait_icr_idle(void)
-{
-        return 0;
-}
-
-static void set_xen_basic_apic_ops(void)
-{
-	apic->read = xen_apic_read;
-	apic->write = xen_apic_write;
-	apic->icr_read = xen_apic_icr_read;
-	apic->icr_write = xen_apic_icr_write;
-	apic->wait_icr_idle = xen_apic_wait_icr_idle;
-	apic->safe_wait_icr_idle = xen_safe_apic_wait_icr_idle;
-	apic->set_apic_id = xen_set_apic_id;
-	apic->get_apic_id = xen_get_apic_id;
-
-#ifdef CONFIG_SMP
-	apic->send_IPI_allbutself = xen_send_IPI_allbutself;
-	apic->send_IPI_mask_allbutself = xen_send_IPI_mask_allbutself;
-	apic->send_IPI_mask = xen_send_IPI_mask;
-	apic->send_IPI_all = xen_send_IPI_all;
-	apic->send_IPI_self = xen_send_IPI_self;
-#endif
-}
-
-#endif
-
 static void xen_clts(void)
 {
 	struct multicall_space mcs;
@@ -1618,7 +1532,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	/*
 	 * set up the basic apic ops.
 	 */
-	set_xen_basic_apic_ops();
+	xen_init_apic();
 #endif
 
 	if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
@@ -1731,8 +1645,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 		if (HYPERVISOR_dom0_op(&op) == 0)
 			boot_params.kbd_status = op.u.firmware_info.u.kbd_shift_flags;
 
-		xen_init_apic();
-
 		/* Make sure ACS will be enabled */
 		pci_request_acs();