summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-10-09 09:39:55 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-10-09 09:39:55 -0700
commitef688f8b8cd3eb20547a6543f03e3d8952b87769 (patch)
treed44f43e19e69bc7828a16a259dd7f42afca02e99
parent0e470763d84dcad27284067647dfb4b1a94dfce0 (diff)
parentc59fb127583869350256656b7ed848c398bef879 (diff)
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm updates from Paolo Bonzini: "The first batch of KVM patches, mostly covering x86. ARM: - Account stage2 page table allocations in memory stats x86: - Account EPT/NPT arm64 page table allocations in memory stats - Tracepoint cleanups/fixes for nested VM-Enter and emulated MSR accesses - Drop eVMCS controls filtering for KVM on Hyper-V, all known versions of Hyper-V now support eVMCS fields associated with features that are enumerated to the guest - Use KVM's sanitized VMCS config as the basis for the values of nested VMX capabilities MSRs - A myriad event/exception fixes and cleanups. Most notably, pending exceptions morph into VM-Exits earlier, as soon as the exception is queued, instead of waiting until the next vmentry. This fixed a longstanding issue where the exceptions would incorrecly become double-faults instead of triggering a vmexit; the common case of page-fault vmexits had a special workaround, but now it's fixed for good - A handful of fixes for memory leaks in error paths - Cleanups for VMREAD trampoline and VMX's VM-Exit assembly flow - Never write to memory from non-sleepable kvm_vcpu_check_block() - Selftests refinements and cleanups - Misc typo cleanups Generic: - remove KVM_REQ_UNHALT" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (94 commits) KVM: remove KVM_REQ_UNHALT KVM: mips, x86: do not rely on KVM_REQ_UNHALT KVM: x86: never write to memory from kvm_vcpu_check_block() KVM: x86: Don't snapshot pending INIT/SIPI prior to checking nested events KVM: nVMX: Make event request on VMXOFF iff INIT/SIPI is pending KVM: nVMX: Make an event request if INIT or SIPI is pending on VM-Enter KVM: SVM: Make an event request if INIT or SIPI is pending when GIF is set KVM: x86: lapic does not have to process INIT if it is blocked KVM: x86: Rename kvm_apic_has_events() to make it INIT/SIPI specific KVM: x86: Rename and expose helper to detect if INIT/SIPI are allowed KVM: nVMX: Make an event request when pending an MTF nested VM-Exit KVM: x86: make vendor code check for all nested events mailmap: Update Oliver's email address KVM: x86: Allow force_emulation_prefix to be written without a reload KVM: selftests: Add an x86-only test to verify nested exception queueing KVM: selftests: Use uapi header to get VMX and SVM exit reasons/codes KVM: x86: Rename inject_pending_events() to kvm_check_and_inject_events() KVM: VMX: Update MTF and ICEBP comments to document KVM's subtle behavior KVM: x86: Treat pending TRIPLE_FAULT requests as pending exceptions KVM: x86: Morph pending exceptions to pending VM-Exits at queue time ...
-rw-r--r--.mailmap1
-rw-r--r--Documentation/admin-guide/cgroup-v2.rst5
-rw-r--r--Documentation/filesystems/proc.rst4
-rw-r--r--Documentation/virt/kvm/api.rst113
-rw-r--r--Documentation/virt/kvm/vcpu-requests.rst28
-rw-r--r--arch/arm64/kvm/arm.c1
-rw-r--r--arch/arm64/kvm/mmu.c36
-rw-r--r--arch/mips/kvm/emulate.c6
-rw-r--r--arch/powerpc/kvm/book3s_pr.c1
-rw-r--r--arch/powerpc/kvm/book3s_pr_papr.c1
-rw-r--r--arch/powerpc/kvm/booke.c1
-rw-r--r--arch/powerpc/kvm/powerpc.c1
-rw-r--r--arch/riscv/kvm/vcpu_insn.c1
-rw-r--r--arch/s390/kvm/kvm-s390.c2
-rw-r--r--arch/x86/include/asm/hyperv-tlfs.h22
-rw-r--r--arch/x86/include/asm/kvm-x86-ops.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h39
-rw-r--r--arch/x86/kvm/cpuid.c18
-rw-r--r--arch/x86/kvm/emulate.c31
-rw-r--r--arch/x86/kvm/hyperv.c70
-rw-r--r--arch/x86/kvm/hyperv.h6
-rw-r--r--arch/x86/kvm/lapic.c38
-rw-r--r--arch/x86/kvm/lapic.h9
-rw-r--r--arch/x86/kvm/mmu/mmu.c22
-rw-r--r--arch/x86/kvm/mmu/paging_tmpl.h2
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.c12
-rw-r--r--arch/x86/kvm/svm/nested.c124
-rw-r--r--arch/x86/kvm/svm/svm.c35
-rw-r--r--arch/x86/kvm/trace.h53
-rw-r--r--arch/x86/kvm/vmx/capabilities.h14
-rw-r--r--arch/x86/kvm/vmx/evmcs.c192
-rw-r--r--arch/x86/kvm/vmx/evmcs.h10
-rw-r--r--arch/x86/kvm/vmx/nested.c468
-rw-r--r--arch/x86/kvm/vmx/nested.h2
-rw-r--r--arch/x86/kvm/vmx/sgx.c2
-rw-r--r--arch/x86/kvm/vmx/vmenter.S24
-rw-r--r--arch/x86/kvm/vmx/vmx.c321
-rw-r--r--arch/x86/kvm/vmx/vmx.h172
-rw-r--r--arch/x86/kvm/vmx/vmx_ops.h2
-rw-r--r--arch/x86/kvm/x86.c576
-rw-r--r--arch/x86/kvm/x86.h16
-rw-r--r--arch/x86/kvm/xen.c1
-rw-r--r--drivers/base/node.c2
-rw-r--r--fs/proc/meminfo.c2
-rw-r--r--include/linux/kvm_host.h16
-rw-r--r--include/linux/mmzone.h1
-rw-r--r--mm/memcontrol.c1
-rw-r--r--mm/page_alloc.c6
-rw-r--r--mm/vmstat.c1
-rw-r--r--tools/testing/selftests/kvm/.gitignore1
-rw-r--r--tools/testing/selftests/kvm/Makefile1
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/evmcs.h45
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/svm_util.h7
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/vmx.h53
-rw-r--r--tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c295
-rw-r--r--tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c24
-rw-r--r--virt/kvm/kvm_main.c9
57 files changed, 1871 insertions, 1077 deletions
diff --git a/.mailmap b/.mailmap
index 191778125ef1..3e63fb0b1088 100644
--- a/.mailmap
+++ b/.mailmap
@@ -336,6 +336,7 @@ Oleksij Rempel <linux@rempel-privat.de> <external.Oleksij.Rempel@de.bosch.com>
Oleksij Rempel <linux@rempel-privat.de> <fixed-term.Oleksij.Rempel@de.bosch.com>
Oleksij Rempel <linux@rempel-privat.de> <o.rempel@pengutronix.de>
Oleksij Rempel <linux@rempel-privat.de> <ore@pengutronix.de>
+Oliver Upton <oliver.upton@linux.dev> <oupton@google.com>
Pali Rohár <pali@kernel.org> <pali.rohar@gmail.com>
Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Patrick Mochel <mochel@digitalimplant.org>
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index be4a77baf784..7ce8130a8924 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1355,6 +1355,11 @@ PAGE_SIZE multiple when read back.
pagetables
Amount of memory allocated for page tables.
+ sec_pagetables
+ Amount of memory allocated for secondary page tables,
+ this currently includes KVM mmu allocations on x86
+ and arm64.
+
percpu (npn)
Amount of memory used for storing per-cpu kernel
data structures.
diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index e7aafc82be99..898c99eae8e4 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -982,6 +982,7 @@ Example output. You may not have all of these fields.
SUnreclaim: 142336 kB
KernelStack: 11168 kB
PageTables: 20540 kB
+ SecPageTables: 0 kB
NFS_Unstable: 0 kB
Bounce: 0 kB
WritebackTmp: 0 kB
@@ -1090,6 +1091,9 @@ KernelStack
Memory consumed by the kernel stacks of all tasks
PageTables
Memory consumed by userspace page tables
+SecPageTables
+ Memory consumed by secondary page tables, this currently
+ currently includes KVM mmu allocations on x86 and arm64.
NFS_Unstable
Always zero. Previous counted pages which had been written to
the server, but has not been committed to stable storage.
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index abd7c32126ce..236a797be71c 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -4074,7 +4074,7 @@ Queues an SMI on the thread's vcpu.
4.97 KVM_X86_SET_MSR_FILTER
----------------------------
-:Capability: KVM_X86_SET_MSR_FILTER
+:Capability: KVM_CAP_X86_MSR_FILTER
:Architectures: x86
:Type: vm ioctl
:Parameters: struct kvm_msr_filter
@@ -4173,8 +4173,10 @@ If an MSR access is not permitted through the filtering, it generates a
allows user space to deflect and potentially handle various MSR accesses
into user space.
-If a vCPU is in running state while this ioctl is invoked, the vCPU may
-experience inconsistent filtering behavior on MSR accesses.
+Note, invoking this ioctl while a vCPU is running is inherently racy. However,
+KVM does guarantee that vCPUs will see either the previous filter or the new
+filter, e.g. MSRs with identical settings in both the old and new filter will
+have deterministic behavior.
4.98 KVM_CREATE_SPAPR_TCE_64
----------------------------
@@ -5287,110 +5289,7 @@ KVM_PV_DUMP
authentication tag all of which are needed to decrypt the dump at a
later time.
-
-4.126 KVM_X86_SET_MSR_FILTER
-----------------------------
-
-:Capability: KVM_CAP_X86_MSR_FILTER
-:Architectures: x86
-:Type: vm ioctl
-:Parameters: struct kvm_msr_filter
-:Returns: 0 on success, < 0 on error
-
-::
-
- struct kvm_msr_filter_range {
- #define KVM_MSR_FILTER_READ (1 << 0)
- #define KVM_MSR_FILTER_WRITE (1 << 1)
- __u32 flags;
- __u32 nmsrs; /* number of msrs in bitmap */
- __u32 base; /* MSR index the bitmap starts at */
- __u8 *bitmap; /* a 1 bit allows the operations in flags, 0 denies */
- };
-
- #define KVM_MSR_FILTER_MAX_RANGES 16
- struct kvm_msr_filter {
- #define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0)
- #define KVM_MSR_FILTER_DEFAULT_DENY (1 << 0)
- __u32 flags;
- struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES];
- };
-
-flags values for ``struct kvm_msr_filter_range``:
-
-``KVM_MSR_FILTER_READ``
-
- Filter read accesses to MSRs using the given bitmap. A 0 in the bitmap
- indicates that a read should immediately fail, while a 1 indicates that
- a read for a particular MSR should be handled regardless of the default
- filter action.
-
-``KVM_MSR_FILTER_WRITE``
-
- Filter write accesses to MSRs using the given bitmap. A 0 in the bitmap
- indicates that a write should immediately fail, while a 1 indicates that
- a write for a particular MSR should be handled regardless of the default
- filter action.
-
-``KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE``
-
- Filter both read and write accesses to MSRs using the given bitmap. A 0
- in the bitmap indicates that both reads and writes should immediately fail,
- while a 1 indicates that reads and writes for a particular MSR are not
- filtered by this range.
-
-flags values for ``struct kvm_msr_filter``:
-
-``KVM_MSR_FILTER_DEFAULT_ALLOW``
-
- If no filter range matches an MSR index that is getting accessed, KVM will
- fall back to allowing access to the MSR.
-
-``KVM_MSR_FILTER_DEFAULT_DENY``
-
- If no filter range matches an MSR index that is getting accessed, KVM will
- fall back to rejecting access to the MSR. In this mode, all MSRs that should
- be processed by KVM need to explicitly be marked as allowed in the bitmaps.
-
-This ioctl allows user space to define up to 16 bitmaps of MSR ranges to
-specify whether a certain MSR access should be explicitly filtered for or not.
-
-If this ioctl has never been invoked, MSR accesses are not guarded and the
-default KVM in-kernel emulation behavior is fully preserved.
-
-Calling this ioctl with an empty set of ranges (all nmsrs == 0) disables MSR
-filtering. In that mode, ``KVM_MSR_FILTER_DEFAULT_DENY`` is invalid and causes
-an error.
-
-As soon as the filtering is in place, every MSR access is processed through
-the filtering except for accesses to the x2APIC MSRs (from 0x800 to 0x8ff);
-x2APIC MSRs are always allowed, independent of the ``default_allow`` setting,
-and their behavior depends on the ``X2APIC_ENABLE`` bit of the APIC base
-register.
-
-If a bit is within one of the defined ranges, read and write accesses are
-guarded by the bitmap's value for the MSR index if the kind of access
-is included in the ``struct kvm_msr_filter_range`` flags. If no range
-cover this particular access, the behavior is determined by the flags
-field in the kvm_msr_filter struct: ``KVM_MSR_FILTER_DEFAULT_ALLOW``
-and ``KVM_MSR_FILTER_DEFAULT_DENY``.
-
-Each bitmap range specifies a range of MSRs to potentially allow access on.
-The range goes from MSR index [base .. base+nmsrs]. The flags field
-indicates whether reads, writes or both reads and writes are filtered
-by setting a 1 bit in the bitmap for the corresponding MSR index.
-
-If an MSR access is not permitted through the filtering, it generates a
-#GP inside the guest. When combined with KVM_CAP_X86_USER_SPACE_MSR, that
-allows user space to deflect and potentially handle various MSR accesses
-into user space.
-
-Note, invoking this ioctl with a vCPU is running is inherently racy. However,
-KVM does guarantee that vCPUs will see either the previous filter or the new
-filter, e.g. MSRs with identical settings in both the old and new filter will
-have deterministic behavior.
-
-4.127 KVM_XEN_HVM_SET_ATTR
+4.126 KVM_XEN_HVM_SET_ATTR
--------------------------
:Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO
diff --git a/Documentation/virt/kvm/vcpu-requests.rst b/Documentation/virt/kvm/vcpu-requests.rst
index 31f62b64e07b..87f04c1fa53d 100644
--- a/Documentation/virt/kvm/vcpu-requests.rst
+++ b/Documentation/virt/kvm/vcpu-requests.rst
@@ -97,7 +97,7 @@ VCPU requests are simply bit indices of the ``vcpu->requests`` bitmap.
This means general bitops, like those documented in [atomic-ops]_ could
also be used, e.g. ::
- clear_bit(KVM_REQ_UNHALT & KVM_REQUEST_MASK, &vcpu->requests);
+ clear_bit(KVM_REQ_UNBLOCK & KVM_REQUEST_MASK, &vcpu->requests);
However, VCPU request users should refrain from doing so, as it would
break the abstraction. The first 8 bits are reserved for architecture
@@ -126,17 +126,6 @@ KVM_REQ_UNBLOCK
or in order to update the interrupt routing and ensure that assigned
devices will wake up the vCPU.
-KVM_REQ_UNHALT
-
- This request may be made from the KVM common function kvm_vcpu_block(),
- which is used to emulate an instruction that causes a CPU to halt until
- one of an architectural specific set of events and/or interrupts is
- received (determined by checking kvm_arch_vcpu_runnable()). When that
- event or interrupt arrives kvm_vcpu_block() makes the request. This is
- in contrast to when kvm_vcpu_block() returns due to any other reason,
- such as a pending signal, which does not indicate the VCPU's halt
- emulation should stop, and therefore does not make the request.
-
KVM_REQ_OUTSIDE_GUEST_MODE
This "request" ensures the target vCPU has exited guest mode prior to the
@@ -297,21 +286,6 @@ architecture dependent. kvm_vcpu_block() calls kvm_arch_vcpu_runnable()
to check if it should awaken. One reason to do so is to provide
architectures a function where requests may be checked if necessary.
-Clearing Requests
------------------
-
-Generally it only makes sense for the receiving VCPU thread to clear a
-request. However, in some circumstances, such as when the requesting
-thread and the receiving VCPU thread are executed serially, such as when
-they are the same thread, or when they are using some form of concurrency
-control to temporarily execute synchronously, then it's possible to know
-that the request may be cleared immediately, rather than waiting for the
-receiving VCPU thread to handle the request in VCPU RUN. The only current
-examples of this are kvm_vcpu_block() calls made by VCPUs to block
-themselves. A possible side-effect of that call is to make the
-KVM_REQ_UNHALT request, which may then be cleared immediately when the
-VCPU returns from the call.
-
References
==========
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 917086be5c6b..446f628a9de1 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -666,7 +666,6 @@ void kvm_vcpu_wfi(struct kvm_vcpu *vcpu)
kvm_vcpu_halt(vcpu);
vcpu_clear_flag(vcpu, IN_WFIT);
- kvm_clear_request(KVM_REQ_UNHALT, vcpu);
preempt_disable();
vgic_v4_load(vcpu);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index c9a13e487187..34c5feed9dc1 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -92,9 +92,13 @@ static bool kvm_is_device_pfn(unsigned long pfn)
static void *stage2_memcache_zalloc_page(void *arg)
{
struct kvm_mmu_memory_cache *mc = arg;
+ void *virt;
/* Allocated with __GFP_ZERO, so no need to zero */
- return kvm_mmu_memory_cache_alloc(mc);
+ virt = kvm_mmu_memory_cache_alloc(mc);
+ if (virt)
+ kvm_account_pgtable_pages(virt, 1);
+ return virt;
}
static void *kvm_host_zalloc_pages_exact(size_t size)
@@ -102,6 +106,21 @@ static void *kvm_host_zalloc_pages_exact(size_t size)
return alloc_pages_exact(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO);
}
+static void *kvm_s2_zalloc_pages_exact(size_t size)
+{
+ void *virt = kvm_host_zalloc_pages_exact(size);
+
+ if (virt)
+ kvm_account_pgtable_pages(virt, (size >> PAGE_SHIFT));
+ return virt;
+}
+
+static void kvm_s2_free_pages_exact(void *virt, size_t size)
+{
+ kvm_account_pgtable_pages(virt, -(size >> PAGE_SHIFT));
+ free_pages_exact(virt, size);
+}
+
static void kvm_host_get_page(void *addr)
{
get_page(virt_to_page(addr));
@@ -112,6 +131,15 @@ static void kvm_host_put_page(void *addr)
put_page(virt_to_page(addr));
}
+static void kvm_s2_put_page(void *addr)
+{
+ struct page *p = virt_to_page(addr);
+ /* Dropping last refcount, the page will be freed */
+ if (page_count(p) == 1)
+ kvm_account_pgtable_pages(addr, -1);
+ put_page(p);
+}
+
static int kvm_host_page_count(void *addr)
{
return page_count(virt_to_page(addr));
@@ -625,10 +653,10 @@ static int get_user_mapping_size(struct kvm *kvm, u64 addr)
static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = {
.zalloc_page = stage2_memcache_zalloc_page,
- .zalloc_pages_exact = kvm_host_zalloc_pages_exact,
- .free_pages_exact = free_pages_exact,
+ .zalloc_pages_exact = kvm_s2_zalloc_pages_exact,
+ .free_pages_exact = kvm_s2_free_pages_exact,
.get_page = kvm_host_get_page,
- .put_page = kvm_host_put_page,
+ .put_page = kvm_s2_put_page,
.page_count = kvm_host_page_count,
.phys_to_virt = kvm_host_va,
.virt_to_phys = kvm_host_pa,
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index b494d8d39290..edaec93a1a1f 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -955,13 +955,11 @@ enum emulation_result kvm_mips_emul_wait(struct kvm_vcpu *vcpu)
kvm_vcpu_halt(vcpu);
/*
- * We we are runnable, then definitely go off to user space to
+ * We are runnable, then definitely go off to user space to
* check if any I/O interrupts are pending.
*/
- if (kvm_check_request(KVM_REQ_UNHALT, vcpu)) {
- kvm_clear_request(KVM_REQ_UNHALT, vcpu);
+ if (kvm_arch_vcpu_runnable(vcpu))
vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
- }
}
return EMULATE_DONE;
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index d6abed6e51e6..9fc4dd8f66eb 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -499,7 +499,6 @@ static void kvmppc_set_msr_pr(struct kvm_vcpu *vcpu, u64 msr)
if (msr & MSR_POW) {
if (!vcpu->arch.pending_exceptions) {
kvm_vcpu_halt(vcpu);
- kvm_clear_request(KVM_REQ_UNHALT, vcpu);
vcpu->stat.generic.halt_wakeup++;
/* Unset POW bit after we woke up */
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index a1f2978b2a86..b2c89e850d7a 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -393,7 +393,6 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
case H_CEDE:
kvmppc_set_msr_fast(vcpu, kvmppc_get_msr(vcpu) | MSR_EE);
kvm_vcpu_halt(vcpu);
- kvm_clear_request(KVM_REQ_UNHALT, vcpu);
vcpu->stat.generic.halt_wakeup++;
return EMULATE_DONE;
case H_LOGICAL_CI_LOAD:
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 06c5830a93f9..7b4920e9fd26 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -719,7 +719,6 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
if (vcpu->arch.shared->msr & MSR_WE) {
local_irq_enable();
kvm_vcpu_halt(vcpu);
- kvm_clear_request(KVM_REQ_UNHALT, vcpu);
hard_irq_disable();
kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index fb1490761c87..ec9c1e3c2ff4 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -239,7 +239,6 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
case EV_HCALL_TOKEN(EV_IDLE):
r = EV_SUCCESS;
kvm_vcpu_halt(vcpu);
- kvm_clear_request(KVM_REQ_UNHALT, vcpu);
break;
default:
r = EV_UNIMPLEMENTED;
diff --git a/arch/riscv/kvm/vcpu_insn.c b/arch/riscv/kvm/vcpu_insn.c
index 7eb90a47b571..0bb52761a3f7 100644
--- a/arch/riscv/kvm/vcpu_insn.c
+++ b/arch/riscv/kvm/vcpu_insn.c
@@ -191,7 +191,6 @@ void kvm_riscv_vcpu_wfi(struct kvm_vcpu *vcpu)
kvm_vcpu_srcu_read_unlock(vcpu);
kvm_vcpu_halt(vcpu);
kvm_vcpu_srcu_read_lock(vcpu);
- kvm_clear_request(KVM_REQ_UNHALT, vcpu);
}
}
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index b7ef0b71014d..45d4b8182b07 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -4343,8 +4343,6 @@ retry:
goto retry;
}
- /* nothing to do, just clear the request */
- kvm_clear_request(KVM_REQ_UNHALT, vcpu);
/* we left the vsie handler, nothing to do, just clear the request */
kvm_clear_request(KVM_REQ_VSIE_RESTART, vcpu);
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 0a9407dc0859..3089ec352743 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -138,6 +138,9 @@
#define HV_X64_NESTED_GUEST_MAPPING_FLUSH BIT(18)
#define HV_X64_NESTED_MSR_BITMAP BIT(19)
+/* Nested features #2. These are HYPERV_CPUID_NESTED_FEATURES.EBX bits. */
+#define HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL BIT(0)
+
/*
* This is specific to AMD and specifies that enlightened TLB flush is
* supported. If guest opts in to this feature, ASID invalidations only
@@ -546,7 +549,7 @@ struct hv_enlightened_vmcs {
u64 guest_rip;
u32 hv_clean_fields;
- u32 hv_padding_32;
+ u32 padding32_1;
u32 hv_synthetic_controls;
struct {
u32 nested_flush_hypercall:1;
@@ -554,14 +557,25 @@ struct hv_enlightened_vmcs {
u32 reserved:30;
} __packed hv_enlightenments_control;
u32 hv_vp_id;
-
+ u32 padding32_2;
u64 hv_vm_id;
u64 partition_assist_page;
u64 padding64_4[4];
u64 guest_bndcfgs;
- u64 padding64_5[7];
+ u64 guest_ia32_perf_global_ctrl;
+ u64 guest_ia32_s_cet;
+ u64 guest_ssp;
+ u64 guest_ia32_int_ssp_table_addr;
+ u64 guest_ia32_lbr_ctl;
+ u64 padding64_5[2];
u64 xss_exit_bitmap;
- u64 padding64_6[7];
+ u64 encls_exiting_bitmap;
+ u64 host_ia32_perf_global_ctrl;
+ u64 tsc_multiplier;
+ u64 host_ia32_s_cet;
+ u64 host_ssp;
+ u64 host_ia32_int_ssp_table_addr;
+ u64 padding64_6;
} __packed;
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE 0
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 51f777071584..82ba4a564e58 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -67,7 +67,7 @@ KVM_X86_OP(get_interrupt_shadow)
KVM_X86_OP(patch_hypercall)
KVM_X86_OP(inject_irq)
KVM_X86_OP(inject_nmi)
-KVM_X86_OP(queue_exception)
+KVM_X86_OP(inject_exception)
KVM_X86_OP(cancel_injection)
KVM_X86_OP(interrupt_allowed)
KVM_X86_OP(nmi_allowed)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index aa381ab69a19..61b9dd34d333 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -615,6 +615,8 @@ struct kvm_vcpu_hv {
u32 enlightenments_eax; /* HYPERV_CPUID_ENLIGHTMENT_INFO.EAX */
u32 enlightenments_ebx; /* HYPERV_CPUID_ENLIGHTMENT_INFO.EBX */
u32 syndbg_cap_eax; /* HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX */
+ u32 nested_eax; /* HYPERV_CPUID_NESTED_FEATURES.EAX */
+ u32 nested_ebx; /* HYPERV_CPUID_NESTED_FEATURES.EBX */
} cpuid_cache;
};
@@ -639,6 +641,16 @@ struct kvm_vcpu_xen {
struct timer_list poll_timer;
};
+struct kvm_queued_exception {
+ bool pending;
+ bool injected;
+ bool has_error_code;
+ u8 vector;
+ u32 error_code;
+ unsigned long payload;
+ bool has_payload;
+};
+
struct kvm_vcpu_arch {
/*
* rip and regs accesses must go through
@@ -738,16 +750,12 @@ struct kvm_vcpu_arch {
u8 event_exit_inst_len;
- struct kvm_queued_exception {
- bool pending;
- bool injected;
- bool has_error_code;
- u8 nr;
- u32 error_code;
- unsigned long payload;
- bool has_payload;
- u8 nested_apf;
- } exception;
+ bool exception_from_userspace;
+
+ /* Exceptions to be injected to the guest. */
+ struct kvm_queued_exception exception;
+ /* Exception VM-Exits to be synthesized to L1. */
+ struct kvm_queued_exception exception_vmexit;
struct kvm_queued_interrupt {
bool injected;
@@ -858,7 +866,6 @@ struct kvm_vcpu_arch {
u32 id;
bool send_user_only;
u32 host_apf_flags;
- unsigned long nested_apf_token;
bool delivery_as_pf_vmexit;
bool pageready_pending;
} apf;
@@ -1524,7 +1531,7 @@ struct kvm_x86_ops {
unsigned char *hypercall_addr);
void (*inject_irq)(struct kvm_vcpu *vcpu, bool reinjected);
void (*inject_nmi)(struct kvm_vcpu *vcpu);
- void (*queue_exception)(struct kvm_vcpu *vcpu);
+ void (*inject_exception)(struct kvm_vcpu *vcpu);
void (*cancel_injection)(struct kvm_vcpu *vcpu);
int (*interrupt_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
int (*nmi_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
@@ -1634,10 +1641,10 @@ struct kvm_x86_ops {
struct kvm_x86_nested_ops {
void (*leave_nested)(struct kvm_vcpu *vcpu);
+ bool (*is_exception_vmexit)(struct kvm_vcpu *vcpu, u8 vector,
+ u32 error_code);
int (*check_events)(struct kvm_vcpu *vcpu);
- bool (*handle_page_fault_workaround)(struct kvm_vcpu *vcpu,
- struct x86_exception *fault);
- bool (*hv_timer_pending)(struct kvm_vcpu *vcpu);
+ bool (*has_events)(struct kvm_vcpu *vcpu);
void (*triple_fault)(struct kvm_vcpu *vcpu);
int (*get_state)(struct kvm_vcpu *vcpu,
struct kvm_nested_state __user *user_kvm_nested_state,
@@ -1863,7 +1870,7 @@ void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long pay
void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr);
void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
-bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu,
+void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu,
struct x86_exception *fault);
bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr);
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 2796dde06302..7065462378e2 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -311,6 +311,15 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
}
EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime);
+static bool kvm_cpuid_has_hyperv(struct kvm_cpuid_entry2 *entries, int nent)
+{
+ struct kvm_cpuid_entry2 *entry;
+
+ entry = cpuid_entry2_find(entries, nent, HYPERV_CPUID_INTERFACE,
+ KVM_CPUID_INDEX_NOT_SIGNIFICANT);
+ return entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX;
+}
+
static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic = vcpu->arch.apic;
@@ -346,7 +355,8 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
vcpu->arch.cr4_guest_rsvd_bits =
__cr4_reserved_bits(guest_cpuid_has, vcpu);
- kvm_hv_set_cpuid(vcpu);
+ kvm_hv_set_cpuid(vcpu, kvm_cpuid_has_hyperv(vcpu->arch.cpuid_entries,
+ vcpu->arch.cpuid_nent));
/* Invoke the vendor callback only after the above state is updated. */
static_call(kvm_x86_vcpu_after_set_cpuid)(vcpu);
@@ -409,6 +419,12 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2,
return 0;
}
+ if (kvm_cpuid_has_hyperv(e2, nent)) {
+ r = kvm_hv_vcpu_init(vcpu);
+ if (r)
+ return r;
+ }
+
r = kvm_check_cpuid(vcpu, e2, nent);
if (r)
return r;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index aacb28c83e43..3b27622d4642 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1137,9 +1137,11 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt)
static void decode_register_operand(struct x86_emulate_ctxt *ctxt,
struct operand *op)
{
- unsigned reg = ctxt->modrm_reg;
+ unsigned int reg;
- if (!(ctxt->d & ModRM))
+ if (ctxt->d & ModRM)
+ reg = ctxt->modrm_reg;
+ else
reg = (ctxt->b & 7) | ((ctxt->rex_prefix & 1) << 3);
if (ctxt->d & Sse) {
@@ -1953,7 +1955,7 @@ static int em_pop_sreg(struct x86_emulate_ctxt *ctxt)
if (rc != X86EMUL_CONTINUE)
return rc;
- if (ctxt->modrm_reg == VCPU_SREG_SS)
+ if (seg == VCPU_SREG_SS)
ctxt->interruptibility = KVM_X86_SHADOW_INT_MOV_SS;
if (ctxt->op_bytes > 2)
rsp_increment(ctxt, ctxt->op_bytes - 2);
@@ -3645,13 +3647,10 @@ static int em_wrmsr(struct x86_emulate_ctxt *ctxt)
| ((u64)reg_read(ctxt, VCPU_REGS_RDX) << 32);
r = ctxt->ops->set_msr_with_filter(ctxt, msr_index, msr_data);
- if (r == X86EMUL_IO_NEEDED)
- return r;
-
- if (r > 0)
+ if (r == X86EMUL_PROPAGATE_FAULT)
return emulate_gp(ctxt, 0);
- return r < 0 ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE;
+ return r;
}
static int em_rdmsr(struct x86_emulate_ctxt *ctxt)
@@ -3662,15 +3661,14 @@ static int em_rdmsr(struct x86_emulate_ctxt *ctxt)
r = ctxt->ops->get_msr_with_filter(ctxt, msr_index, &msr_data);
- if (r == X86EMUL_IO_NEEDED)
- return r;
-
- if (r)
+ if (r == X86EMUL_PROPAGATE_FAULT)
return emulate_gp(ctxt, 0);
- *reg_write(ctxt, VCPU_REGS_RAX) = (u32)msr_data;
- *reg_write(ctxt, VCPU_REGS_RDX) = msr_data >> 32;
- return X86EMUL_CONTINUE;
+ if (r == X86EMUL_CONTINUE) {
+ *reg_write(ctxt, VCPU_REGS_RAX) = (u32)msr_data;
+ *reg_write(ctxt, VCPU_REGS_RDX) = msr_data >> 32;
+ }
+ return r;
}
static int em_store_sreg(struct x86_emulate_ctxt *ctxt, int segment)
@@ -4171,8 +4169,7 @@ static int check_dr7_gd(struct x86_emulate_ctxt *ctxt)
ctxt->ops->get_dr(ctxt, 7, &dr7);
- /* Check if DR7.Global_Enable is set */
- return dr7 & (1 << 13);
+ return dr7 & DR7_GD;
}
static int check_dr_read(struct x86_emulate_ctxt *ctxt)
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index ed804447589c..0adf4a437e85 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -38,9 +38,6 @@
#include "irq.h"
#include "fpu.h"
-/* "Hv#1" signature */
-#define HYPERV_CPUID_SIGNATURE_EAX 0x31237648
-
#define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, 64)
static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer,
@@ -934,11 +931,14 @@ static void stimer_init(struct kvm_vcpu_hv_stimer *stimer, int timer_index)
stimer_prepare_msg(stimer);
}
-static int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
+int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
{
- struct kvm_vcpu_hv *hv_vcpu;
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
int i;
+ if (hv_vcpu)
+ return 0;
+
hv_vcpu = kzalloc(sizeof(struct kvm_vcpu_hv), GFP_KERNEL_ACCOUNT);
if (!hv_vcpu)
return -ENOMEM;
@@ -962,11 +962,9 @@ int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages)
struct kvm_vcpu_hv_synic *synic;
int r;
- if (!to_hv_vcpu(vcpu)) {
- r = kvm_hv_vcpu_init(vcpu);
- if (r)
- return r;
- }
+ r = kvm_hv_vcpu_init(vcpu);
+ if (r)
+ return r;
synic = to_hv_synic(vcpu);
@@ -1660,10 +1658,8 @@ int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
if (!host && !vcpu->arch.hyperv_enabled)
return 1;
- if (!to_hv_vcpu(vcpu)) {
- if (kvm_hv_vcpu_init(vcpu))
- return 1;
- }
+ if (kvm_hv_vcpu_init(vcpu))
+ return 1;
if (kvm_hv_msr_partition_wide(msr)) {
int r;
@@ -1683,10 +1679,8 @@ int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host)
if (!host && !vcpu->arch.hyperv_enabled)
return 1;
- if (!to_hv_vcpu(vcpu)) {
- if (kvm_hv_vcpu_init(vcpu))
- return 1;
- }
+ if (kvm_hv_vcpu_init(vcpu))
+ return 1;
if (kvm_hv_msr_partition_wide(msr)) {
int r;
@@ -1987,49 +1981,49 @@ ret_success:
return HV_STATUS_SUCCESS;
}
-void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu)
+void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu, bool hyperv_enabled)
{
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
struct kvm_cpuid_entry2 *entry;
- struct kvm_vcpu_hv *hv_vcpu;
- entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_INTERFACE);
- if (entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX) {
- vcpu->arch.hyperv_enabled = true;
- } else {
- vcpu->arch.hyperv_enabled = false;
+ vcpu->arch.hyperv_enabled = hyperv_enabled;
+
+ if (!hv_vcpu) {
+ /*
+ * KVM should have already allocated kvm_vcpu_hv if Hyper-V is
+ * enabled in CPUID.
+ */
+ WARN_ON_ONCE(vcpu->arch.hyperv_enabled);
return;
}
- if (!to_hv_vcpu(vcpu) && kvm_hv_vcpu_init(vcpu))
- return;
+ memset(&hv_vcpu->cpuid_cache, 0, sizeof(hv_vcpu->cpuid_cache));
- hv_vcpu = to_hv_vcpu(vcpu);
+ if (!vcpu->arch.hyperv_enabled)
+ return;
entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES);
if (entry) {
hv_vcpu->cpuid_cache.features_eax = entry->eax;
hv_vcpu->cpuid_cache.features_ebx = entry->ebx;
hv_vcpu->cpuid_cache.features_edx = entry->edx;
- } else {
- hv_vcpu->cpuid_cache.features_eax = 0;
- hv_vcpu->cpuid_cache.features_ebx = 0;
- hv_vcpu->cpuid_cache.features_edx = 0;
}
entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_ENLIGHTMENT_INFO);
if (entry) {
hv_vcpu->cpuid_cache.enlightenments_eax = entry->eax;
hv_vcpu->cpuid_cache.enlightenments_ebx = entry->ebx;
- } else {
- hv_vcpu->cpuid_cache.enlightenments_eax = 0;
- hv_vcpu->cpuid_cache.enlightenments_ebx = 0;
}
entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES);
if (entry)
hv_vcpu->cpuid_cache.syndbg_cap_eax = entry->eax;
- else
- hv_vcpu->cpuid_cache.syndbg_cap_eax = 0;
+
+ entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_NESTED_FEATURES);
+ if (entry) {
+ hv_vcpu->cpuid_cache.nested_eax = entry->eax;
+ hv_vcpu->cpuid_cache.nested_ebx = entry->ebx;
+ }
}
int kvm_hv_set_enforce_cpuid(struct kvm_vcpu *vcpu, bool enforce)
@@ -2552,7 +2546,7 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
case HYPERV_CPUID_NESTED_FEATURES:
ent->eax = evmcs_ver;
ent->eax |= HV_X64_NESTED_MSR_BITMAP;
-
+ ent->ebx |= HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL;
break;
case HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS:
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index da2737f2a956..1030b1b50552 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -23,6 +23,9 @@
#include <linux/kvm_host.h>
+/* "Hv#1" signature */
+#define HYPERV_CPUID_SIGNATURE_EAX 0x31237648
+
/*
* The #defines related to the synthetic debugger are required by KDNet, but
* they are not documented in the Hyper-V TLFS because the synthetic debugger
@@ -141,7 +144,8 @@ void kvm_hv_request_tsc_page_update(struct kvm *kvm);
void kvm_hv_init_vm(struct kvm *kvm);
void kvm_hv_destroy_vm(struct kvm *kvm);
-void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu);
+int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu);
+void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu, bool hyperv_enabled);
int kvm_hv_set_enforce_cpuid(struct kvm_vcpu *vcpu, bool enforce);
int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args);
int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 9dda989a1cf0..d7639d126e6c 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -3025,17 +3025,8 @@ int kvm_apic_accept_events(struct kvm_vcpu *vcpu)
struct kvm_lapic *apic = vcpu->arch.apic;
u8 sipi_vector;
int r;
- unsigned long pe;
- if (!lapic_in_kernel(vcpu))
- return 0;
-
- /*
- * Read pending events before calling the check_events
- * callback.
- */
- pe = smp_load_acquire(&apic->pending_events);
- if (!pe)
+ if (!kvm_apic_has_pending_init_or_sipi(vcpu))
return 0;
if (is_guest_mode(vcpu)) {
@@ -3043,38 +3034,31 @@ int kvm_apic_accept_events(struct kvm_vcpu *vcpu)
if (r < 0)
return r == -EBUSY ? 0 : r;
/*
- * If an event has happened and caused a vmexit,
- * we know INITs are latched and therefore
- * we will not incorrectly deliver an APIC
- * event instead of a vmexit.
+ * Continue processing INIT/SIPI even if a nested VM-Exit
+ * occurred, e.g. pending SIPIs should be dropped if INIT+SIPI
+ * are blocked as a result of transitioning to VMX root mode.
*/
}
/*
- * INITs are latched while CPU is in specific states
- * (SMM, VMX root mode, SVM with GIF=0).
- * Because a CPU cannot be in these states immediately
- * after it has processed an INIT signal (and thus in
- * KVM_MP_STATE_INIT_RECEIVED state), just eat SIPIs
- * and leave the INIT pending.
+ * INITs are blocked while CPU is in specific states (SMM, VMX root
+ * mode, SVM with GIF=0), while SIPIs are dropped if the CPU isn't in
+ * wait-for-SIPI (WFS).
*/
- if (kvm_vcpu_latch_init(vcpu)) {
+ if (!kvm_apic_init_sipi_allowed(vcpu)) {
WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED);
- if (test_bit(KVM_APIC_SIPI, &pe))
- clear_bit(KVM_APIC_SIPI, &apic->pending_events);
+ clear_bit(KVM_APIC_SIPI, &apic->pending_events);
return 0;
}
- if (test_bit(KVM_APIC_INIT, &pe)) {
- clear_bit(KVM_APIC_INIT, &apic->pending_events);
+ if (test_and_clear_bit(KVM_APIC_INIT, &apic->pending_events)) {
kvm_vcpu_reset(vcpu, true);
if (kvm_vcpu_is_bsp(apic->vcpu))
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
else
vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
}
- if (test_bit(KVM_APIC_SIPI, &pe)) {
- clear_bit(KVM_APIC_SIPI, &apic->pending_events);
+ if (test_and_clear_bit(KVM_APIC_SIPI, &apic->pending_events)) {
if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
/* evaluate pending_events before reading the vector */
smp_rmb();
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 117a46df5cc1..a5ac4a5a5179 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -7,6 +7,7 @@
#include <linux/kvm_host.h>
#include "hyperv.h"
+#include "kvm_cache_regs.h"
#define KVM_APIC_INIT 0
#define KVM_APIC_SIPI 1
@@ -223,11 +224,17 @@ static inline bool kvm_vcpu_apicv_active(struct kvm_vcpu *vcpu)
return lapic_in_kernel(vcpu) && vcpu->arch.apic->apicv_active;
}
-static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu)
+static inline bool kvm_apic_has_pending_init_or_sipi(struct kvm_vcpu *vcpu)
{
return lapic_in_kernel(vcpu) && vcpu->arch.apic->pending_events;
}
+static inline bool kvm_apic_init_sipi_allowed(struct kvm_vcpu *vcpu)
+{
+ return !is_smm(vcpu) &&
+ !static_call(kvm_x86_apic_init_signal_blocked)(vcpu);
+}
+
static inline bool kvm_lowest_prio_delivery(struct kvm_lapic_irq *irq)
{
return (irq->delivery_mode == APIC_DM_LOWEST ||
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 3552e6af3684..6f81539061d6 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1667,6 +1667,18 @@ static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, long nr)
percpu_counter_add(&kvm_total_used_mmu_pages, nr);
}
+static void kvm_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ kvm_mod_used_mmu_pages(kvm, +1);
+ kvm_account_pgtable_pages((void *)sp->spt, +1);
+}
+
+static void kvm_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ kvm_mod_used_mmu_pages(kvm, -1);
+ kvm_account_pgtable_pages((void *)sp->spt, -1);
+}
+
static void kvm_mmu_free_shadow_page(struct kvm_mmu_page *sp)
{
MMU_WARN_ON(!is_empty_shadow_page(sp->spt));
@@ -2124,7 +2136,7 @@ static struct kvm_mmu_page *kvm_mmu_alloc_shadow_page(struct kvm *kvm,
*/
sp->mmu_valid_gen = kvm->arch.mmu_valid_gen;
list_add(&sp->link, &kvm->arch.active_mmu_pages);
- kvm_mod_used_mmu_pages(kvm, +1);
+ kvm_account_mmu_page(kvm, sp);
sp->gfn = gfn;
sp->role = role;
@@ -2458,7 +2470,7 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
list_add(&sp->link, invalid_list);
else
list_move(&sp->link, invalid_list);
- kvm_mod_used_mmu_pages(kvm, -1);
+ kvm_unaccount_mmu_page(kvm, sp);
} else {
/*
* Remove the active root from the active page list, the root
@@ -4292,7 +4304,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
vcpu->arch.l1tf_flush_l1d = true;
if (!flags) {
- trace_kvm_page_fault(fault_address, error_code);
+ trace_kvm_page_fault(vcpu, fault_address, error_code);
if (kvm_event_needs_reinjection(vcpu))
kvm_mmu_unprotect_page_virt(vcpu, fault_address);
@@ -6704,10 +6716,12 @@ int kvm_mmu_vendor_module_init(void)
ret = register_shrinker(&mmu_shrinker, "x86-mmu");
if (ret)
- goto out;
+ goto out_shrinker;
return 0;
+out_shrinker:
+ percpu_counter_destroy(&kvm_total_used_mmu_pages);
out:
mmu_destroy_caches();
return ret;
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 39e0205e7300..5ab5f94dcb6f 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -472,7 +472,7 @@ error:
#if PTTYPE == PTTYPE_EPT
/*
- * Use PFERR_RSVD_MASK in error_code to to tell if EPT
+ * Use PFERR_RSVD_MASK in error_code to tell if EPT
* misconfiguration requires to be injected. The detection is
* done by is_rsvd_bits_set() above.
*
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index bf2ccf9debca..672f0432d777 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -372,6 +372,16 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn,
}
}
+static void tdp_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ kvm_account_pgtable_pages((void *)sp->spt, +1);
+}
+
+static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ kvm_account_pgtable_pages((void *)sp->spt, -1);
+}
+
/**
* tdp_mmu_unlink_sp() - Remove a shadow page from the list of used pages
*
@@ -384,6 +394,7 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn,
static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp,
bool shared)
{
+ tdp_unaccount_mmu_page(kvm, sp);
if (shared)
spin_lock(&kvm->arch.tdp_mmu_pages_lock);
else
@@ -1132,6 +1143,7 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter,
if (account_nx)
account_huge_nx_page(kvm, sp);
spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
+ tdp_account_mmu_page(kvm, sp);
return 0;
}
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 76dcc8a3e849..4c620999d230 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -55,28 +55,6 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu,
nested_svm_vmexit(svm);
}
-static bool nested_svm_handle_page_fault_workaround(struct kvm_vcpu *vcpu,
- struct x86_exception *fault)
-{
- struct vcpu_svm *svm = to_svm(vcpu);
- struct vmcb *vmcb = svm->vmcb;
-
- WARN_ON(!is_guest_mode(vcpu));
-
- if (vmcb12_is_intercept(&svm->nested.ctl,
- INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) &&
- !WARN_ON_ONCE(svm->nested.nested_run_pending)) {
- vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + PF_VECTOR;
- vmcb->control.exit_code_hi = 0;
- vmcb->control.exit_info_1 = fault->error_code;
- vmcb->control.exit_info_2 = fault->address;
- nested_svm_vmexit(svm);
- return true;
- }
-
- return false;
-}
-
static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -468,7 +446,7 @@ static void nested_save_pending_event_to_vmcb12(struct vcpu_svm *svm,
unsigned int nr;
if (vcpu->arch.exception.injected) {
- nr = vcpu->arch.exception.nr;
+ nr = vcpu->arch.exception.vector;
exit_int_info = nr | SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_EXEPT;
if (vcpu->arch.exception.has_error_code) {
@@ -781,11 +759,15 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa,
struct vcpu_svm *svm = to_svm(vcpu);
int ret;
- trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb12_gpa,
- vmcb12->save.rip,
- vmcb12->control.int_ctl,
- vmcb12->control.event_inj,
- vmcb12->control.nested_ctl);
+ trace_kvm_nested_vmenter(svm->vmcb->save.rip,
+ vmcb12_gpa,
+ vmcb12->save.rip,
+ vmcb12->control.int_ctl,
+ vmcb12->control.event_inj,
+ vmcb12->control.nested_ctl,
+ vmcb12->control.nested_cr3,
+ vmcb12->save.cr3,
+ KVM_ISA_SVM);
trace_kvm_nested_intercepts(vmcb12->control.intercepts[INTERCEPT_CR] & 0xffff,
vmcb12->control.intercepts[INTERCEPT_CR] >> 16,
@@ -1304,44 +1286,46 @@ int nested_svm_check_permissions(struct kvm_vcpu *vcpu)
return 0;
}
-static bool nested_exit_on_exception(struct vcpu_svm *svm)
+static bool nested_svm_is_exception_vmexit(struct kvm_vcpu *vcpu, u8 vector,
+ u32 error_code)
{
- unsigned int nr = svm->vcpu.arch.exception.nr;
+ struct vcpu_svm *svm = to_svm(vcpu);
- return (svm->nested.ctl.intercepts[INTERCEPT_EXCEPTION] & BIT(nr));
+ return (svm->nested.ctl.intercepts[INTERCEPT_EXCEPTION] & BIT(vector));
}
-static void nested_svm_inject_exception_vmexit(struct vcpu_svm *svm)
+static void nested_svm_inject_exception_vmexit(struct kvm_vcpu *vcpu)
{
- unsigned int nr = svm->vcpu.arch.exception.nr;
+ struct kvm_queued_exception *ex = &vcpu->arch.exception_vmexit;
+ struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb *vmcb = svm->vmcb;
- vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr;
+ vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + ex->vector;
vmcb->control.exit_code_hi = 0;
- if (svm->vcpu.arch.exception.has_error_code)
- vmcb->control.exit_info_1 = svm->vcpu.arch.exception.error_code;
+ if (ex->has_error_code)
+ vmcb->control.exit_info_1 = ex->error_code;
/*
* EXITINFO2 is undefined for all exception intercepts other
* than #PF.
*/
- if (nr == PF_VECTOR) {
- if (svm->vcpu.arch.exception.nested_apf)
- vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token;
- else if (svm->vcpu.arch.exception.has_payload)
- vmcb->control.exit_info_2 = svm->vcpu.arch.exception.payload;
+ if (ex->vector == PF_VECTOR) {
+ if (ex->has_payload)
+ vmcb->control.exit_info_2 = ex->payload;
else
- vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
- } else if (nr == DB_VECTOR) {
- /* See inject_pending_event. */
- kvm_deliver_exception_payload(&svm->vcpu);
- if (svm->vcpu.arch.dr7 & DR7_GD) {
- svm->vcpu.arch.dr7 &= ~DR7_GD;
- kvm_update_dr7(&svm->vcpu);
+ vmcb->control.exit_info_2 = vcpu->arch.cr2;
+ } else if (ex->vector == DB_VECTOR) {
+ /* See kvm_check_and_inject_events(). */
+ kvm_deliver_exception_payload(vcpu, ex);
+
+ if (vcpu->arch.dr7 & DR7_GD) {
+ vcpu->arch.dr7 &= ~DR7_GD;
+ kvm_update_dr7(vcpu);
}
- } else
- WARN_ON(svm->vcpu.arch.exception.has_payload);
+ } else {
+ WARN_ON(ex->has_payload);
+ }
nested_svm_vmexit(svm);
}
@@ -1353,10 +1337,22 @@ static inline bool nested_exit_on_init(struct vcpu_svm *svm)
static int svm_check_nested_events(struct kvm_vcpu *vcpu)
{
- struct vcpu_svm *svm = to_svm(vcpu);
- bool block_nested_events =
- kvm_event_needs_reinjection(vcpu) || svm->nested.nested_run_pending;
struct kvm_lapic *apic = vcpu->arch.apic;
+ struct vcpu_svm *svm = to_svm(vcpu);
+ /*
+ * Only a pending nested run blocks a pending exception. If there is a
+ * previously injected event, the pending exception occurred while said
+ * event was being delivered and thus needs to be handled.
+ */
+ bool block_nested_exceptions = svm->nested.nested_run_pending;
+ /*
+ * New events (not exceptions) are only recognized at instruction
+ * boundaries. If an event needs reinjection, then KVM is handling a
+ * VM-Exit that occurred _during_ instruction execution; new events are
+ * blocked until the instruction completes.
+ */
+ bool block_nested_events = block_nested_exceptions ||
+ kvm_event_needs_reinjection(vcpu);
if (lapic_in_kernel(vcpu) &&
test_bit(KVM_APIC_INIT, &apic->pending_events)) {
@@ -1368,18 +1364,16 @@ static int svm_check_nested_events(struct kvm_vcpu *vcpu)
return 0;
}
- if (vcpu->arch.exception.pending) {
- /*
- * Only a pending nested run can block a pending exception.
- * Otherwise an injected NMI/interrupt should either be
- * lost or delivered to the nested hypervisor in the EXITINTINFO
- * vmcb field, while delivering the pending exception.
