Message ID | e7542e718fee0a901d1e626d07ede2227290c552.1294043582.git.jan.kiszka@web.de |
---|---|
State | New |
Headers | show |
On 01/03/2011 10:33 AM, Jan Kiszka wrote: > From: Jan Kiszka<jan.kiszka@siemens.com> > > First of all, we only need this EPT identity and TSS reservation on > Intel CPUs. kvm-amd will ignore it just fine. I'd like to keep arch differences away from userspace. > Then, in order to support loading BIOSes> 256K, reorder the > code, adjusting the base if the kernel supports moving the identity map. > We can drop the check for KVM_CAP_SET_TSS_ADDR as we already depend on > much newer features. There is no ordering on kvm features. Each can come and go as it pleases.
Am 03.01.2011 17:06, Avi Kivity wrote: > On 01/03/2011 10:33 AM, Jan Kiszka wrote: >> From: Jan Kiszka<jan.kiszka@siemens.com> >> >> First of all, we only need this EPT identity and TSS reservation on >> Intel CPUs. > > kvm-amd will ignore it just fine. I'd like to keep arch differences > away from userspace. And I would prefer to avoid needlessly cluttering the physical guest address space where not needed. Long term, we could even give user space a hint (unless it can test it directly) that this workaround is no longer needed as the host Intel CPU supports true real mode. > >> Then, in order to support loading BIOSes> 256K, reorder the >> code, adjusting the base if the kernel supports moving the identity map. >> We can drop the check for KVM_CAP_SET_TSS_ADDR as we already depend on >> much newer features. > > There is no ordering on kvm features. Each can come and go as it pleases. > Well, at least this is not how kvm upstream works so far. Jan
On 01/03/2011 06:52 PM, Jan Kiszka wrote: > Am 03.01.2011 17:06, Avi Kivity wrote: > > On 01/03/2011 10:33 AM, Jan Kiszka wrote: > >> From: Jan Kiszka<jan.kiszka@siemens.com> > >> > >> First of all, we only need this EPT identity and TSS reservation on > >> Intel CPUs. > > > > kvm-amd will ignore it just fine. I'd like to keep arch differences > > away from userspace. > > And I would prefer to avoid needlessly cluttering the physical guest > address space where not needed. Long term, we could even give user space > a hint (unless it can test it directly) that this workaround is no > longer needed as the host Intel CPU supports true real mode. Having different physical address spaces based on the host cpu is bad, even disregarding live migration. If there's a real need, we can do it as an option. I don't see such a need though. We can definitely add a new KVM_CAP for "tss/ept identity supported but not needed". If emulate_invalid_guest_state is eventually fully implemented and becomes the default, it will even be true across the board. > > > >> Then, in order to support loading BIOSes> 256K, reorder the > >> code, adjusting the base if the kernel supports moving the identity map. > >> We can drop the check for KVM_CAP_SET_TSS_ADDR as we already depend on > >> much newer features. > > > > There is no ordering on kvm features. Each can come and go as it pleases. > > > > Well, at least this is not how kvm upstream works so far. Let's change it then.
