[PATCH net-next] sfc: Stop using iommu_present()

[PATCH net-next] sfc: Stop using iommu_present()

[Robin Murphy]

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 <robin.murphy@arm.com>
---
 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

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH net-next] sfc: Stop using iommu_present()

[Robin Murphy]

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 <robin.murphy@arm.com>
---
 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

Re: [PATCH net-next] sfc: Stop using iommu_present()

[Edward Cree]

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 <robin.murphy@arm.com>
Acked-by: Edward Cree <ecree.xilinx@gmail.com>

Re: [PATCH net-next] sfc: Stop using iommu_present()

[Edward Cree]

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 <robin.murphy@arm.com>
Acked-by: Edward Cree <ecree.xilinx@gmail.com>
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [PATCH net-next] sfc: Stop using iommu_present()

[patchwork-bot+netdevbpf]

Hello:

This patch was applied to netdev/net-next.git (master)
by Jakub Kicinski <kuba@kernel.org>:

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 <robin.murphy@arm.com>
> 
> [...]

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

Re: [PATCH net-next] sfc: Stop using iommu_present()

[patchwork-bot+netdevbpf]

Hello:

This patch was applied to netdev/net-next.git (master)
by Jakub Kicinski <kuba@kernel.org>:

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 <robin.murphy@arm.com>
> 
> [...]

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


_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu