Commit ac63cf0a authored by Sean Christopherson's avatar Sean Christopherson Committed by Yu Zhang
Browse files

KVM: Move MMU notifier's mmu_lock acquisition into common helper 

mainline inclusion
from mainline-v5.13-rc1
commit f922bd9b
category: feature
bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I7S3VQ
CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=f922bd9bf33bd5a8c6694927f010f32127810fbf



----------------------------------------------------------------------

Acquire and release mmu_lock in the __kvm_handle_hva_range() helper
instead of requiring the caller to do the same.  This paves the way for
future patches to take mmu_lock if and only if an overlapping memslot is
found, without also having to introduce the on_lock() shenanigans used
to manipulate the notifier count and sequence.

No functional change intended.

Signed-off-by: default avatarSean Christopherson <seanjc@google.com>
Message-Id: <20210402005658.3024832-8-seanjc@google.com>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>

conflict:
	virt/kvm/kvm_main.c

Signed-off-by: default avatarYu Zhang <yu.c.zhang@linux.intel.com>
parent ef18d479

virt/kvm/kvm_main.c

+71 −45
Original line number Diff line number Diff line
@@ -513,28 +513,57 @@ static void kvm_mmu_notifier_invalidate_range(struct mmu_notifier *mn, 


typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);



typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start,

			     unsigned long end);



struct kvm_hva_range {

	unsigned long start;

	unsigned long end;

	pte_t pte;

	hva_handler_t handler;

	on_lock_fn_t on_lock;

	bool flush_on_ret;

	bool may_block;

};



/*

 * Use a dedicated stub instead of NULL to indicate that there is no callback

 * function/handler.  The compiler technically can't guarantee that a real

 * function will have a non-zero address, and so it will generate code to

 * check for !NULL, whereas comparing against a stub will be elided at compile

 * time (unless the compiler is getting long in the tooth, e.g. gcc 4.9).

 */

static void kvm_null_fn(void)

{



}

#define IS_KVM_NULL_FN(fn) ((fn) == (void *)kvm_null_fn)



static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,

						  const struct kvm_hva_range *range)

{

	struct kvm_gfn_range gfn_range;

	struct kvm_memory_slot *slot;

	struct kvm_memslots *slots;

	struct kvm_gfn_range gfn_range;

	bool ret = false;

	int i, idx;



	lockdep_assert_held_write(&kvm->mmu_lock);

	/* A null handler is allowed if and only if on_lock() is provided. */

	if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) &&

			 IS_KVM_NULL_FN(range->handler)))

		return 0;



	KVM_MMU_LOCK(kvm);



	idx = srcu_read_lock(&kvm->srcu);



	if (!IS_KVM_NULL_FN(range->on_lock)) {

		range->on_lock(kvm, range->start, range->end);



		if (IS_KVM_NULL_FN(range->handler))

			goto out_unlock;

	}



	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {

		slots = __kvm_memslots(kvm, i);

		kvm_for_each_memslot(slot, slots) {
@@ -570,6 +599,9 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, 
	if (range->flush_on_ret && (ret || kvm->tlbs_dirty))

		kvm_flush_remote_tlbs(kvm);



out_unlock:

	KVM_MMU_UNLOCK(kvm);



	srcu_read_unlock(&kvm->srcu, idx);



	/* The notifiers are averse to booleans. :-( */
@@ -588,16 +620,12 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn, 
		.end		= end,

		.pte		= pte,

		.handler	= handler,

		.on_lock	= (void *)kvm_null_fn,

		.flush_on_ret	= true,

		.may_block	= false,

	};

	int ret;



	KVM_MMU_LOCK(kvm);

	ret = __kvm_handle_hva_range(kvm, &range);

	KVM_MMU_UNLOCK(kvm);



	return ret;

	return __kvm_handle_hva_range(kvm, &range);

}



static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn,
@@ -611,16 +639,41 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn 
		.end		= end,

