[2/9] KVM: MMU: introduce slot_handle_level() and its helper
diff mbox

Message ID 1430389490-24602-3-git-send-email-guangrong.xiao@linux.intel.com
State New, archived
Headers show

Commit Message

Xiao Guangrong April 30, 2015, 10:24 a.m. UTC
From: Xiao Guangrong <guangrong.xiao@linux.intel.com>

There are several places walking all rmaps for the memslot so that
introduce common functions to cleanup the code

Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
---
 arch/x86/kvm/mmu.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)

Comments

Paolo Bonzini May 7, 2015, 12:04 p.m. UTC | #1
On 30/04/2015 12:24, guangrong.xiao@linux.intel.com wrote:
> From: Xiao Guangrong <guangrong.xiao@linux.intel.com>
> 
> There are several places walking all rmaps for the memslot so that
> introduce common functions to cleanup the code
> 
> Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
> ---
>  arch/x86/kvm/mmu.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 63 insertions(+)
> 
> diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
> index ea3e3e4..75a3459 100644
> --- a/arch/x86/kvm/mmu.c
> +++ b/arch/x86/kvm/mmu.c
> @@ -4410,6 +4410,69 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu)
>  	init_kvm_mmu(vcpu);
>  }
>  
> +/* The return value indicates if tlb flush on all vcpus is needed. */
> +typedef bool (*slot_level_handler) (struct kvm *kvm, unsigned long *rmap);
> +
> +/* The caller should hold mmu-lock before calling this function. */
> +static bool
> +slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
> +		  slot_level_handler fn, int min_level, int max_level,
> +		  bool lock_flush_tlb)

Why not introduce for_each_slot_rmap first, instead of introducing one 
implementation first and then switching to another?  It's a small 
change to reorder the patches like that.  I think we should have three 
iterator macros:

#define for_each_rmap_spte(rmap, iter, spte)

#define for_each_slot_rmap(slot, min_level, max_level, iter, rmapp)

#define for_each_slot_rmap_range(slot, iter, min_level, max_level, \
				 start_gfn, end_gfn, iter, rmapp)

where the last two take care of initializing the walker/iterator in the 
first part of the "for".

This way, this function would be introduced immediately as this very 
readable code:

	struct slot_rmap_iterator iter;
	unsigned long *rmapp;
	bool flush = false;

	for_each_slot_rmap(memslot, min_level, max_level, &iter, rmapp) {
		if (*rmapp)
			flush |= fn(kvm, rmapp);

		if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
			if (flush && lock_flush_tlb) {
				kvm_flush_remote_tlbs(kvm);
				flush = false;
			}
			cond_resched_lock(&kvm->mmu_lock);
		}
	}

	/*
	 * What about adding this here: then callers that pass
	 * lock_flush_tlb == true need not care about the return
	 * value!
	 */
	if (flush && lock_flush_tlb) {
		kvm_flush_remote_tlbs(kvm);
		flush = false;
	}

	return flush;

In addition, some of these functions need to be marked always_inline I 
think; either slot_handle_level/slot_handle_*_level, or the
iterators/walkers.  Can you collect kvm.ko size for both cases?

Thanks,

Paolo

> +{
> +	unsigned long last_gfn;
> +	bool flush = false;
> +	int level;
> +
> +	last_gfn = memslot->base_gfn + memslot->npages - 1;
> +
> +	for (level = min_level; level <= max_level; ++level) {
> +		unsigned long *rmapp;
> +		unsigned long last_index, index;
> +
> +		rmapp = memslot->arch.rmap[level - PT_PAGE_TABLE_LEVEL];
> +		last_index = gfn_to_index(last_gfn, memslot->base_gfn, level);
> +
> +		for (index = 0; index <= last_index; ++index, ++rmapp) {
> +			if (*rmapp)
> +				flush |= fn(kvm, rmapp);
> +
> +			if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
> +				if (flush && lock_flush_tlb) {
> +					kvm_flush_remote_tlbs(kvm);
> +					flush = false;
> +				}
> +				cond_resched_lock(&kvm->mmu_lock);
> +			}
> +		}
> +	}
> +
> +	return flush;
> +}
> +
> +static bool
> +slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
> +		      slot_level_handler fn, bool lock_flush_tlb)
> +{
> +	return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL,
> +		PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES - 1, lock_flush_tlb);
> +}
> +
> +static bool
> +slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
> +			slot_level_handler fn, bool lock_flush_tlb)
> +{
> +	return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL + 1,
> +		PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES - 1, lock_flush_tlb);
> +}
> +
> +static bool
> +slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot,
> +		 slot_level_handler fn, bool lock_flush_tlb)
> +{
> +	return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL,
> +				 PT_PAGE_TABLE_LEVEL, lock_flush_tlb);
> +}
> +
>  void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
>  				      struct kvm_memory_slot *memslot)
>  {
> 
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Xiao Guangrong May 11, 2015, 1 p.m. UTC | #2
On 05/07/2015 08:04 PM, Paolo Bonzini wrote:
>
>
> On 30/04/2015 12:24, guangrong.xiao@linux.intel.com wrote:
>> From: Xiao Guangrong <guangrong.xiao@linux.intel.com>
>>
>> There are several places walking all rmaps for the memslot so that
>> introduce common functions to cleanup the code
>>
>> Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
>> ---
>>   arch/x86/kvm/mmu.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
>>   1 file changed, 63 insertions(+)
>>
>> diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
>> index ea3e3e4..75a3459 100644
>> --- a/arch/x86/kvm/mmu.c
>> +++ b/arch/x86/kvm/mmu.c
>> @@ -4410,6 +4410,69 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu)
>>   	init_kvm_mmu(vcpu);
>>   }
>>
>> +/* The return value indicates if tlb flush on all vcpus is needed. */
>> +typedef bool (*slot_level_handler) (struct kvm *kvm, unsigned long *rmap);
>> +
>> +/* The caller should hold mmu-lock before calling this function. */
>> +static bool
>> +slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
>> +		  slot_level_handler fn, int min_level, int max_level,
>> +		  bool lock_flush_tlb)
>
> Why not introduce for_each_slot_rmap first, instead of introducing one
> implementation first and then switching to another?  It's a small
> change to reorder the patches like that.