- */
- if (svm->nested.nested_run_pending)
+ if (vcpu->arch.exception_vmexit.pending) {
+ if (block_nested_exceptions)
return -EBUSY;
- if (!nested_exit_on_exception(svm))
- return 0;
- nested_svm_inject_exception_vmexit(svm);
+ nested_svm_inject_exception_vmexit(vcpu);
+ return 0;
+ }
+
+ if (vcpu->arch.exception.pending) {
+ if (block_nested_exceptions)
+ return -EBUSY;
return 0;
}
@@ -1720,8 +1714,8 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
struct kvm_x86_nested_ops svm_nested_ops = {
.leave_nested = svm_leave_nested,
+ .is_exception_vmexit = nested_svm_is_exception_vmexit,
.check_events = svm_check_nested_events,
- .handle_page_fault_workaround = nested_svm_handle_page_fault_workaround,
.triple_fault = nested_svm_triple_fault,
.get_nested_state_pages = svm_get_nested_state_pages,
.get_state = svm_get_nested_state,
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index f3813dbacb9f..58f0077d9357 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -461,24 +461,22 @@ static int svm_update_soft_interrupt_rip(struct kvm_vcpu *vcpu)
return 0;
}
-static void svm_queue_exception(struct kvm_vcpu *vcpu)
+static void svm_inject_exception(struct kvm_vcpu *vcpu)
{
+ struct kvm_queued_exception *ex = &vcpu->arch.exception;
struct vcpu_svm *svm = to_svm(vcpu);
- unsigned nr = vcpu->arch.exception.nr;
- bool has_error_code = vcpu->arch.exception.has_error_code;
- u32 error_code = vcpu->arch.exception.error_code;
- kvm_deliver_exception_payload(vcpu);
+ kvm_deliver_exception_payload(vcpu, ex);
- if (kvm_exception_is_soft(nr) &&
+ if (kvm_exception_is_soft(ex->vector) &&
svm_update_soft_interrupt_rip(vcpu))
return;
- svm->vmcb->control.event_inj = nr
+ svm->vmcb->control.event_inj = ex->vector
| SVM_EVTINJ_VALID
- | (has_error_code ? SVM_EVTINJ_VALID_ERR : 0)
+ | (ex->has_error_code ? SVM_EVTINJ_VALID_ERR : 0)
| SVM_EVTINJ_TYPE_EXEPT;
- svm->vmcb->control.event_inj_err = error_code;
+ svm->vmcb->control.event_inj_err = ex->error_code;
}
static void svm_init_erratum_383(void)
@@ -1975,7 +1973,7 @@ static int npf_interception(struct kvm_vcpu *vcpu)
u64 fault_address = svm->vmcb->control.exit_info_2;
u64 error_code = svm->vmcb->control.exit_info_1;
- trace_kvm_page_fault(fault_address, error_code);
+ trace_kvm_page_fault(vcpu, fault_address, error_code);
return kvm_mmu_page_fault(vcpu, fault_address, error_code,
static_cpu_has(X86_FEATURE_DECODEASSISTS) ?
svm->vmcb->control.insn_bytes : NULL,
@@ -2341,7 +2339,8 @@ void svm_set_gif(struct vcpu_svm *svm, bool value)
enable_gif(svm);
if (svm->vcpu.arch.smi_pending ||
svm->vcpu.arch.nmi_pending ||
- kvm_cpu_has_injectable_intr(&svm->vcpu))
+ kvm_cpu_has_injectable_intr(&svm->vcpu) ||
+ kvm_apic_has_pending_init_or_sipi(&svm->vcpu))
kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
} else {
disable_gif(svm);
@@ -3522,7 +3521,7 @@ void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode,
/* Note, this is called iff the local APIC is in-kernel. */
if (!READ_ONCE(vcpu->arch.apic->apicv_active)) {
- /* Process the interrupt via inject_pending_event */
+ /* Process the interrupt via kvm_check_and_inject_events(). */
kvm_make_request(KVM_REQ_EVENT, vcpu);
kvm_vcpu_kick(vcpu);
return;
@@ -4697,15 +4696,7 @@ static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- /*
- * TODO: Last condition latch INIT signals on vCPU when
- * vCPU is in guest-mode and vmcb12 defines intercept on INIT.
- * To properly emulate the INIT intercept,
- * svm_check_nested_events() should call nested_svm_vmexit()
- * if an INIT signal is pending.
- */
- return !gif_set(svm) ||
- (vmcb_is_intercept(&svm->vmcb->control, INTERCEPT_INIT));
+ return !gif_set(svm);
}
static void svm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
@@ -4798,7 +4789,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
.patch_hypercall = svm_patch_hypercall,
.inject_irq = svm_inject_irq,
.inject_nmi = svm_inject_nmi,
- .queue_exception = svm_queue_exception,
+ .inject_exception = svm_inject_exception,
.cancel_injection = svm_cancel_injection,
.interrupt_allowed = svm_interrupt_allowed,
.nmi_allowed = svm_nmi_allowed,
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 2120d7c060a9..bc25589ad588 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -394,20 +394,25 @@ TRACE_EVENT(kvm_inj_exception,
* Tracepoint for page fault.
*/
TRACE_EVENT(kvm_page_fault,
- TP_PROTO(unsigned long fault_address, unsigned int error_code),
- TP_ARGS(fault_address, error_code),
+ TP_PROTO(struct kvm_vcpu *vcpu, u64 fault_address, u64 error_code),
+ TP_ARGS(vcpu, fault_address, error_code),
TP_STRUCT__entry(
- __field( unsigned long, fault_address )
- __field( unsigned int, error_code )
+ __field( unsigned int, vcpu_id )
+ __field( unsigned long, guest_rip )
+ __field( u64, fault_address )
+ __field( u64, error_code )
),
TP_fast_assign(
+ __entry->vcpu_id = vcpu->vcpu_id;
+ __entry->guest_rip = kvm_rip_read(vcpu);
__entry->fault_address = fault_address;
__entry->error_code = error_code;
),
- TP_printk("address %lx error_code %x",
+ TP_printk("vcpu %u rip 0x%lx address 0x%016llx error_code 0x%llx",
+ __entry->vcpu_id, __entry->guest_rip,
__entry->fault_address, __entry->error_code)
);
@@ -589,10 +594,12 @@ TRACE_EVENT(kvm_pv_eoi,
/*
* Tracepoint for nested VMRUN
*/
-TRACE_EVENT(kvm_nested_vmrun,
+TRACE_EVENT(kvm_nested_vmenter,
TP_PROTO(__u64 rip, __u64 vmcb, __u64 nested_rip, __u32 int_ctl,
- __u32 event_inj, bool npt),
- TP_ARGS(rip, vmcb, nested_rip, int_ctl, event_inj, npt),
+ __u32 event_inj, bool tdp_enabled, __u64 guest_tdp_pgd,
+ __u64 guest_cr3, __u32 isa),
+ TP_ARGS(rip, vmcb, nested_rip, int_ctl, event_inj, tdp_enabled,
+ guest_tdp_pgd, guest_cr3, isa),
TP_STRUCT__entry(
__field( __u64, rip )
@@ -600,7 +607,9 @@ TRACE_EVENT(kvm_nested_vmrun,
__field( __u64, nested_rip )
__field( __u32, int_ctl )
__field( __u32, event_inj )
- __field( bool, npt )
+ __field( bool, tdp_enabled )
+ __field( __u64, guest_pgd )
+ __field( __u32, isa )
),
TP_fast_assign(
@@ -609,14 +618,24 @@ TRACE_EVENT(kvm_nested_vmrun,
__entry->nested_rip = nested_rip;
__entry->int_ctl = int_ctl;
__entry->event_inj = event_inj;
- __entry->npt = npt;
- ),
-
- TP_printk("rip: 0x%016llx vmcb: 0x%016llx nrip: 0x%016llx int_ctl: 0x%08x "
- "event_inj: 0x%08x npt: %s",
- __entry->rip, __entry->vmcb, __entry->nested_rip,
- __entry->int_ctl, __entry->event_inj,
- __entry->npt ? "on" : "off")
+ __entry->tdp_enabled = tdp_enabled;
+ __entry->guest_pgd = tdp_enabled ? guest_tdp_pgd : guest_cr3;
+ __entry->isa = isa;
+ ),
+
+ TP_printk("rip: 0x%016llx %s: 0x%016llx nested_rip: 0x%016llx "
+ "int_ctl: 0x%08x event_inj: 0x%08x nested_%s=%s %s: 0x%016llx",
+ __entry->rip,
+ __entry->isa == KVM_ISA_VMX ? "vmcs" : "vmcb",
+ __entry->vmcb,
+ __entry->nested_rip,
+ __entry->int_ctl,
+ __entry->event_inj,
+ __entry->isa == KVM_ISA_VMX ? "ept" : "npt",
+ __entry->tdp_enabled ? "y" : "n",
+ !__entry->tdp_enabled ? "guest_cr3" :
+ __entry->isa == KVM_ISA_VMX ? "nested_eptp" : "nested_cr3",
+ __entry->guest_pgd)
);
TRACE_EVENT(kvm_nested_intercepts,
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index c5e5dfef69c7..87c4e46daf37 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -65,6 +65,7 @@ struct vmcs_config {
u64 cpu_based_3rd_exec_ctrl;
u32 vmexit_ctrl;
u32 vmentry_ctrl;
+ u64 misc;
struct nested_vmx_msrs nested;
};
extern struct vmcs_config vmcs_config;
@@ -82,7 +83,8 @@ static inline bool cpu_has_vmx_basic_inout(void)
static inline bool cpu_has_virtual_nmis(void)
{
- return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS;
+ return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS &&
+ vmcs_config.cpu_based_exec_ctrl & CPU_BASED_NMI_WINDOW_EXITING;
}
static inline bool cpu_has_vmx_preemption_timer(void)
@@ -224,11 +226,8 @@ static inline bool cpu_has_vmx_vmfunc(void)
static inline bool cpu_has_vmx_shadow_vmcs(void)
{
- u64 vmx_msr;
-
/* check if the cpu supports writing r/o exit information fields */
- rdmsrl(MSR_IA32_VMX_MISC, vmx_msr);
- if (!(vmx_msr & MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS))
+ if (!(vmcs_config.misc & MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS))
return false;
return vmcs_config.cpu_based_2nd_exec_ctrl &
@@ -370,10 +369,7 @@ static inline bool cpu_has_vmx_invvpid_global(void)
static inline bool cpu_has_vmx_intel_pt(void)
{
- u64 vmx_msr;
-
- rdmsrl(MSR_IA32_VMX_MISC, vmx_msr);
- return (vmx_msr & MSR_IA32_VMX_MISC_INTEL_PT) &&
+ return (vmcs_config.misc & MSR_IA32_VMX_MISC_INTEL_PT) &&
(vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_PT_USE_GPA) &&
(vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_RTIT_CTL);
}
diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c
index 6a61b1ae7942..d8b23c96d627 100644
--- a/arch/x86/kvm/vmx/evmcs.c
+++ b/arch/x86/kvm/vmx/evmcs.c
@@ -10,6 +10,8 @@
#include "vmx.h"
#include "trace.h"
+#define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK
+
DEFINE_STATIC_KEY_FALSE(enable_evmcs);
#define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x)
@@ -28,6 +30,8 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = {
HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
EVMCS1_FIELD(HOST_IA32_EFER, host_ia32_efer,
HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+ EVMCS1_FIELD(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl,
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
EVMCS1_FIELD(HOST_CR0, host_cr0,
HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
EVMCS1_FIELD(HOST_CR3, host_cr3,
@@ -78,6 +82,8 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = {
HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
EVMCS1_FIELD(GUEST_IA32_EFER, guest_ia32_efer,
HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+ EVMCS1_FIELD(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl,
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
EVMCS1_FIELD(GUEST_PDPTR0, guest_pdptr0,
HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
EVMCS1_FIELD(GUEST_PDPTR1, guest_pdptr1,
@@ -126,6 +132,28 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = {
HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
EVMCS1_FIELD(XSS_EXIT_BITMAP, xss_exit_bitmap,
HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
+ EVMCS1_FIELD(ENCLS_EXITING_BITMAP, encls_exiting_bitmap,
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
+ EVMCS1_FIELD(TSC_MULTIPLIER, tsc_multiplier,
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2),
+ /*
+ * Not used by KVM:
+ *
+ * EVMCS1_FIELD(0x00006828, guest_ia32_s_cet,
+ * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+ * EVMCS1_FIELD(0x0000682A, guest_ssp,
+ * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC),
+ * EVMCS1_FIELD(0x0000682C, guest_ia32_int_ssp_table_addr,
+ * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+ * EVMCS1_FIELD(0x00002816, guest_ia32_lbr_ctl,
+ * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1),
+ * EVMCS1_FIELD(0x00006C18, host_ia32_s_cet,
+ * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+ * EVMCS1_FIELD(0x00006C1A, host_ssp,
+ * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+ * EVMCS1_FIELD(0x00006C1C, host_ia32_int_ssp_table_addr,
+ * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1),
+ */
/* 64 bit read only */
EVMCS1_FIELD(GUEST_PHYSICAL_ADDRESS, guest_physical_address,
@@ -294,19 +322,6 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = {
};
const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1);
-#if IS_ENABLED(CONFIG_HYPERV)
-__init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf)
-{
- vmcs_conf->cpu_based_exec_ctrl &= ~EVMCS1_UNSUPPORTED_EXEC_CTRL;
- vmcs_conf->pin_based_exec_ctrl &= ~EVMCS1_UNSUPPORTED_PINCTRL;
- vmcs_conf->cpu_based_2nd_exec_ctrl &= ~EVMCS1_UNSUPPORTED_2NDEXEC;
- vmcs_conf->cpu_based_3rd_exec_ctrl = 0;
-
- vmcs_conf->vmexit_ctrl &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
- vmcs_conf->vmentry_ctrl &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
-}
-#endif
-
bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa)
{
struct hv_vp_assist_page assist_page;
@@ -334,6 +349,9 @@ uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu)
* versions: lower 8 bits is the minimal version, higher 8 bits is the
* maximum supported version. KVM supports versions from 1 to
* KVM_EVMCS_VERSION.
+ *
+ * Note, do not check the Hyper-V is fully enabled in guest CPUID, this
+ * helper is used to _get_ the vCPU's supported CPUID.
*/
if (kvm_cpu_cap_get(X86_FEATURE_VMX) &&
(!vcpu || to_vmx(vcpu)->nested.enlightened_vmcs_enabled))
@@ -342,10 +360,67 @@ uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu)
return 0;
}
-void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata)
+enum evmcs_revision {
+ EVMCSv1_LEGACY,
+ NR_EVMCS_REVISIONS,
+};
+
+enum evmcs_ctrl_type {
+ EVMCS_EXIT_CTRLS,
+ EVMCS_ENTRY_CTRLS,
+ EVMCS_2NDEXEC,
+ EVMCS_PINCTRL,
+ EVMCS_VMFUNC,
+ NR_EVMCS_CTRLS,
+};
+
+static const u32 evmcs_unsupported_ctrls[NR_EVMCS_CTRLS][NR_EVMCS_REVISIONS] = {
+ [EVMCS_EXIT_CTRLS] = {
+ [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_VMEXIT_CTRL,
+ },
+ [EVMCS_ENTRY_CTRLS] = {
+ [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_VMENTRY_CTRL,
+ },
+ [EVMCS_2NDEXEC] = {
+ [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_2NDEXEC,
+ },
+ [EVMCS_PINCTRL] = {
+ [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_PINCTRL,
+ },
+ [EVMCS_VMFUNC] = {
+ [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_VMFUNC,
+ },
+};
+
+static u32 evmcs_get_unsupported_ctls(enum evmcs_ctrl_type ctrl_type)
+{
+ enum evmcs_revision evmcs_rev = EVMCSv1_LEGACY;
+
+ return evmcs_unsupported_ctrls[ctrl_type][evmcs_rev];
+}
+
+static bool evmcs_has_perf_global_ctrl(struct kvm_vcpu *vcpu)
+{
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+
+ /*
+ * PERF_GLOBAL_CTRL has a quirk where some Windows guests may fail to
+ * boot if a PV CPUID feature flag is not also set. Treat the fields
+ * as unsupported if the flag is not set in guest CPUID. This should
+ * be called only for guest accesses, and all guest accesses should be
+ * gated on Hyper-V being enabled and initialized.
+ */
+ if (WARN_ON_ONCE(!hv_vcpu))
+ return false;
+
+ return hv_vcpu->cpuid_cache.nested_ebx & HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL;
+}
+
+void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
{
u32 ctl_low = (u32)*pdata;
u32 ctl_high = (u32)(*pdata >> 32);
+ u32 unsupported_ctrls;
/*
* Hyper-V 2016 and 2019 try using these features even when eVMCS
@@ -354,77 +429,70 @@ void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata)
switch (msr_index) {
case MSR_IA32_VMX_EXIT_CTLS:
case MSR_IA32_VMX_TRUE_EXIT_CTLS:
- ctl_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
+ unsupported_ctrls = evmcs_get_unsupported_ctls(EVMCS_EXIT_CTRLS);
+ if (!evmcs_has_perf_global_ctrl(vcpu))
+ unsupported_ctrls |= VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
+ ctl_high &= ~unsupported_ctrls;
break;
case MSR_IA32_VMX_ENTRY_CTLS:
case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
- ctl_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
+ unsupported_ctrls = evmcs_get_unsupported_ctls(EVMCS_ENTRY_CTRLS);
+ if (!evmcs_has_perf_global_ctrl(vcpu))
+ unsupported_ctrls |= VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+ ctl_high &= ~unsupported_ctrls;
break;
case MSR_IA32_VMX_PROCBASED_CTLS2:
- ctl_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC;
+ ctl_high &= ~evmcs_get_unsupported_ctls(EVMCS_2NDEXEC);
break;
case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
case MSR_IA32_VMX_PINBASED_CTLS:
- ctl_high &= ~EVMCS1_UNSUPPORTED_PINCTRL;
+ ctl_high &= ~evmcs_get_unsupported_ctls(EVMCS_PINCTRL);
break;
case MSR_IA32_VMX_VMFUNC:
- ctl_low &= ~EVMCS1_UNSUPPORTED_VMFUNC;
+ ctl_low &= ~evmcs_get_unsupported_ctls(EVMCS_VMFUNC);
break;
}
*pdata = ctl_low | ((u64)ctl_high << 32);
}
+static bool nested_evmcs_is_valid_controls(enum evmcs_ctrl_type ctrl_type,
+ u32 val)
+{
+ return !(val & evmcs_get_unsupported_ctls(ctrl_type));
+}
+
int nested_evmcs_check_controls(struct vmcs12 *vmcs12)
{
- int ret = 0;
- u32 unsupp_ctl;
-
- unsupp_ctl = vmcs12->pin_based_vm_exec_control &
- EVMCS1_UNSUPPORTED_PINCTRL;
- if (unsupp_ctl) {
- trace_kvm_nested_vmenter_failed(
- "eVMCS: unsupported pin-based VM-execution controls",
- unsupp_ctl);
- ret = -EINVAL;
- }
+ if (CC(!nested_evmcs_is_valid_controls(EVMCS_PINCTRL,
+ vmcs12->pin_based_vm_exec_control)))
+ return -EINVAL;
- unsupp_ctl = vmcs12->secondary_vm_exec_control &
- EVMCS1_UNSUPPORTED_2NDEXEC;
- if (unsupp_ctl) {
- trace_kvm_nested_vmenter_failed(
- "eVMCS: unsupported secondary VM-execution controls",
- unsupp_ctl);
- ret = -EINVAL;
- }
+ if (CC(!nested_evmcs_is_valid_controls(EVMCS_2NDEXEC,
+ vmcs12->secondary_vm_exec_control)))
+ return -EINVAL;
- unsupp_ctl = vmcs12->vm_exit_controls &
- EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
- if (unsupp_ctl) {
- trace_kvm_nested_vmenter_failed(
- "eVMCS: unsupported VM-exit controls",
- unsupp_ctl);
- ret = -EINVAL;
- }
+ if (CC(!nested_evmcs_is_valid_controls(EVMCS_EXIT_CTRLS,
+ vmcs12->vm_exit_controls)))
+ return -EINVAL;
- unsupp_ctl = vmcs12->vm_entry_controls &
- EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
- if (unsupp_ctl) {
- trace_kvm_nested_vmenter_failed(
- "eVMCS: unsupported VM-entry controls",
- unsupp_ctl);
- ret = -EINVAL;
- }
+ if (CC(!nested_evmcs_is_valid_controls(EVMCS_ENTRY_CTRLS,
+ vmcs12->vm_entry_controls)))
+ return -EINVAL;
- unsupp_ctl = vmcs12->vm_function_control & EVMCS1_UNSUPPORTED_VMFUNC;
- if (unsupp_ctl) {
- trace_kvm_nested_vmenter_failed(
- "eVMCS: unsupported VM-function controls",
- unsupp_ctl);
- ret = -EINVAL;
- }
+ /*
+ * VM-Func controls are 64-bit, but KVM currently doesn't support any
+ * controls in bits 63:32, i.e. dropping those bits on the consistency
+ * check is intentional.
+ */
+ if (WARN_ON_ONCE(vmcs12->vm_function_control >> 32))
+ return -EINVAL;
- return ret;
+ if (CC(!nested_evmcs_is_valid_controls(EVMCS_VMFUNC,
+ vmcs12->vm_function_control)))
+ return -EINVAL;
+
+ return 0;
}
int nested_enable_evmcs(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h
index f886a8ff0342..6f746ef3c038 100644
--- a/arch/x86/kvm/vmx/evmcs.h
+++ b/arch/x86/kvm/vmx/evmcs.h
@@ -42,8 +42,6 @@ DECLARE_STATIC_KEY_FALSE(enable_evmcs);
* PLE_GAP = 0x00004020,
* PLE_WINDOW = 0x00004022,
* VMX_PREEMPTION_TIMER_VALUE = 0x0000482E,
- * GUEST_IA32_PERF_GLOBAL_CTRL = 0x00002808,
- * HOST_IA32_PERF_GLOBAL_CTRL = 0x00002c04,
*
* Currently unsupported in KVM:
* GUEST_IA32_RTIT_CTL = 0x00002814,
@@ -61,9 +59,8 @@ DECLARE_STATIC_KEY_FALSE(enable_evmcs);
SECONDARY_EXEC_TSC_SCALING | \
SECONDARY_EXEC_PAUSE_LOOP_EXITING)
#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL \
- (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \
- VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)
-#define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
+ (VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)
+#define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (0)
#define EVMCS1_UNSUPPORTED_VMFUNC (VMX_VMFUNC_EPTP_SWITCHING)
struct evmcs_field {
@@ -212,7 +209,6 @@ static inline void evmcs_load(u64 phys_addr)
vp_ap->enlighten_vmentry = 1;
}
-__init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf);
#else /* !IS_ENABLED(CONFIG_HYPERV) */
static __always_inline void evmcs_write64(unsigned long field, u64 value) {}
static inline void evmcs_write32(unsigned long field, u32 value) {}
@@ -243,7 +239,7 @@ bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa);
uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu);
int nested_enable_evmcs(struct kvm_vcpu *vcpu,
uint16_t *vmcs_version);
-void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata);
+void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
int nested_evmcs_check_controls(struct vmcs12 *vmcs12);
#endif /* __KVM_X86_VMX_EVMCS_H */
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 7eaf96064cb0..0c62352dda6a 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -439,61 +439,22 @@ static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12,
return inequality ^ bit;
}
-
-/*
- * KVM wants to inject page-faults which it got to the guest. This function
- * checks whether in a nested guest, we need to inject them to L1 or L2.
- */
-static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned long *exit_qual)
+static bool nested_vmx_is_exception_vmexit(struct kvm_vcpu *vcpu, u8 vector,
+ u32 error_code)
{
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
- unsigned int nr = vcpu->arch.exception.nr;
- bool has_payload = vcpu->arch.exception.has_payload;
- unsigned long payload = vcpu->arch.exception.payload;
-
- if (nr == PF_VECTOR) {
- if (vcpu->arch.exception.nested_apf) {
- *exit_qual = vcpu->arch.apf.nested_apf_token;
- return 1;
- }
- if (nested_vmx_is_page_fault_vmexit(vmcs12,
- vcpu->arch.exception.error_code)) {
- *exit_qual = has_payload ? payload : vcpu->arch.cr2;
- return 1;
- }
- } else if (vmcs12->exception_bitmap & (1u << nr)) {
- if (nr == DB_VECTOR) {
- if (!has_payload) {
- payload = vcpu->arch.dr6;
- payload &= ~DR6_BT;
- payload ^= DR6_ACTIVE_LOW;
- }
- *exit_qual = payload;
- } else
- *exit_qual = 0;
- return 1;
- }
- return 0;
-}
-
-static bool nested_vmx_handle_page_fault_workaround(struct kvm_vcpu *vcpu,
- struct x86_exception *fault)
-{
- struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-
- WARN_ON(!is_guest_mode(vcpu));
+ /*
+ * Drop bits 31:16 of the error code when performing the #PF mask+match
+ * check. All VMCS fields involved are 32 bits, but Intel CPUs never
+ * set bits 31:16 and VMX disallows setting bits 31:16 in the injected
+ * error code. Including the to-be-dropped bits in the check might
+ * result in an "impossible" or missed exit from L1's perspective.
