Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux
Pull s390 fixes and kexec-file-load from Martin Schwidefsky:
"After the common code kexec patches went in via Andrew we can now push
the architecture parts to implement the kexec-file-load system call.
Plus a few more bug fixes and cleanups, this includes an update to the
default configurations"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux:
s390/signal: cleanup uapi struct sigaction
s390: rename default_defconfig to debug_defconfig
s390: remove gcov defconfig
s390: update defconfig
s390: add support for IBM z14 Model ZR1
s390: remove couple of duplicate includes
s390/boot: remove unused COMPILE_VERSION and ccflags-y
s390/nospec: include cpu.h
s390/decompressor: Ignore file vmlinux.bin.full
s390/kexec_file: add generated files to .gitignore
s390/Kconfig: Move kexec config options to "Processor type and features"
s390/kexec_file: Add ELF loader
s390/kexec_file: Add crash support to image loader
s390/kexec_file: Add image loader
s390/kexec_file: Add kexec_file_load system call
s390/kexec_file: Add purgatory
s390/kexec_file: Prepare setup.h for kexec_file_load
s390/smsgiucv: disable SMSG on module unload
s390/sclp: avoid potential usage of uninitialized value
diff --git a/Documentation/devicetree/bindings/timer/nuvoton,npcm7xx-timer.txt b/Documentation/devicetree/bindings/timer/nuvoton,npcm7xx-timer.txt
new file mode 100644
index 0000000..ea22dfe
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/nuvoton,npcm7xx-timer.txt
@@ -0,0 +1,21 @@
+Nuvoton NPCM7xx timer
+
+Nuvoton NPCM7xx have three timer modules, each timer module provides five 24-bit
+timer counters.
+
+Required properties:
+- compatible : "nuvoton,npcm750-timer" for Poleg NPCM750.
+- reg : Offset and length of the register set for the device.
+- interrupts : Contain the timer interrupt with flags for
+ falling edge.
+- clocks : phandle of timer reference clock (usually a 25 MHz clock).
+
+Example:
+
+timer@f0008000 {
+ compatible = "nuvoton,npcm750-timer";
+ interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
+ reg = <0xf0008000 0x50>;
+ clocks = <&clk NPCM7XX_CLK_TIMER>;
+};
+
diff --git a/Documentation/devicetree/bindings/timer/nxp,tpm-timer.txt b/Documentation/devicetree/bindings/timer/nxp,tpm-timer.txt
index b4aa7dd..f82087b 100644
--- a/Documentation/devicetree/bindings/timer/nxp,tpm-timer.txt
+++ b/Documentation/devicetree/bindings/timer/nxp,tpm-timer.txt
@@ -15,7 +15,7 @@
- interrupts : Should be the clock event device interrupt.
- clocks : The clocks provided by the SoC to drive the timer, must contain
an entry for each entry in clock-names.
-- clock-names : Must include the following entries: "igp" and "per".
+- clock-names : Must include the following entries: "ipg" and "per".
Example:
tpm5: tpm@40260000 {
diff --git a/arch/parisc/kernel/Makefile b/arch/parisc/kernel/Makefile
index eafd06a..e5de34d 100644
--- a/arch/parisc/kernel/Makefile
+++ b/arch/parisc/kernel/Makefile
@@ -23,7 +23,7 @@
obj-$(CONFIG_PA11) += pci-dma.o
obj-$(CONFIG_PCI) += pci.o
obj-$(CONFIG_MODULES) += module.o
-obj-$(CONFIG_64BIT) += binfmt_elf32.o sys_parisc32.o signal32.o
+obj-$(CONFIG_64BIT) += sys_parisc32.o signal32.o
obj-$(CONFIG_STACKTRACE)+= stacktrace.o
obj-$(CONFIG_AUDIT) += audit.o
obj64-$(CONFIG_AUDIT) += compat_audit.o
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 949c977..c25775f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1013,6 +1013,7 @@
bool (*has_wbinvd_exit)(void);
+ u64 (*read_l1_tsc_offset)(struct kvm_vcpu *vcpu);
void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2);
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index d41d896..c9b1402 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -166,7 +166,7 @@
*/
pte_prot = __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL);
/* Filter out unsuppored __PAGE_KERNEL* bits: */
- pgprot_val(pte_prot) |= __supported_pte_mask;
+ pgprot_val(pte_prot) &= __supported_pte_mask;
pte = pfn_pte(pfn, pte_prot);
set_pte_at(mm, va, ptep, pte);
pte_unmap_unlock(ptep, ptl);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index b58787d..1fc05e4 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1423,12 +1423,23 @@
seg->base = 0;
}
+static u64 svm_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ if (is_guest_mode(vcpu))
+ return svm->nested.hsave->control.tsc_offset;
+
+ return vcpu->arch.tsc_offset;
+}
+
static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
{
struct vcpu_svm *svm = to_svm(vcpu);
u64 g_tsc_offset = 0;
if (is_guest_mode(vcpu)) {
+ /* Write L1's TSC offset. */
g_tsc_offset = svm->vmcb->control.tsc_offset -
svm->nested.hsave->control.tsc_offset;
svm->nested.hsave->control.tsc_offset = offset;
@@ -3322,6 +3333,7 @@
/* Restore the original control entries */
copy_vmcb_control_area(vmcb, hsave);
+ svm->vcpu.arch.tsc_offset = svm->vmcb->control.tsc_offset;
kvm_clear_exception_queue(&svm->vcpu);
kvm_clear_interrupt_queue(&svm->vcpu);
@@ -3482,10 +3494,12 @@
/* We don't want to see VMMCALLs from a nested guest */
clr_intercept(svm, INTERCEPT_VMMCALL);
+ svm->vcpu.arch.tsc_offset += nested_vmcb->control.tsc_offset;
+ svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset;
+
svm->vmcb->control.virt_ext = nested_vmcb->control.virt_ext;
svm->vmcb->control.int_vector = nested_vmcb->control.int_vector;
svm->vmcb->control.int_state = nested_vmcb->control.int_state;
- svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset;
svm->vmcb->control.event_inj = nested_vmcb->control.event_inj;
svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err;
@@ -4035,12 +4049,6 @@
struct vcpu_svm *svm = to_svm(vcpu);
switch (msr_info->index) {
- case MSR_IA32_TSC: {
- msr_info->data = svm->vmcb->control.tsc_offset +
- kvm_scale_tsc(vcpu, rdtsc());
-
- break;
- }
case MSR_STAR:
msr_info->data = svm->vmcb->save.star;
break;
@@ -4193,9 +4201,6 @@
svm->vmcb->save.g_pat = data;
mark_dirty(svm->vmcb, VMCB_NPT);
break;
- case MSR_IA32_TSC:
- kvm_write_tsc(vcpu, msr);
- break;
case MSR_IA32_SPEC_CTRL:
if (!msr->host_initiated &&
!guest_cpuid_has(vcpu, X86_FEATURE_IBRS))
@@ -5265,9 +5270,8 @@
}
if (!ret && svm) {
- trace_kvm_pi_irte_update(svm->vcpu.vcpu_id,
- host_irq, e->gsi,
- vcpu_info.vector,
+ trace_kvm_pi_irte_update(host_irq, svm->vcpu.vcpu_id,
+ e->gsi, vcpu_info.vector,
vcpu_info.pi_desc_addr, set);
}
@@ -7102,6 +7106,7 @@
.has_wbinvd_exit = svm_has_wbinvd_exit,
+ .read_l1_tsc_offset = svm_read_l1_tsc_offset,
.write_tsc_offset = svm_write_tsc_offset,
.set_tdp_cr3 = set_tdp_cr3,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index aafcc98..aa66ccd 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2880,18 +2880,15 @@
vmx_update_msr_bitmap(&vmx->vcpu);
}
-/*
- * reads and returns guest's timestamp counter "register"
- * guest_tsc = (host_tsc * tsc multiplier) >> 48 + tsc_offset
- * -- Intel TSC Scaling for Virtualization White Paper, sec 1.3
- */
-static u64 guest_read_tsc(struct kvm_vcpu *vcpu)
+static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
{
- u64 host_tsc, tsc_offset;
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
- host_tsc = rdtsc();
- tsc_offset = vmcs_read64(TSC_OFFSET);
- return kvm_scale_tsc(vcpu, host_tsc) + tsc_offset;
+ if (is_guest_mode(vcpu) &&
+ (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING))
+ return vcpu->arch.tsc_offset - vmcs12->tsc_offset;
+
+ return vcpu->arch.tsc_offset;
}
/*
@@ -3524,9 +3521,6 @@
#endif
case MSR_EFER:
return kvm_get_msr_common(vcpu, msr_info);
- case MSR_IA32_TSC:
- msr_info->data = guest_read_tsc(vcpu);
- break;
case MSR_IA32_SPEC_CTRL:
if (!msr_info->host_initiated &&
!guest_cpuid_has(vcpu, X86_FEATURE_IBRS) &&
@@ -3646,9 +3640,6 @@
return 1;
vmcs_write64(GUEST_BNDCFGS, data);
break;
- case MSR_IA32_TSC:
- kvm_write_tsc(vcpu, msr_info);
- break;
case MSR_IA32_SPEC_CTRL:
if (!msr_info->host_initiated &&
!guest_cpuid_has(vcpu, X86_FEATURE_IBRS) &&
@@ -10608,6 +10599,16 @@
return true;
}
+static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12)
+{
+ if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
+ !page_address_valid(vcpu, vmcs12->apic_access_addr))
+ return -EINVAL;
+ else
+ return 0;
+}
+
static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
@@ -11176,11 +11177,8 @@
vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
}
- if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
- vmcs_write64(TSC_OFFSET,
- vcpu->arch.tsc_offset + vmcs12->tsc_offset);
- else
- vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+ vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+
if (kvm_has_tsc_control)
decache_tsc_multiplier(vmx);
@@ -11299,6 +11297,9 @@
if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12))
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+ if (nested_vmx_check_apic_access_controls(vcpu, vmcs12))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
if (nested_vmx_check_tpr_shadow_controls(vcpu, vmcs12))
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
@@ -11420,6 +11421,7 @@
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
u32 msr_entry_idx;
u32 exit_qual;
+ int r;
enter_guest_mode(vcpu);
@@ -11429,26 +11431,21 @@
vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02);
vmx_segment_cache_clear(vmx);
- if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) {
- leave_guest_mode(vcpu);
- vmx_switch_vmcs(vcpu, &vmx->vmcs01);
- nested_vmx_entry_failure(vcpu, vmcs12,
- EXIT_REASON_INVALID_STATE, exit_qual);
- return 1;
- }
+ if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+ vcpu->arch.tsc_offset += vmcs12->tsc_offset;
+
+ r = EXIT_REASON_INVALID_STATE;
+ if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual))
+ goto fail;
nested_get_vmcs12_pages(vcpu, vmcs12);
+ r = EXIT_REASON_MSR_LOAD_FAIL;
msr_entry_idx = nested_vmx_load_msr(vcpu,
vmcs12->vm_entry_msr_load_addr,
vmcs12->vm_entry_msr_load_count);
- if (msr_entry_idx) {
- leave_guest_mode(vcpu);
- vmx_switch_vmcs(vcpu, &vmx->vmcs01);
- nested_vmx_entry_failure(vcpu, vmcs12,
- EXIT_REASON_MSR_LOAD_FAIL, msr_entry_idx);
- return 1;
- }
+ if (msr_entry_idx)
+ goto fail;
/*
* Note no nested_vmx_succeed or nested_vmx_fail here. At this point
@@ -11457,6 +11454,14 @@
* the success flag) when L2 exits (see nested_vmx_vmexit()).
