mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Leon Romanovsky <leon@kernel.org>
To: Bjorn Helgaas <bhelgaas@google.com>,
	Logan Gunthorpe <logang@deltatee.com>,
	Chaitanya Kulkarni <kch@nvidia.com>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Jens Axboe <axboe@kernel.dk>, Alex Williamson <alex@shazbot.org>,
	Leon Romanovsky <leon@kernel.org>,
	Ankit Agrawal <ankita@nvidia.com>, Jason Gunthorpe <jgg@ziepe.ca>,
	Jonathan Corbet <corbet@lwn.net>,
	Shuah Khan <skhan@linuxfoundation.org>,
	"Joerg Roedel (AMD)" <joro@8bytes.org>,
	Will Deacon <will@kernel.org>,
	Robin Murphy <robin.murphy@arm.com>
Cc: linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-doc@vger.kernel.org, iommu@lists.linux.dev
Subject: [PATCH v3 11/17] PCI/P2PDMA: Derive peer-to-peer routing from ACS control bits
Date: Tue, 11 Aug 2026 12:30:53 +0300	[thread overview]
Message-ID: <20260811-fix-p2p-acs-v3-11-efc488ee7c03@nvidia.com> (raw)
In-Reply-To: <20260811-fix-p2p-acs-v3-0-efc488ee7c03@nvidia.com>

From: Leon Romanovsky <leonro@nvidia.com>

The redirect test reports an upstream redirect for any ACS redirect or
egress control bit. PCIe r7.0, sec 6.12.3, table 6-11 ties the outcome to
the control bits and the target vector, and an enabled egress control bit
alone does not redirect. Compute the result from the control bits so the
vector can be honored next, using the host-bridge route while the peer
target is unknown.

Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/pci/p2pdma.c | 49 ++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 36 insertions(+), 13 deletions(-)

diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index a364008bbf50..69cef8ca9557 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -21,6 +21,8 @@
 #include <linux/seq_buf.h>
 #include <linux/xarray.h>
 
+#include "pci.h"
+
 /*
  * Lifetime and RCU usage
  *
@@ -536,26 +538,45 @@ static struct pci_dev *find_parent_pci_dev(struct device *dev)
 	return NULL;
 }
 
-/*
- * Check if a PCI bridge has its ACS redirection bits set to redirect P2P
- * TLPs upstream via ACS. Returns 1 if the packets will be redirected
- * upstream, 0 otherwise.
- */
-static int pci_bridge_has_acs_redir(struct pci_dev *pdev)
+enum pci_acs_p2pdma_state {
+	PCI_ACS_P2PDMA_DIRECT,
+	PCI_ACS_P2PDMA_REDIRECT,
+};
+
+static enum pci_acs_p2pdma_state
+pci_acs_p2pdma_state(struct pci_dev *pdev, struct pci_dev *target)
 {
 	int pos;
 	u16 ctrl;
 
 	pos = pdev->acs_cap;
 	if (!pos)
-		return 0;
+		return PCI_ACS_P2PDMA_DIRECT;
 
-	pci_read_config_word(pdev, pos + PCI_ACS_CTRL, &ctrl);
+	if (pci_read_config_word(pdev, pos + PCI_ACS_CTRL, &ctrl))
+		return PCI_ACS_P2PDMA_REDIRECT;
 
-	if (ctrl & (PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC))
-		return 1;
+	if (!(ctrl & PCI_ACS_EC))
+		return ctrl & (PCI_ACS_RR | PCI_ACS_CR) ?
+			PCI_ACS_P2PDMA_REDIRECT : PCI_ACS_P2PDMA_DIRECT;
 
-	return 0;
+	/*
+	 * The vector cannot be read without the peer target, so redirect
+	 * upstream until the paths diverge.
+	 */
+	if (!target)
+		return PCI_ACS_P2PDMA_REDIRECT;
+
+	/*
+	 * PCIe r7.0, sec 6.12.3, table 6-11: a set or indeterminate egress
+	 * control vector bit keeps the request off the direct path; a clear
+	 * bit permits it, subject only to completion redirect.
+	 */
+	if (pci_acs_egress_ctrl_is_set(pdev, target))
+		return PCI_ACS_P2PDMA_REDIRECT;
+
+	return ctrl & PCI_ACS_CR ? PCI_ACS_P2PDMA_REDIRECT :
+				    PCI_ACS_P2PDMA_DIRECT;
 }
 
 static void seq_buf_print_bus_devfn(struct seq_buf *buf, struct pci_dev *pdev)
@@ -767,7 +788,8 @@ calc_map_type_and_dist(struct pci_dev *provider, struct pci_dev *client,
 	while (a) {
 		dist_b = 0;
 
