From: "Ilpo Järvinen" <ilpo.jarvinen@linux.intel.com>
To: Wei Wang <wei.w.wang@hotmail.com>
Cc: bhelgaas@google.com, jgg@nvidia.com, jic23@kernel.org,
error27@gmail.com, kwilczynski@kernel.org,
rdunlap@infradead.org, akpm@linux-foundation.org, bp@alien8.de,
alex@shazbot.org, kevin.tian@intel.com,
manivannan.sadhasivam@oss.qualcomm.com,
LKML <linux-kernel@vger.kernel.org>,
linux-pci@vger.kernel.org
Subject: Re: [PATCH v9 6/6] PCI: Add the enhanced ACS controls check to pci_acs_flags_enabled()
Date: Thu, 3 Sep 2026 14:09:16 +0300 (EEST) [thread overview]
Message-ID: <59e3d834-2628-7ef3-b07a-33ce6e7dd482@linux.intel.com> (raw)
In-Reply-To: <SI2PR01MB439314CABFD64FC0586F2FF8DCB62@SI2PR01MB4393.apcprd01.prod.exchangelabs.com>
On Thu, 3 Sep 2026, Wei Wang wrote:
> The enhanced ACS controls introduced by PCIe Gen 5 ensures better device
> isolation. On devices that support the PCI_ACS_ECAP capability, the
> controls are required to be enabled properly:
> - ACS I/O Request Blocking needs to be enabled to avoid unintended
> upstream I/O requests.
> - ACS DSP and USP Memory Target Access Control needs to be set with
> Request Redirect or Request Blocking to ensure the Downstream and
> Upstream Port memory resource ranges are not accessed by upstream
> memory requests.
> - ACS Unclaimed Request Redirect needs to be enabled to ensure accesses to
> areas that lies within a Switch's Upstream Port memory apertures but not
> within any Downstream Port memory apertures get redirected.
>
> To maintain compatibility with legacy devices that lack PCI_ACS_ECAP
> support, pci_acs_enabled() skips checking for the capability.
>
> Signed-off-by: Wei Wang <wei.w.wang@hotmail.com>
> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
> ---
> drivers/pci/pci.c | 65 +++++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 65 insertions(+)
>
> diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
> index 50a3b61f9898..b951195d5adc 100644
> --- a/drivers/pci/pci.c
> +++ b/drivers/pci/pci.c
> @@ -3648,6 +3648,57 @@ void pci_configure_ari(struct pci_dev *dev)
> }
> }
>
> +static bool pci_dev_has_memory_bars(struct pci_dev *pdev)
> +{
> + int i;
> +
> + for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
> + if (pci_resource_flags(pdev, i) & IORESOURCE_MEM)
> + return true;
> + }
> +
> + return false;
> +}
> +
> +static bool pci_acs_ecap_enabled(struct pci_dev *pdev, u16 ctrl)
> +{
> + struct pci_dev *upstream_pdev;
> +
> + /*
> + * For ACS DSP/USP Memory Target Access Control, either Request
> + * Redirect or Request Blocking must be enabled to enforce isolation.
> + * According to PCIe spec 7.0, the DSP Memory Target Access is
> + * applicable to both Root Ports and Switch Downstream Ports that have
> + * applicable Memory BAR space to protect. So if the device does not
> + * have a Memory BAR, it skips the check.
> + */
> + if (pci_dev_has_memory_bars(pdev) &&
> + FIELD_GET(PCI_ACS_DMAC_MASK, ctrl) != PCI_ACS_MAC_RB &&
> + FIELD_GET(PCI_ACS_DMAC_MASK, ctrl) != PCI_ACS_MAC_RR)
> + return false;
> +
> + if (pci_pcie_type(pdev) == PCI_EXP_TYPE_DOWNSTREAM) {
> + upstream_pdev = pci_upstream_bridge(pdev);
> +
> + /*
> + * The USP Memory Target Access is only applicable to
> + * downstream ports that have applicable Memory BAR space in
> + * the Switch Upstream Port to protect.
