#include <xen/types.h>
#include <xen/domain_page.h>
+#include <xen/event.h>
#include <xen/spinlock.h>
#include <xen/rwlock.h>
#include <xen/mm.h>
#include <asm/altp2m.h>
#include <asm/atomic.h>
#include <asm/event.h>
+#include <asm/hap.h>
+#include <asm/hvm/hvm.h>
#include <xsm/xsm.h>
#include "mm-locks.h"
return 0;
}
+/*
+ * Forking a page only gets called when the VM faults due to no entry being
+ * in the EPT for the access. Depending on the type of access we either
+ * populate the physmap with a shared entry for read-only access or
+ * fork the page if its a write access.
+ *
+ * The client p2m is already locked so we only need to lock
+ * the parent's here.
+ */
+int mem_sharing_fork_page(struct domain *d, gfn_t gfn, bool unsharing)
+{
+ int rc = -ENOENT;
+ shr_handle_t handle;
+ struct domain *parent = d->parent;
+ struct p2m_domain *p2m;
+ unsigned long gfn_l = gfn_x(gfn);
+ mfn_t mfn, new_mfn;
+ p2m_type_t p2mt;
+ struct page_info *page;
+
+ if ( !mem_sharing_is_fork(d) )
+ return -ENOENT;
+
+ if ( !unsharing )
+ {
+ /* For read-only accesses we just add a shared entry to the physmap */
+ while ( parent )
+ {
+ if ( !(rc = nominate_page(parent, gfn, 0, &handle)) )
+ break;
+
+ parent = parent->parent;
+ }
+
+ if ( !rc )
+ {
+ /* The client's p2m is already locked */
+ p2m = p2m_get_hostp2m(parent);
+
+ p2m_lock(p2m);
+ rc = add_to_physmap(parent, gfn_l, handle, d, gfn_l, false);
+ p2m_unlock(p2m);
+
+ if ( !rc )
+ return 0;
+ }
+ }
+
+ /*
+ * If it's a write access (ie. unsharing) or if adding a shared entry to
+ * the physmap failed we'll fork the page directly.
+ */
+ p2m = p2m_get_hostp2m(d);
+ parent = d->parent;
+
+ while ( parent )
+ {
+ mfn = get_gfn_query(parent, gfn_l, &p2mt);
+
+ /* We can't fork grant memory from the parent, only regular ram */
+ if ( mfn_valid(mfn) && p2m_is_ram(p2mt) )
+ break;
+
+ put_gfn(parent, gfn_l);
+ parent = parent->parent;
+ }
+
+ if ( !parent )
+ return -ENOENT;
+
+ if ( !(page = alloc_domheap_page(d, 0)) )
+ {
+ put_gfn(parent, gfn_l);
+ return -ENOMEM;
+ }
+
+ new_mfn = page_to_mfn(page);
+ copy_domain_page(new_mfn, mfn);
+ set_gpfn_from_mfn(mfn_x(new_mfn), gfn_l);
+
+ put_gfn(parent, gfn_l);
+
+ return p2m->set_entry(p2m, gfn, new_mfn, PAGE_ORDER_4K, p2m_ram_rw,
+ p2m->default_access, -1);
+}
+
+static int bring_up_vcpus(struct domain *cd, struct domain *d)
+{
+ unsigned int i;
+ int ret = -EINVAL;
+
+ if ( d->max_vcpus != cd->max_vcpus ||
+ (ret = cpupool_move_domain(cd, d->cpupool)) )
+ return ret;
+
+ for ( i = 0; i < cd->max_vcpus; i++ )
+ {
+ if ( !d->vcpu[i] || cd->vcpu[i] )
+ continue;
