|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [xen stable-4.17] x86/vmx: implement Notify VM Exit
commit b745ff30113d2bd91e2d34cf56437b2fe2e2ea35
Author: Roger Pau Monné <roger.pau@xxxxxxxxxx>
AuthorDate: Tue Mar 21 13:42:43 2023 +0100
Commit: Jan Beulich <jbeulich@xxxxxxxx>
CommitDate: Tue Mar 21 13:42:43 2023 +0100
x86/vmx: implement Notify VM Exit
Under certain conditions guests can get the CPU stuck in an unbounded
loop without the possibility of an interrupt window to occur on
instruction boundary. This was the case with the scenarios described
in XSA-156.
Make use of the Notify VM Exit mechanism, that will trigger a VM Exit
if no interrupt window occurs for a specified amount of time. Note
that using the Notify VM Exit avoids having to trap #AC and #DB
exceptions, as Xen is guaranteed to get a VM Exit even if the guest
puts the CPU in a loop without an interrupt window, as such disable
the intercepts if the feature is available and enabled.
Setting the notify VM exit window to 0 is safe because there's a
threshold added by the hardware in order to have a sane window value.
Note the handling of EXIT_REASON_NOTIFY in the nested virtualization
case is passed to L0, and hence a nested guest being able to trigger a
notify VM exit with an invalid context would be able to crash the L1
hypervisor (by L0 destroying the domain). Since we don't expose VM
Notify support to L1 it should already enable the required
protections in order to prevent VM Notify from triggering in the first
place.
Suggested-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
Signed-off-by: Roger Pau Monné <roger.pau@xxxxxxxxxx>
Reviewed-by: Kevin Tian <kevin.tian@xxxxxxxxx>
x86/vmx: Partially revert "x86/vmx: implement Notify VM Exit"
The original patch tried to do two things - implement VMNotify, and
re-optimise VT-x to not intercept #DB/#AC by default.
The second part is buggy in multiple ways. Both GDBSX and Introspection
need
to conditionally intercept #DB, which was not accounted for. Also, #DB
interception has nothing at all to do with cpu_has_monitor_trap_flag.
Revert the second half, leaving #DB/#AC intercepted unilaterally, but with
VMNotify active by default when available.
Fixes: 573279cde1c4 ("x86/vmx: implement Notify VM Exit")
Signed-off-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
Reviewed-by: Kevin Tian <kevin.tian@xxxxxxxxx>
master commit: 573279cde1c4e752d4df34bc65ffafa17573148e
master date: 2022-12-19 11:24:14 +0100
master commit: 5f08bc9404c7cfa8131e262c7dbcb4d96c752686
master date: 2023-01-20 19:39:32 +0000
---
docs/misc/xen-command-line.pandoc | 11 +++++++++++
xen/arch/x86/hvm/vmx/vmcs.c | 10 ++++++++++
xen/arch/x86/hvm/vmx/vmx.c | 16 ++++++++++++++++
xen/arch/x86/hvm/vmx/vvmx.c | 1 +
xen/arch/x86/include/asm/hvm/vmx/vmcs.h | 4 ++++
xen/arch/x86/include/asm/hvm/vmx/vmx.h | 6 ++++++
xen/arch/x86/include/asm/perfc_defn.h | 3 ++-
7 files changed, 50 insertions(+), 1 deletion(-)
diff --git a/docs/misc/xen-command-line.pandoc
b/docs/misc/xen-command-line.pandoc
index 5be5ce10c6..d601120faa 100644
--- a/docs/misc/xen-command-line.pandoc
+++ b/docs/misc/xen-command-line.pandoc
@@ -2634,6 +2634,17 @@ guest will notify Xen that it has failed to acquire a
spinlock.
<major>, <minor> and <build> must be integers. The values will be
encoded in guest CPUID 0x40000002 if viridian enlightenments are enabled.
+### vm-notify-window (Intel)
+> `= <integer>`
+
+> Default: `0`
+
+Specify the value of the VM Notify window used to detect locked VMs. Set to -1
+to disable the feature. Value is in units of crystal clock cycles.
+
+Note the hardware might add a threshold to the provided value in order to make
+it safe, and hence using 0 is fine.