> + */
> + if (upstream_pdev && pci_dev_has_memory_bars(upstream_pdev) &&
> + FIELD_GET(PCI_ACS_UMAC_MASK, ctrl) != PCI_ACS_MAC_RB &&
> + FIELD_GET(PCI_ACS_UMAC_MASK, ctrl) != PCI_ACS_MAC_RR)
> + return false;
> +
> + /* PCI_ACS_URRC is applicable to Downstream Ports only. */
> + if (!(ctrl & PCI_ACS_URRC))
> + return false;
> + }
> +
> + /* PCI_ACS_IB is applicable to both Root and Downstream Ports. */
> + return !!(ctrl & PCI_ACS_IB);
When the return type is bool, !!() construct is unnecessary.
> +}
> +
> static bool pci_acs_flags_enabled(struct pci_dev *pdev, u16 acs_flags)
> {
> int pos;
> @@ -3665,6 +3716,18 @@ static bool pci_acs_flags_enabled(struct pci_dev *pdev, u16 acs_flags)
> acs_flags &= (pdev->acs_capabilities | PCI_ACS_EC);
>
> pci_read_config_word(pdev, pos + PCI_ACS_CTRL, &ctrl);
> +
> + if (acs_flags & PCI_ACS_ECAP) {
> + if (!pci_acs_ecap_enabled(pdev, ctrl))
> + return false;
> + /*
> + * The check for the required controls in PCI_ACS_ECAP has
> + * passed. Clear the ECAP flag and continue to check the
> + * basic ACS controls.
> + */
> + acs_flags &= ~PCI_ACS_ECAP;
> + }
> +
> return (ctrl & acs_flags) == acs_flags;
> }
>
> @@ -3723,6 +3786,8 @@ bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags)
> */
> case PCI_EXP_TYPE_DOWNSTREAM:
> case PCI_EXP_TYPE_ROOT_PORT:
> + /* PCI_ACS_ECAP applies to Root and Downstream Ports only */
> + acs_flags |= PCI_ACS_ECAP;
> return pci_acs_flags_enabled(pdev, acs_flags);
> /*
> * PCIe 3.0, 6.12.1.2 specifies ACS capabilities that should be
>
--
i.
next prev parent reply other threads:[~2026-09-03 11:09 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-03 3:46 [PATCH v9 0/6] PCI: Add support for ACS Enhanced Capability Wei Wang
2026-09-03 3:46 ` [PATCH v9 1/6] PCI: Validate ACS control bits against device-specific ACS capabilities Wei Wang
2026-09-03 4:01 ` sashiko-bot
2026-09-03 11:07 ` Ilpo Järvinen
2026-09-03 12:51 ` Wei Wang
2026-09-03 3:46 ` [PATCH v9 2/6] Documentation/kernel-parameters: Add multi-device config_acs example Wei Wang
2026-09-03 4:06 ` sashiko-bot
2026-09-03 3:46 ` [PATCH v9 3/6] PCI: Consolidate delimiter handling into pci_dev_str_match() Wei Wang
2026-09-03 4:15 ` sashiko-bot
2026-09-03 3:46 ` [PATCH v9 4/6] PCI: Refactor disable_acs_redir and config_acs param handling Wei Wang
2026-09-03 4:26 ` sashiko-bot
2026-09-03 12:23 ` Wei Wang
2026-09-03 3:46 ` [PATCH v9 5/6] PCI: Enable the enhanced ACS controls introduced by PCI_ACS_ECAP Wei Wang
2026-09-03 4:39 ` sashiko-bot
2026-09-03 3:46 ` [PATCH v9 6/6] PCI: Add the enhanced ACS controls check to pci_acs_flags_enabled() Wei Wang
2026-09-03 4:44 ` sashiko-bot
2026-09-03 11:09 ` Ilpo Järvinen [this message]
2026-09-03 12:46 ` Wei Wang
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=59e3d834-2628-7ef3-b07a-33ce6e7dd482@linux.intel.com \
--to=ilpo.jarvinen@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=alex@shazbot.org \
--cc=bhelgaas@google.com \
--cc=bp@alien8.de \
--cc=error27@gmail.com \
--cc=jgg@nvidia.com \
--cc=jic23@kernel.org \
--cc=kevin.tian@intel.com \
--cc=kwilczynski@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=manivannan.sadhasivam@oss.qualcomm.com \
--cc=rdunlap@infradead.org \
--cc=wei.w.wang@hotmail.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.