+ */
+ if (vector == PF_VECTOR)
+ return nested_vmx_is_page_fault_vmexit(vmcs12, (u16)error_code);
- if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) &&
- !WARN_ON_ONCE(to_vmx(vcpu)->nested.nested_run_pending)) {
- vmcs12->vm_exit_intr_error_code = fault->error_code;
- nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
- PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
- INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK,
- fault->address);
- return true;
- }
- return false;
+ return (vmcs12->exception_bitmap & (1u << vector));
}
static int nested_vmx_check_io_bitmap_controls(struct kvm_vcpu *vcpu,
@@ -1607,6 +1568,10 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields
vmcs12->guest_rflags = evmcs->guest_rflags;
vmcs12->guest_interruptibility_info =
evmcs->guest_interruptibility_info;
+ /*
+ * Not present in struct vmcs12:
+ * vmcs12->guest_ssp = evmcs->guest_ssp;
+ */
}
if (unlikely(!(hv_clean_fields &
@@ -1653,6 +1618,13 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields
vmcs12->host_fs_selector = evmcs->host_fs_selector;
vmcs12->host_gs_selector = evmcs->host_gs_selector;
vmcs12->host_tr_selector = evmcs->host_tr_selector;
+ vmcs12->host_ia32_perf_global_ctrl = evmcs->host_ia32_perf_global_ctrl;
+ /*
+ * Not present in struct vmcs12:
+ * vmcs12->host_ia32_s_cet = evmcs->host_ia32_s_cet;
+ * vmcs12->host_ssp = evmcs->host_ssp;
+ * vmcs12->host_ia32_int_ssp_table_addr = evmcs->host_ia32_int_ssp_table_addr;
+ */
}
if (unlikely(!(hv_clean_fields &
@@ -1720,6 +1692,8 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields
vmcs12->tsc_offset = evmcs->tsc_offset;
vmcs12->virtual_apic_page_addr = evmcs->virtual_apic_page_addr;
vmcs12->xss_exit_bitmap = evmcs->xss_exit_bitmap;
+ vmcs12->encls_exiting_bitmap = evmcs->encls_exiting_bitmap;
+ vmcs12->tsc_multiplier = evmcs->tsc_multiplier;
}
if (unlikely(!(hv_clean_fields &
@@ -1767,6 +1741,13 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields
vmcs12->guest_bndcfgs = evmcs->guest_bndcfgs;
vmcs12->guest_activity_state = evmcs->guest_activity_state;
vmcs12->guest_sysenter_cs = evmcs->guest_sysenter_cs;
+ vmcs12->guest_ia32_perf_global_ctrl = evmcs->guest_ia32_perf_global_ctrl;
+ /*
+ * Not present in struct vmcs12:
+ * vmcs12->guest_ia32_s_cet = evmcs->guest_ia32_s_cet;
+ * vmcs12->guest_ia32_lbr_ctl = evmcs->guest_ia32_lbr_ctl;
+ * vmcs12->guest_ia32_int_ssp_table_addr = evmcs->guest_ia32_int_ssp_table_addr;
+ */
}
/*
@@ -1869,12 +1850,23 @@ static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx)
* evmcs->vm_exit_msr_store_count = vmcs12->vm_exit_msr_store_count;
* evmcs->vm_exit_msr_load_count = vmcs12->vm_exit_msr_load_count;
* evmcs->vm_entry_msr_load_count = vmcs12->vm_entry_msr_load_count;
+ * evmcs->guest_ia32_perf_global_ctrl = vmcs12->guest_ia32_perf_global_ctrl;
+ * evmcs->host_ia32_perf_global_ctrl = vmcs12->host_ia32_perf_global_ctrl;
+ * evmcs->encls_exiting_bitmap = vmcs12->encls_exiting_bitmap;
+ * evmcs->tsc_multiplier = vmcs12->tsc_multiplier;
*
* Not present in struct vmcs12:
* evmcs->exit_io_instruction_ecx = vmcs12->exit_io_instruction_ecx;
* evmcs->exit_io_instruction_esi = vmcs12->exit_io_instruction_esi;
* evmcs->exit_io_instruction_edi = vmcs12->exit_io_instruction_edi;
* evmcs->exit_io_instruction_eip = vmcs12->exit_io_instruction_eip;
+ * evmcs->host_ia32_s_cet = vmcs12->host_ia32_s_cet;
+ * evmcs->host_ssp = vmcs12->host_ssp;
+ * evmcs->host_ia32_int_ssp_table_addr = vmcs12->host_ia32_int_ssp_table_addr;
+ * evmcs->guest_ia32_s_cet = vmcs12->guest_ia32_s_cet;
+ * evmcs->guest_ia32_lbr_ctl = vmcs12->guest_ia32_lbr_ctl;
+ * evmcs->guest_ia32_int_ssp_table_addr = vmcs12->guest_ia32_int_ssp_table_addr;
+ * evmcs->guest_ssp = vmcs12->guest_ssp;
*/
evmcs->guest_es_selector = vmcs12->guest_es_selector;
@@ -1982,7 +1974,7 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld(
bool evmcs_gpa_changed = false;
u64 evmcs_gpa;
- if (likely(!vmx->nested.enlightened_vmcs_enabled))
+ if (likely(!guest_cpuid_has_evmcs(vcpu)))
return EVMPTRLD_DISABLED;
if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa)) {
@@ -2328,9 +2320,14 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0
* are emulated by vmx_set_efer() in prepare_vmcs02(), but speculate
* on the related bits (if supported by the CPU) in the hope that
* we can avoid VMWrites during vmx_set_efer().
+ *
+ * Similarly, take vmcs01's PERF_GLOBAL_CTRL in the hope that if KVM is
+ * loading PERF_GLOBAL_CTRL via the VMCS for L1, then KVM will want to
+ * do the same for L2.
*/
exec_control = __vm_entry_controls_get(vmcs01);
- exec_control |= vmcs12->vm_entry_controls;
+ exec_control |= (vmcs12->vm_entry_controls &
+ ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL);
exec_control &= ~(VM_ENTRY_IA32E_MODE | VM_ENTRY_LOAD_IA32_EFER);
if (cpu_has_load_ia32_efer()) {
if (guest_efer & EFER_LMA)
@@ -2863,7 +2860,7 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu,
nested_check_vm_entry_controls(vcpu, vmcs12))
return -EINVAL;
- if (to_vmx(vcpu)->nested.enlightened_vmcs_enabled)
+ if (guest_cpuid_has_evmcs(vcpu))
return nested_evmcs_check_controls(vmcs12);
return 0;
@@ -3145,7 +3142,7 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu)
* L2 was running), map it here to make sure vmcs12 changes are
* properly reflected.
*/
- if (vmx->nested.enlightened_vmcs_enabled &&
+ if (guest_cpuid_has_evmcs(vcpu) &&
vmx->nested.hv_evmcs_vmptr == EVMPTR_MAP_PENDING) {
enum nested_evmptrld_status evmptrld_status =
nested_vmx_handle_enlightened_vmptrld(vcpu, false);
@@ -3364,12 +3361,24 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
};
u32 failed_index;
+ trace_kvm_nested_vmenter(kvm_rip_read(vcpu),
+ vmx->nested.current_vmptr,
+ vmcs12->guest_rip,
+ vmcs12->guest_intr_status,
+ vmcs12->vm_entry_intr_info_field,
+ vmcs12->secondary_vm_exec_control & SECONDARY_EXEC_ENABLE_EPT,
+ vmcs12->ept_pointer,
+ vmcs12->guest_cr3,
+ KVM_ISA_VMX);
+
kvm_service_local_tlb_flush_requests(vcpu);
evaluate_pending_interrupts = exec_controls_get(vmx) &
(CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING);
if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu))
evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu);
+ if (!evaluate_pending_interrupts)
+ evaluate_pending_interrupts |= kvm_apic_has_pending_init_or_sipi(vcpu);
if (!vmx->nested.nested_run_pending ||
!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
@@ -3450,18 +3459,10 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
}
/*
- * If L1 had a pending IRQ/NMI until it executed
- * VMLAUNCH/VMRESUME which wasn't delivered because it was
- * disallowed (e.g. interrupts disabled), L0 needs to
- * evaluate if this pending event should cause an exit from L2
- * to L1 or delivered directly to L2 (e.g. In case L1 don't
- * intercept EXTERNAL_INTERRUPT).
- *
- * Usually this would be handled by the processor noticing an
- * IRQ/NMI window request, or checking RVI during evaluation of
- * pending virtual interrupts. However, this setting was done
- * on VMCS01 and now VMCS02 is active instead. Thus, we force L0
- * to perform pending event evaluation by requesting a KVM_REQ_EVENT.
+ * Re-evaluate pending events if L1 had a pending IRQ/NMI/INIT/SIPI
+ * when it executed VMLAUNCH/VMRESUME, as entering non-root mode can
+ * effectively unblock various events, e.g. INIT/SIPI cause VM-Exit
+ * unconditionally.
*/
if (unlikely(evaluate_pending_interrupts))
kvm_make_request(KVM_REQ_EVENT, vcpu);
@@ -3718,7 +3719,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu,
is_double_fault(exit_intr_info))) {
vmcs12->idt_vectoring_info_field = 0;
} else if (vcpu->arch.exception.injected) {
- nr = vcpu->arch.exception.nr;
+ nr = vcpu->arch.exception.vector;
idt_vectoring = nr | VECTORING_INFO_VALID_MASK;
if (kvm_exception_is_soft(nr)) {
@@ -3819,19 +3820,40 @@ mmio_needed:
return -ENXIO;
}
-static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu,
- unsigned long exit_qual)
+static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu)
{
+ struct kvm_queued_exception *ex = &vcpu->arch.exception_vmexit;
+ u32 intr_info = ex->vector | INTR_INFO_VALID_MASK;
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
- unsigned int nr = vcpu->arch.exception.nr;
- u32 intr_info = nr | INTR_INFO_VALID_MASK;
+ unsigned long exit_qual;
+
+ if (ex->has_payload) {
+ exit_qual = ex->payload;
+ } else if (ex->vector == PF_VECTOR) {
+ exit_qual = vcpu->arch.cr2;
+ } else if (ex->vector == DB_VECTOR) {
+ exit_qual = vcpu->arch.dr6;
+ exit_qual &= ~DR6_BT;
+ exit_qual ^= DR6_ACTIVE_LOW;
+ } else {
+ exit_qual = 0;
+ }
- if (vcpu->arch.exception.has_error_code) {
- vmcs12->vm_exit_intr_error_code = vcpu->arch.exception.error_code;
+ if (ex->has_error_code) {
+ /*
+ * Intel CPUs do not generate error codes with bits 31:16 set,
+ * and more importantly VMX disallows setting bits 31:16 in the
+ * injected error code for VM-Entry. Drop the bits to mimic
+ * hardware and avoid inducing failure on nested VM-Entry if L1
+ * chooses to inject the exception back to L2. AMD CPUs _do_
+ * generate "full" 32-bit error codes, so KVM allows userspace
+ * to inject exception error codes with bits 31:16 set.
+ */
+ vmcs12->vm_exit_intr_error_code = (u16)ex->error_code;
intr_info |= INTR_INFO_DELIVER_CODE_MASK;
}
- if (kvm_exception_is_soft(nr))
+ if (kvm_exception_is_soft(ex->vector))
intr_info |= INTR_TYPE_SOFT_EXCEPTION;
else
intr_info |= INTR_TYPE_HARD_EXCEPTION;
@@ -3844,16 +3866,39 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu,
}
/*
- * Returns true if a debug trap is pending delivery.
+ * Returns true if a debug trap is (likely) pending delivery. Infer the class
+ * of a #DB (trap-like vs. fault-like) from the exception payload (to-be-DR6).
+ * Using the payload is flawed because code breakpoints (fault-like) and data
+ * breakpoints (trap-like) set the same bits in DR6 (breakpoint detected), i.e.
+ * this will return false positives if a to-be-injected code breakpoint #DB is
+ * pending (from KVM's perspective, but not "pending" across an instruction
+ * boundary). ICEBP, a.k.a. INT1, is also not reflected here even though it
+ * too is trap-like.
*
- * In KVM, debug traps bear an exception payload. As such, the class of a #DB
- * exception may be inferred from the presence of an exception payload.
+ * KVM "works" despite these flaws as ICEBP isn't currently supported by the
+ * emulator, Monitor Trap Flag is not marked pending on intercepted #DBs (the
+ * #DB has already happened), and MTF isn't marked pending on code breakpoints
+ * from the emulator (because such #DBs are fault-like and thus don't trigger
+ * actions that fire on instruction retire).
+ */
+static unsigned long vmx_get_pending_dbg_trap(struct kvm_queued_exception *ex)
+{
+ if (!ex->pending || ex->vector != DB_VECTOR)
+ return 0;
+
+ /* General Detect #DBs are always fault-like. */
+ return ex->payload & ~DR6_BD;
+}
+
+/*
+ * Returns true if there's a pending #DB exception that is lower priority than
+ * a pending Monitor Trap Flag VM-Exit. TSS T-flag #DBs are not emulated by
+ * KVM, but could theoretically be injected by userspace. Note, this code is
+ * imperfect, see above.
*/
-static inline bool vmx_pending_dbg_trap(struct kvm_vcpu *vcpu)
+static bool vmx_is_low_priority_db_trap(struct kvm_queued_exception *ex)
{
- return vcpu->arch.exception.pending &&
- vcpu->arch.exception.nr == DB_VECTOR &&
- vcpu->arch.exception.payload;
+ return vmx_get_pending_dbg_trap(ex) & ~DR6_BT;
}
/*
@@ -3865,9 +3910,11 @@ static inline bool vmx_pending_dbg_trap(struct kvm_vcpu *vcpu)
*/
static void nested_vmx_update_pending_dbg(struct kvm_vcpu *vcpu)
{
- if (vmx_pending_dbg_trap(vcpu))
- vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
- vcpu->arch.exception.payload);
+ unsigned long pending_dbg;
+
+ pending_dbg = vmx_get_pending_dbg_trap(&vcpu->arch.exception);
+ if (pending_dbg)
+ vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, pending_dbg);
}
static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu)
@@ -3876,21 +3923,113 @@ static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu)
to_vmx(vcpu)->nested.preemption_timer_expired;
}
+static bool vmx_has_nested_events(struct kvm_vcpu *vcpu)
+{
+ return nested_vmx_preemption_timer_pending(vcpu) ||
+ to_vmx(vcpu)->nested.mtf_pending;
+}
+
+/*
+ * Per the Intel SDM's table "Priority Among Concurrent Events", with minor
+ * edits to fill in missing examples, e.g. #DB due to split-lock accesses,
+ * and less minor edits to splice in the priority of VMX Non-Root specific
+ * events, e.g. MTF and NMI/INTR-window exiting.
+ *
+ * 1 Hardware Reset and Machine Checks
+ * - RESET
+ * - Machine Check
+ *
+ * 2 Trap on Task Switch
+ * - T flag in TSS is set (on task switch)
+ *
+ * 3 External Hardware Interventions
+ * - FLUSH
+ * - STOPCLK
+ * - SMI
+ * - INIT
+ *
+ * 3.5 Monitor Trap Flag (MTF) VM-exit[1]
+ *
+ * 4 Traps on Previous Instruction
+ * - Breakpoints
+ * - Trap-class Debug Exceptions (#DB due to TF flag set, data/I-O
+ * breakpoint, or #DB due to a split-lock access)
+ *
+ * 4.3 VMX-preemption timer expired VM-exit
+ *
+ * 4.6 NMI-window exiting VM-exit[2]
+ *
+ * 5 Nonmaskable Interrupts (NMI)
+ *
+ * 5.5 Interrupt-window exiting VM-exit and Virtual-interrupt delivery
+ *
+ * 6 Maskable Hardware Interrupts
+ *
+ * 7 Code Breakpoint Fault
+ *
+ * 8 Faults from Fetching Next Instruction
+ * - Code-Segment Limit Violation
+ * - Code Page Fault
+ * - Control protection exception (missing ENDBRANCH at target of indirect
+ * call or jump)
+ *
+ * 9 Faults from Decoding Next Instruction
+ * - Instruction length > 15 bytes
+ * - Invalid Opcode
+ * - Coprocessor Not Available
+ *
+ *10 Faults on Executing Instruction
+ * - Overflow
+ * - Bound error
+ * - Invalid TSS
+ * - Segment Not Present
+ * - Stack fault
+ * - General Protection
+ * - Data Page Fault
+ * - Alignment Check
+ * - x86 FPU Floating-point exception
+ * - SIMD floating-point exception
+ * - Virtualization exception
+ * - Control protection exception
+ *
+ * [1] Per the "Monitor Trap Flag" section: System-management interrupts (SMIs),
+ * INIT signals, and higher priority events take priority over MTF VM exits.
+ * MTF VM exits take priority over debug-trap exceptions and lower priority
+ * events.
+ *
+ * [2] Debug-trap exceptions and higher priority events take priority over VM exits
+ * caused by the VMX-preemption timer. VM exits caused by the VMX-preemption
+ * timer take priority over VM exits caused by the "NMI-window exiting"
+ * VM-execution control and lower priority events.
+ *
+ * [3] Debug-trap exceptions and higher priority events take priority over VM exits
+ * caused by "NMI-window exiting". VM exits caused by this control take
+ * priority over non-maskable interrupts (NMIs) and lower priority events.
+ *
+ * [4] Virtual-interrupt delivery has the same priority as that of VM exits due to
+ * the 1-setting of the "interrupt-window exiting" VM-execution control. Thus,
+ * non-maskable interrupts (NMIs) and higher priority events take priority over
+ * delivery of a virtual interrupt; delivery of a virtual interrupt takes
+ * priority over external interrupts and lower priority events.
+ */
static int vmx_check_nested_events(struct kvm_vcpu *vcpu)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- unsigned long exit_qual;
- bool block_nested_events =
- vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu);
- bool mtf_pending = vmx->nested.mtf_pending;
struct kvm_lapic *apic = vcpu->arch.apic;
-
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
/*
- * Clear the MTF state. If a higher priority VM-exit is delivered first,
- * this state is discarded.
+ * Only a pending nested run blocks a pending exception. If there is a
+ * previously injected event, the pending exception occurred while said
+ * event was being delivered and thus needs to be handled.
*/
- if (!block_nested_events)
- vmx->nested.mtf_pending = false;
+ bool block_nested_exceptions = vmx->nested.nested_run_pending;
+ /*
+ * New events (not exceptions) are only recognized at instruction
+ * boundaries. If an event needs reinjection, then KVM is handling a
+ * VM-Exit that occurred _during_ instruction execution; new events are
+ * blocked until the instruction completes.
+ */
+ bool block_nested_events = block_nested_exceptions ||
+ kvm_event_needs_reinjection(vcpu);
if (lapic_in_kernel(vcpu) &&
test_bit(KVM_APIC_INIT, &apic->pending_events)) {
@@ -3900,6 +4039,9 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu)
clear_bit(KVM_APIC_INIT, &apic->pending_events);
if (vcpu->arch.mp_state != KVM_MP_STATE_INIT_RECEIVED)
nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0);
+
+ /* MTF is discarded if the vCPU is in WFS. */
+ vmx->nested.mtf_pending = false;
return 0;
}
@@ -3909,31 +4051,41 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu)
return -EBUSY;
clear_bit(KVM_APIC_SIPI, &apic->pending_events);
- if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED)
+ if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
nested_vmx_vmexit(vcpu, EXIT_REASON_SIPI_SIGNAL, 0,
apic->sipi_vector & 0xFFUL);
- return 0;
+ return 0;
+ }
+ /* Fallthrough, the SIPI is completely ignored. */
}
/*
- * Process any exceptions that are not debug traps before MTF.
+ * Process exceptions that are higher priority than Monitor Trap Flag:
+ * fault-like exceptions, TSS T flag #DB (not emulated by KVM, but
+ * could theoretically come in from userspace), and ICEBP (INT1).
*
- * Note that only a pending nested run can block a pending exception.
- * Otherwise an injected NMI/interrupt should either be
- * lost or delivered to the nested hypervisor in the IDT_VECTORING_INFO,
- * while delivering the pending exception.
+ * TODO: SMIs have higher priority than MTF and trap-like #DBs (except
+ * for TSS T flag #DBs). KVM also doesn't save/restore pending MTF
+ * across SMI/RSM as it should; that needs to be addressed in order to
+ * prioritize SMI over MTF and trap-like #DBs.
*/
-
- if (vcpu->arch.exception.pending && !vmx_pending_dbg_trap(vcpu)) {
- if (vmx->nested.nested_run_pending)
+ if (vcpu->arch.exception_vmexit.pending &&
+ !vmx_is_low_priority_db_trap(&vcpu->arch.exception_vmexit)) {
+ if (block_nested_exceptions)
return -EBUSY;
- if (!nested_vmx_check_exception(vcpu, &exit_qual))
- goto no_vmexit;
- nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
+
+ nested_vmx_inject_exception_vmexit(vcpu);
return 0;
}
- if (mtf_pending) {
+ if (vcpu->arch.exception.pending &&
+ !vmx_is_low_priority_db_trap(&vcpu->arch.exception)) {
+ if (block_nested_exceptions)
+ return -EBUSY;
+ goto no_vmexit;
+ }
+
+ if (vmx->nested.mtf_pending) {
if (block_nested_events)
return -EBUSY;
nested_vmx_update_pending_dbg(vcpu);
@@ -3941,15 +4093,20 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu)
return 0;
}
- if (vcpu->arch.exception.pending) {
- if (vmx->nested.nested_run_pending)
+ if (vcpu->arch.exception_vmexit.pending) {
+ if (block_nested_exceptions)
return -EBUSY;
- if (!nested_vmx_check_exception(vcpu, &exit_qual))
- goto no_vmexit;
- nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
+
+ nested_vmx_inject_exception_vmexit(vcpu);
return 0;
}
+ if (vcpu->arch.exception.pending) {
+ if (block_nested_exceptions)
+ return -EBUSY;
+ goto no_vmexit;
+ }
+
if (nested_vmx_preemption_timer_pending(vcpu)) {
if (block_nested_events)
return -EBUSY;
@@ -4255,14 +4412,6 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
nested_vmx_abort(vcpu,
VMX_ABORT_SAVE_GUEST_MSR_FAIL);
}
-
- /*
- * Drop what we picked up for L2 via vmx_complete_interrupts. It is
- * preserved above and would only end up incorrectly in L1.
- */
- vcpu->arch.nmi_injected = false;
- kvm_clear_exception_queue(vcpu);
- kvm_clear_interrupt_queue(vcpu);
}
/*
@@ -4538,6 +4687,9 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ /* Pending MTF traps are discarded on VM-Exit. */
+ vmx->nested.mtf_pending = false;
+
/* trying to cancel vmlaunch/vmresume is a bug */
WARN_ON_ONCE(vmx->nested.nested_run_pending);
@@ -4602,6 +4754,17 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
WARN_ON_ONCE(nested_early_check);
}
+ /*
+ * Drop events/exceptions that were queued for re-injection to L2
+ * (picked up via vmx_complete_interrupts()), as well as exceptions
+ * that were pending for L2. Note, this must NOT be hoisted above
+ * prepare_vmcs12(), events/exceptions queued for re-injection need to
+ * be captured in vmcs12 (see vmcs12_save_pending_event()).
+ */
+ vcpu->arch.nmi_injected = false;
+ kvm_clear_exception_queue(vcpu);
+ kvm_clear_interrupt_queue(vcpu);
+
vmx_switch_vmcs(vcpu, &vmx->vmcs01);
/* Update any VMCS fields that might have changed while L2 ran */
@@ -5030,8 +5193,8 @@ static int handle_vmxoff(struct kvm_vcpu *vcpu)
free_nested(vcpu);
- /* Process a latched INIT during time CPU was in VMX operation */
- kvm_make_request(KVM_REQ_EVENT, vcpu);
+ if (kvm_apic_has_pending_init_or_sipi(vcpu))
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
return nested_vmx_succeed(vcpu);
}
@@ -5067,7 +5230,7 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
* state. It is possible that the area will stay mapped as
* vmx->nested.hv_evmcs but this shouldn't be a problem.
*/
- if (likely(!vmx->nested.enlightened_vmcs_enabled ||
+ if (likely(!guest_cpuid_has_evmcs(vcpu) ||
!nested_enlightened_vmentry(vcpu, &evmcs_gpa))) {
if (vmptr == vmx->nested.current_vmptr)
nested_release_vmcs12(vcpu);
@@ -6463,6 +6626,9 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
if (ret)
goto error_guest_mode;
+ if (vmx->nested.mtf_pending)
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+
return 0;
error_guest_mode:
@@ -6522,8 +6688,10 @@ static u64 nested_vmx_calc_vmcs_enum_msr(void)
* bit in the high half is on if the corresponding bit in the control field
* may be on. See also vmx_control_verify().
*/
-void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
+void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps)
{
+ struct nested_vmx_msrs *msrs = &vmcs_conf->nested;
+
/*
* Note that as a general rule, the high half of the MSRs (bits in
* the control fields which may be 1) should be initialized by the
@@ -6540,11 +6708,10 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
*/
/* pin-based controls */
- rdmsr(MSR_IA32_VMX_PINBASED_CTLS,
- msrs->pinbased_ctls_low,
- msrs->pinbased_ctls_high);
- msrs->pinbased_ctls_low |=
+ msrs->pinbased_ctls_low =
PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
+
+ msrs->pinbased_ctls_high = vmcs_conf->pin_based_exec_ctrl;
msrs->pinbased_ctls_high &=
PIN_BASED_EXT_INTR_MASK |
PIN_BASED_NMI_EXITING |
@@ -6555,50 +6722,47 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
PIN_BASED_VMX_PREEMPTION_TIMER;
/* exit controls */
- rdmsr(MSR_IA32_VMX_EXIT_CTLS,
- msrs->exit_ctls_low,
- msrs->exit_ctls_high);
msrs->exit_ctls_low =
VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
+ msrs->exit_ctls_high = vmcs_conf->vmexit_ctrl;
msrs->exit_ctls_high &=
#ifdef CONFIG_X86_64
VM_EXIT_HOST_ADDR_SPACE_SIZE |
#endif
VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT |
- VM_EXIT_CLEAR_BNDCFGS | VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
+ VM_EXIT_CLEAR_BNDCFGS;
msrs->exit_ctls_high |=
VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
- VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT;
+ VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT |
+ VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
/* We support free control of debug control saving. */
msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS;
/* entry controls */
- rdmsr(MSR_IA32_VMX_ENTRY_CTLS,
- msrs->entry_ctls_low,
- msrs->entry_ctls_high);
msrs->entry_ctls_low =
VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR;
+
+ msrs->entry_ctls_high = vmcs_conf->vmentry_ctrl;
msrs->entry_ctls_high &=
#ifdef CONFIG_X86_64
VM_ENTRY_IA32E_MODE |
#endif
- VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_BNDCFGS |
- VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+ VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_BNDCFGS;
msrs->entry_ctls_high |=
- (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER);
+ (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER |
+ VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL);
/* We support free control of debug control loading. */
msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS;
/* cpu-based controls */
- rdmsr(MSR_IA32_VMX_PROCBASED_CTLS,
- msrs->procbased_ctls_low,
- msrs->procbased_ctls_high);
msrs->procbased_ctls_low =
CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
+
+ msrs->procbased_ctls_high = vmcs_conf->cpu_based_exec_ctrl;
msrs->procbased_ctls_high &=
CPU_BASED_INTR_WINDOW_EXITING |
CPU_BASED_NMI_WINDOW_EXITING | CPU_BASED_USE_TSC_OFFSETTING |
@@ -6632,12 +6796,9 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
* depend on CPUID bits, they are added later by
* vmx_vcpu_after_set_cpuid.
