* [PATCH v3] Fix one error in mthca_alloc
@ 2021-08-27 0:52 kangning
2021-08-31 9:52 ` Leon Romanovsky
0 siblings, 1 reply; 7+ messages in thread
From: kangning @ 2021-08-27 0:52 UTC (permalink / raw)
To: haakon.bugge; +Cc: linux-rdma, kangning
drivers/infiniband/hw/mthca/mthca_allocator.c: alloc->last left unchanged in mthca_alloc, which
has impact on performance of function find_next_zero_bit in mthca_alloc.
Signed-off-by: kangning <kangning18z@ict.ac.cn>
---
I squashed two commits into one in this version.
drivers/infiniband/hw/mthca/mthca_allocator.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/infiniband/hw/mthca/mthca_allocator.c b/drivers/infiniband/hw/mthca/mthca_allocator.c
index aef1d274a14e..1141695093e7 100644
--- a/drivers/infiniband/hw/mthca/mthca_allocator.c
+++ b/drivers/infiniband/hw/mthca/mthca_allocator.c
@@ -51,6 +51,9 @@ u32 mthca_alloc(struct mthca_alloc *alloc)
}
if (obj < alloc->max) {
+ alloc->last = obj + 1;
+ if (alloc->last == alloc->max)
+ alloc->last = 0;
set_bit(obj, alloc->table);
obj |= alloc->top;
} else
--
2.17.1
^ permalink raw reply related [flat|nested] 7+ messages in thread
* Re: [PATCH v3] Fix one error in mthca_alloc
2021-08-27 0:52 [PATCH v3] Fix one error in mthca_alloc kangning
@ 2021-08-31 9:52 ` Leon Romanovsky
2021-08-31 10:40 ` 康宁
` (2 more replies)
0 siblings, 3 replies; 7+ messages in thread
From: Leon Romanovsky @ 2021-08-31 9:52 UTC (permalink / raw)
To: kangning; +Cc: haakon.bugge, linux-rdma
On Fri, Aug 27, 2021 at 08:52:28AM +0800, kangning wrote:
> drivers/infiniband/hw/mthca/mthca_allocator.c: alloc->last left unchanged in mthca_alloc, which
> has impact on performance of function find_next_zero_bit in mthca_alloc.
I don't know what the sentence above means, but the change is unlikely
to be correct.
When alloc->last starts to be equal to alloc->max, the
find_next_zero_bit() will always return alloc->max. which will ensure
that the following code is executed.
48 if (obj >= alloc->max) {
49 alloc->top = (alloc->top + alloc->max) & alloc->mask;
50 obj = find_first_zero_bit(alloc->table, alloc->max);
51 }
However the mthca_alloc() function has other error, it returns -1 while
based on its declaration it needs to be unsigned,
Thanks
>
> Signed-off-by: kangning <kangning18z@ict.ac.cn>
> ---
>
> I squashed two commits into one in this version.
>
> drivers/infiniband/hw/mthca/mthca_allocator.c | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/drivers/infiniband/hw/mthca/mthca_allocator.c b/drivers/infiniband/hw/mthca/mthca_allocator.c
> index aef1d274a14e..1141695093e7 100644
> --- a/drivers/infiniband/hw/mthca/mthca_allocator.c
> +++ b/drivers/infiniband/hw/mthca/mthca_allocator.c
> @@ -51,6 +51,9 @@ u32 mthca_alloc(struct mthca_alloc *alloc)
> }
>
> if (obj < alloc->max) {
> + alloc->last = obj + 1;
> + if (alloc->last == alloc->max)
> + alloc->last = 0;
> set_bit(obj, alloc->table);
> obj |= alloc->top;
> } else
> --
> 2.17.1
>
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: Re: [PATCH v3] Fix one error in mthca_alloc
2021-08-31 9:52 ` Leon Romanovsky
@ 2021-08-31 10:40 ` 康宁
2021-08-31 12:00 ` Leon Romanovsky
2021-08-31 10:47 ` 康宁
[not found] ` <202109011027459851120@ict.ac.cn>
2 siblings, 1 reply; 7+ messages in thread
From: 康宁 @ 2021-08-31 10:40 UTC (permalink / raw)
To: Leon Romanovsky; +Cc: haakon.bugge, linux-rdma
>
> On Fri, Aug 27, 2021 at 08:52:28AM +0800, kangning wrote:
> > drivers/infiniband/hw/mthca/mthca_allocator.c: alloc->last left unchanged in mthca_alloc, which
> > has impact on performance of function find_next_zero_bit in mthca_alloc.
