From: Pranjal Shrivastava <praan@google.com>
To: iommu@lists.linux.dev, linux-pci@vger.kernel.org,
linux-kernel@vger.kernel.org
Cc: Joerg Roedel <joro@8bytes.org>, Will Deacon <will@kernel.org>,
Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>,
Vasant Hegde <vasant.hegde@amd.com>,
Ankit Soni <ankit.soni@amd.com>,
Jason Gunthorpe <jgg@nvidia.com>,
Bjorn Helgaas <bhelgaas@google.com>,
Samiullah Khawaja <skhawaja@google.com>,
Pranjal Shrivastava <praan@google.com>
Subject: [PATCH v4 1/4] iommu/amd: Refactor device probe and capability initialization
Date: Thu, 10 Sep 2026 14:26:52 +0000 [thread overview]
Message-ID: <20260910142655.3281464-2-praan@google.com> (raw)
In-Reply-To: <20260910142655.3281464-1-praan@google.com>
Restructure the device probe path to improve readability and prepare for
cleaner error handling. Refactor check_device() into lookup_device to
explicitly validate and return the amd_iommu ptr & devid. Refactor
iommu_init_device() to return the allocated dev_data. Consolidate all
PCI cap inits (MSI domains, PASID, ATS) into a new helper:
iommu_init_device_caps().
Suggested-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Signed-off-by: Pranjal Shrivastava <praan@google.com>
---
drivers/iommu/amd/iommu.c | 117 +++++++++++++++++++-------------------
1 file changed, 59 insertions(+), 58 deletions(-)
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 4dc306a4b5c6..5e144a60c397 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -675,7 +675,8 @@ static void pdev_disable_caps(struct pci_dev *pdev)
* This function checks if the driver got a valid device from the caller to
* avoid dereferencing invalid pointers.
*/
-static bool check_device(struct device *dev)
+static bool lookup_device(struct device *dev,
+ struct amd_iommu **iommu_out, u16 *devid_out)
{
struct amd_iommu_pci_seg *pci_seg;
struct amd_iommu *iommu;
@@ -690,7 +691,7 @@ static bool check_device(struct device *dev)
devid = PCI_SBDF_TO_DEVID(sbdf);
iommu = rlookup_amd_iommu(dev);
- if (!iommu)
+ if (!iommu || !iommu->iommu.ops)
return false;
/* Out of our scope? */
@@ -698,47 +699,33 @@ static bool check_device(struct device *dev)
if (devid > pci_seg->last_bdf)
return false;
+ *iommu_out = iommu;
+ *devid_out = devid;
return true;
}
-static int iommu_init_device(struct amd_iommu *iommu, struct device *dev)
+static struct iommu_dev_data *iommu_init_device(struct amd_iommu *iommu,
+ struct device *dev, u16 devid)
{
struct iommu_dev_data *dev_data;
- int devid, sbdf;
-
- if (dev_iommu_priv_get(dev))
- return 0;
- sbdf = get_device_sbdf_id(dev);
- if (sbdf < 0)
- return sbdf;
-
- devid = PCI_SBDF_TO_DEVID(sbdf);
dev_data = find_dev_data(iommu, devid);
if (!dev_data)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
dev_data->dev = dev;
/*
- * The dev_iommu_priv_set() needes to be called before setup_aliases.
+ * The dev_iommu_priv_set() needs to be called before setup_aliases.
* Otherwise, subsequent call to dev_iommu_priv_get() will fail.
*/
dev_iommu_priv_set(dev, dev_data);
setup_aliases(iommu, dev);
- /*
- * By default we use passthrough mode for IOMMUv2 capable device.
- * But if amd_iommu=force_isolation is set (e.g. to debug DMA to
- * invalid address), we ignore the capability for the device so
- * it'll be forced to go into translation mode.
- */
- if ((iommu_default_passthrough() || !amd_iommu_force_isolation) &&
- dev_is_pci(dev) && amd_iommu_gt_ppr_supported()) {
- dev_data->flags = pdev_get_caps(to_pci_dev(dev));
- }
+ /* Wait for DTE updates to go through */
+ iommu_completion_wait(iommu);
- return 0;
+ return dev_data;
}
static void iommu_ignore_device(struct amd_iommu *iommu, struct device *dev)
@@ -2487,49 +2474,73 @@ static void detach_device(struct device *dev)
mutex_unlock(&dev_data->mutex);
}
+static void iommu_init_device_caps(struct iommu_dev_data *dev_data,
+ struct device *dev,
+ struct amd_iommu *iommu)
+{
+ if (FEATURE_NUM_INT_REMAP_SUP_2K(amd_iommu_efr2))
+ dev_data->max_irqs = MAX_IRQS_PER_TABLE_2K;
+ else
+ dev_data->max_irqs = MAX_IRQS_PER_TABLE_512;
+
+ amd_iommu_set_pci_msi_domain(dev, iommu);
+
+ if (!dev_is_pci(dev))
+ return;
+
+ /*
+ * By default we use passthrough mode for IOMMUv2 capable device.
+ * But if amd_iommu=force_isolation is set (e.g. to debug DMA to
+ * invalid address), we ignore the capability for the device so
+ * it'll be forced to go into translation mode.