*/
return 0;
+
+fail:
+ if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+ vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
+ leave_guest_mode(vcpu);
+ vmx_switch_vmcs(vcpu, &vmx->vmcs01);
+ nested_vmx_entry_failure(vcpu, vmcs12, r, exit_qual);
+ return 1;
}
/*
@@ -12028,6 +12033,9 @@
leave_guest_mode(vcpu);
+ if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+ vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
+
if (likely(!vmx->fail)) {
if (exit_reason == -1)
sync_vmcs12(vcpu, vmcs12);
@@ -12224,10 +12232,16 @@
static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- u64 tscl = rdtsc();
- u64 guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
- u64 delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
+ struct vcpu_vmx *vmx;
+ u64 tscl, guest_tscl, delta_tsc;
+
+ if (kvm_mwait_in_guest(vcpu->kvm))
+ return -EOPNOTSUPP;
+
+ vmx = to_vmx(vcpu);
+ tscl = rdtsc();
+ guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
+ delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
/* Convert to host delta tsc if tsc scaling is enabled */
if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio &&
@@ -12533,7 +12547,7 @@
vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
vcpu_info.vector = irq.vector;
- trace_kvm_pi_irte_update(vcpu->vcpu_id, host_irq, e->gsi,
+ trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
vcpu_info.vector, vcpu_info.pi_desc_addr, set);
if (set)
@@ -12712,6 +12726,7 @@
.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
+ .read_l1_tsc_offset = vmx_read_l1_tsc_offset,
.write_tsc_offset = vmx_write_tsc_offset,
.set_tdp_cr3 = vmx_set_cr3,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b2ff74b..51ecd38 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1490,7 +1490,7 @@
static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset)
{
- u64 curr_offset = vcpu->arch.tsc_offset;
+ u64 curr_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu);
vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset;
}
@@ -1532,7 +1532,9 @@
u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
{
- return vcpu->arch.tsc_offset + kvm_scale_tsc(vcpu, host_tsc);
+ u64 tsc_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu);
+
+ return tsc_offset + kvm_scale_tsc(vcpu, host_tsc);
}
EXPORT_SYMBOL_GPL(kvm_read_l1_tsc);
@@ -2362,6 +2364,9 @@
return 1;
vcpu->arch.smbase = data;
break;
+ case MSR_IA32_TSC:
+ kvm_write_tsc(vcpu, msr_info);
+ break;
case MSR_SMI_COUNT:
if (!msr_info->host_initiated)
return 1;
@@ -2605,6 +2610,9 @@
case MSR_IA32_UCODE_REV:
msr_info->data = vcpu->arch.microcode_version;
break;
+ case MSR_IA32_TSC:
+ msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset;
+ break;
case MSR_MTRRcap:
case 0x200 ... 0x2ff:
return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data);
@@ -2819,7 +2827,8 @@
static inline bool kvm_can_mwait_in_guest(void)
{
return boot_cpu_has(X86_FEATURE_MWAIT) &&
- !boot_cpu_has_bug(X86_BUG_MONITOR);
+ !boot_cpu_has_bug(X86_BUG_MONITOR) &&
+ boot_cpu_has(X86_FEATURE_ARAT);
}
int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 07dc541..8e8b04c 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -732,6 +732,7 @@
*/
enum {
Opt_queue_depth,
+ Opt_lock_timeout,
Opt_last_int,
/* int args above */
Opt_last_string,
@@ -740,11 +741,13 @@
Opt_read_write,
Opt_lock_on_read,
Opt_exclusive,
+ Opt_notrim,
Opt_err
};
static match_table_t rbd_opts_tokens = {
{Opt_queue_depth, "queue_depth=%d"},
+ {Opt_lock_timeout, "lock_timeout=%d"},
/* int args above */
/* string args above */
{Opt_read_only, "read_only"},
@@ -753,20 +756,25 @@
{Opt_read_write, "rw"}, /* Alternate spelling */
{Opt_lock_on_read, "lock_on_read"},
{Opt_exclusive, "exclusive"},
+ {Opt_notrim, "notrim"},
{Opt_err, NULL}
};
struct rbd_options {
int queue_depth;
+ unsigned long lock_timeout;
bool read_only;
bool lock_on_read;
bool exclusive;
+ bool trim;
};
#define RBD_QUEUE_DEPTH_DEFAULT BLKDEV_MAX_RQ
+#define RBD_LOCK_TIMEOUT_DEFAULT 0 /* no timeout */
#define RBD_READ_ONLY_DEFAULT false
#define RBD_LOCK_ON_READ_DEFAULT false
#define RBD_EXCLUSIVE_DEFAULT false
+#define RBD_TRIM_DEFAULT true
static int parse_rbd_opts_token(char *c, void *private)
{
@@ -796,6 +804,14 @@
}
rbd_opts->queue_depth = intval;
break;
+ case Opt_lock_timeout:
+ /* 0 is "wait forever" (i.e. infinite timeout) */
+ if (intval < 0 || intval > INT_MAX / 1000) {
+ pr_err("lock_timeout out of range\n");
+ return -EINVAL;
+ }
+ rbd_opts->lock_timeout = msecs_to_jiffies(intval * 1000);
+ break;
case Opt_read_only:
rbd_opts->read_only = true;
break;
@@ -808,6 +824,9 @@
case Opt_exclusive:
rbd_opts->exclusive = true;
break;
+ case Opt_notrim:
+ rbd_opts->trim = false;
+ break;
default:
/* libceph prints "bad option" msg */
return -EINVAL;
@@ -1392,7 +1411,7 @@
case OBJ_OP_DISCARD:
return true;
default:
- rbd_assert(0);
+ BUG();
}
}
@@ -2466,7 +2485,7 @@
}
return false;
default:
- rbd_assert(0);
+ BUG();
}
}
@@ -2494,7 +2513,7 @@
}
return false;
default:
- rbd_assert(0);
+ BUG();
}
}
@@ -3533,9 +3552,22 @@
/*
* lock_rwsem must be held for read
*/
-static void rbd_wait_state_locked(struct rbd_device *rbd_dev)
+static int rbd_wait_state_locked(struct rbd_device *rbd_dev, bool may_acquire)
{
DEFINE_WAIT(wait);
+ unsigned long timeout;
+ int ret = 0;
+
+ if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags))
+ return -EBLACKLISTED;
+
+ if (rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED)
+ return 0;
+
+ if (!may_acquire) {
+ rbd_warn(rbd_dev, "exclusive lock required");
+ return -EROFS;
+ }
do {
/*
@@ -3547,12 +3579,22 @@
prepare_to_wait_exclusive(&rbd_dev->lock_waitq, &wait,
TASK_UNINTERRUPTIBLE);
up_read(&rbd_dev->lock_rwsem);
- schedule();
+ timeout = schedule_timeout(ceph_timeout_jiffies(
+ rbd_dev->opts->lock_timeout));
down_read(&rbd_dev->lock_rwsem);
- } while (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED &&
- !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags));
+ if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
+ ret = -EBLACKLISTED;
+ break;
+ }
+ if (!timeout) {
+ rbd_warn(rbd_dev, "timed out waiting for lock");
+ ret = -ETIMEDOUT;
+ break;
+ }
+ } while (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED);
finish_wait(&rbd_dev->lock_waitq, &wait);
+ return ret;
}
static void rbd_queue_workfn(struct work_struct *work)
@@ -3638,19 +3680,10 @@
(op_type != OBJ_OP_READ || rbd_dev->opts->lock_on_read);
if (must_be_locked) {
down_read(&rbd_dev->lock_rwsem);
- if (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED &&
- !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
- if (rbd_dev->opts->exclusive) {
- rbd_warn(rbd_dev, "exclusive lock required");
- result = -EROFS;
- goto err_unlock;
- }
- rbd_wait_state_locked(rbd_dev);
- }
- if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
- result = -EBLACKLISTED;
+ result = rbd_wait_state_locked(rbd_dev,
+ !rbd_dev->opts->exclusive);
+ if (result)
goto err_unlock;
- }
}
img_request = rbd_img_request_create(rbd_dev, op_type, snapc);
@@ -3902,7 +3935,8 @@
{
struct gendisk *disk;
struct request_queue *q;
- u64 segment_size;
+ unsigned int objset_bytes =
+ rbd_dev->layout.object_size * rbd_dev->layout.stripe_count;
int err;
/* create gendisk info */
@@ -3942,20 +3976,19 @@
blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
/* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */
- /* set io sizes to object size */
- segment_size = rbd_obj_bytes(&rbd_dev->header);
- blk_queue_max_hw_sectors(q, segment_size / SECTOR_SIZE);
+ blk_queue_max_hw_sectors(q, objset_bytes >> SECTOR_SHIFT);
q->limits.max_sectors = queue_max_hw_sectors(q);
blk_queue_max_segments(q, USHRT_MAX);
blk_queue_max_segment_size(q, UINT_MAX);
- blk_queue_io_min(q, segment_size);
- blk_queue_io_opt(q, segment_size);
+ blk_queue_io_min(q, objset_bytes);
+ blk_queue_io_opt(q, objset_bytes);
- /* enable the discard support */
- blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
- q->limits.discard_granularity = segment_size;
- blk_queue_max_discard_sectors(q, segment_size / SECTOR_SIZE);
- blk_queue_max_write_zeroes_sectors(q, segment_size / SECTOR_SIZE);
+ if (rbd_dev->opts->trim) {
+ blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
+ q->limits.discard_granularity = objset_bytes;
+ blk_queue_max_discard_sectors(q, objset_bytes >> SECTOR_SHIFT);
+ blk_queue_max_write_zeroes_sectors(q, objset_bytes >> SECTOR_SHIFT);
+ }
if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
@@ -5179,8 +5212,10 @@
rbd_opts->read_only = RBD_READ_ONLY_DEFAULT;
rbd_opts->queue_depth = RBD_QUEUE_DEPTH_DEFAULT;
+ rbd_opts->lock_timeout = RBD_LOCK_TIMEOUT_DEFAULT;
rbd_opts->lock_on_read = RBD_LOCK_ON_READ_DEFAULT;
rbd_opts->exclusive = RBD_EXCLUSIVE_DEFAULT;
+ rbd_opts->trim = RBD_TRIM_DEFAULT;
copts = ceph_parse_options(options, mon_addrs,
mon_addrs + mon_addrs_size - 1,
@@ -5216,6 +5251,8 @@
static int rbd_add_acquire_lock(struct rbd_device *rbd_dev)
{
+ int ret;
+
if (!(rbd_dev->header.features & RBD_FEATURE_EXCLUSIVE_LOCK)) {
rbd_warn(rbd_dev, "exclusive-lock feature is not enabled");
return -EINVAL;
@@ -5223,9 +5260,9 @@
/* FIXME: "rbd map --exclusive" should be in interruptible */
down_read(&rbd_dev->lock_rwsem);
- rbd_wait_state_locked(rbd_dev);
+ ret = rbd_wait_state_locked(rbd_dev, true);
up_read(&rbd_dev->lock_rwsem);
- if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
+ if (ret) {
rbd_warn(rbd_dev, "failed to acquire exclusive lock");
return -EROFS;
}
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 9ee2888..8e8a097 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -133,6 +133,14 @@
help
Enables support for the VT8500 driver.