>
> I don't know what the sentence above means, but the change is unlikely
> to be correct.
>
> When alloc->last starts to be equal to alloc->max, the
> find_next_zero_bit() will always return alloc->max. which will ensure
> that the following code is executed.
>
> 48 if (obj >= alloc->max) {
> 49 alloc->top = (alloc->top + alloc->max) & alloc->mask;
> 50 obj = find_first_zero_bit(alloc->table, alloc->max);
> 51 }
>
Thanks for your review.
Yes, your analysis is right. However, this is a bitmap allocator for resource id allocation (like QP, and CQ).
We first look at the situation where no resource id is released.
When the value of alloc->last starts to reaches alloc->max, the bitmap will
be full. In this case, it's normal to return an invalid value.
Now, let's add resource releasing into consideration.
The following code is part of mthca_free:
70 spin_lock_irqsave(&alloc->lock, flags);
71
72 clear_bit(obj, alloc->table);
73 alloc->last = min(alloc->last, obj);
74 alloc->top = (alloc->top + alloc->max) & alloc->mask;
mthca_free() is used to release the allocated resource id. It will update alloc->last when obj is freed.
So, if the bitmap has space for allocation, my modification can continuously work.
>
> However the mthca_alloc() function has other error, it returns -1 while
> based on its declaration it needs to be unsigned,
I think you are right about this. But obj is the return value of u32 type, which is the requirement of resource id
(though it may not fully use 32 bits). I have no idea of how to fix it.
Thanks.
>
> Thanks
>
> >
> > Signed-off-by: kangning <kangning18z@ict.ac.cn>
> > ---
> >
> > I squashed two commits into one in this version.
> >
> > drivers/infiniband/hw/mthca/mthca_allocator.c | 3 +++
> > 1 file changed, 3 insertions(+)
> >
> > diff --git a/drivers/infiniband/hw/mthca/mthca_allocator.c b/drivers/infiniband/hw/mthca/mthca_allocator.c
> > index aef1d274a14e..1141695093e7 100644
> > --- a/drivers/infiniband/hw/mthca/mthca_allocator.c
> > +++ b/drivers/infiniband/hw/mthca/mthca_allocator.c
> > @@ -51,6 +51,9 @@ u32 mthca_alloc(struct mthca_alloc *alloc)
> > }
> >
> > if (obj < alloc->max) {
> > + alloc->last = obj + 1;
> > + if (alloc->last == alloc->max)
> > + alloc->last = 0;
> > set_bit(obj, alloc->table);
> > obj |= alloc->top;
> > } else
> > --
> > 2.17.1
> >
</kangning18z@ict.ac.cn>
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: Re: [PATCH v3] Fix one error in mthca_alloc
2021-08-31 9:52 ` Leon Romanovsky
2021-08-31 10:40 ` 康宁
@ 2021-08-31 10:47 ` 康宁
[not found] ` <202109011027459851120@ict.ac.cn>
2 siblings, 0 replies; 7+ messages in thread
From: 康宁 @ 2021-08-31 10:47 UTC (permalink / raw)
To: Leon Romanovsky; +Cc: haakon.bugge, linux-rdma
>
> On Fri, Aug 27, 2021 at 08:52:28AM +0800, kangning wrote:
> > drivers/infiniband/hw/mthca/mthca_allocator.c: alloc->last left unchanged in mthca_alloc, which
> > has impact on performance of function find_next_zero_bit in mthca_alloc.
>
> I don't know what the sentence above means, but the change is unlikely
> to be correct.
>
> When alloc->last starts to be equal to alloc->max, the
> find_next_zero_bit() will always return alloc->max. which will ensure
> that the following code is executed.
>
> 48 if (obj >= alloc->max) {
> 49 alloc->top = (alloc->top + alloc->max) & alloc->mask;
> 50 obj = find_first_zero_bit(alloc->table, alloc->max);
> 51 }
>
Thanks for your review.
Your analysis is right. However, this is a bitmap allocator for resource id allocation (like QP, and CQ).
We first look at the situation where no resource id is released.
When the value of alloc->last starts to reaches alloc->max, the bitmap will
be full. In this case, it's normal to return an invalid value.
Now, let's add resource releasing into consideration.
The following code is part of mthca_free():
70 spin_lock_irqsave(&alloc->lock, flags);
71
72 clear_bit(obj, alloc->table);
73 alloc->last = min(alloc->last, obj);
74 alloc->top = (alloc->top + alloc->max) & alloc->mask;
mthca_free() is used to release the allocated resource id. It will update alloc->last when obj is freed.
So, if the bitmap has space for allocation, my modification can continuously work.
>
> However the mthca_alloc() function has other error, it returns -1 while
> based on its declaration it needs to be unsigned,
I think you are right about this. But obj is the return value of u32 type, which is the requirement of resource id
(though it may not fully use 32 bits). I have no idea of how to fix it.
Thanks.
>
> Thanks
>
> >
> > Signed-off-by: kangning <kangning18z@ict.ac.cn>
> > ---
> >
> > I squashed two commits into one in this version.
> >
> > drivers/infiniband/hw/mthca/mthca_allocator.c | 3 +++
> > 1 file changed, 3 insertions(+)
> >
> > diff --git a/drivers/infiniband/hw/mthca/mthca_allocator.c b/drivers/infiniband/hw/mthca/mthca_allocator.c
> > index aef1d274a14e..1141695093e7 100644
> > --- a/drivers/infiniband/hw/mthca/mthca_allocator.c
> > +++ b/drivers/infiniband/hw/mthca/mthca_allocator.c
> > @@ -51,6 +51,9 @@ u32 mthca_alloc(struct mthca_alloc *alloc)
> > }
> >
> > if (obj < alloc->max) {
> > + alloc->last = obj + 1;
> > + if (alloc->last == alloc->max)
> > + alloc->last = 0;
> > set_bit(obj, alloc->table);
> > obj |= alloc->top;
> > } else
> > --
> > 2.17.1
> >
</kangning18z@ict.ac.cn>
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: Re: [PATCH v3] Fix one error in mthca_alloc
2021-08-31 10:40 ` 康宁
@ 2021-08-31 12:00 ` Leon Romanovsky
2021-08-31 12:16 ` kangning18z
0 siblings, 1 reply; 7+ messages in thread
From: Leon Romanovsky @ 2021-08-31 12:00 UTC (permalink / raw)
To: 康宁; +Cc: haakon.bugge, linux-rdma
On Tue, Aug 31, 2021 at 06:40:38PM +0800, 康宁 wrote:
> >
> > On Fri, Aug 27, 2021 at 08:52:28AM +0800, kangning wrote:
> > > drivers/infiniband/hw/mthca/mthca_allocator.c: alloc->last left unchanged in mthca_alloc, which
> > > has impact on performance of function find_next_zero_bit in mthca_alloc.
> >
> > I don't know what the sentence above means, but the change is unlikely
> > to be correct.
> >
> > When alloc->last starts to be equal to alloc->max, the
> > find_next_zero_bit() will always return alloc->max. which will ensure
> > that the following code is executed.
> >
> > 48 if (obj >= alloc->max) {
> > 49 alloc->top = (alloc->top + alloc->max) & alloc->mask;
> > 50 obj = find_first_zero_bit(alloc->table, alloc->max);
> > 51 }
> >
>
> Thanks for your review.
> Yes, your analysis is right. However, this is a bitmap allocator for resource id allocation (like QP, and CQ).
> We first look at the situation where no resource id is released.
> When the value of alloc->last starts to reaches alloc->max, the bitmap will
> be full. In this case, it's normal to return an invalid value.
>
> Now, let's add resource releasing into consideration.
> The following code is part of mthca_free:
>
> 70 spin_lock_irqsave(&alloc->lock, flags);
> 71
> 72 clear_bit(obj, alloc->table);
> 73 alloc->last = min(alloc->last, obj);
> 74 alloc->top = (alloc->top + alloc->max) & alloc->mask;
>
> mthca_free() is used to release the allocated resource id. It will update alloc->last when obj is freed.
> So, if the bitmap has space for allocation, my modification can continuously work.
After alloc->last starts to be equal to alloc->max, the bitmap is
searches with find_first_zero_bit() call. That will ensure that we look
for any bit between 0 and alloc->max.
So no, your change can't be right.
Thanks
>
> >
> > However the mthca_alloc() function has other error, it returns -1 while
> > based on its declaration it needs to be unsigned,
>
> I think you are right about this. But obj is the return value of u32 type, which is the requirement of resource id
> (though it may not fully use 32 bits). I have no idea of how to fix it.
>
> Thanks.
>
> >
> > Thanks
> >
> > >
> > > Signed-off-by: kangning <kangning18z@ict.ac.cn>
> > > ---
> > >
> > > I squashed two commits into one in this version.
> > >
> > > drivers/infiniband/hw/mthca/mthca_allocator.c | 3 +++
> > > 1 file changed, 3 insertions(+)
> > >
> > > diff --git a/drivers/infiniband/hw/mthca/mthca_allocator.c b/drivers/infiniband/hw/mthca/mthca_allocator.c
> > > index aef1d274a14e..1141695093e7 100644
> > > --- a/drivers/infiniband/hw/mthca/mthca_allocator.c
> > > +++ b/drivers/infiniband/hw/mthca/mthca_allocator.c
> > > @@ -51,6 +51,9 @@ u32 mthca_alloc(struct mthca_alloc *alloc)
> > > }
> > >
> > > if (obj < alloc->max) {
> > > + alloc->last = obj + 1;
> > > + if (alloc->last == alloc->max)
> > > + alloc->last = 0;
> > > set_bit(obj, alloc->table);
> > > obj |= alloc->top;
> > > } else
> > > --
> > > 2.17.1
> > >
> </kangning18z@ict.ac.cn>
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: Re: [PATCH v3] Fix one error in mthca_alloc
2021-08-31 12:00 ` Leon Romanovsky
@ 2021-08-31 12:16 ` kangning18z
0 siblings, 0 replies; 7+ messages in thread
From: kangning18z @ 2021-08-31 12:16 UTC (permalink / raw)
To: leon; +Cc: linux-rdma
> On Tue, Aug 31, 2021 at 06:40:38PM +0800, 康宁 wrote:
> > >
> > > On Fri, Aug 27, 2021 at 08:52:28AM +0800, kangning wrote:
> > > > drivers/infiniband/hw/mthca/mthca_allocator.c: alloc->last left unchanged in mthca_alloc, which
> > > > has impact on performance of function find_next_zero_bit in mthca_alloc.
> > >
> > > I don't know what the sentence above means, but the change is unlikely
> > > to be correct.
> > >
> > > When alloc->last starts to be equal to alloc->max, the
> > > find_next_zero_bit() will always return alloc->max. which will ensure
> > > that the following code is executed.
> > >
> > > 48 if (obj >= alloc->max) {
> > > 49 alloc->top = (alloc->top + alloc->max) & alloc->mask;
> > > 50 obj = find_first_zero_bit(alloc->table, alloc->max);
> > > 51 }
> > >
> >
> > Thanks for your review.
> > Yes, your analysis is right. However, this is a bitmap allocator for resource id allocation (like QP, and CQ).
> > We first look at the situation where no resource id is released.
> > When the value of alloc->last starts to reaches alloc->max, the bitmap will
> > be full. In this case, it's normal to return an invalid value.
> >
> > Now, let's add resource releasing into consideration.
