From: Leon Romanovsky <leon@kernel.org>
To: Bjorn Helgaas <bhelgaas@google.com>,
Logan Gunthorpe <logang@deltatee.com>,
Jonathan Corbet <corbet@lwn.net>,
Shuah Khan <skhan@linuxfoundation.org>,
Alex Williamson <alex@shazbot.org>
Cc: linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-doc@vger.kernel.org,
"Claude Opus 4.8" <noreply@anthropic.com>
Subject: [PATCH 10/13] PCI/P2PDMA: Extract pure ACS routing decision helpers
Date: Sun, 2 Aug 2026 18:09:48 +0300 [thread overview]
Message-ID: <20260802-fix-p2p-acs-v1-10-a7c5eb64fff6@nvidia.com> (raw)
In-Reply-To: <20260802-fix-p2p-acs-v1-0-a7c5eb64fff6@nvidia.com>
From: Leon Romanovsky <leonro@nvidia.com>
The ACS Egress Control routing decision (PCIe r7.0, sec 6.12.3,
table 6-11) and the Egress Control Vector Size rule were embedded in
functions that also perform config-space I/O and walk the PCIe
hierarchy. That made the branch-heavy logic -- in particular the paths
that require an Egress Control Vector, which are unreachable on most
hardware -- difficult to exercise in isolation.
Factor the logic into two pure helpers:
- pci_acs_p2pdma_decision() maps the ACS control word, whether the
target port is known, and the target's Egress Control Vector bit to
a routing state.
- pci_acs_egress_port_valid() applies the "a vector size of 0 encodes
256 bits" rule to decide whether a target port is within the vector.
pci_acs_p2pdma_state() and pci_acs_egress_ctrl_set() now call these. No
functional change intended: pci_acs_egress_ctrl_set() still checks the
port range before reading the vector DWORD.
The helpers are exposed under CONFIG_KUNIT via VISIBLE_IF_KUNIT so the
following patch can unit-test them.
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Assisted-by: Claude Opus 4.8 <noreply@anthropic.com>
---
drivers/pci/p2pdma.c | 65 +++++++++++++++++++++++++++++-----------------------
drivers/pci/pci.c | 26 +++++++++++++++++----
drivers/pci/pci.h | 17 ++++++++++++++
3 files changed, 75 insertions(+), 33 deletions(-)
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index dbccc1d0c4e3..62e715a4ac84 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -491,46 +491,53 @@ static struct pci_dev *find_parent_pci_dev(struct device *dev)
return NULL;
}
-enum pci_acs_p2pdma_state {
- PCI_ACS_P2PDMA_DIRECT,
- PCI_ACS_P2PDMA_REDIRECT,
- PCI_ACS_P2PDMA_NOT_SUPPORTED,
-};
+/*
+ * PCIe r7.0, sec 6.12.3, table 6-11: decide how a peer-to-peer request at an
+ * ACS-capable ingress port routes, given its Egress Control register @ctrl,
+ * whether the target port is known (@has_target), and that target's Egress
+ * Control Vector bit (@egress: 1 set, 0 clear, negative if it could not be
+ * read).
+ *
+ * Egress Control applies only where the target is known (the path divergence).
+ * There, a set vector bit redirects the request only when Request Redirect is
+ * set; with Request Redirect clear it is an ACS Violation. A clear vector bit
+ * permits direct routing, subject to Completion Redirect.
+ */
+VISIBLE_IF_KUNIT enum pci_acs_p2pdma_state
+pci_acs_p2pdma_decision(u16 ctrl, bool has_target, int egress)
+{
+ if (!has_target || !(ctrl & PCI_ACS_EC))
+ return ctrl & (PCI_ACS_RR | PCI_ACS_CR) ?
+ PCI_ACS_P2PDMA_REDIRECT : PCI_ACS_P2PDMA_DIRECT;
+
+ if (egress < 0)
+ return PCI_ACS_P2PDMA_NOT_SUPPORTED;
+ if (egress)
+ return ctrl & PCI_ACS_RR ? PCI_ACS_P2PDMA_REDIRECT :
+ PCI_ACS_P2PDMA_NOT_SUPPORTED;
+
+ return ctrl & PCI_ACS_CR ? PCI_ACS_P2PDMA_REDIRECT :
+ PCI_ACS_P2PDMA_DIRECT;
+}
+EXPORT_SYMBOL_IF_KUNIT(pci_acs_p2pdma_decision);
static enum pci_acs_p2pdma_state
pci_acs_p2pdma_state(struct pci_dev *pdev, struct pci_dev *target)
{
- int pos, ret;
+ int egress = 0;
u16 ctrl;
- pos = pdev->acs_cap;
- if (!pos)
+ if (!pdev->acs_cap)
return PCI_ACS_P2PDMA_DIRECT;
- if (pci_read_config_word(pdev, pos + PCI_ACS_CTRL, &ctrl))
+ if (pci_read_config_word(pdev, pdev->acs_cap + PCI_ACS_CTRL, &ctrl))
return PCI_ACS_P2PDMA_NOT_SUPPORTED;
- /* EC applies only at the path divergence where the target is known. */
- if (!target || !(ctrl & PCI_ACS_EC))
- return ctrl & (PCI_ACS_RR | PCI_ACS_CR) ?