*/
- if (msrs->procbased_ctls_high & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)
- rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
- msrs->secondary_ctls_low,
- msrs->secondary_ctls_high);
-
msrs->secondary_ctls_low = 0;
+
+ msrs->secondary_ctls_high = vmcs_conf->cpu_based_2nd_exec_ctrl;
msrs->secondary_ctls_high &=
SECONDARY_EXEC_DESC |
SECONDARY_EXEC_ENABLE_RDTSCP |
@@ -6717,10 +6878,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
msrs->secondary_ctls_high |= SECONDARY_EXEC_ENCLS_EXITING;
/* miscellaneous data */
- rdmsr(MSR_IA32_VMX_MISC,
- msrs->misc_low,
- msrs->misc_high);
- msrs->misc_low &= VMX_MISC_SAVE_EFER_LMA;
+ msrs->misc_low = (u32)vmcs_conf->misc & VMX_MISC_SAVE_EFER_LMA;
msrs->misc_low |=
MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS |
VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE |
@@ -6814,9 +6972,9 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *))
struct kvm_x86_nested_ops vmx_nested_ops = {
.leave_nested = vmx_leave_nested,
+ .is_exception_vmexit = nested_vmx_is_exception_vmexit,
.check_events = vmx_check_nested_events,
- .handle_page_fault_workaround = nested_vmx_handle_page_fault_workaround,
- .hv_timer_pending = nested_vmx_preemption_timer_pending,
+ .has_events = vmx_has_nested_events,
.triple_fault = nested_vmx_triple_fault,
.get_state = vmx_get_nested_state,
.set_state = vmx_set_nested_state,
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index 88b00a7359e4..6312c9541c3c 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -17,7 +17,7 @@ enum nvmx_vmentry_status {
};
void vmx_leave_nested(struct kvm_vcpu *vcpu);
-void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps);
+void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps);
void nested_vmx_hardware_unsetup(void);
__init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *));
void nested_vmx_set_vmcs_shadowing_bitmap(void);
diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c
index aba8cebdc587..8f95c7c01433 100644
--- a/arch/x86/kvm/vmx/sgx.c
+++ b/arch/x86/kvm/vmx/sgx.c
@@ -129,7 +129,7 @@ static int sgx_inject_fault(struct kvm_vcpu *vcpu, gva_t gva, int trapnr)
ex.address = gva;
ex.error_code_valid = true;
ex.nested_page_fault = false;
- kvm_inject_page_fault(vcpu, &ex);
+ kvm_inject_emulated_page_fault(vcpu, &ex);
} else {
kvm_inject_gp(vcpu, 0);
}
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 6de96b943804..8477d8bdd69c 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -189,13 +189,16 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL)
xor %ebx, %ebx
.Lclear_regs:
+ /* Discard @regs. The register is irrelevant, it just can't be RBX. */
+ pop %_ASM_AX
+
/*
* Clear all general purpose registers except RSP and RBX to prevent
* speculative use of the guest's values, even those that are reloaded
* via the stack. In theory, an L1 cache miss when restoring registers
* could lead to speculative execution with the guest's values.
* Zeroing XORs are dirt cheap, i.e. the extra paranoia is essentially
- * free. RSP and RAX are exempt as RSP is restored by hardware during
+ * free. RSP and RBX are exempt as RSP is restored by hardware during
* VM-Exit and RBX is explicitly loaded with 0 or 1 to hold the return
* value.
*/
@@ -216,9 +219,6 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL)
xor %r15d, %r15d
#endif
- /* "POP" @regs. */
- add $WORD_SIZE, %_ASM_SP
-
/*
* IMPORTANT: RSB filling and SPEC_CTRL handling must be done before
* the first unbalanced RET after vmexit!
@@ -234,7 +234,6 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL)
FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT,\
X86_FEATURE_RSB_VMEXIT_LITE
-
pop %_ASM_ARG2 /* @flags */
pop %_ASM_ARG1 /* @vmx */
@@ -293,22 +292,13 @@ SYM_FUNC_START(vmread_error_trampoline)
push %r10
push %r11
#endif
-#ifdef CONFIG_X86_64
+
/* Load @field and @fault to arg1 and arg2 respectively. */
- mov 3*WORD_SIZE(%rbp), %_ASM_ARG2
- mov 2*WORD_SIZE(%rbp), %_ASM_ARG1
-#else
- /* Parameters are passed on the stack for 32-bit (see asmlinkage). */
- push 3*WORD_SIZE(%ebp)
- push 2*WORD_SIZE(%ebp)
-#endif
+ mov 3*WORD_SIZE(%_ASM_BP), %_ASM_ARG2
+ mov 2*WORD_SIZE(%_ASM_BP), %_ASM_ARG1
call vmread_error
-#ifndef CONFIG_X86_64
- add $8, %esp
-#endif
-
/* Zero out @fault, which will be popped into the result register. */
_ASM_MOV $0, 3*WORD_SIZE(%_ASM_BP)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index c9b49a09e6b5..9dba04b6b019 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -439,7 +439,7 @@ do { \
pr_warn_ratelimited(fmt); \
} while (0)
-asmlinkage void vmread_error(unsigned long field, bool fault)
+void vmread_error(unsigned long field, bool fault)
{
if (fault)
kvm_spurious_fault();
@@ -864,7 +864,7 @@ unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx)
return flags;
}
-static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
+static __always_inline void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
unsigned long entry, unsigned long exit)
{
vm_entry_controls_clearbit(vmx, entry);
@@ -922,7 +922,7 @@ skip_guest:
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
}
-static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx,
+static __always_inline void add_atomic_switch_msr_special(struct vcpu_vmx *vmx,
unsigned long entry, unsigned long exit,
unsigned long guest_val_vmcs, unsigned long host_val_vmcs,
u64 guest_val, u64 host_val)
@@ -1652,17 +1652,25 @@ static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu)
/*
* Per the SDM, MTF takes priority over debug-trap exceptions besides
- * T-bit traps. As instruction emulation is completed (i.e. at the
- * instruction boundary), any #DB exception pending delivery must be a
- * debug-trap. Record the pending MTF state to be delivered in
+ * TSS T-bit traps and ICEBP (INT1). KVM doesn't emulate T-bit traps
+ * or ICEBP (in the emulator proper), and skipping of ICEBP after an
+ * intercepted #DB deliberately avoids single-step #DB and MTF updates
+ * as ICEBP is higher priority than both. As instruction emulation is
+ * completed at this point (i.e. KVM is at the instruction boundary),
+ * any #DB exception pending delivery must be a debug-trap of lower
+ * priority than MTF. Record the pending MTF state to be delivered in
* vmx_check_nested_events().
*/
if (nested_cpu_has_mtf(vmcs12) &&
(!vcpu->arch.exception.pending ||
- vcpu->arch.exception.nr == DB_VECTOR))
+ vcpu->arch.exception.vector == DB_VECTOR) &&
+ (!vcpu->arch.exception_vmexit.pending ||
+ vcpu->arch.exception_vmexit.vector == DB_VECTOR)) {
vmx->nested.mtf_pending = true;
- else
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+ } else {
vmx->nested.mtf_pending = false;
+ }
}
static int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu)
@@ -1684,32 +1692,40 @@ static void vmx_clear_hlt(struct kvm_vcpu *vcpu)
vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE);
}
-static void vmx_queue_exception(struct kvm_vcpu *vcpu)
+static void vmx_inject_exception(struct kvm_vcpu *vcpu)
{
+ struct kvm_queued_exception *ex = &vcpu->arch.exception;
+ u32 intr_info = ex->vector | INTR_INFO_VALID_MASK;
struct vcpu_vmx *vmx = to_vmx(vcpu);
- unsigned nr = vcpu->arch.exception.nr;
- bool has_error_code = vcpu->arch.exception.has_error_code;
- u32 error_code = vcpu->arch.exception.error_code;
- u32 intr_info = nr | INTR_INFO_VALID_MASK;
- kvm_deliver_exception_payload(vcpu);
+ kvm_deliver_exception_payload(vcpu, ex);
- if (has_error_code) {
- vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
+ if (ex->has_error_code) {
+ /*
+ * Despite the error code being architecturally defined as 32
+ * bits, and the VMCS field being 32 bits, Intel CPUs and thus
+ * VMX don't actually supporting setting bits 31:16. Hardware
+ * will (should) never provide a bogus error code, but AMD CPUs
+ * do generate error codes with bits 31:16 set, and so KVM's
+ * ABI lets userspace shove in arbitrary 32-bit values. Drop
+ * the upper bits to avoid VM-Fail, losing information that
+ * does't really exist is preferable to killing the VM.
+ */
+ vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, (u16)ex->error_code);
intr_info |= INTR_INFO_DELIVER_CODE_MASK;
}
if (vmx->rmode.vm86_active) {
int inc_eip = 0;
- if (kvm_exception_is_soft(nr))
+ if (kvm_exception_is_soft(ex->vector))
inc_eip = vcpu->arch.event_exit_inst_len;
- kvm_inject_realmode_interrupt(vcpu, nr, inc_eip);
+ kvm_inject_realmode_interrupt(vcpu, ex->vector, inc_eip);
return;
}
WARN_ON_ONCE(vmx->emulation_required);
- if (kvm_exception_is_soft(nr)) {
+ if (kvm_exception_is_soft(ex->vector)) {
vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
vmx->vcpu.arch.event_exit_inst_len);
intr_info |= INTR_TYPE_SOFT_EXCEPTION;
@@ -1930,9 +1946,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
* sanity checking and refuse to boot. Filter all unsupported
* features out.
*/
- if (!msr_info->host_initiated &&
- vmx->nested.enlightened_vmcs_enabled)
- nested_evmcs_filter_control_msr(msr_info->index,
+ if (!msr_info->host_initiated && guest_cpuid_has_evmcs(vcpu))
+ nested_evmcs_filter_control_msr(vcpu, msr_info->index,
&msr_info->data);
break;
case MSR_IA32_RTIT_CTL:
@@ -2494,6 +2509,30 @@ static bool cpu_has_sgx(void)
return cpuid_eax(0) >= 0x12 && (cpuid_eax(0x12) & BIT(0));
}
+/*
+ * Some cpus support VM_{ENTRY,EXIT}_IA32_PERF_GLOBAL_CTRL but they
+ * can't be used due to errata where VM Exit may incorrectly clear
+ * IA32_PERF_GLOBAL_CTRL[34:32]. Work around the errata by using the
+ * MSR load mechanism to switch IA32_PERF_GLOBAL_CTRL.
+ */
+static bool cpu_has_perf_global_ctrl_bug(void)
+{
+ if (boot_cpu_data.x86 == 0x6) {
+ switch (boot_cpu_data.x86_model) {
+ case INTEL_FAM6_NEHALEM_EP: /* AAK155 */
+ case INTEL_FAM6_NEHALEM: /* AAP115 */
+ case INTEL_FAM6_WESTMERE: /* AAT100 */
+ case INTEL_FAM6_WESTMERE_EP: /* BC86,AAY89,BD102 */
+ case INTEL_FAM6_NEHALEM_EX: /* BA97 */
+ return true;
+ default:
+ break;
+ }
+ }
+
+ return false;
+}
+
static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt,
u32 msr, u32 *result)
{
@@ -2526,13 +2565,13 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
struct vmx_capability *vmx_cap)
{
u32 vmx_msr_low, vmx_msr_high;
- u32 min, opt, min2, opt2;
u32 _pin_based_exec_control = 0;
u32 _cpu_based_exec_control = 0;
u32 _cpu_based_2nd_exec_control = 0;
u64 _cpu_based_3rd_exec_control = 0;
u32 _vmexit_control = 0;
u32 _vmentry_control = 0;
+ u64 misc_msr;
int i;
/*
@@ -2552,64 +2591,17 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
};
memset(vmcs_conf, 0, sizeof(*vmcs_conf));
- min = CPU_BASED_HLT_EXITING |
-#ifdef CONFIG_X86_64
- CPU_BASED_CR8_LOAD_EXITING |
- CPU_BASED_CR8_STORE_EXITING |
-#endif
- CPU_BASED_CR3_LOAD_EXITING |
- CPU_BASED_CR3_STORE_EXITING |
- CPU_BASED_UNCOND_IO_EXITING |
- CPU_BASED_MOV_DR_EXITING |
- CPU_BASED_USE_TSC_OFFSETTING |
- CPU_BASED_MWAIT_EXITING |
- CPU_BASED_MONITOR_EXITING |
- CPU_BASED_INVLPG_EXITING |
- CPU_BASED_RDPMC_EXITING;
-
- opt = CPU_BASED_TPR_SHADOW |
- CPU_BASED_USE_MSR_BITMAPS |
- CPU_BASED_ACTIVATE_SECONDARY_CONTROLS |
- CPU_BASED_ACTIVATE_TERTIARY_CONTROLS;
- if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS,
- &_cpu_based_exec_control) < 0)
+
+ if (adjust_vmx_controls(KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL,
+ KVM_OPTIONAL_VMX_CPU_BASED_VM_EXEC_CONTROL,
+ MSR_IA32_VMX_PROCBASED_CTLS,
+ &_cpu_based_exec_control))
return -EIO;
-#ifdef CONFIG_X86_64
- if (_cpu_based_exec_control & CPU_BASED_TPR_SHADOW)
- _cpu_based_exec_control &= ~CPU_BASED_CR8_LOAD_EXITING &
- ~CPU_BASED_CR8_STORE_EXITING;
-#endif
if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) {
- min2 = 0;
- opt2 = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
- SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
- SECONDARY_EXEC_WBINVD_EXITING |
- SECONDARY_EXEC_ENABLE_VPID |
- SECONDARY_EXEC_ENABLE_EPT |
- SECONDARY_EXEC_UNRESTRICTED_GUEST |
- SECONDARY_EXEC_PAUSE_LOOP_EXITING |
- SECONDARY_EXEC_DESC |
- SECONDARY_EXEC_ENABLE_RDTSCP |
- SECONDARY_EXEC_ENABLE_INVPCID |
- SECONDARY_EXEC_APIC_REGISTER_VIRT |
- SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
- SECONDARY_EXEC_SHADOW_VMCS |
- SECONDARY_EXEC_XSAVES |
- SECONDARY_EXEC_RDSEED_EXITING |
- SECONDARY_EXEC_RDRAND_EXITING |
- SECONDARY_EXEC_ENABLE_PML |
- SECONDARY_EXEC_TSC_SCALING |
- SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE |
- SECONDARY_EXEC_PT_USE_GPA |
- SECONDARY_EXEC_PT_CONCEAL_VMX |
- SECONDARY_EXEC_ENABLE_VMFUNC |
- SECONDARY_EXEC_BUS_LOCK_DETECTION |
- SECONDARY_EXEC_NOTIFY_VM_EXITING;
- if (cpu_has_sgx())
- opt2 |= SECONDARY_EXEC_ENCLS_EXITING;
- if (adjust_vmx_controls(min2, opt2,
+ if (adjust_vmx_controls(KVM_REQUIRED_VMX_SECONDARY_VM_EXEC_CONTROL,
+ KVM_OPTIONAL_VMX_SECONDARY_VM_EXEC_CONTROL,
MSR_IA32_VMX_PROCBASED_CTLS2,
- &_cpu_based_2nd_exec_control) < 0)
+ &_cpu_based_2nd_exec_control))
return -EIO;
}
#ifndef CONFIG_X86_64
@@ -2627,13 +2619,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
rdmsr_safe(MSR_IA32_VMX_EPT_VPID_CAP,
&vmx_cap->ept, &vmx_cap->vpid);
- if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) {
- /* CR3 accesses and invlpg don't need to cause VM Exits when EPT
- enabled */
- _cpu_based_exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING |
- CPU_BASED_CR3_STORE_EXITING |
- CPU_BASED_INVLPG_EXITING);
- } else if (vmx_cap->ept) {
+ if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) &&
+ vmx_cap->ept) {
pr_warn_once("EPT CAP should not exist if not support "
"1-setting enable EPT VM-execution control\n");
@@ -2653,32 +2640,24 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
vmx_cap->vpid = 0;
}
- if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_TERTIARY_CONTROLS) {
- u64 opt3 = TERTIARY_EXEC_IPI_VIRT;
+ if (!cpu_has_sgx())
+ _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_ENCLS_EXITING;
- _cpu_based_3rd_exec_control = adjust_vmx_controls64(opt3,
+ if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_TERTIARY_CONTROLS)
+ _cpu_based_3rd_exec_control =
+ adjust_vmx_controls64(KVM_OPTIONAL_VMX_TERTIARY_VM_EXEC_CONTROL,
MSR_IA32_VMX_PROCBASED_CTLS3);
- }
- min = VM_EXIT_SAVE_DEBUG_CONTROLS | VM_EXIT_ACK_INTR_ON_EXIT;
-#ifdef CONFIG_X86_64
- min |= VM_EXIT_HOST_ADDR_SPACE_SIZE;
-#endif
- opt = VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL |
- VM_EXIT_LOAD_IA32_PAT |
- VM_EXIT_LOAD_IA32_EFER |
- VM_EXIT_CLEAR_BNDCFGS |
- VM_EXIT_PT_CONCEAL_PIP |
- VM_EXIT_CLEAR_IA32_RTIT_CTL;
- if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS,
- &_vmexit_control) < 0)
+ if (adjust_vmx_controls(KVM_REQUIRED_VMX_VM_EXIT_CONTROLS,
+ KVM_OPTIONAL_VMX_VM_EXIT_CONTROLS,
+ MSR_IA32_VMX_EXIT_CTLS,
+ &_vmexit_control))
return -EIO;
- min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING;
- opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR |
- PIN_BASED_VMX_PREEMPTION_TIMER;
- if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS,
- &_pin_based_exec_control) < 0)
+ if (adjust_vmx_controls(KVM_REQUIRED_VMX_PIN_BASED_VM_EXEC_CONTROL,
+ KVM_OPTIONAL_VMX_PIN_BASED_VM_EXEC_CONTROL,
+ MSR_IA32_VMX_PINBASED_CTLS,
+ &_pin_based_exec_control))
return -EIO;
if (cpu_has_broken_vmx_preemption_timer())
@@ -2687,15 +2666,10 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY))
_pin_based_exec_control &= ~PIN_BASED_POSTED_INTR;
- min = VM_ENTRY_LOAD_DEBUG_CONTROLS;
- opt = VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL |
- VM_ENTRY_LOAD_IA32_PAT |
- VM_ENTRY_LOAD_IA32_EFER |
- VM_ENTRY_LOAD_BNDCFGS |
- VM_ENTRY_PT_CONCEAL_PIP |
- VM_ENTRY_LOAD_IA32_RTIT_CTL;
- if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS,
- &_vmentry_control) < 0)
+ if (adjust_vmx_controls(KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS,
+ KVM_OPTIONAL_VMX_VM_ENTRY_CONTROLS,
+ MSR_IA32_VMX_ENTRY_CTLS,
+ &_vmentry_control))
return -EIO;
for (i = 0; i < ARRAY_SIZE(vmcs_entry_exit_pairs); i++) {
@@ -2715,30 +2689,6 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
_vmexit_control &= ~x_ctrl;
}
- /*
- * Some cpus support VM_{ENTRY,EXIT}_IA32_PERF_GLOBAL_CTRL but they
- * can't be used due to an errata where VM Exit may incorrectly clear
- * IA32_PERF_GLOBAL_CTRL[34:32]. Workaround the errata by using the
- * MSR load mechanism to switch IA32_PERF_GLOBAL_CTRL.
- */
- if (boot_cpu_data.x86 == 0x6) {
- switch (boot_cpu_data.x86_model) {
- case 26: /* AAK155 */
- case 30: /* AAP115 */
- case 37: /* AAT100 */
- case 44: /* BC86,AAY89,BD102 */
- case 46: /* BA97 */
- _vmentry_control &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
- _vmexit_control &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
- pr_warn_once("kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL "
- "does not work properly. Using workaround\n");
- break;
- default:
- break;
- }
- }
-
-
rdmsr(MSR_IA32_VMX_BASIC, vmx_msr_low, vmx_msr_high);
/* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */
@@ -2755,6 +2705,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
if (((vmx_msr_high >> 18) & 15) != 6)
return -EIO;
+ rdmsrl(MSR_IA32_VMX_MISC, misc_msr);
+
vmcs_conf->size = vmx_msr_high & 0x1fff;
vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff;
@@ -2766,11 +2718,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
vmcs_conf->cpu_based_3rd_exec_ctrl = _cpu_based_3rd_exec_control;
vmcs_conf->vmexit_ctrl = _vmexit_control;
vmcs_conf->vmentry_ctrl = _vmentry_control;
-
-#if IS_ENABLED(CONFIG_HYPERV)
- if (enlightened_vmcs)
- evmcs_sanitize_exec_ctrls(vmcs_conf);
-#endif
+ vmcs_conf->misc = misc_msr;
return 0;
}
@@ -3037,10 +2985,15 @@ int vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
return 0;
vcpu->arch.efer = efer;
+#ifdef CONFIG_X86_64
if (efer & EFER_LMA)
vm_entry_controls_setbit(vmx, VM_ENTRY_IA32E_MODE);
else
vm_entry_controls_clearbit(vmx, VM_ENTRY_IA32E_MODE);
+#else
+ if (KVM_BUG_ON(efer & EFER_LMA, vcpu->kvm))
+ return 1;
+#endif
vmx_setup_uret_msrs(vmx);
return 0;
@@ -4327,18 +4280,37 @@ static u32 vmx_vmentry_ctrl(void)
if (vmx_pt_mode_is_system())
vmentry_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP |
VM_ENTRY_LOAD_IA32_RTIT_CTL);
- /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */
- return vmentry_ctrl &
- ~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | VM_ENTRY_LOAD_IA32_EFER);
+ /*
+ * IA32e mode, and loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically.
+ */
+ vmentry_ctrl &= ~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL |
+ VM_ENTRY_LOAD_IA32_EFER |
+ VM_ENTRY_IA32E_MODE);
+
+ if (cpu_has_perf_global_ctrl_bug())
+ vmentry_ctrl &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+
+ return vmentry_ctrl;
}
static u32 vmx_vmexit_ctrl(void)
{
u32 vmexit_ctrl = vmcs_config.vmexit_ctrl;
+ /*
+ * Not used by KVM and never set in vmcs01 or vmcs02, but emulated for
+ * nested virtualization and thus allowed to be set in vmcs12.
+ */
+ vmexit_ctrl &= ~(VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER |
+ VM_EXIT_SAVE_VMX_PREEMPTION_TIMER);
+
if (vmx_pt_mode_is_system())
vmexit_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP |
VM_EXIT_CLEAR_IA32_RTIT_CTL);
+
+ if (cpu_has_perf_global_ctrl_bug())
+ vmexit_ctrl &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
+
/* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */
return vmexit_ctrl &
~(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_LOAD_IA32_EFER);
@@ -4376,20 +4348,38 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx)
{
u32 exec_control = vmcs_config.cpu_based_exec_ctrl;
+ /*
+ * Not used by KVM, but fully supported for nesting, i.e. are allowed in
+ * vmcs12 and propagated to vmcs02 when set in vmcs12.
+ */
+ exec_control &= ~(CPU_BASED_RDTSC_EXITING |
+ CPU_BASED_USE_IO_BITMAPS |
+ CPU_BASED_MONITOR_TRAP_FLAG |
+ CPU_BASED_PAUSE_EXITING);
+
+ /* INTR_WINDOW_EXITING and NMI_WINDOW_EXITING are toggled dynamically */
+ exec_control &= ~(CPU_BASED_INTR_WINDOW_EXITING |
+ CPU_BASED_NMI_WINDOW_EXITING);
+
if (vmx->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)
exec_control &= ~CPU_BASED_MOV_DR_EXITING;
- if (!cpu_need_tpr_shadow(&vmx->vcpu)) {
+ if (!cpu_need_tpr_shadow(&vmx->vcpu))
exec_control &= ~CPU_BASED_TPR_SHADOW;
+
#ifdef CONFIG_X86_64
+ if (exec_control & CPU_BASED_TPR_SHADOW)
+ exec_control &= ~(CPU_BASED_CR8_LOAD_EXITING |
+ CPU_BASED_CR8_STORE_EXITING);
+ else
exec_control |= CPU_BASED_CR8_STORE_EXITING |
CPU_BASED_CR8_LOAD_EXITING;
#endif
- }
- if (!enable_ept)
- exec_control |= CPU_BASED_CR3_STORE_EXITING |
- CPU_BASED_CR3_LOAD_EXITING |
- CPU_BASED_INVLPG_EXITING;
+ /* No need to intercept CR3 access or INVPLG when using EPT. */
+ if (enable_ept)
+ exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING |
+ CPU_BASED_CR3_STORE_EXITING |
+ CPU_BASED_INVLPG_EXITING);
if (kvm_mwait_in_guest(vmx->vcpu.kvm))
exec_control &= ~(CPU_BASED_MWAIT_EXITING |
CPU_BASED_MONITOR_EXITING);
@@ -5155,8 +5145,10 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
* instruction. ICEBP generates a trap-like #DB, but
* despite its interception control being tied to #DB,
* is an instruction intercept, i.e. the VM-Exit occurs
- * on the ICEBP itself. Note, skipping ICEBP also
- * clears STI and MOVSS blocking.
+ * on the ICEBP itself. Use the inner "skip" helper to
+ * avoid single-step #DB and MTF updates, as ICEBP is
+ * higher priority. Note, skipping ICEBP still clears
+ * STI and MOVSS blocking.
