From: Jon Derrick <jonathan.derrick@intel.com>
To: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Cc: <linux-pci@vger.kernel.org>, Bjorn Helgaas <helgaas@kernel.org>,
Jon Derrick <jonathan.derrick@intel.com>,
Jian-Hong Pan <jhp@endlessos.org>
Subject: [PATCH v4] PCI: vmd: Offset Client VMD MSI-X vectors
Date: Mon, 2 Nov 2020 15:22:23 -0700 [thread overview]
Message-ID: <20201102222223.92978-1-jonathan.derrick@intel.com> (raw)
Client VMD platforms have a software-triggered MSI-X vector 0 that will
not forward hardware-remapped MSI from the sub-device domain. This
causes an issue with VMD platforms that use AHCI behind VMD and have a
single MSI-X vector remapped to VMD vector 0. Add a VMD MSI-X vector
offset for these platforms.
Signed-off-by: Jon Derrick <jonathan.derrick@intel.com>
Tested-by: Jian-Hong Pan <jhp@endlessos.org>
---
v3->v4: Rebase for v5.10
drivers/pci/controller/vmd.c | 37 +++++++++++++++++++++++++-----------
1 file changed, 26 insertions(+), 11 deletions(-)
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index f375c21ceeb1..c31e4d5cb146 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -53,6 +53,12 @@ enum vmd_features {
* vendor-specific capability space
*/
VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP = (1 << 2),
+
+ /*
+ * Device may use MSI-X vector 0 for software triggering and will not
+ * be used for MSI remapping
+ */
+ VMD_FEAT_OFFSET_FIRST_VECTOR = (1 << 3),
};
/*
@@ -104,6 +110,7 @@ struct vmd_dev {
struct irq_domain *irq_domain;
struct pci_bus *bus;
u8 busn_start;
+ u8 first_vec;
};
static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus)
@@ -199,11 +206,11 @@ static irq_hw_number_t vmd_get_hwirq(struct msi_domain_info *info,
*/
static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd, struct msi_desc *desc)
{
- int i, best = 1;
unsigned long flags;
+ int i, best;
- if (vmd->msix_count == 1)
- return &vmd->irqs[0];
+ if (vmd->msix_count == 1 + vmd->first_vec)
+ return &vmd->irqs[vmd->first_vec];
/*
* White list for fast-interrupt handlers. All others will share the
@@ -213,11 +220,12 @@ static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd, struct msi_desc *d
case PCI_CLASS_STORAGE_EXPRESS:
break;
default:
- return &vmd->irqs[0];
+ return &vmd->irqs[vmd->first_vec];
}
raw_spin_lock_irqsave(&list_lock, flags);
- for (i = 1; i < vmd->msix_count; i++)
+ best = vmd->first_vec + 1;
+ for (i = best; i < vmd->msix_count; i++)
if (vmd->irqs[i].count < vmd->irqs[best].count)
best = i;
vmd->irqs[best].count++;
@@ -550,8 +558,8 @@ static int vmd_alloc_irqs(struct vmd_dev *vmd)
if (vmd->msix_count < 0)
return -ENODEV;
- vmd->msix_count = pci_alloc_irq_vectors(dev, 1, vmd->msix_count,
- PCI_IRQ_MSIX);
+ vmd->msix_count = pci_alloc_irq_vectors(dev, vmd->first_vec + 1,
+ vmd->msix_count, PCI_IRQ_MSIX);
if (vmd->msix_count < 0)
return vmd->msix_count;
@@ -719,6 +727,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features)
static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
{
+ unsigned long features = (unsigned long) id->driver_data;
struct vmd_dev *vmd;
int err;
@@ -743,13 +752,16 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32)))
return -ENODEV;
+ if (features & VMD_FEAT_OFFSET_FIRST_VECTOR)
+ vmd->first_vec = 1;
+
err = vmd_alloc_irqs(vmd);
if (err)
return err;
spin_lock_init(&vmd->cfg_lock);
pci_set_drvdata(dev, vmd);
- err = vmd_enable_domain(vmd, (unsigned long) id->driver_data);
+ err = vmd_enable_domain(vmd, features);
if (err)
return err;
@@ -818,13 +830,16 @@ static const struct pci_device_id vmd_ids[] = {
VMD_FEAT_HAS_BUS_RESTRICTIONS,},
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x467f),
.driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP |
- VMD_FEAT_HAS_BUS_RESTRICTIONS,},
+ VMD_FEAT_HAS_BUS_RESTRICTIONS |
+ VMD_FEAT_OFFSET_FIRST_VECTOR,},
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4c3d),
.driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP |
- VMD_FEAT_HAS_BUS_RESTRICTIONS,},
+ VMD_FEAT_HAS_BUS_RESTRICTIONS |
+ VMD_FEAT_OFFSET_FIRST_VECTOR,},
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_9A0B),
.driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP |
- VMD_FEAT_HAS_BUS_RESTRICTIONS,},
+ VMD_FEAT_HAS_BUS_RESTRICTIONS |
+ VMD_FEAT_OFFSET_FIRST_VECTOR,},
{0,}
};
MODULE_DEVICE_TABLE(pci, vmd_ids);
--
2.25.1
next reply other threads:[~2020-11-02 22:22 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-02 22:22 Jon Derrick [this message]
2020-11-21 0:52 ` [PATCH v4] PCI: vmd: Offset Client VMD MSI-X vectors Derrick, Jonathan
2020-11-23 9:45 ` Lorenzo Pieralisi
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=20201102222223.92978-1-jonathan.derrick@intel.com \
--to=jonathan.derrick@intel.com \
--cc=helgaas@kernel.org \
--cc=jhp@endlessos.org \
--cc=linux-pci@vger.kernel.org \
--cc=lorenzo.pieralisi@arm.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).