+config NPCM7XX_TIMER
+ bool "NPCM7xx timer driver" if COMPILE_TEST
+ depends on HAS_IOMEM
+ select CLKSRC_MMIO
+ help
+ Enable 24-bit TIMER0 and TIMER1 counters in the NPCM7xx architecture,
+ While TIMER0 serves as clockevent and TIMER1 serves as clocksource.
+
config CADENCE_TTC_TIMER
bool "Cadence TTC timer driver" if COMPILE_TEST
depends on COMMON_CLK
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index e8e76df..00caf37 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -56,6 +56,7 @@
obj-$(CONFIG_OXNAS_RPS_TIMER) += timer-oxnas-rps.o
obj-$(CONFIG_OWL_TIMER) += owl-timer.o
obj-$(CONFIG_SPRD_TIMER) += timer-sprd.o
+obj-$(CONFIG_NPCM7XX_TIMER) += timer-npcm7xx.o
obj-$(CONFIG_ARC_TIMERS) += arc_timer.o
obj-$(CONFIG_ARM_ARCH_TIMER) += arm_arch_timer.o
diff --git a/drivers/clocksource/timer-imx-tpm.c b/drivers/clocksource/timer-imx-tpm.c
index 21bffdc..05d97a6 100644
--- a/drivers/clocksource/timer-imx-tpm.c
+++ b/drivers/clocksource/timer-imx-tpm.c
@@ -17,9 +17,14 @@
#include <linux/of_irq.h>
#include <linux/sched_clock.h>
+#define TPM_PARAM 0x4
+#define TPM_PARAM_WIDTH_SHIFT 16
+#define TPM_PARAM_WIDTH_MASK (0xff << 16)
#define TPM_SC 0x10
#define TPM_SC_CMOD_INC_PER_CNT (0x1 << 3)
#define TPM_SC_CMOD_DIV_DEFAULT 0x3
+#define TPM_SC_CMOD_DIV_MAX 0x7
+#define TPM_SC_TOF_MASK (0x1 << 7)
#define TPM_CNT 0x14
#define TPM_MOD 0x18
#define TPM_STATUS 0x1c
@@ -29,8 +34,11 @@
#define TPM_C0SC_MODE_SHIFT 2
#define TPM_C0SC_MODE_MASK 0x3c
#define TPM_C0SC_MODE_SW_COMPARE 0x4
+#define TPM_C0SC_CHF_MASK (0x1 << 7)
#define TPM_C0V 0x24
+static int counter_width;
+static int rating;
static void __iomem *timer_base;
static struct clock_event_device clockevent_tpm;
@@ -83,10 +91,11 @@
tpm_delay_timer.freq = rate;
register_current_timer_delay(&tpm_delay_timer);
- sched_clock_register(tpm_read_sched_clock, 32, rate);
+ sched_clock_register(tpm_read_sched_clock, counter_width, rate);
return clocksource_mmio_init(timer_base + TPM_CNT, "imx-tpm",
- rate, 200, 32, clocksource_mmio_readl_up);
+ rate, rating, counter_width,
+ clocksource_mmio_readl_up);
}
static int tpm_set_next_event(unsigned long delta,
@@ -139,7 +148,6 @@
.set_state_oneshot = tpm_set_state_oneshot,
.set_next_event = tpm_set_next_event,
.set_state_shutdown = tpm_set_state_shutdown,
- .rating = 200,
};
static int __init tpm_clockevent_init(unsigned long rate, int irq)
@@ -149,10 +157,11 @@
ret = request_irq(irq, tpm_timer_interrupt, IRQF_TIMER | IRQF_IRQPOLL,
"i.MX7ULP TPM Timer", &clockevent_tpm);
+ clockevent_tpm.rating = rating;
clockevent_tpm.cpumask = cpumask_of(0);
clockevent_tpm.irq = irq;
- clockevents_config_and_register(&clockevent_tpm,
- rate, 300, 0xfffffffe);
+ clockevents_config_and_register(&clockevent_tpm, rate, 300,
+ GENMASK(counter_width - 1, 1));
return ret;
}
@@ -179,7 +188,7 @@
ipg = of_clk_get_by_name(np, "ipg");
per = of_clk_get_by_name(np, "per");
if (IS_ERR(ipg) || IS_ERR(per)) {
- pr_err("tpm: failed to get igp or per clk\n");
+ pr_err("tpm: failed to get ipg or per clk\n");
ret = -ENODEV;
goto err_clk_get;
}
@@ -197,6 +206,11 @@
goto err_per_clk_enable;
}
+ counter_width = (readl(timer_base + TPM_PARAM) & TPM_PARAM_WIDTH_MASK)
+ >> TPM_PARAM_WIDTH_SHIFT;
+ /* use rating 200 for 32-bit counter and 150 for 16-bit counter */
+ rating = counter_width == 0x20 ? 200 : 150;
+
/*
* Initialize tpm module to a known state
* 1) Counter disabled
@@ -205,16 +219,25 @@
* 4) Channel0 disabled
* 5) DMA transfers disabled
*/
+ /* make sure counter is disabled */
writel(0, timer_base + TPM_SC);
+ /* TOF is W1C */
+ writel(TPM_SC_TOF_MASK, timer_base + TPM_SC);
writel(0, timer_base + TPM_CNT);
- writel(0, timer_base + TPM_C0SC);
+ /* CHF is W1C */
+ writel(TPM_C0SC_CHF_MASK, timer_base + TPM_C0SC);
- /* increase per cnt, div 8 by default */
- writel(TPM_SC_CMOD_INC_PER_CNT | TPM_SC_CMOD_DIV_DEFAULT,
+ /*
+ * increase per cnt,
+ * div 8 for 32-bit counter and div 128 for 16-bit counter
+ */
+ writel(TPM_SC_CMOD_INC_PER_CNT |
+ (counter_width == 0x20 ?
+ TPM_SC_CMOD_DIV_DEFAULT : TPM_SC_CMOD_DIV_MAX),
timer_base + TPM_SC);
/* set MOD register to maximum for free running mode */
- writel(0xffffffff, timer_base + TPM_MOD);
+ writel(GENMASK(counter_width - 1, 0), timer_base + TPM_MOD);
rate = clk_get_rate(per) >> 3;
ret = tpm_clocksource_init(rate);
diff --git a/drivers/clocksource/timer-npcm7xx.c b/drivers/clocksource/timer-npcm7xx.c
new file mode 100644
index 0000000..7a9bb55
--- /dev/null
+++ b/drivers/clocksource/timer-npcm7xx.c
@@ -0,0 +1,215 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2014-2018 Nuvoton Technologies tomer.maimon@nuvoton.com
+ * All rights reserved.
+ *
+ * Copyright 2017 Google, Inc.
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/err.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/clockchips.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+#include "timer-of.h"
+
+/* Timers registers */
+#define NPCM7XX_REG_TCSR0 0x0 /* Timer 0 Control and Status Register */
+#define NPCM7XX_REG_TICR0 0x8 /* Timer 0 Initial Count Register */
+#define NPCM7XX_REG_TCSR1 0x4 /* Timer 1 Control and Status Register */
+#define NPCM7XX_REG_TICR1 0xc /* Timer 1 Initial Count Register */
+#define NPCM7XX_REG_TDR1 0x14 /* Timer 1 Data Register */
+#define NPCM7XX_REG_TISR 0x18 /* Timer Interrupt Status Register */
+
+/* Timers control */
+#define NPCM7XX_Tx_RESETINT 0x1f
+#define NPCM7XX_Tx_PERIOD BIT(27)
+#define NPCM7XX_Tx_INTEN BIT(29)
+#define NPCM7XX_Tx_COUNTEN BIT(30)
+#define NPCM7XX_Tx_ONESHOT 0x0
+#define NPCM7XX_Tx_OPER GENMASK(3, 27)
+#define NPCM7XX_Tx_MIN_PRESCALE 0x1
+#define NPCM7XX_Tx_TDR_MASK_BITS 24
+#define NPCM7XX_Tx_MAX_CNT 0xFFFFFF
+#define NPCM7XX_T0_CLR_INT 0x1
+#define NPCM7XX_Tx_CLR_CSR 0x0
+
+/* Timers operating mode */
+#define NPCM7XX_START_PERIODIC_Tx (NPCM7XX_Tx_PERIOD | NPCM7XX_Tx_COUNTEN | \
+ NPCM7XX_Tx_INTEN | \
+ NPCM7XX_Tx_MIN_PRESCALE)
+
+#define NPCM7XX_START_ONESHOT_Tx (NPCM7XX_Tx_ONESHOT | NPCM7XX_Tx_COUNTEN | \
+ NPCM7XX_Tx_INTEN | \
+ NPCM7XX_Tx_MIN_PRESCALE)
+
+#define NPCM7XX_START_Tx (NPCM7XX_Tx_COUNTEN | NPCM7XX_Tx_PERIOD | \
+ NPCM7XX_Tx_MIN_PRESCALE)
+
+#define NPCM7XX_DEFAULT_CSR (NPCM7XX_Tx_CLR_CSR | NPCM7XX_Tx_MIN_PRESCALE)
+
+static int npcm7xx_timer_resume(struct clock_event_device *evt)
+{
+ struct timer_of *to = to_timer_of(evt);
+ u32 val;
+
+ val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
+ val |= NPCM7XX_Tx_COUNTEN;
+ writel(val, timer_of_base(to) + NPCM7XX_REG_TCSR0);
+
+ return 0;
+}
+
+static int npcm7xx_timer_shutdown(struct clock_event_device *evt)
+{
+ struct timer_of *to = to_timer_of(evt);
+ u32 val;
+
+ val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
+ val &= ~NPCM7XX_Tx_COUNTEN;
+ writel(val, timer_of_base(to) + NPCM7XX_REG_TCSR0);
+
+ return 0;
+}
+
+static int npcm7xx_timer_oneshot(struct clock_event_device *evt)
+{
+ struct timer_of *to = to_timer_of(evt);
+ u32 val;
+
+ val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
+ val &= ~NPCM7XX_Tx_OPER;
+
+ val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
+ val |= NPCM7XX_START_ONESHOT_Tx;
+ writel(val, timer_of_base(to) + NPCM7XX_REG_TCSR0);
+
+ return 0;
+}
+
+static int npcm7xx_timer_periodic(struct clock_event_device *evt)
+{
+ struct timer_of *to = to_timer_of(evt);
+ u32 val;
+
+ val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
+ val &= ~NPCM7XX_Tx_OPER;
+
+ writel(timer_of_period(to), timer_of_base(to) + NPCM7XX_REG_TICR0);
+ val |= NPCM7XX_START_PERIODIC_Tx;
+
+ writel(val, timer_of_base(to) + NPCM7XX_REG_TCSR0);
+
+ return 0;
+}
+
+static int npcm7xx_clockevent_set_next_event(unsigned long evt,
+ struct clock_event_device *clk)
+{
+ struct timer_of *to = to_timer_of(clk);
