diff mbox series

[v3,2/8] KVM: Integrate gfn_to_memslot_approx() into search_memslots()

Message ID b8258ced64a81c7d90320c2921fe08b11eb47362.1621191551.git.maciej.szmigiero@oracle.com (mailing list archive)
State New, archived
Headers show
Series KVM: Scalable memslots implementation | expand

Commit Message

Maciej S. Szmigiero May 16, 2021, 9:44 p.m. UTC
From: "Maciej S. Szmigiero" <maciej.szmigiero@oracle.com>

s390 arch has gfn_to_memslot_approx() which is almost identical to
search_memslots(), differing only in that in case the gfn falls in a hole
one of the memslots bordering the hole is returned.

Add this lookup mode as an option to search_memslots() so we don't have two
almost identical functions for looking up a memslot by its gfn.

Signed-off-by: Maciej S. Szmigiero <maciej.szmigiero@oracle.com>
---
 arch/powerpc/kvm/book3s_64_vio.c    |  2 +-
 arch/powerpc/kvm/book3s_64_vio_hv.c |  2 +-
 arch/s390/kvm/kvm-s390.c            | 39 ++---------------------------
 include/linux/kvm_host.h            | 13 +++++++---
 4 files changed, 14 insertions(+), 42 deletions(-)

Comments

Sean Christopherson May 19, 2021, 9:24 p.m. UTC | #1
On Sun, May 16, 2021, Maciej S. Szmigiero wrote:
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index 8895b95b6a22..3c40c7d32f7e 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -1091,10 +1091,14 @@ bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args);
>   * gfn_to_memslot() itself isn't here as an inline because that would
>   * bloat other code too much.
>   *
> + * With "approx" set returns the memslot also when the address falls
> + * in a hole. In that case one of the memslots bordering the hole is
> + * returned.
> + *
>   * IMPORTANT: Slots are sorted from highest GFN to lowest GFN!
>   */
>  static inline struct kvm_memory_slot *
> -search_memslots(struct kvm_memslots *slots, gfn_t gfn)
> +search_memslots(struct kvm_memslots *slots, gfn_t gfn, bool approx)

An alternative to modifying the PPC code would be to make the existing
search_memslots() a wrapper to __search_memslots(), with the latter taking
@approx.

We might also want to make this __always_inline to improve the likelihood of the
compiler optimizing away @approx.  I doubt it matters in practice...

>  {
>  	int start = 0, end = slots->used_slots;
>  	int slot = atomic_read(&slots->lru_slot);
> @@ -1116,19 +1120,22 @@ search_memslots(struct kvm_memslots *slots, gfn_t gfn)
>  			start = slot + 1;
>  	}
>  
> +	if (approx && start >= slots->used_slots)
> +		return &memslots[slots->used_slots - 1];
> +
>  	if (start < slots->used_slots && gfn >= memslots[start].base_gfn &&
>  	    gfn < memslots[start].base_gfn + memslots[start].npages) {
>  		atomic_set(&slots->lru_slot, start);
>  		return &memslots[start];
>  	}
>  
> -	return NULL;
> +	return approx ? &memslots[start] : NULL;
>  }
>  
>  static inline struct kvm_memory_slot *
>  __gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn)
>  {
> -	return search_memslots(slots, gfn);
> +	return search_memslots(slots, gfn, false);
>  }
>  
>  static inline unsigned long
Maciej S. Szmigiero May 21, 2021, 7:03 a.m. UTC | #2
On 19.05.2021 23:24, Sean Christopherson wrote:
> On Sun, May 16, 2021, Maciej S. Szmigiero wrote:
>> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
>> index 8895b95b6a22..3c40c7d32f7e 100644
>> --- a/include/linux/kvm_host.h
>> +++ b/include/linux/kvm_host.h
>> @@ -1091,10 +1091,14 @@ bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args);
>>    * gfn_to_memslot() itself isn't here as an inline because that would
>>    * bloat other code too much.
>>    *
>> + * With "approx" set returns the memslot also when the address falls
>> + * in a hole. In that case one of the memslots bordering the hole is
>> + * returned.
>> + *
>>    * IMPORTANT: Slots are sorted from highest GFN to lowest GFN!
>>    */
>>   static inline struct kvm_memory_slot *
>> -search_memslots(struct kvm_memslots *slots, gfn_t gfn)
>> +search_memslots(struct kvm_memslots *slots, gfn_t gfn, bool approx)
> 
> An alternative to modifying the PPC code would be to make the existing
> search_memslots() a wrapper to __search_memslots(), with the latter taking
> @approx.

I guess you mean that if search_memslots() only does an exact search
(like the current code does) its 3 callers won't have to be modified.
Will do it then.

> We might also want to make this __always_inline to improve the likelihood of the
> compiler optimizing away @approx.  I doubt it matters in practice...

Sounds like a good idea, will do.

Thanks,
Maciej
Paolo Bonzini June 10, 2021, 4:17 p.m. UTC | #3
On 19/05/21 23:24, Sean Christopherson wrote:
> An alternative to modifying the PPC code would be to make the existing
> search_memslots() a wrapper to __search_memslots(), with the latter taking
> @approx.