*
* For all other #DBs, set vmcs.PENDING_DBG_EXCEPTIONS.BS
* if single-step is enabled in RFLAGS and STI or MOVSS
@@ -5638,7 +5630,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI);
gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
- trace_kvm_page_fault(gpa, exit_qualification);
+ trace_kvm_page_fault(vcpu, gpa, exit_qualification);
/* Is it a read fault? */
error_code = (exit_qualification & EPT_VIOLATION_ACC_READ)
@@ -5710,7 +5702,7 @@ static bool vmx_emulation_required_with_pending_exception(struct kvm_vcpu *vcpu)
struct vcpu_vmx *vmx = to_vmx(vcpu);
return vmx->emulation_required && !vmx->rmode.vm86_active &&
- (vcpu->arch.exception.pending || vcpu->arch.exception.injected);
+ (kvm_is_exception_pending(vcpu) || vcpu->arch.exception.injected);
}
static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
@@ -7430,7 +7422,7 @@ static int __init vmx_check_processor_compat(void)
if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0)
return -EIO;
if (nested)
- nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept);
+ nested_vmx_setup_ctls_msrs(&vmcs_conf, vmx_cap.ept);
if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) {
printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n",
smp_processor_id());
@@ -8070,7 +8062,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
.patch_hypercall = vmx_patch_hypercall,
.inject_irq = vmx_inject_irq,
.inject_nmi = vmx_inject_nmi,
- .queue_exception = vmx_queue_exception,
+ .inject_exception = vmx_inject_exception,
.cancel_injection = vmx_cancel_injection,
.interrupt_allowed = vmx_interrupt_allowed,
.nmi_allowed = vmx_nmi_allowed,
@@ -8227,6 +8219,10 @@ static __init int hardware_setup(void)
if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0)
return -EIO;
+ if (cpu_has_perf_global_ctrl_bug())
+ pr_warn_once("kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL "
+ "does not work properly. Using workaround\n");
+
if (boot_cpu_has(X86_FEATURE_NX))
kvm_enable_efer_bits(EFER_NX);
@@ -8341,11 +8337,9 @@ static __init int hardware_setup(void)
if (enable_preemption_timer) {
u64 use_timer_freq = 5000ULL * 1000 * 1000;
- u64 vmx_msr;
- rdmsrl(MSR_IA32_VMX_MISC, vmx_msr);
cpu_preemption_timer_multi =
- vmx_msr & VMX_MISC_PREEMPTION_TIMER_RATE_MASK;
+ vmcs_config.misc & VMX_MISC_PREEMPTION_TIMER_RATE_MASK;
if (tsc_khz)
use_timer_freq = (u64)tsc_khz * 1000;
@@ -8381,8 +8375,7 @@ static __init int hardware_setup(void)
setup_default_sgx_lepubkeyhash();
if (nested) {
- nested_vmx_setup_ctls_msrs(&vmcs_config.nested,
- vmx_capability.ept);
+ nested_vmx_setup_ctls_msrs(&vmcs_config, vmx_capability.ept);
r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers);
if (r)
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 24d58c2ffaa3..a3da84f4ea45 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -477,29 +477,145 @@ static inline u8 vmx_get_rvi(void)
return vmcs_read16(GUEST_INTR_STATUS) & 0xff;
}
-#define BUILD_CONTROLS_SHADOW(lname, uname, bits) \
-static inline void lname##_controls_set(struct vcpu_vmx *vmx, u##bits val) \
-{ \
- if (vmx->loaded_vmcs->controls_shadow.lname != val) { \
- vmcs_write##bits(uname, val); \
- vmx->loaded_vmcs->controls_shadow.lname = val; \
- } \
-} \
-static inline u##bits __##lname##_controls_get(struct loaded_vmcs *vmcs) \
-{ \
- return vmcs->controls_shadow.lname; \
-} \
-static inline u##bits lname##_controls_get(struct vcpu_vmx *vmx) \
-{ \
- return __##lname##_controls_get(vmx->loaded_vmcs); \
-} \
-static inline void lname##_controls_setbit(struct vcpu_vmx *vmx, u##bits val) \
-{ \
- lname##_controls_set(vmx, lname##_controls_get(vmx) | val); \
-} \
-static inline void lname##_controls_clearbit(struct vcpu_vmx *vmx, u##bits val) \
-{ \
- lname##_controls_set(vmx, lname##_controls_get(vmx) & ~val); \
+#define __KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS \
+ (VM_ENTRY_LOAD_DEBUG_CONTROLS)
+#ifdef CONFIG_X86_64
+ #define KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS \
+ (__KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS | \
+ VM_ENTRY_IA32E_MODE)
+#else
+ #define KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS \
+ __KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS
+#endif
+#define KVM_OPTIONAL_VMX_VM_ENTRY_CONTROLS \
+ (VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \
+ VM_ENTRY_LOAD_IA32_PAT | \
+ VM_ENTRY_LOAD_IA32_EFER | \
+ VM_ENTRY_LOAD_BNDCFGS | \
+ VM_ENTRY_PT_CONCEAL_PIP | \
+ VM_ENTRY_LOAD_IA32_RTIT_CTL)
+
+#define __KVM_REQUIRED_VMX_VM_EXIT_CONTROLS \
+ (VM_EXIT_SAVE_DEBUG_CONTROLS | \
+ VM_EXIT_ACK_INTR_ON_EXIT)
+#ifdef CONFIG_X86_64
+ #define KVM_REQUIRED_VMX_VM_EXIT_CONTROLS \
+ (__KVM_REQUIRED_VMX_VM_EXIT_CONTROLS | \
+ VM_EXIT_HOST_ADDR_SPACE_SIZE)
+#else
+ #define KVM_REQUIRED_VMX_VM_EXIT_CONTROLS \
+ __KVM_REQUIRED_VMX_VM_EXIT_CONTROLS
+#endif
+#define KVM_OPTIONAL_VMX_VM_EXIT_CONTROLS \
+ (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \
+ VM_EXIT_SAVE_IA32_PAT | \
+ VM_EXIT_LOAD_IA32_PAT | \
+ VM_EXIT_SAVE_IA32_EFER | \
+ VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | \
+ VM_EXIT_LOAD_IA32_EFER | \
+ VM_EXIT_CLEAR_BNDCFGS | \
+ VM_EXIT_PT_CONCEAL_PIP | \
+ VM_EXIT_CLEAR_IA32_RTIT_CTL)
+
+#define KVM_REQUIRED_VMX_PIN_BASED_VM_EXEC_CONTROL \
+ (PIN_BASED_EXT_INTR_MASK | \
+ PIN_BASED_NMI_EXITING)
+#define KVM_OPTIONAL_VMX_PIN_BASED_VM_EXEC_CONTROL \
+ (PIN_BASED_VIRTUAL_NMIS | \
+ PIN_BASED_POSTED_INTR | \
+ PIN_BASED_VMX_PREEMPTION_TIMER)
+
+#define __KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL \
+ (CPU_BASED_HLT_EXITING | \
+ CPU_BASED_CR3_LOAD_EXITING | \
+ CPU_BASED_CR3_STORE_EXITING | \
+ CPU_BASED_UNCOND_IO_EXITING | \
+ CPU_BASED_MOV_DR_EXITING | \
+ CPU_BASED_USE_TSC_OFFSETTING | \
+ CPU_BASED_MWAIT_EXITING | \
+ CPU_BASED_MONITOR_EXITING | \
+ CPU_BASED_INVLPG_EXITING | \
+ CPU_BASED_RDPMC_EXITING | \
+ CPU_BASED_INTR_WINDOW_EXITING)
+
+#ifdef CONFIG_X86_64
+ #define KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL \
+ (__KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL | \
+ CPU_BASED_CR8_LOAD_EXITING | \
+ CPU_BASED_CR8_STORE_EXITING)
+#else
+ #define KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL \
+ __KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL
+#endif
+
+#define KVM_OPTIONAL_VMX_CPU_BASED_VM_EXEC_CONTROL \
+ (CPU_BASED_RDTSC_EXITING | \
+ CPU_BASED_TPR_SHADOW | \
+ CPU_BASED_USE_IO_BITMAPS | \
+ CPU_BASED_MONITOR_TRAP_FLAG | \
+ CPU_BASED_USE_MSR_BITMAPS | \
+ CPU_BASED_NMI_WINDOW_EXITING | \
+ CPU_BASED_PAUSE_EXITING | \
+ CPU_BASED_ACTIVATE_SECONDARY_CONTROLS | \
+ CPU_BASED_ACTIVATE_TERTIARY_CONTROLS)
+
+#define KVM_REQUIRED_VMX_SECONDARY_VM_EXEC_CONTROL 0
+#define KVM_OPTIONAL_VMX_SECONDARY_VM_EXEC_CONTROL \
+ (SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | \
+ SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \
+ SECONDARY_EXEC_WBINVD_EXITING | \
+ SECONDARY_EXEC_ENABLE_VPID | \
+ SECONDARY_EXEC_ENABLE_EPT | \
+ SECONDARY_EXEC_UNRESTRICTED_GUEST | \
+ SECONDARY_EXEC_PAUSE_LOOP_EXITING | \
+ SECONDARY_EXEC_DESC | \
+ SECONDARY_EXEC_ENABLE_RDTSCP | \
+ SECONDARY_EXEC_ENABLE_INVPCID | \
+ SECONDARY_EXEC_APIC_REGISTER_VIRT | \
+ SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | \
+ SECONDARY_EXEC_SHADOW_VMCS | \
+ SECONDARY_EXEC_XSAVES | \
+ SECONDARY_EXEC_RDSEED_EXITING | \
+ SECONDARY_EXEC_RDRAND_EXITING | \
+ SECONDARY_EXEC_ENABLE_PML | \
+ SECONDARY_EXEC_TSC_SCALING | \
+ SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \
+ SECONDARY_EXEC_PT_USE_GPA | \
+ SECONDARY_EXEC_PT_CONCEAL_VMX | \
+ SECONDARY_EXEC_ENABLE_VMFUNC | \
+ SECONDARY_EXEC_BUS_LOCK_DETECTION | \
+ SECONDARY_EXEC_NOTIFY_VM_EXITING | \
+ SECONDARY_EXEC_ENCLS_EXITING)
+
+#define KVM_REQUIRED_VMX_TERTIARY_VM_EXEC_CONTROL 0
+#define KVM_OPTIONAL_VMX_TERTIARY_VM_EXEC_CONTROL \
+ (TERTIARY_EXEC_IPI_VIRT)
+
+#define BUILD_CONTROLS_SHADOW(lname, uname, bits) \
+static inline void lname##_controls_set(struct vcpu_vmx *vmx, u##bits val) \
+{ \
+ if (vmx->loaded_vmcs->controls_shadow.lname != val) { \
+ vmcs_write##bits(uname, val); \
+ vmx->loaded_vmcs->controls_shadow.lname = val; \
+ } \
+} \
+static inline u##bits __##lname##_controls_get(struct loaded_vmcs *vmcs) \
+{ \
+ return vmcs->controls_shadow.lname; \
+} \
+static inline u##bits lname##_controls_get(struct vcpu_vmx *vmx) \
+{ \
+ return __##lname##_controls_get(vmx->loaded_vmcs); \
+} \
+static __always_inline void lname##_controls_setbit(struct vcpu_vmx *vmx, u##bits val) \
+{ \
+ BUILD_BUG_ON(!(val & (KVM_REQUIRED_VMX_##uname | KVM_OPTIONAL_VMX_##uname))); \
+ lname##_controls_set(vmx, lname##_controls_get(vmx) | val); \
+} \
+static __always_inline void lname##_controls_clearbit(struct vcpu_vmx *vmx, u##bits val) \
+{ \
+ BUILD_BUG_ON(!(val & (KVM_REQUIRED_VMX_##uname | KVM_OPTIONAL_VMX_##uname))); \
+ lname##_controls_set(vmx, lname##_controls_get(vmx) & ~val); \
}
BUILD_CONTROLS_SHADOW(vm_entry, VM_ENTRY_CONTROLS, 32)
BUILD_CONTROLS_SHADOW(vm_exit, VM_EXIT_CONTROLS, 32)
@@ -626,4 +742,14 @@ static inline bool vmx_can_use_ipiv(struct kvm_vcpu *vcpu)
return lapic_in_kernel(vcpu) && enable_ipiv;
}
+static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu)
+{
+ /*
+ * eVMCS is exposed to the guest if Hyper-V is enabled in CPUID and
+ * eVMCS has been explicitly enabled by userspace.
+ */
+ return vcpu->arch.hyperv_enabled &&
+ to_vmx(vcpu)->nested.enlightened_vmcs_enabled;
+}
+
#endif /* __KVM_X86_VMX_H */
diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h
index 5cfc49ddb1b4..ec268df83ed6 100644
--- a/arch/x86/kvm/vmx/vmx_ops.h
+++ b/arch/x86/kvm/vmx/vmx_ops.h
@@ -10,7 +10,7 @@
#include "vmcs.h"
#include "../x86.h"
-asmlinkage void vmread_error(unsigned long field, bool fault);
+void vmread_error(unsigned long field, bool fault);
__attribute__((regparm(0))) void vmread_error_trampoline(unsigned long field,
bool fault);
void vmwrite_error(unsigned long field, unsigned long value);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b0c47b41c264..4bd5f8a751de 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -173,8 +173,13 @@ bool __read_mostly enable_vmware_backdoor = false;
module_param(enable_vmware_backdoor, bool, S_IRUGO);
EXPORT_SYMBOL_GPL(enable_vmware_backdoor);
-static bool __read_mostly force_emulation_prefix = false;
-module_param(force_emulation_prefix, bool, S_IRUGO);
+/*
+ * Flags to manipulate forced emulation behavior (any non-zero value will
+ * enable forced emulation).
+ */
+#define KVM_FEP_CLEAR_RFLAGS_RF BIT(1)
+static int __read_mostly force_emulation_prefix;
+module_param(force_emulation_prefix, int, 0644);
int __read_mostly pi_inject_timer = -1;
module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR);
@@ -528,6 +533,7 @@ static int exception_class(int vector)
#define EXCPT_TRAP 1
#define EXCPT_ABORT 2
#define EXCPT_INTERRUPT 3
+#define EXCPT_DB 4
static int exception_type(int vector)
{
@@ -538,8 +544,14 @@ static int exception_type(int vector)
mask = 1 << vector;
- /* #DB is trap, as instruction watchpoints are handled elsewhere */
- if (mask & ((1 << DB_VECTOR) | (1 << BP_VECTOR) | (1 << OF_VECTOR)))
+ /*
+ * #DBs can be trap-like or fault-like, the caller must check other CPU
+ * state, e.g. DR6, to determine whether a #DB is a trap or fault.
+ */
+ if (mask & (1 << DB_VECTOR))
+ return EXCPT_DB;
+
+ if (mask & ((1 << BP_VECTOR) | (1 << OF_VECTOR)))
return EXCPT_TRAP;
if (mask & ((1 << DF_VECTOR) | (1 << MC_VECTOR)))
@@ -549,16 +561,13 @@ static int exception_type(int vector)
return EXCPT_FAULT;
}
-void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu)
+void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu,
+ struct kvm_queued_exception *ex)
{
- unsigned nr = vcpu->arch.exception.nr;
- bool has_payload = vcpu->arch.exception.has_payload;
- unsigned long payload = vcpu->arch.exception.payload;
-
- if (!has_payload)
+ if (!ex->has_payload)
return;
- switch (nr) {
+ switch (ex->vector) {
case DB_VECTOR:
/*
* "Certain debug exceptions may clear bit 0-3. The
@@ -583,8 +592,8 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu)
* So they need to be flipped for DR6.
*/
vcpu->arch.dr6 |= DR6_ACTIVE_LOW;
- vcpu->arch.dr6 |= payload;
- vcpu->arch.dr6 ^= payload & DR6_ACTIVE_LOW;
+ vcpu->arch.dr6 |= ex->payload;
+ vcpu->arch.dr6 ^= ex->payload & DR6_ACTIVE_LOW;
/*
* The #DB payload is defined as compatible with the 'pending
@@ -595,15 +604,30 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu)
vcpu->arch.dr6 &= ~BIT(12);
break;
case PF_VECTOR:
- vcpu->arch.cr2 = payload;
+ vcpu->arch.cr2 = ex->payload;
break;
}
- vcpu->arch.exception.has_payload = false;
- vcpu->arch.exception.payload = 0;
+ ex->has_payload = false;
+ ex->payload = 0;
}
EXPORT_SYMBOL_GPL(kvm_deliver_exception_payload);
+static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vector,
+ bool has_error_code, u32 error_code,
+ bool has_payload, unsigned long payload)
+{
+ struct kvm_queued_exception *ex = &vcpu->arch.exception_vmexit;
+
+ ex->vector = vector;
+ ex->injected = false;
+ ex->pending = true;
+ ex->has_error_code = has_error_code;
+ ex->error_code = error_code;
+ ex->has_payload = has_payload;
+ ex->payload = payload;
+}
+
static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
unsigned nr, bool has_error, u32 error_code,
bool has_payload, unsigned long payload, bool reinject)
@@ -613,18 +637,31 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
kvm_make_request(KVM_REQ_EVENT, vcpu);
+ /*
+ * If the exception is destined for L2 and isn't being reinjected,
+ * morph it to a VM-Exit if L1 wants to intercept the exception. A
+ * previously injected exception is not checked because it was checked
+ * when it was original queued, and re-checking is incorrect if _L1_
+ * injected the exception, in which case it's exempt from interception.
+ */
+ if (!reinject && is_guest_mode(vcpu) &&
+ kvm_x86_ops.nested_ops->is_exception_vmexit(vcpu, nr, error_code)) {
+ kvm_queue_exception_vmexit(vcpu, nr, has_error, error_code,
+ has_payload, payload);
+ return;
+ }
+
if (!vcpu->arch.exception.pending && !vcpu->arch.exception.injected) {
queue:
if (reinject) {
/*
- * On vmentry, vcpu->arch.exception.pending is only
- * true if an event injection was blocked by
- * nested_run_pending. In that case, however,
- * vcpu_enter_guest requests an immediate exit,
- * and the guest shouldn't proceed far enough to
- * need reinjection.
+ * On VM-Entry, an exception can be pending if and only
+ * if event injection was blocked by nested_run_pending.
+ * In that case, however, vcpu_enter_guest() requests an
+ * immediate exit, and the guest shouldn't proceed far
+ * enough to need reinjection.
*/
- WARN_ON_ONCE(vcpu->arch.exception.pending);
+ WARN_ON_ONCE(kvm_is_exception_pending(vcpu));
vcpu->arch.exception.injected = true;
if (WARN_ON_ONCE(has_payload)) {
/*
@@ -639,17 +676,18 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
vcpu->arch.exception.injected = false;
}
vcpu->arch.exception.has_error_code = has_error;
- vcpu->arch.exception.nr = nr;
+ vcpu->arch.exception.vector = nr;
vcpu->arch.exception.error_code = error_code;
vcpu->arch.exception.has_payload = has_payload;
vcpu->arch.exception.payload = payload;
if (!is_guest_mode(vcpu))
- kvm_deliver_exception_payload(vcpu);
+ kvm_deliver_exception_payload(vcpu,
+ &vcpu->arch.exception);
return;
}
/* to check exception */
- prev_nr = vcpu->arch.exception.nr;
+ prev_nr = vcpu->arch.exception.vector;
if (prev_nr == DF_VECTOR) {
/* triple fault -> shutdown */
kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
@@ -657,25 +695,22 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
}
class1 = exception_class(prev_nr);
class2 = exception_class(nr);
- if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY)
- || (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) {
+ if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY) ||
+ (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) {
/*
- * Generate double fault per SDM Table 5-5. Set
- * exception.pending = true so that the double fault
- * can trigger a nested vmexit.
+ * Synthesize #DF. Clear the previously injected or pending
+ * exception so as not to incorrectly trigger shutdown.
*/
- vcpu->arch.exception.pending = true;
vcpu->arch.exception.injected = false;
- vcpu->arch.exception.has_error_code = true;
- vcpu->arch.exception.nr = DF_VECTOR;
- vcpu->arch.exception.error_code = 0;
- vcpu->arch.exception.has_payload = false;
- vcpu->arch.exception.payload = 0;
- } else
+ vcpu->arch.exception.pending = false;
+
+ kvm_queue_exception_e(vcpu, DF_VECTOR, 0);
+ } else {
/* replace previous exception with a new one in a hope
that instruction re-execution will regenerate lost
exception */
goto queue;
+ }
}
void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr)
@@ -729,20 +764,22 @@ static int complete_emulated_insn_gp(struct kvm_vcpu *vcpu, int err)
void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
{
++vcpu->stat.pf_guest;
- vcpu->arch.exception.nested_apf =
- is_guest_mode(vcpu) && fault->async_page_fault;
- if (vcpu->arch.exception.nested_apf) {
- vcpu->arch.apf.nested_apf_token = fault->address;
- kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code);
- } else {
+
+ /*
+ * Async #PF in L2 is always forwarded to L1 as a VM-Exit regardless of
+ * whether or not L1 wants to intercept "regular" #PF.
+ */
+ if (is_guest_mode(vcpu) && fault->async_page_fault)
+ kvm_queue_exception_vmexit(vcpu, PF_VECTOR,
+ true, fault->error_code,
+ true, fault->address);
+ else
kvm_queue_exception_e_p(vcpu, PF_VECTOR, fault->error_code,
fault->address);
- }
}
EXPORT_SYMBOL_GPL(kvm_inject_page_fault);
-/* Returns true if the page fault was immediately morphed into a VM-Exit. */
-bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu,
+void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu,
struct x86_exception *fault)
{
struct kvm_mmu *fault_mmu;
@@ -760,26 +797,7 @@ bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu,
kvm_mmu_invalidate_gva(vcpu, fault_mmu, fault->address,
fault_mmu->root.hpa);
- /*
- * A workaround for KVM's bad exception handling. If KVM injected an
- * exception into L2, and L2 encountered a #PF while vectoring the
- * injected exception, manually check to see if L1 wants to intercept
- * #PF, otherwise queuing the #PF will lead to #DF or a lost exception.
- * In all other cases, defer the check to nested_ops->check_events(),
- * which will correctly handle priority (this does not). Note, other
- * exceptions, e.g. #GP, are theoretically affected, #PF is simply the
- * most problematic, e.g. when L0 and L1 are both intercepting #PF for
- * shadow paging.
- *
- * TODO: Rewrite exception handling to track injected and pending
- * (VM-Exit) exceptions separately.
- */
- if (unlikely(vcpu->arch.exception.injected && is_guest_mode(vcpu)) &&
- kvm_x86_ops.nested_ops->handle_page_fault_workaround(vcpu, fault))
- return true;
-
fault_mmu->inject_page_fault(vcpu, fault);
- return false;
}
EXPORT_SYMBOL_GPL(kvm_inject_emulated_page_fault);
@@ -4841,7 +4859,7 @@ static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu)
return (kvm_arch_interrupt_allowed(vcpu) &&
kvm_cpu_accept_dm_intr(vcpu) &&
!kvm_event_needs_reinjection(vcpu) &&
- !vcpu->arch.exception.pending);
+ !kvm_is_exception_pending(vcpu));
}
static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
@@ -5016,25 +5034,38 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu,
static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events)
{
+ struct kvm_queued_exception *ex;
+
process_nmi(vcpu);
if (kvm_check_request(KVM_REQ_SMI, vcpu))
process_smi(vcpu);
/*
- * In guest mode, payload delivery should be deferred,
- * so that the L1 hypervisor can intercept #PF before
- * CR2 is modified (or intercept #DB before DR6 is
- * modified under nVMX). Unless the per-VM capability,
- * KVM_CAP_EXCEPTION_PAYLOAD, is set, we may not defer the delivery of
- * an exception payload and handle after a KVM_GET_VCPU_EVENTS. Since we
- * opportunistically defer the exception payload, deliver it if the
- * capability hasn't been requested before processing a
- * KVM_GET_VCPU_EVENTS.
+ * KVM's ABI only allows for one exception to be migrated. Luckily,
+ * the only time there can be two queued exceptions is if there's a
+ * non-exiting _injected_ exception, and a pending exiting exception.
+ * In that case, ignore the VM-Exiting exception as it's an extension
+ * of the injected exception.
+ */
+ if (vcpu->arch.exception_vmexit.pending &&
+ !vcpu->arch.exception.pending &&
+ !vcpu->arch.exception.injected)
+ ex = &vcpu->arch.exception_vmexit;
+ else
+ ex = &vcpu->arch.exception;
+
+ /*
+ * In guest mode, payload delivery should be deferred if the exception
+ * will be intercepted by L1, e.g. KVM should not modifying CR2 if L1
+ * intercepts #PF, ditto for DR6 and #DBs. If the per-VM capability,
+ * KVM_CAP_EXCEPTION_PAYLOAD, is not set, userspace may or may not
+ * propagate the payload and so it cannot be safely deferred. Deliver
+ * the payload if the capability hasn't been requested.
*/
if (!vcpu->kvm->arch.exception_payload_enabled &&
- vcpu->arch.exception.pending && vcpu->arch.exception.has_payload)
- kvm_deliver_exception_payload(vcpu);
+ ex->pending && ex->has_payload)
+ kvm_deliver_exception_payload(vcpu, ex);
/*
* The API doesn't provide the instruction length for software
@@ -5042,26 +5073,25 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
* isn't advanced, we should expect to encounter the exception
* again.
*/
- if (kvm_exception_is_soft(vcpu->arch.exception.nr)) {
+ if (kvm_exception_is_soft(ex->vector)) {
events->exception.injected = 0;
events->exception.pending = 0;
} else {
- events->exception.injected = vcpu->arch.exception.injected;
- events->exception.pending = vcpu->arch.exception.pending;
+ events->exception.injected = ex->injected;
+ events->exception.pending = ex->pending;
/*
* For ABI compatibility, deliberately conflate
* pending and injected exceptions when
* KVM_CAP_EXCEPTION_PAYLOAD isn't enabled.
*/
if (!vcpu->kvm->arch.exception_payload_enabled)
- events->exception.injected |=
- vcpu->arch.exception.pending;
+ events->exception.injected |= ex->pending;
}
- events->exception.nr = vcpu->arch.exception.nr;
- events->exception.has_error_code = vcpu->arch.exception.has_error_code;
- events->exception.error_code = vcpu->arch.exception.error_code;
- events->exception_has_payload = vcpu->arch.exception.has_payload;
- events->exception_payload = vcpu->arch.exception.payload;
+ events->exception.nr = ex->vector;
+ events->exception.has_error_code = ex->has_error_code;
+ events->exception.error_code = ex->error_code;
+ events->exception_has_payload = ex->has_payload;
+ events->exception_payload = ex->payload;
events->interrupt.injected =
vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft;
@@ -5131,9 +5161,22 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
return -EINVAL;
process_nmi(vcpu);
+
+ /*
+ * Flag that userspace is stuffing an exception, the next KVM_RUN will
+ * morph the exception to a VM-Exit if appropriate. Do this only for
+ * pending exceptions, already-injected exceptions are not subject to
+ * intercpetion. Note, userspace that conflates pending and injected
+ * is hosed, and will incorrectly convert an injected exception into a
+ * pending exception, which in turn may cause a spurious VM-Exit.