+ u32 val;
+
+ writel(evt, timer_of_base(to) + NPCM7XX_REG_TICR0);
+ val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
+ val |= NPCM7XX_START_Tx;
+ writel(val, timer_of_base(to) + NPCM7XX_REG_TCSR0);
+
+ return 0;
+}
+
+static irqreturn_t npcm7xx_timer0_interrupt(int irq, void *dev_id)
+{
+ struct clock_event_device *evt = (struct clock_event_device *)dev_id;
+ struct timer_of *to = to_timer_of(evt);
+
+ writel(NPCM7XX_T0_CLR_INT, timer_of_base(to) + NPCM7XX_REG_TISR);
+
+ evt->event_handler(evt);
+
+ return IRQ_HANDLED;
+}
+
+static struct timer_of npcm7xx_to = {
+ .flags = TIMER_OF_IRQ | TIMER_OF_BASE | TIMER_OF_CLOCK,
+
+ .clkevt = {
+ .name = "npcm7xx-timer0",
+ .features = CLOCK_EVT_FEAT_PERIODIC |
+ CLOCK_EVT_FEAT_ONESHOT,
+ .set_next_event = npcm7xx_clockevent_set_next_event,
+ .set_state_shutdown = npcm7xx_timer_shutdown,
+ .set_state_periodic = npcm7xx_timer_periodic,
+ .set_state_oneshot = npcm7xx_timer_oneshot,
+ .tick_resume = npcm7xx_timer_resume,
+ .rating = 300,
+ },
+
+ .of_irq = {
+ .handler = npcm7xx_timer0_interrupt,
+ .flags = IRQF_TIMER | IRQF_IRQPOLL,
+ },
+};
+
+static void __init npcm7xx_clockevents_init(void)
+{
+ writel(NPCM7XX_DEFAULT_CSR,
+ timer_of_base(&npcm7xx_to) + NPCM7XX_REG_TCSR0);
+
+ writel(NPCM7XX_Tx_RESETINT,
+ timer_of_base(&npcm7xx_to) + NPCM7XX_REG_TISR);
+
+ npcm7xx_to.clkevt.cpumask = cpumask_of(0);
+ clockevents_config_and_register(&npcm7xx_to.clkevt,
+ timer_of_rate(&npcm7xx_to),
+ 0x1, NPCM7XX_Tx_MAX_CNT);
+}
+
+static void __init npcm7xx_clocksource_init(void)
+{
+ u32 val;
+
+ writel(NPCM7XX_DEFAULT_CSR,
+ timer_of_base(&npcm7xx_to) + NPCM7XX_REG_TCSR1);
+ writel(NPCM7XX_Tx_MAX_CNT,
+ timer_of_base(&npcm7xx_to) + NPCM7XX_REG_TICR1);
+
+ val = readl(timer_of_base(&npcm7xx_to) + NPCM7XX_REG_TCSR1);
+ val |= NPCM7XX_START_Tx;
+ writel(val, timer_of_base(&npcm7xx_to) + NPCM7XX_REG_TCSR1);
+
+ clocksource_mmio_init(timer_of_base(&npcm7xx_to) +
+ NPCM7XX_REG_TDR1,
+ "npcm7xx-timer1", timer_of_rate(&npcm7xx_to),
+ 200, (unsigned int)NPCM7XX_Tx_TDR_MASK_BITS,
+ clocksource_mmio_readl_down);
+}
+
+static int __init npcm7xx_timer_init(struct device_node *np)
+{
+ int ret;
+
+ ret = timer_of_init(np, &npcm7xx_to);
+ if (ret)
+ return ret;
+
+ /* Clock input is divided by PRESCALE + 1 before it is fed */
+ /* to the counter */
+ npcm7xx_to.of_clk.rate = npcm7xx_to.of_clk.rate /
+ (NPCM7XX_Tx_MIN_PRESCALE + 1);
+
+ npcm7xx_clocksource_init();
+ npcm7xx_clockevents_init();
+
+ pr_info("Enabling NPCM7xx clocksource timer base: %px, IRQ: %d ",
+ timer_of_base(&npcm7xx_to), timer_of_irq(&npcm7xx_to));
+
+ return 0;
+}
+
+TIMER_OF_DECLARE(npcm7xx, "nuvoton,npcm750-timer", npcm7xx_timer_init);
+
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 8bf6025..ae05692 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -669,13 +669,15 @@
CEPH_CAP_FILE_BUFFER|
CEPH_CAP_AUTH_EXCL|
CEPH_CAP_XATTR_EXCL)) {
- if (timespec_compare(ctime, &inode->i_ctime) > 0) {
+ if (ci->i_version == 0 ||
+ timespec_compare(ctime, &inode->i_ctime) > 0) {
dout("ctime %ld.%09ld -> %ld.%09ld inc w/ cap\n",
inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec,
ctime->tv_sec, ctime->tv_nsec);
inode->i_ctime = *ctime;
}
- if (ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) > 0) {
+ if (ci->i_version == 0 ||
+ ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) > 0) {
/* the MDS did a utimes() */
dout("mtime %ld.%09ld -> %ld.%09ld "
"tw %d -> %d\n",
@@ -795,7 +797,6 @@
new_issued = ~issued & le32_to_cpu(info->cap.caps);
/* update inode */
- ci->i_version = le64_to_cpu(info->version);
inode->i_rdev = le32_to_cpu(info->rdev);
inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
@@ -868,6 +869,9 @@
xattr_blob = NULL;
}
+ /* finally update i_version */
+ ci->i_version = le64_to_cpu(info->version);
+
inode->i_mapping->a_ops = &ceph_aops;
switch (inode->i_mode & S_IFMT) {
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index dc44de9..2ddcc96 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -4,17 +4,18 @@
UNAME_M := $(shell uname -m)
LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c
-LIBKVM_x86_64 = lib/x86.c
+LIBKVM_x86_64 = lib/x86.c lib/vmx.c
TEST_GEN_PROGS_x86_64 = set_sregs_test
TEST_GEN_PROGS_x86_64 += sync_regs_test
+TEST_GEN_PROGS_x86_64 += vmx_tsc_adjust_test
TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
LIBKVM += $(LIBKVM_$(UNAME_M))
INSTALL_HDR_PATH = $(top_srcdir)/usr
LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
-CFLAGS += -O2 -g -I$(LINUX_HDR_PATH) -Iinclude -I$(<D)
+CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_HDR_PATH) -Iinclude -I$(<D)
# After inclusion, $(OUTPUT) is defined and
# $(TEST_GEN_PROGS) starts with $(OUTPUT)/
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 57974ad..637b701 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -112,24 +112,27 @@
vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm,
vm_paddr_t paddr_min, uint32_t memslot);
-void kvm_get_supported_cpuid(struct kvm_cpuid2 *cpuid);
+struct kvm_cpuid2 *kvm_get_supported_cpuid(void);
void vcpu_set_cpuid(
struct kvm_vm *vm, uint32_t vcpuid, struct kvm_cpuid2 *cpuid);
-struct kvm_cpuid2 *allocate_kvm_cpuid2(void);
struct kvm_cpuid_entry2 *
-find_cpuid_index_entry(struct kvm_cpuid2 *cpuid, uint32_t function,
- uint32_t index);
+kvm_get_supported_cpuid_index(uint32_t function, uint32_t index);
static inline struct kvm_cpuid_entry2 *
-find_cpuid_entry(struct kvm_cpuid2 *cpuid, uint32_t function)
+kvm_get_supported_cpuid_entry(uint32_t function)
{
- return find_cpuid_index_entry(cpuid, function, 0);
+ return kvm_get_supported_cpuid_index(function, 0);
}
struct kvm_vm *vm_create_default(uint32_t vcpuid, void *guest_code);
void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code);
+typedef void (*vmx_guest_code_t)(vm_vaddr_t vmxon_vaddr,
+ vm_paddr_t vmxon_paddr,
+ vm_vaddr_t vmcs_vaddr,
+ vm_paddr_t vmcs_paddr);
+
struct kvm_userspace_memory_region *
kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
uint64_t end);
diff --git a/tools/testing/selftests/kvm/include/vmx.h b/tools/testing/selftests/kvm/include/vmx.h
new file mode 100644
index 0000000..6ed8499
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/vmx.h
@@ -0,0 +1,494 @@
+/*
+ * tools/testing/selftests/kvm/include/vmx.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ */
+
+#ifndef SELFTEST_KVM_VMX_H
+#define SELFTEST_KVM_VMX_H
+
+#include <stdint.h>
+#include "x86.h"
+
+#define CPUID_VMX_BIT 5
+
+#define CPUID_VMX (1 << 5)
+
+/*
+ * Definitions of Primary Processor-Based VM-Execution Controls.
+ */
+#define CPU_BASED_VIRTUAL_INTR_PENDING 0x00000004
+#define CPU_BASED_USE_TSC_OFFSETING 0x00000008
+#define CPU_BASED_HLT_EXITING 0x00000080
+#define CPU_BASED_INVLPG_EXITING 0x00000200
+#define CPU_BASED_MWAIT_EXITING 0x00000400
+#define CPU_BASED_RDPMC_EXITING 0x00000800
+#define CPU_BASED_RDTSC_EXITING 0x00001000
+#define CPU_BASED_CR3_LOAD_EXITING 0x00008000
+#define CPU_BASED_CR3_STORE_EXITING 0x00010000
+#define CPU_BASED_CR8_LOAD_EXITING 0x00080000
+#define CPU_BASED_CR8_STORE_EXITING 0x00100000
+#define CPU_BASED_TPR_SHADOW 0x00200000
+#define CPU_BASED_VIRTUAL_NMI_PENDING 0x00400000
+#define CPU_BASED_MOV_DR_EXITING 0x00800000
+#define CPU_BASED_UNCOND_IO_EXITING 0x01000000
+#define CPU_BASED_USE_IO_BITMAPS 0x02000000
+#define CPU_BASED_MONITOR_TRAP 0x08000000
+#define CPU_BASED_USE_MSR_BITMAPS 0x10000000
+#define CPU_BASED_MONITOR_EXITING 0x20000000
+#define CPU_BASED_PAUSE_EXITING 0x40000000
+#define CPU_BASED_ACTIVATE_SECONDARY_CONTROLS 0x80000000
+
+#define CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR 0x0401e172
+
+/*
+ * Definitions of Secondary Processor-Based VM-Execution Controls.