+ */
+ if ((iommu_default_passthrough() || !amd_iommu_force_isolation) &&
+ amd_iommu_gt_ppr_supported()) {
+ dev_data->flags = pdev_get_caps(to_pci_dev(dev));
+ }
+
+ /*
+ * If IOMMU and device supports PASID then it will contain max
+ * supported PASIDs, else it will be zero.
+ */
+ if (amd_iommu_pasid_supported() &&
+ pdev_pasid_supported(dev_data)) {
+ dev_data->max_pasids = min_t(u32, iommu->iommu.max_pasids,
+ pci_max_pasids(to_pci_dev(dev)));
+ }
+
+ pci_prepare_ats(to_pci_dev(dev), PAGE_SHIFT);
+}
+
static struct iommu_device *amd_iommu_probe_device(struct device *dev)
{
struct iommu_device *iommu_dev;
struct amd_iommu *iommu;
struct iommu_dev_data *dev_data;
- int ret;
-
- if (!check_device(dev))
- return ERR_PTR(-ENODEV);
-
- iommu = rlookup_amd_iommu(dev);
- if (!iommu)
- return ERR_PTR(-ENODEV);
+ u16 devid;
- /* Not registered yet? */
- if (!iommu->iommu.ops)
+ if (!lookup_device(dev, &iommu, &devid))
return ERR_PTR(-ENODEV);
if (dev_iommu_priv_get(dev))
return &iommu->iommu;
- ret = iommu_init_device(iommu, dev);
- if (ret) {
+ dev_data = iommu_init_device(iommu, dev, devid);
+ if (IS_ERR(dev_data)) {
dev_err(dev, "Failed to initialize - trying to proceed anyway\n");
- iommu_dev = ERR_PTR(ret);
+ iommu_dev = ERR_CAST(dev_data);
iommu_ignore_device(iommu, dev);
goto out_err;
}
- amd_iommu_set_pci_msi_domain(dev, iommu);
+ iommu_init_device_caps(dev_data, dev, iommu);
iommu_dev = &iommu->iommu;
/*
- * If IOMMU and device supports PASID then it will contain max
- * supported PASIDs, else it will be zero.
+ * When DMA translation is unavailable return error so the iommu core
+ * won't attempt domain attach for this device, while preserving its
+ * rlookup entry for interrupt remapping.
*/
- dev_data = dev_iommu_priv_get(dev);
- if (amd_iommu_pasid_supported() && dev_is_pci(dev) &&
- pdev_pasid_supported(dev_data)) {
- dev_data->max_pasids = min_t(u32, iommu->iommu.max_pasids,
- pci_max_pasids(to_pci_dev(dev)));
- }
-
if (amd_iommu_pgtable == PD_MODE_NONE) {
pr_warn_once("%s: DMA translation not supported by iommu.\n",
__func__);
@@ -2537,16 +2548,6 @@ static struct iommu_device *amd_iommu_probe_device(struct device *dev)
goto out_err;
}
- iommu_completion_wait(iommu);
-
- if (FEATURE_NUM_INT_REMAP_SUP_2K(amd_iommu_efr2))
- dev_data->max_irqs = MAX_IRQS_PER_TABLE_2K;
- else
- dev_data->max_irqs = MAX_IRQS_PER_TABLE_512;
-
- if (dev_is_pci(dev))
- pci_prepare_ats(to_pci_dev(dev), PAGE_SHIFT);
-
out_err:
return iommu_dev;
}
--
2.55.0.1003.g10538fe699-goog
next prev parent reply other threads:[~2026-09-10 14:27 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-10 14:26 [PATCH v4 0/4] iommu/amd: Refactors for ATS robustness Pranjal Shrivastava
2026-09-10 14:26 ` Pranjal Shrivastava [this message]
2026-09-10 14:35 ` [PATCH v4 1/4] iommu/amd: Refactor device probe and capability initialization sashiko-bot
2026-09-10 14:26 ` [PATCH v4 2/4] iommu/amd: Remove iommu_ignore_device() Pranjal Shrivastava
2026-09-10 14:40 ` sashiko-bot
2026-09-10 14:40 ` Jason Gunthorpe
2026-09-11 4:26 ` Vasant Hegde
2026-09-10 14:26 ` [PATCH v4 3/4] iommu/amd: Fail probe on ATS configuration failure Pranjal Shrivastava
2026-09-10 14:38 ` sashiko-bot
2026-09-10 14:26 ` [PATCH v4 4/4] PCI/ATS: Mandate checking pci_ats_supported() before pci_prepare_ats() Pranjal Shrivastava
2026-09-10 14:35 ` sashiko-bot
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=20260910142655.3281464-2-praan@google.com \
--to=praan@google.com \
--cc=ankit.soni@amd.com \
--cc=bhelgaas@google.com \
--cc=iommu@lists.linux.dev \
--cc=jgg@nvidia.com \
--cc=joro@8bytes.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=skhawaja@google.com \
--cc=suravee.suthikulpanit@amd.com \
--cc=vasant.hegde@amd.com \
--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 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.