+ */
+ vcpu->arch.exception_from_userspace = events->exception.pending;
+
+ vcpu->arch.exception_vmexit.pending = false;
+
vcpu->arch.exception.injected = events->exception.injected;
vcpu->arch.exception.pending = events->exception.pending;
- vcpu->arch.exception.nr = events->exception.nr;
+ vcpu->arch.exception.vector = events->exception.nr;
vcpu->arch.exception.has_error_code = events->exception.has_error_code;
vcpu->arch.exception.error_code = events->exception.error_code;
vcpu->arch.exception.has_payload = events->exception_has_payload;
@@ -7257,6 +7300,7 @@ static int kvm_can_emulate_insn(struct kvm_vcpu *vcpu, int emul_type,
int handle_ud(struct kvm_vcpu *vcpu)
{
static const char kvm_emulate_prefix[] = { __KVM_EMULATE_PREFIX };
+ int fep_flags = READ_ONCE(force_emulation_prefix);
int emul_type = EMULTYPE_TRAP_UD;
char sig[5]; /* ud2; .ascii "kvm" */
struct x86_exception e;
@@ -7264,10 +7308,12 @@ int handle_ud(struct kvm_vcpu *vcpu)
if (unlikely(!kvm_can_emulate_insn(vcpu, emul_type, NULL, 0)))
return 1;
- if (force_emulation_prefix &&
+ if (fep_flags &&
kvm_read_guest_virt(vcpu, kvm_get_linear_rip(vcpu),
sig, sizeof(sig), &e) == 0 &&
memcmp(sig, kvm_emulate_prefix, sizeof(sig)) == 0) {
+ if (fep_flags & KVM_FEP_CLEAR_RFLAGS_RF)
+ kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) & ~X86_EFLAGS_RF);
kvm_rip_write(vcpu, kvm_rip_read(vcpu) + sizeof(sig));
emul_type = EMULTYPE_TRAP_UD_FORCED;
}
@@ -7933,14 +7979,20 @@ static int emulator_get_msr_with_filter(struct x86_emulate_ctxt *ctxt,
int r;
r = kvm_get_msr_with_filter(vcpu, msr_index, pdata);
+ if (r < 0)
+ return X86EMUL_UNHANDLEABLE;
- if (r && kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_RDMSR, 0,
- complete_emulated_rdmsr, r)) {
- /* Bounce to user space */
- return X86EMUL_IO_NEEDED;
+ if (r) {
+ if (kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_RDMSR, 0,
+ complete_emulated_rdmsr, r))
+ return X86EMUL_IO_NEEDED;
+
+ trace_kvm_msr_read_ex(msr_index);
+ return X86EMUL_PROPAGATE_FAULT;
}
- return r;
+ trace_kvm_msr_read(msr_index, *pdata);
+ return X86EMUL_CONTINUE;
}
static int emulator_set_msr_with_filter(struct x86_emulate_ctxt *ctxt,
@@ -7950,14 +8002,20 @@ static int emulator_set_msr_with_filter(struct x86_emulate_ctxt *ctxt,
int r;
r = kvm_set_msr_with_filter(vcpu, msr_index, data);
+ if (r < 0)
+ return X86EMUL_UNHANDLEABLE;
- if (r && kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_WRMSR, data,
- complete_emulated_msr_access, r)) {
- /* Bounce to user space */
- return X86EMUL_IO_NEEDED;
+ if (r) {
+ if (kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_WRMSR, data,
+ complete_emulated_msr_access, r))
+ return X86EMUL_IO_NEEDED;
+
+ trace_kvm_msr_write_ex(msr_index, data);
+ return X86EMUL_PROPAGATE_FAULT;
}
- return r;
+ trace_kvm_msr_write(msr_index, data);
+ return X86EMUL_CONTINUE;
}
static int emulator_get_msr(struct x86_emulate_ctxt *ctxt,
@@ -8161,18 +8219,17 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
}
}
-static bool inject_emulated_exception(struct kvm_vcpu *vcpu)
+static void inject_emulated_exception(struct kvm_vcpu *vcpu)
{
struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
- if (ctxt->exception.vector == PF_VECTOR)
- return kvm_inject_emulated_page_fault(vcpu, &ctxt->exception);
- if (ctxt->exception.error_code_valid)
+ if (ctxt->exception.vector == PF_VECTOR)
+ kvm_inject_emulated_page_fault(vcpu, &ctxt->exception);
+ else if (ctxt->exception.error_code_valid)
kvm_queue_exception_e(vcpu, ctxt->exception.vector,
ctxt->exception.error_code);
else
kvm_queue_exception(vcpu, ctxt->exception.vector);
- return false;
}
static struct x86_emulate_ctxt *alloc_emulate_ctxt(struct kvm_vcpu *vcpu)
@@ -8548,8 +8605,46 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu)
}
EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction);
-static bool kvm_vcpu_check_code_breakpoint(struct kvm_vcpu *vcpu, int *r)
+static bool kvm_is_code_breakpoint_inhibited(struct kvm_vcpu *vcpu)
{
+ u32 shadow;
+
+ if (kvm_get_rflags(vcpu) & X86_EFLAGS_RF)
+ return true;
+
+ /*
+ * Intel CPUs inhibit code #DBs when MOV/POP SS blocking is active,
+ * but AMD CPUs do not. MOV/POP SS blocking is rare, check that first
+ * to avoid the relatively expensive CPUID lookup.
+ */
+ shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
+ return (shadow & KVM_X86_SHADOW_INT_MOV_SS) &&
+ guest_cpuid_is_intel(vcpu);
+}
+
+static bool kvm_vcpu_check_code_breakpoint(struct kvm_vcpu *vcpu,
+ int emulation_type, int *r)
+{
+ WARN_ON_ONCE(emulation_type & EMULTYPE_NO_DECODE);
+
+ /*
+ * Do not check for code breakpoints if hardware has already done the
+ * checks, as inferred from the emulation type. On NO_DECODE and SKIP,
+ * the instruction has passed all exception checks, and all intercepted
+ * exceptions that trigger emulation have lower priority than code
+ * breakpoints, i.e. the fact that the intercepted exception occurred
+ * means any code breakpoints have already been serviced.
+ *
+ * Note, KVM needs to check for code #DBs on EMULTYPE_TRAP_UD_FORCED as
+ * hardware has checked the RIP of the magic prefix, but not the RIP of
+ * the instruction being emulated. The intent of forced emulation is
+ * to behave as if KVM intercepted the instruction without an exception
+ * and without a prefix.
+ */
+ if (emulation_type & (EMULTYPE_NO_DECODE | EMULTYPE_SKIP |
+ EMULTYPE_TRAP_UD | EMULTYPE_VMWARE_GP | EMULTYPE_PF))
+ return false;
+
if (unlikely(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) &&
(vcpu->arch.guest_debug_dr7 & DR7_BP_EN_MASK)) {
struct kvm_run *kvm_run = vcpu->run;
@@ -8569,7 +8664,7 @@ static bool kvm_vcpu_check_code_breakpoint(struct kvm_vcpu *vcpu, int *r)
}
if (unlikely(vcpu->arch.dr7 & DR7_BP_EN_MASK) &&
- !(kvm_get_rflags(vcpu) & X86_EFLAGS_RF)) {
+ !kvm_is_code_breakpoint_inhibited(vcpu)) {
unsigned long eip = kvm_get_linear_rip(vcpu);
u32 dr6 = kvm_vcpu_check_hw_bp(eip, 0,
vcpu->arch.dr7,
@@ -8671,8 +8766,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
* are fault-like and are higher priority than any faults on
* the code fetch itself.
*/
- if (!(emulation_type & EMULTYPE_SKIP) &&
- kvm_vcpu_check_code_breakpoint(vcpu, &r))
+ if (kvm_vcpu_check_code_breakpoint(vcpu, emulation_type, &r))
return r;
r = x86_decode_emulated_instruction(vcpu, emulation_type,
@@ -8770,8 +8864,7 @@ restart:
if (ctxt->have_exception) {
r = 1;
- if (inject_emulated_exception(vcpu))
- return r;
+ inject_emulated_exception(vcpu);
} else if (vcpu->arch.pio.count) {
if (!vcpu->arch.pio.in) {
/* FIXME: return into emulator if single-stepping. */
@@ -8801,6 +8894,12 @@ writeback:
unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu);
toggle_interruptibility(vcpu, ctxt->interruptibility);
vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
+
+ /*
+ * Note, EXCPT_DB is assumed to be fault-like as the emulator
+ * only supports code breakpoints and general detect #DB, both
+ * of which are fault-like.
+ */
if (!ctxt->have_exception ||
exception_type(ctxt->exception.vector) == EXCPT_TRAP) {
kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_INSTRUCTIONS);
@@ -9662,74 +9761,155 @@ int kvm_check_nested_events(struct kvm_vcpu *vcpu)
static void kvm_inject_exception(struct kvm_vcpu *vcpu)
{
- trace_kvm_inj_exception(vcpu->arch.exception.nr,
+ trace_kvm_inj_exception(vcpu->arch.exception.vector,
vcpu->arch.exception.has_error_code,
vcpu->arch.exception.error_code,
vcpu->arch.exception.injected);
if (vcpu->arch.exception.error_code && !is_protmode(vcpu))
vcpu->arch.exception.error_code = false;
- static_call(kvm_x86_queue_exception)(vcpu);
+ static_call(kvm_x86_inject_exception)(vcpu);
}
-static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit)
+/*
+ * Check for any event (interrupt or exception) that is ready to be injected,
+ * and if there is at least one event, inject the event with the highest
+ * priority. This handles both "pending" events, i.e. events that have never
+ * been injected into the guest, and "injected" events, i.e. events that were
+ * injected as part of a previous VM-Enter, but weren't successfully delivered
+ * and need to be re-injected.
+ *
+ * Note, this is not guaranteed to be invoked on a guest instruction boundary,
+ * i.e. doesn't guarantee that there's an event window in the guest. KVM must
+ * be able to inject exceptions in the "middle" of an instruction, and so must
+ * also be able to re-inject NMIs and IRQs in the middle of an instruction.
+ * I.e. for exceptions and re-injected events, NOT invoking this on instruction
+ * boundaries is necessary and correct.
+ *
+ * For simplicity, KVM uses a single path to inject all events (except events
+ * that are injected directly from L1 to L2) and doesn't explicitly track
+ * instruction boundaries for asynchronous events. However, because VM-Exits
+ * that can occur during instruction execution typically result in KVM skipping
+ * the instruction or injecting an exception, e.g. instruction and exception
+ * intercepts, and because pending exceptions have higher priority than pending
+ * interrupts, KVM still honors instruction boundaries in most scenarios.
+ *
+ * But, if a VM-Exit occurs during instruction execution, and KVM does NOT skip
+ * the instruction or inject an exception, then KVM can incorrecty inject a new
+ * asynchrounous event if the event became pending after the CPU fetched the
+ * instruction (in the guest). E.g. if a page fault (#PF, #NPF, EPT violation)
+ * occurs and is resolved by KVM, a coincident NMI, SMI, IRQ, etc... can be
+ * injected on the restarted instruction instead of being deferred until the
+ * instruction completes.
+ *
+ * In practice, this virtualization hole is unlikely to be observed by the
+ * guest, and even less likely to cause functional problems. To detect the
+ * hole, the guest would have to trigger an event on a side effect of an early
+ * phase of instruction execution, e.g. on the instruction fetch from memory.
+ * And for it to be a functional problem, the guest would need to depend on the
+ * ordering between that side effect, the instruction completing, _and_ the
+ * delivery of the asynchronous event.
+ */
+static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
+ bool *req_immediate_exit)
{
+ bool can_inject;
int r;
- bool can_inject = true;
- /* try to reinject previous events if any */
+ /*
+ * Process nested events first, as nested VM-Exit supercedes event
+ * re-injection. If there's an event queued for re-injection, it will
+ * be saved into the appropriate vmc{b,s}12 fields on nested VM-Exit.
+ */
+ if (is_guest_mode(vcpu))
+ r = kvm_check_nested_events(vcpu);
+ else
+ r = 0;
- if (vcpu->arch.exception.injected) {
- kvm_inject_exception(vcpu);
- can_inject = false;
- }
/*
- * Do not inject an NMI or interrupt if there is a pending
- * exception. Exceptions and interrupts are recognized at
- * instruction boundaries, i.e. the start of an instruction.
- * Trap-like exceptions, e.g. #DB, have higher priority than
- * NMIs and interrupts, i.e. traps are recognized before an
- * NMI/interrupt that's pending on the same instruction.
- * Fault-like exceptions, e.g. #GP and #PF, are the lowest
- * priority, but are only generated (pended) during instruction
- * execution, i.e. a pending fault-like exception means the
- * fault occurred on the *previous* instruction and must be
- * serviced prior to recognizing any new events in order to
- * fully complete the previous instruction.
+ * Re-inject exceptions and events *especially* if immediate entry+exit
+ * to/from L2 is needed, as any event that has already been injected
+ * into L2 needs to complete its lifecycle before injecting a new event.
+ *
+ * Don't re-inject an NMI or interrupt if there is a pending exception.
+ * This collision arises if an exception occurred while vectoring the
+ * injected event, KVM intercepted said exception, and KVM ultimately
+ * determined the fault belongs to the guest and queues the exception
+ * for injection back into the guest.
+ *
+ * "Injected" interrupts can also collide with pending exceptions if
+ * userspace ignores the "ready for injection" flag and blindly queues
+ * an interrupt. In that case, prioritizing the exception is correct,
+ * as the exception "occurred" before the exit to userspace. Trap-like
+ * exceptions, e.g. most #DBs, have higher priority than interrupts.
+ * And while fault-like exceptions, e.g. #GP and #PF, are the lowest
+ * priority, they're only generated (pended) during instruction
+ * execution, and interrupts are recognized at instruction boundaries.
+ * Thus a pending fault-like exception means the fault occurred on the
+ * *previous* instruction and must be serviced prior to recognizing any
+ * new events in order to fully complete the previous instruction.
*/
- else if (!vcpu->arch.exception.pending) {
- if (vcpu->arch.nmi_injected) {
- static_call(kvm_x86_inject_nmi)(vcpu);
- can_inject = false;
- } else if (vcpu->arch.interrupt.injected) {
- static_call(kvm_x86_inject_irq)(vcpu, true);
- can_inject = false;
- }
- }
+ if (vcpu->arch.exception.injected)
+ kvm_inject_exception(vcpu);
+ else if (kvm_is_exception_pending(vcpu))
+ ; /* see above */
+ else if (vcpu->arch.nmi_injected)
+ static_call(kvm_x86_inject_nmi)(vcpu);
+ else if (vcpu->arch.interrupt.injected)
+ static_call(kvm_x86_inject_irq)(vcpu, true);
+ /*
+ * Exceptions that morph to VM-Exits are handled above, and pending
+ * exceptions on top of injected exceptions that do not VM-Exit should
+ * either morph to #DF or, sadly, override the injected exception.
+ */
WARN_ON_ONCE(vcpu->arch.exception.injected &&
vcpu->arch.exception.pending);
/*
- * Call check_nested_events() even if we reinjected a previous event
- * in order for caller to determine if it should require immediate-exit
- * from L2 to L1 due to pending L1 events which require exit
- * from L2 to L1.
+ * Bail if immediate entry+exit to/from the guest is needed to complete
+ * nested VM-Enter or event re-injection so that a different pending
+ * event can be serviced (or if KVM needs to exit to userspace).
+ *
+ * Otherwise, continue processing events even if VM-Exit occurred. The
+ * VM-Exit will have cleared exceptions that were meant for L2, but
+ * there may now be events that can be injected into L1.
*/
- if (is_guest_mode(vcpu)) {
- r = kvm_check_nested_events(vcpu);
- if (r < 0)
- goto out;
- }
+ if (r < 0)
+ goto out;
+
+ /*
+ * A pending exception VM-Exit should either result in nested VM-Exit
+ * or force an immediate re-entry and exit to/from L2, and exception
+ * VM-Exits cannot be injected (flag should _never_ be set).
+ */
+ WARN_ON_ONCE(vcpu->arch.exception_vmexit.injected ||
+ vcpu->arch.exception_vmexit.pending);
+
+ /*
+ * New events, other than exceptions, cannot be injected if KVM needs
+ * to re-inject a previous event. See above comments on re-injecting
+ * for why pending exceptions get priority.
+ */
+ can_inject = !kvm_event_needs_reinjection(vcpu);
- /* try to inject new event if pending */
if (vcpu->arch.exception.pending) {
- if (exception_type(vcpu->arch.exception.nr) == EXCPT_FAULT)
+ /*
+ * Fault-class exceptions, except #DBs, set RF=1 in the RFLAGS
+ * value pushed on the stack. Trap-like exception and all #DBs
+ * leave RF as-is (KVM follows Intel's behavior in this regard;
+ * AMD states that code breakpoint #DBs excplitly clear RF=0).
+ *
+ * Note, most versions of Intel's SDM and AMD's APM incorrectly
+ * describe the behavior of General Detect #DBs, which are
+ * fault-like. They do _not_ set RF, a la code breakpoints.
+ */
+ if (exception_type(vcpu->arch.exception.vector) == EXCPT_FAULT)
__kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) |
X86_EFLAGS_RF);
- if (vcpu->arch.exception.nr == DB_VECTOR) {
- kvm_deliver_exception_payload(vcpu);
+ if (vcpu->arch.exception.vector == DB_VECTOR) {
+ kvm_deliver_exception_payload(vcpu, &vcpu->arch.exception);
if (vcpu->arch.dr7 & DR7_GD) {
vcpu->arch.dr7 &= ~DR7_GD;
kvm_update_dr7(vcpu);
@@ -9801,11 +9981,11 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit)
}
if (is_guest_mode(vcpu) &&
- kvm_x86_ops.nested_ops->hv_timer_pending &&
- kvm_x86_ops.nested_ops->hv_timer_pending(vcpu))
+ kvm_x86_ops.nested_ops->has_events &&
+ kvm_x86_ops.nested_ops->has_events(vcpu))
*req_immediate_exit = true;
- WARN_ON(vcpu->arch.exception.pending);
+ WARN_ON(kvm_is_exception_pending(vcpu));
return 0;
out:
@@ -10110,7 +10290,7 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu)
* When APICv gets disabled, we may still have injected interrupts
* pending. At the same time, KVM_REQ_EVENT may not be set as APICv was
* still active when the interrupt got accepted. Make sure
- * inject_pending_event() is called to check for that.
+ * kvm_check_and_inject_events() is called to check for that.
*/
if (!apic->apicv_active)
kvm_make_request(KVM_REQ_EVENT, vcpu);
@@ -10407,7 +10587,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
goto out;
}
- r = inject_pending_event(vcpu, &req_immediate_exit);
+ r = kvm_check_and_inject_events(vcpu, &req_immediate_exit);
if (r < 0) {
r = 0;
goto out;
@@ -10646,10 +10826,26 @@ static inline int vcpu_block(struct kvm_vcpu *vcpu)
if (hv_timer)
kvm_lapic_switch_to_hv_timer(vcpu);
- if (!kvm_check_request(KVM_REQ_UNHALT, vcpu))
+ /*
+ * If the vCPU is not runnable, a signal or another host event
+ * of some kind is pending; service it without changing the
+ * vCPU's activity state.
+ */
+ if (!kvm_arch_vcpu_runnable(vcpu))
return 1;
}
+ /*
+ * Evaluate nested events before exiting the halted state. This allows
+ * the halt state to be recorded properly in the VMCS12's activity
+ * state field (AMD does not have a similar field and a VM-Exit always
+ * causes a spurious wakeup from HLT).
+ */
+ if (is_guest_mode(vcpu)) {
+ if (kvm_check_nested_events(vcpu) < 0)
+ return 0;
+ }
+
if (kvm_apic_accept_events(vcpu) < 0)
return 0;
switch(vcpu->arch.mp_state) {
@@ -10673,9 +10869,6 @@ static inline int vcpu_block(struct kvm_vcpu *vcpu)
static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu)
{
- if (is_guest_mode(vcpu))
- kvm_check_nested_events(vcpu);
-
return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
!vcpu->arch.apf.halted);
}
@@ -10824,6 +11017,7 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
{
+ struct kvm_queued_exception *ex = &vcpu->arch.exception;
struct kvm_run *kvm_run = vcpu->run;
int r;
@@ -10852,7 +11046,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
r = 0;
goto out;
}
- kvm_clear_request(KVM_REQ_UNHALT, vcpu);
r = -EAGAIN;
if (signal_pending(current)) {
r = -EINTR;
@@ -10882,6 +11075,21 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
}
}
+ /*
+ * If userspace set a pending exception and L2 is active, convert it to
+ * a pending VM-Exit if L1 wants to intercept the exception.
+ */
+ if (vcpu->arch.exception_from_userspace && is_guest_mode(vcpu) &&
+ kvm_x86_ops.nested_ops->is_exception_vmexit(vcpu, ex->vector,
+ ex->error_code)) {
+ kvm_queue_exception_vmexit(vcpu, ex->vector,
+ ex->has_error_code, ex->error_code,
+ ex->has_payload, ex->payload);
+ ex->injected = false;
+ ex->pending = false;
+ }
+ vcpu->arch.exception_from_userspace = false;
+
if (unlikely(vcpu->arch.complete_userspace_io)) {
int (*cui)(struct kvm_vcpu *) = vcpu->arch.complete_userspace_io;
vcpu->arch.complete_userspace_io = NULL;
@@ -10988,6 +11196,7 @@ static void __set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
kvm_set_rflags(vcpu, regs->rflags | X86_EFLAGS_FIXED);
vcpu->arch.exception.pending = false;
+ vcpu->arch.exception_vmexit.pending = false;
kvm_make_request(KVM_REQ_EVENT, vcpu);
}
@@ -11125,11 +11334,12 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
}
/*
- * KVM_MP_STATE_INIT_RECEIVED means the processor is in
- * INIT state; latched init should be reported using
- * KVM_SET_VCPU_EVENTS, so reject it here.
+ * Pending INITs are reported using KVM_SET_VCPU_EVENTS, disallow
+ * forcing the guest into INIT/SIPI if those events are supposed to be
+ * blocked. KVM prioritizes SMI over INIT, so reject INIT/SIPI state
+ * if an SMI is pending as well.
*/
- if ((kvm_vcpu_latch_init(vcpu) || vcpu->arch.smi_pending) &&
+ if ((!kvm_apic_init_sipi_allowed(vcpu) || vcpu->arch.smi_pending) &&
(mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED ||
mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED))
goto out;
@@ -11368,7 +11578,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) {
r = -EBUSY;
- if (vcpu->arch.exception.pending)
+ if (kvm_is_exception_pending(vcpu))
goto out;
if (dbg->control & KVM_GUESTDBG_INJECT_DB)
kvm_queue_exception(vcpu, DB_VECTOR);
@@ -11750,8 +11960,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
struct fpstate *fpstate = vcpu->arch.guest_fpu.fpstate;
/*
- * To avoid have the INIT path from kvm_apic_has_events() that be
- * called with loaded FPU and does not let userspace fix the state.
+ * All paths that lead to INIT are required to load the guest's
+ * FPU state (because most paths are buried in KVM_RUN).
*/
if (init_event)
kvm_put_guest_fpu(vcpu);
@@ -12080,6 +12290,10 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
if (ret)
goto out_page_track;
+ ret = static_call(kvm_x86_vm_init)(kvm);
+ if (ret)
+ goto out_uninit_mmu;
+
INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
atomic_set(&kvm->arch.noncoherent_dma_count, 0);
@@ -12115,8 +12329,10 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm_hv_init_vm(kvm);
kvm_xen_init_vm(kvm);
- return static_call(kvm_x86_vm_init)(kvm);
+ return 0;
+out_uninit_mmu:
+ kvm_mmu_uninit_vm(kvm);
out_page_track:
kvm_page_track_cleanup(kvm);
out:
@@ -12589,13 +12805,14 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
if (!list_empty_careful(&vcpu->async_pf.done))
return true;
- if (kvm_apic_has_events(vcpu))
+ if (kvm_apic_has_pending_init_or_sipi(vcpu) &&
+ kvm_apic_init_sipi_allowed(vcpu))
return true;
if (vcpu->arch.pv.pv_unhalted)
return true;
- if (vcpu->arch.exception.pending)
+ if (kvm_is_exception_pending(vcpu))
return true;
if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
@@ -12617,16 +12834,13 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
return true;
if (is_guest_mode(vcpu) &&
- kvm_x86_ops.nested_ops->hv_timer_pending &&
- kvm_x86_ops.nested_ops->hv_timer_pending(vcpu))
+ kvm_x86_ops.nested_ops->has_events &&
+ kvm_x86_ops.nested_ops->has_events(vcpu))
return true;
if (kvm_xen_has_pending_events(vcpu))
return true;
- if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu))
- return true;
-
return false;
}
@@ -12850,7 +13064,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
{
if (unlikely(!lapic_in_kernel(vcpu) ||
kvm_event_needs_reinjection(vcpu) ||
- vcpu->arch.exception.pending))
+ kvm_is_exception_pending(vcpu)))
return false;
if (kvm_hlt_in_guest(vcpu->kvm) && !kvm_can_deliver_async_pf(vcpu))
@@ -13401,7 +13615,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr);
-EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmrun);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmenter);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 1926d2cb8e79..829d3134c1eb 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -82,10 +82,18 @@ static inline unsigned int __shrink_ple_window(unsigned int val,
void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu);
int kvm_check_nested_events(struct kvm_vcpu *vcpu);
+static inline bool kvm_is_exception_pending(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.exception.pending ||
+ vcpu->arch.exception_vmexit.pending ||
+ kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu);
+}
+
static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu)
{
vcpu->arch.exception.pending = false;
vcpu->arch.exception.injected = false;
+ vcpu->arch.exception_vmexit.pending = false;
}
static inline void kvm_queue_interrupt(struct kvm_vcpu *vcpu, u8 vector,
@@ -267,11 +275,6 @@ static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk)
return !(kvm->arch.disabled_quirks & quirk);
}
-static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu)
-{
- return is_smm(vcpu) || static_call(kvm_x86_apic_init_signal_blocked)(vcpu);
-}
-
void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
u64 get_kvmclock_ns(struct kvm *kvm);
@@ -286,7 +289,8 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu,
int handle_ud(struct kvm_vcpu *vcpu);
-void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu);
+void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu,
+ struct kvm_queued_exception *ex);
void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu);
u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 280cb5dc7341..93c628d3e3a9 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -1065,7 +1065,6 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode,
del_timer(&vcpu->arch.xen.poll_timer);
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
- kvm_clear_request(KVM_REQ_UNHALT, vcpu);
}
vcpu->arch.xen.poll_evtchn = 0;
diff --git a/drivers/base/node.c b/drivers/base/node.c
index eb0f43784c2b..432d40a5f910 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -433,6 +433,7 @@ static ssize_t node_read_meminfo(struct device *dev,
"Node %d ShadowCallStack:%8lu kB\n"
#endif
"Node %d PageTables: %8lu kB\n"
+ "Node %d SecPageTables: %8lu kB\n"
"Node %d NFS_Unstable: %8lu kB\n"
"Node %d Bounce: %8lu kB\n"
"Node %d WritebackTmp: %8lu kB\n"
@@ -459,6 +460,7 @@ static ssize_t node_read_meminfo(struct device *dev,
nid, node_page_state(pgdat, NR_KERNEL_SCS_KB),
#endif
nid, K(node_page_state(pgdat, NR_PAGETABLE)),
+ nid, K(node_page_state(pgdat, NR_SECONDARY_PAGETABLE)),
nid, 0UL,
nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)),
nid, K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 6e89f0e2fd20..208efd4fa52c 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -115,6 +115,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
#endif
show_val_kb(m, "PageTables: ",
global_node_page_state(NR_PAGETABLE));
+ show_val_kb(m, "SecPageTables: ",
+ global_node_page_state(NR_SECONDARY_PAGETABLE));
show_val_kb(m, "NFS_Unstable: ", 0);
show_val_kb(m, "Bounce: ",
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index f4519d3689e1..32f259fa5801 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -151,12 +151,11 @@ static inline bool is_error_page(struct page *page)
#define KVM_REQUEST_NO_ACTION BIT(10)
/*
* Architecture-independent vcpu->requests bit members
- * Bits 4-7 are reserved for more arch-independent bits.
