#include <xen/libelf.h>
#include <xen/pfn.h>
#include <xen/guest_access.h>
+#include <xen/acpi.h>
#include <asm/regs.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/io_apic.h>
#include <asm/hpet.h>
+#include <acpi/actables.h>
+
#include <public/version.h>
#include <public/hvm/hvm_info_table.h>
#include <public/arch-x86/hvm/start_info.h>
*/
#define HVM_VM86_TSS_SIZE 265
+static unsigned int __initdata acpi_intr_overrides;
+static struct acpi_madt_interrupt_override __initdata *intsrcovr;
+
+static unsigned int __initdata acpi_nmi_sources;
+static struct acpi_madt_nmi_source __initdata *nmisrc;
+
/*
* dom0_mem=[min:<min_amt>,][max:<max_amt>,][<amt>]
*
return 0;
}
+static int __init acpi_count_intr_ovr(struct acpi_subtable_header *header,
+ const unsigned long end)
+{
+
+ acpi_intr_overrides++;
+ return 0;
+}
+
+static int __init acpi_set_intr_ovr(struct acpi_subtable_header *header,
+ const unsigned long end)
+{
+ const struct acpi_madt_interrupt_override *intr =
+ container_of(header, struct acpi_madt_interrupt_override, header);
+
+ *intsrcovr = *intr;
+ intsrcovr++;
+
+ return 0;
+}
+
+static int __init acpi_count_nmi_src(struct acpi_subtable_header *header,
+ const unsigned long end)
+{
+
+ acpi_nmi_sources++;
+ return 0;
+}
+
+static int __init acpi_set_nmi_src(struct acpi_subtable_header *header,
+ const unsigned long end)
+{
+ const struct acpi_madt_nmi_source *src =
+ container_of(header, struct acpi_madt_nmi_source, header);
+
+ *nmisrc = *src;
+ nmisrc++;
+
+ return 0;
+}
+
+static int __init pvh_setup_acpi_madt(struct domain *d, paddr_t *addr)
+{
+ struct acpi_table_madt *madt;
+ struct acpi_table_header *table;
+ struct acpi_madt_io_apic *io_apic;
+ struct acpi_madt_local_x2apic *x2apic;
+ acpi_status status;
+ unsigned long size;
+ unsigned int i, max_vcpus;
+ int rc;
+
+ /* Count number of interrupt overrides in the MADT. */
+ acpi_table_parse_madt(ACPI_MADT_TYPE_INTERRUPT_OVERRIDE,
+ acpi_count_intr_ovr, UINT_MAX);
+
+ /* Count number of NMI sources in the MADT. */
+ acpi_table_parse_madt(ACPI_MADT_TYPE_NMI_SOURCE, acpi_count_nmi_src,
+ UINT_MAX);
+
+ max_vcpus = dom0_max_vcpus();
+ /* Calculate the size of the crafted MADT. */
+ size = sizeof(*madt);
+ /*
+ * FIXME: the current vIO-APIC code just supports one IO-APIC instance
+ * per domain. This must be fixed in order to provide the same amount of
+ * IO APICs as available on bare metal.
+ */
+ size += sizeof(*io_apic);
+ size += sizeof(*intsrcovr) * acpi_intr_overrides;
+ size += sizeof(*nmisrc) * acpi_nmi_sources;
+ size += sizeof(*x2apic) * max_vcpus;
+
+ madt = xzalloc_bytes(size);
+ if ( !madt )
+ {
+ printk("Unable to allocate memory for MADT table\n");
+ return -ENOMEM;
+ }
+
+ /* Copy the native MADT table header. */
+ status = acpi_get_table(ACPI_SIG_MADT, 0, &table);
+ if ( !ACPI_SUCCESS(status) )
+ {
+ printk("Failed to get MADT ACPI table, aborting.\n");
+ return -EINVAL;
+ }
+ madt->header = *table;
+ madt->address = APIC_DEFAULT_PHYS_BASE;
+ /*
+ * NB: this is currently set to 4, which is the revision in the ACPI
+ * spec 6.1. Sadly ACPICA doesn't provide revision numbers for the
+ * tables described in the headers.
+ */
+ madt->header.revision = min_t(unsigned char, table->revision, 4);
+
+ /*
+ * Setup the IO APIC entry.
+ * FIXME: the current vIO-APIC code just supports one IO-APIC instance
+ * per domain. This must be fixed in order to provide the same amount of
+ * IO APICs as available on bare metal, and with the same IDs as found in
+ * the native IO APIC MADT entries.