+ */
+#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
+#define SECONDARY_EXEC_ENABLE_EPT 0x00000002
+#define SECONDARY_EXEC_DESC 0x00000004
+#define SECONDARY_EXEC_RDTSCP 0x00000008
+#define SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE 0x00000010
+#define SECONDARY_EXEC_ENABLE_VPID 0x00000020
+#define SECONDARY_EXEC_WBINVD_EXITING 0x00000040
+#define SECONDARY_EXEC_UNRESTRICTED_GUEST 0x00000080
+#define SECONDARY_EXEC_APIC_REGISTER_VIRT 0x00000100
+#define SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY 0x00000200
+#define SECONDARY_EXEC_PAUSE_LOOP_EXITING 0x00000400
+#define SECONDARY_EXEC_RDRAND_EXITING 0x00000800
+#define SECONDARY_EXEC_ENABLE_INVPCID 0x00001000
+#define SECONDARY_EXEC_ENABLE_VMFUNC 0x00002000
+#define SECONDARY_EXEC_SHADOW_VMCS 0x00004000
+#define SECONDARY_EXEC_RDSEED_EXITING 0x00010000
+#define SECONDARY_EXEC_ENABLE_PML 0x00020000
+#define SECONDARY_EPT_VE 0x00040000
+#define SECONDARY_ENABLE_XSAV_RESTORE 0x00100000
+#define SECONDARY_EXEC_TSC_SCALING 0x02000000
+
+#define PIN_BASED_EXT_INTR_MASK 0x00000001
+#define PIN_BASED_NMI_EXITING 0x00000008
+#define PIN_BASED_VIRTUAL_NMIS 0x00000020
+#define PIN_BASED_VMX_PREEMPTION_TIMER 0x00000040
+#define PIN_BASED_POSTED_INTR 0x00000080
+
+#define PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR 0x00000016
+
+#define VM_EXIT_SAVE_DEBUG_CONTROLS 0x00000004
+#define VM_EXIT_HOST_ADDR_SPACE_SIZE 0x00000200
+#define VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL 0x00001000
+#define VM_EXIT_ACK_INTR_ON_EXIT 0x00008000
+#define VM_EXIT_SAVE_IA32_PAT 0x00040000
+#define VM_EXIT_LOAD_IA32_PAT 0x00080000
+#define VM_EXIT_SAVE_IA32_EFER 0x00100000
+#define VM_EXIT_LOAD_IA32_EFER 0x00200000
+#define VM_EXIT_SAVE_VMX_PREEMPTION_TIMER 0x00400000
+
+#define VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR 0x00036dff
+
+#define VM_ENTRY_LOAD_DEBUG_CONTROLS 0x00000004
+#define VM_ENTRY_IA32E_MODE 0x00000200
+#define VM_ENTRY_SMM 0x00000400
+#define VM_ENTRY_DEACT_DUAL_MONITOR 0x00000800
+#define VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL 0x00002000
+#define VM_ENTRY_LOAD_IA32_PAT 0x00004000
+#define VM_ENTRY_LOAD_IA32_EFER 0x00008000
+
+#define VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR 0x000011ff
+
+#define VMX_MISC_PREEMPTION_TIMER_RATE_MASK 0x0000001f
+#define VMX_MISC_SAVE_EFER_LMA 0x00000020
+
+#define EXIT_REASON_FAILED_VMENTRY 0x80000000
+#define EXIT_REASON_EXCEPTION_NMI 0
+#define EXIT_REASON_EXTERNAL_INTERRUPT 1
+#define EXIT_REASON_TRIPLE_FAULT 2
+#define EXIT_REASON_PENDING_INTERRUPT 7
+#define EXIT_REASON_NMI_WINDOW 8
+#define EXIT_REASON_TASK_SWITCH 9
+#define EXIT_REASON_CPUID 10
+#define EXIT_REASON_HLT 12
+#define EXIT_REASON_INVD 13
+#define EXIT_REASON_INVLPG 14
+#define EXIT_REASON_RDPMC 15
+#define EXIT_REASON_RDTSC 16
+#define EXIT_REASON_VMCALL 18
+#define EXIT_REASON_VMCLEAR 19
+#define EXIT_REASON_VMLAUNCH 20
+#define EXIT_REASON_VMPTRLD 21
+#define EXIT_REASON_VMPTRST 22
+#define EXIT_REASON_VMREAD 23
+#define EXIT_REASON_VMRESUME 24
+#define EXIT_REASON_VMWRITE 25
+#define EXIT_REASON_VMOFF 26
+#define EXIT_REASON_VMON 27
+#define EXIT_REASON_CR_ACCESS 28
+#define EXIT_REASON_DR_ACCESS 29
+#define EXIT_REASON_IO_INSTRUCTION 30
+#define EXIT_REASON_MSR_READ 31
+#define EXIT_REASON_MSR_WRITE 32
+#define EXIT_REASON_INVALID_STATE 33
+#define EXIT_REASON_MWAIT_INSTRUCTION 36
+#define EXIT_REASON_MONITOR_INSTRUCTION 39
+#define EXIT_REASON_PAUSE_INSTRUCTION 40
+#define EXIT_REASON_MCE_DURING_VMENTRY 41
+#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
+#define EXIT_REASON_APIC_ACCESS 44
+#define EXIT_REASON_EOI_INDUCED 45
+#define EXIT_REASON_EPT_VIOLATION 48
+#define EXIT_REASON_EPT_MISCONFIG 49
+#define EXIT_REASON_INVEPT 50
+#define EXIT_REASON_RDTSCP 51
+#define EXIT_REASON_PREEMPTION_TIMER 52
+#define EXIT_REASON_INVVPID 53
+#define EXIT_REASON_WBINVD 54
+#define EXIT_REASON_XSETBV 55
+#define EXIT_REASON_APIC_WRITE 56
+#define EXIT_REASON_INVPCID 58
+#define EXIT_REASON_PML_FULL 62
+#define EXIT_REASON_XSAVES 63
+#define EXIT_REASON_XRSTORS 64
+#define LAST_EXIT_REASON 64
+
+enum vmcs_field {
+ VIRTUAL_PROCESSOR_ID = 0x00000000,
+ POSTED_INTR_NV = 0x00000002,
+ GUEST_ES_SELECTOR = 0x00000800,
+ GUEST_CS_SELECTOR = 0x00000802,
+ GUEST_SS_SELECTOR = 0x00000804,
+ GUEST_DS_SELECTOR = 0x00000806,
+ GUEST_FS_SELECTOR = 0x00000808,
+ GUEST_GS_SELECTOR = 0x0000080a,
+ GUEST_LDTR_SELECTOR = 0x0000080c,
+ GUEST_TR_SELECTOR = 0x0000080e,
+ GUEST_INTR_STATUS = 0x00000810,
+ GUEST_PML_INDEX = 0x00000812,
+ HOST_ES_SELECTOR = 0x00000c00,
+ HOST_CS_SELECTOR = 0x00000c02,
+ HOST_SS_SELECTOR = 0x00000c04,
+ HOST_DS_SELECTOR = 0x00000c06,
+ HOST_FS_SELECTOR = 0x00000c08,
+ HOST_GS_SELECTOR = 0x00000c0a,
+ HOST_TR_SELECTOR = 0x00000c0c,
+ IO_BITMAP_A = 0x00002000,
+ IO_BITMAP_A_HIGH = 0x00002001,
+ IO_BITMAP_B = 0x00002002,
+ IO_BITMAP_B_HIGH = 0x00002003,
+ MSR_BITMAP = 0x00002004,
+ MSR_BITMAP_HIGH = 0x00002005,
+ VM_EXIT_MSR_STORE_ADDR = 0x00002006,
+ VM_EXIT_MSR_STORE_ADDR_HIGH = 0x00002007,
+ VM_EXIT_MSR_LOAD_ADDR = 0x00002008,
+ VM_EXIT_MSR_LOAD_ADDR_HIGH = 0x00002009,
+ VM_ENTRY_MSR_LOAD_ADDR = 0x0000200a,
+ VM_ENTRY_MSR_LOAD_ADDR_HIGH = 0x0000200b,
+ PML_ADDRESS = 0x0000200e,
+ PML_ADDRESS_HIGH = 0x0000200f,
+ TSC_OFFSET = 0x00002010,
+ TSC_OFFSET_HIGH = 0x00002011,
+ VIRTUAL_APIC_PAGE_ADDR = 0x00002012,
+ VIRTUAL_APIC_PAGE_ADDR_HIGH = 0x00002013,
+ APIC_ACCESS_ADDR = 0x00002014,
+ APIC_ACCESS_ADDR_HIGH = 0x00002015,
+ POSTED_INTR_DESC_ADDR = 0x00002016,
+ POSTED_INTR_DESC_ADDR_HIGH = 0x00002017,
+ EPT_POINTER = 0x0000201a,
+ EPT_POINTER_HIGH = 0x0000201b,
+ EOI_EXIT_BITMAP0 = 0x0000201c,
+ EOI_EXIT_BITMAP0_HIGH = 0x0000201d,
+ EOI_EXIT_BITMAP1 = 0x0000201e,
+ EOI_EXIT_BITMAP1_HIGH = 0x0000201f,
+ EOI_EXIT_BITMAP2 = 0x00002020,
+ EOI_EXIT_BITMAP2_HIGH = 0x00002021,
+ EOI_EXIT_BITMAP3 = 0x00002022,
+ EOI_EXIT_BITMAP3_HIGH = 0x00002023,
+ VMREAD_BITMAP = 0x00002026,
+ VMREAD_BITMAP_HIGH = 0x00002027,
+ VMWRITE_BITMAP = 0x00002028,
+ VMWRITE_BITMAP_HIGH = 0x00002029,
+ XSS_EXIT_BITMAP = 0x0000202C,
+ XSS_EXIT_BITMAP_HIGH = 0x0000202D,
+ TSC_MULTIPLIER = 0x00002032,
+ TSC_MULTIPLIER_HIGH = 0x00002033,
+ GUEST_PHYSICAL_ADDRESS = 0x00002400,
+ GUEST_PHYSICAL_ADDRESS_HIGH = 0x00002401,
+ VMCS_LINK_POINTER = 0x00002800,
+ VMCS_LINK_POINTER_HIGH = 0x00002801,
+ GUEST_IA32_DEBUGCTL = 0x00002802,
+ GUEST_IA32_DEBUGCTL_HIGH = 0x00002803,
+ GUEST_IA32_PAT = 0x00002804,
+ GUEST_IA32_PAT_HIGH = 0x00002805,
+ GUEST_IA32_EFER = 0x00002806,
+ GUEST_IA32_EFER_HIGH = 0x00002807,
+ GUEST_IA32_PERF_GLOBAL_CTRL = 0x00002808,
+ GUEST_IA32_PERF_GLOBAL_CTRL_HIGH= 0x00002809,
+ GUEST_PDPTR0 = 0x0000280a,
+ GUEST_PDPTR0_HIGH = 0x0000280b,
+ GUEST_PDPTR1 = 0x0000280c,
+ GUEST_PDPTR1_HIGH = 0x0000280d,
+ GUEST_PDPTR2 = 0x0000280e,
+ GUEST_PDPTR2_HIGH = 0x0000280f,
+ GUEST_PDPTR3 = 0x00002810,
+ GUEST_PDPTR3_HIGH = 0x00002811,
+ GUEST_BNDCFGS = 0x00002812,
+ GUEST_BNDCFGS_HIGH = 0x00002813,
+ HOST_IA32_PAT = 0x00002c00,
+ HOST_IA32_PAT_HIGH = 0x00002c01,
+ HOST_IA32_EFER = 0x00002c02,
+ HOST_IA32_EFER_HIGH = 0x00002c03,
+ HOST_IA32_PERF_GLOBAL_CTRL = 0x00002c04,
+ HOST_IA32_PERF_GLOBAL_CTRL_HIGH = 0x00002c05,
+ PIN_BASED_VM_EXEC_CONTROL = 0x00004000,
+ CPU_BASED_VM_EXEC_CONTROL = 0x00004002,
+ EXCEPTION_BITMAP = 0x00004004,