- PCI_ACS_P2PDMA_REDIRECT : PCI_ACS_P2PDMA_DIRECT;
+ /* Egress Control is evaluated only where the target is known. */
+ if (target && (ctrl & PCI_ACS_EC))
+ egress = pci_acs_egress_ctrl_set(pdev, target);
- /*
- * PCIe r7.0, sec 6.12.3, table 6-11: a set Egress Control Vector
- * bit redirects the request only when Request Redirect is set. With
- * Request Redirect clear, the request is handled as an ACS Violation.
- * A clear vector bit permits direct routing, subject to Completion
- * Redirect.
- */
- ret = pci_acs_egress_ctrl_set(pdev, target);
- if (ret < 0)
- return PCI_ACS_P2PDMA_NOT_SUPPORTED;
- if (ret)
- return ctrl & PCI_ACS_RR ? PCI_ACS_P2PDMA_REDIRECT :
- PCI_ACS_P2PDMA_NOT_SUPPORTED;
-
- return ctrl & PCI_ACS_CR ? PCI_ACS_P2PDMA_REDIRECT :
- PCI_ACS_P2PDMA_DIRECT;
+ return pci_acs_p2pdma_decision(ctrl, target, egress);
}
static void seq_buf_print_bus_devfn(struct seq_buf *buf, struct pci_dev *pdev)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index bc1c3b68c131..c9e64003f8d2 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3562,6 +3562,26 @@ static bool pci_acs_egress_vector_port(const struct pci_dev *dev)
type == PCI_EXP_TYPE_DOWNSTREAM;
}
+/**
+ * pci_acs_egress_port_valid - Is a target port within the Egress Control Vector
+ * @acs_caps: the ingress port's ACS Capability register
+ * @target_port: the target Downstream Port number
+ *
+ * The Egress Control Vector Size occupies bits 15:8 of the ACS Capability
+ * register (PCIe r7.0, sec 7.7.12). A size of 0 encodes 256 bits, so
+ * every port number is addressable.
+ *
+ * Return: %true if @target_port has a bit in the Egress Control Vector.
+ */
+VISIBLE_IF_KUNIT
+bool pci_acs_egress_port_valid(u16 acs_caps, u8 target_port)
+{
+ unsigned int vector_size = acs_caps >> 8;
+
+ return !vector_size || target_port < vector_size;
+}
+EXPORT_SYMBOL_IF_KUNIT(pci_acs_egress_port_valid);
+
/**
* pci_acs_egress_ctrl_set - Read an ACS Egress Control Vector bit
* @pdev: ingress Root or Switch Downstream Port
@@ -3572,7 +3592,6 @@ static bool pci_acs_egress_vector_port(const struct pci_dev *dev)
*/
int pci_acs_egress_ctrl_set(struct pci_dev *pdev, struct pci_dev *target)
{
- unsigned int vector_size;
u32 lnkcap, vector;
u8 target_port;
int ret;
@@ -3587,10 +3606,8 @@ int pci_acs_egress_ctrl_set(struct pci_dev *pdev, struct pci_dev *target)
return pcibios_err_to_errno(ret);
target_port = FIELD_GET(PCI_EXP_LNKCAP_PN, lnkcap);
- vector_size = pdev->acs_capabilities >> 8;
- /* An Egress Control Vector Size of 0 encodes 256 bits. */
- if (vector_size && target_port >= vector_size)
+ if (!pci_acs_egress_port_valid(pdev->acs_capabilities, target_port))
return -ERANGE;
ret = pci_read_config_dword(pdev,
@@ -3602,6 +3619,7 @@ int pci_acs_egress_ctrl_set(struct pci_dev *pdev, struct pci_dev *target)
return !!(vector & BIT(target_port % 32));
}
+EXPORT_SYMBOL_IF_KUNIT(pci_acs_egress_ctrl_set);
static bool pci_acs_flags_enabled(struct pci_dev *pdev, u16 acs_flags)
{
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 5da067f8abc3..6f40b43d3c3f 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -2,6 +2,7 @@
#ifndef DRIVERS_PCI_H
#define DRIVERS_PCI_H
+#include <kunit/visibility.h>
#include <linux/align.h>
#include <linux/bitfield.h>
#include <linux/pci.h>
@@ -1046,6 +1047,22 @@ resource_size_t pci_min_window_alignment(struct pci_bus *bus,
void pci_acs_init(struct pci_dev *dev);
void pci_enable_acs(struct pci_dev *dev);
int pci_acs_egress_ctrl_set(struct pci_dev *pdev, struct pci_dev *target);
+
+/*
+ * Peer-to-peer routing decision for an ACS-capable ingress port, per
+ * PCIe r7.0, sec 6.12.3, table 6-11.
+ */
+enum pci_acs_p2pdma_state {
+ PCI_ACS_P2PDMA_DIRECT, /* peer-to-peer permitted directly */
+ PCI_ACS_P2PDMA_REDIRECT, /* redirected upstream to host bridge */
+ PCI_ACS_P2PDMA_NOT_SUPPORTED, /* no usable peer-to-peer route */
+};
+
+#if IS_ENABLED(CONFIG_KUNIT)
+bool pci_acs_egress_port_valid(u16 acs_caps, u8 target_port);
+enum pci_acs_p2pdma_state pci_acs_p2pdma_decision(u16 ctrl, bool has_target,
+ int egress);
+#endif
#ifdef CONFIG_PCI_QUIRKS
int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags);
int pci_dev_specific_enable_acs(struct pci_dev *dev);
--
2.55.0
next prev parent reply other threads:[~2026-08-02 15:11 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-02 15:09 [PATCH 00/13] PCI/P2PDMA: Fix ACS egress control handling Leon Romanovsky
2026-08-02 15:09 ` [PATCH 01/13] PCI/P2PDMA: Safely terminate ACS redirect lists Leon Romanovsky
2026-08-04 19:49 ` Logan Gunthorpe
2026-08-02 15:09 ` [PATCH 02/13] PCI/P2PDMA: Report ACS ports when the paths share no upstream bridge Leon Romanovsky
2026-08-04 19:52 ` Logan Gunthorpe
2026-08-02 15:09 ` [PATCH 03/13] PCI/P2PDMA: Document the Address Type assumption Leon Romanovsky
2026-08-04 19:55 ` Logan Gunthorpe
2026-08-02 15:09 ` [PATCH 04/13] PCI: Account for Direct Translated P2P in ACS isolation checks Leon Romanovsky
2026-08-04 20:03 ` Logan Gunthorpe
2026-08-02 15:09 ` [PATCH 05/13] PCI: Add ACS egress control vector accessor Leon Romanovsky
2026-08-04 21:55 ` Logan Gunthorpe
2026-08-02 15:09 ` [PATCH 06/13] PCI: Account for ACS egress control in isolation checks Leon Romanovsky
2026-08-04 21:55 ` Logan Gunthorpe
2026-08-02 15:09 ` [PATCH 07/13] PCI/P2PDMA: Derive peer-to-peer routing from ACS control bits Leon Romanovsky
2026-08-04 21:55 ` Logan Gunthorpe
2026-08-04 21:58 ` Logan Gunthorpe
2026-08-02 15:09 ` [PATCH 08/13] PCI/P2PDMA: Honor ACS egress control vectors Leon Romanovsky
2026-08-04 21:56 ` Logan Gunthorpe
2026-08-02 15:09 ` [PATCH 09/13] PCI/P2PDMA: Document ACS egress control handling Leon Romanovsky
2026-08-04 22:01 ` Logan Gunthorpe
2026-08-05 9:02 ` Leon Romanovsky
2026-08-02 15:09 ` Leon Romanovsky [this message]
2026-08-04 22:07 ` [PATCH 10/13] PCI/P2PDMA: Extract pure ACS routing decision helpers Logan Gunthorpe
2026-08-05 9:06 ` Leon Romanovsky
2026-08-02 15:09 ` [PATCH 11/13] PCI/P2PDMA: Add KUnit tests for ACS routing decisions Leon Romanovsky
2026-08-04 22:37 ` Logan Gunthorpe
2026-08-02 15:09 ` [PATCH 12/13] PCI/P2PDMA: Add KUnit coverage for the ACS P2P routing walk Leon Romanovsky
2026-08-04 22:37 ` Logan Gunthorpe
2026-08-02 15:09 ` [PATCH 13/13] PCI: Add KUnit coverage for ACS isolation checks Leon Romanovsky
2026-08-04 22:38 ` Logan Gunthorpe
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=20260802-fix-p2p-acs-v1-10-a7c5eb64fff6@nvidia.com \
--to=leon@kernel.org \
--cc=alex@shazbot.org \
--cc=bhelgaas@google.com \
--cc=corbet@lwn.net \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=logang@deltatee.com \
--cc=noreply@anthropic.com \
--cc=skhan@linuxfoundation.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