On Tue, Oct 06, 2026 at 05:28:45PM -0500, Bjorn Helgaas wrote:
On Thu, Oct 01, 2026 at 02:55:18PM +0300, Leon Romanovsky wrote:
From: Leon Romanovsky leonro@nvidia.com
A Downstream Port with ACS Direct Translated P2P enabled routes a Request whose Address Type is Translated "to the peer Egress Port without redirection, regardless of ACS P2P Request Redirect and ACS P2P Egress Control", per PCIe r7.0 sec 6.12.3. P2PDMA assumes every Request carries an Untranslated address, so it sends an ATS client through the host bridge even where the fabric would route it straight to the peer.
"sends an ATS client through the host bridge" -- I assume this really means "we told the caller that Requests would be routed through the host bridge" when in reality they wouldn't? I don't think this actually changes any routing in the fabric, does it?
I'd say it does. Before this patch, we didn't return `bus_address` here nor took the P2P path.
Thanks
So essentially we told the caller that P2P between A and B was, e.g., 5 hops when it was really only 2?
Add PCI_P2PDMA_TLP_TRANSLATED and consult Direct Translated P2P for the Requests it describes.
Reviewed-by: Logan Gunthorpe logang@deltatee.com Tested-by: Tushar Dave tdave@nvidia.com Signed-off-by: Leon Romanovsky leonro@nvidia.com
drivers/pci/p2pdma.c | 9 +++++++++ 1 file changed, 9 insertions(+)
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index 569a74de3b3a..3fd2cb8d16f0 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -548,6 +548,15 @@ pci_acs_p2pdma_request(u16 ctrl, unsigned int tlp_flags) */ if (ctrl & PCI_ACS_TB) return PCI_ACS_P2PDMA_BLOCKED;
/** PCIe r7.0 sec 6.12.3: ACS Direct Translated P2P routes a* Request carrying a Translated address to the peer "without* redirection, regardless of ACS P2P Request Redirect and ACS* P2P Egress Control settings".*/if (ctrl & PCI_ACS_DT)return PCI_ACS_P2PDMA_DIRECT;return ctrl & (PCI_ACS_RR | PCI_ACS_EC) ?
-- 2.55.0