+ PAGE_FAULT_ERROR_CODE_MASK = 0x00004006,
+ PAGE_FAULT_ERROR_CODE_MATCH = 0x00004008,
+ CR3_TARGET_COUNT = 0x0000400a,
+ VM_EXIT_CONTROLS = 0x0000400c,
+ VM_EXIT_MSR_STORE_COUNT = 0x0000400e,
+ VM_EXIT_MSR_LOAD_COUNT = 0x00004010,
+ VM_ENTRY_CONTROLS = 0x00004012,
+ VM_ENTRY_MSR_LOAD_COUNT = 0x00004014,
+ VM_ENTRY_INTR_INFO_FIELD = 0x00004016,
+ VM_ENTRY_EXCEPTION_ERROR_CODE = 0x00004018,
+ VM_ENTRY_INSTRUCTION_LEN = 0x0000401a,
+ TPR_THRESHOLD = 0x0000401c,
+ SECONDARY_VM_EXEC_CONTROL = 0x0000401e,
+ PLE_GAP = 0x00004020,
+ PLE_WINDOW = 0x00004022,
+ VM_INSTRUCTION_ERROR = 0x00004400,
+ VM_EXIT_REASON = 0x00004402,
+ VM_EXIT_INTR_INFO = 0x00004404,
+ VM_EXIT_INTR_ERROR_CODE = 0x00004406,
+ IDT_VECTORING_INFO_FIELD = 0x00004408,
+ IDT_VECTORING_ERROR_CODE = 0x0000440a,
+ VM_EXIT_INSTRUCTION_LEN = 0x0000440c,
+ VMX_INSTRUCTION_INFO = 0x0000440e,
+ GUEST_ES_LIMIT = 0x00004800,
+ GUEST_CS_LIMIT = 0x00004802,
+ GUEST_SS_LIMIT = 0x00004804,
+ GUEST_DS_LIMIT = 0x00004806,
+ GUEST_FS_LIMIT = 0x00004808,
+ GUEST_GS_LIMIT = 0x0000480a,
+ GUEST_LDTR_LIMIT = 0x0000480c,
+ GUEST_TR_LIMIT = 0x0000480e,
+ GUEST_GDTR_LIMIT = 0x00004810,
+ GUEST_IDTR_LIMIT = 0x00004812,
+ GUEST_ES_AR_BYTES = 0x00004814,
+ GUEST_CS_AR_BYTES = 0x00004816,
+ GUEST_SS_AR_BYTES = 0x00004818,
+ GUEST_DS_AR_BYTES = 0x0000481a,
+ GUEST_FS_AR_BYTES = 0x0000481c,
+ GUEST_GS_AR_BYTES = 0x0000481e,
+ GUEST_LDTR_AR_BYTES = 0x00004820,
+ GUEST_TR_AR_BYTES = 0x00004822,
+ GUEST_INTERRUPTIBILITY_INFO = 0x00004824,
+ GUEST_ACTIVITY_STATE = 0X00004826,
+ GUEST_SYSENTER_CS = 0x0000482A,
+ VMX_PREEMPTION_TIMER_VALUE = 0x0000482E,
+ HOST_IA32_SYSENTER_CS = 0x00004c00,
+ CR0_GUEST_HOST_MASK = 0x00006000,
+ CR4_GUEST_HOST_MASK = 0x00006002,
+ CR0_READ_SHADOW = 0x00006004,
+ CR4_READ_SHADOW = 0x00006006,
+ CR3_TARGET_VALUE0 = 0x00006008,
+ CR3_TARGET_VALUE1 = 0x0000600a,
+ CR3_TARGET_VALUE2 = 0x0000600c,
+ CR3_TARGET_VALUE3 = 0x0000600e,
+ EXIT_QUALIFICATION = 0x00006400,
+ GUEST_LINEAR_ADDRESS = 0x0000640a,
+ GUEST_CR0 = 0x00006800,
+ GUEST_CR3 = 0x00006802,
+ GUEST_CR4 = 0x00006804,
+ GUEST_ES_BASE = 0x00006806,
+ GUEST_CS_BASE = 0x00006808,
+ GUEST_SS_BASE = 0x0000680a,
+ GUEST_DS_BASE = 0x0000680c,
+ GUEST_FS_BASE = 0x0000680e,
+ GUEST_GS_BASE = 0x00006810,
+ GUEST_LDTR_BASE = 0x00006812,
+ GUEST_TR_BASE = 0x00006814,
+ GUEST_GDTR_BASE = 0x00006816,
+ GUEST_IDTR_BASE = 0x00006818,
+ GUEST_DR7 = 0x0000681a,
+ GUEST_RSP = 0x0000681c,
+ GUEST_RIP = 0x0000681e,
+ GUEST_RFLAGS = 0x00006820,
+ GUEST_PENDING_DBG_EXCEPTIONS = 0x00006822,
+ GUEST_SYSENTER_ESP = 0x00006824,
+ GUEST_SYSENTER_EIP = 0x00006826,
+ HOST_CR0 = 0x00006c00,
+ HOST_CR3 = 0x00006c02,
+ HOST_CR4 = 0x00006c04,
+ HOST_FS_BASE = 0x00006c06,
+ HOST_GS_BASE = 0x00006c08,
+ HOST_TR_BASE = 0x00006c0a,
+ HOST_GDTR_BASE = 0x00006c0c,
+ HOST_IDTR_BASE = 0x00006c0e,
+ HOST_IA32_SYSENTER_ESP = 0x00006c10,
+ HOST_IA32_SYSENTER_EIP = 0x00006c12,
+ HOST_RSP = 0x00006c14,
+ HOST_RIP = 0x00006c16,
+};
+
+struct vmx_msr_entry {
+ uint32_t index;
+ uint32_t reserved;
+ uint64_t value;
+} __attribute__ ((aligned(16)));
+
+static inline int vmxon(uint64_t phys)
+{
+ uint8_t ret;
+
+ __asm__ __volatile__ ("vmxon %[pa]; setna %[ret]"
+ : [ret]"=rm"(ret)
+ : [pa]"m"(phys)
+ : "cc", "memory");
+
+ return ret;
+}
+
+static inline void vmxoff(void)
+{
+ __asm__ __volatile__("vmxoff");
+}
+
+static inline int vmclear(uint64_t vmcs_pa)
+{
+ uint8_t ret;
+
+ __asm__ __volatile__ ("vmclear %[pa]; setna %[ret]"
+ : [ret]"=rm"(ret)
+ : [pa]"m"(vmcs_pa)
+ : "cc", "memory");
+
+ return ret;
+}
+
+static inline int vmptrld(uint64_t vmcs_pa)
+{
+ uint8_t ret;
+
+ __asm__ __volatile__ ("vmptrld %[pa]; setna %[ret]"
+ : [ret]"=rm"(ret)
+ : [pa]"m"(vmcs_pa)
+ : "cc", "memory");
+
+ return ret;
+}
+
+/*
+ * No guest state (e.g. GPRs) is established by this vmlaunch.
+ */
+static inline int vmlaunch(void)
+{
+ int ret;
+
+ __asm__ __volatile__("push %%rbp;"
+ "push %%rcx;"
+ "push %%rdx;"
+ "push %%rsi;"
+ "push %%rdi;"
+ "push $0;"
+ "vmwrite %%rsp, %[host_rsp];"
+ "lea 1f(%%rip), %%rax;"
+ "vmwrite %%rax, %[host_rip];"
+ "vmlaunch;"
+ "incq (%%rsp);"
+ "1: pop %%rax;"
+ "pop %%rdi;"
+ "pop %%rsi;"
+ "pop %%rdx;"
+ "pop %%rcx;"
+ "pop %%rbp;"
+ : [ret]"=&a"(ret)
+ : [host_rsp]"r"((uint64_t)HOST_RSP),
+ [host_rip]"r"((uint64_t)HOST_RIP)
+ : "memory", "cc", "rbx", "r8", "r9", "r10",
+ "r11", "r12", "r13", "r14", "r15");
+ return ret;
+}
+
+/*
+ * No guest state (e.g. GPRs) is established by this vmresume.
+ */
+static inline int vmresume(void)
+{
+ int ret;
+
+ __asm__ __volatile__("push %%rbp;"
+ "push %%rcx;"
+ "push %%rdx;"
+ "push %%rsi;"
+ "push %%rdi;"
+ "push $0;"
+ "vmwrite %%rsp, %[host_rsp];"
+ "lea 1f(%%rip), %%rax;"
+ "vmwrite %%rax, %[host_rip];"
+ "vmresume;"
+ "incq (%%rsp);"
+ "1: pop %%rax;"
+ "pop %%rdi;"
+ "pop %%rsi;"
+ "pop %%rdx;"
+ "pop %%rcx;"
+ "pop %%rbp;"
+ : [ret]"=&a"(ret)
+ : [host_rsp]"r"((uint64_t)HOST_RSP),
+ [host_rip]"r"((uint64_t)HOST_RIP)
+ : "memory", "cc", "rbx", "r8", "r9", "r10",
+ "r11", "r12", "r13", "r14", "r15");
+ return ret;
+}
+
+static inline int vmread(uint64_t encoding, uint64_t *value)
+{
+ uint64_t tmp;
+ uint8_t ret;
+
+ __asm__ __volatile__("vmread %[encoding], %[value]; setna %[ret]"
+ : [value]"=rm"(tmp), [ret]"=rm"(ret)
+ : [encoding]"r"(encoding)
+ : "cc", "memory");
+
+ *value = tmp;
+ return ret;
+}
+
+/*
+ * A wrapper around vmread that ignores errors and returns zero if the
+ * vmread instruction fails.
+ */
+static inline uint64_t vmreadz(uint64_t encoding)
+{
+ uint64_t value = 0;
+ vmread(encoding, &value);
+ return value;
+}
+
+static inline int vmwrite(uint64_t encoding, uint64_t value)
+{
+ uint8_t ret;
+
+ __asm__ __volatile__ ("vmwrite %[value], %[encoding]; setna %[ret]"
+ : [ret]"=rm"(ret)
+ : [value]"rm"(value), [encoding]"r"(encoding)
+ : "cc", "memory");
+
+ return ret;
+}
+
+static inline uint32_t vmcs_revision(void)
+{
+ return rdmsr(MSR_IA32_VMX_BASIC);
+}
+
+void prepare_for_vmx_operation(void);
+void prepare_vmcs(void *guest_rip, void *guest_rsp);
+struct kvm_vm *vm_create_default_vmx(uint32_t vcpuid,
+ vmx_guest_code_t guest_code);
+
+#endif /* !SELFTEST_KVM_VMX_H */
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 7ca1bb4..2cedfda 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -378,7 +378,7 @@
* complicated. This function uses a reasonable default length for
* the array and performs the appropriate allocation.
*/
-struct kvm_cpuid2 *allocate_kvm_cpuid2(void)
+static struct kvm_cpuid2 *allocate_kvm_cpuid2(void)
{
struct kvm_cpuid2 *cpuid;
int nent = 100;
@@ -402,17 +402,21 @@
* Input Args: None
*
* Output Args:
- * cpuid - The supported KVM CPUID
*
- * Return: void
+ * Return: The supported KVM CPUID
*
* Get the guest CPUID supported by KVM.
*/
-void kvm_get_supported_cpuid(struct kvm_cpuid2 *cpuid)
+struct kvm_cpuid2 *kvm_get_supported_cpuid(void)
{
+ static struct kvm_cpuid2 *cpuid;
int ret;
int kvm_fd;
+ if (cpuid)
+ return cpuid;
+
+ cpuid = allocate_kvm_cpuid2();
kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
TEST_ASSERT(kvm_fd >= 0, "open %s failed, rc: %i errno: %i",
KVM_DEV_PATH, kvm_fd, errno);
@@ -422,6 +426,7 @@
ret, errno);
close(kvm_fd);
+ return cpuid;
}
/* Locate a cpuid entry.
@@ -435,12 +440,13 @@
* Return: A pointer to the cpuid entry. Never returns NULL.
