summaryrefslogtreecommitdiff
path: root/virt/kvm/kvm_main.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-09-07 13:52:20 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2023-09-07 13:52:20 -0700
commit0c02183427b4d2002992f26d4917c1263c5d4a7f (patch)
tree426a0b282af3f309934cf0ff813b02c385e7ea04 /virt/kvm/kvm_main.c
parent4a0fc73da97efd23a383ca839e6fe86410268f6b (diff)
parentd011151616e73de20c139580b73fa4c7042bd861 (diff)
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm updates from Paolo Bonzini: "ARM: - Clean up vCPU targets, always returning generic v8 as the preferred target - Trap forwarding infrastructure for nested virtualization (used for traps that are taken from an L2 guest and are needed by the L1 hypervisor) - FEAT_TLBIRANGE support to only invalidate specific ranges of addresses when collapsing a table PTE to a block PTE. This avoids that the guest refills the TLBs again for addresses that aren't covered by the table PTE. - Fix vPMU issues related to handling of PMUver. - Don't unnecessary align non-stack allocations in the EL2 VA space - Drop HCR_VIRT_EXCP_MASK, which was never used... - Don't use smp_processor_id() in kvm_arch_vcpu_load(), but the cpu parameter instead - Drop redundant call to kvm_set_pfn_accessed() in user_mem_abort() - Remove prototypes without implementations RISC-V: - Zba, Zbs, Zicntr, Zicsr, Zifencei, and Zihpm support for guest - Added ONE_REG interface for SATP mode - Added ONE_REG interface to enable/disable multiple ISA extensions - Improved error codes returned by ONE_REG interfaces - Added KVM_GET_REG_LIST ioctl() implementation for KVM RISC-V - Added get-reg-list selftest for KVM RISC-V s390: - PV crypto passthrough enablement (Tony, Steffen, Viktor, Janosch) Allows a PV guest to use crypto cards. Card access is governed by the firmware and once a crypto queue is "bound" to a PV VM every other entity (PV or not) looses access until it is not bound anymore. Enablement is done via flags when creating the PV VM. - Guest debug fixes (Ilya) x86: - Clean up KVM's handling of Intel architectural events - Intel bugfixes - Add support for SEV-ES DebugSwap, allowing SEV-ES guests to use debug registers and generate/handle #DBs - Clean up LBR virtualization code - Fix a bug where KVM fails to set the target pCPU during an IRTE update - Fix fatal bugs in SEV-ES intrahost migration - Fix a bug where the recent (architecturally correct) change to reinject #BP and skip INT3 broke SEV guests (can't decode INT3 to skip it) - Retry APIC map recalculation if a vCPU is added/enabled - Overhaul emergency reboot code to bring SVM up to par with VMX, tie the "emergency disabling" behavior to KVM actually being loaded, and move all of the logic within KVM - Fix user triggerable WARNs in SVM where KVM incorrectly assumes the TSC ratio MSR cannot diverge from the default when TSC scaling is disabled up related code - Add a framework to allow "caching" feature flags so that KVM can check if the guest can use a feature without needing to search guest CPUID - Rip out the ancient MMU_DEBUG crud and replace the useful bits with CONFIG_KVM_PROVE_MMU - Fix KVM's handling of !visible guest roots to avoid premature triple fault injection - Overhaul KVM's page-track APIs, and KVMGT's usage, to reduce the API surface that is needed by external users (currently only KVMGT), and fix a variety of issues in the process Generic: - Wrap kvm_{gfn,hva}_range.pte in a union to allow mmu_notifier events to pass action specific data without needing to constantly update the main handlers. - Drop unused function declarations Selftests: - Add testcases to x86's sync_regs_test for detecting KVM TOCTOU bugs - Add support for printf() in guest code and covert all guest asserts to use printf-based reporting - Clean up the PMU event filter test and add new testcases - Include x86 selftests in the KVM x86 MAINTAINERS entry" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (279 commits) KVM: x86/mmu: Include mmu.h in spte.h KVM: x86/mmu: Use dummy root, backed by zero page, for !visible guest roots KVM: x86/mmu: Disallow guest from using !visible slots for page tables KVM: x86/mmu: Harden TDP MMU iteration against root w/o shadow page KVM: x86/mmu: Harden new PGD against roots without shadow pages KVM: x86/mmu: Add helper to convert root hpa to shadow page drm/i915/gvt: Drop final dependencies on KVM internal details KVM: x86/mmu: Handle KVM bookkeeping in page-track APIs, not callers KVM: x86/mmu: Drop @slot param from exported/external page-track APIs KVM: x86/mmu: Bug the VM if write-tracking is used but not enabled KVM: x86/mmu: Assert that correct locks are held for page write-tracking KVM: x86/mmu: Rename page-track APIs to reflect the new reality KVM: x86/mmu: Drop infrastructure for multiple page-track modes KVM: x86/mmu: Use page-track notifiers iff there are external users KVM: x86/mmu: Move KVM-only page-track declarations to internal header KVM: x86: Remove the unused page-track hook track_flush_slot() drm/i915/gvt: switch from ->track_flush_slot() to ->track_remove_region() KVM: x86: Add a new page-track hook to handle memslot deletion drm/i915/gvt: Don't bother removing write-protection on to-be-deleted slot KVM: x86: Reject memslot MOVE operations if KVMGT is attached ...