+ */
+ if ( nr_ioapics > 1 )
+ printk("WARNING: found %d IO APICs, Dom0 will only have access to 1 emulated IO APIC\n",
+ nr_ioapics);
+ io_apic = (void *)(madt + 1);
+ io_apic->header.type = ACPI_MADT_TYPE_IO_APIC;
+ io_apic->header.length = sizeof(*io_apic);
+ io_apic->id = domain_vioapic(d)->id;
+ io_apic->address = VIOAPIC_DEFAULT_BASE_ADDRESS;
+
+ x2apic = (void *)(io_apic + 1);
+ for ( i = 0; i < max_vcpus; i++ )
+ {
+ x2apic->header.type = ACPI_MADT_TYPE_LOCAL_X2APIC;
+ x2apic->header.length = sizeof(*x2apic);
+ x2apic->uid = i;
+ x2apic->local_apic_id = i * 2;
+ x2apic->lapic_flags = ACPI_MADT_ENABLED;
+ x2apic++;
+ }
+
+ /* Setup interrupt overrides. */
+ intsrcovr = (void *)x2apic;
+ acpi_table_parse_madt(ACPI_MADT_TYPE_INTERRUPT_OVERRIDE, acpi_set_intr_ovr,
+ acpi_intr_overrides);
+
+ /* Setup NMI sources. */
+ nmisrc = (void *)intsrcovr;
+ acpi_table_parse_madt(ACPI_MADT_TYPE_NMI_SOURCE, acpi_set_nmi_src,
+ acpi_nmi_sources);
+
+ ASSERT(((void *)nmisrc - (void *)madt) == size);
+ madt->header.length = size;
+ /*
+ * Calling acpi_tb_checksum here is a layering violation, but
+ * introducing a wrapper for such simple usage seems overkill.
+ */
+ madt->header.checksum -= acpi_tb_checksum(ACPI_CAST_PTR(u8, madt), size);
+
+ /* Place the new MADT in guest memory space. */
+ if ( pvh_steal_ram(d, size, 0, GB(4), addr) )
+ {
+ printk("Unable to find allocate guest RAM for MADT\n");
+ return -ENOMEM;
+ }
+
+ /* Mark this region as E820_ACPI. */
+ if ( pvh_add_mem_range(d, *addr, *addr + size, E820_ACPI) )
+ printk("Unable to add MADT region to memory map\n");
+
+ rc = hvm_copy_to_guest_phys(*addr, madt, size, d->vcpu[0]);
+ if ( rc )
+ {
+ printk("Unable to copy MADT into guest memory\n");
+ return rc;
+ }
+ xfree(madt);
+
+ return 0;
+}
+
+static bool __init acpi_memory_banned(unsigned long address,
+ unsigned long size)
+{
+ unsigned long mfn, nr_pages, i;
+
+ mfn = PFN_DOWN(address);
+ nr_pages = PFN_UP((address & ~PAGE_MASK) + size);
+ for ( i = 0 ; i < nr_pages; i++ )
+ if ( !page_is_ram_type(mfn + i, RAM_TYPE_RESERVED) &&
+ !page_is_ram_type(mfn + i, RAM_TYPE_ACPI) )
+ return true;
+
+ return false;
+}
+
+static bool __init pvh_acpi_table_allowed(const char *sig)
+{
+ static const char __initconst banned_tables[][ACPI_NAME_SIZE] = {
+ ACPI_SIG_HPET, ACPI_SIG_SLIT, ACPI_SIG_SRAT, ACPI_SIG_MPST,
+ ACPI_SIG_PMTT, ACPI_SIG_MADT, ACPI_SIG_DMAR};
+ unsigned int i;
+
+ for ( i = 0 ; i < ARRAY_SIZE(banned_tables); i++ )
+ if ( strncmp(sig, banned_tables[i], ACPI_NAME_SIZE) == 0 )
+ return false;
+
+ /* Make sure table doesn't reside in a RAM region. */
+ if ( acpi_memory_banned(acpi_gbl_root_table_list.tables[i].address,
+ acpi_gbl_root_table_list.tables[i].length) )
+ {
+ printk("Skipping table %.4s because resides in a non-ACPI, non-reserved region\n",
+ sig);
+ return false;
+ }
+
+ return true;
+}
+
+static int __init pvh_setup_acpi_xsdt(struct domain *d, paddr_t madt_addr,
+ paddr_t *addr)
+{
+ struct acpi_table_xsdt *xsdt;
+ struct acpi_table_header *table;
+ struct acpi_table_rsdp *rsdp;
+ unsigned long size = sizeof(*xsdt);
+ unsigned int i, j, num_tables = 0;
+ paddr_t xsdt_paddr;
+ int rc;
+
+ /*
+ * Restore original DMAR table signature, we are going to filter it from
+ * the new XSDT that is presented to the guest, so it is no longer
+ * necessary to have it's signature zapped.
