[PATCH v5 2/2] PCI: endpoint: pci-epf-vntb: Honor MSI-X selection
From: Koichiro Den
Date: Wed Oct 14 2026 - 21:46:58 EST
ntb_hw_epf tries MSI-X first and falls back to MSI. It reports the
result in COMMAND_CONFIGURE_DOORBELL. pci-epf-vntb ignores MSIX_ENABLE,
configures only MSI, and always raises peer interrupts with PCI_IRQ_MSI.
When MSI-X is selected, the host does not program MSI, so raising it can
issue a write to an invalid address. This was observed as IOMMU faults
on the RC, with no doorbell interrupts delivered.
Configure MSI-X when supported and use the selected type for peer
doorbells and link events. Allocate the MSI-X Table and PBA in the config
BAR and configure db_count entries. Use this EPF-owned layout even if the
EPC has fixed, hardware-owned Table/PBA regions, as pci-epf-test and
nvmet-pci-epf already do.
Fixes: e35f56bb0330 ("PCI: endpoint: Support NTB transfer between RC and EP")
Signed-off-by: Koichiro Den <den@xxxxxxxxxxxxx>
---
Changes since v4:
- Split out the local epf cleanup into a prep patch. (Frank)
- Keep the MSI labels in the interrupt-numbering comment. (Frank)
- Rebase on the link-state fix and honor MSI-X for link events too.
- Link to v4: https://lore.kernel.org/r/20261014053256.2378817-1-den@xxxxxxxxxxxxx/
drivers/pci/endpoint/functions/pci-epf-vntb.c | 47 ++++++++++++++++---
1 file changed, 41 insertions(+), 6 deletions(-)
diff --git a/drivers/pci/endpoint/functions/pci-epf-vntb.c b/drivers/pci/endpoint/functions/pci-epf-vntb.c
index d74402ea10bf..f4eede5330c6 100644
--- a/drivers/pci/endpoint/functions/pci-epf-vntb.c
+++ b/drivers/pci/endpoint/functions/pci-epf-vntb.c
@@ -152,6 +152,7 @@ struct epf_ntb {
struct mutex link_lock;
bool host_linkup;
bool vhost_linkup;
+ bool peer_msix;
/*
* True when doorbells are interrupt-driven (MSI or embedded), false
@@ -159,6 +160,7 @@ struct epf_ntb {
*/
bool msi_doorbell;
u32 spad_size;
+ u32 msix_table_offset;
enum pci_barno epf_ntb_bar[VNTB_BAR_NUM];
@@ -202,13 +204,16 @@ static void epf_ntb_update_link(struct epf_ntb *ntb)
static int epf_ntb_notify_link(struct ntb_dev *ndev)
{
- struct pci_epf *epf = ntb_ndev(ndev)->epf;
+ struct epf_ntb *ntb = ntb_ndev(ndev);
+ struct pci_epf *epf = ntb->epf;
+ unsigned int irq_type;
int ret;
ntb_link_event(ndev);
+ irq_type = ntb->peer_msix ? PCI_IRQ_MSIX : PCI_IRQ_MSI;
ret = pci_epc_raise_irq(epf->epc, epf->func_no, epf->vfunc_no,
- PCI_IRQ_MSI, EPF_IRQ_LINK + 1);
+ irq_type, EPF_IRQ_LINK + 1);
if (ret)
dev_err(&epf->dev, "Failed to raise link event IRQ: %d\n", ret);
@@ -310,6 +315,7 @@ static void epf_ntb_teardown_mw(struct epf_ntb *ntb, u32 mw)
*/
static void epf_ntb_cmd_handler(struct work_struct *work)
{
+ const struct pci_epc_features *epc_features;
struct epf_ntb_ctrl *ctrl;
u32 command, argument;
struct epf_ntb *ntb;
@@ -342,6 +348,15 @@ static void epf_ntb_cmd_handler(struct work_struct *work)
switch (command) {
case COMMAND_CONFIGURE_DOORBELL:
+ epc_features = pci_epc_get_features(ntb->epf->epc,
+ ntb->epf->func_no,
+ ntb->epf->vfunc_no);
+ if (((argument & MSIX_ENABLE) && !epc_features->msix_capable) ||
+ (!(argument & MSIX_ENABLE) && !epc_features->msi_capable)) {
+ ctrl->command_status = COMMAND_STATUS_ERROR;
+ break;
+ }
+ ntb->peer_msix = argument & MSIX_ENABLE;
ctrl->command_status = COMMAND_STATUS_OK;
break;
case COMMAND_TEARDOWN_DOORBELL:
@@ -483,8 +498,9 @@ static void epf_ntb_config_spad_bar_free(struct epf_ntb *ntb)
* @ntb: NTB device that facilitates communication between HOST and VHOST
*
* Allocate the Local Memory mentioned in the above diagram. The size of
- * CONFIG REGION is sizeof(struct epf_ntb_ctrl) and size of SCRATCHPAD REGION
- * is obtained from "spad-count" configfs entry.