+ * Bits 3-7 are reserved for more arch-independent bits.
*/
#define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_VM_DEAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_UNBLOCK 2
-#define KVM_REQ_UNHALT 3
#define KVM_REQUEST_ARCH_BASE 8
/*
@@ -2248,6 +2247,19 @@ static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu)
#endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */
/*
+ * If more than one page is being (un)accounted, @virt must be the address of
+ * the first page of a block of pages what were allocated together (i.e
+ * accounted together).
+ *
+ * kvm_account_pgtable_pages() is thread-safe because mod_lruvec_page_state()
+ * is thread-safe.
+ */
+static inline void kvm_account_pgtable_pages(void *virt, int nr)
+{
+ mod_lruvec_page_state(virt_to_page(virt), NR_SECONDARY_PAGETABLE, nr);
+}
+
+/*
* This defines how many reserved entries we want to keep before we
* kick the vcpu to the userspace to avoid dirty ring full. This
* value can be tuned to higher if e.g. PML is enabled on the host.
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index e24b40c52468..355d842d2731 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -216,6 +216,7 @@ enum node_stat_item {
NR_KERNEL_SCS_KB, /* measured in KiB */
#endif
NR_PAGETABLE, /* used for pagetables */
+ NR_SECONDARY_PAGETABLE, /* secondary pagetables, e.g. KVM pagetables */
#ifdef CONFIG_SWAP
NR_SWAPCACHE,
#endif
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b69979c9ced5..9d054e3767ce 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1401,6 +1401,7 @@ static const struct memory_stat memory_stats[] = {
{ "kernel", MEMCG_KMEM },
{ "kernel_stack", NR_KERNEL_STACK_KB },
{ "pagetables", NR_PAGETABLE },
+ { "sec_pagetables", NR_SECONDARY_PAGETABLE },
{ "percpu", MEMCG_PERCPU_B },
{ "sock", MEMCG_SOCK },
{ "vmalloc", MEMCG_VMALLOC },
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d04211f0ef0b..08522a831c7a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6085,7 +6085,8 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
" active_file:%lu inactive_file:%lu isolated_file:%lu\n"
" unevictable:%lu dirty:%lu writeback:%lu\n"
" slab_reclaimable:%lu slab_unreclaimable:%lu\n"
- " mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n"
+ " mapped:%lu shmem:%lu pagetables:%lu\n"
+ " sec_pagetables:%lu bounce:%lu\n"
" kernel_misc_reclaimable:%lu\n"
" free:%lu free_pcp:%lu free_cma:%lu\n",
global_node_page_state(NR_ACTIVE_ANON),
@@ -6102,6 +6103,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
global_node_page_state(NR_FILE_MAPPED),
global_node_page_state(NR_SHMEM),
global_node_page_state(NR_PAGETABLE),
+ global_node_page_state(NR_SECONDARY_PAGETABLE),
global_zone_page_state(NR_BOUNCE),
global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE),
global_zone_page_state(NR_FREE_PAGES),
@@ -6135,6 +6137,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
" shadow_call_stack:%lukB"
#endif
" pagetables:%lukB"
+ " sec_pagetables:%lukB"
" all_unreclaimable? %s"
"\n",
pgdat->node_id,
@@ -6160,6 +6163,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
node_page_state(pgdat, NR_KERNEL_SCS_KB),
#endif
K(node_page_state(pgdat, NR_PAGETABLE)),
+ K(node_page_state(pgdat, NR_SECONDARY_PAGETABLE)),
pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ?
"yes" : "no");
}
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 90af9a8572f5..da264a040c55 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1247,6 +1247,7 @@ const char * const vmstat_text[] = {
"nr_shadow_call_stack",
#endif
"nr_page_table_pages",
+ "nr_sec_page_table_pages",
#ifdef CONFIG_SWAP
"nr_swapcached",
#endif
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index d625a3f83780..45d9aee1c0d8 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -28,6 +28,7 @@
/x86_64/max_vcpuid_cap_test
/x86_64/mmio_warning_test
/x86_64/monitor_mwait_test
+/x86_64/nested_exceptions_test
/x86_64/nx_huge_pages_test
/x86_64/platform_info_test
/x86_64/pmu_event_filter_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 6448cb9f710f..fde3ae8cfa4c 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -91,6 +91,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/kvm_clock_test
TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test
TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test
TEST_GEN_PROGS_x86_64 += x86_64/monitor_mwait_test
+TEST_GEN_PROGS_x86_64 += x86_64/nested_exceptions_test
TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test
TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id
diff --git a/tools/testing/selftests/kvm/include/x86_64/evmcs.h b/tools/testing/selftests/kvm/include/x86_64/evmcs.h
index 3c9260f8e116..58db74f68af2 100644
--- a/tools/testing/selftests/kvm/include/x86_64/evmcs.h
+++ b/tools/testing/selftests/kvm/include/x86_64/evmcs.h
@@ -203,14 +203,25 @@ struct hv_enlightened_vmcs {
u32 reserved:30;
} hv_enlightenments_control;
u32 hv_vp_id;
-
+ u32 padding32_2;
u64 hv_vm_id;
u64 partition_assist_page;
u64 padding64_4[4];
u64 guest_bndcfgs;
- u64 padding64_5[7];
+ u64 guest_ia32_perf_global_ctrl;
+ u64 guest_ia32_s_cet;
+ u64 guest_ssp;
+ u64 guest_ia32_int_ssp_table_addr;
+ u64 guest_ia32_lbr_ctl;
+ u64 padding64_5[2];
u64 xss_exit_bitmap;
- u64 padding64_6[7];
+ u64 encls_exiting_bitmap;
+ u64 host_ia32_perf_global_ctrl;
+ u64 tsc_multiplier;
+ u64 host_ia32_s_cet;
+ u64 host_ssp;
+ u64 host_ia32_int_ssp_table_addr;
+ u64 padding64_6;
};
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE 0
@@ -656,6 +667,18 @@ static inline int evmcs_vmread(uint64_t encoding, uint64_t *value)
case VIRTUAL_PROCESSOR_ID:
*value = current_evmcs->virtual_processor_id;
break;
+ case HOST_IA32_PERF_GLOBAL_CTRL:
+ *value = current_evmcs->host_ia32_perf_global_ctrl;
+ break;
+ case GUEST_IA32_PERF_GLOBAL_CTRL:
+ *value = current_evmcs->guest_ia32_perf_global_ctrl;
+ break;
+ case ENCLS_EXITING_BITMAP:
+ *value = current_evmcs->encls_exiting_bitmap;
+ break;
+ case TSC_MULTIPLIER:
+ *value = current_evmcs->tsc_multiplier;
+ break;
default: return 1;
}
@@ -1169,6 +1192,22 @@ static inline int evmcs_vmwrite(uint64_t encoding, uint64_t value)
current_evmcs->virtual_processor_id = value;
current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT;
break;
+ case HOST_IA32_PERF_GLOBAL_CTRL:
+ current_evmcs->host_ia32_perf_global_ctrl = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+ break;
+ case GUEST_IA32_PERF_GLOBAL_CTRL:
+ current_evmcs->guest_ia32_perf_global_ctrl = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
+ break;
+ case ENCLS_EXITING_BITMAP:
+ current_evmcs->encls_exiting_bitmap = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2;
+ break;
+ case TSC_MULTIPLIER:
+ current_evmcs->tsc_multiplier = value;
+ current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2;
+ break;
default: return 1;
}
diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86_64/svm_util.h
index a339b537a575..7aee6244ab6a 100644
--- a/tools/testing/selftests/kvm/include/x86_64/svm_util.h
+++ b/tools/testing/selftests/kvm/include/x86_64/svm_util.h
@@ -9,15 +9,12 @@
#ifndef SELFTEST_KVM_SVM_UTILS_H
#define SELFTEST_KVM_SVM_UTILS_H
+#include <asm/svm.h>
+
#include <stdint.h>
#include "svm.h"
#include "processor.h"
-#define SVM_EXIT_EXCP_BASE 0x040
-#define SVM_EXIT_HLT 0x078
-#define SVM_EXIT_MSR 0x07c
-#define SVM_EXIT_VMMCALL 0x081
-
struct svm_test_data {
/* VMCB */
struct vmcb *vmcb; /* gva */
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index 790c6d1ecb34..71b290b6469d 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -8,6 +8,8 @@
#ifndef SELFTEST_KVM_VMX_H
#define SELFTEST_KVM_VMX_H
+#include <asm/vmx.h>
+
#include <stdint.h>
#include "processor.h"
#include "apic.h"
@@ -100,55 +102,6 @@
#define VMX_EPT_VPID_CAP_AD_BITS 0x00200000
#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_INTERRUPT_WINDOW 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,
@@ -208,6 +161,8 @@ enum vmcs_field {
VMWRITE_BITMAP_HIGH = 0x00002029,
XSS_EXIT_BITMAP = 0x0000202C,
XSS_EXIT_BITMAP_HIGH = 0x0000202D,
+ ENCLS_EXITING_BITMAP = 0x0000202E,
+ ENCLS_EXITING_BITMAP_HIGH = 0x0000202F,
TSC_MULTIPLIER = 0x00002032,
TSC_MULTIPLIER_HIGH = 0x00002033,
GUEST_PHYSICAL_ADDRESS = 0x00002400,
diff --git a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c b/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c
new file mode 100644
index 000000000000..ac33835f78f4
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c
@@ -0,0 +1,295 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#define _GNU_SOURCE /* for program_invocation_short_name */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+#include "svm_util.h"
+
+#define L2_GUEST_STACK_SIZE 256
+
+/*
+ * Arbitrary, never shoved into KVM/hardware, just need to avoid conflict with
+ * the "real" exceptions used, #SS/#GP/#DF (12/13/8).
+ */
+#define FAKE_TRIPLE_FAULT_VECTOR 0xaa
+
+/* Arbitrary 32-bit error code injected by this test. */
+#define SS_ERROR_CODE 0xdeadbeef
+
+/*
+ * Bit '0' is set on Intel if the exception occurs while delivering a previous
+ * event/exception. AMD's wording is ambiguous, but presumably the bit is set
+ * if the exception occurs while delivering an external event, e.g. NMI or INTR,
+ * but not for exceptions that occur when delivering other exceptions or
+ * software interrupts.
+ *
+ * Note, Intel's name for it, "External event", is misleading and much more
+ * aligned with AMD's behavior, but the SDM is quite clear on its behavior.
+ */
+#define ERROR_CODE_EXT_FLAG BIT(0)
+
+/*
+ * Bit '1' is set if the fault occurred when looking up a descriptor in the
+ * IDT, which is the case here as the IDT is empty/NULL.
+ */
+#define ERROR_CODE_IDT_FLAG BIT(1)
+
+/*
+ * The #GP that occurs when vectoring #SS should show the index into the IDT
+ * for #SS, plus have the "IDT flag" set.
+ */
+#define GP_ERROR_CODE_AMD ((SS_VECTOR * 8) | ERROR_CODE_IDT_FLAG)
+#define GP_ERROR_CODE_INTEL ((SS_VECTOR * 8) | ERROR_CODE_IDT_FLAG | ERROR_CODE_EXT_FLAG)
+
+/*
+ * Intel and AMD both shove '0' into the error code on #DF, regardless of what
+ * led to the double fault.
+ */
+#define DF_ERROR_CODE 0
+
+#define INTERCEPT_SS (BIT_ULL(SS_VECTOR))
+#define INTERCEPT_SS_DF (INTERCEPT_SS | BIT_ULL(DF_VECTOR))
+#define INTERCEPT_SS_GP_DF (INTERCEPT_SS_DF | BIT_ULL(GP_VECTOR))
+
+static void l2_ss_pending_test(void)
+{
+ GUEST_SYNC(SS_VECTOR);
+}
+
+static void l2_ss_injected_gp_test(void)
+{
+ GUEST_SYNC(GP_VECTOR);
+}
+
+static void l2_ss_injected_df_test(void)
+{
+ GUEST_SYNC(DF_VECTOR);
+}
+
+static void l2_ss_injected_tf_test(void)
+{
+ GUEST_SYNC(FAKE_TRIPLE_FAULT_VECTOR);
+}
+
+static void svm_run_l2(struct svm_test_data *svm, void *l2_code, int vector,
+ uint32_t error_code)
+{
+ struct vmcb *vmcb = svm->vmcb;
+ struct vmcb_control_area *ctrl = &vmcb->control;
+
+ vmcb->save.rip = (u64)l2_code;
+ run_guest(vmcb, svm->vmcb_gpa);
+
+ if (vector == FAKE_TRIPLE_FAULT_VECTOR)
+ return;
+
+ GUEST_ASSERT_EQ(ctrl->exit_code, (SVM_EXIT_EXCP_BASE + vector));
+ GUEST_ASSERT_EQ(ctrl->exit_info_1, error_code);
+}
+
+static void l1_svm_code(struct svm_test_data *svm)
+{
+ struct vmcb_control_area *ctrl = &svm->vmcb->control;
+ unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+
+ generic_svm_setup(svm, NULL, &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+ svm->vmcb->save.idtr.limit = 0;
+ ctrl->intercept |= BIT_ULL(INTERCEPT_SHUTDOWN);
+
+ ctrl->intercept_exceptions = INTERCEPT_SS_GP_DF;
+ svm_run_l2(svm, l2_ss_pending_test, SS_VECTOR, SS_ERROR_CODE);
+ svm_run_l2(svm, l2_ss_injected_gp_test, GP_VECTOR, GP_ERROR_CODE_AMD);
+
+ ctrl->intercept_exceptions = INTERCEPT_SS_DF;
+ svm_run_l2(svm, l2_ss_injected_df_test, DF_VECTOR, DF_ERROR_CODE);
+
+ ctrl->intercept_exceptions = INTERCEPT_SS;
+ svm_run_l2(svm, l2_ss_injected_tf_test, FAKE_TRIPLE_FAULT_VECTOR, 0);
+ GUEST_ASSERT_EQ(ctrl->exit_code, SVM_EXIT_SHUTDOWN);
+
+ GUEST_DONE();
+}
+
+static void vmx_run_l2(void *l2_code, int vector, uint32_t error_code)
+{
+ GUEST_ASSERT(!vmwrite(GUEST_RIP, (u64)l2_code));
+
+ GUEST_ASSERT_EQ(vector == SS_VECTOR ? vmlaunch() : vmresume(), 0);
+
+ if (vector == FAKE_TRIPLE_FAULT_VECTOR)
+ return;
+
+ GUEST_ASSERT_EQ(vmreadz(VM_EXIT_REASON), EXIT_REASON_EXCEPTION_NMI);
+ GUEST_ASSERT_EQ((vmreadz(VM_EXIT_INTR_INFO) & 0xff), vector);
+ GUEST_ASSERT_EQ(vmreadz(VM_EXIT_INTR_ERROR_CODE), error_code);
+}
+
+static void l1_vmx_code(struct vmx_pages *vmx)
+{
+ unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+
+ GUEST_ASSERT_EQ(prepare_for_vmx_operation(vmx), true);
+
+ GUEST_ASSERT_EQ(load_vmcs(vmx), true);
+
+ prepare_vmcs(vmx, NULL, &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+ GUEST_ASSERT_EQ(vmwrite(GUEST_IDTR_LIMIT, 0), 0);
+
+ /*
+ * VMX disallows injecting an exception with error_code[31:16] != 0,
+ * and hardware will never generate a VM-Exit with bits 31:16 set.
+ * KVM should likewise truncate the "bad" userspace value.
+ */
+ GUEST_ASSERT_EQ(vmwrite(EXCEPTION_BITMAP, INTERCEPT_SS_GP_DF), 0);
+ vmx_run_l2(l2_ss_pending_test, SS_VECTOR, (u16)SS_ERROR_CODE);
+ vmx_run_l2(l2_ss_injected_gp_test, GP_VECTOR, GP_ERROR_CODE_INTEL);
+
+ GUEST_ASSERT_EQ(vmwrite(EXCEPTION_BITMAP, INTERCEPT_SS_DF), 0);
+ vmx_run_l2(l2_ss_injected_df_test, DF_VECTOR, DF_ERROR_CODE);
+
+ GUEST_ASSERT_EQ(vmwrite(EXCEPTION_BITMAP, INTERCEPT_SS), 0);
+ vmx_run_l2(l2_ss_injected_tf_test, FAKE_TRIPLE_FAULT_VECTOR, 0);
+ GUEST_ASSERT_EQ(vmreadz(VM_EXIT_REASON), EXIT_REASON_TRIPLE_FAULT);
+
+ GUEST_DONE();
+}
+
+static void __attribute__((__flatten__)) l1_guest_code(void *test_data)
+{
+ if (this_cpu_has(X86_FEATURE_SVM))
+ l1_svm_code(test_data);
+ else
+ l1_vmx_code(test_data);
+}
+
+static void assert_ucall_vector(struct kvm_vcpu *vcpu, int vector)
+{
+ struct kvm_run *run = vcpu->run;
+ struct ucall uc;
+
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Unexpected exit reason: %u (%s),\n",
+ run->exit_reason, exit_reason_str(run->exit_reason));
+
+ switch (get_ucall(vcpu, &uc)) {
+ case UCALL_SYNC:
+ TEST_ASSERT(vector == uc.args[1],
+ "Expected L2 to ask for %d, got %ld", vector, uc.args[1]);
+ break;
+ case UCALL_DONE:
+ TEST_ASSERT(vector == -1,
+ "Expected L2 to ask for %d, L2 says it's done", vector);
+ break;
+ case UCALL_ABORT:
+ TEST_FAIL("%s at %s:%ld (0x%lx != 0x%lx)",
+ (const char *)uc.args[0], __FILE__, uc.args[1],
+ uc.args[2], uc.args[3]);
+ break;
+ default:
+ TEST_FAIL("Expected L2 to ask for %d, got unexpected ucall %lu", vector, uc.cmd);
+ }
+}
+
+static void queue_ss_exception(struct kvm_vcpu *vcpu, bool inject)
+{
+ struct kvm_vcpu_events events;
+
+ vcpu_events_get(vcpu, &events);
+
+ TEST_ASSERT(!events.exception.pending,
+ "Vector %d unexpectedlt pending", events.exception.nr);
+ TEST_ASSERT(!events.exception.injected,
+ "Vector %d unexpectedly injected", events.exception.nr);
+
+ events.flags = KVM_VCPUEVENT_VALID_PAYLOAD;
+ events.exception.pending = !inject;
+ events.exception.injected = inject;
+ events.exception.nr = SS_VECTOR;
+ events.exception.has_error_code = true;
+ events.exception.error_code = SS_ERROR_CODE;
+ vcpu_events_set(vcpu, &events);
+}
+
+/*
+ * Verify KVM_{G,S}ET_EVENTS play nice with pending vs. injected exceptions
+ * when an exception is being queued for L2. Specifically, verify that KVM
+ * honors L1 exception intercept controls when a #SS is pending/injected,
+ * triggers a #GP on vectoring the #SS, morphs to #DF if #GP isn't intercepted
+ * by L1, and finally causes (nested) SHUTDOWN if #DF isn't intercepted by L1.
+ */
+int main(int argc, char *argv[])
+{
+ vm_vaddr_t nested_test_data_gva;
+ struct kvm_vcpu_events events;
+ struct kvm_vcpu *vcpu;
+ struct kvm_vm *vm;
+
+ TEST_REQUIRE(kvm_has_cap(KVM_CAP_EXCEPTION_PAYLOAD));
+ TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM) || kvm_cpu_has(X86_FEATURE_VMX));
+
+ vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
+ vm_enable_cap(vm, KVM_CAP_EXCEPTION_PAYLOAD, -2ul);
+
+ if (kvm_cpu_has(X86_FEATURE_SVM))
+ vcpu_alloc_svm(vm, &nested_test_data_gva);
+ else
+ vcpu_alloc_vmx(vm, &nested_test_data_gva);
+
+ vcpu_args_set(vcpu, 1, nested_test_data_gva);
+
+ /* Run L1 => L2. L2 should sync and request #SS. */
+ vcpu_run(vcpu);
+ assert_ucall_vector(vcpu, SS_VECTOR);
+
+ /* Pend #SS and request immediate exit. #SS should still be pending. */
+ queue_ss_exception(vcpu, false);
+ vcpu->run->immediate_exit = true;
+ vcpu_run_complete_io(vcpu);
+
+ /* Verify the pending events comes back out the same as it went in. */
+ vcpu_events_get(vcpu, &events);
+ ASSERT_EQ(events.flags & KVM_VCPUEVENT_VALID_PAYLOAD,
+ KVM_VCPUEVENT_VALID_PAYLOAD);
+ ASSERT_EQ(events.exception.pending, true);
+ ASSERT_EQ(events.exception.nr, SS_VECTOR);
+ ASSERT_EQ(events.exception.has_error_code, true);
+ ASSERT_EQ(events.exception.error_code, SS_ERROR_CODE);
+
+ /*
+ * Run for real with the pending #SS, L1 should get a VM-Exit due to
+ * #SS interception and re-enter L2 to request #GP (via injected #SS).
+ */
+ vcpu->run->immediate_exit = false;
+ vcpu_run(vcpu);
+ assert_ucall_vector(vcpu, GP_VECTOR);
+
+ /*
+ * Inject #SS, the #SS should bypass interception and cause #GP, which
+ * L1 should intercept before KVM morphs it to #DF. L1 should then
+ * disable #GP interception and run L2 to request #DF (via #SS => #GP).
+ */
+ queue_ss_exception(vcpu, true);
+ vcpu_run(vcpu);
+ assert_ucall_vector(vcpu, DF_VECTOR);
+
+ /*
+ * Inject #SS, the #SS should bypass interception and cause #GP, which
+ * L1 is no longer interception, and so should see a #DF VM-Exit. L1
+ * should then signal that is done.
+ */
+ queue_ss_exception(vcpu, true);
+ vcpu_run(vcpu);
+ assert_ucall_vector(vcpu, FAKE_TRIPLE_FAULT_VECTOR);
+
+ /*
+ * Inject #SS yet again. L1 is not intercepting #GP or #DF, and so
+ * should see nested TRIPLE_FAULT / SHUTDOWN.
+ */
+ queue_ss_exception(vcpu, true);
+ vcpu_run(vcpu);
+ assert_ucall_vector(vcpu, -1);
+
+ kvm_vm_free(vm);
+}
diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
index cc6421716400..e19933ea34ca 100644
--- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
+++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
@@ -118,13 +118,6 @@ void run_test(int reclaim_period_ms, bool disable_nx_huge_pages,
vm = vm_create(1);
if (disable_nx_huge_pages) {
- /*
- * Cannot run the test without NX huge pages if the kernel
- * does not support it.
- */
- if (!kvm_check_cap(KVM_CAP_VM_DISABLE_NX_HUGE_PAGES))
- return;
-
r = __vm_disable_nx_huge_pages(vm);
if (reboot_permissions) {
TEST_ASSERT(!r, "Disabling NX huge pages should succeed if process has reboot permissions");
@@ -248,18 +241,13 @@ int main(int argc, char **argv)
}
}
- if (token != MAGIC_TOKEN) {
- print_skip("This test must be run with the magic token %d.\n"
- "This is done by nx_huge_pages_test.sh, which\n"
- "also handles environment setup for the test.",
- MAGIC_TOKEN);
- exit(KSFT_SKIP);
- }
+ TEST_REQUIRE(kvm_has_cap(KVM_CAP_VM_DISABLE_NX_HUGE_PAGES));
+ TEST_REQUIRE(reclaim_period_ms > 0);
- if (!reclaim_period_ms) {
- print_skip("The NX reclaim period must be specified and non-zero");
- exit(KSFT_SKIP);
- }
+ __TEST_REQUIRE(token == MAGIC_TOKEN,
+ "This test must be run with the magic token %d.\n"
+ "This is done by nx_huge_pages_test.sh, which\n"
+ "also handles environment setup for the test.");
run_test(reclaim_period_ms, false, reboot_permissions);
run_test(reclaim_period_ms, true, reboot_permissions);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 584a5bab3af3..26383e63d9dd 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3409,10 +3409,8 @@ static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu)
int ret = -EINTR;
int idx = srcu_read_lock(&vcpu->kvm->srcu);
- if (kvm_arch_vcpu_runnable(vcpu)) {
- kvm_make_request(KVM_REQ_UNHALT, vcpu);
+ if (kvm_arch_vcpu_runnable(vcpu))
goto out;
- }
if (kvm_cpu_has_pending_timer(vcpu))
goto out;
if (signal_pending(current))
@@ -5881,7 +5879,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
r = kvm_async_pf_init();
if (r)
- goto out_free_5;
+ goto out_free_4;
kvm_chardev_ops.owner = module;
@@ -5905,10 +5903,9 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
out_unreg:
kvm_async_pf_deinit();
-out_free_5:
+out_free_4:
for_each_possible_cpu(cpu)
free_cpumask_var(per_cpu(cpu_kick_mask, cpu));
-out_free_4:
kmem_cache_destroy(kvm_vcpu_cache);
out_free_3:
unregister_reboot_notifier(&kvm_reboot_notifier);