Diffstat (limited to 'virt/kvm/kvm_main.c')
-rw-r--r--virt/kvm/kvm_main.c54
1 files changed, 40 insertions, 14 deletions
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 2500178cf444..486800a7024b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -345,7 +345,6 @@ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
}
EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request);
-#ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL
void kvm_flush_remote_tlbs(struct kvm *kvm)
{
++kvm->stat.generic.remote_tlb_flush_requests;
@@ -361,12 +360,38 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
* kvm_make_all_cpus_request() reads vcpu->mode. We reuse that
* barrier here.
*/
- if (!kvm_arch_flush_remote_tlb(kvm)
+ if (!kvm_arch_flush_remote_tlbs(kvm)
|| kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
++kvm->stat.generic.remote_tlb_flush;
}
EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
-#endif
+
+void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages)
+{
+ if (!kvm_arch_flush_remote_tlbs_range(kvm, gfn, nr_pages))
+ return;
+
+ /*
+ * Fall back to a flushing entire TLBs if the architecture range-based
+ * TLB invalidation is unsupported or can't be performed for whatever
+ * reason.
+ */
+ kvm_flush_remote_tlbs(kvm);
+}
+
+void kvm_flush_remote_tlbs_memslot(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot)
+{
+ /*
+ * All current use cases for flushing the TLBs for a specific memslot
+ * are related to dirty logging, and many do the TLB flush out of
+ * mmu_lock. The interaction between the various operations on memslot
+ * must be serialized by slots_locks to ensure the TLB flush from one
+ * operation is observed by any other operation on the same memslot.
+ */
+ lockdep_assert_held(&kvm->slots_lock);
+ kvm_flush_remote_tlbs_range(kvm, memslot->base_gfn, memslot->npages);
+}
static void kvm_flush_shadow_all(struct kvm *kvm)
{
@@ -526,7 +551,7 @@ typedef void (*on_unlock_fn_t)(struct kvm *kvm);
struct kvm_hva_range {
unsigned long start;
unsigned long end;
- pte_t pte;
+ union kvm_mmu_notifier_arg arg;
hva_handler_t handler;
on_lock_fn_t on_lock;
on_unlock_fn_t on_unlock;
@@ -547,6 +572,8 @@ static void kvm_null_fn(void)
}
#define IS_KVM_NULL_FN(fn) ((fn) == (void *)kvm_null_fn)
+static const union kvm_mmu_notifier_arg KVM_MMU_NOTIFIER_NO_ARG;
+
/* Iterate over each memslot intersecting [start, last] (inclusive) range */
#define kvm_for_each_memslot_in_hva_range(node, slots, start, last) \
for (node = interval_tree_iter_first(&slots->hva_tree, start, last); \
@@ -591,7 +618,7 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
* bother making these conditional (to avoid writes on
* the second or later invocation of the handler).
*/
- gfn_range.pte = range->pte;
+ gfn_range.arg = range->arg;
gfn_range.may_block = range->may_block;
/*
@@ -632,14 +659,14 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
unsigned long start,
unsigned long end,
- pte_t pte,
+ union kvm_mmu_notifier_arg arg,
hva_handler_t handler)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
const struct kvm_hva_range range = {
.start = start,
.end = end,
- .pte = pte,
+ .arg = arg,
.handler = handler,
.on_lock = (void *)kvm_null_fn,
.on_unlock = (void *)kvm_null_fn,
@@ -659,7 +686,6 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn
const struct kvm_hva_range range = {
.start = start,
.end = end,
- .pte = __pte(0),
.handler = handler,
.on_lock = (void *)kvm_null_fn,
.on_unlock = (void *)kvm_null_fn,
@@ -693,6 +719,7 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
pte_t pte)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
+ const union kvm_mmu_notifier_arg arg = { .pte = pte };
trace_kvm_set_spte_hva(address);
@@ -708,7 +735,7 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
if (!READ_ONCE(kvm->mmu_invalidate_in_progress))
return;
- kvm_handle_hva_range(mn, address, address + 1, pte, kvm_change_spte_gfn);
+ kvm_handle_hva_range(mn, address, address + 1, arg, kvm_change_spte_gfn);
}
void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
@@ -747,7 +774,6 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
const struct kvm_hva_range hva_range = {
.start = range->start,
.end = range->end,
- .pte = __pte(0),
.handler = kvm_unmap_gfn_range,
.on_lock = kvm_mmu_invalidate_begin,
.on_unlock = kvm_arch_guest_memory_reclaimed,
@@ -812,7 +838,6 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
const struct kvm_hva_range hva_range = {
.start = range->start,
.end = range->end,
- .pte = __pte(0),
.handler = (void *)kvm_null_fn,
.on_lock = kvm_mmu_invalidate_end,
.on_unlock = (void *)kvm_null_fn,
@@ -845,7 +870,8 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
{
trace_kvm_age_hva(start, end);
- return kvm_handle_hva_range(mn, start, end, __pte(0), kvm_age_gfn);
+ return kvm_handle_hva_range(mn, start, end, KVM_MMU_NOTIFIER_NO_ARG,
+ kvm_age_gfn);
}
static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn,
@@ -2180,7 +2206,7 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
}
if (flush)
- kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
+ kvm_flush_remote_tlbs_memslot(kvm, memslot);
if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n))
return -EFAULT;
@@ -2297,7 +2323,7 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm,
KVM_MMU_UNLOCK(kvm);
if (flush)
- kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
+ kvm_flush_remote_tlbs_memslot(kvm, memslot);
return 0;
}