+
+ if ( !vcpu_create(cd, i) )
+ return -EINVAL;
+ }
+
+ domain_update_node_affinity(cd);
+ return 0;
+}
+
+static int copy_vcpu_settings(struct domain *cd, const struct domain *d)
+{
+ unsigned int i;
+ struct p2m_domain *p2m = p2m_get_hostp2m(cd);
+ int ret = -EINVAL;
+
+ for ( i = 0; i < cd->max_vcpus; i++ )
+ {
+ const struct vcpu *d_vcpu = d->vcpu[i];
+ struct vcpu *cd_vcpu = cd->vcpu[i];
+ mfn_t vcpu_info_mfn;
+
+ if ( !d_vcpu || !cd_vcpu )
+ continue;
+
+ /* Copy & map in the vcpu_info page if the guest uses one */
+ vcpu_info_mfn = d_vcpu->vcpu_info_mfn;
+ if ( !mfn_eq(vcpu_info_mfn, INVALID_MFN) )
+ {
+ mfn_t new_vcpu_info_mfn = cd_vcpu->vcpu_info_mfn;
+
+ /* Allocate & map the page for it if it hasn't been already */
+ if ( mfn_eq(new_vcpu_info_mfn, INVALID_MFN) )
+ {
+ gfn_t gfn = mfn_to_gfn(d, vcpu_info_mfn);
+ unsigned long gfn_l = gfn_x(gfn);
+ struct page_info *page;
+
+ if ( !(page = alloc_domheap_page(cd, 0)) )
+ return -ENOMEM;
+
+ new_vcpu_info_mfn = page_to_mfn(page);
+ set_gpfn_from_mfn(mfn_x(new_vcpu_info_mfn), gfn_l);
+
+ ret = p2m->set_entry(p2m, gfn, new_vcpu_info_mfn,
+ PAGE_ORDER_4K, p2m_ram_rw,
+ p2m->default_access, -1);
+ if ( ret )
+ return ret;
+
+ ret = map_vcpu_info(cd_vcpu, gfn_l,
+ PAGE_OFFSET(d_vcpu->vcpu_info));
+ if ( ret )
+ return ret;
+ }
+
+ copy_domain_page(new_vcpu_info_mfn, vcpu_info_mfn);
+ }
+
+ /*
+ * TODO: to support VMs with PV interfaces copy additional
+ * settings here, such as PV timers.
+ */
+ }
+
+ return 0;
+}
+
+static int fork_hap_allocation(struct domain *cd, struct domain *d)
+{
+ int rc;
+ bool preempted;
+ unsigned long mb = hap_get_allocation(d);
+
+ if ( mb == hap_get_allocation(cd) )
+ return 0;
+
+ paging_lock(cd);
+ rc = hap_set_allocation(cd, mb << (20 - PAGE_SHIFT), &preempted);
+ paging_unlock(cd);
+
+ return preempted ? -ERESTART : rc;
+}
+
+static void copy_tsc(struct domain *cd, struct domain *d)
+{
+ uint32_t tsc_mode;
+ uint32_t gtsc_khz;
+ uint32_t incarnation;
+ uint64_t elapsed_nsec;
+
+ tsc_get_info(d, &tsc_mode, &elapsed_nsec, >sc_khz, &incarnation);
+ /* Don't bump incarnation on set */
+ tsc_set_info(cd, tsc_mode, elapsed_nsec, gtsc_khz, incarnation - 1);
+}
+
+static int copy_special_pages(struct domain *cd, struct domain *d)
+{
+ mfn_t new_mfn, old_mfn;
+ struct p2m_domain *p2m = p2m_get_hostp2m(cd);
+ static const unsigned int params[] =
+ {
+ HVM_PARAM_STORE_PFN,
+ HVM_PARAM_IOREQ_PFN,
+ HVM_PARAM_BUFIOREQ_PFN,
+ HVM_PARAM_CONSOLE_PFN
+ };
+ unsigned int i;
+ int rc;
+
+ for ( i = 0; i < ARRAY_SIZE(params); i++ )
+ {
+ p2m_type_t t;
+ uint64_t value = 0;