+
### vpid (Intel)
> `= <boolean>`
diff --git a/xen/arch/x86/hvm/vmx/vmcs.c b/xen/arch/x86/hvm/vmx/vmcs.c
index a0d5e8d6ab..7912053bda 100644
--- a/xen/arch/x86/hvm/vmx/vmcs.c
+++ b/xen/arch/x86/hvm/vmx/vmcs.c
@@ -67,6 +67,9 @@ integer_param("ple_gap", ple_gap);
static unsigned int __read_mostly ple_window = 4096;
integer_param("ple_window", ple_window);
+static unsigned int __ro_after_init vm_notify_window;
+integer_param("vm-notify-window", vm_notify_window);
+
static bool __read_mostly opt_ept_pml = true;
static s8 __read_mostly opt_ept_ad = -1;
int8_t __read_mostly opt_ept_exec_sp = -1;
@@ -210,6 +213,7 @@ static void __init vmx_display_features(void)
P(cpu_has_vmx_pml, "Page Modification Logging");
P(cpu_has_vmx_tsc_scaling, "TSC Scaling");
P(cpu_has_vmx_bus_lock_detection, "Bus Lock Detection");
+ P(cpu_has_vmx_notify_vm_exiting, "Notify VM Exit");
#undef P
if ( !printed )
@@ -329,6 +333,8 @@ static int vmx_init_vmcs_config(bool bsp)
opt |= SECONDARY_EXEC_UNRESTRICTED_GUEST;
if ( opt_ept_pml )
opt |= SECONDARY_EXEC_ENABLE_PML;
+ if ( vm_notify_window != ~0u )
+ opt |= SECONDARY_EXEC_NOTIFY_VM_EXITING;
/*
* "APIC Register Virtualization" and "Virtual Interrupt Delivery"
@@ -1290,6 +1296,10 @@ static int construct_vmcs(struct vcpu *v)
v->arch.hvm.vmx.exception_bitmap = HVM_TRAP_MASK
| (paging_mode_hap(d) ? 0 : (1U << TRAP_page_fault))
| (v->arch.fully_eager_fpu ? 0 : (1U << TRAP_no_device));
+
+ if ( cpu_has_vmx_notify_vm_exiting )
+ __vmwrite(NOTIFY_WINDOW, vm_notify_window);
+
vmx_update_exception_bitmap(v);
v->arch.hvm.guest_cr[0] = X86_CR0_PE | X86_CR0_ET;
diff --git a/xen/arch/x86/hvm/vmx/vmx.c b/xen/arch/x86/hvm/vmx/vmx.c
index 456726e897..f0e759eeaf 100644
--- a/xen/arch/x86/hvm/vmx/vmx.c
+++ b/xen/arch/x86/hvm/vmx/vmx.c
@@ -4622,6 +4622,22 @@ void vmx_vmexit_handler(struct cpu_user_regs *regs)
*/
break;
+ case EXIT_REASON_NOTIFY:
+ __vmread(EXIT_QUALIFICATION, &exit_qualification);
+
+ if ( unlikely(exit_qualification & NOTIFY_VM_CONTEXT_INVALID) )
+ {
+ perfc_incr(vmnotify_crash);
+ gprintk(XENLOG_ERR, "invalid VM context after notify vmexit\n");
+ domain_crash(v->domain);
+ break;
+ }
+
+ if ( unlikely(exit_qualification & INTR_INFO_NMI_UNBLOCKED_BY_IRET) )
+ undo_nmis_unblocked_by_iret();
+
+ break;
+
case EXIT_REASON_VMX_PREEMPTION_TIMER_EXPIRED:
case EXIT_REASON_INVPCID:
/* fall through */
diff --git a/xen/arch/x86/hvm/vmx/vvmx.c b/xen/arch/x86/hvm/vmx/vvmx.c
index 2095c1e612..f8fe8d0c14 100644
--- a/xen/arch/x86/hvm/vmx/vvmx.c
+++ b/xen/arch/x86/hvm/vmx/vvmx.c
@@ -2487,6 +2487,7 @@ int nvmx_n2_vmexit_handler(struct cpu_user_regs *regs,
case EXIT_REASON_EPT_MISCONFIG:
case EXIT_REASON_EXTERNAL_INTERRUPT:
case EXIT_REASON_BUS_LOCK:
+ case EXIT_REASON_NOTIFY:
/* pass to L0 handler */
break;
case VMX_EXIT_REASONS_FAILED_VMENTRY:
diff --git a/xen/arch/x86/include/asm/hvm/vmx/vmcs.h