+ */
+ acpi_dmar_reinstate();
+
+ /* Count the number of tables that will be added to the XSDT. */
+ for( i = 0; i < acpi_gbl_root_table_list.count; i++ )
+ {
+ const char *sig = acpi_gbl_root_table_list.tables[i].signature.ascii;
+
+ if ( pvh_acpi_table_allowed(sig) )
+ num_tables++;
+ }
+
+ /*
+ * No need to add or subtract anything because struct acpi_table_xsdt
+ * includes one array slot already, and we have filtered out the original
+ * MADT and we are going to add a custom built MADT.
+ */
+ size += num_tables * sizeof(xsdt->table_offset_entry[0]);
+
+ xsdt = xzalloc_bytes(size);
+ if ( !xsdt )
+ {
+ printk("Unable to allocate memory for XSDT table\n");
+ return -ENOMEM;
+ }
+
+ /* Copy the native XSDT table header. */
+ rsdp = acpi_os_map_memory(acpi_os_get_root_pointer(), sizeof(*rsdp));
+ if ( !rsdp )
+ {
+ printk("Unable to map RSDP\n");
+ return -EINVAL;
+ }
+ xsdt_paddr = rsdp->xsdt_physical_address;
+ acpi_os_unmap_memory(rsdp, sizeof(*rsdp));
+ table = acpi_os_map_memory(xsdt_paddr, sizeof(*table));
+ if ( !table )
+ {
+ printk("Unable to map XSDT\n");
+ return -EINVAL;
+ }
+ xsdt->header = *table;
+ acpi_os_unmap_memory(table, sizeof(*table));
+
+ /* Add the custom MADT. */
+ xsdt->table_offset_entry[0] = madt_addr;
+
+ /* Copy the addresses of the rest of the allowed tables. */
+ for( i = 0, j = 1; i < acpi_gbl_root_table_list.count; i++ )
+ {
+ const char *sig = acpi_gbl_root_table_list.tables[i].signature.ascii;
+
+ if ( pvh_acpi_table_allowed(sig) )
+ xsdt->table_offset_entry[j++] =
+ acpi_gbl_root_table_list.tables[i].address;
+ }
+
+ xsdt->header.revision = 1;
+ xsdt->header.length = size;
+ /*
+ * Calling acpi_tb_checksum here is a layering violation, but
+ * introducing a wrapper for such simple usage seems overkill.
+ */
+ xsdt->header.checksum -= acpi_tb_checksum(ACPI_CAST_PTR(u8, xsdt), size);
+
+ /* Place the new XSDT in guest memory space. */
+ if ( pvh_steal_ram(d, size, 0, GB(4), addr) )
+ {
+ printk("Unable to find guest RAM for XSDT\n");
+ return -ENOMEM;
+ }
+
+ /* Mark this region as E820_ACPI. */
+ if ( pvh_add_mem_range(d, *addr, *addr + size, E820_ACPI) )
+ printk("Unable to add XSDT region to memory map\n");
+
+ rc = hvm_copy_to_guest_phys(*addr, xsdt, size, d->vcpu[0]);
+ if ( rc )
+ {
+ printk("Unable to copy XSDT into guest memory\n");
+ return rc;
+ }
+ xfree(xsdt);
+
+ return 0;
+}
+
+static int __init pvh_setup_acpi(struct domain *d, paddr_t start_info)
+{
+ unsigned long pfn, nr_pages;
+ paddr_t madt_paddr, xsdt_paddr, rsdp_paddr;
+ unsigned int i;
+ int rc;
+ struct acpi_table_rsdp *native_rsdp, rsdp = {
+ .signature = ACPI_SIG_RSDP,
+ .revision = 2,
+ .length = sizeof(rsdp),
+ };
+
+
+ /* Scan top-level tables and add their regions to the guest memory map. */
+ for( i = 0; i < acpi_gbl_root_table_list.count; i++ )
+ {
+ const char *sig = acpi_gbl_root_table_list.tables[i].signature.ascii;
+ unsigned long addr = acpi_gbl_root_table_list.tables[i].address;
+ unsigned long size = acpi_gbl_root_table_list.tables[i].length;
+
+ /*
+ * Make sure the original MADT is also mapped, so that Dom0 can
+ * properly access the data returned by _MAT methods in case it's
+ * re-using MADT memory.
