Even if an IOMMU might be present for some PCI segment in the system,
that doesn't necessarily mean it provides translation for the device
we care about. It appears that what we care about here is specifically
whether DMA mapping ops involve any IOMMU overhead or not, so check for
translation actually being active for our device.
Signed-off-by: Robin Murphy <[email protected]>
---
drivers/net/ethernet/sfc/falcon/rx.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/sfc/falcon/rx.c b/drivers/net/ethernet/sfc/falcon/rx.c
index 0c6cc2191369..6bbdb5d2eebf 100644
--- a/drivers/net/ethernet/sfc/falcon/rx.c
+++ b/drivers/net/ethernet/sfc/falcon/rx.c
@@ -718,12 +718,14 @@ static void ef4_init_rx_recycle_ring(struct ef4_nic *efx,
struct ef4_rx_queue *rx_queue)
{
unsigned int bufs_in_recycle_ring, page_ring_size;
+ struct iommu_domain __maybe_unused *domain;
/* Set the RX recycle ring size */
#ifdef CONFIG_PPC64
bufs_in_recycle_ring = EF4_RECYCLE_RING_SIZE_IOMMU;
#else
- if (iommu_present(&pci_bus_type))
+ domain = iommu_get_domain_for_dev(&efx->pci_dev->dev);
+ if (domain && domain->type != IOMMU_DOMAIN_IDENTITY)
bufs_in_recycle_ring = EF4_RECYCLE_RING_SIZE_IOMMU;
else
bufs_in_recycle_ring = EF4_RECYCLE_RING_SIZE_NOIOMMU;
--
2.28.0.dirty
On 05/04/2022 14:40, Robin Murphy wrote:
> Even if an IOMMU might be present for some PCI segment in the system,
> that doesn't necessarily mean it provides translation for the device
> we care about. It appears that what we care about here is specifically
> whether DMA mapping ops involve any IOMMU overhead or not, so check for
> translation actually being active for our device.
>
> Signed-off-by: Robin Murphy <[email protected]>
Acked-by: Edward Cree <[email protected]>
Hello:
This patch was applied to netdev/net-next.git (master)
by Jakub Kicinski <[email protected]>:
On Tue, 5 Apr 2022 14:40:55 +0100 you wrote:
> Even if an IOMMU might be present for some PCI segment in the system,
> that doesn't necessarily mean it provides translation for the device
> we care about. It appears that what we care about here is specifically
> whether DMA mapping ops involve any IOMMU overhead or not, so check for
> translation actually being active for our device.
>
> Signed-off-by: Robin Murphy <[email protected]>
>
> [...]
Here is the summary with links:
- [net-next] sfc: Stop using iommu_present()
https://git.kernel.org/netdev/net-next/c/6a62924c0a81
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html