-		if (pci_bridge_has_acs_redir(a)) {
+		if (pci_acs_p2pdma_state(a, NULL) ==
+		    PCI_ACS_P2PDMA_REDIRECT) {
 			seq_buf_print_bus_devfn(&acs_list, a);
 			acs_cnt++;
 		}
@@ -796,7 +818,8 @@ calc_map_type_and_dist(struct pci_dev *provider, struct pci_dev *client,
 		if (a == bb)
 			break;
 
-		if (pci_bridge_has_acs_redir(bb)) {
+		if (pci_acs_p2pdma_state(bb, NULL) ==
+		    PCI_ACS_P2PDMA_REDIRECT) {
 			seq_buf_print_bus_devfn(&acs_list, bb);
 			acs_cnt++;
 		}

-- 
2.55.0


  parent reply	other threads:[~2026-08-11  9:32 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-11  9:30 [PATCH v3 00/17] PCI/P2PDMA: Fix ACS egress control handling Leon Romanovsky
2026-08-11  9:30 ` [PATCH v3 01/17] PCI/P2PDMA: Do not tear down the allocate attribute on registration failure Leon Romanovsky
2026-08-11  9:30 ` [PATCH v3 02/17] PCI/P2PDMA: Wait for RCU readers before freeing state Leon Romanovsky
2026-08-11  9:30 ` [PATCH v3 03/17] PCI/P2PDMA: Restrict the p2pmem search to pool backed providers Leon Romanovsky
2026-08-11  9:30 ` [PATCH v3 04/17] PCI/P2PDMA: Safely terminate ACS redirect lists Leon Romanovsky
2026-08-11  9:30 ` [PATCH v3 05/17] PCI/P2PDMA: Document the pdev->p2pdma lifetime and RCU rules Leon Romanovsky
2026-08-11  9:30 ` [PATCH v3 06/17] PCI/P2PDMA: Gate the host bridge whitelist warning on verbose Leon Romanovsky
2026-08-11  9:30 ` [PATCH v3 07/17] PCI/P2PDMA: Document the Address Type assumption Leon Romanovsky
2026-08-11  9:30 ` [PATCH v3 08/17] PCI: Account for Direct Translated P2P in ACS isolation checks Leon Romanovsky
2026-08-11  9:30 ` [PATCH v3 09/17] PCI: Add ACS egress control vector accessor Leon Romanovsky
2026-08-11  9:30 ` [PATCH v3 10/17] PCI: Account for ACS egress control in isolation checks Leon Romanovsky
2026-08-11  9:30 ` Leon Romanovsky [this message]
2026-08-11  9:30 ` [PATCH v3 12/17] PCI/P2PDMA: Honor ACS egress control vectors Leon Romanovsky
2026-08-11  9:30 ` [PATCH v3 13/17] PCI/P2PDMA: Document ACS egress control handling Leon Romanovsky
2026-08-11  9:30 ` [PATCH v3 14/17] PCI/P2PDMA: Extract pure ACS routing decision helpers Leon Romanovsky
2026-08-11  9:30 ` [PATCH v3 15/17] PCI/P2PDMA: Add KUnit tests for ACS routing decisions Leon Romanovsky
2026-08-11  9:30 ` [PATCH v3 16/17] PCI/P2PDMA: Add KUnit coverage for the ACS P2P routing walk Leon Romanovsky
2026-08-11  9:30 ` [PATCH v3 17/17] PCI: Add KUnit coverage for ACS isolation checks Leon Romanovsky
2026-08-18  8:35 ` [PATCH v3 00/17] PCI/P2PDMA: Fix ACS egress control handling Leon Romanovsky

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260811-fix-p2p-acs-v3-11-efc488ee7c03@nvidia.com \
    --to=leon@kernel.org \
    --cc=alex@shazbot.org \
    --cc=ankita@nvidia.com \
    --cc=axboe@kernel.dk \
    --cc=bhelgaas@google.com \
    --cc=corbet@lwn.net \
    --cc=gregkh@linuxfoundation.org \
    --cc=iommu@lists.linux.dev \
    --cc=jgg@ziepe.ca \
    --cc=joro@8bytes.org \
    --cc=kch@nvidia.com \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=logang@deltatee.com \
    --cc=robin.murphy@arm.com \
    --cc=skhan@linuxfoundation.org \
    --cc=will@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®