Let's just modify PPC to use __gfn_to_memslot instead of search_memslots().

__gfn_to_memslot() has never introduced any functionality over 
search_memslots(), ever since search_memslots() was introduced in 2011.

Paolo

> We might also want to make this __always_inline to improve the likelihood of the
> compiler optimizing away @approx.  I doubt it matters in practice...
>
diff mbox series

Patch

diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 8da93fdfa59e..148525120504 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -346,7 +346,7 @@  static long kvmppc_tce_to_ua(struct kvm *kvm, unsigned long tce,
 	unsigned long gfn = tce >> PAGE_SHIFT;
 	struct kvm_memory_slot *memslot;
 
-	memslot = search_memslots(kvm_memslots(kvm), gfn);
+	memslot = search_memslots(kvm_memslots(kvm), gfn, false);
 	if (!memslot)
 		return -EINVAL;
 
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 083a4e037718..a4042403630d 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -80,7 +80,7 @@  static long kvmppc_rm_tce_to_ua(struct kvm *kvm,
 	unsigned long gfn = tce >> PAGE_SHIFT;
 	struct kvm_memory_slot *memslot;
 
-	memslot = search_memslots(kvm_memslots_raw(kvm), gfn);
+	memslot = search_memslots(kvm_memslots_raw(kvm), gfn, false);
 	if (!memslot)
 		return -EINVAL;
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 1296fc10f80c..75e635ede6ff 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1921,41 +1921,6 @@  static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 /* for consistency */
 #define KVM_S390_CMMA_SIZE_MAX ((u32)KVM_S390_SKEYS_MAX)
 
-/*
- * Similar to gfn_to_memslot, but returns the index of a memslot also when the
- * address falls in a hole. In that case the index of one of the memslots
- * bordering the hole is returned.
- */
-static int gfn_to_memslot_approx(struct kvm_memslots *slots, gfn_t gfn)
-{
-	int start = 0, end = slots->used_slots;
-	int slot = atomic_read(&slots->lru_slot);
-	struct kvm_memory_slot *memslots = slots->memslots;
-
-	if (gfn >= memslots[slot].base_gfn &&
-	    gfn < memslots[slot].base_gfn + memslots[slot].npages)
-		return slot;
-
-	while (start < end) {
-		slot = start + (end - start) / 2;
-
-		if (gfn >= memslots[slot].base_gfn)
-			end = slot;
-		else
-			start = slot + 1;
-	}
-
-	if (start >= slots->used_slots)
-		return slots->used_slots - 1;
-
-	if (gfn >= memslots[start].base_gfn &&
-	    gfn < memslots[start].base_gfn + memslots[start].npages) {
-		atomic_set(&slots->lru_slot, start);
-	}
-
-	return start;
-}
-
 static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args,
 			      u8 *res, unsigned long bufsize)
 {
@@ -1982,8 +1947,8 @@  static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args,
 static unsigned long kvm_s390_next_dirty_cmma(struct kvm_memslots *slots,
 					      unsigned long cur_gfn)
 {
-	int slotidx = gfn_to_memslot_approx(slots, cur_gfn);
-	struct kvm_memory_slot *ms = slots->memslots + slotidx;
+	struct kvm_memory_slot *ms = search_memslots(slots, cur_gfn, true);
+	int slotidx = ms - slots->memslots;
 	unsigned long ofs = cur_gfn - ms->base_gfn;
 
 	if (ms->base_gfn + ms->npages <= cur_gfn) {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 8895b95b6a22..3c40c7d32f7e 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1091,10 +1091,14 @@  bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args);
  * gfn_to_memslot() itself isn't here as an inline because that would
  * bloat other code too much.
  *
+ * With "approx" set returns the memslot also when the address falls
+ * in a hole. In that case one of the memslots bordering the hole is
+ * returned.
+ *
  * IMPORTANT: Slots are sorted from highest GFN to lowest GFN!
  */
 static inline struct kvm_memory_slot *
-search_memslots(struct kvm_memslots *slots, gfn_t gfn)
+search_memslots(struct kvm_memslots *slots, gfn_t gfn, bool approx)
 {
 	int start = 0, end = slots->used_slots;
 	int slot = atomic_read(&slots->lru_slot);
@@ -1116,19 +1120,22 @@  search_memslots(struct kvm_memslots *slots, gfn_t gfn)
 			start = slot + 1;
 	}
 
+	if (approx && start >= slots->used_slots)
+		return &memslots[slots->used_slots - 1];
+
 	if (start < slots->used_slots && gfn >= memslots[start].base_gfn &&
 	    gfn < memslots[start].base_gfn + memslots[start].npages) {
 		atomic_set(&slots->lru_slot, start);
 		return &memslots[start];
 	}
 
-	return NULL;
+	return approx ? &memslots[start] : NULL;
 }
 
 static inline struct kvm_memory_slot *
 __gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn)
 {
-	return search_memslots(slots, gfn);
+	return search_memslots(slots, gfn, false);
 }
 
 static inline unsigned long