Yes, it's better, will do it in v2.

> I think we should have three
> iterator macros:
>
> #define for_each_rmap_spte(rmap, iter, spte)
>
> #define for_each_slot_rmap(slot, min_level, max_level, iter, rmapp)
>
> #define for_each_slot_rmap_range(slot, iter, min_level, max_level, \
> 				 start_gfn, end_gfn, iter, rmapp)
>
> where the last two take care of initializing the walker/iterator in the
> first part of the "for".

Okay, i agree.

>
> This way, this function would be introduced immediately as this very
> readable code:
>
> 	struct slot_rmap_iterator iter;
> 	unsigned long *rmapp;
> 	bool flush = false;
>
> 	for_each_slot_rmap(memslot, min_level, max_level, &iter, rmapp) {
> 		if (*rmapp)
> 			flush |= fn(kvm, rmapp);
>
> 		if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
> 			if (flush && lock_flush_tlb) {
> 				kvm_flush_remote_tlbs(kvm);
> 				flush = false;
> 			}
> 			cond_resched_lock(&kvm->mmu_lock);
> 		}
> 	}
>
> 	/*
> 	 * What about adding this here: then callers that pass
> 	 * lock_flush_tlb == true need not care about the return
> 	 * value!
> 	 */
> 	if (flush && lock_flush_tlb) {
> 		kvm_flush_remote_tlbs(kvm);
> 		flush = false;
> 	}
>
> 	return flush;

Good idea.

>
> In addition, some of these functions need to be marked always_inline I
> think; either slot_handle_level/slot_handle_*_level, or the
> iterators/walkers.  Can you collect kvm.ko size for both cases?

After applying patch 1 ~ 5:

no inline:
$ size arch/x86/kvm/kvm.ko
    text    data     bss     dec     hex filename
  366406   51535     473  418414   6626e arch/x86/kvm/kvm.ko

inline:
$ size arch/x86/kvm/kvm.ko
    text    data     bss     dec     hex filename
  366638   51535     473  418646   66356 arch/x86/kvm/kvm.ko

Since there are static functions i prefer allowing GCC automatically
optimizes the code to marking always-inline.

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch
diff mbox

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index ea3e3e4..75a3459 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4410,6 +4410,69 @@  void kvm_mmu_setup(struct kvm_vcpu *vcpu)
 	init_kvm_mmu(vcpu);
 }
 
+/* The return value indicates if tlb flush on all vcpus is needed. */
+typedef bool (*slot_level_handler) (struct kvm *kvm, unsigned long *rmap);
+
+/* The caller should hold mmu-lock before calling this function. */
+static bool
+slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
+		  slot_level_handler fn, int min_level, int max_level,
+		  bool lock_flush_tlb)
+{
+	unsigned long last_gfn;
+	bool flush = false;
+	int level;
+
+	last_gfn = memslot->base_gfn + memslot->npages - 1;
+
+	for (level = min_level; level <= max_level; ++level) {
+		unsigned long *rmapp;
+		unsigned long last_index, index;
+
+		rmapp = memslot->arch.rmap[level - PT_PAGE_TABLE_LEVEL];
+		last_index = gfn_to_index(last_gfn, memslot->base_gfn, level);
+
+		for (index = 0; index <= last_index; ++index, ++rmapp) {
+			if (*rmapp)
+				flush |= fn(kvm, rmapp);
+
+			if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+				if (flush && lock_flush_tlb) {
+					kvm_flush_remote_tlbs(kvm);
+					flush = false;
+				}
+				cond_resched_lock(&kvm->mmu_lock);
+			}
+		}
+	}
+
+	return flush;
+}
+
+static bool
+slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
+		      slot_level_handler fn, bool lock_flush_tlb)
+{
+	return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL,
+		PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES - 1, lock_flush_tlb);
+}
+
+static bool
+slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
+			slot_level_handler fn, bool lock_flush_tlb)
+{
+	return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL + 1,
+		PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES - 1, lock_flush_tlb);
+}
+
+static bool
+slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot,
+		 slot_level_handler fn, bool lock_flush_tlb)
+{
+	return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL,
+				 PT_PAGE_TABLE_LEVEL, lock_flush_tlb);
+}
+
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
 				      struct kvm_memory_slot *memslot)
 {