*/
struct kvm_cpuid_entry2 *
-find_cpuid_index_entry(struct kvm_cpuid2 *cpuid, uint32_t function,
- uint32_t index)
+kvm_get_supported_cpuid_index(uint32_t function, uint32_t index)
{
+ struct kvm_cpuid2 *cpuid;
struct kvm_cpuid_entry2 *entry = NULL;
int i;
+ cpuid = kvm_get_supported_cpuid();
for (i = 0; i < cpuid->nent; i++) {
if (cpuid->entries[i].function == function &&
cpuid->entries[i].index == index) {
@@ -1435,7 +1441,7 @@
sparsebit_idx_t pg;
TEST_ASSERT((paddr_min % vm->page_size) == 0, "Min physical address "
- "not divisable by page size.\n"
+ "not divisible by page size.\n"
" paddr_min: 0x%lx page_size: 0x%x",
paddr_min, vm->page_size);
diff --git a/tools/testing/selftests/kvm/lib/sparsebit.c b/tools/testing/selftests/kvm/lib/sparsebit.c
index 0c5cf3e..b132bc9 100644
--- a/tools/testing/selftests/kvm/lib/sparsebit.c
+++ b/tools/testing/selftests/kvm/lib/sparsebit.c
@@ -121,7 +121,7 @@
* avoided by moving the setting of the nodes mask bits into
* the previous nodes num_after setting.
*
- * + Node starting index is evenly divisable by the number of bits
+ * + Node starting index is evenly divisible by the number of bits
* within a nodes mask member.
*
* + Nodes never represent a range of bits that wrap around the
@@ -1741,7 +1741,7 @@
/* Validate node index is divisible by the mask size */
if (nodep->idx % MASK_BITS) {
- fprintf(stderr, "Node index not divisable by "
+ fprintf(stderr, "Node index not divisible by "
"mask size,\n"
" nodep: %p nodep->idx: 0x%lx "
"MASK_BITS: %lu\n",
diff --git a/tools/testing/selftests/kvm/lib/vmx.c b/tools/testing/selftests/kvm/lib/vmx.c
new file mode 100644
index 0000000..0231bc0
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/vmx.c
@@ -0,0 +1,243 @@
+/*
+ * tools/testing/selftests/kvm/lib/x86.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "x86.h"
+#include "vmx.h"
+
+/* Create a default VM for VMX tests.
+ *
+ * Input Args:
+ * vcpuid - The id of the single VCPU to add to the VM.
+ * guest_code - The vCPU's entry point
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Pointer to opaque structure that describes the created VM.
+ */
+struct kvm_vm *
+vm_create_default_vmx(uint32_t vcpuid, vmx_guest_code_t guest_code)
+{
+ struct kvm_cpuid2 *cpuid;
+ struct kvm_vm *vm;
+ vm_vaddr_t vmxon_vaddr;
+ vm_paddr_t vmxon_paddr;
+ vm_vaddr_t vmcs_vaddr;
+ vm_paddr_t vmcs_paddr;
+
+ vm = vm_create_default(vcpuid, (void *) guest_code);
+
+ /* Enable nesting in CPUID */
+ vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid());
+
+ /* Setup of a region of guest memory for the vmxon region. */
+ vmxon_vaddr = vm_vaddr_alloc(vm, getpagesize(), 0, 0, 0);
+ vmxon_paddr = addr_gva2gpa(vm, vmxon_vaddr);
+
+ /* Setup of a region of guest memory for a vmcs. */
+ vmcs_vaddr = vm_vaddr_alloc(vm, getpagesize(), 0, 0, 0);
+ vmcs_paddr = addr_gva2gpa(vm, vmcs_vaddr);
+
+ vcpu_args_set(vm, vcpuid, 4, vmxon_vaddr, vmxon_paddr, vmcs_vaddr,
+ vmcs_paddr);
+
+ return vm;
+}
+
+void prepare_for_vmx_operation(void)
+{
+ uint64_t feature_control;
+ uint64_t required;
+ unsigned long cr0;
+ unsigned long cr4;
+
+ /*
+ * Ensure bits in CR0 and CR4 are valid in VMX operation:
+ * - Bit X is 1 in _FIXED0: bit X is fixed to 1 in CRx.
+ * - Bit X is 0 in _FIXED1: bit X is fixed to 0 in CRx.
+ */
+ __asm__ __volatile__("mov %%cr0, %0" : "=r"(cr0) : : "memory");
+ cr0 &= rdmsr(MSR_IA32_VMX_CR0_FIXED1);
+ cr0 |= rdmsr(MSR_IA32_VMX_CR0_FIXED0);
+ __asm__ __volatile__("mov %0, %%cr0" : : "r"(cr0) : "memory");
+
+ __asm__ __volatile__("mov %%cr4, %0" : "=r"(cr4) : : "memory");
+ cr4 &= rdmsr(MSR_IA32_VMX_CR4_FIXED1);
+ cr4 |= rdmsr(MSR_IA32_VMX_CR4_FIXED0);
+ /* Enable VMX operation */
+ cr4 |= X86_CR4_VMXE;
+ __asm__ __volatile__("mov %0, %%cr4" : : "r"(cr4) : "memory");
+
+ /*
+ * Configure IA32_FEATURE_CONTROL MSR to allow VMXON:
+ * Bit 0: Lock bit. If clear, VMXON causes a #GP.
+ * Bit 2: Enables VMXON outside of SMX operation. If clear, VMXON
+ * outside of SMX causes a #GP.
+ */
+ required = FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+ required |= FEATURE_CONTROL_LOCKED;
+ feature_control = rdmsr(MSR_IA32_FEATURE_CONTROL);
+ if ((feature_control & required) != required)
+ wrmsr(MSR_IA32_FEATURE_CONTROL, feature_control | required);
+}
+
+/*
+ * Initialize the control fields to the most basic settings possible.
+ */
+static inline void init_vmcs_control_fields(void)
+{
+ vmwrite(VIRTUAL_PROCESSOR_ID, 0);
+ vmwrite(POSTED_INTR_NV, 0);
+
+ vmwrite(PIN_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_PINBASED_CTLS));
+ vmwrite(CPU_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_PROCBASED_CTLS));
+ vmwrite(EXCEPTION_BITMAP, 0);
+ vmwrite(PAGE_FAULT_ERROR_CODE_MASK, 0);
+ vmwrite(PAGE_FAULT_ERROR_CODE_MATCH, -1); /* Never match */
+ vmwrite(CR3_TARGET_COUNT, 0);
+ vmwrite(VM_EXIT_CONTROLS, rdmsr(MSR_IA32_VMX_EXIT_CTLS) |
+ VM_EXIT_HOST_ADDR_SPACE_SIZE); /* 64-bit host */
+ vmwrite(VM_EXIT_MSR_STORE_COUNT, 0);
+ vmwrite(VM_EXIT_MSR_LOAD_COUNT, 0);
+ vmwrite(VM_ENTRY_CONTROLS, rdmsr(MSR_IA32_VMX_ENTRY_CTLS) |
+ VM_ENTRY_IA32E_MODE); /* 64-bit guest */
+ vmwrite(VM_ENTRY_MSR_LOAD_COUNT, 0);
+ vmwrite(VM_ENTRY_INTR_INFO_FIELD, 0);
+ vmwrite(TPR_THRESHOLD, 0);
+ vmwrite(SECONDARY_VM_EXEC_CONTROL, 0);
+
+ vmwrite(CR0_GUEST_HOST_MASK, 0);
+ vmwrite(CR4_GUEST_HOST_MASK, 0);
+ vmwrite(CR0_READ_SHADOW, get_cr0());
+ vmwrite(CR4_READ_SHADOW, get_cr4());
+}
+
+/*
+ * Initialize the host state fields based on the current host state, with
+ * the exception of HOST_RSP and HOST_RIP, which should be set by vmlaunch
+ * or vmresume.
+ */
+static inline void init_vmcs_host_state(void)
+{
+ uint32_t exit_controls = vmreadz(VM_EXIT_CONTROLS);
+
+ vmwrite(HOST_ES_SELECTOR, get_es());
+ vmwrite(HOST_CS_SELECTOR, get_cs());
+ vmwrite(HOST_SS_SELECTOR, get_ss());
+ vmwrite(HOST_DS_SELECTOR, get_ds());
+ vmwrite(HOST_FS_SELECTOR, get_fs());
+ vmwrite(HOST_GS_SELECTOR, get_gs());
+ vmwrite(HOST_TR_SELECTOR, get_tr());
+
+ if (exit_controls & VM_EXIT_LOAD_IA32_PAT)
+ vmwrite(HOST_IA32_PAT, rdmsr(MSR_IA32_CR_PAT));
+ if (exit_controls & VM_EXIT_LOAD_IA32_EFER)
+ vmwrite(HOST_IA32_EFER, rdmsr(MSR_EFER));
+ if (exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
+ vmwrite(HOST_IA32_PERF_GLOBAL_CTRL,
+ rdmsr(MSR_CORE_PERF_GLOBAL_CTRL));
+
+ vmwrite(HOST_IA32_SYSENTER_CS, rdmsr(MSR_IA32_SYSENTER_CS));
+
+ vmwrite(HOST_CR0, get_cr0());
+ vmwrite(HOST_CR3, get_cr3());
+ vmwrite(HOST_CR4, get_cr4());
+ vmwrite(HOST_FS_BASE, rdmsr(MSR_FS_BASE));
+ vmwrite(HOST_GS_BASE, rdmsr(MSR_GS_BASE));
+ vmwrite(HOST_TR_BASE,
+ get_desc64_base((struct desc64 *)(get_gdt_base() + get_tr())));
+ vmwrite(HOST_GDTR_BASE, get_gdt_base());
+ vmwrite(HOST_IDTR_BASE, get_idt_base());
+ vmwrite(HOST_IA32_SYSENTER_ESP, rdmsr(MSR_IA32_SYSENTER_ESP));
+ vmwrite(HOST_IA32_SYSENTER_EIP, rdmsr(MSR_IA32_SYSENTER_EIP));
+}
+
+/*
+ * Initialize the guest state fields essentially as a clone of
+ * the host state fields. Some host state fields have fixed
+ * values, and we set the corresponding guest state fields accordingly.