+ * CONFIG REGION is sizeof(struct epf_ntb_ctrl), plus space for the MSI-X
+ * Table and PBA if supported. The size of SCRATCHPAD REGION is obtained
+ * from "spad-count" configfs entry.
*
* Returns: Zero for success, or an error code in case of failure
*/
@@ -505,6 +521,12 @@ static int epf_ntb_config_spad_bar_alloc(struct epf_ntb *ntb)
spad_count = ntb->spad_count;
ctrl_size = ALIGN(sizeof(struct epf_ntb_ctrl), sizeof(u32));
+ if (epc_features->msix_capable) {
+ ntb->msix_table_offset = ALIGN(ctrl_size, 8);
+ ctrl_size = ntb->msix_table_offset +
+ ntb->db_count * PCI_MSIX_ENTRY_SIZE +
+ BITS_TO_U64(ntb->db_count) * sizeof(u64);
+ }
spad_size = 2 * spad_count * sizeof(u32);
base = pci_epf_alloc_space(epf, ctrl_size + spad_size,
@@ -573,6 +595,17 @@ static int epf_ntb_configure_interrupt(struct epf_ntb *ntb)
}
}
+ if (epc_features->msix_capable) {
+ ret = pci_epc_set_msix(epf->epc, epf->func_no, epf->vfunc_no,
+ ntb->db_count,
+ ntb->epf_ntb_bar[BAR_CONFIG],
+ ntb->msix_table_offset);
+ if (ret) {
+ dev_err(dev, "MSI-X configuration failed\n");
+ return ret;
+ }
+ }
+
return 0;
}
@@ -1577,6 +1610,7 @@ static void vntb_epf_peer_db_work(struct work_struct *work)
struct epf_ntb *ntb = container_of(work, struct epf_ntb, peer_db_work);
struct pci_epf *epf = ntb->epf;
unsigned int budget = VNTB_PEER_DB_WORK_BUDGET;
+ unsigned int irq_type;
u8 func_no, vfunc_no;
unsigned int db_bit;
u32 interrupt_num;
@@ -1588,6 +1622,7 @@ static void vntb_epf_peer_db_work(struct work_struct *work)
func_no = epf->func_no;
vfunc_no = epf->vfunc_no;
+ irq_type = ntb->peer_msix ? PCI_IRQ_MSIX : PCI_IRQ_MSI;
/*
* Drain doorbells from peer_db_pending in snapshots (atomic64_xchg()).
@@ -1601,7 +1636,7 @@ static void vntb_epf_peer_db_work(struct work_struct *work)
while (db_bits) {
/*
- * pci_epc_raise_irq() for MSI expects a 1-based
+ * pci_epc_raise_irq() for MSI/MSI-X expects a 1-based
* interrupt number. The first usable doorbell starts
* at EPF_IRQ_DB_START in the legacy slot layout.
*
@@ -1621,7 +1656,7 @@ static void vntb_epf_peer_db_work(struct work_struct *work)
db_bits &= ~BIT_ULL(db_bit);
ret = pci_epc_raise_irq(epf->epc, func_no, vfunc_no,
- PCI_IRQ_MSI, interrupt_num);
+ irq_type, interrupt_num);
if (ret)
dev_err(&epf->dev,
"Failed to raise IRQ for interrupt_num %u: %d\n",
--
2.54.0