+ */
+ if ( strncmp(sig, ACPI_SIG_MADT, ACPI_NAME_SIZE)
+ ? pvh_acpi_table_allowed(sig)
+ : !acpi_memory_banned(addr, size) )
+ pvh_add_mem_range(d, addr, addr + size, E820_ACPI);
+ }
+
+ /* Identity map ACPI e820 regions. */
+ for ( i = 0; i < d->arch.nr_e820; i++ )
+ {
+ if ( d->arch.e820[i].type != E820_ACPI &&
+ d->arch.e820[i].type != E820_NVS )
+ continue;
+
+ pfn = PFN_DOWN(d->arch.e820[i].addr);
+ nr_pages = PFN_UP((d->arch.e820[i].addr & ~PAGE_MASK) +
+ d->arch.e820[i].size);
+
+ rc = modify_identity_mmio(d, pfn, nr_pages, true);
+ if ( rc )
+ {
+ printk("Failed to map ACPI region [%#lx, %#lx) into Dom0 memory map\n",
+ pfn, pfn + nr_pages);
+ return rc;
+ }
+ }
+
+ rc = pvh_setup_acpi_madt(d, &madt_paddr);
+ if ( rc )
+ return rc;
+
+ rc = pvh_setup_acpi_xsdt(d, madt_paddr, &xsdt_paddr);
+ if ( rc )
+ return rc;
+
+ /* Craft a custom RSDP. */
+ native_rsdp = acpi_os_map_memory(acpi_os_get_root_pointer(), sizeof(rsdp));
+ memcpy(rsdp.oem_id, native_rsdp->oem_id, sizeof(rsdp.oem_id));
+ acpi_os_unmap_memory(native_rsdp, sizeof(rsdp));
+ rsdp.xsdt_physical_address = xsdt_paddr;
+ /*
+ * Calling acpi_tb_checksum here is a layering violation, but
+ * introducing a wrapper for such simple usage seems overkill.
+ */
+ rsdp.checksum -= acpi_tb_checksum(ACPI_CAST_PTR(u8, &rsdp),
+ ACPI_RSDP_REV0_SIZE);
+ rsdp.extended_checksum -= acpi_tb_checksum(ACPI_CAST_PTR(u8, &rsdp),
+ sizeof(rsdp));
+
+ /*
+ * Place the new RSDP in guest memory space.
+ *
+ * NB: this RSDP is not going to replace the original RSDP, which should
+ * still be accessible to the guest. However that RSDP is going to point to
+ * the native RSDT, and should not be used for the Dom0 kernel's boot
+ * purposes (we keep it visible for post boot access).
+ */
+ if ( pvh_steal_ram(d, sizeof(rsdp), 0, GB(4), &rsdp_paddr) )
+ {
+ printk("Unable to allocate guest RAM for RSDP\n");
+ return -ENOMEM;
+ }
+
+ /* Mark this region as E820_ACPI. */
+ if ( pvh_add_mem_range(d, rsdp_paddr, rsdp_paddr + sizeof(rsdp),
+ E820_ACPI) )
+ printk("Unable to add RSDP region to memory map\n");
+
+ /* Copy RSDP into guest memory. */
+ rc = hvm_copy_to_guest_phys(rsdp_paddr, &rsdp, sizeof(rsdp), d->vcpu[0]);
+ if ( rc )
+ {
+ printk("Unable to copy RSDP into guest memory\n");
+ return rc;
+ }
+
+ /* Copy RSDP address to start_info. */
+ rc = hvm_copy_to_guest_phys(start_info +
+ offsetof(struct hvm_start_info, rsdp_paddr),
+ &rsdp_paddr,
+ sizeof(((struct hvm_start_info *)
+ 0)->rsdp_paddr),
+ d->vcpu[0]);
+ if ( rc )
+ {
+ printk("Unable to copy RSDP into guest memory\n");
+ return rc;
+ }
+
+ return 0;
+}
+
static int __init construct_dom0_pvh(struct domain *d, const module_t *image,
unsigned long image_headroom,
module_t *initrd,
return rc;
}
+ rc = pvh_setup_acpi(d, start_info);
+ if ( rc )
+ {
+ printk("Failed to setup Dom0 ACPI tables: %d\n", rc);
+ return rc;
+ }
+
panic("Building a PVHv2 Dom0 is not yet supported.");
return 0;
}
projects / xen.git / commitdiff