Re: [PATCH 2/6] iommu/amd: Remove amd_iommu_devtable_lock

2019-09-26 Thread Jerry Snitselaar
On Wed Sep 25 19, Joerg Roedel wrote: From: Joerg Roedel The lock is not necessary because the device table does not contain shared state that needs protection. Locking is only needed on an individual entry basis, and that needs to happen on the iommu_dev_data level. Fixes: 92d420ec028d

Re: [PATCH 2/6] iommu/amd: Remove amd_iommu_devtable_lock

2019-09-25 Thread Sironi, Filippo via iommu
> On 25. Sep 2019, at 08:50, Sironi, Filippo wrote: > > > >> On 25. Sep 2019, at 06:22, Joerg Roedel wrote: >> >> From: Joerg Roedel >> >> The lock is not necessary because the device table does not >> contain shared state that needs protection. Locking is only >> needed on an

Re: [PATCH 2/6] iommu/amd: Remove amd_iommu_devtable_lock

2019-09-25 Thread Sironi, Filippo via iommu
> On 25. Sep 2019, at 06:22, Joerg Roedel wrote: > > From: Joerg Roedel > > The lock is not necessary because the device table does not > contain shared state that needs protection. Locking is only > needed on an individual entry basis, and that needs to > happen on the iommu_dev_data

[PATCH 2/6] iommu/amd: Remove amd_iommu_devtable_lock

2019-09-25 Thread Joerg Roedel
From: Joerg Roedel The lock is not necessary because the device table does not contain shared state that needs protection. Locking is only needed on an individual entry basis, and that needs to happen on the iommu_dev_data level. Fixes: 92d420ec028d ("iommu/amd: Relax locking in dma_ops path")