Re: [PATCH RESEND v5 2/5] iova: Allow rcache range upper limit to be flexible

2022-07-06 Thread Will Deacon
On Thu, Apr 07, 2022 at 03:52:53PM +0800, Leizhen (ThunderTown) wrote:
> On 2022/4/4 19:27, John Garry wrote:
> > Some low-level drivers may request DMA mappings whose IOVA length exceeds
> > that of the current rcache upper limit.
> > 
> > This means that allocations for those IOVAs will never be cached, and
> > always must be allocated and freed from the RB tree per DMA mapping cycle.
> > This has a significant effect on performance, more so since commit
> > 4e89dce72521 ("iommu/iova: Retry from last rb tree node if iova search
> > fails"), as discussed at [0].
> > 
> > As a first step towards allowing the rcache range upper limit be
> > configured, hold this value in the IOVA rcache structure, and allocate
> > the rcaches separately.
> > 
> > Delete macro IOVA_RANGE_CACHE_MAX_SIZE in case it's reused by mistake.
> > 
> > [0] 
> > https://lore.kernel.org/linux-iommu/20210129092120.1482-1-thunder.leiz...@huawei.com/
> > 
> > Signed-off-by: John Garry 
> > ---
> >  drivers/iommu/iova.c | 20 ++--
> >  include/linux/iova.h |  3 +++
> >  2 files changed, 13 insertions(+), 10 deletions(-)
> > 
> > diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
> > index db77aa675145..5c22b9187b79 100644
> > --- a/drivers/iommu/iova.c
> > +++ b/drivers/iommu/iova.c
> > @@ -15,8 +15,6 @@
> >  /* The anchor node sits above the top of the usable address space */
> >  #define IOVA_ANCHOR~0UL
> >  
> > -#define IOVA_RANGE_CACHE_MAX_SIZE 6/* log of max cached IOVA range 
> > size (in pages) */
> > -
> >  static bool iova_rcache_insert(struct iova_domain *iovad,
> >unsigned long pfn,
> >unsigned long size);
> > @@ -443,7 +441,7 @@ alloc_iova_fast(struct iova_domain *iovad, unsigned 
> > long size,
> >  * rounding up anything cacheable to make sure that can't happen. The
> >  * order of the unadjusted size will still match upon freeing.
> >  */
> > -   if (size < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
> > +   if (size < (1 << (iovad->rcache_max_size - 1)))
> > size = roundup_pow_of_two(size);
> >  
> > iova_pfn = iova_rcache_get(iovad, size, limit_pfn + 1);
> > @@ -713,13 +711,15 @@ int iova_domain_init_rcaches(struct iova_domain 
> > *iovad)
> > unsigned int cpu;
> > int i, ret;
> >  
> > -   iovad->rcaches = kcalloc(IOVA_RANGE_CACHE_MAX_SIZE,
> > +   iovad->rcache_max_size = 6; /* Arbitrarily high default */
> 
> It would be better to assign this constant value to iovad->rcache_max_size
> in init_iova_domain().

I think it's fine where it is as it's a meaningless number outside of the
rcache code.

Will
___
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization


Re: [PATCH RESEND v5 2/5] iova: Allow rcache range upper limit to be flexible

2022-07-06 Thread Will Deacon
On Mon, Apr 04, 2022 at 07:27:11PM +0800, John Garry wrote:
> Some low-level drivers may request DMA mappings whose IOVA length exceeds
> that of the current rcache upper limit.
> 
> This means that allocations for those IOVAs will never be cached, and
> always must be allocated and freed from the RB tree per DMA mapping cycle.
> This has a significant effect on performance, more so since commit
> 4e89dce72521 ("iommu/iova: Retry from last rb tree node if iova search
> fails"), as discussed at [0].
> 
> As a first step towards allowing the rcache range upper limit be
> configured, hold this value in the IOVA rcache structure, and allocate
> the rcaches separately.
> 
> Delete macro IOVA_RANGE_CACHE_MAX_SIZE in case it's reused by mistake.
> 
> [0] 
> https://lore.kernel.org/linux-iommu/20210129092120.1482-1-thunder.leiz...@huawei.com/
> 
> Signed-off-by: John Garry 
> ---
>  drivers/iommu/iova.c | 20 ++--
>  include/linux/iova.h |  3 +++
>  2 files changed, 13 insertions(+), 10 deletions(-)

Acked-by: Will Deacon 

Will
___
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization