linux/arch/x86/kvm/mmu/tdp_mmu.h

119 lines
4.1 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
#ifndef __KVM_X86_MMU_TDP_MMU_H
#define __KVM_X86_MMU_TDP_MMU_H
#include <linux/kvm_host.h>
hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu);
__must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root)
{
return refcount_inc_not_zero(&root->tdp_mmu_root_count);
}
void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
bool shared);
bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id, gfn_t start,
gfn_t end, bool can_yield, bool flush);
static inline bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id,
gfn_t start, gfn_t end, bool flush)
{
return __kvm_tdp_mmu_zap_gfn_range(kvm, as_id, start, end, true, flush);
}
static inline bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
{
KVM: x86/mmu: Fix TDP MMU page table level TDP MMU iterator's level is identical to page table's actual level. For instance, for the last level page table (whose entry points to one 4K page), iter->level is 1 (PG_LEVEL_4K), and in case of 5 level paging, the iter->level is mmu->shadow_root_level, which is 5. However, struct kvm_mmu_page's level currently is not set correctly when it is allocated in kvm_tdp_mmu_map(). When iterator hits non-present SPTE and needs to allocate a new child page table, currently iter->level, which is the level of the page table where the non-present SPTE belongs to, is used. This results in struct kvm_mmu_page's level always having its parent's level (excpet root table's level, which is initialized explicitly using mmu->shadow_root_level). This is kinda wrong, and not consistent with existing non TDP MMU code. Fortuantely sp->role.level is only used in handle_removed_tdp_mmu_page() and kvm_tdp_mmu_zap_sp(), and they are already aware of this and behave correctly. However to make it consistent with legacy MMU code (and fix the issue that both root page table and its child page table have shadow_root_level), use iter->level - 1 in kvm_tdp_mmu_map(), and change handle_removed_tdp_mmu_page() and kvm_tdp_mmu_zap_sp() accordingly. Reviewed-by: Ben Gardon <bgardon@google.com> Signed-off-by: Kai Huang <kai.huang@intel.com> Message-Id: <bcb6569b6e96cb78aaa7b50640e6e6b53291a74e.1623717884.git.kai.huang@intel.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2021-06-15 08:57:11 +08:00
gfn_t end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level + 1);
/*
* Don't allow yielding, as the caller may have a flush pending. Note,
* if mmu_lock is held for write, zapping will never yield in this case,
* but explicitly disallow it for safety. The TDP MMU does not yield
* until it has made forward progress (steps sideways), and when zapping
* a single shadow page that it's guaranteed to see (thus the mmu_lock
* requirement), its "step sideways" will always step beyond the bounds
* of the shadow page's gfn range and stop iterating before yielding.
*/
lockdep_assert_held_write(&kvm->mmu_lock);
return __kvm_tdp_mmu_zap_gfn_range(kvm, kvm_mmu_page_as_id(sp),
sp->gfn, end, false, false);
}
void kvm_tdp_mmu_zap_all(struct kvm *kvm);
void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm);
void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm);
int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
bool flush);
bool kvm_tdp_mmu_age_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
bool kvm_tdp_mmu_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
bool kvm_tdp_mmu_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm,
const struct kvm_memory_slot *slot, int min_level);
bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm,
const struct kvm_memory_slot *slot);
void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
struct kvm_memory_slot *slot,
gfn_t gfn, unsigned long mask,
bool wrprot);
void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
const struct kvm_memory_slot *slot);
bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
struct kvm_memory_slot *slot, gfn_t gfn,
int min_level);
KVM: x86/mmu: Split huge pages mapped by the TDP MMU when dirty logging is enabled When dirty logging is enabled without initially-all-set, try to split all huge pages in the memslot down to 4KB pages so that vCPUs do not have to take expensive write-protection faults to split huge pages. Eager page splitting is best-effort only. This commit only adds the support for the TDP MMU, and even there splitting may fail due to out of memory conditions. Failures to split a huge page is fine from a correctness standpoint because KVM will always follow up splitting by write-protecting any remaining huge pages. Eager page splitting moves the cost of splitting huge pages off of the vCPU threads and onto the thread enabling dirty logging on the memslot. This is useful because: 1. Splitting on the vCPU thread interrupts vCPUs execution and is disruptive to customers whereas splitting on VM ioctl threads can run in parallel with vCPU execution. 2. Splitting all huge pages at once is more efficient because it does not require performing VM-exit handling or walking the page table for every 4KiB page in the memslot, and greatly reduces the amount of contention on the mmu_lock. For example, when running dirty_log_perf_test with 96 virtual CPUs, 1GiB per vCPU, and 1GiB HugeTLB memory, the time it takes vCPUs to write to all of their memory after dirty logging is enabled decreased by 95% from 2.94s to 0.14s. Eager Page Splitting is over 100x more efficient than the current implementation of splitting on fault under the read lock. For example, taking the same workload as above, Eager Page Splitting reduced the CPU required to split all huge pages from ~270 CPU-seconds ((2.94s - 0.14s) * 96 vCPU threads) to only 1.55 CPU-seconds. Eager page splitting does increase the amount of time it takes to enable dirty logging since it has split all huge pages. For example, the time it took to enable dirty logging in the 96GiB region of the aforementioned test increased from 0.001s to 1.55s. Reviewed-by: Peter Xu <peterx@redhat.com> Signed-off-by: David Matlack <dmatlack@google.com> Message-Id: <20220119230739.2234394-16-dmatlack@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2022-01-20 07:07:36 +08:00
void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm,
const struct kvm_memory_slot *slot,
gfn_t start, gfn_t end,
int target_level);
static inline void kvm_tdp_mmu_walk_lockless_begin(void)
{
rcu_read_lock();
}
static inline void kvm_tdp_mmu_walk_lockless_end(void)
{
rcu_read_unlock();
}
int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
int *root_level);
u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, u64 addr,
u64 *spte);
#ifdef CONFIG_X86_64
bool kvm_mmu_init_tdp_mmu(struct kvm *kvm);
void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm);
static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return sp->tdp_mmu_page; }
static inline bool is_tdp_mmu(struct kvm_mmu *mmu)
{
struct kvm_mmu_page *sp;
hpa_t hpa = mmu->root_hpa;
if (WARN_ON(!VALID_PAGE(hpa)))
return false;
/*
* A NULL shadow page is legal when shadowing a non-paging guest with
* PAE paging, as the MMU will be direct with root_hpa pointing at the
* pae_root page, not a shadow page.
*/
sp = to_shadow_page(hpa);
return sp && is_tdp_mmu_page(sp) && sp->root_count;
}
#else
static inline bool kvm_mmu_init_tdp_mmu(struct kvm *kvm) { return false; }
static inline void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) {}
static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return false; }
static inline bool is_tdp_mmu(struct kvm_mmu *mmu) { return false; }
#endif
#endif /* __KVM_X86_MMU_TDP_MMU_H */