		.pte		= __pte(0),

		.handler	= handler,

		.on_lock	= (void *)kvm_null_fn,

		.flush_on_ret	= false,

		.may_block	= false,

	};

	int ret;



	KVM_MMU_LOCK(kvm);

	ret = __kvm_handle_hva_range(kvm, &range);

	KVM_MMU_UNLOCK(kvm);

	return __kvm_handle_hva_range(kvm, &range);

}



	return ret;

static void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start,

				   unsigned long end)

{

	/*

	 * The count increase must become visible at unlock time as no

	 * spte can be established without taking the mmu_lock and

	 * count is also read inside the mmu_lock critical section.

	 */

	kvm->mmu_notifier_count++;

	if (likely(kvm->mmu_notifier_count == 1)) {

		kvm->mmu_notifier_range_start = start;

		kvm->mmu_notifier_range_end = end;

	} else {

		/*

		 * Fully tracking multiple concurrent ranges has dimishing

		 * returns. Keep things simple and just find the minimal range

		 * which includes the current and new ranges. As there won't be

		 * enough information to subtract a range after its invalidate

		 * completes, any ranges invalidated concurrently will

		 * accumulate and persist until all outstanding invalidates

		 * complete.

		 */

		kvm->mmu_notifier_range_start =

			min(kvm->mmu_notifier_range_start, start);

		kvm->mmu_notifier_range_end =

			max(kvm->mmu_notifier_range_end, end);

	}

}

#endif /* KVM_ARCH_WANT_NEW_MMU_NOTIFIER_APIS */
@@ -663,6 +716,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, 
		.end		= range->end,

		.pte		= __pte(0),

		.handler	= kvm_unmap_gfn_range,

		.on_lock	= kvm_inc_notifier_count,

		.flush_on_ret	= true,

		.may_block	= mmu_notifier_range_blockable(range),

	};
@@ -672,47 +726,19 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, 


	trace_kvm_unmap_hva_range(range->start, range->end);



#ifndef KVM_ARCH_WANT_NEW_MMU_NOTIFIER_APIS

	idx = srcu_read_lock(&kvm->srcu);

#endif



	KVM_MMU_LOCK(kvm);

	/*

	 * The count increase must become visible at unlock time as no

	 * spte can be established without taking the mmu_lock and

	 * count is also read inside the mmu_lock critical section.

	 */

	kvm->mmu_notifier_count++;

	if (likely(kvm->mmu_notifier_count == 1)) {

		kvm->mmu_notifier_range_start = range->start;

		kvm->mmu_notifier_range_end = range->end;

	} else {

		/*

		 * Fully tracking multiple concurrent ranges has dimishing

		 * returns. Keep things simple and just find the minimal range

		 * which includes the current and new ranges. As there won't be

		 * enough information to subtract a range after its invalidate

		 * completes, any ranges invalidated concurrently will

		 * accumulate and persist until all outstanding invalidates

		 * complete.

		 */

		kvm->mmu_notifier_range_start =

			min(kvm->mmu_notifier_range_start, range->start);

		kvm->mmu_notifier_range_end =

			max(kvm->mmu_notifier_range_end, range->end);

	}



#ifdef KVM_ARCH_WANT_NEW_MMU_NOTIFIER_APIS

	__kvm_handle_hva_range(kvm, &hva_range);

#else

	idx = srcu_read_lock(&kvm->srcu);

	KVM_MMU_LOCK(kvm);

	need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end,

					     range->flags);

	/* we've to flush the tlb before the pages can be freed */

	if (need_tlb_flush || kvm->tlbs_dirty)

		kvm_flush_remote_tlbs(kvm);

	KVM_MMU_UNLOCK(kvm);

#endif

	

	KVM_MMU_UNLOCK(kvm);

	kvm_arch_guest_memory_reclaimed(kvm);

#ifndef KVM_ARCH_WANT_NEW_MMU_NOTIFIER_APIS

	srcu_read_unlock(&kvm->srcu, idx);