Re: [PATCH RESEND 6/9] hw/arm/smmu-common: Manage IOTLB block entries

Hi Peter, On 6/30/20 6:29 PM, Auger Eric wrote: > Hi Peter, > > On 6/30/20 5:50 PM, Peter Maydell wrote: >> On Fri, 26 Jun 2020 at 14:53, Auger Eric wrote: >>> On 6/25/20 5:30 PM, Peter Maydell wrote: Rather than looping around doing multiple hash table lookups like this, why not just

Re: [PATCH RESEND 6/9] hw/arm/smmu-common: Manage IOTLB block entries

Hi Peter, On 6/30/20 5:50 PM, Peter Maydell wrote: > On Fri, 26 Jun 2020 at 14:53, Auger Eric wrote: >> On 6/25/20 5:30 PM, Peter Maydell wrote: >>> Rather than looping around doing multiple hash table lookups like >>> this, why not just avoid including the tg and level in the >>> key equality te

Re: [PATCH RESEND 6/9] hw/arm/smmu-common: Manage IOTLB block entries

On Fri, 26 Jun 2020 at 14:53, Auger Eric wrote: > On 6/25/20 5:30 PM, Peter Maydell wrote: > > Rather than looping around doing multiple hash table lookups like > > this, why not just avoid including the tg and level in the > > key equality test? > > > > If I understand the range-based-invalidatio

Re: [PATCH RESEND 6/9] hw/arm/smmu-common: Manage IOTLB block entries

Hi Peter, On 6/26/20 3:53 PM, Auger Eric wrote: > Hi Peter, > > On 6/25/20 5:30 PM, Peter Maydell wrote: >> On Thu, 11 Jun 2020 at 17:16, Eric Auger wrote: >>> >>> At the moment each entry in the IOTLB corresponds to a page sized >>> mapping (4K, 16K or 64K), even if the page belongs to a mapped

Re: [PATCH RESEND 6/9] hw/arm/smmu-common: Manage IOTLB block entries

Hi Peter, On 6/25/20 5:30 PM, Peter Maydell wrote: > On Thu, 11 Jun 2020 at 17:16, Eric Auger wrote: >> >> At the moment each entry in the IOTLB corresponds to a page sized >> mapping (4K, 16K or 64K), even if the page belongs to a mapped >> block. In case of block mapping this unefficiently cons

Re: [PATCH RESEND 6/9] hw/arm/smmu-common: Manage IOTLB block entries

On Thu, 11 Jun 2020 at 17:16, Eric Auger wrote: > > At the moment each entry in the IOTLB corresponds to a page sized > mapping (4K, 16K or 64K), even if the page belongs to a mapped > block. In case of block mapping this unefficiently consume IOTLB > entries. > > Change the value of the entry so

[PATCH RESEND 6/9] hw/arm/smmu-common: Manage IOTLB block entries

At the moment each entry in the IOTLB corresponds to a page sized mapping (4K, 16K or 64K), even if the page belongs to a mapped block. In case of block mapping this unefficiently consume IOTLB entries. Change the value of the entry so that it reflects the actual mapping it belongs to (block or pa