Am 03.01.2011 17:59, Avi Kivity wrote: > On 01/03/2011 06:52 PM, Jan Kiszka wrote: >> Am 03.01.2011 17:06, Avi Kivity wrote: >> > On 01/03/2011 10:33 AM, Jan Kiszka wrote: >> >> From: Jan Kiszka<jan.kiszka@siemens.com> >> >> >> >> First of all, we only need this EPT identity and TSS reservation on >> >> Intel CPUs. >> > >> > kvm-amd will ignore it just fine. I'd like to keep arch differences >> > away from userspace. >> >> And I would prefer to avoid needlessly cluttering the physical guest >> address space where not needed. Long term, we could even give user space >> a hint (unless it can test it directly) that this workaround is no >> longer needed as the host Intel CPU supports true real mode. > > Having different physical address spaces based on the host cpu is bad, > even disregarding live migration. If there's a real need, we can do it > as an option. I don't see such a need though. I see, migration is a killer argument. Jan
diff --git a/target-i386/kvm.c b/target-i386/kvm.c index 6d31dde..caca407 100644 --- a/target-i386/kvm.c +++ b/target-i386/kvm.c @@ -575,23 +575,12 @@ static int kvm_get_supported_msrs(void) return ret; } -static int kvm_init_identity_map_page(void) +static bool host_supports_vmx(void) { -#ifdef KVM_CAP_SET_IDENTITY_MAP_ADDR - int ret; - uint64_t addr = 0xfffbc000; - - if (!kvm_check_extension(KVM_CAP_SET_IDENTITY_MAP_ADDR)) { - return 0; - } + uint32_t ecx, unused; - ret = kvm_vm_ioctl(KVM_SET_IDENTITY_MAP_ADDR, &addr); - if (ret < 0) { - fprintf(stderr, "kvm_set_identity_map_addr: %s\n", strerror(ret)); - return ret; - } -#endif - return 0; + host_cpuid(1, 0, &unused, &unused, &ecx, &unused); + return ecx & CPUID_EXT_VMX; } int kvm_arch_init(void) @@ -611,35 +600,47 @@ int kvm_arch_init(void) uname(&utsname); lm_capable_kernel = strcmp(utsname.machine, "x86_64") == 0; - /* create vm86 tss. KVM uses vm86 mode to emulate 16-bit code - * directly. In order to use vm86 mode, a TSS is needed. Since this - * must be part of guest physical memory, we need to allocate it. Older - * versions of KVM just assumed that it would be at the end of physical - * memory but that doesn't work with more than 4GB of memory. We simply - * refuse to work with those older versions of KVM. */ - ret = kvm_check_extension(KVM_CAP_SET_TSS_ADDR); - if (ret <= 0) { - fprintf(stderr, "kvm does not support KVM_CAP_SET_TSS_ADDR\n"); - return ret; - } + if (host_supports_vmx()) { + /* + * On older Intel CPUs, KVM uses vm86 mode to emulate 16-bit code + * directly. In order to use vm86 mode, an EPT identity map and a TSS + * are needed. Since these must be part of guest physical memory, we + * need to allocate them, both by setting their start addresses in the + * kernel and by creating a corresponding e820 entry. We need 4 pages + * before the BIOS. + * + * Older KVM versions may not support setting the identity map base. + * In that case we need to stick with the default, i.e. a 256K maximum + * BIOS size. + */ + uint64_t identity_base = 0xfffbc000; - /* this address is 3 pages before the bios, and the bios should present - * as unavaible memory. FIXME, need to ensure the e820 map deals with - * this? - */ - /* - * Tell fw_cfg to notify the BIOS to reserve the range. - */ - if (e820_add_entry(0xfffbc000, 0x4000, E820_RESERVED) < 0) { - perror("e820_add_entry() table is full"); - exit(1); - } - ret = kvm_vm_ioctl(KVM_SET_TSS_ADDR, 0xfffbd000); - if (ret < 0) { - return ret; +#ifdef KVM_CAP_SET_IDENTITY_MAP_ADDR + if (kvm_check_extension(KVM_CAP_SET_IDENTITY_MAP_ADDR)) { + /* Allows up to 16M BIOSes. */ + identity_base = 0xfeffc000; + + ret = kvm_vm_ioctl(KVM_SET_IDENTITY_MAP_ADDR, &identity_base); + if (ret < 0) { + return ret; + } + } +#endif + /* Set TSS base one page after EPT identity map. */ + ret = kvm_vm_ioctl(KVM_SET_TSS_ADDR, identity_base + 0x1000); + if (ret < 0) { + return ret; + } + + /* Tell fw_cfg to notify the BIOS to reserve the range. */ + ret = e820_add_entry(identity_base, 0x4000, E820_RESERVED); + if (ret < 0) { + fprintf(stderr, "e820_add_entry() table is full\n"); + return ret; + } } - return kvm_init_identity_map_page(); + return 0; } static void set_v8086_seg(struct kvm_segment *lhs, const SegmentCache *rhs) @@ -1592,14 +1593,6 @@ static int kvm_handle_halt(CPUState *env) return 1; } -static bool host_supports_vmx(void) -{ - uint32_t ecx, unused; - - host_cpuid(1, 0, &unused, &unused, &ecx, &unused); - return ecx & CPUID_EXT_VMX; -} - #define VMX_INVALID_GUEST_STATE 0x80000021 int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run)