b/xen/arch/x86/include/asm/hvm/vmx/vmcs.h
index f3df5113d4..78404e42b3 100644
--- a/xen/arch/x86/include/asm/hvm/vmx/vmcs.h
+++ b/xen/arch/x86/include/asm/hvm/vmx/vmcs.h
@@ -268,6 +268,7 @@ extern u32 vmx_vmentry_control;
#define SECONDARY_EXEC_XSAVES 0x00100000
#define SECONDARY_EXEC_TSC_SCALING 0x02000000
#define SECONDARY_EXEC_BUS_LOCK_DETECTION 0x40000000
+#define SECONDARY_EXEC_NOTIFY_VM_EXITING 0x80000000
extern u32 vmx_secondary_exec_control;
#define VMX_EPT_EXEC_ONLY_SUPPORTED 0x00000001
@@ -349,6 +350,8 @@ extern u64 vmx_ept_vpid_cap;
(vmx_secondary_exec_control & SECONDARY_EXEC_TSC_SCALING)
#define cpu_has_vmx_bus_lock_detection \
(vmx_secondary_exec_control & SECONDARY_EXEC_BUS_LOCK_DETECTION)
+#define cpu_has_vmx_notify_vm_exiting \
+ (vmx_secondary_exec_control & SECONDARY_EXEC_NOTIFY_VM_EXITING)
#define VMCS_RID_TYPE_MASK 0x80000000
@@ -456,6 +459,7 @@ enum vmcs_field {
SECONDARY_VM_EXEC_CONTROL = 0x0000401e,
PLE_GAP = 0x00004020,
PLE_WINDOW = 0x00004022,
+ NOTIFY_WINDOW = 0x00004024,
VM_INSTRUCTION_ERROR = 0x00004400,
VM_EXIT_REASON = 0x00004402,
VM_EXIT_INTR_INFO = 0x00004404,
diff --git a/xen/arch/x86/include/asm/hvm/vmx/vmx.h
b/xen/arch/x86/include/asm/hvm/vmx/vmx.h
index eae39365aa..8e1e42ac47 100644
--- a/xen/arch/x86/include/asm/hvm/vmx/vmx.h
+++ b/xen/arch/x86/include/asm/hvm/vmx/vmx.h
@@ -221,6 +221,7 @@ static inline void pi_clear_sn(struct pi_desc *pi_desc)
#define EXIT_REASON_XSAVES 63
#define EXIT_REASON_XRSTORS 64
#define EXIT_REASON_BUS_LOCK 74
+#define EXIT_REASON_NOTIFY 75
/* Remember to also update VMX_PERF_EXIT_REASON_SIZE! */
/*
@@ -236,6 +237,11 @@ static inline void pi_clear_sn(struct pi_desc *pi_desc)
#define INTR_INFO_VALID_MASK 0x80000000 /* 31 */
#define INTR_INFO_RESVD_BITS_MASK 0x7ffff000
+/*
+ * Exit Qualifications for NOTIFY VM EXIT
+ */
+#define NOTIFY_VM_CONTEXT_INVALID 1u
+
/*
* Exit Qualifications for MOV for Control Register Access
*/
diff --git a/xen/arch/x86/include/asm/perfc_defn.h
b/xen/arch/x86/include/asm/perfc_defn.h
index 6fce21e85a..487e20dc97 100644
--- a/xen/arch/x86/include/asm/perfc_defn.h
+++ b/xen/arch/x86/include/asm/perfc_defn.h
@@ -6,7 +6,7 @@ PERFCOUNTER_ARRAY(exceptions, "exceptions", 32)
#ifdef CONFIG_HVM
-#define VMX_PERF_EXIT_REASON_SIZE 75
+#define VMX_PERF_EXIT_REASON_SIZE 76
#define VMEXIT_NPF_PERFC 143
#define SVM_PERF_EXIT_REASON_SIZE (VMEXIT_NPF_PERFC + 1)
PERFCOUNTER_ARRAY(vmexits, "vmexits",
@@ -129,5 +129,6 @@ PERFCOUNTER(iommu_pt_shatters, "IOMMU page table
shatters")
PERFCOUNTER(iommu_pt_coalesces, "IOMMU page table coalesces")
PERFCOUNTER(buslock, "Bus Locks Detected")
+PERFCOUNTER(vmnotify_crash, "domain crashes by Notify VM Exit")
/*#endif*/ /* __XEN_PERFC_DEFN_H__ */
--
generated by git-patchbot for /home/xen/git/xen.git#stable-4.17
|
 |
Lists.xenproject.org is hosted with RackSpace, monitoring our |