+ */
+static inline void init_vmcs_guest_state(void *rip, void *rsp)
+{
+ vmwrite(GUEST_ES_SELECTOR, vmreadz(HOST_ES_SELECTOR));
+ vmwrite(GUEST_CS_SELECTOR, vmreadz(HOST_CS_SELECTOR));
+ vmwrite(GUEST_SS_SELECTOR, vmreadz(HOST_SS_SELECTOR));
+ vmwrite(GUEST_DS_SELECTOR, vmreadz(HOST_DS_SELECTOR));
+ vmwrite(GUEST_FS_SELECTOR, vmreadz(HOST_FS_SELECTOR));
+ vmwrite(GUEST_GS_SELECTOR, vmreadz(HOST_GS_SELECTOR));
+ vmwrite(GUEST_LDTR_SELECTOR, 0);
+ vmwrite(GUEST_TR_SELECTOR, vmreadz(HOST_TR_SELECTOR));
+ vmwrite(GUEST_INTR_STATUS, 0);
+ vmwrite(GUEST_PML_INDEX, 0);
+
+ vmwrite(VMCS_LINK_POINTER, -1ll);
+ vmwrite(GUEST_IA32_DEBUGCTL, 0);
+ vmwrite(GUEST_IA32_PAT, vmreadz(HOST_IA32_PAT));
+ vmwrite(GUEST_IA32_EFER, vmreadz(HOST_IA32_EFER));
+ vmwrite(GUEST_IA32_PERF_GLOBAL_CTRL,
+ vmreadz(HOST_IA32_PERF_GLOBAL_CTRL));
+
+ vmwrite(GUEST_ES_LIMIT, -1);
+ vmwrite(GUEST_CS_LIMIT, -1);
+ vmwrite(GUEST_SS_LIMIT, -1);
+ vmwrite(GUEST_DS_LIMIT, -1);
+ vmwrite(GUEST_FS_LIMIT, -1);
+ vmwrite(GUEST_GS_LIMIT, -1);
+ vmwrite(GUEST_LDTR_LIMIT, -1);
+ vmwrite(GUEST_TR_LIMIT, 0x67);
+ vmwrite(GUEST_GDTR_LIMIT, 0xffff);
+ vmwrite(GUEST_IDTR_LIMIT, 0xffff);
+ vmwrite(GUEST_ES_AR_BYTES,
+ vmreadz(GUEST_ES_SELECTOR) == 0 ? 0x10000 : 0xc093);
+ vmwrite(GUEST_CS_AR_BYTES, 0xa09b);
+ vmwrite(GUEST_SS_AR_BYTES, 0xc093);
+ vmwrite(GUEST_DS_AR_BYTES,
+ vmreadz(GUEST_DS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+ vmwrite(GUEST_FS_AR_BYTES,
+ vmreadz(GUEST_FS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+ vmwrite(GUEST_GS_AR_BYTES,
+ vmreadz(GUEST_GS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+ vmwrite(GUEST_LDTR_AR_BYTES, 0x10000);
+ vmwrite(GUEST_TR_AR_BYTES, 0x8b);
+ vmwrite(GUEST_INTERRUPTIBILITY_INFO, 0);
+ vmwrite(GUEST_ACTIVITY_STATE, 0);
+ vmwrite(GUEST_SYSENTER_CS, vmreadz(HOST_IA32_SYSENTER_CS));
+ vmwrite(VMX_PREEMPTION_TIMER_VALUE, 0);
+
+ vmwrite(GUEST_CR0, vmreadz(HOST_CR0));
+ vmwrite(GUEST_CR3, vmreadz(HOST_CR3));
+ vmwrite(GUEST_CR4, vmreadz(HOST_CR4));
+ vmwrite(GUEST_ES_BASE, 0);
+ vmwrite(GUEST_CS_BASE, 0);
+ vmwrite(GUEST_SS_BASE, 0);
+ vmwrite(GUEST_DS_BASE, 0);
+ vmwrite(GUEST_FS_BASE, vmreadz(HOST_FS_BASE));
+ vmwrite(GUEST_GS_BASE, vmreadz(HOST_GS_BASE));
+ vmwrite(GUEST_LDTR_BASE, 0);
+ vmwrite(GUEST_TR_BASE, vmreadz(HOST_TR_BASE));
+ vmwrite(GUEST_GDTR_BASE, vmreadz(HOST_GDTR_BASE));
+ vmwrite(GUEST_IDTR_BASE, vmreadz(HOST_IDTR_BASE));
+ vmwrite(GUEST_DR7, 0x400);
+ vmwrite(GUEST_RSP, (uint64_t)rsp);
+ vmwrite(GUEST_RIP, (uint64_t)rip);
+ vmwrite(GUEST_RFLAGS, 2);
+ vmwrite(GUEST_PENDING_DBG_EXCEPTIONS, 0);
+ vmwrite(GUEST_SYSENTER_ESP, vmreadz(HOST_IA32_SYSENTER_ESP));
+ vmwrite(GUEST_SYSENTER_EIP, vmreadz(HOST_IA32_SYSENTER_EIP));
+}
+
+void prepare_vmcs(void *guest_rip, void *guest_rsp)
+{
+ init_vmcs_control_fields();
+ init_vmcs_host_state();
+ init_vmcs_guest_state(guest_rip, guest_rsp);
+}
diff --git a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
new file mode 100644
index 0000000..8f7f620
--- /dev/null
+++ b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
@@ -0,0 +1,231 @@
+/*
+ * gtests/tests/vmx_tsc_adjust_test.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ *
+ * IA32_TSC_ADJUST test
+ *
+ * According to the SDM, "if an execution of WRMSR to the
+ * IA32_TIME_STAMP_COUNTER MSR adds (or subtracts) value X from the TSC,
+ * the logical processor also adds (or subtracts) value X from the
+ * IA32_TSC_ADJUST MSR.
+ *
+ * Note that when L1 doesn't intercept writes to IA32_TSC, a
+ * WRMSR(IA32_TSC) from L2 sets L1's TSC value, not L2's perceived TSC
+ * value.
+ *
+ * This test verifies that this unusual case is handled correctly.
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "x86.h"
+#include "vmx.h"
+
+#include <string.h>
+#include <sys/ioctl.h>
+
+#ifndef MSR_IA32_TSC_ADJUST
+#define MSR_IA32_TSC_ADJUST 0x3b
+#endif
+
+#define PAGE_SIZE 4096
+#define VCPU_ID 5
+
+#define TSC_ADJUST_VALUE (1ll << 32)
+#define TSC_OFFSET_VALUE -(1ll << 48)
+
+enum {
+ PORT_ABORT = 0x1000,
+ PORT_REPORT,
+ PORT_DONE,
+};
+
+struct vmx_page {
+ vm_vaddr_t virt;
+ vm_paddr_t phys;
+};
+
+enum {
+ VMXON_PAGE = 0,
+ VMCS_PAGE,
+ MSR_BITMAP_PAGE,
+
+ NUM_VMX_PAGES,
+};
+
+struct kvm_single_msr {
+ struct kvm_msrs header;
+ struct kvm_msr_entry entry;
+} __attribute__((packed));
+
+/* The virtual machine object. */
+static struct kvm_vm *vm;
+
+/* Array of vmx_page descriptors that is shared with the guest. */
+struct vmx_page *vmx_pages;
+
+#define exit_to_l0(_port, _arg) do_exit_to_l0(_port, (unsigned long) (_arg))
+static void do_exit_to_l0(uint16_t port, unsigned long arg)
+{
+ __asm__ __volatile__("in %[port], %%al"
+ :
+ : [port]"d"(port), "D"(arg)
+ : "rax");
+}
+
+
+#define GUEST_ASSERT(_condition) do { \
+ if (!(_condition)) \
+ exit_to_l0(PORT_ABORT, "Failed guest assert: " #_condition); \
+} while (0)
+
+static void check_ia32_tsc_adjust(int64_t max)
+{
+ int64_t adjust;
+
+ adjust = rdmsr(MSR_IA32_TSC_ADJUST);
+ exit_to_l0(PORT_REPORT, adjust);
+ GUEST_ASSERT(adjust <= max);
+}
+
+static void l2_guest_code(void)
+{
+ uint64_t l1_tsc = rdtsc() - TSC_OFFSET_VALUE;
+
+ wrmsr(MSR_IA32_TSC, l1_tsc - TSC_ADJUST_VALUE);
+ check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
+
+ /* Exit to L1 */
+ __asm__ __volatile__("vmcall");
+}
+
+static void l1_guest_code(struct vmx_page *vmx_pages)
+{
+#define L2_GUEST_STACK_SIZE 64
+ unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+ uint32_t control;
+ uintptr_t save_cr3;
+
+ GUEST_ASSERT(rdtsc() < TSC_ADJUST_VALUE);
+ wrmsr(MSR_IA32_TSC, rdtsc() - TSC_ADJUST_VALUE);
+ check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
+
+ prepare_for_vmx_operation();
+
+ /* Enter VMX root operation. */
+ *(uint32_t *)vmx_pages[VMXON_PAGE].virt = vmcs_revision();
+ GUEST_ASSERT(!vmxon(vmx_pages[VMXON_PAGE].phys));
+
+ /* Load a VMCS. */
+ *(uint32_t *)vmx_pages[VMCS_PAGE].virt = vmcs_revision();
+ GUEST_ASSERT(!vmclear(vmx_pages[VMCS_PAGE].phys));
+ GUEST_ASSERT(!vmptrld(vmx_pages[VMCS_PAGE].phys));
+
+ /* Prepare the VMCS for L2 execution. */
+ prepare_vmcs(l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+ control = vmreadz(CPU_BASED_VM_EXEC_CONTROL);
+ control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETING;
+ vmwrite(CPU_BASED_VM_EXEC_CONTROL, control);
+ vmwrite(MSR_BITMAP, vmx_pages[MSR_BITMAP_PAGE].phys);
+ vmwrite(TSC_OFFSET, TSC_OFFSET_VALUE);
+
+ /* Jump into L2. First, test failure to load guest CR3. */
+ save_cr3 = vmreadz(GUEST_CR3);
+ vmwrite(GUEST_CR3, -1ull);
+ GUEST_ASSERT(!vmlaunch());
+ GUEST_ASSERT(vmreadz(VM_EXIT_REASON) ==
+ (EXIT_REASON_FAILED_VMENTRY | EXIT_REASON_INVALID_STATE));
+ check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
+ vmwrite(GUEST_CR3, save_cr3);
+
+ GUEST_ASSERT(!vmlaunch());
+ GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+ check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
+
+ exit_to_l0(PORT_DONE, 0);
+}
+
+static void allocate_vmx_page(struct vmx_page *page)
+{
+ vm_vaddr_t virt;
+
+ virt = vm_vaddr_alloc(vm, PAGE_SIZE, 0, 0, 0);
+ memset(addr_gva2hva(vm, virt), 0, PAGE_SIZE);
+
+ page->virt = virt;
+ page->phys = addr_gva2gpa(vm, virt);
+}
+
+static vm_vaddr_t allocate_vmx_pages(void)
+{
+ vm_vaddr_t vmx_pages_vaddr;
+ int i;
+
+ vmx_pages_vaddr = vm_vaddr_alloc(
+ vm, sizeof(struct vmx_page) * NUM_VMX_PAGES, 0, 0, 0);
+
+ vmx_pages = (void *) addr_gva2hva(vm, vmx_pages_vaddr);
+
+ for (i = 0; i < NUM_VMX_PAGES; i++)
+ allocate_vmx_page(&vmx_pages[i]);
+
+ return vmx_pages_vaddr;
+}
+
+void report(int64_t val)
+{
+ printf("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n",
+ val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE);
+}
+
+int main(int argc, char *argv[])
+{
+ vm_vaddr_t vmx_pages_vaddr;
+ struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
+
+ if (!(entry->ecx & CPUID_VMX)) {
+ printf("nested VMX not enabled, skipping test");
+ return 0;
+ }
+
+ vm = vm_create_default_vmx(VCPU_ID, (void *) l1_guest_code);
+
+ /* Allocate VMX pages and shared descriptors (vmx_pages). */
+ vmx_pages_vaddr = allocate_vmx_pages();
+ vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_vaddr);
+
+ for (;;) {
+ volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+ struct kvm_regs regs;
+
+ vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Got exit_reason other than KVM_EXIT_IO: %u (%s),\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ vcpu_regs_get(vm, VCPU_ID, ®s);
+
+ switch (run->io.port) {
+ case PORT_ABORT:
+ TEST_ASSERT(false, "%s", (const char *) regs.rdi);
+ /* NOT REACHED */
+ case PORT_REPORT:
+ report(regs.rdi);
+ break;
+ case PORT_DONE:
+ goto done;
+ default:
+ TEST_ASSERT(false, "Unknown port 0x%x.", run->io.port);
+ }
+ }
+
+ kvm_vm_free(vm);
+done:
+ return 0;
+}