> > The following code is part of mthca_free:
> >
> > 70 spin_lock_irqsave(&alloc->lock, flags);
> > 71
> > 72 clear_bit(obj, alloc->table);
> > 73 alloc->last = min(alloc->last, obj);
> > 74 alloc->top = (alloc->top + alloc->max) & alloc->mask;
> >
> > mthca_free() is used to release the allocated resource id. It will update alloc->last when obj is freed.
> > So, if the bitmap has space for allocation, my modification can continuously work.
>
> After alloc->last starts to be equal to alloc->max, the bitmap is
> searches with find_first_zero_bit() call. That will ensure that we look
> for any bit between 0 and alloc->max.
>
> So no, your change can't be right.
If you never call function mthca_free(), you will never find a valid bit in [0, alloc->max]
with find_first_zero_bit() call. Cause every bits between 0 and alloc->max are alloacted.
But if you called mthca_free() before, the freed obj is assigned to alloc->last, and we
still can allocate the bitmap.
My modification is correct.
>
> Thanks
>
> >
> > >
> > > However the mthca_alloc() function has other error, it returns -1 while
> > > based on its declaration it needs to be unsigned,
> >
> > I think you are right about this. But obj is the return value of u32 type, which is the requirement of resource id
> > (though it may not fully use 32 bits). I have no idea of how to fix it.
> >
> > Thanks.
> >
> > >
> > > Thanks
> > >
> > > >
> > > > Signed-off-by: kangning <kangning18z@ict.ac.cn>
> > > > ---
> > > >
> > > > I squashed two commits into one in this version.
> > > >
> > > > drivers/infiniband/hw/mthca/mthca_allocator.c | 3 +++
> > > > 1 file changed, 3 insertions(+)
> > > >
> > > > diff --git a/drivers/infiniband/hw/mthca/mthca_allocator.c b/drivers/infiniband/hw/mthca/mthca_allocator.c
> > > > index aef1d274a14e..1141695093e7 100644
> > > > --- a/drivers/infiniband/hw/mthca/mthca_allocator.c
> > > > +++ b/drivers/infiniband/hw/mthca/mthca_allocator.c
> > > > @@ -51,6 +51,9 @@ u32 mthca_alloc(struct mthca_alloc *alloc)
> > > > }
> > > >
> > > > if (obj < alloc->max) {
> > > > + alloc->last = obj + 1;
> > > > + if (alloc->last == alloc->max)
> > > > + alloc->last = 0;
> > > > set_bit(obj, alloc->table);
> > > > obj |= alloc->top;
> > > > } else
> > > > --
> > > > 2.17.1
> > > >
> > </kangning18z@ict.ac.cn>
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: Re: [PATCH v3] Fix one error in mthca_alloc
[not found] ` <202109011027459851120@ict.ac.cn>
@ 2021-09-01 7:51 ` Leon Romanovsky
0 siblings, 0 replies; 7+ messages in thread
From: Leon Romanovsky @ 2021-09-01 7:51 UTC (permalink / raw)
To: kangning18z; +Cc: haakon.bugge, linux-rdma
On Wed, Sep 01, 2021 at 10:27:46AM +0800, kangning18z@ict.ac.cn wrote:
>
<...>
> Thank you for your review.
Do you have mthca card in hand to test your changes?
This driver didn't get any changes for a long time and we
don't even know if it works or not.
I would prefer to minimize changes to that driver.
Thanks
^ permalink raw reply [flat|nested] 7+ messages in thread
end of thread, other threads:[~2021-09-01 7:51 UTC | newest]
Thread overview: 7+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-08-27 0:52 [PATCH v3] Fix one error in mthca_alloc kangning
2021-08-31 9:52 ` Leon Romanovsky
2021-08-31 10:40 ` 康宁
2021-08-31 12:00 ` Leon Romanovsky
2021-08-31 12:16 ` kangning18z
2021-08-31 10:47 ` 康宁
[not found] ` <202109011027459851120@ict.ac.cn>
2021-09-01 7:51 ` Leon Romanovsky
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.