KVM: x86: Allow Qemu/KVM to use PVH entry point

For certain applications it is desirable to rapidly boot a KVM virtual
machine. In cases where legacy hardware and software support within the
guest is not needed, Qemu should be able to boot directly into the
uncompressed Linux kernel binary without the need to run firmware.

There already exists an ABI to allow this for Xen PVH guests and the ABI
is supported by Linux and FreeBSD:

   https://xenbits.xen.org/docs/unstable/misc/pvh.html

This patch enables Qemu to use that same entry point for booting KVM
guests.

Signed-off-by: Maran Wilson <maran.wilson@oracle.com>
Suggested-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Suggested-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Tested-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>

diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
index 2089e44143003c1f413b744fca0440048e7d8ebf..c625f57472f76a4344d8c1464a9efd6d631b22c8 100644 (file)
--- a/arch/x86/Kbuild
+++ b/arch/x86/Kbuild
@@ -7,7 +7,7 @@ obj-$(CONFIG_KVM) += kvm/
 # Xen paravirtualization support
 obj-$(CONFIG_XEN) += xen/
 
-obj-$(CONFIG_XEN_PVH) += platform/pvh/
+obj-$(CONFIG_PVH) += platform/pvh/
 
 # Hyper-V paravirtualization support
 obj-$(subst m,y,$(CONFIG_HYPERV)) += hyperv/

diff --git a/arch/x86/platform/pvh/Makefile b/arch/x86/platform/pvh/Makefile
index 9fd25efcd2a3e6bf15aa10bd3db24cdd10b2b1c8..5dec5067c9fb775478fb79a8d7e0296f1035f4e3 100644 (file)
--- a/arch/x86/platform/pvh/Makefile
+++ b/arch/x86/platform/pvh/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
 OBJECT_FILES_NON_STANDARD_head.o := y
 
-obj-$(CONFIG_XEN_PVH) += enlighten.o
-obj-$(CONFIG_XEN_PVH) += head.o
+obj-$(CONFIG_PVH) += enlighten.o
+obj-$(CONFIG_PVH) += head.o

diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c
index 8040b3fbf5454b5a8372657ea67012fb230c6fec..62f5c70459440e9403afa34d59d299fb90c382cd 100644 (file)
--- a/arch/x86/platform/pvh/enlighten.c
+++ b/arch/x86/platform/pvh/enlighten.c
@@ -8,6 +8,8 @@
 #include <asm/e820/api.h>
 #include <asm/x86_init.h>
 
+#include <asm/xen/interface.h>
+
 #include <xen/xen.h>
 #include <xen/interface/hvm/start_info.h>
 
@@ -40,11 +42,28 @@ void __init __weak mem_map_via_hcall(struct boot_params *ptr __maybe_unused)
        BUG();
 }
 
-static void __init init_pvh_bootparams(void)
+static void __init init_pvh_bootparams(bool xen_guest)
 {
        memset(&pvh_bootparams, 0, sizeof(pvh_bootparams));
 
-       mem_map_via_hcall(&pvh_bootparams);
+       if ((pvh_start_info.version > 0) && (pvh_start_info.memmap_entries)) {
+               struct hvm_memmap_table_entry *ep;
+               int i;
+
+               ep = __va(pvh_start_info.memmap_paddr);
+               pvh_bootparams.e820_entries = pvh_start_info.memmap_entries;
+
+               for (i = 0; i < pvh_bootparams.e820_entries ; i++, ep++) {
+                       pvh_bootparams.e820_table[i].addr = ep->addr;
+                       pvh_bootparams.e820_table[i].size = ep->size;
+                       pvh_bootparams.e820_table[i].type = ep->type;
+               }
+       } else if (xen_guest) {
+               mem_map_via_hcall(&pvh_bootparams);
+       } else {
+               /* Non-xen guests are not supported by version 0 */
+               BUG();
+       }
 
        if (pvh_bootparams.e820_entries < E820_MAX_ENTRIES_ZEROPAGE - 1) {
                pvh_bootparams.e820_table[pvh_bootparams.e820_entries].addr =
@@ -75,7 +94,7 @@ static void __init init_pvh_bootparams(void)
         * environment (i.e. hardware_subarch 0).
         */
        pvh_bootparams.hdr.version = (2 << 8) | 12;
-       pvh_bootparams.hdr.type_of_loader = (9 << 4) | 0; /* Xen loader */
+       pvh_bootparams.hdr.type_of_loader = ((xen_guest ? 0x9 : 0xb) << 4) | 0;
 
        x86_init.acpi.get_root_pointer = pvh_get_root_pointer;
 }
@@ -90,13 +109,10 @@ void __init __weak xen_pvh_init(void)
        BUG();
 }
 
-/*
- * When we add support for other hypervisors like Qemu/KVM, this routine can
- * selectively invoke the appropriate initialization based on guest type.
- */
-static void hypervisor_specific_init(void)
+static void hypervisor_specific_init(bool xen_guest)
 {
-       xen_pvh_init();
+       if (xen_guest)
+               xen_pvh_init();
 }
 
 /*
@@ -105,13 +121,17 @@ static void hypervisor_specific_init(void)
  */
 void __init xen_prepare_pvh(void)
 {
+
+       u32 msr = xen_cpuid_base();
+       bool xen_guest = !!msr;
+
        if (pvh_start_info.magic != XEN_HVM_START_MAGIC_VALUE) {
                xen_raw_printk("Error: Unexpected magic value (0x%08x)\n",
                                pvh_start_info.magic);
                BUG();
        }
 
-       hypervisor_specific_init();
+       hypervisor_specific_init(xen_guest);
 
-       init_pvh_bootparams();
+       init_pvh_bootparams(xen_guest);
 }