svn commit: r304858 - in head/sys/amd64/vmm: . io

[John Baldwin]

Author: jhb
Date: Fri Aug 26 20:15:22 2016
New Revision: 304858
URL: https://svnweb.freebsd.org/changeset/base/304858

Log:
  Enable I/O MMU when PCI pass through is first used.
  
  Rather than enabling the I/O MMU when the vmm module is loaded,
  defer initialization until the first attempt to pass a PCI device
  through to a guest.  If the I/O MMU fails to initialize or is not
  present, than fail the attempt to pass a PCI device through to a
  guest.
  
  The hw.vmm.force_iommu tunable has been removed since the I/O MMU is
  no longer enabled during boot.  However, the I/O MMU support can be
  disabled by setting the hw.vmm.iommu.enable tunable to 0 to prevent
  use of the I/O MMU on any systems where it is buggy.
  
  Reviewed by:	grehan
  MFC after:	1 week
  Differential Revision:	https://reviews.freebsd.org/D7448

Modified:
  head/sys/amd64/vmm/io/iommu.c
  head/sys/amd64/vmm/io/iommu.h
  head/sys/amd64/vmm/vmm.c

Modified: head/sys/amd64/vmm/io/iommu.c
==============================================================================
--- head/sys/amd64/vmm/io/iommu.c	Fri Aug 26 19:23:17 2016	(r304857)
+++ head/sys/amd64/vmm/io/iommu.c	Fri Aug 26 20:15:22 2016	(r304858)
@@ -38,6 +38,7 @@ __FBSDID("$FreeBSD$");
 #include <dev/pci/pcivar.h>
 #include <dev/pci/pcireg.h>
 
+#include <machine/cpu.h>
 #include <machine/md_var.h>
 
 #include "vmm_util.h"
@@ -51,6 +52,10 @@ static int iommu_avail;
 SYSCTL_INT(_hw_vmm_iommu, OID_AUTO, initialized, CTLFLAG_RD, &iommu_avail,
     0, "bhyve iommu initialized?");
 
+static int iommu_enable = 1;
+SYSCTL_INT(_hw_vmm_iommu, OID_AUTO, enable, CTLFLAG_RDTUN, &iommu_enable, 0,
+    "Enable use of I/O MMU (required for PCI passthrough).");
+
 static struct iommu_ops *ops;
 static void *host_domain;
 
@@ -148,7 +153,7 @@ IOMMU_DISABLE(void)
 		(*ops->disable)();
 }
 
-void
+static void
 iommu_init(void)
 {
 	int error, bus, slot, func;
@@ -156,6 +161,9 @@ iommu_init(void)
 	const char *name;
 	device_t dev;
 
+	if (!iommu_enable)
+		return;
+
 	if (vmm_is_intel())
 		ops = &iommu_ops_intel;
 	else if (vmm_is_amd())
@@ -174,8 +182,13 @@ iommu_init(void)
 	 */
 	maxaddr = vmm_mem_maxaddr();
 	host_domain = IOMMU_CREATE_DOMAIN(maxaddr);
-	if (host_domain == NULL)
-		panic("iommu_init: unable to create a host domain");
+	if (host_domain == NULL) {
+		printf("iommu_init: unable to create a host domain");
+		IOMMU_CLEANUP();
+		ops = NULL;
+		iommu_avail = 0;
+		return;
+	}
 
 	/*
 	 * Create 1:1 mappings from '0' to 'maxaddr' for devices assigned to
@@ -216,7 +229,16 @@ iommu_cleanup(void)
 void *
 iommu_create_domain(vm_paddr_t maxaddr)
 {
+	static volatile int iommu_initted;
 
+	if (iommu_initted < 2) {
+		if (atomic_cmpset_int(&iommu_initted, 0, 1)) {
+			iommu_init();
+			atomic_store_rel_int(&iommu_initted, 2);
+		} else
+			while (iommu_initted == 1)
+				cpu_spinwait();
+	}
 	return (IOMMU_CREATE_DOMAIN(maxaddr));
 }
 

Modified: head/sys/amd64/vmm/io/iommu.h
==============================================================================
--- head/sys/amd64/vmm/io/iommu.h	Fri Aug 26 19:23:17 2016	(r304857)
+++ head/sys/amd64/vmm/io/iommu.h	Fri Aug 26 20:15:22 2016	(r304858)
@@ -61,7 +61,6 @@ struct iommu_ops {
 extern struct iommu_ops iommu_ops_intel;
 extern struct iommu_ops iommu_ops_amd;
 
-void	iommu_init(void);
 void	iommu_cleanup(void);
 void	*iommu_host_domain(void);
 void	*iommu_create_domain(vm_paddr_t maxaddr);

Modified: head/sys/amd64/vmm/vmm.c
==============================================================================
--- head/sys/amd64/vmm/vmm.c	Fri Aug 26 19:23:17 2016	(r304857)
+++ head/sys/amd64/vmm/vmm.c	Fri Aug 26 20:15:22 2016	(r304858)
@@ -224,11 +224,6 @@ SYSCTL_INT(_hw_vmm, OID_AUTO, trace_gues
     &trace_guest_exceptions, 0,
     "Trap into hypervisor on all guest exceptions and reflect them back");
 
-static int vmm_force_iommu = 0;
-TUNABLE_INT("hw.vmm.force_iommu", &vmm_force_iommu);
-SYSCTL_INT(_hw_vmm, OID_AUTO, force_iommu, CTLFLAG_RDTUN, &vmm_force_iommu, 0,
-    "Force use of I/O MMU even if no passthrough devices were found.");
-
 static void vm_free_memmap(struct vm *vm, int ident);
 static bool sysmem_mapping(struct vm *vm, struct mem_map *mm);
 static void vcpu_notify_event_locked(struct vcpu *vcpu, bool lapic_intr);
@@ -358,8 +353,6 @@ vmm_handler(module_t mod, int what, void
 	switch (what) {
 	case MOD_LOAD:
 		vmmdev_init();
-		if (vmm_force_iommu || ppt_avail_devices() > 0)
-			iommu_init();
 		error = vmm_init();
 		if (error == 0)
 			vmm_initialized = 1;
@@ -396,9 +389,6 @@ static moduledata_t vmm_kmod = {
 /*
  * vmm initialization has the following dependencies:
  *
- * - iommu initialization must happen after the pci passthru driver has had
- *   a chance to attach to any passthru devices (after SI_SUB_CONFIGURE).
- *
  * - VT-x initialization requires smp_rendezvous() and therefore must happen
  *   after SMP is fully functional (after SI_SUB_SMP).
  */
@@ -893,6 +883,8 @@ vm_assign_pptdev(struct vm *vm, int bus,
 		    ("vm_assign_pptdev: iommu must be NULL"));
 		maxaddr = sysmem_maxaddr(vm);
 		vm->iommu = iommu_create_domain(maxaddr);
+		if (vm->iommu == NULL)
+			return (ENXIO);
 		vm_iommu_map(vm);
 	}