+ struct page_info *page;
+
+ if ( hvm_get_param(d, params[i], &value) || !value )
+ continue;
+
+ old_mfn = get_gfn_query_unlocked(d, value, &t);
+ new_mfn = get_gfn_query_unlocked(cd, value, &t);
+
+ /* Allocate the page and map it in if it's not present */
+ if ( mfn_eq(new_mfn, INVALID_MFN) )
+ {
+ if ( !(page = alloc_domheap_page(cd, 0)) )
+ return -ENOMEM;
+
+ new_mfn = page_to_mfn(page);
+ set_gpfn_from_mfn(mfn_x(new_mfn), value);
+
+ rc = p2m->set_entry(p2m, _gfn(value), new_mfn, PAGE_ORDER_4K,
+ p2m_ram_rw, p2m->default_access, -1);
+ if ( rc )
+ return rc;
+ }
+
+ copy_domain_page(new_mfn, old_mfn);
+ }
+
+ old_mfn = _mfn(virt_to_mfn(d->shared_info));
+ new_mfn = _mfn(virt_to_mfn(cd->shared_info));
+ copy_domain_page(new_mfn, old_mfn);
+
+ return 0;
+}
+
+static int copy_settings(struct domain *cd, struct domain *d)
+{
+ int rc;
+
+ if ( (rc = copy_vcpu_settings(cd, d)) )
+ return rc;
+
+ if ( (rc = hvm_copy_context_and_params(cd, d)) )
+ return rc;
+
+ if ( (rc = copy_special_pages(cd, d)) )
+ return rc;
+
+ copy_tsc(cd, d);
+
+ return rc;
+}
+
+static int fork(struct domain *cd, struct domain *d)
+{
+ int rc = -EBUSY;
+
+ if ( !cd->controller_pause_count )
+ return rc;
+
+ if ( !cd->parent )
+ {
+ if ( !get_domain(d) )
+ {
+ ASSERT_UNREACHABLE();
+ return -EBUSY;
+ }
+
+ domain_pause(d);
+ cd->max_pages = d->max_pages;
+ cd->parent = d;
+ }
+
+ /* This is preemptible so it's the first to get done */
+ if ( (rc = fork_hap_allocation(cd, d)) )
+ goto done;
+
+ if ( (rc = bring_up_vcpus(cd, d)) )
+ goto done;
+
+ rc = copy_settings(cd, d);
+
+ done:
+ if ( rc && rc != -ERESTART )
+ {
+ domain_unpause(d);
+ put_domain(d);
+ cd->parent = NULL;
+ }
+
+ return rc;
+}
+
int mem_sharing_memop(XEN_GUEST_HANDLE_PARAM(xen_mem_sharing_op_t) arg)
{
int rc;
rc = debug_gref(d, mso.u.debug.u.gref);
break;
+ case XENMEM_sharing_op_fork:
+ {
+ struct domain *pd;
+
+ rc = -EINVAL;
+ if ( mso.u.fork.pad[0] || mso.u.fork.pad[1] || mso.u.fork.pad[2] )
+ goto out;
+
+ rc = rcu_lock_live_remote_domain_by_id(mso.u.fork.parent_domain,
+ &pd);
+ if ( rc )
+ goto out;
+
+ rc = -EINVAL;
+ if ( pd->max_vcpus != d->max_vcpus )
+ {
+ rcu_unlock_domain(pd);
+ goto out;
+ }
+
+ if ( !mem_sharing_enabled(pd) && (rc = mem_sharing_control(pd, true)) )
+ {
+ rcu_unlock_domain(pd);
+ goto out;
+ }
+
+ rc = fork(d, pd);
+
+ if ( rc == -ERESTART )
+ rc = hypercall_create_continuation(__HYPERVISOR_memory_op,
+ "lh", XENMEM_sharing_op,
+ arg);
+ rcu_unlock_domain(pd);
+ break;
+ }
+
default:
rc = -ENOSYS;
break;
projects / people / sstabellini / xen-unstable.git / .git / commitdiff